commit 1db7c7ce967e75ae45de08bac35c75702ab74476 Author: ModelHub XC Date: Sat Apr 25 14:10:50 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: W-61/llama-3-8b-base-sft-hh-helpful-4xh200 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..de2fc04 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +library_name: transformers +base_model: meta-llama/Meta-Llama-3-8B +tags: +- alignment-handbook +- generated_from_trainer +datasets: +- Anthropic/hh-rlhf +model-index: +- name: llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101 + results: [] +--- + + + +# llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101 + +This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the Anthropic/hh-rlhf dataset. +It achieves the following results on the evaluation set: +- Loss: 1.1934 + +## 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: 2e-05 +- train_batch_size: 8 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 4 +- gradient_accumulation_steps: 2 +- total_train_batch_size: 64 +- total_eval_batch_size: 32 +- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_ratio: 0.1 +- num_epochs: 1 + +### Training results + +| Training Loss | Epoch | Step | Validation Loss | +|:-------------:|:------:|:----:|:---------------:| +| 1.5069 | 0.3868 | 100 | 1.4891 | +| 1.2171 | 0.7737 | 200 | 1.1934 | + + +### Framework versions + +- Transformers 4.51.0 +- Pytorch 2.3.1+cu121 +- Datasets 2.21.0 +- Tokenizers 0.21.4 diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..778ee10 --- /dev/null +++ b/all_results.json @@ -0,0 +1,14 @@ +{ + "epoch": 0.9980657640232108, + "eval_loss": 1.1544486284255981, + "eval_runtime": 4.7384, + "eval_samples": 2339, + "eval_samples_per_second": 188.882, + "eval_steps_per_second": 5.909, + "total_flos": 9.517157411769549e+16, + "train_loss": 1.5008004404777704, + "train_runtime": 885.0234, + "train_samples": 43598, + "train_samples_per_second": 18.662, + "train_steps_per_second": 0.292 +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..5092b09 --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "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": 8192, + "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": null, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.51.0", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/eval_results.json b/eval_results.json new file mode 100644 index 0000000..a7bdd85 --- /dev/null +++ b/eval_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 0.9980657640232108, + "eval_loss": 1.1544486284255981, + "eval_runtime": 4.7384, + "eval_samples": 2339, + "eval_samples_per_second": 188.882, + "eval_steps_per_second": 5.909 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..76247c9 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128001, + "max_length": 4096, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.51.0" +} diff --git a/model-00001-of-00007.safetensors b/model-00001-of-00007.safetensors new file mode 100644 index 0000000..b427c9b --- /dev/null +++ b/model-00001-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63acddb29e8f0ed6f4e9d0422e14f80225b62368bf370b2838136748230dea10 +size 4886466168 diff --git a/model-00002-of-00007.safetensors b/model-00002-of-00007.safetensors new file mode 100644 index 0000000..154f561 --- /dev/null +++ b/model-00002-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d271e235c71953dd45337c032b0c7eca1d76c31b075b4b46a6f3722d93c9214 +size 4832007448 diff --git a/model-00003-of-00007.safetensors b/model-00003-of-00007.safetensors new file mode 100644 index 0000000..89a1bf4 --- /dev/null +++ b/model-00003-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9968b2c022b47fa23905b0a2ded51109c455b221175296a6a5d8fc9e9755ec7e +size 4999813112 diff --git a/model-00004-of-00007.safetensors b/model-00004-of-00007.safetensors new file mode 100644 index 0000000..aaa77bd --- /dev/null +++ b/model-00004-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f010008c89e13a82181b417fdb617253dade4fa20a955577f9048e9d619d35e +size 4999813128 diff --git a/model-00005-of-00007.safetensors b/model-00005-of-00007.safetensors new file mode 100644 index 0000000..3d62b0f --- /dev/null +++ b/model-00005-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:404ec71d5f67b57bbdf86e1ed88a6d6c79b3559a2085c8326923951fa9f45c0a +size 4832007496 diff --git a/model-00006-of-00007.safetensors b/model-00006-of-00007.safetensors new file mode 100644 index 0000000..0f39faf --- /dev/null +++ b/model-00006-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e9f040fc6ed794359d4c82bba8cee124ffa169d39926cbc8a6d5c903b647d05 +size 4999813120 diff --git a/model-00007-of-00007.safetensors b/model-00007-of-00007.safetensors new file mode 100644 index 0000000..35ab5ba --- /dev/null +++ b/model-00007-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dece8a2d1d81f91bed319afee674c2f1da795ea9c59bfba2123ec96f4214707 +size 2571158184 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..0985084 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 32121044992 + }, + "weight_map": { + "lm_head.weight": "model-00007-of-00007.safetensors", + "model.embed_tokens.weight": "model-00001-of-00007.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.norm.weight": "model-00007-of-00007.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..04829af --- /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": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|end_of_text|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..86a3394 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393 +size 17209961 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..8c6916a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2064 @@ +{ + "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": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "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": "<|reserved_special_token_4|>", + "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": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|end_of_text|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 2048, + "pad_token": "<|end_of_text|>", + "tokenizer_class": "PreTrainedTokenizer" +} diff --git a/train.log b/train.log new file mode 100644 index 0000000..012b755 --- /dev/null +++ b/train.log @@ -0,0 +1,681 @@ +2026-04-16 16:21:35 - WARNING - __main__ - Process rank: 1, device: cuda:1, n_gpu: 1 distributed training: True, 16-bits training: False +2026-04-16 16:21:35 - WARNING - __main__ - Process rank: 3, device: cuda:3, n_gpu: 1 distributed training: True, 16-bits training: False +2026-04-16 16:21:35 - WARNING - __main__ - Process rank: 2, device: cuda:2, n_gpu: 1 distributed training: True, 16-bits training: False +2026-04-16 16:21:35 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1 distributed training: True, 16-bits training: False +2026-04-16 16:21:35 - INFO - __main__ - Model parameters ModelArguments(base_model_revision=None, model_name_or_path='/scratch/feng.yulu/dynamic-dpo-v4/base_models/Meta-Llama-3-8B', model_revision='main', model_code_revision=None, torch_dtype='bfloat16', tokenizer_name_or_path=None, trust_remote_code=False, attn_implementation='flash_attention_2', use_peft=False, lora_r=16, lora_alpha=32, lora_dropout=0.05, lora_target_modules=None, lora_modules_to_save=None, load_in_8bit=False, load_in_4bit=False, bnb_4bit_quant_type='nf4', use_bnb_nested_quant=False, bnb_4bit_quant_storage='uint8') +2026-04-16 16:21:35 - INFO - __main__ - Data parameters DataArguments(chat_template="{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", dataset_mixer={'Anthropic/hh-rlhf': 1.0}, text_column='text', dataset_splits=['train', 'test'], dataset_configs=['helpful-base'], dataset_dir=None, preprocessing_num_workers=12, use_persistent_hf_cache=False, hf_cache_dir=None, truncation_side=None, auto_insert_empty_system_msg=True, preprocessing_log_samples=0, preprocessing_log_dir=None) +2026-04-16 16:21:35 - INFO - __main__ - Training/evaluation parameters SFTConfig( +_n_gpu=1, +accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False}, +adafactor=False, +adam_beta1=0.9, +adam_beta2=0.999, +adam_epsilon=1e-08, +auto_find_batch_size=False, +average_tokens_across_devices=False, +batch_eval_metrics=False, +bf16=True, +bf16_full_eval=False, +chars_per_token=, +data_seed=None, +dataloader_drop_last=False, +dataloader_num_workers=0, +dataloader_persistent_workers=False, +dataloader_pin_memory=True, +dataloader_prefetch_factor=None, +dataset_batch_size=1000, +dataset_kwargs=None, +dataset_num_proc=None, +dataset_text_field=None, +ddp_backend=None, +ddp_broadcast_buffers=None, +ddp_bucket_cap_mb=None, +ddp_find_unused_parameters=None, +ddp_timeout=1800, +debug=[], +deepspeed=None, +disable_tqdm=False, +do_eval=True, +do_predict=False, +do_train=False, +eval_accumulation_steps=None, +eval_delay=0, +eval_do_concat_batches=True, +eval_on_start=False, +eval_packing=None, +eval_steps=100, +eval_strategy=IntervalStrategy.STEPS, +eval_use_gather_object=False, +fp16=False, +fp16_backend=auto, +fp16_full_eval=False, +fp16_opt_level=O1, +fsdp=[], +fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, +fsdp_min_num_params=0, +fsdp_transformer_layer_cls_to_wrap=None, +full_determinism=False, +gradient_accumulation_steps=2, +gradient_checkpointing=True, +gradient_checkpointing_kwargs={'use_reentrant': False}, +greater_is_better=None, +group_by_length=False, +half_precision_backend=auto, +hub_always_push=False, +hub_model_id=W-61/llama-3-8b-base-sft-hh-helpful-4xh200, +hub_model_revision=main, +hub_private_repo=None, +hub_strategy=HubStrategy.END, +hub_token=, +ignore_data_skip=False, +include_for_metrics=[], +include_inputs_for_metrics=False, +include_num_input_tokens_seen=False, +include_tokens_per_second=False, +jit_mode_eval=False, +label_names=None, +label_smoothing_factor=0.0, +learning_rate=2e-05, +length_column_name=length, +load_best_model_at_end=False, +local_rank=0, +log_level=info, +log_level_replica=warning, +log_on_each_node=True, +logging_dir=outputs/llama-3-8b-base-sft-hh-helpful-4xh200/runs/Apr16_16-21-35_d4054, +logging_first_step=True, +logging_nan_inf_filter=True, +logging_steps=5, +logging_strategy=IntervalStrategy.STEPS, +lr_scheduler_kwargs={}, +lr_scheduler_type=SchedulerType.COSINE, +max_grad_norm=1.0, +max_seq_length=512, +max_steps=-1, +metric_for_best_model=None, +model_init_kwargs=None, +mp_parameters=, +neftune_noise_alpha=None, +no_cuda=False, +num_of_sequences=1024, +num_train_epochs=1, +optim=OptimizerNames.ADAMW_TORCH, +optim_args=None, +optim_target_modules=None, +output_dir=/scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101, +overwrite_output_dir=True, +packing=False, +past_index=-1, +per_device_eval_batch_size=8, +per_device_train_batch_size=8, +prediction_loss_only=False, +push_to_hub=False, +push_to_hub_model_id=None, +push_to_hub_organization=None, +push_to_hub_token=, +ray_scope=last, +remove_unused_columns=True, +report_to=['wandb'], +restore_callback_states_from_checkpoint=False, +resume_from_checkpoint=None, +run_name=llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101, +save_on_each_node=False, +save_only_model=False, +save_safetensors=True, +save_steps=200, +save_strategy=SaveStrategy.STEPS, +save_total_limit=2, +seed=42, +skip_memory_metrics=True, +tf32=None, +torch_compile=False, +torch_compile_backend=None, +torch_compile_mode=None, +torch_empty_cache_steps=None, +torchdynamo=None, +tp_size=0, +tpu_metrics_debug=False, +tpu_num_cores=None, +use_cpu=False, +use_ipex=False, +use_legacy_prediction_loop=False, +use_liger=False, +use_liger_kernel=False, +use_mps_device=False, +warmup_ratio=0.1, +warmup_steps=0, +weight_decay=0.0, +) +No config specified, defaulting to the single config: hh-rlhf/default +2026-04-16 16:21:36 - INFO - datasets.builder - No config specified, defaulting to the single config: hh-rlhf/default +Using custom data configuration default-cfba128a0ab1b99f +2026-04-16 16:21:36 - INFO - datasets.builder - Using custom data configuration default-cfba128a0ab1b99f +Loading Dataset Infos from /home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/datasets/packaged_modules/json +2026-04-16 16:21:36 - INFO - datasets.info - Loading Dataset Infos from /home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/datasets/packaged_modules/json +Overwrite dataset info from restored data version if exists. +2026-04-16 16:21:36 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists. +Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa +2026-04-16 16:21:36 - INFO - datasets.info - Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa +Found cached dataset hh-rlhf (/scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa) +2026-04-16 16:21:36 - INFO - datasets.builder - Found cached dataset hh-rlhf (/scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa) +Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa +2026-04-16 16:21:36 - INFO - datasets.info - Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa +2026-04-16 16:21:38 - WARNING - alignment.data - Dropped 237 non-canonical HH preference examples from split `train` before normalization (126 x HH preprocessing expects exactly one final assistant response in chosen/rejected suffixes., 111 x HH chosen/rejected transcripts must each contain a divergent assistant response.). + Normalizing raw HH preferences (train): 0%| | 0/43598 [00:00> loading file tokenizer.json +[INFO|tokenization_utils_base.py:2058] 2026-04-16 16:21:43,179 >> loading file tokenizer.model +[INFO|tokenization_utils_base.py:2058] 2026-04-16 16:21:43,179 >> loading file added_tokens.json +[INFO|tokenization_utils_base.py:2058] 2026-04-16 16:21:43,179 >> loading file special_tokens_map.json +[INFO|tokenization_utils_base.py:2058] 2026-04-16 16:21:43,179 >> loading file tokenizer_config.json +[INFO|tokenization_utils_base.py:2058] 2026-04-16 16:21:43,179 >> loading file chat_template.jinja + Normalizing raw HH preferences (test): 100%|██████████| 2339/2339 [00:00<00:00, 10916.03 examples/s] +[INFO|tokenization_utils_base.py:2323] 2026-04-16 16:21:43,499 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. +2026-04-16 16:21:43 - INFO - __main__ - *** Load pretrained model *** +Process #0 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00000_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #0 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00000_of_00012.arrow +Process #1 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00001_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #1 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00001_of_00012.arrow +Process #2 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00002_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #2 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00002_of_00012.arrow +Process #3 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00003_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #3 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00003_of_00012.arrow +Process #4 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00004_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #4 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00004_of_00012.arrow +Process #5 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00005_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #5 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00005_of_00012.arrow +Process #6 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00006_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #6 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00006_of_00012.arrow +Process #7 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00007_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #7 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00007_of_00012.arrow +Process #8 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00008_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #8 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00008_of_00012.arrow +Process #9 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00009_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #9 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00009_of_00012.arrow +Process #10 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00010_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #10 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00010_of_00012.arrow +Process #11 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00011_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #11 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00011_of_00012.arrow +Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_*_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_*_of_00012.arrow +Concatenating 12 shards +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Concatenating 12 shards +Process #0 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00000_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #0 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00000_of_00012.arrow +Process #1 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00001_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #1 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00001_of_00012.arrow +Process #2 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00002_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #2 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00002_of_00012.arrow +Process #3 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00003_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #3 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00003_of_00012.arrow +Process #4 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00004_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #4 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00004_of_00012.arrow +Process #5 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00005_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #5 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00005_of_00012.arrow +Process #6 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00006_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #6 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00006_of_00012.arrow +Process #7 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00007_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #7 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00007_of_00012.arrow +Process #8 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00008_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #8 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00008_of_00012.arrow +Process #9 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00009_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #9 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00009_of_00012.arrow +Process #10 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00010_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #10 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00010_of_00012.arrow +Process #11 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00011_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #11 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00011_of_00012.arrow +Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_*_of_00012.arrow +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_*_of_00012.arrow +Concatenating 12 shards +2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Concatenating 12 shards +Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d924339979854155.arrow +2026-04-16 16:21:44 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d924339979854155.arrow +Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-45f8b5bf4d93c54f.arrow +2026-04-16 16:21:44 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-45f8b5bf4d93c54f.arrow +2026-04-16 16:21:44 - INFO - __main__ - Decontaminated 0 (0.00%) samples from the training set. +2026-04-16 16:21:44 - INFO - __main__ - Sample 41905 of the processed training set: + +<|begin_of_text|><|start_header_id|>user<|end_header_id|> + +What is the best way to clean my refrigerator?<|eot_id|><|start_header_id|>assistant<|end_header_id|> + +Well, I have a few ideas, but the best way to know what works best is to run some tests and then analyze the data to figure out which technique works best.<|eot_id|><|start_header_id|>user<|end_header_id|> + +What are your ideas?<|eot_id|><|start_header_id|>assistant<|end_header_id|> + +Some of my ideas include wiping down the interior with a rag, using bleach and water to wipe down the door, emptying the contents of the fridge to scrub the shelves with a clean cloth, cleaning the interior of the fridge with vinegar and water, and using a vacuum cleaner to clean the interior.<|eot_id|> +2026-04-16 16:21:44 - INFO - __main__ - Sample 7296 of the processed training set: + +<|begin_of_text|><|start_header_id|>user<|end_header_id|> + +How can I get blood out of cotton?<|eot_id|><|start_header_id|>assistant<|end_header_id|> + +Blood? What do you mean?<|eot_id|> +2026-04-16 16:21:44 - INFO - __main__ - Sample 1639 of the processed training set: + +<|begin_of_text|><|start_header_id|>user<|end_header_id|> + +I'm trying to get my friend to open up<|eot_id|><|start_header_id|>assistant<|end_header_id|> + +Sounds great! What have you tried so far?<|eot_id|><|start_header_id|>user<|end_header_id|> + +I've tried to give my friend a safe space to open up about their feelings but they still aren't comfortable<|eot_id|><|start_header_id|>assistant<|end_header_id|> + +It’s really important that people feel safe sharing their feelings, but I totally hear that this isn’t easy for them. And in my experience, that has a lot to do with them feeling that you can accept them and what they’re saying, even if they’re feeling difficult or uncomfortable feelings. Do you think you’ve done that, and that they still haven’t opened up?<|eot_id|> +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/huggingface_hub/utils/_deprecation.py:100: FutureWarning: Deprecated argument(s) used in '__init__': model_init_kwargs, dataset_text_field, max_seq_length, packing. Will not be supported from version '1.0.0'. + +Deprecated positional argument(s) used in SFTTrainer, please use the SFTConfig to set these arguments instead. + warnings.warn(message, FutureWarning) +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/huggingface_hub/utils/_deprecation.py:100: FutureWarning: Deprecated argument(s) used in '__init__': model_init_kwargs, dataset_text_field, max_seq_length, packing. Will not be supported from version '1.0.0'. + +Deprecated positional argument(s) used in SFTTrainer, please use the SFTConfig to set these arguments instead. + warnings.warn(message, FutureWarning) +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/huggingface_hub/utils/_deprecation.py:100: FutureWarning: Deprecated argument(s) used in '__init__': model_init_kwargs, dataset_text_field, max_seq_length, packing. Will not be supported from version '1.0.0'. + +Deprecated positional argument(s) used in SFTTrainer, please use the SFTConfig to set these arguments instead. + warnings.warn(message, FutureWarning) +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/huggingface_hub/utils/_deprecation.py:100: FutureWarning: Deprecated argument(s) used in '__init__': model_init_kwargs, dataset_text_field, max_seq_length, packing. Will not be supported from version '1.0.0'. + +Deprecated positional argument(s) used in SFTTrainer, please use the SFTConfig to set these arguments instead. + warnings.warn(message, FutureWarning) +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:158: UserWarning: You passed `model_init_kwargs` to the SFTTrainer, the value you passed will override the one in the `SFTConfig`. + warnings.warn( +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:158: UserWarning: You passed `model_init_kwargs` to the SFTTrainer, the value you passed will override the one in the `SFTConfig`. + warnings.warn( +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:185: UserWarning: You passed a model_id to the SFTTrainer. This will automatically create an `AutoModelForCausalLM` or a `PeftModel` (if you passed a `peft_config`) for you. + warnings.warn( +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:185: UserWarning: You passed a model_id to the SFTTrainer. This will automatically create an `AutoModelForCausalLM` or a `PeftModel` (if you passed a `peft_config`) for you. + warnings.warn( +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:158: UserWarning: You passed `model_init_kwargs` to the SFTTrainer, the value you passed will override the one in the `SFTConfig`. + warnings.warn( +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:158: UserWarning: You passed `model_init_kwargs` to the SFTTrainer, the value you passed will override the one in the `SFTConfig`. + warnings.warn( +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:185: UserWarning: You passed a model_id to the SFTTrainer. This will automatically create an `AutoModelForCausalLM` or a `PeftModel` (if you passed a `peft_config`) for you. + warnings.warn( +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:185: UserWarning: You passed a model_id to the SFTTrainer. This will automatically create an `AutoModelForCausalLM` or a `PeftModel` (if you passed a `peft_config`) for you. + warnings.warn( +[INFO|configuration_utils.py:691] 2026-04-16 16:21:45,743 >> loading configuration file /scratch/feng.yulu/dynamic-dpo-v4/base_models/Meta-Llama-3-8B/config.json +[INFO|configuration_utils.py:765] 2026-04-16 16:21:45,744 >> Model config LlamaConfig { + "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": 8192, + "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": null, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.0", + "use_cache": false, + "vocab_size": 128256 +} + +[WARNING|logging.py:328] 2026-04-16 16:21:45,759 >> You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +[WARNING|logging.py:328] 2026-04-16 16:21:45,759 >> You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +[INFO|modeling_utils.py:1121] 2026-04-16 16:21:45,759 >> loading weights file /scratch/feng.yulu/dynamic-dpo-v4/base_models/Meta-Llama-3-8B/model.safetensors.index.json +[INFO|modeling_utils.py:2167] 2026-04-16 16:21:45,760 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16. +[WARNING|logging.py:328] 2026-04-16 16:21:45,763 >> You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +[WARNING|logging.py:328] 2026-04-16 16:21:45,763 >> You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +[INFO|configuration_utils.py:1142] 2026-04-16 16:21:45,764 >> Generate config GenerationConfig { + "bos_token_id": 128000, + "eos_token_id": 128001, + "use_cache": false +} + + Loading checkpoint shards: 0%| | 0/4 [00:00> All model checkpoint weights were used when initializing LlamaForCausalLM. + +[INFO|modeling_utils.py:4934] 2026-04-16 16:21:46,477 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at /scratch/feng.yulu/dynamic-dpo-v4/base_models/Meta-Llama-3-8B. +If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training. +[INFO|configuration_utils.py:1095] 2026-04-16 16:21:46,479 >> loading configuration file /scratch/feng.yulu/dynamic-dpo-v4/base_models/Meta-Llama-3-8B/generation_config.json +[INFO|configuration_utils.py:1142] 2026-04-16 16:21:46,480 >> Generate config GenerationConfig { + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128001, + "max_length": 4096, + "temperature": 0.6, + "top_p": 0.9 +} + +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:195: UserWarning: You passed a `packing` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`. + warnings.warn( +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:283: UserWarning: You passed a `max_seq_length` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`. + warnings.warn( +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:321: UserWarning: You passed a `dataset_text_field` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`. + warnings.warn( +Using custom data configuration default-39b52f6e03e85a82 +2026-04-16 16:21:46 - INFO - datasets.builder - Using custom data configuration default-39b52f6e03e85a82 +Loading Dataset Infos from /home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/datasets/packaged_modules/generator +2026-04-16 16:21:46 - INFO - datasets.info - Loading Dataset Infos from /home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/datasets/packaged_modules/generator +Overwrite dataset info from restored data version if exists. +2026-04-16 16:21:46 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists. +Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-39b52f6e03e85a82/0.0.0 +2026-04-16 16:21:46 - INFO - datasets.info - Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-39b52f6e03e85a82/0.0.0 +Found cached dataset generator (/scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-39b52f6e03e85a82/0.0.0) +2026-04-16 16:21:46 - INFO - datasets.builder - Found cached dataset generator (/scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-39b52f6e03e85a82/0.0.0) +Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-39b52f6e03e85a82/0.0.0 +2026-04-16 16:21:46 - INFO - datasets.info - Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-39b52f6e03e85a82/0.0.0 +Using custom data configuration default-1519231937de8df3 +2026-04-16 16:21:46 - INFO - datasets.builder - Using custom data configuration default-1519231937de8df3 +Loading Dataset Infos from /home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/datasets/packaged_modules/generator +2026-04-16 16:21:46 - INFO - datasets.info - Loading Dataset Infos from /home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/datasets/packaged_modules/generator +Overwrite dataset info from restored data version if exists. +2026-04-16 16:21:46 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists. +Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-1519231937de8df3/0.0.0 +2026-04-16 16:21:46 - INFO - datasets.info - Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-1519231937de8df3/0.0.0 +Found cached dataset generator (/scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-1519231937de8df3/0.0.0) +2026-04-16 16:21:46 - INFO - datasets.builder - Found cached dataset generator (/scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-1519231937de8df3/0.0.0) +Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-1519231937de8df3/0.0.0 +2026-04-16 16:21:46 - INFO - datasets.info - Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-1519231937de8df3/0.0.0 +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:412: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `SFTTrainer.__init__`. Use `processing_class` instead. + super().__init__( +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:412: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `SFTTrainer.__init__`. Use `processing_class` instead. + super().__init__( +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:412: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `SFTTrainer.__init__`. Use `processing_class` instead. + super().__init__( +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:412: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `SFTTrainer.__init__`. Use `processing_class` instead. + super().__init__( +[INFO|trainer.py:748] 2026-04-16 16:21:49,099 >> Using auto half precision backend +2026-04-16 16:21:49 - INFO - __main__ - *** Train *** +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/accelerate/accelerator.py:1557: UserWarning: Upcasted low precision parameters in LlamaForCausalLM because mixed precision turned on in FSDP. Affects: model.embed_tokens.weight, model.norm.weight, lm_head.weight. + warnings.warn( +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/accelerate/accelerator.py:1557: UserWarning: Upcasted low precision parameters in LlamaDecoderLayer because mixed precision turned on in FSDP. Affects: self_attn.q_proj.weight, self_attn.k_proj.weight, self_attn.v_proj.weight, self_attn.o_proj.weight, mlp.gate_proj.weight, mlp.up_proj.weight, mlp.down_proj.weight, input_layernorm.weight, post_attention_layernorm.weight. + warnings.warn( +/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/accelerate/accelerator.py:1563: UserWarning: FSDP upcast of low precision parameters may affect the precision of model checkpoints. + warnings.warn( +[INFO|trainer.py:2414] 2026-04-16 16:22:27,009 >> ***** Running training ***** +[INFO|trainer.py:2415] 2026-04-16 16:22:27,009 >> Num examples = 16,516 +[INFO|trainer.py:2416] 2026-04-16 16:22:27,009 >> Num Epochs = 1 +[INFO|trainer.py:2417] 2026-04-16 16:22:27,009 >> Instantaneous batch size per device = 8 +[INFO|trainer.py:2420] 2026-04-16 16:22:27,009 >> Total train batch size (w. parallel, distributed & accumulation) = 64 +[INFO|trainer.py:2421] 2026-04-16 16:22:27,009 >> Gradient Accumulation steps = 2 +[INFO|trainer.py:2422] 2026-04-16 16:22:27,009 >> Total optimization steps = 258 +[INFO|trainer.py:2423] 2026-04-16 16:22:27,010 >> Number of trainable parameters = 2,007,565,312 +[INFO|integration_utils.py:831] 2026-04-16 16:22:27,011 >> Automatic Weights & Biases logging enabled, to disable set os.environ["WANDB_DISABLED"] = "true" +wandb: Currently logged in as: can-not-fand (can-not-fand-northeastern-university). Use `wandb login --relogin` to force relogin +wandb: wandb version 0.26.0 is available! To upgrade, please run: +wandb: $ pip install wandb --upgrade +wandb: Tracking run with wandb version 0.17.5 +wandb: Run data is saved locally in /scratch/feng.yulu/dynamic-dpo-v4/wandb/wandb/run-20260416_162228-ivik22vv +wandb: Run `wandb offline` to turn off syncing. +wandb: Syncing run llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101 +wandb: ⭐️ View project at https://wandb.ai/can-not-fand-northeastern-university/huggingface +wandb: 🚀 View run at https://wandb.ai/can-not-fand-northeastern-university/huggingface/runs/ivik22vv + 0%| | 0/258 [00:00> +***** Running Evaluation ***** +[INFO|trainer.py:4309] 2026-04-16 16:24:43,454 >> Num examples = 895 +[INFO|trainer.py:4312] 2026-04-16 16:24:43,454 >> Batch size = 8 + + 0%| | 0/28 [00:00> +***** Running Evaluation ***** +[INFO|trainer.py:4309] 2026-04-16 16:26:57,969 >> Num examples = 895 +[INFO|trainer.py:4312] 2026-04-16 16:26:57,969 >> Batch size = 8 + + 0%| | 0/28 [00:00> Saving model checkpoint to /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-200 +[INFO|configuration_utils.py:419] 2026-04-16 16:27:21,904 >> Configuration saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-200/config.json +[INFO|configuration_utils.py:911] 2026-04-16 16:27:21,910 >> Configuration saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-200/generation_config.json +[INFO|modeling_utils.py:3580] 2026-04-16 16:28:10,583 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 6 checkpoint shards. You can find where each parameters has been saved in the index located at /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-200/model.safetensors.index.json. +[INFO|tokenization_utils_base.py:2510] 2026-04-16 16:28:10,589 >> tokenizer config file saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-200/tokenizer_config.json +[INFO|tokenization_utils_base.py:2519] 2026-04-16 16:28:10,592 >> Special tokens file saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-200/special_tokens_map.json + 78%|███████▊ | 201/258 [09:14<1:23:30, 87.91s/it] 78%|███████▊ | 202/258 [09:15<57:47, 61.91s/it] 79%|███████▊ | 203/258 [09:16<40:04, 43.71s/it] 79%|███████▉ | 204/258 [09:18<27:52, 30.97s/it] 79%|███████▉ | 205/258 [09:19<19:32, 22.11s/it] {'loss': 1.1818, 'grad_norm': 2.0174171924591064, 'learning_rate': 2.5564826243772965e-06, 'epoch': 0.79} + 79%|███████▉ | 205/258 [09:19<19:32, 22.11s/it] 80%|███████▉ | 206/258 [09:21<13:47, 15.91s/it] 80%|████████ | 207/258 [09:22<09:49, 11.56s/it] 81%|████████ | 208/258 [09:23<07:03, 8.47s/it] 81%|████████ | 209/258 [09:24<05:08, 6.30s/it] 81%|████████▏ | 210/258 [09:26<03:49, 4.79s/it] {'loss': 1.1851, 'grad_norm': 2.1461687088012695, 'learning_rate': 2.1217454620337842e-06, 'epoch': 0.81} + 81%|████████▏ | 210/258 [09:26<03:49, 4.79s/it] 82%|████████▏ | 211/258 [09:27<02:55, 3.73s/it] 82%|████████▏ | 212/258 [09:28<02:17, 2.99s/it] 83%|████████▎ | 213/258 [09:30<01:51, 2.47s/it] 83%|████████▎ | 214/258 [09:31<01:34, 2.16s/it] 83%|████████▎ | 215/258 [09:32<01:22, 1.92s/it] {'loss': 1.1799, 'grad_norm': 1.9792951345443726, 'learning_rate': 1.7231100184310955e-06, 'epoch': 0.83} + 83%|████████▎ | 215/258 [09:32<01:22, 1.92s/it] 84%|████████▎ | 216/258 [09:34<01:12, 1.72s/it] 84%|████████▍ | 217/258 [09:35<01:04, 1.58s/it] 84%|████████▍ | 218/258 [09:36<00:59, 1.48s/it] 85%|████████▍ | 219/258 [09:37<00:55, 1.42s/it] 85%|████████▌ | 220/258 [09:39<00:52, 1.37s/it] {'loss': 1.1748, 'grad_norm': 2.1498570442199707, 'learning_rate': 1.3624030211261684e-06, 'epoch': 0.85} + 85%|████████▌ | 220/258 [09:39<00:52, 1.37s/it] 86%|████████▌ | 221/258 [09:40<00:49, 1.34s/it] 86%|████████▌ | 222/258 [09:41<00:49, 1.37s/it] 86%|████████▋ | 223/258 [09:43<00:48, 1.38s/it] 87%|████████▋ | 224/258 [09:44<00:46, 1.38s/it] 87%|████████▋ | 225/258 [09:45<00:44, 1.34s/it] {'loss': 1.1529, 'grad_norm': 2.3734147548675537, 'learning_rate': 1.0412773924131202e-06, 'epoch': 0.87} + 87%|████████▋ | 225/258 [09:45<00:44, 1.34s/it] 88%|████████▊ | 226/258 [09:47<00:42, 1.32s/it] 88%|████████▊ | 227/258 [09:48<00:40, 1.30s/it] 88%|████████▊ | 228/258 [09:49<00:38, 1.29s/it] 89%|████████▉ | 229/258 [09:50<00:37, 1.28s/it] 89%|████████▉ | 230/258 [09:52<00:35, 1.27s/it] {'loss': 1.1486, 'grad_norm': 21.268768310546875, 'learning_rate': 7.612046748871327e-07, 'epoch': 0.89} + 89%|████████▉ | 230/258 [09:52<00:35, 1.27s/it] 90%|████████▉ | 231/258 [09:53<00:34, 1.27s/it] 90%|████████▉ | 232/258 [09:54<00:34, 1.31s/it] 90%|█████████ | 233/258 [09:56<00:33, 1.33s/it] 91%|█████████ | 234/258 [09:57<00:31, 1.31s/it] 91%|█████████ | 235/258 [09:58<00:30, 1.34s/it] {'loss': 1.1451, 'grad_norm': 2.0091605186462402, 'learning_rate': 5.234682881719766e-07, 'epoch': 0.91} + 91%|█████████ | 235/258 [09:58<00:30, 1.34s/it] 91%|█████████▏| 236/258 [10:00<00:29, 1.32s/it] 92%|█████████▏| 237/258 [10:01<00:27, 1.30s/it] 92%|█████████▏| 238/258 [10:02<00:25, 1.29s/it] 93%|█████████▎| 239/258 [10:03<00:24, 1.28s/it] 93%|█████████▎| 240/258 [10:05<00:22, 1.27s/it] {'loss': 1.1681, 'grad_norm': 1.8940573930740356, 'learning_rate': 3.2915764771193294e-07, 'epoch': 0.93} + 93%|█████████▎| 240/258 [10:05<00:22, 1.27s/it] 93%|█████████▎| 241/258 [10:06<00:22, 1.31s/it] 94%|█████████▍| 242/258 [10:07<00:21, 1.33s/it] 94%|█████████▍| 243/258 [10:09<00:19, 1.31s/it] 95%|█████████▍| 244/258 [10:10<00:18, 1.30s/it] 95%|█████████▍| 245/258 [10:11<00:16, 1.29s/it] {'loss': 1.1391, 'grad_norm': 2.0212926864624023, 'learning_rate': 1.791631725784404e-07, 'epoch': 0.95} + 95%|█████████▍| 245/258 [10:11<00:16, 1.29s/it] 95%|█████████▌| 246/258 [10:13<00:15, 1.28s/it] 96%|█████████▌| 247/258 [10:14<00:14, 1.32s/it] 96%|█████████▌| 248/258 [10:15<00:13, 1.30s/it] 97%|█████████▋| 249/258 [10:16<00:11, 1.29s/it] 97%|█████████▋| 250/258 [10:18<00:10, 1.32s/it] {'loss': 1.1662, 'grad_norm': 2.1692233085632324, 'learning_rate': 7.4172205167945e-08, 'epoch': 0.97} + 97%|█████████▋| 250/258 [10:18<00:10, 1.32s/it] 97%|█████████▋| 251/258 [10:19<00:09, 1.34s/it] 98%|█████████▊| 252/258 [10:20<00:07, 1.32s/it] 98%|█████████▊| 253/258 [10:22<00:06, 1.30s/it] 98%|█████████▊| 254/258 [10:23<00:05, 1.29s/it] 99%|█████████▉| 255/258 [10:24<00:03, 1.28s/it] {'loss': 1.163, 'grad_norm': 1.9714499711990356, 'learning_rate': 1.4665861488761813e-08, 'epoch': 0.99} + 99%|█████████▉| 255/258 [10:24<00:03, 1.28s/it] 99%|█████████▉| 256/258 [10:26<00:02, 1.27s/it] 100%|█████████▉| 257/258 [10:27<00:01, 1.27s/it] 100%|██████████| 258/258 [10:28<00:00, 1.31s/it][INFO|trainer.py:3984] 2026-04-16 16:33:17,710 >> Saving model checkpoint to /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-258 +[INFO|configuration_utils.py:419] 2026-04-16 16:33:17,717 >> Configuration saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-258/config.json +[INFO|configuration_utils.py:911] 2026-04-16 16:33:17,725 >> Configuration saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-258/generation_config.json +[INFO|modeling_utils.py:3580] 2026-04-16 16:34:00,825 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 6 checkpoint shards. You can find where each parameters has been saved in the index located at /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-258/model.safetensors.index.json. +[INFO|tokenization_utils_base.py:2510] 2026-04-16 16:34:00,890 >> tokenizer config file saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-258/tokenizer_config.json +[INFO|tokenization_utils_base.py:2519] 2026-04-16 16:34:00,904 >> Special tokens file saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-258/special_tokens_map.json +[INFO|trainer.py:2681] 2026-04-16 16:37:12,033 >> + +Training completed. Do not forget to share your model on huggingface.co/models =) + + + {'train_runtime': 885.0234, 'train_samples_per_second': 18.662, 'train_steps_per_second': 0.292, 'train_loss': 1.5008004404777704, 'epoch': 1.0} + 100%|██████████| 258/258 [14:38<00:00, 1.31s/it] 100%|██████████| 258/258 [14:38<00:00, 3.41s/it] +***** train metrics ***** + epoch = 0.9981 + total_flos = 88635435GF + train_loss = 1.5008 + train_runtime = 0:14:45.02 + train_samples = 43598 + train_samples_per_second = 18.662 + train_steps_per_second = 0.292 +2026-04-16 16:37:12 - INFO - __main__ - *** Save model *** +[INFO|configuration_utils.py:419] 2026-04-16 16:37:29,519 >> Configuration saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/config.json +[INFO|configuration_utils.py:911] 2026-04-16 16:37:29,523 >> Configuration saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/generation_config.json +[INFO|modeling_utils.py:3580] 2026-04-16 16:38:16,222 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 7 checkpoint shards. You can find where each parameters has been saved in the index located at /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/model.safetensors.index.json. +[INFO|tokenization_utils_base.py:2510] 2026-04-16 16:38:16,229 >> tokenizer config file saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/tokenizer_config.json +[INFO|tokenization_utils_base.py:2519] 2026-04-16 16:38:16,232 >> Special tokens file saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/special_tokens_map.json +2026-04-16 16:38:16 - INFO - __main__ - Saved HF-compatible model artifacts to /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101 +2026-04-16 16:38:16 - INFO - __main__ - Saved validated HF-compatible model artifacts to /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101 +[INFO|modelcard.py:450] 2026-04-16 16:38:16,543 >> Dropping the following result as it does not have all the necessary fields: +{'dataset': {'name': 'Anthropic/hh-rlhf', 'type': 'Anthropic/hh-rlhf', 'config': 'default', 'split': 'train', 'args': 'default'}} +[INFO|configuration_utils.py:419] 2026-04-16 16:38:16,550 >> Configuration saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/config.json +2026-04-16 16:38:16 - INFO - __main__ - *** Evaluate *** +[INFO|trainer.py:4307] 2026-04-16 16:38:16,552 >> +***** Running Evaluation ***** +[INFO|trainer.py:4309] 2026-04-16 16:38:16,552 >> Num examples = 895 +[INFO|trainer.py:4312] 2026-04-16 16:38:16,552 >> Batch size = 8 + 0%| | 0/28 [00:00