commit 1db71364d82aa6a324a714960e19433df3aa0df0 Author: ModelHub XC Date: Fri May 22 20:13:12 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mlfoundations-dev/oh_v1.3_gpt_4o_mini Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b491dd3 --- /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 + +training_args.bin filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json 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..46da4cd --- /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_v1.3_gpt_4o_mini + results: [] +--- + + + +# oh_v1.3_gpt_4o_mini + +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_v1.3_gpt_4o_mini dataset. +It achieves the following results on the evaluation set: +- Loss: 0.7332 + +## 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: 16 +- gradient_accumulation_steps: 4 +- total_train_batch_size: 512 +- total_eval_batch_size: 128 +- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: constant +- num_epochs: 3.0 + +### Training results + +| Training Loss | Epoch | Step | Validation Loss | +|:-------------:|:------:|:----:|:---------------:| +| 0.7434 | 0.9973 | 272 | 0.7440 | +| 0.6845 | 1.9963 | 544 | 0.7305 | +| 0.6373 | 2.9954 | 816 | 0.7332 | + + +### 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..f506dce --- /dev/null +++ b/all_results.json @@ -0,0 +1,12 @@ +{ + "epoch": 2.9954170485792853, + "eval_loss": 0.7332214117050171, + "eval_runtime": 93.8096, + "eval_samples_per_second": 78.35, + "eval_steps_per_second": 0.618, + "total_flos": 1366411632967680.0, + "train_loss": 0.7035682309491962, + "train_runtime": 14220.3782, + "train_samples_per_second": 29.46, + "train_steps_per_second": 0.057 +} \ 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..9581a05 --- /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_v1.3_gpt_4o_mini +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: '4' +gradient_checkpointing: 'True' +hub_model_id: mlfoundations-dev/oh_v1.3_gpt_4o_mini +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_v1.3_gpt_4o_mini +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..d04003b --- /dev/null +++ b/eval_results.json @@ -0,0 +1,7 @@ +{ + "epoch": 2.9954170485792853, + "eval_loss": 0.7332214117050171, + "eval_runtime": 93.8096, + "eval_samples_per_second": 78.35, + "eval_steps_per_second": 0.618 +} \ 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..1f6d664 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad255bcedbb511599e1bedcd8e8cf9305c27d989004329da6b8bd3aed7b4798c +size 4976698672 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..2f972ae --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dc401136cf31c6ddcf5d956214a10e191aa405943de5d19951137c896f0cb36 +size 4999802720 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..4c0330a --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f60161d27bb92605fc5a38fd8e339f080a37c4089e970a937871f8080e728e9 +size 4915916176 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..7e2a12e --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f67b28bcfcc5ca34f746f705c84dd049735f917a0b64e79b8a9e9ec9041f33f +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..fcfafbb --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 2.9954170485792853, + "total_flos": 1366411632967680.0, + "train_loss": 0.7035682309491962, + "train_runtime": 14220.3782, + "train_samples_per_second": 29.46, + "train_steps_per_second": 0.057 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..dbba6e5 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,85 @@ +{"current_steps": 10, "total_steps": 816, "loss": 1.033, "lr": 5e-06, "epoch": 0.03666361136571952, "percentage": 1.23, "elapsed_time": "0:02:55", "remaining_time": "3:55:13"} +{"current_steps": 20, "total_steps": 816, "loss": 0.9011, "lr": 5e-06, "epoch": 0.07332722273143905, "percentage": 2.45, "elapsed_time": "0:05:44", "remaining_time": "3:48:40"} +{"current_steps": 30, "total_steps": 816, "loss": 0.8764, "lr": 5e-06, "epoch": 0.10999083409715857, "percentage": 3.68, "elapsed_time": "0:08:33", "remaining_time": "3:44:10"} +{"current_steps": 40, "total_steps": 816, "loss": 0.8446, "lr": 5e-06, "epoch": 0.1466544454628781, "percentage": 4.9, "elapsed_time": "0:11:23", "remaining_time": "3:40:58"} +{"current_steps": 50, "total_steps": 816, "loss": 0.8204, "lr": 5e-06, "epoch": 0.18331805682859761, "percentage": 6.13, "elapsed_time": "0:14:12", "remaining_time": "3:37:42"} +{"current_steps": 60, "total_steps": 816, "loss": 0.8104, "lr": 5e-06, "epoch": 0.21998166819431714, "percentage": 7.35, "elapsed_time": "0:17:00", "remaining_time": "3:34:21"} +{"current_steps": 70, "total_steps": 816, "loss": 0.7968, "lr": 5e-06, "epoch": 0.2566452795600367, "percentage": 8.58, "elapsed_time": "0:19:49", "remaining_time": "3:31:11"} +{"current_steps": 80, "total_steps": 816, "loss": 0.7836, "lr": 5e-06, "epoch": 0.2933088909257562, "percentage": 9.8, "elapsed_time": "0:22:36", "remaining_time": "3:28:02"} +{"current_steps": 90, "total_steps": 816, "loss": 0.7781, "lr": 5e-06, "epoch": 0.32997250229147573, "percentage": 11.03, "elapsed_time": "0:25:24", "remaining_time": "3:24:59"} +{"current_steps": 100, "total_steps": 816, "loss": 0.7732, "lr": 5e-06, "epoch": 0.36663611365719523, "percentage": 12.25, "elapsed_time": "0:28:14", "remaining_time": "3:22:10"} +{"current_steps": 110, "total_steps": 816, "loss": 0.7711, "lr": 5e-06, "epoch": 0.4032997250229148, "percentage": 13.48, "elapsed_time": "0:31:01", "remaining_time": "3:19:05"} +{"current_steps": 120, "total_steps": 816, "loss": 0.7637, "lr": 5e-06, "epoch": 0.4399633363886343, "percentage": 14.71, "elapsed_time": "0:33:47", "remaining_time": "3:16:00"} +{"current_steps": 130, "total_steps": 816, "loss": 0.7617, "lr": 5e-06, "epoch": 0.4766269477543538, "percentage": 15.93, "elapsed_time": "0:36:34", "remaining_time": "3:12:59"} +{"current_steps": 140, "total_steps": 816, "loss": 0.7562, "lr": 5e-06, "epoch": 0.5132905591200734, "percentage": 17.16, "elapsed_time": "0:39:20", "remaining_time": "3:09:59"} +{"current_steps": 150, "total_steps": 816, "loss": 0.7601, "lr": 5e-06, "epoch": 0.5499541704857929, "percentage": 18.38, "elapsed_time": "0:42:09", "remaining_time": "3:07:09"} +{"current_steps": 160, "total_steps": 816, "loss": 0.7561, "lr": 5e-06, "epoch": 0.5866177818515124, "percentage": 19.61, "elapsed_time": "0:44:57", "remaining_time": "3:04:19"} +{"current_steps": 170, "total_steps": 816, "loss": 0.7549, "lr": 5e-06, "epoch": 0.6232813932172319, "percentage": 20.83, "elapsed_time": "0:47:46", "remaining_time": "3:01:31"} +{"current_steps": 180, "total_steps": 816, "loss": 0.7525, "lr": 5e-06, "epoch": 0.6599450045829515, "percentage": 22.06, "elapsed_time": "0:50:35", "remaining_time": "2:58:45"} +{"current_steps": 190, "total_steps": 816, "loss": 0.7507, "lr": 5e-06, "epoch": 0.696608615948671, "percentage": 23.28, "elapsed_time": "0:53:25", "remaining_time": "2:56:00"} +{"current_steps": 200, "total_steps": 816, "loss": 0.7492, "lr": 5e-06, "epoch": 0.7332722273143905, "percentage": 24.51, "elapsed_time": "0:56:14", "remaining_time": "2:53:13"} +{"current_steps": 210, "total_steps": 816, "loss": 0.7446, "lr": 5e-06, "epoch": 0.76993583868011, "percentage": 25.74, "elapsed_time": "0:59:01", "remaining_time": "2:50:20"} +{"current_steps": 220, "total_steps": 816, "loss": 0.7512, "lr": 5e-06, "epoch": 0.8065994500458296, "percentage": 26.96, "elapsed_time": "1:01:50", "remaining_time": "2:47:33"} +{"current_steps": 230, "total_steps": 816, "loss": 0.744, "lr": 5e-06, "epoch": 0.843263061411549, "percentage": 28.19, "elapsed_time": "1:04:39", "remaining_time": "2:44:43"} +{"current_steps": 240, "total_steps": 816, "loss": 0.7431, "lr": 5e-06, "epoch": 0.8799266727772685, "percentage": 29.41, "elapsed_time": "1:07:26", "remaining_time": "2:41:51"} +{"current_steps": 250, "total_steps": 816, "loss": 0.7399, "lr": 5e-06, "epoch": 0.916590284142988, "percentage": 30.64, "elapsed_time": "1:10:15", "remaining_time": "2:39:03"} +{"current_steps": 260, "total_steps": 816, "loss": 0.7457, "lr": 5e-06, "epoch": 0.9532538955087076, "percentage": 31.86, "elapsed_time": "1:13:02", "remaining_time": "2:36:12"} +{"current_steps": 270, "total_steps": 816, "loss": 0.7434, "lr": 5e-06, "epoch": 0.9899175068744271, "percentage": 33.09, "elapsed_time": "1:15:50", "remaining_time": "2:33:21"} +{"current_steps": 272, "total_steps": 816, "eval_loss": 0.743977963924408, "epoch": 0.997250229147571, "percentage": 33.33, "elapsed_time": "1:18:04", "remaining_time": "2:36:08"} +{"current_steps": 280, "total_steps": 816, "loss": 0.7593, "lr": 5e-06, "epoch": 1.0284142988084326, "percentage": 34.31, "elapsed_time": "1:21:12", "remaining_time": "2:35:26"} +{"current_steps": 290, "total_steps": 816, "loss": 0.6885, "lr": 5e-06, "epoch": 1.065077910174152, "percentage": 35.54, "elapsed_time": "1:23:58", "remaining_time": "2:32:18"} +{"current_steps": 300, "total_steps": 816, "loss": 0.6893, "lr": 5e-06, "epoch": 1.1017415215398716, "percentage": 36.76, "elapsed_time": "1:26:45", "remaining_time": "2:29:13"} +{"current_steps": 310, "total_steps": 816, "loss": 0.6868, "lr": 5e-06, "epoch": 1.138405132905591, "percentage": 37.99, "elapsed_time": "1:29:33", "remaining_time": "2:26:10"} +{"current_steps": 320, "total_steps": 816, "loss": 0.6885, "lr": 5e-06, "epoch": 1.1750687442713108, "percentage": 39.22, "elapsed_time": "1:32:21", "remaining_time": "2:23:09"} +{"current_steps": 330, "total_steps": 816, "loss": 0.6871, "lr": 5e-06, "epoch": 1.2117323556370303, "percentage": 40.44, "elapsed_time": "1:35:09", "remaining_time": "2:20:08"} +{"current_steps": 340, "total_steps": 816, "loss": 0.6935, "lr": 5e-06, "epoch": 1.2483959670027498, "percentage": 41.67, "elapsed_time": "1:37:58", "remaining_time": "2:17:09"} +{"current_steps": 350, "total_steps": 816, "loss": 0.6943, "lr": 5e-06, "epoch": 1.2850595783684693, "percentage": 42.89, "elapsed_time": "1:40:44", "remaining_time": "2:14:08"} +{"current_steps": 360, "total_steps": 816, "loss": 0.6938, "lr": 5e-06, "epoch": 1.3217231897341888, "percentage": 44.12, "elapsed_time": "1:43:31", "remaining_time": "2:11:07"} +{"current_steps": 370, "total_steps": 816, "loss": 0.6856, "lr": 5e-06, "epoch": 1.3583868010999083, "percentage": 45.34, "elapsed_time": "1:46:16", "remaining_time": "2:08:05"} +{"current_steps": 380, "total_steps": 816, "loss": 0.69, "lr": 5e-06, "epoch": 1.3950504124656278, "percentage": 46.57, "elapsed_time": "1:49:04", "remaining_time": "2:05:08"} +{"current_steps": 390, "total_steps": 816, "loss": 0.682, "lr": 5e-06, "epoch": 1.4317140238313475, "percentage": 47.79, "elapsed_time": "1:51:52", "remaining_time": "2:02:11"} +{"current_steps": 400, "total_steps": 816, "loss": 0.6917, "lr": 5e-06, "epoch": 1.468377635197067, "percentage": 49.02, "elapsed_time": "1:54:39", "remaining_time": "1:59:14"} +{"current_steps": 410, "total_steps": 816, "loss": 0.6871, "lr": 5e-06, "epoch": 1.5050412465627865, "percentage": 50.25, "elapsed_time": "1:57:26", "remaining_time": "1:56:17"} +{"current_steps": 420, "total_steps": 816, "loss": 0.6829, "lr": 5e-06, "epoch": 1.541704857928506, "percentage": 51.47, "elapsed_time": "2:00:12", "remaining_time": "1:53:20"} +{"current_steps": 430, "total_steps": 816, "loss": 0.6824, "lr": 5e-06, "epoch": 1.5783684692942255, "percentage": 52.7, "elapsed_time": "2:03:00", "remaining_time": "1:50:24"} +{"current_steps": 440, "total_steps": 816, "loss": 0.6822, "lr": 5e-06, "epoch": 1.615032080659945, "percentage": 53.92, "elapsed_time": "2:05:47", "remaining_time": "1:47:30"} +{"current_steps": 450, "total_steps": 816, "loss": 0.6879, "lr": 5e-06, "epoch": 1.6516956920256645, "percentage": 55.15, "elapsed_time": "2:08:35", "remaining_time": "1:44:35"} +{"current_steps": 460, "total_steps": 816, "loss": 0.6804, "lr": 5e-06, "epoch": 1.6883593033913842, "percentage": 56.37, "elapsed_time": "2:11:22", "remaining_time": "1:41:40"} +{"current_steps": 470, "total_steps": 816, "loss": 0.686, "lr": 5e-06, "epoch": 1.7250229147571035, "percentage": 57.6, "elapsed_time": "2:14:08", "remaining_time": "1:38:45"} +{"current_steps": 480, "total_steps": 816, "loss": 0.6856, "lr": 5e-06, "epoch": 1.7616865261228232, "percentage": 58.82, "elapsed_time": "2:16:55", "remaining_time": "1:35:51"} +{"current_steps": 490, "total_steps": 816, "loss": 0.6814, "lr": 5e-06, "epoch": 1.7983501374885427, "percentage": 60.05, "elapsed_time": "2:19:42", "remaining_time": "1:32:57"} +{"current_steps": 500, "total_steps": 816, "loss": 0.6855, "lr": 5e-06, "epoch": 1.8350137488542622, "percentage": 61.27, "elapsed_time": "2:22:31", "remaining_time": "1:30:04"} +{"current_steps": 510, "total_steps": 816, "loss": 0.6875, "lr": 5e-06, "epoch": 1.8716773602199817, "percentage": 62.5, "elapsed_time": "2:25:17", "remaining_time": "1:27:10"} +{"current_steps": 520, "total_steps": 816, "loss": 0.6856, "lr": 5e-06, "epoch": 1.9083409715857012, "percentage": 63.73, "elapsed_time": "2:28:05", "remaining_time": "1:24:18"} +{"current_steps": 530, "total_steps": 816, "loss": 0.6841, "lr": 5e-06, "epoch": 1.9450045829514209, "percentage": 64.95, "elapsed_time": "2:30:54", "remaining_time": "1:21:26"} +{"current_steps": 540, "total_steps": 816, "loss": 0.6845, "lr": 5e-06, "epoch": 1.9816681943171401, "percentage": 66.18, "elapsed_time": "2:33:43", "remaining_time": "1:18:34"} +{"current_steps": 544, "total_steps": 816, "eval_loss": 0.7305116057395935, "epoch": 1.996333638863428, "percentage": 66.67, "elapsed_time": "2:36:33", "remaining_time": "1:18:16"} +{"current_steps": 550, "total_steps": 816, "loss": 0.707, "lr": 5e-06, "epoch": 2.020164986251146, "percentage": 67.4, "elapsed_time": "2:39:11", "remaining_time": "1:16:59"} +{"current_steps": 560, "total_steps": 816, "loss": 0.6313, "lr": 5e-06, "epoch": 2.056828597616865, "percentage": 68.63, "elapsed_time": "2:41:58", "remaining_time": "1:14:02"} +{"current_steps": 570, "total_steps": 816, "loss": 0.6281, "lr": 5e-06, "epoch": 2.093492208982585, "percentage": 69.85, "elapsed_time": "2:44:46", "remaining_time": "1:11:06"} +{"current_steps": 580, "total_steps": 816, "loss": 0.631, "lr": 5e-06, "epoch": 2.130155820348304, "percentage": 71.08, "elapsed_time": "2:47:34", "remaining_time": "1:08:11"} +{"current_steps": 590, "total_steps": 816, "loss": 0.6351, "lr": 5e-06, "epoch": 2.166819431714024, "percentage": 72.3, "elapsed_time": "2:50:21", "remaining_time": "1:05:15"} +{"current_steps": 600, "total_steps": 816, "loss": 0.634, "lr": 5e-06, "epoch": 2.203483043079743, "percentage": 73.53, "elapsed_time": "2:53:07", "remaining_time": "1:02:19"} +{"current_steps": 610, "total_steps": 816, "loss": 0.6327, "lr": 5e-06, "epoch": 2.240146654445463, "percentage": 74.75, "elapsed_time": "2:55:53", "remaining_time": "0:59:24"} +{"current_steps": 620, "total_steps": 816, "loss": 0.6339, "lr": 5e-06, "epoch": 2.276810265811182, "percentage": 75.98, "elapsed_time": "2:58:40", "remaining_time": "0:56:28"} +{"current_steps": 630, "total_steps": 816, "loss": 0.636, "lr": 5e-06, "epoch": 2.313473877176902, "percentage": 77.21, "elapsed_time": "3:01:26", "remaining_time": "0:53:34"} +{"current_steps": 640, "total_steps": 816, "loss": 0.6342, "lr": 5e-06, "epoch": 2.3501374885426216, "percentage": 78.43, "elapsed_time": "3:04:13", "remaining_time": "0:50:39"} +{"current_steps": 650, "total_steps": 816, "loss": 0.637, "lr": 5e-06, "epoch": 2.386801099908341, "percentage": 79.66, "elapsed_time": "3:06:59", "remaining_time": "0:47:45"} +{"current_steps": 660, "total_steps": 816, "loss": 0.63, "lr": 5e-06, "epoch": 2.4234647112740606, "percentage": 80.88, "elapsed_time": "3:09:44", "remaining_time": "0:44:50"} +{"current_steps": 670, "total_steps": 816, "loss": 0.6288, "lr": 5e-06, "epoch": 2.46012832263978, "percentage": 82.11, "elapsed_time": "3:12:30", "remaining_time": "0:41:57"} +{"current_steps": 680, "total_steps": 816, "loss": 0.6381, "lr": 5e-06, "epoch": 2.4967919340054996, "percentage": 83.33, "elapsed_time": "3:15:19", "remaining_time": "0:39:03"} +{"current_steps": 690, "total_steps": 816, "loss": 0.6332, "lr": 5e-06, "epoch": 2.5334555453712193, "percentage": 84.56, "elapsed_time": "3:18:05", "remaining_time": "0:36:10"} +{"current_steps": 700, "total_steps": 816, "loss": 0.6351, "lr": 5e-06, "epoch": 2.5701191567369386, "percentage": 85.78, "elapsed_time": "3:20:53", "remaining_time": "0:33:17"} +{"current_steps": 710, "total_steps": 816, "loss": 0.6363, "lr": 5e-06, "epoch": 2.606782768102658, "percentage": 87.01, "elapsed_time": "3:23:40", "remaining_time": "0:30:24"} +{"current_steps": 720, "total_steps": 816, "loss": 0.6355, "lr": 5e-06, "epoch": 2.6434463794683776, "percentage": 88.24, "elapsed_time": "3:26:27", "remaining_time": "0:27:31"} +{"current_steps": 730, "total_steps": 816, "loss": 0.6351, "lr": 5e-06, "epoch": 2.6801099908340973, "percentage": 89.46, "elapsed_time": "3:29:12", "remaining_time": "0:24:38"} +{"current_steps": 740, "total_steps": 816, "loss": 0.638, "lr": 5e-06, "epoch": 2.7167736021998166, "percentage": 90.69, "elapsed_time": "3:31:58", "remaining_time": "0:21:46"} +{"current_steps": 750, "total_steps": 816, "loss": 0.6388, "lr": 5e-06, "epoch": 2.7534372135655363, "percentage": 91.91, "elapsed_time": "3:34:44", "remaining_time": "0:18:53"} +{"current_steps": 760, "total_steps": 816, "loss": 0.6364, "lr": 5e-06, "epoch": 2.7901008249312556, "percentage": 93.14, "elapsed_time": "3:37:32", "remaining_time": "0:16:01"} +{"current_steps": 770, "total_steps": 816, "loss": 0.6421, "lr": 5e-06, "epoch": 2.8267644362969753, "percentage": 94.36, "elapsed_time": "3:40:18", "remaining_time": "0:13:09"} +{"current_steps": 780, "total_steps": 816, "loss": 0.6379, "lr": 5e-06, "epoch": 2.863428047662695, "percentage": 95.59, "elapsed_time": "3:43:05", "remaining_time": "0:10:17"} +{"current_steps": 790, "total_steps": 816, "loss": 0.6414, "lr": 5e-06, "epoch": 2.9000916590284143, "percentage": 96.81, "elapsed_time": "3:45:51", "remaining_time": "0:07:25"} +{"current_steps": 800, "total_steps": 816, "loss": 0.6361, "lr": 5e-06, "epoch": 2.936755270394134, "percentage": 98.04, "elapsed_time": "3:48:38", "remaining_time": "0:04:34"} +{"current_steps": 810, "total_steps": 816, "loss": 0.6373, "lr": 5e-06, "epoch": 2.9734188817598532, "percentage": 99.26, "elapsed_time": "3:51:25", "remaining_time": "0:01:42"} +{"current_steps": 816, "total_steps": 816, "eval_loss": 0.7332214117050171, "epoch": 2.9954170485792853, "percentage": 100.0, "elapsed_time": "3:55:44", "remaining_time": "0:00:00"} +{"current_steps": 816, "total_steps": 816, "epoch": 2.9954170485792853, "percentage": 100.0, "elapsed_time": "3:56:59", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..1f6d305 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,633 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.9954170485792853, + "eval_steps": 500, + "global_step": 816, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.03666361136571952, + "grad_norm": 10.920966734668648, + "learning_rate": 5e-06, + "loss": 1.033, + "step": 10 + }, + { + "epoch": 0.07332722273143905, + "grad_norm": 2.445980198452297, + "learning_rate": 5e-06, + "loss": 0.9011, + "step": 20 + }, + { + "epoch": 0.10999083409715857, + "grad_norm": 1.5424232386159482, + "learning_rate": 5e-06, + "loss": 0.8764, + "step": 30 + }, + { + "epoch": 0.1466544454628781, + "grad_norm": 1.1797649838046136, + "learning_rate": 5e-06, + "loss": 0.8446, + "step": 40 + }, + { + "epoch": 0.18331805682859761, + "grad_norm": 1.0295589020655365, + "learning_rate": 5e-06, + "loss": 0.8204, + "step": 50 + }, + { + "epoch": 0.21998166819431714, + "grad_norm": 1.2160434357225554, + "learning_rate": 5e-06, + "loss": 0.8104, + "step": 60 + }, + { + "epoch": 0.2566452795600367, + "grad_norm": 1.2135493715768004, + "learning_rate": 5e-06, + "loss": 0.7968, + "step": 70 + }, + { + "epoch": 0.2933088909257562, + "grad_norm": 0.7594488712178804, + "learning_rate": 5e-06, + "loss": 0.7836, + "step": 80 + }, + { + "epoch": 0.32997250229147573, + "grad_norm": 0.8913076302913621, + "learning_rate": 5e-06, + "loss": 0.7781, + "step": 90 + }, + { + "epoch": 0.36663611365719523, + "grad_norm": 1.126183659145103, + "learning_rate": 5e-06, + "loss": 0.7732, + "step": 100 + }, + { + "epoch": 0.4032997250229148, + "grad_norm": 0.7476760341544976, + "learning_rate": 5e-06, + "loss": 0.7711, + "step": 110 + }, + { + "epoch": 0.4399633363886343, + "grad_norm": 0.828783632948725, + "learning_rate": 5e-06, + "loss": 0.7637, + "step": 120 + }, + { + "epoch": 0.4766269477543538, + "grad_norm": 0.7005369874659794, + "learning_rate": 5e-06, + "loss": 0.7617, + "step": 130 + }, + { + "epoch": 0.5132905591200734, + "grad_norm": 0.6781356553576761, + "learning_rate": 5e-06, + "loss": 0.7562, + "step": 140 + }, + { + "epoch": 0.5499541704857929, + "grad_norm": 0.6643060954517749, + "learning_rate": 5e-06, + "loss": 0.7601, + "step": 150 + }, + { + "epoch": 0.5866177818515124, + "grad_norm": 0.654862572470797, + "learning_rate": 5e-06, + "loss": 0.7561, + "step": 160 + }, + { + "epoch": 0.6232813932172319, + "grad_norm": 0.7126834121476828, + "learning_rate": 5e-06, + "loss": 0.7549, + "step": 170 + }, + { + "epoch": 0.6599450045829515, + "grad_norm": 0.5845932549413623, + "learning_rate": 5e-06, + "loss": 0.7525, + "step": 180 + }, + { + "epoch": 0.696608615948671, + "grad_norm": 0.583642927450063, + "learning_rate": 5e-06, + "loss": 0.7507, + "step": 190 + }, + { + "epoch": 0.7332722273143905, + "grad_norm": 0.5759630428428489, + "learning_rate": 5e-06, + "loss": 0.7492, + "step": 200 + }, + { + "epoch": 0.76993583868011, + "grad_norm": 0.597809207757354, + "learning_rate": 5e-06, + "loss": 0.7446, + "step": 210 + }, + { + "epoch": 0.8065994500458296, + "grad_norm": 0.6520665055230834, + "learning_rate": 5e-06, + "loss": 0.7512, + "step": 220 + }, + { + "epoch": 0.843263061411549, + "grad_norm": 0.6521761800994458, + "learning_rate": 5e-06, + "loss": 0.744, + "step": 230 + }, + { + "epoch": 0.8799266727772685, + "grad_norm": 0.6083361886529014, + "learning_rate": 5e-06, + "loss": 0.7431, + "step": 240 + }, + { + "epoch": 0.916590284142988, + "grad_norm": 0.8966782629847545, + "learning_rate": 5e-06, + "loss": 0.7399, + "step": 250 + }, + { + "epoch": 0.9532538955087076, + "grad_norm": 0.6584181334872885, + "learning_rate": 5e-06, + "loss": 0.7457, + "step": 260 + }, + { + "epoch": 0.9899175068744271, + "grad_norm": 0.5614900416740534, + "learning_rate": 5e-06, + "loss": 0.7434, + "step": 270 + }, + { + "epoch": 0.997250229147571, + "eval_loss": 0.743977963924408, + "eval_runtime": 96.6447, + "eval_samples_per_second": 76.052, + "eval_steps_per_second": 0.6, + "step": 272 + }, + { + "epoch": 1.0284142988084326, + "grad_norm": 0.6377526876986616, + "learning_rate": 5e-06, + "loss": 0.7593, + "step": 280 + }, + { + "epoch": 1.065077910174152, + "grad_norm": 0.8312923337011684, + "learning_rate": 5e-06, + "loss": 0.6885, + "step": 290 + }, + { + "epoch": 1.1017415215398716, + "grad_norm": 0.6499984381614756, + "learning_rate": 5e-06, + "loss": 0.6893, + "step": 300 + }, + { + "epoch": 1.138405132905591, + "grad_norm": 0.658519279927457, + "learning_rate": 5e-06, + "loss": 0.6868, + "step": 310 + }, + { + "epoch": 1.1750687442713108, + "grad_norm": 0.6307182099292118, + "learning_rate": 5e-06, + "loss": 0.6885, + "step": 320 + }, + { + "epoch": 1.2117323556370303, + "grad_norm": 0.6191143311988347, + "learning_rate": 5e-06, + "loss": 0.6871, + "step": 330 + }, + { + "epoch": 1.2483959670027498, + "grad_norm": 0.6735946598593434, + "learning_rate": 5e-06, + "loss": 0.6935, + "step": 340 + }, + { + "epoch": 1.2850595783684693, + "grad_norm": 0.7213451984916242, + "learning_rate": 5e-06, + "loss": 0.6943, + "step": 350 + }, + { + "epoch": 1.3217231897341888, + "grad_norm": 0.5841901070016948, + "learning_rate": 5e-06, + "loss": 0.6938, + "step": 360 + }, + { + "epoch": 1.3583868010999083, + "grad_norm": 0.6609752377099979, + "learning_rate": 5e-06, + "loss": 0.6856, + "step": 370 + }, + { + "epoch": 1.3950504124656278, + "grad_norm": 0.6004672142282963, + "learning_rate": 5e-06, + "loss": 0.69, + "step": 380 + }, + { + "epoch": 1.4317140238313475, + "grad_norm": 0.7494020947088555, + "learning_rate": 5e-06, + "loss": 0.682, + "step": 390 + }, + { + "epoch": 1.468377635197067, + "grad_norm": 0.6711006066177567, + "learning_rate": 5e-06, + "loss": 0.6917, + "step": 400 + }, + { + "epoch": 1.5050412465627865, + "grad_norm": 0.6517430215570676, + "learning_rate": 5e-06, + "loss": 0.6871, + "step": 410 + }, + { + "epoch": 1.541704857928506, + "grad_norm": 0.6180564693914907, + "learning_rate": 5e-06, + "loss": 0.6829, + "step": 420 + }, + { + "epoch": 1.5783684692942255, + "grad_norm": 0.5764324092377354, + "learning_rate": 5e-06, + "loss": 0.6824, + "step": 430 + }, + { + "epoch": 1.615032080659945, + "grad_norm": 0.7134204082562298, + "learning_rate": 5e-06, + "loss": 0.6822, + "step": 440 + }, + { + "epoch": 1.6516956920256645, + "grad_norm": 0.7630512170385407, + "learning_rate": 5e-06, + "loss": 0.6879, + "step": 450 + }, + { + "epoch": 1.6883593033913842, + "grad_norm": 0.6285437172539765, + "learning_rate": 5e-06, + "loss": 0.6804, + "step": 460 + }, + { + "epoch": 1.7250229147571035, + "grad_norm": 0.5968789313484854, + "learning_rate": 5e-06, + "loss": 0.686, + "step": 470 + }, + { + "epoch": 1.7616865261228232, + "grad_norm": 0.6425175740435289, + "learning_rate": 5e-06, + "loss": 0.6856, + "step": 480 + }, + { + "epoch": 1.7983501374885427, + "grad_norm": 0.7614365266625939, + "learning_rate": 5e-06, + "loss": 0.6814, + "step": 490 + }, + { + "epoch": 1.8350137488542622, + "grad_norm": 0.5496379357416068, + "learning_rate": 5e-06, + "loss": 0.6855, + "step": 500 + }, + { + "epoch": 1.8716773602199817, + "grad_norm": 0.8494093367270151, + "learning_rate": 5e-06, + "loss": 0.6875, + "step": 510 + }, + { + "epoch": 1.9083409715857012, + "grad_norm": 0.6756166103000668, + "learning_rate": 5e-06, + "loss": 0.6856, + "step": 520 + }, + { + "epoch": 1.9450045829514209, + "grad_norm": 0.7228484772895967, + "learning_rate": 5e-06, + "loss": 0.6841, + "step": 530 + }, + { + "epoch": 1.9816681943171401, + "grad_norm": 0.7786774729146112, + "learning_rate": 5e-06, + "loss": 0.6845, + "step": 540 + }, + { + "epoch": 1.996333638863428, + "eval_loss": 0.7305116057395935, + "eval_runtime": 96.1532, + "eval_samples_per_second": 76.441, + "eval_steps_per_second": 0.603, + "step": 544 + }, + { + "epoch": 2.020164986251146, + "grad_norm": 1.0425759476709966, + "learning_rate": 5e-06, + "loss": 0.707, + "step": 550 + }, + { + "epoch": 2.056828597616865, + "grad_norm": 0.8473344095764829, + "learning_rate": 5e-06, + "loss": 0.6313, + "step": 560 + }, + { + "epoch": 2.093492208982585, + "grad_norm": 0.7205628261028438, + "learning_rate": 5e-06, + "loss": 0.6281, + "step": 570 + }, + { + "epoch": 2.130155820348304, + "grad_norm": 0.6604987014823058, + "learning_rate": 5e-06, + "loss": 0.631, + "step": 580 + }, + { + "epoch": 2.166819431714024, + "grad_norm": 0.6774961015973217, + "learning_rate": 5e-06, + "loss": 0.6351, + "step": 590 + }, + { + "epoch": 2.203483043079743, + "grad_norm": 0.8519809292040578, + "learning_rate": 5e-06, + "loss": 0.634, + "step": 600 + }, + { + "epoch": 2.240146654445463, + "grad_norm": 0.693823740633704, + "learning_rate": 5e-06, + "loss": 0.6327, + "step": 610 + }, + { + "epoch": 2.276810265811182, + "grad_norm": 0.6448705487045298, + "learning_rate": 5e-06, + "loss": 0.6339, + "step": 620 + }, + { + "epoch": 2.313473877176902, + "grad_norm": 0.5865817788059118, + "learning_rate": 5e-06, + "loss": 0.636, + "step": 630 + }, + { + "epoch": 2.3501374885426216, + "grad_norm": 0.8116556137845999, + "learning_rate": 5e-06, + "loss": 0.6342, + "step": 640 + }, + { + "epoch": 2.386801099908341, + "grad_norm": 0.6231657257473445, + "learning_rate": 5e-06, + "loss": 0.637, + "step": 650 + }, + { + "epoch": 2.4234647112740606, + "grad_norm": 0.6250913266909794, + "learning_rate": 5e-06, + "loss": 0.63, + "step": 660 + }, + { + "epoch": 2.46012832263978, + "grad_norm": 0.582068921531117, + "learning_rate": 5e-06, + "loss": 0.6288, + "step": 670 + }, + { + "epoch": 2.4967919340054996, + "grad_norm": 0.6912367969819871, + "learning_rate": 5e-06, + "loss": 0.6381, + "step": 680 + }, + { + "epoch": 2.5334555453712193, + "grad_norm": 0.7147652107920064, + "learning_rate": 5e-06, + "loss": 0.6332, + "step": 690 + }, + { + "epoch": 2.5701191567369386, + "grad_norm": 0.5792260811836798, + "learning_rate": 5e-06, + "loss": 0.6351, + "step": 700 + }, + { + "epoch": 2.606782768102658, + "grad_norm": 0.7963438662743851, + "learning_rate": 5e-06, + "loss": 0.6363, + "step": 710 + }, + { + "epoch": 2.6434463794683776, + "grad_norm": 0.9276380358330181, + "learning_rate": 5e-06, + "loss": 0.6355, + "step": 720 + }, + { + "epoch": 2.6801099908340973, + "grad_norm": 0.9313823270809661, + "learning_rate": 5e-06, + "loss": 0.6351, + "step": 730 + }, + { + "epoch": 2.7167736021998166, + "grad_norm": 0.7304200587600748, + "learning_rate": 5e-06, + "loss": 0.638, + "step": 740 + }, + { + "epoch": 2.7534372135655363, + "grad_norm": 0.6212966397528322, + "learning_rate": 5e-06, + "loss": 0.6388, + "step": 750 + }, + { + "epoch": 2.7901008249312556, + "grad_norm": 0.6720686482466423, + "learning_rate": 5e-06, + "loss": 0.6364, + "step": 760 + }, + { + "epoch": 2.8267644362969753, + "grad_norm": 0.6438467896193539, + "learning_rate": 5e-06, + "loss": 0.6421, + "step": 770 + }, + { + "epoch": 2.863428047662695, + "grad_norm": 0.6043416931907646, + "learning_rate": 5e-06, + "loss": 0.6379, + "step": 780 + }, + { + "epoch": 2.9000916590284143, + "grad_norm": 0.6496494693588303, + "learning_rate": 5e-06, + "loss": 0.6414, + "step": 790 + }, + { + "epoch": 2.936755270394134, + "grad_norm": 0.8144443719589332, + "learning_rate": 5e-06, + "loss": 0.6361, + "step": 800 + }, + { + "epoch": 2.9734188817598532, + "grad_norm": 0.7037764123768507, + "learning_rate": 5e-06, + "loss": 0.6373, + "step": 810 + }, + { + "epoch": 2.9954170485792853, + "eval_loss": 0.7332214117050171, + "eval_runtime": 94.4197, + "eval_samples_per_second": 77.844, + "eval_steps_per_second": 0.614, + "step": 816 + }, + { + "epoch": 2.9954170485792853, + "step": 816, + "total_flos": 1366411632967680.0, + "train_loss": 0.7035682309491962, + "train_runtime": 14220.3782, + "train_samples_per_second": 29.46, + "train_steps_per_second": 0.057 + } + ], + "logging_steps": 10, + "max_steps": 816, + "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": 1366411632967680.0, + "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..b6bdf26 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8baf9eae949940237851325d5f9dbadd1a80ca1a6f07f4de82e70f739b749ef0 +size 7160 diff --git a/training_eval_loss.png b/training_eval_loss.png new file mode 100644 index 0000000..a50e877 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..da4bb30 Binary files /dev/null and b/training_loss.png differ