commit 9534c9c26e9cbeae12b3ef665e857e81477916bf Author: ModelHub XC Date: Fri May 22 13:14:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: HCY123902/llama-3-8b-dpo-tw23-beta-1e-0 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f5e045b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.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 +checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4c1f70c --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: princeton-nlp/Llama-3-Base-8B-SFT +library_name: transformers +model_name: llama-3-8b-dpo-tw23-beta-1e-0 +tags: +- generated_from_trainer +- trl +- dpo +licence: license +--- + +# Model Card for llama-3-8b-dpo-tw23-beta-1e-0 + +This model is a fine-tuned version of [princeton-nlp/Llama-3-Base-8B-SFT](https://huggingface.co/princeton-nlp/Llama-3-Base-8B-SFT). +It has been trained using [TRL](https://github.com/huggingface/trl). + +## Quick start + +```python +from transformers import pipeline + +question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" +generator = pipeline("text-generation", model="HCY123902/llama-3-8b-dpo-tw23-beta-1e-0", device="cuda") +output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] +print(output["generated_text"]) +``` + +## Training procedure + +[Visualize in Weights & Biases](https://wandb.ai/2320032466hchy/attention_dpo/runs/jjhiqvm4) + + +This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290). + +### Framework versions + +- TRL: 0.20.0 +- Transformers: 4.54.1 +- Pytorch: 2.7.1+cu128 +- Datasets: 3.6.0 +- Tokenizers: 0.21.1 + +## Citations + +Cite DPO as: + +```bibtex +@inproceedings{rafailov2023direct, + title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}}, + author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn}, + year = 2023, + booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023}, + url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html}, + editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, +} +``` + +Cite TRL as: + +```bibtex +@misc{vonwerra2022trl, + title = {{TRL: Transformer Reinforcement Learning}}, + author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, + year = 2020, + journal = {GitHub repository}, + publisher = {GitHub}, + howpublished = {\url{https://github.com/huggingface/trl}} +} +``` \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..39bd0c9 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,5 @@ +{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|> + +'+ 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|> + +' }}{% endif %} \ No newline at end of file diff --git a/checkpoint-1000/chat_template.jinja b/checkpoint-1000/chat_template.jinja new file mode 100644 index 0000000..39bd0c9 --- /dev/null +++ b/checkpoint-1000/chat_template.jinja @@ -0,0 +1,5 @@ +{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|> + +'+ 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|> + +' }}{% endif %} \ No newline at end of file diff --git a/checkpoint-1000/config.json b/checkpoint-1000/config.json new file mode 100644 index 0000000..3f8f5c0 --- /dev/null +++ b/checkpoint-1000/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": "bfloat16", + "transformers_version": "4.54.1", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/checkpoint-1000/generation_config.json b/checkpoint-1000/generation_config.json new file mode 100644 index 0000000..fc3c54a --- /dev/null +++ b/checkpoint-1000/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "eos_token_id": 128001, + "transformers_version": "4.54.1" +} diff --git a/checkpoint-1000/global_step1000/zero_pp_rank_0_mp_rank_00_model_states.pt b/checkpoint-1000/global_step1000/zero_pp_rank_0_mp_rank_00_model_states.pt new file mode 100644 index 0000000..ced0ce6 --- /dev/null +++ b/checkpoint-1000/global_step1000/zero_pp_rank_0_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bed638b269dbaa911aa4f7a6c02a370622118093d074c0ae06e23dd132519cf +size 149296 diff --git a/checkpoint-1000/global_step1000/zero_pp_rank_1_mp_rank_00_model_states.pt b/checkpoint-1000/global_step1000/zero_pp_rank_1_mp_rank_00_model_states.pt new file mode 100644 index 0000000..af61d1c --- /dev/null +++ b/checkpoint-1000/global_step1000/zero_pp_rank_1_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b33e9759369cecd527813132594cfd2c5adda1d7ecd7adf49175c3786fea9e2f +size 149296 diff --git a/checkpoint-1000/latest b/checkpoint-1000/latest new file mode 100644 index 0000000..e2d3435 --- /dev/null +++ b/checkpoint-1000/latest @@ -0,0 +1 @@ +global_step1000 \ No newline at end of file diff --git a/checkpoint-1000/model-00001-of-00004.safetensors b/checkpoint-1000/model-00001-of-00004.safetensors new file mode 100644 index 0000000..e95f74d --- /dev/null +++ b/checkpoint-1000/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93e477d6d266155ee5bae0f0fc9565a74bb8734ee8d91581de0e2a7da294f407 +size 4976698672 diff --git a/checkpoint-1000/model-00002-of-00004.safetensors b/checkpoint-1000/model-00002-of-00004.safetensors new file mode 100644 index 0000000..059b217 --- /dev/null +++ b/checkpoint-1000/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fecf137b71cbf9dac75005ba5c2f9010791ee1e075628c2faebb4473235253a4 +size 4999802720 diff --git a/checkpoint-1000/model-00003-of-00004.safetensors b/checkpoint-1000/model-00003-of-00004.safetensors new file mode 100644 index 0000000..c3633d2 --- /dev/null +++ b/checkpoint-1000/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb1ef83d60567e2df5ed66e1508355618a91b3ab5831edfdb2f7c24c9e755869 +size 4915916176 diff --git a/checkpoint-1000/model-00004-of-00004.safetensors b/checkpoint-1000/model-00004-of-00004.safetensors new file mode 100644 index 0000000..8d984a6 --- /dev/null +++ b/checkpoint-1000/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37843cbc30dd8dfeac5ebf807c751d753f98fed08d0783a746324759a8da377e +size 1168138808 diff --git a/checkpoint-1000/model.safetensors.index.json b/checkpoint-1000/model.safetensors.index.json new file mode 100644 index 0000000..58a7ef4 --- /dev/null +++ b/checkpoint-1000/model.safetensors.index.json @@ -0,0 +1,299 @@ +{ + "metadata": { + "total_parameters": 266240, + "total_size": 16060522496 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/checkpoint-1000/rng_state_0.pth b/checkpoint-1000/rng_state_0.pth new file mode 100644 index 0000000..37c843b --- /dev/null +++ b/checkpoint-1000/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddb2e15baa025bd61fe183f8e343e7ff470b9a01aecd8defcf155a1cf00393e3 +size 14917 diff --git a/checkpoint-1000/rng_state_1.pth b/checkpoint-1000/rng_state_1.pth new file mode 100644 index 0000000..d8eccdd --- /dev/null +++ b/checkpoint-1000/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07ee73a4738a457f3198cccec25cf12377bb1eba6c29e95c9fecf83c1487d401 +size 14917 diff --git a/checkpoint-1000/scheduler.pt b/checkpoint-1000/scheduler.pt new file mode 100644 index 0000000..7c34b16 --- /dev/null +++ b/checkpoint-1000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f1b2374548a5ec63cdcc0490db6ed738cd23c8550fb53eb0592574609549746 +size 1465 diff --git a/checkpoint-1000/special_tokens_map.json b/checkpoint-1000/special_tokens_map.json new file mode 100644 index 0000000..e5b39b6 --- /dev/null +++ b/checkpoint-1000/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "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": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-1000/tokenizer.json b/checkpoint-1000/tokenizer.json new file mode 100644 index 0000000..03aa64f --- /dev/null +++ b/checkpoint-1000/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0968dcc0ee8e56c7dccd34a7f51f8065ea0cb9e2cc529e3243d1e5c0a4bdaa0c +size 17208754 diff --git a/checkpoint-1000/tokenizer_config.json b/checkpoint-1000/tokenizer_config.json new file mode 100644 index 0000000..877a9a9 --- /dev/null +++ b/checkpoint-1000/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "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|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|end_of_text|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 32768, + "pad_token": "<|end_of_text|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-1000/trainer_state.json b/checkpoint-1000/trainer_state.json new file mode 100644 index 0000000..5f83ac6 --- /dev/null +++ b/checkpoint-1000/trainer_state.json @@ -0,0 +1,2199 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.5234231876472127, + "eval_steps": 500, + "global_step": 1000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0005234231876472127, + "grad_norm": 124.9239730834961, + "learning_rate": 0.0, + "logits/chosen": -0.4007568359375, + "logits/rejected": -0.41790771484375, + "logps/chosen": -297.796875, + "logps/rejected": -248.078125, + "logps/weighted_chosen": -4.70263671875, + "logps/weighted_rejected": -3.35546875, + "loss": 0.6914, + "rewards/accuracies": 0.0, + "rewards/chosen": 0.0, + "rewards/margins": 0.0, + "rewards/rejected": 0.0, + "rewards/weighted_accuracies": 0.0, + "rewards/weighted_chosen": 0.0, + "rewards/weighted_margins": 0.0, + "rewards/weighted_rejected": 0.0, + "step": 1 + }, + { + "epoch": 0.005234231876472127, + "grad_norm": 265.8483581542969, + "learning_rate": 4.6875e-08, + "logits/chosen": -0.3176540732383728, + "logits/rejected": -0.3532511293888092, + "logps/chosen": -275.5720520019531, + "logps/rejected": -255.88714599609375, + "logps/weighted_chosen": -2.5362956523895264, + "logps/weighted_rejected": -2.774468421936035, + "loss": 0.6903, + "rewards/accuracies": 0.2743055522441864, + "rewards/chosen": 0.0078125, + "rewards/margins": 0.02973090298473835, + "rewards/rejected": -0.02191840298473835, + "rewards/weighted_accuracies": 0.3055555522441864, + "rewards/weighted_chosen": 0.0025702582206577063, + "rewards/weighted_margins": 0.0017564562149345875, + "rewards/weighted_rejected": 0.0008138020639307797, + "step": 10 + }, + { + "epoch": 0.010468463752944255, + "grad_norm": 17.298032760620117, + "learning_rate": 9.895833333333332e-08, + "logits/chosen": -0.2979484498500824, + "logits/rejected": -0.3138488829135895, + "logps/chosen": -294.40625, + "logps/rejected": -272.69061279296875, + "logps/weighted_chosen": -2.3424315452575684, + "logps/weighted_rejected": -2.307080030441284, + "loss": 0.6912, + "rewards/accuracies": 0.296875, + "rewards/chosen": 0.007617187686264515, + "rewards/margins": 0.05781250074505806, + "rewards/rejected": -0.05019531399011612, + "rewards/weighted_accuracies": 0.3531250059604645, + "rewards/weighted_chosen": 0.0003913879336323589, + "rewards/weighted_margins": 0.00116729736328125, + "rewards/weighted_rejected": -0.0007759094005450606, + "step": 20 + }, + { + "epoch": 0.015702695629416383, + "grad_norm": 79.90486907958984, + "learning_rate": 1.5104166666666664e-07, + "logits/chosen": -0.2918685972690582, + "logits/rejected": -0.3376312255859375, + "logps/chosen": -298.02032470703125, + "logps/rejected": -268.0210876464844, + "logps/weighted_chosen": -2.290698289871216, + "logps/weighted_rejected": -2.578540086746216, + "loss": 0.6921, + "rewards/accuracies": 0.3187499940395355, + "rewards/chosen": 0.0751953125, + "rewards/margins": 0.10107421875, + "rewards/rejected": -0.02587890625, + "rewards/weighted_accuracies": 0.375, + "rewards/weighted_chosen": 0.0023864745162427425, + "rewards/weighted_margins": -9.1552734375e-05, + "rewards/weighted_rejected": 0.0024780272506177425, + "step": 30 + }, + { + "epoch": 0.02093692750588851, + "grad_norm": 32.818607330322266, + "learning_rate": 2.03125e-07, + "logits/chosen": -0.3010299801826477, + "logits/rejected": -0.3435005247592926, + "logps/chosen": -278.60235595703125, + "logps/rejected": -253.9250030517578, + "logps/weighted_chosen": -2.3670654296875, + "logps/weighted_rejected": -2.760937452316284, + "loss": 0.6923, + "rewards/accuracies": 0.34375, + "rewards/chosen": 0.12041015923023224, + "rewards/margins": 0.13857421278953552, + "rewards/rejected": -0.01816406287252903, + "rewards/weighted_accuracies": 0.4156250059604645, + "rewards/weighted_chosen": 0.0007911681896075606, + "rewards/weighted_margins": -0.00026035308837890625, + "rewards/weighted_rejected": 0.0010513305896893144, + "step": 40 + }, + { + "epoch": 0.02617115938236064, + "grad_norm": 17.478111267089844, + "learning_rate": 2.552083333333333e-07, + "logits/chosen": -0.2825515866279602, + "logits/rejected": -0.3209354281425476, + "logps/chosen": -280.23126220703125, + "logps/rejected": -267.45001220703125, + "logps/weighted_chosen": -2.329760789871216, + "logps/weighted_rejected": -2.414306640625, + "loss": 0.6877, + "rewards/accuracies": 0.30937498807907104, + "rewards/chosen": 0.01835937425494194, + "rewards/margins": -0.06035156175494194, + "rewards/rejected": 0.07871093600988388, + "rewards/weighted_accuracies": 0.41874998807907104, + "rewards/weighted_chosen": 0.0070404051803052425, + "rewards/weighted_margins": 0.00885009765625, + "rewards/weighted_rejected": -0.0018066406482830644, + "step": 50 + }, + { + "epoch": 0.031405391258832765, + "grad_norm": 39.04142761230469, + "learning_rate": 3.0729166666666665e-07, + "logits/chosen": -0.3157821595668793, + "logits/rejected": -0.30972975492477417, + "logps/chosen": -277.58123779296875, + "logps/rejected": -261.6187438964844, + "logps/weighted_chosen": -2.753100633621216, + "logps/weighted_rejected": -2.6282715797424316, + "loss": 0.6846, + "rewards/accuracies": 0.34687501192092896, + "rewards/chosen": 0.13593749701976776, + "rewards/margins": 0.02968749962747097, + "rewards/rejected": 0.10625000298023224, + "rewards/weighted_accuracies": 0.4937500059604645, + "rewards/weighted_chosen": 0.02093353308737278, + "rewards/weighted_margins": 0.015999604016542435, + "rewards/weighted_rejected": 0.0049346922896802425, + "step": 60 + }, + { + "epoch": 0.036639623135304895, + "grad_norm": 73.14978790283203, + "learning_rate": 3.59375e-07, + "logits/chosen": -0.32021790742874146, + "logits/rejected": -0.32699280977249146, + "logps/chosen": -289.6148376464844, + "logps/rejected": -244.8367156982422, + "logps/weighted_chosen": -2.221527099609375, + "logps/weighted_rejected": -2.581958055496216, + "loss": 0.6775, + "rewards/accuracies": 0.49687498807907104, + "rewards/chosen": 0.43046873807907104, + "rewards/margins": 0.5244140625, + "rewards/rejected": -0.09394530951976776, + "rewards/weighted_accuracies": 0.53125, + "rewards/weighted_chosen": 0.030600737780332565, + "rewards/weighted_margins": 0.034238435328006744, + "rewards/weighted_rejected": -0.0036373138427734375, + "step": 70 + }, + { + "epoch": 0.04187385501177702, + "grad_norm": 65.60453796386719, + "learning_rate": 4.114583333333333e-07, + "logits/chosen": -0.28860169649124146, + "logits/rejected": -0.3099655210971832, + "logps/chosen": -289.33984375, + "logps/rejected": -270.3453063964844, + "logps/weighted_chosen": -2.456127882003784, + "logps/weighted_rejected": -2.6986327171325684, + "loss": 0.6733, + "rewards/accuracies": 0.48124998807907104, + "rewards/chosen": 0.509765625, + "rewards/margins": 0.56396484375, + "rewards/rejected": -0.05419921875, + "rewards/weighted_accuracies": 0.5625, + "rewards/weighted_chosen": 0.04326324537396431, + "rewards/weighted_margins": 0.05183257907629013, + "rewards/weighted_rejected": -0.008570862002670765, + "step": 80 + }, + { + "epoch": 0.04710808688824915, + "grad_norm": 30.41583824157715, + "learning_rate": 4.6354166666666664e-07, + "logits/chosen": -0.3197769224643707, + "logits/rejected": -0.3126419186592102, + "logps/chosen": -280.0874938964844, + "logps/rejected": -257.95782470703125, + "logps/weighted_chosen": -2.6199097633361816, + "logps/weighted_rejected": -2.705517530441284, + "loss": 0.6743, + "rewards/accuracies": 0.4937500059604645, + "rewards/chosen": 0.5191406011581421, + "rewards/margins": 0.6358398199081421, + "rewards/rejected": -0.11669921875, + "rewards/weighted_accuracies": 0.5718749761581421, + "rewards/weighted_chosen": 0.07943420112133026, + "rewards/weighted_margins": 0.07568969577550888, + "rewards/weighted_rejected": 0.003753662109375, + "step": 90 + }, + { + "epoch": 0.05234231876472128, + "grad_norm": 61.700382232666016, + "learning_rate": 5.156249999999999e-07, + "logits/chosen": -0.2895751893520355, + "logits/rejected": -0.3621200621128082, + "logps/chosen": -290.88592529296875, + "logps/rejected": -286.73126220703125, + "logps/weighted_chosen": -2.083447217941284, + "logps/weighted_rejected": -2.6861205101013184, + "loss": 0.6862, + "rewards/accuracies": 0.5406249761581421, + "rewards/chosen": 0.10849609225988388, + "rewards/margins": 0.94482421875, + "rewards/rejected": -0.8363281488418579, + "rewards/weighted_accuracies": 0.574999988079071, + "rewards/weighted_chosen": 0.05786743015050888, + "rewards/weighted_margins": 0.058258056640625, + "rewards/weighted_rejected": -0.0002998351992573589, + "step": 100 + }, + { + "epoch": 0.05757655064119341, + "grad_norm": 33.45664978027344, + "learning_rate": 5.677083333333333e-07, + "logits/chosen": -0.3412017822265625, + "logits/rejected": -0.3312934935092926, + "logps/chosen": -296.8671875, + "logps/rejected": -262.3460998535156, + "logps/weighted_chosen": -2.776904344558716, + "logps/weighted_rejected": -2.8023438453674316, + "loss": 0.6835, + "rewards/accuracies": 0.546875, + "rewards/chosen": -0.4873046875, + "rewards/margins": 1.0051758289337158, + "rewards/rejected": -1.4924805164337158, + "rewards/weighted_accuracies": 0.5062500238418579, + "rewards/weighted_chosen": 0.01709899865090847, + "rewards/weighted_margins": 0.05614929273724556, + "rewards/weighted_rejected": -0.03909149020910263, + "step": 110 + }, + { + "epoch": 0.06281078251766553, + "grad_norm": 61.74055862426758, + "learning_rate": 6.197916666666666e-07, + "logits/chosen": -0.3482359051704407, + "logits/rejected": -0.3736562728881836, + "logps/chosen": -295.49530029296875, + "logps/rejected": -256.08282470703125, + "logps/weighted_chosen": -2.066760301589966, + "logps/weighted_rejected": -2.2858643531799316, + "loss": 0.6833, + "rewards/accuracies": 0.5687500238418579, + "rewards/chosen": -0.8194335699081421, + "rewards/margins": 1.502539038658142, + "rewards/rejected": -2.321972608566284, + "rewards/weighted_accuracies": 0.5874999761581421, + "rewards/weighted_chosen": 0.01521911658346653, + "rewards/weighted_margins": 0.05682678148150444, + "rewards/weighted_rejected": -0.04169006273150444, + "step": 120 + }, + { + "epoch": 0.06804501439413765, + "grad_norm": 45.78140640258789, + "learning_rate": 6.718749999999999e-07, + "logits/chosen": -0.3164505064487457, + "logits/rejected": -0.3121093809604645, + "logps/chosen": -306.4761657714844, + "logps/rejected": -279.87030029296875, + "logps/weighted_chosen": -2.1032347679138184, + "logps/weighted_rejected": -2.432788133621216, + "loss": 0.6718, + "rewards/accuracies": 0.6312500238418579, + "rewards/chosen": -0.4637207090854645, + "rewards/margins": 1.8840820789337158, + "rewards/rejected": -2.347851514816284, + "rewards/weighted_accuracies": 0.559374988079071, + "rewards/weighted_chosen": 0.01874847337603569, + "rewards/weighted_margins": 0.07195129245519638, + "rewards/weighted_rejected": -0.05319824069738388, + "step": 130 + }, + { + "epoch": 0.07327924627060979, + "grad_norm": 47.97172546386719, + "learning_rate": 7.239583333333333e-07, + "logits/chosen": -0.36130523681640625, + "logits/rejected": -0.3767889142036438, + "logps/chosen": -300.2398376464844, + "logps/rejected": -276.47344970703125, + "logps/weighted_chosen": -2.402172803878784, + "logps/weighted_rejected": -2.704345703125, + "loss": 0.6601, + "rewards/accuracies": 0.625, + "rewards/chosen": -1.6025390625, + "rewards/margins": 2.2777342796325684, + "rewards/rejected": -3.8802733421325684, + "rewards/weighted_accuracies": 0.628125011920929, + "rewards/weighted_chosen": 0.0066894530318677425, + "rewards/weighted_margins": 0.10413207858800888, + "rewards/weighted_rejected": -0.0973968505859375, + "step": 140 + }, + { + "epoch": 0.07851347814708191, + "grad_norm": 18.48399543762207, + "learning_rate": 7.760416666666666e-07, + "logits/chosen": -0.3260757327079773, + "logits/rejected": -0.33597564697265625, + "logps/chosen": -286.6578063964844, + "logps/rejected": -255.8078155517578, + "logps/weighted_chosen": -2.939697265625, + "logps/weighted_rejected": -2.9384522438049316, + "loss": 0.6693, + "rewards/accuracies": 0.6312500238418579, + "rewards/chosen": -2.329296827316284, + "rewards/margins": 2.532031297683716, + "rewards/rejected": -4.861328125, + "rewards/weighted_accuracies": 0.625, + "rewards/weighted_chosen": 0.01940460130572319, + "rewards/weighted_margins": 0.12819823622703552, + "rewards/weighted_rejected": -0.10869445651769638, + "step": 150 + }, + { + "epoch": 0.08374771002355404, + "grad_norm": 16.847576141357422, + "learning_rate": 8.28125e-07, + "logits/chosen": -0.37299805879592896, + "logits/rejected": -0.4207763671875, + "logps/chosen": -306.01873779296875, + "logps/rejected": -279.0289001464844, + "logps/weighted_chosen": -2.4432616233825684, + "logps/weighted_rejected": -2.4922118186950684, + "loss": 0.631, + "rewards/accuracies": 0.6468750238418579, + "rewards/chosen": -2.1587891578674316, + "rewards/margins": 3.69091796875, + "rewards/rejected": -5.849707126617432, + "rewards/weighted_accuracies": 0.637499988079071, + "rewards/weighted_chosen": 0.04796142503619194, + "rewards/weighted_margins": 0.21007385849952698, + "rewards/weighted_rejected": -0.1621856689453125, + "step": 160 + }, + { + "epoch": 0.08898194190002617, + "grad_norm": 237.514404296875, + "learning_rate": 8.802083333333333e-07, + "logits/chosen": -0.42098236083984375, + "logits/rejected": -0.4231323301792145, + "logps/chosen": -306.859375, + "logps/rejected": -266.03125, + "logps/weighted_chosen": -2.6180663108825684, + "logps/weighted_rejected": -2.9256348609924316, + "loss": 0.709, + "rewards/accuracies": 0.6343749761581421, + "rewards/chosen": -3.73828125, + "rewards/margins": 4.098242282867432, + "rewards/rejected": -7.836328029632568, + "rewards/weighted_accuracies": 0.6031249761581421, + "rewards/weighted_chosen": 0.06289978325366974, + "rewards/weighted_margins": 0.186981201171875, + "rewards/weighted_rejected": -0.12393493950366974, + "step": 170 + }, + { + "epoch": 0.0942161737764983, + "grad_norm": 52.46952819824219, + "learning_rate": 9.322916666666666e-07, + "logits/chosen": -0.38860780000686646, + "logits/rejected": -0.40771445631980896, + "logps/chosen": -280.2789001464844, + "logps/rejected": -267.69219970703125, + "logps/weighted_chosen": -2.579449415206909, + "logps/weighted_rejected": -3.0037841796875, + "loss": 0.6853, + "rewards/accuracies": 0.6343749761581421, + "rewards/chosen": -6.609179496765137, + "rewards/margins": 4.819726467132568, + "rewards/rejected": -11.427831649780273, + "rewards/weighted_accuracies": 0.6031249761581421, + "rewards/weighted_chosen": -0.04149780422449112, + "rewards/weighted_margins": 0.20274047553539276, + "rewards/weighted_rejected": -0.24451598525047302, + "step": 180 + }, + { + "epoch": 0.09945040565297043, + "grad_norm": 37.741477966308594, + "learning_rate": 9.84375e-07, + "logits/chosen": -0.4061637818813324, + "logits/rejected": -0.4410812258720398, + "logps/chosen": -314.60626220703125, + "logps/rejected": -278.87811279296875, + "logps/weighted_chosen": -2.378369092941284, + "logps/weighted_rejected": -2.7929444313049316, + "loss": 0.6517, + "rewards/accuracies": 0.625, + "rewards/chosen": -8.988476753234863, + "rewards/margins": 6.061327934265137, + "rewards/rejected": -15.050390243530273, + "rewards/weighted_accuracies": 0.621874988079071, + "rewards/weighted_chosen": -0.11425475776195526, + "rewards/weighted_margins": 0.22973021864891052, + "rewards/weighted_rejected": -0.3441314697265625, + "step": 190 + }, + { + "epoch": 0.10468463752944256, + "grad_norm": 76.11390686035156, + "learning_rate": 9.99959085414323e-07, + "logits/chosen": -0.4347488284111023, + "logits/rejected": -0.46932679414749146, + "logps/chosen": -319.34686279296875, + "logps/rejected": -274.1890563964844, + "logps/weighted_chosen": -2.6759276390075684, + "logps/weighted_rejected": -3.110583543777466, + "loss": 0.6539, + "rewards/accuracies": 0.6312500238418579, + "rewards/chosen": -10.064160346984863, + "rewards/margins": 6.332421779632568, + "rewards/rejected": -16.395898818969727, + "rewards/weighted_accuracies": 0.612500011920929, + "rewards/weighted_chosen": -0.08293457329273224, + "rewards/weighted_margins": 0.25919800996780396, + "rewards/weighted_rejected": -0.34211426973342896, + "step": 200 + }, + { + "epoch": 0.10991886940591468, + "grad_norm": 19.709537506103516, + "learning_rate": 9.997587035630105e-07, + "logits/chosen": -0.4373016357421875, + "logits/rejected": -0.47842711210250854, + "logps/chosen": -298.6578063964844, + "logps/rejected": -305.07733154296875, + "logps/weighted_chosen": -2.4120116233825684, + "logps/weighted_rejected": -3.137524366378784, + "loss": 0.6448, + "rewards/accuracies": 0.6656249761581421, + "rewards/chosen": -11.547070503234863, + "rewards/margins": 8.876855850219727, + "rewards/rejected": -20.425390243530273, + "rewards/weighted_accuracies": 0.659375011920929, + "rewards/weighted_chosen": -0.12418060004711151, + "rewards/weighted_margins": 0.24833527207374573, + "rewards/weighted_rejected": -0.37247925996780396, + "step": 210 + }, + { + "epoch": 0.11515310128238682, + "grad_norm": 39.1947135925293, + "learning_rate": 9.99391406364405e-07, + "logits/chosen": -0.424050897359848, + "logits/rejected": -0.4263656735420227, + "logps/chosen": -306.5453186035156, + "logps/rejected": -291.21405029296875, + "logps/weighted_chosen": -2.8793702125549316, + "logps/weighted_rejected": -3.2673583030700684, + "loss": 0.6969, + "rewards/accuracies": 0.612500011920929, + "rewards/chosen": -14.446874618530273, + "rewards/margins": 7.897851467132568, + "rewards/rejected": -22.343358993530273, + "rewards/weighted_accuracies": 0.606249988079071, + "rewards/weighted_chosen": -0.2553466856479645, + "rewards/weighted_margins": 0.21260376274585724, + "rewards/weighted_rejected": -0.46800535917282104, + "step": 220 + }, + { + "epoch": 0.12038733315885894, + "grad_norm": 437.028564453125, + "learning_rate": 9.988573164927884e-07, + "logits/chosen": -0.3824310302734375, + "logits/rejected": -0.4174056947231293, + "logps/chosen": -282.2710876464844, + "logps/rejected": -277.2734375, + "logps/weighted_chosen": -2.547900438308716, + "logps/weighted_rejected": -2.85693359375, + "loss": 0.7367, + "rewards/accuracies": 0.675000011920929, + "rewards/chosen": -13.438867568969727, + "rewards/margins": 12.128320693969727, + "rewards/rejected": -25.565820693969727, + "rewards/weighted_accuracies": 0.621874988079071, + "rewards/weighted_chosen": -0.24434813857078552, + "rewards/weighted_margins": 0.2164306640625, + "rewards/weighted_rejected": -0.4607299864292145, + "step": 230 + }, + { + "epoch": 0.12562156503533106, + "grad_norm": 139.88975524902344, + "learning_rate": 9.98156612329838e-07, + "logits/chosen": -0.4804244935512543, + "logits/rejected": -0.527056872844696, + "logps/chosen": -279.6773376464844, + "logps/rejected": -310.64532470703125, + "logps/weighted_chosen": -2.464794874191284, + "logps/weighted_rejected": -3.058520555496216, + "loss": 0.6735, + "rewards/accuracies": 0.637499988079071, + "rewards/chosen": -14.966699600219727, + "rewards/margins": 13.450976371765137, + "rewards/rejected": -28.419336318969727, + "rewards/weighted_accuracies": 0.6625000238418579, + "rewards/weighted_chosen": -0.11341552436351776, + "rewards/weighted_margins": 0.26569825410842896, + "rewards/weighted_rejected": -0.37919312715530396, + "step": 240 + }, + { + "epoch": 0.13085579691180318, + "grad_norm": 939.5078125, + "learning_rate": 9.97289527905053e-07, + "logits/chosen": -0.4899856448173523, + "logits/rejected": -0.4979141354560852, + "logps/chosen": -281.9039001464844, + "logps/rejected": -282.93438720703125, + "logps/weighted_chosen": -2.8607420921325684, + "logps/weighted_rejected": -3.0235595703125, + "loss": 0.7231, + "rewards/accuracies": 0.6343749761581421, + "rewards/chosen": -17.384668350219727, + "rewards/margins": 9.600194931030273, + "rewards/rejected": -26.986328125, + "rewards/weighted_accuracies": 0.5843750238418579, + "rewards/weighted_chosen": -0.20379944145679474, + "rewards/weighted_margins": 0.18174438178539276, + "rewards/weighted_rejected": -0.3856750428676605, + "step": 250 + }, + { + "epoch": 0.1360900287882753, + "grad_norm": 24.300647735595703, + "learning_rate": 9.962563528175875e-07, + "logits/chosen": -0.4584365785121918, + "logits/rejected": -0.4911254942417145, + "logps/chosen": -317.06329345703125, + "logps/rejected": -289.06561279296875, + "logps/weighted_chosen": -2.4532713890075684, + "logps/weighted_rejected": -3.330212354660034, + "loss": 0.6636, + "rewards/accuracies": 0.590624988079071, + "rewards/chosen": -18.153711318969727, + "rewards/margins": 10.150195121765137, + "rewards/rejected": -28.3046875, + "rewards/weighted_accuracies": 0.6187499761581421, + "rewards/weighted_chosen": -0.18357238173484802, + "rewards/weighted_margins": 0.269927978515625, + "rewards/weighted_rejected": -0.4535202085971832, + "step": 260 + }, + { + "epoch": 0.14132426066474746, + "grad_norm": 228.46092224121094, + "learning_rate": 9.950574321395277e-07, + "logits/chosen": -0.4871993958950043, + "logits/rejected": -0.5071777105331421, + "logps/chosen": -310.2124938964844, + "logps/rejected": -291.5687561035156, + "logps/weighted_chosen": -2.747607469558716, + "logps/weighted_rejected": -3.0499024391174316, + "loss": 0.6525, + "rewards/accuracies": 0.6156250238418579, + "rewards/chosen": -20.7822265625, + "rewards/margins": 7.598730564117432, + "rewards/rejected": -28.382030487060547, + "rewards/weighted_accuracies": 0.6499999761581421, + "rewards/weighted_chosen": -0.2510986328125, + "rewards/weighted_margins": 0.2596893310546875, + "rewards/weighted_rejected": -0.5105804204940796, + "step": 270 + }, + { + "epoch": 0.14655849254121958, + "grad_norm": 713.1409912109375, + "learning_rate": 9.936931663006413e-07, + "logits/chosen": -0.4856887757778168, + "logits/rejected": -0.4791274964809418, + "logps/chosen": -323.875, + "logps/rejected": -312.1109313964844, + "logps/weighted_chosen": -2.7660155296325684, + "logps/weighted_rejected": -3.293591260910034, + "loss": 0.6155, + "rewards/accuracies": 0.671875, + "rewards/chosen": -20.981639862060547, + "rewards/margins": 11.869140625, + "rewards/rejected": -32.850975036621094, + "rewards/weighted_accuracies": 0.675000011920929, + "rewards/weighted_chosen": -0.13939818739891052, + "rewards/weighted_margins": 0.34244996309280396, + "rewards/weighted_rejected": -0.48178404569625854, + "step": 280 + }, + { + "epoch": 0.1517927244176917, + "grad_norm": 10845.4873046875, + "learning_rate": 9.921640109546357e-07, + "logits/chosen": -0.433615118265152, + "logits/rejected": -0.5038871765136719, + "logps/chosen": -285.6937561035156, + "logps/rejected": -280.76251220703125, + "logps/weighted_chosen": -2.63427734375, + "logps/weighted_rejected": -3.711669921875, + "loss": 0.65, + "rewards/accuracies": 0.6625000238418579, + "rewards/chosen": -18.829492568969727, + "rewards/margins": 10.345703125, + "rewards/rejected": -29.1728515625, + "rewards/weighted_accuracies": 0.6187499761581421, + "rewards/weighted_chosen": -0.12302856147289276, + "rewards/weighted_margins": 0.3319152891635895, + "rewards/weighted_rejected": -0.45494383573532104, + "step": 290 + }, + { + "epoch": 0.15702695629416383, + "grad_norm": 47.70283889770508, + "learning_rate": 9.90470476826975e-07, + "logits/chosen": -0.4355606138706207, + "logits/rejected": -0.4278717041015625, + "logps/chosen": -288.78045654296875, + "logps/rejected": -296.9765625, + "logps/weighted_chosen": -2.532849073410034, + "logps/weighted_rejected": -3.0221924781799316, + "loss": 0.6674, + "rewards/accuracies": 0.6625000238418579, + "rewards/chosen": -19.346094131469727, + "rewards/margins": 10.255078315734863, + "rewards/rejected": -29.59765625, + "rewards/weighted_accuracies": 0.6187499761581421, + "rewards/weighted_chosen": -0.21412047743797302, + "rewards/weighted_margins": 0.2544006407260895, + "rewards/weighted_rejected": -0.4681999087333679, + "step": 300 + }, + { + "epoch": 0.16226118817063595, + "grad_norm": 644.2051391601562, + "learning_rate": 9.886131295443002e-07, + "logits/chosen": -0.462362676858902, + "logits/rejected": -0.5182906985282898, + "logps/chosen": -301.2421875, + "logps/rejected": -280.125, + "logps/weighted_chosen": -2.5293211936950684, + "logps/weighted_rejected": -2.9417481422424316, + "loss": 0.6339, + "rewards/accuracies": 0.668749988079071, + "rewards/chosen": -19.940235137939453, + "rewards/margins": 9.952539443969727, + "rewards/rejected": -29.892187118530273, + "rewards/weighted_accuracies": 0.65625, + "rewards/weighted_chosen": 0.0126800537109375, + "rewards/weighted_margins": 0.4334716796875, + "rewards/weighted_rejected": -0.42060548067092896, + "step": 310 + }, + { + "epoch": 0.16749542004710807, + "grad_norm": 42.43592834472656, + "learning_rate": 9.865925894455166e-07, + "logits/chosen": -0.538470447063446, + "logits/rejected": -0.5473419427871704, + "logps/chosen": -323.84686279296875, + "logps/rejected": -290.7406311035156, + "logps/weighted_chosen": -2.8351807594299316, + "logps/weighted_rejected": -3.2470703125, + "loss": 0.6762, + "rewards/accuracies": 0.637499988079071, + "rewards/chosen": -23.906444549560547, + "rewards/margins": 9.430078506469727, + "rewards/rejected": -33.3359375, + "rewards/weighted_accuracies": 0.6187499761581421, + "rewards/weighted_chosen": -0.23797301948070526, + "rewards/weighted_margins": 0.272064208984375, + "rewards/weighted_rejected": -0.5102294683456421, + "step": 320 + }, + { + "epoch": 0.17272965192358022, + "grad_norm": 46.229000091552734, + "learning_rate": 9.84409531374603e-07, + "logits/chosen": -0.5096954107284546, + "logits/rejected": -0.4907272458076477, + "logps/chosen": -332.18280029296875, + "logps/rejected": -298.5718688964844, + "logps/weighted_chosen": -2.775341749191284, + "logps/weighted_rejected": -3.165026903152466, + "loss": 0.6741, + "rewards/accuracies": 0.637499988079071, + "rewards/chosen": -27.408203125, + "rewards/margins": 8.212109565734863, + "rewards/rejected": -35.61640548706055, + "rewards/weighted_accuracies": 0.6312500238418579, + "rewards/weighted_chosen": -0.17764969170093536, + "rewards/weighted_margins": 0.241455078125, + "rewards/weighted_rejected": -0.41897353529930115, + "step": 330 + }, + { + "epoch": 0.17796388380005235, + "grad_norm": 70.134521484375, + "learning_rate": 9.820646844552219e-07, + "logits/chosen": -0.5079803466796875, + "logits/rejected": -0.5622657537460327, + "logps/chosen": -301.3257751464844, + "logps/rejected": -303.1468811035156, + "logps/weighted_chosen": -2.852612257003784, + "logps/weighted_rejected": -3.0445556640625, + "loss": 0.6485, + "rewards/accuracies": 0.6968749761581421, + "rewards/chosen": -24.6875, + "rewards/margins": 12.933984756469727, + "rewards/rejected": -37.61992263793945, + "rewards/weighted_accuracies": 0.65625, + "rewards/weighted_chosen": -0.19311293959617615, + "rewards/weighted_margins": 0.3020080626010895, + "rewards/weighted_rejected": -0.4951171875, + "step": 340 + }, + { + "epoch": 0.18319811567652447, + "grad_norm": 37.5682373046875, + "learning_rate": 9.795588318471964e-07, + "logits/chosen": -0.5787566900253296, + "logits/rejected": -0.5869846343994141, + "logps/chosen": -283.0796813964844, + "logps/rejected": -310.00469970703125, + "logps/weighted_chosen": -2.5658936500549316, + "logps/weighted_rejected": -2.95947265625, + "loss": 0.6307, + "rewards/accuracies": 0.625, + "rewards/chosen": -23.71875, + "rewards/margins": 9.896288871765137, + "rewards/rejected": -33.61249923706055, + "rewards/weighted_accuracies": 0.6468750238418579, + "rewards/weighted_chosen": -0.1531631499528885, + "rewards/weighted_margins": 0.32664793729782104, + "rewards/weighted_rejected": -0.479653924703598, + "step": 350 + }, + { + "epoch": 0.1884323475529966, + "grad_norm": 145.69015502929688, + "learning_rate": 9.768928104849415e-07, + "logits/chosen": -0.6053832769393921, + "logits/rejected": -0.6036437749862671, + "logps/chosen": -306.9140625, + "logps/rejected": -283.77655029296875, + "logps/weighted_chosen": -2.835888624191284, + "logps/weighted_rejected": -2.9885010719299316, + "loss": 0.6741, + "rewards/accuracies": 0.612500011920929, + "rewards/chosen": -24.237499237060547, + "rewards/margins": 10.624218940734863, + "rewards/rejected": -34.85859298706055, + "rewards/weighted_accuracies": 0.640625, + "rewards/weighted_chosen": -0.1663818359375, + "rewards/weighted_margins": 0.3080078065395355, + "rewards/weighted_rejected": -0.4744934141635895, + "step": 360 + }, + { + "epoch": 0.19366657942946872, + "grad_norm": 1347.0242919921875, + "learning_rate": 9.740675107979355e-07, + "logits/chosen": -0.5699676275253296, + "logits/rejected": -0.5878998041152954, + "logps/chosen": -342.36248779296875, + "logps/rejected": -311.7203063964844, + "logps/weighted_chosen": -2.303784132003784, + "logps/weighted_rejected": -3.164013624191284, + "loss": 0.6624, + "rewards/accuracies": 0.6312500238418579, + "rewards/chosen": -27.253124237060547, + "rewards/margins": 9.823046684265137, + "rewards/rejected": -37.07597732543945, + "rewards/weighted_accuracies": 0.643750011920929, + "rewards/weighted_chosen": -0.24745483696460724, + "rewards/weighted_margins": 0.27247315645217896, + "rewards/weighted_rejected": -0.5200088620185852, + "step": 370 + }, + { + "epoch": 0.19890081130594087, + "grad_norm": 1152.541748046875, + "learning_rate": 9.71083876413323e-07, + "logits/chosen": -0.5426742434501648, + "logits/rejected": -0.5510879755020142, + "logps/chosen": -331.25390625, + "logps/rejected": -310.33123779296875, + "logps/weighted_chosen": -2.4026856422424316, + "logps/weighted_rejected": -3.172229051589966, + "loss": 0.6676, + "rewards/accuracies": 0.621874988079071, + "rewards/chosen": -28.869922637939453, + "rewards/margins": 11.865234375, + "rewards/rejected": -40.73320388793945, + "rewards/weighted_accuracies": 0.6187499761581421, + "rewards/weighted_chosen": -0.24112549424171448, + "rewards/weighted_margins": 0.2662292420864105, + "rewards/weighted_rejected": -0.5070465207099915, + "step": 380 + }, + { + "epoch": 0.204135043182413, + "grad_norm": 69.06751251220703, + "learning_rate": 9.67942903840751e-07, + "logits/chosen": -0.5844222903251648, + "logits/rejected": -0.6357940435409546, + "logps/chosen": -331.53436279296875, + "logps/rejected": -316.50469970703125, + "logps/weighted_chosen": -2.523181200027466, + "logps/weighted_rejected": -3.170581102371216, + "loss": 0.6281, + "rewards/accuracies": 0.659375011920929, + "rewards/chosen": -27.312108993530273, + "rewards/margins": 14.989062309265137, + "rewards/rejected": -42.309181213378906, + "rewards/weighted_accuracies": 0.675000011920929, + "rewards/weighted_chosen": -0.17550353705883026, + "rewards/weighted_margins": 0.357177734375, + "rewards/weighted_rejected": -0.532818615436554, + "step": 390 + }, + { + "epoch": 0.2093692750588851, + "grad_norm": 64.58200073242188, + "learning_rate": 9.646456421395447e-07, + "logits/chosen": -0.573455810546875, + "logits/rejected": -0.5838836431503296, + "logps/chosen": -348.1484375, + "logps/rejected": -349.8687438964844, + "logps/weighted_chosen": -2.479809522628784, + "logps/weighted_rejected": -3.226489305496216, + "loss": 0.6551, + "rewards/accuracies": 0.65625, + "rewards/chosen": -29.957422256469727, + "rewards/margins": 16.478321075439453, + "rewards/rejected": -46.43476486206055, + "rewards/weighted_accuracies": 0.640625, + "rewards/weighted_chosen": -0.203724667429924, + "rewards/weighted_margins": 0.254974365234375, + "rewards/weighted_rejected": -0.4586502015590668, + "step": 400 + }, + { + "epoch": 0.21460350693535724, + "grad_norm": 19.509164810180664, + "learning_rate": 9.611931925683266e-07, + "logits/chosen": -0.5067977905273438, + "logits/rejected": -0.5407257080078125, + "logps/chosen": -337.97967529296875, + "logps/rejected": -311.12811279296875, + "logps/weighted_chosen": -2.369091749191284, + "logps/weighted_rejected": -2.994799852371216, + "loss": 0.5919, + "rewards/accuracies": 0.6656249761581421, + "rewards/chosen": -31.741016387939453, + "rewards/margins": 15.541796684265137, + "rewards/rejected": -47.293357849121094, + "rewards/weighted_accuracies": 0.6937500238418579, + "rewards/weighted_chosen": -0.17744140326976776, + "rewards/weighted_margins": 0.386505126953125, + "rewards/weighted_rejected": -0.563507080078125, + "step": 410 + }, + { + "epoch": 0.21983773881182936, + "grad_norm": 29.50520133972168, + "learning_rate": 9.575867082172085e-07, + "logits/chosen": -0.5286194086074829, + "logits/rejected": -0.5688308477401733, + "logps/chosen": -344.96563720703125, + "logps/rejected": -328.64532470703125, + "logps/weighted_chosen": -2.8730225563049316, + "logps/weighted_rejected": -2.930432081222534, + "loss": 0.6442, + "rewards/accuracies": 0.675000011920929, + "rewards/chosen": -40.091796875, + "rewards/margins": 18.596485137939453, + "rewards/rejected": -58.685935974121094, + "rewards/weighted_accuracies": 0.628125011920929, + "rewards/weighted_chosen": -0.38405150175094604, + "rewards/weighted_margins": 0.39207762479782104, + "rewards/weighted_rejected": -0.7763046026229858, + "step": 420 + }, + { + "epoch": 0.22507197068830148, + "grad_norm": 15.081392288208008, + "learning_rate": 9.538273936226673e-07, + "logits/chosen": -0.5923309326171875, + "logits/rejected": -0.625653088092804, + "logps/chosen": -301.640625, + "logps/rejected": -313.77032470703125, + "logps/weighted_chosen": -3.0785889625549316, + "logps/weighted_rejected": -3.5872559547424316, + "loss": 0.668, + "rewards/accuracies": 0.628125011920929, + "rewards/chosen": -36.12675857543945, + "rewards/margins": 13.111328125, + "rewards/rejected": -49.236328125, + "rewards/weighted_accuracies": 0.6312500238418579, + "rewards/weighted_chosen": -0.28452759981155396, + "rewards/weighted_margins": 0.3635620176792145, + "rewards/weighted_rejected": -0.64788818359375, + "step": 430 + }, + { + "epoch": 0.23030620256477363, + "grad_norm": 23.0412540435791, + "learning_rate": 9.499165043652391e-07, + "logits/chosen": -0.5760772824287415, + "logits/rejected": -0.5774017572402954, + "logps/chosen": -328.1015625, + "logps/rejected": -318.84454345703125, + "logps/weighted_chosen": -3.0999755859375, + "logps/weighted_rejected": -3.371142625808716, + "loss": 0.6452, + "rewards/accuracies": 0.640625, + "rewards/chosen": -36.97431564331055, + "rewards/margins": 15.057812690734863, + "rewards/rejected": -52.0390625, + "rewards/weighted_accuracies": 0.628125011920929, + "rewards/weighted_chosen": -0.39061737060546875, + "rewards/weighted_margins": 0.3595825135707855, + "rewards/weighted_rejected": -0.7500244379043579, + "step": 440 + }, + { + "epoch": 0.23554043444124576, + "grad_norm": 22.85993003845215, + "learning_rate": 9.458553466501665e-07, + "logits/chosen": -0.6301513910293579, + "logits/rejected": -0.6610687375068665, + "logps/chosen": -324.77032470703125, + "logps/rejected": -298.57501220703125, + "logps/weighted_chosen": -3.1078124046325684, + "logps/weighted_rejected": -3.38037109375, + "loss": 0.6501, + "rewards/accuracies": 0.640625, + "rewards/chosen": -38.617774963378906, + "rewards/margins": 16.141407012939453, + "rewards/rejected": -54.763671875, + "rewards/weighted_accuracies": 0.653124988079071, + "rewards/weighted_chosen": -0.4693542420864105, + "rewards/weighted_margins": 0.4438629150390625, + "rewards/weighted_rejected": -0.9127838015556335, + "step": 450 + }, + { + "epoch": 0.24077466631771788, + "grad_norm": 11.338366508483887, + "learning_rate": 9.416452768711366e-07, + "logits/chosen": -0.6437957882881165, + "logits/rejected": -0.674633800983429, + "logps/chosen": -333.87188720703125, + "logps/rejected": -318.10467529296875, + "logps/weighted_chosen": -2.8603515625, + "logps/weighted_rejected": -3.472119092941284, + "loss": 0.6881, + "rewards/accuracies": 0.6468750238418579, + "rewards/chosen": -41.862693786621094, + "rewards/margins": 16.437694549560547, + "rewards/rejected": -58.305076599121094, + "rewards/weighted_accuracies": 0.653124988079071, + "rewards/weighted_chosen": -0.43403321504592896, + "rewards/weighted_margins": 0.4345336854457855, + "rewards/weighted_rejected": -0.8688415288925171, + "step": 460 + }, + { + "epoch": 0.24600889819419, + "grad_norm": 35.14228057861328, + "learning_rate": 9.372877011572557e-07, + "logits/chosen": -0.5738860964775085, + "logits/rejected": -0.5953949093818665, + "logps/chosen": -350.23046875, + "logps/rejected": -329.484375, + "logps/weighted_chosen": -2.7630372047424316, + "logps/weighted_rejected": -3.2092041969299316, + "loss": 0.6424, + "rewards/accuracies": 0.6187499761581421, + "rewards/chosen": -39.640037536621094, + "rewards/margins": 15.155468940734863, + "rewards/rejected": -54.796485900878906, + "rewards/weighted_accuracies": 0.671875, + "rewards/weighted_chosen": -0.338470458984375, + "rewards/weighted_margins": 0.4430099427700043, + "rewards/weighted_rejected": -0.781768798828125, + "step": 470 + }, + { + "epoch": 0.2512431300706621, + "grad_norm": 55.78861618041992, + "learning_rate": 9.327840749034141e-07, + "logits/chosen": -0.6301849484443665, + "logits/rejected": -0.6710245013237, + "logps/chosen": -324.8578186035156, + "logps/rejected": -336.734375, + "logps/weighted_chosen": -2.5625243186950684, + "logps/weighted_rejected": -3.774975538253784, + "loss": 0.636, + "rewards/accuracies": 0.668749988079071, + "rewards/chosen": -37.658203125, + "rewards/margins": 22.687694549560547, + "rewards/rejected": -60.357421875, + "rewards/weighted_accuracies": 0.6812499761581421, + "rewards/weighted_chosen": -0.2594970762729645, + "rewards/weighted_margins": 0.48378294706344604, + "rewards/weighted_rejected": -0.7435302734375, + "step": 480 + }, + { + "epoch": 0.2564773619471343, + "grad_norm": 38.52030563354492, + "learning_rate": 9.281359022841965e-07, + "logits/chosen": -0.5341835021972656, + "logits/rejected": -0.550585925579071, + "logps/chosen": -320.76171875, + "logps/rejected": -314.70391845703125, + "logps/weighted_chosen": -2.91943359375, + "logps/weighted_rejected": -4.169653415679932, + "loss": 0.6375, + "rewards/accuracies": 0.653124988079071, + "rewards/chosen": -45.831443786621094, + "rewards/margins": 24.026952743530273, + "rewards/rejected": -69.88359069824219, + "rewards/weighted_accuracies": 0.668749988079071, + "rewards/weighted_chosen": -0.516644299030304, + "rewards/weighted_margins": 0.518634021282196, + "rewards/weighted_rejected": -1.0354125499725342, + "step": 490 + }, + { + "epoch": 0.26171159382360637, + "grad_norm": 15.318764686584473, + "learning_rate": 9.233447357514989e-07, + "logits/chosen": -0.5592590570449829, + "logits/rejected": -0.6022475957870483, + "logps/chosen": -347.77423095703125, + "logps/rejected": -342.21875, + "logps/weighted_chosen": -3.2605223655700684, + "logps/weighted_rejected": -3.667773485183716, + "loss": 0.6494, + "rewards/accuracies": 0.659375011920929, + "rewards/chosen": -49.72968673706055, + "rewards/margins": 22.665430068969727, + "rewards/rejected": -72.4097671508789, + "rewards/weighted_accuracies": 0.65625, + "rewards/weighted_chosen": -0.4633804261684418, + "rewards/weighted_margins": 0.527294933795929, + "rewards/weighted_rejected": -0.990936279296875, + "step": 500 + }, + { + "epoch": 0.26171159382360637, + "eval_logits/chosen": -0.6649160385131836, + "eval_logits/rejected": -0.682785153388977, + "eval_logps/chosen": -345.551513671875, + "eval_logps/rejected": -345.9989929199219, + "eval_logps/weighted_chosen": -2.992426872253418, + "eval_logps/weighted_rejected": -3.637266159057617, + "eval_loss": 0.6663314700126648, + "eval_rewards/accuracies": 0.6305000185966492, + "eval_rewards/chosen": -56.88743591308594, + "eval_rewards/margins": 21.448062896728516, + "eval_rewards/rejected": -78.32637786865234, + "eval_rewards/weighted_accuracies": 0.6480000019073486, + "eval_rewards/weighted_chosen": -0.5315031409263611, + "eval_rewards/weighted_margins": 0.43671876192092896, + "eval_rewards/weighted_rejected": -0.9682218432426453, + "eval_runtime": 1455.1048, + "eval_samples_per_second": 1.374, + "eval_steps_per_second": 0.344, + "step": 500 + }, + { + "epoch": 0.2669458257000785, + "grad_norm": 51.472145080566406, + "learning_rate": 9.184121755160232e-07, + "logits/chosen": -0.659375011920929, + "logits/rejected": -0.689471423625946, + "logps/chosen": -355.8125, + "logps/rejected": -371.6640625, + "logps/weighted_chosen": -3.25238037109375, + "logps/weighted_rejected": -3.708740234375, + "loss": 0.6929, + "rewards/accuracies": 0.6499999761581421, + "rewards/chosen": -54.556640625, + "rewards/margins": 28.4453125, + "rewards/rejected": -83.0054702758789, + "rewards/weighted_accuracies": 0.6625000238418579, + "rewards/weighted_chosen": -0.532073974609375, + "rewards/weighted_margins": 0.402008056640625, + "rewards/weighted_rejected": -0.934326171875, + "step": 510 + }, + { + "epoch": 0.2721800575765506, + "grad_norm": 39.522377014160156, + "learning_rate": 9.133398690128193e-07, + "logits/chosen": -0.668170154094696, + "logits/rejected": -0.691680908203125, + "logps/chosen": -380.31561279296875, + "logps/rejected": -371.16094970703125, + "logps/weighted_chosen": -2.9228272438049316, + "logps/weighted_rejected": -3.671313524246216, + "loss": 0.6462, + "rewards/accuracies": 0.6468750238418579, + "rewards/chosen": -58.849220275878906, + "rewards/margins": 31.808202743530273, + "rewards/rejected": -90.65234375, + "rewards/weighted_accuracies": 0.7281249761581421, + "rewards/weighted_chosen": -0.3155883848667145, + "rewards/weighted_margins": 0.47456055879592896, + "rewards/weighted_rejected": -0.790509045124054, + "step": 520 + }, + { + "epoch": 0.27741428945302277, + "grad_norm": 40.427040100097656, + "learning_rate": 9.081295103510554e-07, + "logits/chosen": -0.5946930050849915, + "logits/rejected": -0.64569091796875, + "logps/chosen": -355.3265686035156, + "logps/rejected": -368.6781311035156, + "logps/weighted_chosen": -2.624804735183716, + "logps/weighted_rejected": -3.721435546875, + "loss": 0.5869, + "rewards/accuracies": 0.640625, + "rewards/chosen": -71.3091812133789, + "rewards/margins": 27.795703887939453, + "rewards/rejected": -99.08203125, + "rewards/weighted_accuracies": 0.6812499761581421, + "rewards/weighted_chosen": -0.41926270723342896, + "rewards/weighted_margins": 0.5740417242050171, + "rewards/weighted_rejected": -0.993090808391571, + "step": 530 + }, + { + "epoch": 0.2826485213294949, + "grad_norm": 21.890594482421875, + "learning_rate": 9.027828397481989e-07, + "logits/chosen": -0.5646041631698608, + "logits/rejected": -0.5952346920967102, + "logps/chosen": -338.10467529296875, + "logps/rejected": -359.58282470703125, + "logps/weighted_chosen": -3.3427734375, + "logps/weighted_rejected": -4.061425685882568, + "loss": 0.6384, + "rewards/accuracies": 0.6656249761581421, + "rewards/chosen": -77.6187515258789, + "rewards/margins": 26.623828887939453, + "rewards/rejected": -104.2367172241211, + "rewards/weighted_accuracies": 0.65625, + "rewards/weighted_chosen": -0.63751220703125, + "rewards/weighted_margins": 0.47407835721969604, + "rewards/weighted_rejected": -1.1118652820587158, + "step": 540 + }, + { + "epoch": 0.287882753205967, + "grad_norm": 28.308740615844727, + "learning_rate": 8.973016429487988e-07, + "logits/chosen": -0.6230270266532898, + "logits/rejected": -0.630328357219696, + "logps/chosen": -362.5726623535156, + "logps/rejected": -369.64373779296875, + "logps/weighted_chosen": -3.282421827316284, + "logps/weighted_rejected": -3.598876953125, + "loss": 0.6423, + "rewards/accuracies": 0.675000011920929, + "rewards/chosen": -80.73359680175781, + "rewards/margins": 34.60234451293945, + "rewards/rejected": -115.34687805175781, + "rewards/weighted_accuracies": 0.684374988079071, + "rewards/weighted_chosen": -0.597552478313446, + "rewards/weighted_margins": 0.46974486112594604, + "rewards/weighted_rejected": -1.067834496498108, + "step": 550 + }, + { + "epoch": 0.29311698508243916, + "grad_norm": 108.37396240234375, + "learning_rate": 8.916877506280601e-07, + "logits/chosen": -0.6662933230400085, + "logits/rejected": -0.657055675983429, + "logps/chosen": -369.0171813964844, + "logps/rejected": -373.078125, + "logps/weighted_chosen": -3.2555909156799316, + "logps/weighted_rejected": -3.583251953125, + "loss": 0.6414, + "rewards/accuracies": 0.675000011920929, + "rewards/chosen": -88.1117172241211, + "rewards/margins": 30.770702362060547, + "rewards/rejected": -118.8863296508789, + "rewards/weighted_accuracies": 0.684374988079071, + "rewards/weighted_chosen": -0.57525634765625, + "rewards/weighted_margins": 0.5091766119003296, + "rewards/weighted_rejected": -1.084588646888733, + "step": 560 + }, + { + "epoch": 0.29835121695891126, + "grad_norm": 20.634323120117188, + "learning_rate": 8.85943037780415e-07, + "logits/chosen": -0.7054427862167358, + "logits/rejected": -0.7076568603515625, + "logps/chosen": -373.78125, + "logps/rejected": -348.30780029296875, + "logps/weighted_chosen": -3.1310057640075684, + "logps/weighted_rejected": -3.516772508621216, + "loss": 0.624, + "rewards/accuracies": 0.590624988079071, + "rewards/chosen": -87.689453125, + "rewards/margins": 18.8154296875, + "rewards/rejected": -106.50468444824219, + "rewards/weighted_accuracies": 0.6781250238418579, + "rewards/weighted_chosen": -0.5498199462890625, + "rewards/weighted_margins": 0.480499267578125, + "rewards/weighted_rejected": -1.030615210533142, + "step": 570 + }, + { + "epoch": 0.3035854488353834, + "grad_norm": 19.36369514465332, + "learning_rate": 8.800694230932884e-07, + "logits/chosen": -0.6282256841659546, + "logits/rejected": -0.6369781494140625, + "logps/chosen": -372.3421936035156, + "logps/rejected": -367.71563720703125, + "logps/weighted_chosen": -2.7366943359375, + "logps/weighted_rejected": -3.2843260765075684, + "loss": 0.6563, + "rewards/accuracies": 0.574999988079071, + "rewards/chosen": -82.69844055175781, + "rewards/margins": 19.826171875, + "rewards/rejected": -102.53633117675781, + "rewards/weighted_accuracies": 0.6312500238418579, + "rewards/weighted_chosen": -0.4037841856479645, + "rewards/weighted_margins": 0.385406494140625, + "rewards/weighted_rejected": -0.7893310785293579, + "step": 580 + }, + { + "epoch": 0.30881968071185556, + "grad_norm": 17.115406036376953, + "learning_rate": 8.740688683062723e-07, + "logits/chosen": -0.7163940668106079, + "logits/rejected": -0.729107677936554, + "logps/chosen": -413.54608154296875, + "logps/rejected": -381.59375, + "logps/weighted_chosen": -2.6946043968200684, + "logps/weighted_rejected": -3.377270460128784, + "loss": 0.6482, + "rewards/accuracies": 0.606249988079071, + "rewards/chosen": -84.58671569824219, + "rewards/margins": 21.25390625, + "rewards/rejected": -105.85078430175781, + "rewards/weighted_accuracies": 0.675000011920929, + "rewards/weighted_chosen": -0.3194335997104645, + "rewards/weighted_margins": 0.46089476346969604, + "rewards/weighted_rejected": -0.780108630657196, + "step": 590 + }, + { + "epoch": 0.31405391258832765, + "grad_norm": 21.21268081665039, + "learning_rate": 8.679433775559215e-07, + "logits/chosen": -0.6942993402481079, + "logits/rejected": -0.7400848269462585, + "logps/chosen": -414.60467529296875, + "logps/rejected": -400.4125061035156, + "logps/weighted_chosen": -2.6637206077575684, + "logps/weighted_rejected": -3.6212401390075684, + "loss": 0.6532, + "rewards/accuracies": 0.637499988079071, + "rewards/chosen": -89.740234375, + "rewards/margins": 25.157617568969727, + "rewards/rejected": -114.8902359008789, + "rewards/weighted_accuracies": 0.6499999761581421, + "rewards/weighted_chosen": -0.4604248106479645, + "rewards/weighted_margins": 0.40590208768844604, + "rewards/weighted_rejected": -0.8660339117050171, + "step": 600 + }, + { + "epoch": 0.3192881444647998, + "grad_norm": 52.20835876464844, + "learning_rate": 8.616949967063871e-07, + "logits/chosen": -0.6779068112373352, + "logits/rejected": -0.7114807367324829, + "logps/chosen": -354.9515686035156, + "logps/rejected": -375.41094970703125, + "logps/weighted_chosen": -2.974072217941284, + "logps/weighted_rejected": -3.5394530296325684, + "loss": 0.6742, + "rewards/accuracies": 0.671875, + "rewards/chosen": -86.57109069824219, + "rewards/margins": 28.051952362060547, + "rewards/rejected": -114.6156234741211, + "rewards/weighted_accuracies": 0.653124988079071, + "rewards/weighted_chosen": -0.4645446836948395, + "rewards/weighted_margins": 0.36915284395217896, + "rewards/weighted_rejected": -0.8335021734237671, + "step": 610 + }, + { + "epoch": 0.3245223763412719, + "grad_norm": 22.18308448791504, + "learning_rate": 8.553258126661154e-07, + "logits/chosen": -0.7243606448173523, + "logits/rejected": -0.7389724850654602, + "logps/chosen": -374.96563720703125, + "logps/rejected": -378.7953186035156, + "logps/weighted_chosen": -3.1138672828674316, + "logps/weighted_rejected": -3.898486375808716, + "loss": 0.6444, + "rewards/accuracies": 0.612500011920929, + "rewards/chosen": -95.001953125, + "rewards/margins": 27.532812118530273, + "rewards/rejected": -122.50508117675781, + "rewards/weighted_accuracies": 0.65625, + "rewards/weighted_chosen": -0.5153747797012329, + "rewards/weighted_margins": 0.505627453327179, + "rewards/weighted_rejected": -1.0211060047149658, + "step": 620 + }, + { + "epoch": 0.32975660821774405, + "grad_norm": 40.515403747558594, + "learning_rate": 8.488379526908368e-07, + "logits/chosen": -0.719134509563446, + "logits/rejected": -0.729626476764679, + "logps/chosen": -393.68359375, + "logps/rejected": -405.1734313964844, + "logps/weighted_chosen": -3.021240234375, + "logps/weighted_rejected": -3.6431641578674316, + "loss": 0.6548, + "rewards/accuracies": 0.6343749761581421, + "rewards/chosen": -102.9828109741211, + "rewards/margins": 33.127342224121094, + "rewards/rejected": -136.0828094482422, + "rewards/weighted_accuracies": 0.6781250238418579, + "rewards/weighted_chosen": -0.5511718988418579, + "rewards/weighted_margins": 0.46650999784469604, + "rewards/weighted_rejected": -1.018225073814392, + "step": 630 + }, + { + "epoch": 0.33499084009421615, + "grad_norm": 62.75144958496094, + "learning_rate": 8.422335836730802e-07, + "logits/chosen": -0.7076660394668579, + "logits/rejected": -0.7095870971679688, + "logps/chosen": -371.7562561035156, + "logps/rejected": -414.140625, + "logps/weighted_chosen": -2.911572217941284, + "logps/weighted_rejected": -3.5963377952575684, + "loss": 0.6254, + "rewards/accuracies": 0.668749988079071, + "rewards/chosen": -98.0855484008789, + "rewards/margins": 38.46601486206055, + "rewards/rejected": -136.51718139648438, + "rewards/weighted_accuracies": 0.690625011920929, + "rewards/weighted_chosen": -0.5848175287246704, + "rewards/weighted_margins": 0.512927234172821, + "rewards/weighted_rejected": -1.097833275794983, + "step": 640 + }, + { + "epoch": 0.3402250719706883, + "grad_norm": 41.57294845581055, + "learning_rate": 8.355149114184485e-07, + "logits/chosen": -0.7601822018623352, + "logits/rejected": -0.7432464361190796, + "logps/chosen": -409.87188720703125, + "logps/rejected": -429.62188720703125, + "logps/weighted_chosen": -3.059814453125, + "logps/weighted_rejected": -3.5130615234375, + "loss": 0.5909, + "rewards/accuracies": 0.653124988079071, + "rewards/chosen": -102.44218444824219, + "rewards/margins": 44.93242263793945, + "rewards/rejected": -147.43515014648438, + "rewards/weighted_accuracies": 0.6968749761581421, + "rewards/weighted_chosen": -0.5836563110351562, + "rewards/weighted_margins": 0.5829010009765625, + "rewards/weighted_rejected": -1.166589379310608, + "step": 650 + }, + { + "epoch": 0.34545930384716045, + "grad_norm": 45.57954025268555, + "learning_rate": 8.286841799088963e-07, + "logits/chosen": -0.802441418170929, + "logits/rejected": -0.7937591671943665, + "logps/chosen": -387.9624938964844, + "logps/rejected": -394.9937438964844, + "logps/weighted_chosen": -2.703906297683716, + "logps/weighted_rejected": -3.4778809547424316, + "loss": 0.6382, + "rewards/accuracies": 0.596875011920929, + "rewards/chosen": -103.9437484741211, + "rewards/margins": 27.896678924560547, + "rewards/rejected": -131.8410186767578, + "rewards/weighted_accuracies": 0.675000011920929, + "rewards/weighted_chosen": -0.571490466594696, + "rewards/weighted_margins": 0.549023449420929, + "rewards/weighted_rejected": -1.12017822265625, + "step": 660 + }, + { + "epoch": 0.35069353572363254, + "grad_norm": 37.978858947753906, + "learning_rate": 8.217436705532599e-07, + "logits/chosen": -0.7893584966659546, + "logits/rejected": -0.8069244623184204, + "logps/chosen": -414.5484313964844, + "logps/rejected": -398.55780029296875, + "logps/weighted_chosen": -2.7833495140075684, + "logps/weighted_rejected": -3.48388671875, + "loss": 0.5742, + "rewards/accuracies": 0.6187499761581421, + "rewards/chosen": -111.7906265258789, + "rewards/margins": 23.006250381469727, + "rewards/rejected": -134.8093719482422, + "rewards/weighted_accuracies": 0.6812499761581421, + "rewards/weighted_chosen": -0.4879394471645355, + "rewards/weighted_margins": 0.6075531244277954, + "rewards/weighted_rejected": -1.095251441001892, + "step": 670 + }, + { + "epoch": 0.3559277676001047, + "grad_norm": 731.5437622070312, + "learning_rate": 8.14695701425284e-07, + "logits/chosen": -0.7789825201034546, + "logits/rejected": -0.8169800043106079, + "logps/chosen": -417.2015686035156, + "logps/rejected": -403.9624938964844, + "logps/weighted_chosen": -2.839160203933716, + "logps/weighted_rejected": -3.607421875, + "loss": 0.6329, + "rewards/accuracies": 0.5874999761581421, + "rewards/chosen": -111.77265930175781, + "rewards/margins": 29.793750762939453, + "rewards/rejected": -141.5343780517578, + "rewards/weighted_accuracies": 0.6812499761581421, + "rewards/weighted_chosen": -0.5055176019668579, + "rewards/weighted_margins": 0.5288635492324829, + "rewards/weighted_rejected": -1.034582495689392, + "step": 680 + }, + { + "epoch": 0.3611619994765768, + "grad_norm": 23.96302604675293, + "learning_rate": 8.075426264894046e-07, + "logits/chosen": -0.7564483880996704, + "logits/rejected": -0.785125732421875, + "logps/chosen": -418.2562561035156, + "logps/rejected": -427.62030029296875, + "logps/weighted_chosen": -2.916186571121216, + "logps/weighted_rejected": -4.193115234375, + "loss": 0.5335, + "rewards/accuracies": 0.637499988079071, + "rewards/chosen": -112.79512023925781, + "rewards/margins": 37.262107849121094, + "rewards/rejected": -150.0929718017578, + "rewards/weighted_accuracies": 0.737500011920929, + "rewards/weighted_chosen": -0.5042785406112671, + "rewards/weighted_margins": 0.7850341796875, + "rewards/weighted_rejected": -1.2886931896209717, + "step": 690 + }, + { + "epoch": 0.36639623135304894, + "grad_norm": 30.07147789001465, + "learning_rate": 8.002868348145435e-07, + "logits/chosen": -0.7395874261856079, + "logits/rejected": -0.7387515902519226, + "logps/chosen": -413.5406188964844, + "logps/rejected": -407.9750061035156, + "logps/weighted_chosen": -2.937329053878784, + "logps/weighted_rejected": -3.2009034156799316, + "loss": 0.6394, + "rewards/accuracies": 0.6031249761581421, + "rewards/chosen": -113.3121109008789, + "rewards/margins": 26.630273818969727, + "rewards/rejected": -139.94921875, + "rewards/weighted_accuracies": 0.675000011920929, + "rewards/weighted_chosen": -0.5579589605331421, + "rewards/weighted_margins": 0.46031492948532104, + "rewards/weighted_rejected": -1.017907738685608, + "step": 700 + }, + { + "epoch": 0.3716304632295211, + "grad_norm": 38.97393035888672, + "learning_rate": 7.92930749776179e-07, + "logits/chosen": -0.7464812994003296, + "logits/rejected": -0.7725540399551392, + "logps/chosen": -388.9750061035156, + "logps/rejected": -398.98126220703125, + "logps/weighted_chosen": -3.270263671875, + "logps/weighted_rejected": -3.752880811691284, + "loss": 0.6589, + "rewards/accuracies": 0.6156250238418579, + "rewards/chosen": -117.39530944824219, + "rewards/margins": 21.184764862060547, + "rewards/rejected": -138.5859375, + "rewards/weighted_accuracies": 0.621874988079071, + "rewards/weighted_chosen": -0.5594116449356079, + "rewards/weighted_margins": 0.44041746854782104, + "rewards/weighted_rejected": -0.9994751214981079, + "step": 710 + }, + { + "epoch": 0.3768646951059932, + "grad_norm": 21.152732849121094, + "learning_rate": 7.854768282469582e-07, + "logits/chosen": -0.7833511233329773, + "logits/rejected": -0.8182953000068665, + "logps/chosen": -379.1953125, + "logps/rejected": -416.29998779296875, + "logps/weighted_chosen": -2.8000245094299316, + "logps/weighted_rejected": -3.4732422828674316, + "loss": 0.6116, + "rewards/accuracies": 0.625, + "rewards/chosen": -101.853515625, + "rewards/margins": 36.69355392456055, + "rewards/rejected": -138.53866577148438, + "rewards/weighted_accuracies": 0.6812499761581421, + "rewards/weighted_chosen": -0.414450079202652, + "rewards/weighted_margins": 0.53369140625, + "rewards/weighted_rejected": -0.948101818561554, + "step": 720 + }, + { + "epoch": 0.38209892698246534, + "grad_norm": 267.910400390625, + "learning_rate": 7.779275597761215e-07, + "logits/chosen": -0.7315715551376343, + "logits/rejected": -0.778778076171875, + "logps/chosen": -380.20623779296875, + "logps/rejected": -408.5703125, + "logps/weighted_chosen": -2.9701170921325684, + "logps/weighted_rejected": -3.582080125808716, + "loss": 0.5809, + "rewards/accuracies": 0.643750011920929, + "rewards/chosen": -104.14375305175781, + "rewards/margins": 35.924217224121094, + "rewards/rejected": -140.08749389648438, + "rewards/weighted_accuracies": 0.7093750238418579, + "rewards/weighted_chosen": -0.3895111083984375, + "rewards/weighted_margins": 0.6164184808731079, + "rewards/weighted_rejected": -1.0058715343475342, + "step": 730 + }, + { + "epoch": 0.38733315885893743, + "grad_norm": 67.87287902832031, + "learning_rate": 7.702854657580126e-07, + "logits/chosen": -0.7619155645370483, + "logits/rejected": -0.772930920124054, + "logps/chosen": -405.0328063964844, + "logps/rejected": -391.39373779296875, + "logps/weighted_chosen": -2.9206786155700684, + "logps/weighted_rejected": -3.8096680641174316, + "loss": 0.6077, + "rewards/accuracies": 0.6312500238418579, + "rewards/chosen": -110.5816421508789, + "rewards/margins": 26.568944931030273, + "rewards/rejected": -137.11093139648438, + "rewards/weighted_accuracies": 0.671875, + "rewards/weighted_chosen": -0.441131591796875, + "rewards/weighted_margins": 0.5765472650527954, + "rewards/weighted_rejected": -1.0178649425506592, + "step": 740 + }, + { + "epoch": 0.3925673907354096, + "grad_norm": 46.017822265625, + "learning_rate": 7.625530985899547e-07, + "logits/chosen": -0.722912609577179, + "logits/rejected": -0.7346221804618835, + "logps/chosen": -379.953125, + "logps/rejected": -388.6000061035156, + "logps/weighted_chosen": -2.8084716796875, + "logps/weighted_rejected": -3.8277587890625, + "loss": 0.5923, + "rewards/accuracies": 0.59375, + "rewards/chosen": -113.12422180175781, + "rewards/margins": 30.504297256469727, + "rewards/rejected": -143.63516235351562, + "rewards/weighted_accuracies": 0.6937500238418579, + "rewards/weighted_chosen": -0.549816906452179, + "rewards/weighted_margins": 0.5676025152206421, + "rewards/weighted_rejected": -1.1176025867462158, + "step": 750 + }, + { + "epoch": 0.39780162261188173, + "grad_norm": 29.748411178588867, + "learning_rate": 7.547330408197694e-07, + "logits/chosen": -0.7272213101387024, + "logits/rejected": -0.7657715082168579, + "logps/chosen": -423.21875, + "logps/rejected": -402.828125, + "logps/weighted_chosen": -2.842236280441284, + "logps/weighted_rejected": -3.7777099609375, + "loss": 0.6328, + "rewards/accuracies": 0.590624988079071, + "rewards/chosen": -127.716796875, + "rewards/margins": 18.883983612060547, + "rewards/rejected": -146.58828735351562, + "rewards/weighted_accuracies": 0.671875, + "rewards/weighted_chosen": -0.5538665652275085, + "rewards/weighted_margins": 0.509082019329071, + "rewards/weighted_rejected": -1.063262939453125, + "step": 760 + }, + { + "epoch": 0.40303585448835383, + "grad_norm": 36.96773147583008, + "learning_rate": 7.468279042832271e-07, + "logits/chosen": -0.73992919921875, + "logits/rejected": -0.757153332233429, + "logps/chosen": -398.8296813964844, + "logps/rejected": -451.765625, + "logps/weighted_chosen": -2.8755125999450684, + "logps/weighted_rejected": -3.5738768577575684, + "loss": 0.6346, + "rewards/accuracies": 0.6468750238418579, + "rewards/chosen": -119.18359375, + "rewards/margins": 43.133201599121094, + "rewards/rejected": -162.3484344482422, + "rewards/weighted_accuracies": 0.6812499761581421, + "rewards/weighted_chosen": -0.599902331829071, + "rewards/weighted_margins": 0.4711242616176605, + "rewards/weighted_rejected": -1.0711486339569092, + "step": 770 + }, + { + "epoch": 0.408270086364826, + "grad_norm": 31.340259552001953, + "learning_rate": 7.388403292317154e-07, + "logits/chosen": -0.7140892148017883, + "logits/rejected": -0.7637573480606079, + "logps/chosen": -424.03436279296875, + "logps/rejected": -419.3531188964844, + "logps/weighted_chosen": -2.7535400390625, + "logps/weighted_rejected": -3.53564453125, + "loss": 0.5954, + "rewards/accuracies": 0.606249988079071, + "rewards/chosen": -122.986328125, + "rewards/margins": 30.427734375, + "rewards/rejected": -153.4421844482422, + "rewards/weighted_accuracies": 0.699999988079071, + "rewards/weighted_chosen": -0.5587218999862671, + "rewards/weighted_margins": 0.592761218547821, + "rewards/weighted_rejected": -1.1515014171600342, + "step": 780 + }, + { + "epoch": 0.4135043182412981, + "grad_norm": 22.861244201660156, + "learning_rate": 7.307729834504154e-07, + "logits/chosen": -0.7405792474746704, + "logits/rejected": -0.7957550287246704, + "logps/chosen": -408.3984375, + "logps/rejected": -426.87811279296875, + "logps/weighted_chosen": -2.751171827316284, + "logps/weighted_rejected": -3.7800049781799316, + "loss": 0.6317, + "rewards/accuracies": 0.612500011920929, + "rewards/chosen": -126.57695007324219, + "rewards/margins": 34.237892150878906, + "rewards/rejected": -160.8195343017578, + "rewards/weighted_accuracies": 0.699999988079071, + "rewards/weighted_chosen": -0.590838611125946, + "rewards/weighted_margins": 0.5351654291152954, + "rewards/weighted_rejected": -1.1267273426055908, + "step": 790 + }, + { + "epoch": 0.4187385501177702, + "grad_norm": 47.63352966308594, + "learning_rate": 7.226285613672847e-07, + "logits/chosen": -0.6944122314453125, + "logits/rejected": -0.7281158566474915, + "logps/chosen": -399.3265686035156, + "logps/rejected": -450.2906188964844, + "logps/weighted_chosen": -2.772753953933716, + "logps/weighted_rejected": -3.867480516433716, + "loss": 0.604, + "rewards/accuracies": 0.659375011920929, + "rewards/chosen": -121.8121109008789, + "rewards/margins": 49.55859375, + "rewards/rejected": -171.38046264648438, + "rewards/weighted_accuracies": 0.7093750238418579, + "rewards/weighted_chosen": -0.5663421750068665, + "rewards/weighted_margins": 0.5819091796875, + "rewards/weighted_rejected": -1.148461937904358, + "step": 800 + }, + { + "epoch": 0.4239727819942423, + "grad_norm": 19.353519439697266, + "learning_rate": 7.144097831531398e-07, + "logits/chosen": -0.6676399111747742, + "logits/rejected": -0.6886535882949829, + "logps/chosen": -402.2984313964844, + "logps/rejected": -432.3531188964844, + "logps/weighted_chosen": -2.8445801734924316, + "logps/weighted_rejected": -3.7008299827575684, + "loss": 0.6044, + "rewards/accuracies": 0.640625, + "rewards/chosen": -132.17343139648438, + "rewards/margins": 36.122459411621094, + "rewards/rejected": -168.2585906982422, + "rewards/weighted_accuracies": 0.690625011920929, + "rewards/weighted_chosen": -0.573992908000946, + "rewards/weighted_margins": 0.569226086139679, + "rewards/weighted_rejected": -1.143530249595642, + "step": 810 + }, + { + "epoch": 0.42920701387071447, + "grad_norm": 29.685457229614258, + "learning_rate": 7.061193938131396e-07, + "logits/chosen": -0.6138809323310852, + "logits/rejected": -0.6571716070175171, + "logps/chosen": -440.6265563964844, + "logps/rejected": -433.95001220703125, + "logps/weighted_chosen": -3.1656250953674316, + "logps/weighted_rejected": -3.6409668922424316, + "loss": 0.5893, + "rewards/accuracies": 0.596875011920929, + "rewards/chosen": -140.87890625, + "rewards/margins": 27.572656631469727, + "rewards/rejected": -168.5109405517578, + "rewards/weighted_accuracies": 0.684374988079071, + "rewards/weighted_chosen": -0.5785247683525085, + "rewards/weighted_margins": 0.638214111328125, + "rewards/weighted_rejected": -1.216912865638733, + "step": 820 + }, + { + "epoch": 0.4344412457471866, + "grad_norm": 28.759309768676758, + "learning_rate": 6.977601622699789e-07, + "logits/chosen": -0.6784942746162415, + "logits/rejected": -0.7357269525527954, + "logps/chosen": -413.9476623535156, + "logps/rejected": -463.1390686035156, + "logps/weighted_chosen": -3.047466993331909, + "logps/weighted_rejected": -3.9415526390075684, + "loss": 0.5322, + "rewards/accuracies": 0.671875, + "rewards/chosen": -129.1398468017578, + "rewards/margins": 55.296485900878906, + "rewards/rejected": -184.421875, + "rewards/weighted_accuracies": 0.7250000238418579, + "rewards/weighted_chosen": -0.4962509274482727, + "rewards/weighted_margins": 0.755261242389679, + "rewards/weighted_rejected": -1.2515869140625, + "step": 830 + }, + { + "epoch": 0.4396754776236587, + "grad_norm": 41.56013107299805, + "learning_rate": 6.893348804390882e-07, + "logits/chosen": -0.809680163860321, + "logits/rejected": -0.809558093547821, + "logps/chosen": -445.3421936035156, + "logps/rejected": -454.68438720703125, + "logps/weighted_chosen": -3.277099609375, + "logps/weighted_rejected": -3.73974609375, + "loss": 0.5971, + "rewards/accuracies": 0.59375, + "rewards/chosen": -150.06405639648438, + "rewards/margins": 44.780860900878906, + "rewards/rejected": -194.8703155517578, + "rewards/weighted_accuracies": 0.6968749761581421, + "rewards/weighted_chosen": -0.6049469113349915, + "rewards/weighted_margins": 0.59771728515625, + "rewards/weighted_rejected": -1.2025878429412842, + "step": 840 + }, + { + "epoch": 0.44490970950013087, + "grad_norm": 21.975399017333984, + "learning_rate": 6.808463622961578e-07, + "logits/chosen": -0.838226318359375, + "logits/rejected": -0.878466784954071, + "logps/chosen": -470.1796875, + "logps/rejected": -514.8531494140625, + "logps/weighted_chosen": -3.189526319503784, + "logps/weighted_rejected": -4.007568359375, + "loss": 0.5758, + "rewards/accuracies": 0.621874988079071, + "rewards/chosen": -177.51953125, + "rewards/margins": 55.28593826293945, + "rewards/rejected": -232.81094360351562, + "rewards/weighted_accuracies": 0.706250011920929, + "rewards/weighted_chosen": -0.6749969720840454, + "rewards/weighted_margins": 0.754681408405304, + "rewards/weighted_rejected": -1.429284691810608, + "step": 850 + }, + { + "epoch": 0.45014394137660296, + "grad_norm": 22.851951599121094, + "learning_rate": 6.722974429372925e-07, + "logits/chosen": -0.839556872844696, + "logits/rejected": -0.871502697467804, + "logps/chosen": -531.9484252929688, + "logps/rejected": -532.2999877929688, + "logps/weighted_chosen": -3.0276856422424316, + "logps/weighted_rejected": -4.387353420257568, + "loss": 0.5743, + "rewards/accuracies": 0.5874999761581421, + "rewards/chosen": -228.4031219482422, + "rewards/margins": 41.707420349121094, + "rewards/rejected": -270.15155029296875, + "rewards/weighted_accuracies": 0.7406250238418579, + "rewards/weighted_chosen": -0.8227783441543579, + "rewards/weighted_margins": 0.8454529047012329, + "rewards/weighted_rejected": -1.6683471202850342, + "step": 860 + }, + { + "epoch": 0.4553781732530751, + "grad_norm": 34.66981887817383, + "learning_rate": 6.636909776321128e-07, + "logits/chosen": -0.8797591924667358, + "logits/rejected": -0.864776611328125, + "logps/chosen": -461.953125, + "logps/rejected": -522.6062622070312, + "logps/weighted_chosen": -3.339587450027466, + "logps/weighted_rejected": -4.197558403015137, + "loss": 0.5676, + "rewards/accuracies": 0.590624988079071, + "rewards/chosen": -200.29843139648438, + "rewards/margins": 57.83671951293945, + "rewards/rejected": -258.1499938964844, + "rewards/weighted_accuracies": 0.706250011920929, + "rewards/weighted_chosen": -0.8672088384628296, + "rewards/weighted_margins": 0.72900390625, + "rewards/weighted_rejected": -1.596582055091858, + "step": 870 + }, + { + "epoch": 0.46061240512954726, + "grad_norm": 402.62530517578125, + "learning_rate": 6.550298408701174e-07, + "logits/chosen": -0.860809326171875, + "logits/rejected": -0.9049621820449829, + "logps/chosen": -489.68438720703125, + "logps/rejected": -540.2687377929688, + "logps/weighted_chosen": -3.544872999191284, + "logps/weighted_rejected": -4.589892387390137, + "loss": 0.596, + "rewards/accuracies": 0.637499988079071, + "rewards/chosen": -202.95565795898438, + "rewards/margins": 54.89179611206055, + "rewards/rejected": -257.78515625, + "rewards/weighted_accuracies": 0.6968749761581421, + "rewards/weighted_chosen": -0.791333019733429, + "rewards/weighted_margins": 0.6679824590682983, + "rewards/weighted_rejected": -1.4595428705215454, + "step": 880 + }, + { + "epoch": 0.46584663700601936, + "grad_norm": 342.0785827636719, + "learning_rate": 6.463169254006276e-07, + "logits/chosen": -0.8872314691543579, + "logits/rejected": -0.918865978717804, + "logps/chosen": -482.1578063964844, + "logps/rejected": -486.10467529296875, + "logps/weighted_chosen": -3.362231492996216, + "logps/weighted_rejected": -4.306298732757568, + "loss": 0.5402, + "rewards/accuracies": 0.6156250238418579, + "rewards/chosen": -201.04843139648438, + "rewards/margins": 38.162498474121094, + "rewards/rejected": -239.21133422851562, + "rewards/weighted_accuracies": 0.7281249761581421, + "rewards/weighted_chosen": -0.7565551996231079, + "rewards/weighted_margins": 0.8916381597518921, + "rewards/weighted_rejected": -1.6484863758087158, + "step": 890 + }, + { + "epoch": 0.4710808688824915, + "grad_norm": 84.898193359375, + "learning_rate": 6.375551412666326e-07, + "logits/chosen": -0.8932129144668579, + "logits/rejected": -0.909472644329071, + "logps/chosen": -485.47967529296875, + "logps/rejected": -491.5093688964844, + "logps/weighted_chosen": -3.119433641433716, + "logps/weighted_rejected": -4.143603324890137, + "loss": 0.6461, + "rewards/accuracies": 0.578125, + "rewards/chosen": -211.3484344482422, + "rewards/margins": 23.850391387939453, + "rewards/rejected": -235.22225952148438, + "rewards/weighted_accuracies": 0.653124988079071, + "rewards/weighted_chosen": -0.972399890422821, + "rewards/weighted_margins": 0.627001941204071, + "rewards/weighted_rejected": -1.599572777748108, + "step": 900 + }, + { + "epoch": 0.4763151007589636, + "grad_norm": 242.4366455078125, + "learning_rate": 6.287474148328583e-07, + "logits/chosen": -0.855010986328125, + "logits/rejected": -0.8482757806777954, + "logps/chosen": -457.9312438964844, + "logps/rejected": -459.96875, + "logps/weighted_chosen": -3.5470948219299316, + "logps/weighted_rejected": -4.787109375, + "loss": 0.6583, + "rewards/accuracies": 0.5874999761581421, + "rewards/chosen": -187.0656280517578, + "rewards/margins": 25.948827743530273, + "rewards/rejected": -213.04296875, + "rewards/weighted_accuracies": 0.628125011920929, + "rewards/weighted_chosen": -0.9626404047012329, + "rewards/weighted_margins": 0.5732177495956421, + "rewards/weighted_rejected": -1.5358765125274658, + "step": 910 + }, + { + "epoch": 0.48154933263543576, + "grad_norm": 163.63558959960938, + "learning_rate": 6.198966878083857e-07, + "logits/chosen": -0.8556182980537415, + "logits/rejected": -0.8749450445175171, + "logps/chosen": -450.89373779296875, + "logps/rejected": -486.953125, + "logps/weighted_chosen": -3.41851806640625, + "logps/weighted_rejected": -4.127148628234863, + "loss": 0.598, + "rewards/accuracies": 0.6000000238418579, + "rewards/chosen": -179.65234375, + "rewards/margins": 40.17695236206055, + "rewards/rejected": -219.8562469482422, + "rewards/weighted_accuracies": 0.6812499761581421, + "rewards/weighted_chosen": -0.7931762933731079, + "rewards/weighted_margins": 0.6718719601631165, + "rewards/weighted_rejected": -1.465295433998108, + "step": 920 + }, + { + "epoch": 0.48678356451190785, + "grad_norm": 299.4981689453125, + "learning_rate": 6.110059162641439e-07, + "logits/chosen": -0.8365691900253296, + "logits/rejected": -0.8519042730331421, + "logps/chosen": -456.8046875, + "logps/rejected": -481.1812438964844, + "logps/weighted_chosen": -2.855395555496216, + "logps/weighted_rejected": -3.79541015625, + "loss": 0.5691, + "rewards/accuracies": 0.621874988079071, + "rewards/chosen": -174.2941436767578, + "rewards/margins": 39.63788986206055, + "rewards/rejected": -213.9421844482422, + "rewards/weighted_accuracies": 0.699999988079071, + "rewards/weighted_chosen": -0.6965240240097046, + "rewards/weighted_margins": 0.643646240234375, + "rewards/weighted_rejected": -1.340509057044983, + "step": 930 + }, + { + "epoch": 0.49201779638838, + "grad_norm": 139.11936950683594, + "learning_rate": 6.020780696456059e-07, + "logits/chosen": -0.818524181842804, + "logits/rejected": -0.8568817377090454, + "logps/chosen": -432.6015625, + "logps/rejected": -482.3765563964844, + "logps/weighted_chosen": -2.738085985183716, + "logps/weighted_rejected": -3.7889161109924316, + "loss": 0.6145, + "rewards/accuracies": 0.65625, + "rewards/chosen": -161.802734375, + "rewards/margins": 53.56367111206055, + "rewards/rejected": -215.30624389648438, + "rewards/weighted_accuracies": 0.6812499761581421, + "rewards/weighted_chosen": -0.751434326171875, + "rewards/weighted_margins": 0.5673767328262329, + "rewards/weighted_rejected": -1.319006323814392, + "step": 940 + }, + { + "epoch": 0.49725202826485215, + "grad_norm": 2830.01513671875, + "learning_rate": 5.931161297810185e-07, + "logits/chosen": -0.897666335105896, + "logits/rejected": -0.912066638469696, + "logps/chosen": -450.53125, + "logps/rejected": -480.78436279296875, + "logps/weighted_chosen": -3.4595704078674316, + "logps/weighted_rejected": -4.21240234375, + "loss": 0.6411, + "rewards/accuracies": 0.596875011920929, + "rewards/chosen": -177.23983764648438, + "rewards/margins": 42.097267150878906, + "rewards/rejected": -219.32852172851562, + "rewards/weighted_accuracies": 0.6468750238418579, + "rewards/weighted_chosen": -0.7506958246231079, + "rewards/weighted_margins": 0.633044421672821, + "rewards/weighted_rejected": -1.3831908702850342, + "step": 950 + }, + { + "epoch": 0.5024862601413242, + "grad_norm": 294.5556640625, + "learning_rate": 5.841230898854959e-07, + "logits/chosen": -0.8446868658065796, + "logits/rejected": -0.860076904296875, + "logps/chosen": -493.5140686035156, + "logps/rejected": -503.9921875, + "logps/weighted_chosen": -3.2405028343200684, + "logps/weighted_rejected": -4.144775390625, + "loss": 0.6412, + "rewards/accuracies": 0.625, + "rewards/chosen": -193.3210906982422, + "rewards/margins": 49.00800704956055, + "rewards/rejected": -242.33749389648438, + "rewards/weighted_accuracies": 0.690625011920929, + "rewards/weighted_chosen": -0.8943328857421875, + "rewards/weighted_margins": 0.655200183391571, + "rewards/weighted_rejected": -1.549963355064392, + "step": 960 + }, + { + "epoch": 0.5077204920177963, + "grad_norm": 1039.4329833984375, + "learning_rate": 5.751019535613102e-07, + "logits/chosen": -0.816241443157196, + "logits/rejected": -0.831072986125946, + "logps/chosen": -434.7757873535156, + "logps/rejected": -476.2437438964844, + "logps/weighted_chosen": -3.277026414871216, + "logps/weighted_rejected": -4.411572456359863, + "loss": 0.6001, + "rewards/accuracies": 0.637499988079071, + "rewards/chosen": -174.7824249267578, + "rewards/margins": 54.372657775878906, + "rewards/rejected": -229.171875, + "rewards/weighted_accuracies": 0.699999988079071, + "rewards/weighted_chosen": -0.8984619379043579, + "rewards/weighted_margins": 0.785168468952179, + "rewards/weighted_rejected": -1.68408203125, + "step": 970 + }, + { + "epoch": 0.5129547238942685, + "grad_norm": 63.553932189941406, + "learning_rate": 5.660557337947117e-07, + "logits/chosen": -0.8274612426757812, + "logits/rejected": -0.832653820514679, + "logps/chosen": -484.9125061035156, + "logps/rejected": -491.22344970703125, + "logps/weighted_chosen": -2.8631834983825684, + "logps/weighted_rejected": -3.8985838890075684, + "loss": 0.5745, + "rewards/accuracies": 0.6031249761581421, + "rewards/chosen": -190.4035186767578, + "rewards/margins": 43.454689025878906, + "rewards/rejected": -233.85311889648438, + "rewards/weighted_accuracies": 0.7093750238418579, + "rewards/weighted_chosen": -0.7985321283340454, + "rewards/weighted_margins": 0.6566101312637329, + "rewards/weighted_rejected": -1.454565405845642, + "step": 980 + }, + { + "epoch": 0.5181889557707406, + "grad_norm": 474.792724609375, + "learning_rate": 5.569874519496174e-07, + "logits/chosen": -0.8315078616142273, + "logits/rejected": -0.875781238079071, + "logps/chosen": -461.2124938964844, + "logps/rejected": -500.48907470703125, + "logps/weighted_chosen": -3.374279737472534, + "logps/weighted_rejected": -4.527905464172363, + "loss": 0.5744, + "rewards/accuracies": 0.5874999761581421, + "rewards/chosen": -186.0480499267578, + "rewards/margins": 47.295310974121094, + "rewards/rejected": -233.33749389648438, + "rewards/weighted_accuracies": 0.721875011920929, + "rewards/weighted_chosen": -0.7532867193222046, + "rewards/weighted_margins": 0.7921081781387329, + "rewards/weighted_rejected": -1.5448729991912842, + "step": 990 + }, + { + "epoch": 0.5234231876472127, + "grad_norm": 46.039974212646484, + "learning_rate": 5.47900136758499e-07, + "logits/chosen": -0.7764679193496704, + "logits/rejected": -0.8226165771484375, + "logps/chosen": -472.5015563964844, + "logps/rejected": -484.1937561035156, + "logps/weighted_chosen": -3.4063720703125, + "logps/weighted_rejected": -4.413744926452637, + "loss": 0.5675, + "rewards/accuracies": 0.590624988079071, + "rewards/chosen": -204.89297485351562, + "rewards/margins": 36.982810974121094, + "rewards/rejected": -241.89883422851562, + "rewards/weighted_accuracies": 0.703125, + "rewards/weighted_chosen": -0.9316650629043579, + "rewards/weighted_margins": 0.817004382610321, + "rewards/weighted_rejected": -1.748803734779358, + "step": 1000 + }, + { + "epoch": 0.5234231876472127, + "eval_logits/chosen": -0.8910121917724609, + "eval_logits/rejected": -0.9021777510643005, + "eval_logps/chosen": -512.3715209960938, + "eval_logps/rejected": -536.406982421875, + "eval_logps/weighted_chosen": -3.448028326034546, + "eval_logps/weighted_rejected": -4.361933708190918, + "eval_loss": 0.5965847373008728, + "eval_rewards/accuracies": 0.5910000205039978, + "eval_rewards/chosen": -223.7135009765625, + "eval_rewards/margins": 45.03103256225586, + "eval_rewards/rejected": -268.75, + "eval_rewards/weighted_accuracies": 0.690500020980835, + "eval_rewards/weighted_chosen": -0.9871044754981995, + "eval_rewards/weighted_margins": 0.7057854533195496, + "eval_rewards/weighted_rejected": -1.6928898096084595, + "eval_runtime": 1512.2328, + "eval_samples_per_second": 1.323, + "eval_steps_per_second": 0.331, + "step": 1000 + } + ], + "logging_steps": 10, + "max_steps": 1911, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1000/training_args.bin b/checkpoint-1000/training_args.bin new file mode 100644 index 0000000..2a96666 --- /dev/null +++ b/checkpoint-1000/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af898db701df81d78da638b0a1b962531f0493f59e9b2be3d881d4701a7c223a +size 8721 diff --git a/checkpoint-1000/zero_to_fp32.py b/checkpoint-1000/zero_to_fp32.py new file mode 100644 index 0000000..0e75914 --- /dev/null +++ b/checkpoint-1000/zero_to_fp32.py @@ -0,0 +1,760 @@ +#!/usr/bin/env python + +# Copyright (c) Microsoft Corporation. +# SPDX-License-Identifier: Apache-2.0 + +# DeepSpeed Team + +# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets +# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in +# the future. Once extracted, the weights don't require DeepSpeed and can be used in any +# application. +# +# example: +# python zero_to_fp32.py . output_dir/ +# or +# python zero_to_fp32.py . output_dir/ --safe_serialization + +import argparse +import torch +import glob +import math +import os +import re +import gc +import json +import numpy as np +from tqdm import tqdm +from collections import OrderedDict +from dataclasses import dataclass + +# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with +# DeepSpeed data structures it has to be available in the current python environment. +from deepspeed.utils import logger +from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS, + FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES, + FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS) + + +@dataclass +class zero_model_state: + buffers: dict() + param_shapes: dict() + shared_params: list + ds_version: int + frozen_param_shapes: dict() + frozen_param_fragments: dict() + + +debug = 0 + +# load to cpu +device = torch.device('cpu') + + +def atoi(text): + return int(text) if text.isdigit() else text + + +def natural_keys(text): + ''' + alist.sort(key=natural_keys) sorts in human order + http://nedbatchelder.com/blog/200712/human_sorting.html + (See Toothy's implementation in the comments) + ''' + return [atoi(c) for c in re.split(r'(\d+)', text)] + + +def get_model_state_file(checkpoint_dir, zero_stage): + if not os.path.isdir(checkpoint_dir): + raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist") + + # there should be only one file + if zero_stage <= 2: + file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt") + elif zero_stage == 3: + file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt") + + if not os.path.exists(file): + raise FileNotFoundError(f"can't find model states file at '{file}'") + + return file + + +def get_checkpoint_files(checkpoint_dir, glob_pattern): + # XXX: need to test that this simple glob rule works for multi-node setup too + ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys) + + if len(ckpt_files) == 0: + raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'") + + return ckpt_files + + +def get_optim_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt") + + +def get_model_state_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_model_states.pt") + + +def parse_model_states(files): + zero_model_states = [] + for file in files: + state_dict = torch.load(file, map_location=device, weights_only=False) + + if BUFFER_NAMES not in state_dict: + raise ValueError(f"{file} is not a model state checkpoint") + buffer_names = state_dict[BUFFER_NAMES] + if debug: + print("Found buffers:", buffer_names) + + # recover just the buffers while restoring them to fp32 if they were saved in fp16 + buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names} + param_shapes = state_dict[PARAM_SHAPES] + + # collect parameters that are included in param_shapes + param_names = [] + for s in param_shapes: + for name in s.keys(): + param_names.append(name) + + # update with frozen parameters + frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None) + if frozen_param_shapes is not None: + if debug: + print(f"Found frozen_param_shapes: {frozen_param_shapes}") + param_names += list(frozen_param_shapes.keys()) + + # handle shared params + shared_params = [[k, v] for k, v in state_dict["shared_params"].items()] + + ds_version = state_dict.get(DS_VERSION, None) + + frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None) + + z_model_state = zero_model_state(buffers=buffers, + param_shapes=param_shapes, + shared_params=shared_params, + ds_version=ds_version, + frozen_param_shapes=frozen_param_shapes, + frozen_param_fragments=frozen_param_fragments) + zero_model_states.append(z_model_state) + + return zero_model_states + + +def parse_optim_states(files, ds_checkpoint_dir): + total_files = len(files) + state_dicts = [] + for f in tqdm(files, desc='Loading checkpoint shards'): + state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False) + # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights + # and also handle the case where it was already removed by another helper script + state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None) + state_dicts.append(state_dict) + + if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]: + raise ValueError(f"{files[0]} is not a zero checkpoint") + zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE] + world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT] + + # For ZeRO-2 each param group can have different partition_count as data parallelism for expert + # parameters can be different from data parallelism for non-expert parameters. So we can just + # use the max of the partition_count to get the dp world_size. + + if type(world_size) is list: + world_size = max(world_size) + + if world_size != total_files: + raise ValueError( + f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. " + "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes." + ) + + # the groups are named differently in each stage + if zero_stage <= 2: + fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS + elif zero_stage == 3: + fp32_groups_key = FP32_FLAT_GROUPS + else: + raise ValueError(f"unknown zero stage {zero_stage}") + + fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))] + return zero_stage, world_size, fp32_flat_groups + + +def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters): + """ + Returns fp32 state_dict reconstructed from ds checkpoint + + Args: + - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are) + + """ + print(f"Processing zero checkpoint '{ds_checkpoint_dir}'") + + optim_files = get_optim_files(ds_checkpoint_dir) + zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir) + print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}") + + model_files = get_model_state_files(ds_checkpoint_dir) + + zero_model_states = parse_model_states(model_files) + print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}') + + if zero_stage <= 2: + return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + elif zero_stage == 3: + return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + + +def _zero2_merge_frozen_params(state_dict, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + frozen_param_fragments = zero_model_states[0].frozen_param_fragments + + if debug: + num_elem = sum(s.numel() for s in frozen_param_shapes.values()) + print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in frozen_param_fragments.values()]) + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + state_dict[name] = frozen_param_fragments[name] + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +def _has_callable(obj, fn): + attr = getattr(obj, fn, None) + return callable(attr) + + +def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + + # Reconstruction protocol: + # + # XXX: document this + + if debug: + for i in range(world_size): + for j in range(len(fp32_flat_groups[0])): + print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}") + + # XXX: memory usage doubles here (zero2) + num_param_groups = len(fp32_flat_groups[0]) + merged_single_partition_of_fp32_groups = [] + for i in range(num_param_groups): + merged_partitions = [sd[i] for sd in fp32_flat_groups] + full_single_fp32_vector = torch.cat(merged_partitions, 0) + merged_single_partition_of_fp32_groups.append(full_single_fp32_vector) + avail_numel = sum( + [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups]) + + if debug: + wanted_params = sum([len(shapes) for shapes in param_shapes]) + wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes]) + # not asserting if there is a mismatch due to possible padding + print(f"Have {avail_numel} numels to process.") + print(f"Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + total_numel = 0 + total_params = 0 + for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups): + offset = 0 + avail_numel = full_single_fp32_vector.numel() + for name, shape in shapes.items(): + + unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape) + total_numel += unpartitioned_numel + total_params += 1 + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape) + offset += unpartitioned_numel + + # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and + # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex + # paddings performed in the code it's almost impossible to predict the exact numbers w/o the + # live optimizer object, so we are checking that the numbers are within the right range + align_to = 2 * world_size + + def zero2_align(x): + return align_to * math.ceil(x / align_to) + + if debug: + print(f"original offset={offset}, avail_numel={avail_numel}") + + offset = zero2_align(offset) + avail_numel = zero2_align(avail_numel) + + if debug: + print(f"aligned offset={offset}, avail_numel={avail_numel}") + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero2_merge_frozen_params(state_dict, zero_model_states) + + _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def zero3_partitioned_param_info(unpartitioned_numel, world_size): + remainder = unpartitioned_numel % world_size + padding_numel = (world_size - remainder) if remainder else 0 + partitioned_numel = math.ceil(unpartitioned_numel / world_size) + return partitioned_numel, padding_numel + + +def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + if debug: + for i in range(world_size): + num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values()) + print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in zero_model_states[0].frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states) + state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape) + + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +class GatheredTensor: + """ + A pseudo tensor that collects partitioned weights. + It is more memory efficient when there are multiple groups. + """ + + def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape): + self.flat_groups = flat_groups + self.flat_groups_offset = flat_groups_offset + self.offset = offset + self.partitioned_numel = partitioned_numel + self.shape = shape + self.dtype = self.flat_groups[0][0].dtype + + def contiguous(self): + """ + Merge partitioned weights from flat_groups into a single tensor. + """ + end_idx = self.offset + self.partitioned_numel + world_size = len(self.flat_groups) + pad_flat_param_chunks = [] + + for rank_i in range(world_size): + # for each rank, we need to collect weights from related group/groups + flat_groups_at_rank_i = self.flat_groups[rank_i] + start_group_id = None + end_group_id = None + for group_id in range(len(self.flat_groups_offset)): + if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]: + start_group_id = group_id + if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]: + end_group_id = group_id + break + # collect weights from related group/groups + for group_id in range(start_group_id, end_group_id + 1): + flat_tensor = flat_groups_at_rank_i[group_id] + start_offset = self.offset - self.flat_groups_offset[group_id] + end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id] + pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset]) + + # collect weights from all ranks + pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0) + param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous() + return param + + +def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size + + # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each + # param, re-consolidating each param, while dealing with padding if any + + # merge list of dicts, preserving order + param_shapes = {k: v for d in param_shapes for k, v in d.items()} + + if debug: + for i in range(world_size): + print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}") + + wanted_params = len(param_shapes) + wanted_numel = sum(shape.numel() for shape in param_shapes.values()) + # not asserting if there is a mismatch due to possible padding + avail_numel = fp32_flat_groups[0].numel() * world_size + print(f"Trainable params: Have {avail_numel} numels to process.") + print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + offset = 0 + total_numel = 0 + total_params = 0 + flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]])) + for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'): + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + total_params += 1 + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + # memory efficient tensor + tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape) + state_dict[name] = tensor + offset += partitioned_numel + + offset *= world_size + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero3_merge_frozen_params(state_dict, world_size, zero_model_states) + + _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def to_torch_tensor(state_dict, return_empty_tensor=False): + """ + Convert state_dict of GatheredTensor to torch tensor + """ + torch_state_dict = {} + converted_tensors = {} + for name, tensor in state_dict.items(): + tensor_id = id(tensor) + if tensor_id in converted_tensors: # shared tensors + shared_tensor = torch_state_dict[converted_tensors[tensor_id]] + torch_state_dict[name] = shared_tensor + else: + converted_tensors[tensor_id] = name + if return_empty_tensor: + torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype) + else: + torch_state_dict[name] = tensor.contiguous() + return torch_state_dict + + +def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, + tag=None, + exclude_frozen_parameters=False, + lazy_mode=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with + ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example + via a model hub. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient. + Convert the pesduo tensor to torch tensor by ``.contiguous()`` + + Returns: + - pytorch ``state_dict`` + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint + # do the training and checkpoint saving + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu + model = model.cpu() # move to cpu + model.load_state_dict(state_dict) + # submit to model hub or save the model to share with others + + In this example the ``model`` will no longer be usable in the deepspeed context of the same + application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead. + + Note: the above usage may not work if your application doesn't have sufficient free CPU memory. + You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with + the checkpoint. Or you can load state_dict in lazy mode :: + + from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu + for name, lazy_tensor in state_dict.item(): + tensor = lazy_tensor.contiguous() # to cpu + print(name, tensor) + # del tensor to release memory if it no longer in use + """ + if tag is None: + latest_path = os.path.join(checkpoint_dir, 'latest') + if os.path.isfile(latest_path): + with open(latest_path, 'r') as fd: + tag = fd.read().strip() + else: + raise ValueError(f"Unable to find 'latest' file at {latest_path}") + + ds_checkpoint_dir = os.path.join(checkpoint_dir, tag) + + if not os.path.isdir(ds_checkpoint_dir): + raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist") + + state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters) + if lazy_mode: + return state_dict + else: + return to_torch_tensor(state_dict) + + +def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, + output_dir, + max_shard_size="5GB", + safe_serialization=False, + tag=None, + exclude_frozen_parameters=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be + loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``output_dir``: directory to the pytorch fp32 state_dict output files + - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB + - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`). + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + """ + + # Dependency pre-check + if safe_serialization: + try: + from safetensors.torch import save_file + except ImportError: + print('If you want to use `safe_serialization`, please `pip install safetensors`') + raise + if max_shard_size is not None: + try: + from huggingface_hub import split_torch_state_dict_into_shards + except ImportError: + print('If you want to use `max_shard_size`, please `pip install huggingface_hub`') + raise + + # Convert zero checkpoint to state_dict + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, + tag, + exclude_frozen_parameters, + lazy_mode=True) + + # Shard the model if it is too big. + weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin" + if max_shard_size is not None: + filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors") + # an memory-efficient approach for sharding + empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True) + state_dict_split = split_torch_state_dict_into_shards(empty_state_dict, + filename_pattern=filename_pattern, + max_shard_size=max_shard_size) + else: + from collections import namedtuple + StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"]) + state_dict_split = StateDictSplit(is_sharded=False, + filename_to_tensors={weights_name: list(state_dict.keys())}) + + # Save the model by shard + os.makedirs(output_dir, exist_ok=True) + filename_to_tensors = state_dict_split.filename_to_tensors.items() + for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"): + shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors} + shard_state_dict = to_torch_tensor(shard_state_dict) + output_path = os.path.join(output_dir, shard_file) + if safe_serialization: + save_file(shard_state_dict, output_path, metadata={"format": "pt"}) + else: + torch.save(shard_state_dict, output_path) + # release the memory of current shard + for tensor_name in list(shard_state_dict.keys()): + del state_dict[tensor_name] + del shard_state_dict[tensor_name] + del shard_state_dict + gc.collect() + + # Save index if sharded + if state_dict_split.is_sharded: + index = { + "metadata": state_dict_split.metadata, + "weight_map": state_dict_split.tensor_to_filename, + } + save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json" + save_index_file = os.path.join(output_dir, save_index_file) + with open(save_index_file, "w", encoding="utf-8") as f: + content = json.dumps(index, indent=2, sort_keys=True) + "\n" + f.write(content) + + +def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None): + """ + 1. Put the provided model to cpu + 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` + 3. Load it into the provided model + + Args: + - ``model``: the model object to update + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + + Returns: + - ``model`: modified model + + Make sure you have plenty of CPU memory available before you call this function. If you don't + have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it + conveniently placed for you in the checkpoint folder. + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint + model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir) + # submit to model hub or save the model to share with others + + Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context + of the same application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + """ + logger.info(f"Extracting fp32 weights") + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag) + + logger.info(f"Overwriting model with fp32 weights") + model = model.cpu() + model.load_state_dict(state_dict, strict=False) + + return model + + +if __name__ == "__main__": + parser = argparse.ArgumentParser() + parser.add_argument("checkpoint_dir", + type=str, + help="path to the desired checkpoint folder, e.g., path/checkpoint-12") + parser.add_argument("output_dir", + type=str, + help="directory to the pytorch fp32 state_dict output files" + "(e.g. path/checkpoint-12-output/)") + parser.add_argument( + "--max_shard_size", + type=str, + default="5GB", + help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size" + "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`" + "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances" + "without CPU OOM issues.") + parser.add_argument( + "--safe_serialization", + default=False, + action='store_true', + help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).") + parser.add_argument("-t", + "--tag", + type=str, + default=None, + help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1") + parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters") + parser.add_argument("-d", "--debug", action='store_true', help="enable debug") + args = parser.parse_args() + + debug = args.debug + + convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, + args.output_dir, + max_shard_size=args.max_shard_size, + safe_serialization=args.safe_serialization, + tag=args.tag, + exclude_frozen_parameters=args.exclude_frozen_parameters) diff --git a/checkpoint-500/chat_template.jinja b/checkpoint-500/chat_template.jinja new file mode 100644 index 0000000..39bd0c9 --- /dev/null +++ b/checkpoint-500/chat_template.jinja @@ -0,0 +1,5 @@ +{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|> + +'+ 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|> + +' }}{% endif %} \ No newline at end of file diff --git a/checkpoint-500/config.json b/checkpoint-500/config.json new file mode 100644 index 0000000..3f8f5c0 --- /dev/null +++ b/checkpoint-500/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": "bfloat16", + "transformers_version": "4.54.1", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/checkpoint-500/generation_config.json b/checkpoint-500/generation_config.json new file mode 100644 index 0000000..fc3c54a --- /dev/null +++ b/checkpoint-500/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "eos_token_id": 128001, + "transformers_version": "4.54.1" +} diff --git a/checkpoint-500/latest b/checkpoint-500/latest new file mode 100644 index 0000000..f0b47ce --- /dev/null +++ b/checkpoint-500/latest @@ -0,0 +1 @@ +global_step500 \ No newline at end of file diff --git a/checkpoint-500/model-00001-of-00004.safetensors b/checkpoint-500/model-00001-of-00004.safetensors new file mode 100644 index 0000000..dfc0073 --- /dev/null +++ b/checkpoint-500/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd352a69d690bfac80c07bc9573f8a3db74c5cae3613b44e648aea38245e8bf8 +size 4976698672 diff --git a/checkpoint-500/model-00002-of-00004.safetensors b/checkpoint-500/model-00002-of-00004.safetensors new file mode 100644 index 0000000..e5523f8 --- /dev/null +++ b/checkpoint-500/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dae71313c6039729409cfa749c62581e7635546483b43c5365a4d65b17048ebb +size 4999802720 diff --git a/checkpoint-500/model-00003-of-00004.safetensors b/checkpoint-500/model-00003-of-00004.safetensors new file mode 100644 index 0000000..552385d --- /dev/null +++ b/checkpoint-500/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81fe67c7769733dadf27291a27ca0e55f009971b0daceccccf841b1b441a8be6 +size 4915916176 diff --git a/checkpoint-500/model-00004-of-00004.safetensors b/checkpoint-500/model-00004-of-00004.safetensors new file mode 100644 index 0000000..1b28d9a --- /dev/null +++ b/checkpoint-500/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16177bc67a220fc32404fe8d26d1994db3ebc66f101e647efdfd4157f7d6912d +size 1168138808 diff --git a/checkpoint-500/model.safetensors.index.json b/checkpoint-500/model.safetensors.index.json new file mode 100644 index 0000000..58a7ef4 --- /dev/null +++ b/checkpoint-500/model.safetensors.index.json @@ -0,0 +1,299 @@ +{ + "metadata": { + "total_parameters": 266240, + "total_size": 16060522496 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/checkpoint-500/rng_state_0.pth b/checkpoint-500/rng_state_0.pth new file mode 100644 index 0000000..6ae1c3a --- /dev/null +++ b/checkpoint-500/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33fe1a45c0111b18df213058c73c3a4e717295b975e92faf7b2e048e6504b3f3 +size 14917 diff --git a/checkpoint-500/rng_state_1.pth b/checkpoint-500/rng_state_1.pth new file mode 100644 index 0000000..58bf4e2 --- /dev/null +++ b/checkpoint-500/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bf26da988f2f17ca0d366aece1dfdb5c3bcab91066168b7062b361b8c3ac2d6 +size 14917 diff --git a/checkpoint-500/scheduler.pt b/checkpoint-500/scheduler.pt new file mode 100644 index 0000000..a2af8e9 --- /dev/null +++ b/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f8728b8c285bed1ca96ea99a5e658a8a9c58f9dd1ce1805f1213195612503b +size 1465 diff --git a/checkpoint-500/special_tokens_map.json b/checkpoint-500/special_tokens_map.json new file mode 100644 index 0000000..e5b39b6 --- /dev/null +++ b/checkpoint-500/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "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": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-500/tokenizer.json b/checkpoint-500/tokenizer.json new file mode 100644 index 0000000..03aa64f --- /dev/null +++ b/checkpoint-500/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0968dcc0ee8e56c7dccd34a7f51f8065ea0cb9e2cc529e3243d1e5c0a4bdaa0c +size 17208754 diff --git a/checkpoint-500/tokenizer_config.json b/checkpoint-500/tokenizer_config.json new file mode 100644 index 0000000..877a9a9 --- /dev/null +++ b/checkpoint-500/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "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|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|end_of_text|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 32768, + "pad_token": "<|end_of_text|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-500/trainer_state.json b/checkpoint-500/trainer_state.json new file mode 100644 index 0000000..8650a35 --- /dev/null +++ b/checkpoint-500/trainer_state.json @@ -0,0 +1,1127 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.26171159382360637, + "eval_steps": 500, + "global_step": 500, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0005234231876472127, + "grad_norm": 124.9239730834961, + "learning_rate": 0.0, + "logits/chosen": -0.4007568359375, + "logits/rejected": -0.41790771484375, + "logps/chosen": -297.796875, + "logps/rejected": -248.078125, + "logps/weighted_chosen": -4.70263671875, + "logps/weighted_rejected": -3.35546875, + "loss": 0.6914, + "rewards/accuracies": 0.0, + "rewards/chosen": 0.0, + "rewards/margins": 0.0, + "rewards/rejected": 0.0, + "rewards/weighted_accuracies": 0.0, + "rewards/weighted_chosen": 0.0, + "rewards/weighted_margins": 0.0, + "rewards/weighted_rejected": 0.0, + "step": 1 + }, + { + "epoch": 0.005234231876472127, + "grad_norm": 265.8483581542969, + "learning_rate": 4.6875e-08, + "logits/chosen": -0.3176540732383728, + "logits/rejected": -0.3532511293888092, + "logps/chosen": -275.5720520019531, + "logps/rejected": -255.88714599609375, + "logps/weighted_chosen": -2.5362956523895264, + "logps/weighted_rejected": -2.774468421936035, + "loss": 0.6903, + "rewards/accuracies": 0.2743055522441864, + "rewards/chosen": 0.0078125, + "rewards/margins": 0.02973090298473835, + "rewards/rejected": -0.02191840298473835, + "rewards/weighted_accuracies": 0.3055555522441864, + "rewards/weighted_chosen": 0.0025702582206577063, + "rewards/weighted_margins": 0.0017564562149345875, + "rewards/weighted_rejected": 0.0008138020639307797, + "step": 10 + }, + { + "epoch": 0.010468463752944255, + "grad_norm": 17.298032760620117, + "learning_rate": 9.895833333333332e-08, + "logits/chosen": -0.2979484498500824, + "logits/rejected": -0.3138488829135895, + "logps/chosen": -294.40625, + "logps/rejected": -272.69061279296875, + "logps/weighted_chosen": -2.3424315452575684, + "logps/weighted_rejected": -2.307080030441284, + "loss": 0.6912, + "rewards/accuracies": 0.296875, + "rewards/chosen": 0.007617187686264515, + "rewards/margins": 0.05781250074505806, + "rewards/rejected": -0.05019531399011612, + "rewards/weighted_accuracies": 0.3531250059604645, + "rewards/weighted_chosen": 0.0003913879336323589, + "rewards/weighted_margins": 0.00116729736328125, + "rewards/weighted_rejected": -0.0007759094005450606, + "step": 20 + }, + { + "epoch": 0.015702695629416383, + "grad_norm": 79.90486907958984, + "learning_rate": 1.5104166666666664e-07, + "logits/chosen": -0.2918685972690582, + "logits/rejected": -0.3376312255859375, + "logps/chosen": -298.02032470703125, + "logps/rejected": -268.0210876464844, + "logps/weighted_chosen": -2.290698289871216, + "logps/weighted_rejected": -2.578540086746216, + "loss": 0.6921, + "rewards/accuracies": 0.3187499940395355, + "rewards/chosen": 0.0751953125, + "rewards/margins": 0.10107421875, + "rewards/rejected": -0.02587890625, + "rewards/weighted_accuracies": 0.375, + "rewards/weighted_chosen": 0.0023864745162427425, + "rewards/weighted_margins": -9.1552734375e-05, + "rewards/weighted_rejected": 0.0024780272506177425, + "step": 30 + }, + { + "epoch": 0.02093692750588851, + "grad_norm": 32.818607330322266, + "learning_rate": 2.03125e-07, + "logits/chosen": -0.3010299801826477, + "logits/rejected": -0.3435005247592926, + "logps/chosen": -278.60235595703125, + "logps/rejected": -253.9250030517578, + "logps/weighted_chosen": -2.3670654296875, + "logps/weighted_rejected": -2.760937452316284, + "loss": 0.6923, + "rewards/accuracies": 0.34375, + "rewards/chosen": 0.12041015923023224, + "rewards/margins": 0.13857421278953552, + "rewards/rejected": -0.01816406287252903, + "rewards/weighted_accuracies": 0.4156250059604645, + "rewards/weighted_chosen": 0.0007911681896075606, + "rewards/weighted_margins": -0.00026035308837890625, + "rewards/weighted_rejected": 0.0010513305896893144, + "step": 40 + }, + { + "epoch": 0.02617115938236064, + "grad_norm": 17.478111267089844, + "learning_rate": 2.552083333333333e-07, + "logits/chosen": -0.2825515866279602, + "logits/rejected": -0.3209354281425476, + "logps/chosen": -280.23126220703125, + "logps/rejected": -267.45001220703125, + "logps/weighted_chosen": -2.329760789871216, + "logps/weighted_rejected": -2.414306640625, + "loss": 0.6877, + "rewards/accuracies": 0.30937498807907104, + "rewards/chosen": 0.01835937425494194, + "rewards/margins": -0.06035156175494194, + "rewards/rejected": 0.07871093600988388, + "rewards/weighted_accuracies": 0.41874998807907104, + "rewards/weighted_chosen": 0.0070404051803052425, + "rewards/weighted_margins": 0.00885009765625, + "rewards/weighted_rejected": -0.0018066406482830644, + "step": 50 + }, + { + "epoch": 0.031405391258832765, + "grad_norm": 39.04142761230469, + "learning_rate": 3.0729166666666665e-07, + "logits/chosen": -0.3157821595668793, + "logits/rejected": -0.30972975492477417, + "logps/chosen": -277.58123779296875, + "logps/rejected": -261.6187438964844, + "logps/weighted_chosen": -2.753100633621216, + "logps/weighted_rejected": -2.6282715797424316, + "loss": 0.6846, + "rewards/accuracies": 0.34687501192092896, + "rewards/chosen": 0.13593749701976776, + "rewards/margins": 0.02968749962747097, + "rewards/rejected": 0.10625000298023224, + "rewards/weighted_accuracies": 0.4937500059604645, + "rewards/weighted_chosen": 0.02093353308737278, + "rewards/weighted_margins": 0.015999604016542435, + "rewards/weighted_rejected": 0.0049346922896802425, + "step": 60 + }, + { + "epoch": 0.036639623135304895, + "grad_norm": 73.14978790283203, + "learning_rate": 3.59375e-07, + "logits/chosen": -0.32021790742874146, + "logits/rejected": -0.32699280977249146, + "logps/chosen": -289.6148376464844, + "logps/rejected": -244.8367156982422, + "logps/weighted_chosen": -2.221527099609375, + "logps/weighted_rejected": -2.581958055496216, + "loss": 0.6775, + "rewards/accuracies": 0.49687498807907104, + "rewards/chosen": 0.43046873807907104, + "rewards/margins": 0.5244140625, + "rewards/rejected": -0.09394530951976776, + "rewards/weighted_accuracies": 0.53125, + "rewards/weighted_chosen": 0.030600737780332565, + "rewards/weighted_margins": 0.034238435328006744, + "rewards/weighted_rejected": -0.0036373138427734375, + "step": 70 + }, + { + "epoch": 0.04187385501177702, + "grad_norm": 65.60453796386719, + "learning_rate": 4.114583333333333e-07, + "logits/chosen": -0.28860169649124146, + "logits/rejected": -0.3099655210971832, + "logps/chosen": -289.33984375, + "logps/rejected": -270.3453063964844, + "logps/weighted_chosen": -2.456127882003784, + "logps/weighted_rejected": -2.6986327171325684, + "loss": 0.6733, + "rewards/accuracies": 0.48124998807907104, + "rewards/chosen": 0.509765625, + "rewards/margins": 0.56396484375, + "rewards/rejected": -0.05419921875, + "rewards/weighted_accuracies": 0.5625, + "rewards/weighted_chosen": 0.04326324537396431, + "rewards/weighted_margins": 0.05183257907629013, + "rewards/weighted_rejected": -0.008570862002670765, + "step": 80 + }, + { + "epoch": 0.04710808688824915, + "grad_norm": 30.41583824157715, + "learning_rate": 4.6354166666666664e-07, + "logits/chosen": -0.3197769224643707, + "logits/rejected": -0.3126419186592102, + "logps/chosen": -280.0874938964844, + "logps/rejected": -257.95782470703125, + "logps/weighted_chosen": -2.6199097633361816, + "logps/weighted_rejected": -2.705517530441284, + "loss": 0.6743, + "rewards/accuracies": 0.4937500059604645, + "rewards/chosen": 0.5191406011581421, + "rewards/margins": 0.6358398199081421, + "rewards/rejected": -0.11669921875, + "rewards/weighted_accuracies": 0.5718749761581421, + "rewards/weighted_chosen": 0.07943420112133026, + "rewards/weighted_margins": 0.07568969577550888, + "rewards/weighted_rejected": 0.003753662109375, + "step": 90 + }, + { + "epoch": 0.05234231876472128, + "grad_norm": 61.700382232666016, + "learning_rate": 5.156249999999999e-07, + "logits/chosen": -0.2895751893520355, + "logits/rejected": -0.3621200621128082, + "logps/chosen": -290.88592529296875, + "logps/rejected": -286.73126220703125, + "logps/weighted_chosen": -2.083447217941284, + "logps/weighted_rejected": -2.6861205101013184, + "loss": 0.6862, + "rewards/accuracies": 0.5406249761581421, + "rewards/chosen": 0.10849609225988388, + "rewards/margins": 0.94482421875, + "rewards/rejected": -0.8363281488418579, + "rewards/weighted_accuracies": 0.574999988079071, + "rewards/weighted_chosen": 0.05786743015050888, + "rewards/weighted_margins": 0.058258056640625, + "rewards/weighted_rejected": -0.0002998351992573589, + "step": 100 + }, + { + "epoch": 0.05757655064119341, + "grad_norm": 33.45664978027344, + "learning_rate": 5.677083333333333e-07, + "logits/chosen": -0.3412017822265625, + "logits/rejected": -0.3312934935092926, + "logps/chosen": -296.8671875, + "logps/rejected": -262.3460998535156, + "logps/weighted_chosen": -2.776904344558716, + "logps/weighted_rejected": -2.8023438453674316, + "loss": 0.6835, + "rewards/accuracies": 0.546875, + "rewards/chosen": -0.4873046875, + "rewards/margins": 1.0051758289337158, + "rewards/rejected": -1.4924805164337158, + "rewards/weighted_accuracies": 0.5062500238418579, + "rewards/weighted_chosen": 0.01709899865090847, + "rewards/weighted_margins": 0.05614929273724556, + "rewards/weighted_rejected": -0.03909149020910263, + "step": 110 + }, + { + "epoch": 0.06281078251766553, + "grad_norm": 61.74055862426758, + "learning_rate": 6.197916666666666e-07, + "logits/chosen": -0.3482359051704407, + "logits/rejected": -0.3736562728881836, + "logps/chosen": -295.49530029296875, + "logps/rejected": -256.08282470703125, + "logps/weighted_chosen": -2.066760301589966, + "logps/weighted_rejected": -2.2858643531799316, + "loss": 0.6833, + "rewards/accuracies": 0.5687500238418579, + "rewards/chosen": -0.8194335699081421, + "rewards/margins": 1.502539038658142, + "rewards/rejected": -2.321972608566284, + "rewards/weighted_accuracies": 0.5874999761581421, + "rewards/weighted_chosen": 0.01521911658346653, + "rewards/weighted_margins": 0.05682678148150444, + "rewards/weighted_rejected": -0.04169006273150444, + "step": 120 + }, + { + "epoch": 0.06804501439413765, + "grad_norm": 45.78140640258789, + "learning_rate": 6.718749999999999e-07, + "logits/chosen": -0.3164505064487457, + "logits/rejected": -0.3121093809604645, + "logps/chosen": -306.4761657714844, + "logps/rejected": -279.87030029296875, + "logps/weighted_chosen": -2.1032347679138184, + "logps/weighted_rejected": -2.432788133621216, + "loss": 0.6718, + "rewards/accuracies": 0.6312500238418579, + "rewards/chosen": -0.4637207090854645, + "rewards/margins": 1.8840820789337158, + "rewards/rejected": -2.347851514816284, + "rewards/weighted_accuracies": 0.559374988079071, + "rewards/weighted_chosen": 0.01874847337603569, + "rewards/weighted_margins": 0.07195129245519638, + "rewards/weighted_rejected": -0.05319824069738388, + "step": 130 + }, + { + "epoch": 0.07327924627060979, + "grad_norm": 47.97172546386719, + "learning_rate": 7.239583333333333e-07, + "logits/chosen": -0.36130523681640625, + "logits/rejected": -0.3767889142036438, + "logps/chosen": -300.2398376464844, + "logps/rejected": -276.47344970703125, + "logps/weighted_chosen": -2.402172803878784, + "logps/weighted_rejected": -2.704345703125, + "loss": 0.6601, + "rewards/accuracies": 0.625, + "rewards/chosen": -1.6025390625, + "rewards/margins": 2.2777342796325684, + "rewards/rejected": -3.8802733421325684, + "rewards/weighted_accuracies": 0.628125011920929, + "rewards/weighted_chosen": 0.0066894530318677425, + "rewards/weighted_margins": 0.10413207858800888, + "rewards/weighted_rejected": -0.0973968505859375, + "step": 140 + }, + { + "epoch": 0.07851347814708191, + "grad_norm": 18.48399543762207, + "learning_rate": 7.760416666666666e-07, + "logits/chosen": -0.3260757327079773, + "logits/rejected": -0.33597564697265625, + "logps/chosen": -286.6578063964844, + "logps/rejected": -255.8078155517578, + "logps/weighted_chosen": -2.939697265625, + "logps/weighted_rejected": -2.9384522438049316, + "loss": 0.6693, + "rewards/accuracies": 0.6312500238418579, + "rewards/chosen": -2.329296827316284, + "rewards/margins": 2.532031297683716, + "rewards/rejected": -4.861328125, + "rewards/weighted_accuracies": 0.625, + "rewards/weighted_chosen": 0.01940460130572319, + "rewards/weighted_margins": 0.12819823622703552, + "rewards/weighted_rejected": -0.10869445651769638, + "step": 150 + }, + { + "epoch": 0.08374771002355404, + "grad_norm": 16.847576141357422, + "learning_rate": 8.28125e-07, + "logits/chosen": -0.37299805879592896, + "logits/rejected": -0.4207763671875, + "logps/chosen": -306.01873779296875, + "logps/rejected": -279.0289001464844, + "logps/weighted_chosen": -2.4432616233825684, + "logps/weighted_rejected": -2.4922118186950684, + "loss": 0.631, + "rewards/accuracies": 0.6468750238418579, + "rewards/chosen": -2.1587891578674316, + "rewards/margins": 3.69091796875, + "rewards/rejected": -5.849707126617432, + "rewards/weighted_accuracies": 0.637499988079071, + "rewards/weighted_chosen": 0.04796142503619194, + "rewards/weighted_margins": 0.21007385849952698, + "rewards/weighted_rejected": -0.1621856689453125, + "step": 160 + }, + { + "epoch": 0.08898194190002617, + "grad_norm": 237.514404296875, + "learning_rate": 8.802083333333333e-07, + "logits/chosen": -0.42098236083984375, + "logits/rejected": -0.4231323301792145, + "logps/chosen": -306.859375, + "logps/rejected": -266.03125, + "logps/weighted_chosen": -2.6180663108825684, + "logps/weighted_rejected": -2.9256348609924316, + "loss": 0.709, + "rewards/accuracies": 0.6343749761581421, + "rewards/chosen": -3.73828125, + "rewards/margins": 4.098242282867432, + "rewards/rejected": -7.836328029632568, + "rewards/weighted_accuracies": 0.6031249761581421, + "rewards/weighted_chosen": 0.06289978325366974, + "rewards/weighted_margins": 0.186981201171875, + "rewards/weighted_rejected": -0.12393493950366974, + "step": 170 + }, + { + "epoch": 0.0942161737764983, + "grad_norm": 52.46952819824219, + "learning_rate": 9.322916666666666e-07, + "logits/chosen": -0.38860780000686646, + "logits/rejected": -0.40771445631980896, + "logps/chosen": -280.2789001464844, + "logps/rejected": -267.69219970703125, + "logps/weighted_chosen": -2.579449415206909, + "logps/weighted_rejected": -3.0037841796875, + "loss": 0.6853, + "rewards/accuracies": 0.6343749761581421, + "rewards/chosen": -6.609179496765137, + "rewards/margins": 4.819726467132568, + "rewards/rejected": -11.427831649780273, + "rewards/weighted_accuracies": 0.6031249761581421, + "rewards/weighted_chosen": -0.04149780422449112, + "rewards/weighted_margins": 0.20274047553539276, + "rewards/weighted_rejected": -0.24451598525047302, + "step": 180 + }, + { + "epoch": 0.09945040565297043, + "grad_norm": 37.741477966308594, + "learning_rate": 9.84375e-07, + "logits/chosen": -0.4061637818813324, + "logits/rejected": -0.4410812258720398, + "logps/chosen": -314.60626220703125, + "logps/rejected": -278.87811279296875, + "logps/weighted_chosen": -2.378369092941284, + "logps/weighted_rejected": -2.7929444313049316, + "loss": 0.6517, + "rewards/accuracies": 0.625, + "rewards/chosen": -8.988476753234863, + "rewards/margins": 6.061327934265137, + "rewards/rejected": -15.050390243530273, + "rewards/weighted_accuracies": 0.621874988079071, + "rewards/weighted_chosen": -0.11425475776195526, + "rewards/weighted_margins": 0.22973021864891052, + "rewards/weighted_rejected": -0.3441314697265625, + "step": 190 + }, + { + "epoch": 0.10468463752944256, + "grad_norm": 76.11390686035156, + "learning_rate": 9.99959085414323e-07, + "logits/chosen": -0.4347488284111023, + "logits/rejected": -0.46932679414749146, + "logps/chosen": -319.34686279296875, + "logps/rejected": -274.1890563964844, + "logps/weighted_chosen": -2.6759276390075684, + "logps/weighted_rejected": -3.110583543777466, + "loss": 0.6539, + "rewards/accuracies": 0.6312500238418579, + "rewards/chosen": -10.064160346984863, + "rewards/margins": 6.332421779632568, + "rewards/rejected": -16.395898818969727, + "rewards/weighted_accuracies": 0.612500011920929, + "rewards/weighted_chosen": -0.08293457329273224, + "rewards/weighted_margins": 0.25919800996780396, + "rewards/weighted_rejected": -0.34211426973342896, + "step": 200 + }, + { + "epoch": 0.10991886940591468, + "grad_norm": 19.709537506103516, + "learning_rate": 9.997587035630105e-07, + "logits/chosen": -0.4373016357421875, + "logits/rejected": -0.47842711210250854, + "logps/chosen": -298.6578063964844, + "logps/rejected": -305.07733154296875, + "logps/weighted_chosen": -2.4120116233825684, + "logps/weighted_rejected": -3.137524366378784, + "loss": 0.6448, + "rewards/accuracies": 0.6656249761581421, + "rewards/chosen": -11.547070503234863, + "rewards/margins": 8.876855850219727, + "rewards/rejected": -20.425390243530273, + "rewards/weighted_accuracies": 0.659375011920929, + "rewards/weighted_chosen": -0.12418060004711151, + "rewards/weighted_margins": 0.24833527207374573, + "rewards/weighted_rejected": -0.37247925996780396, + "step": 210 + }, + { + "epoch": 0.11515310128238682, + "grad_norm": 39.1947135925293, + "learning_rate": 9.99391406364405e-07, + "logits/chosen": -0.424050897359848, + "logits/rejected": -0.4263656735420227, + "logps/chosen": -306.5453186035156, + "logps/rejected": -291.21405029296875, + "logps/weighted_chosen": -2.8793702125549316, + "logps/weighted_rejected": -3.2673583030700684, + "loss": 0.6969, + "rewards/accuracies": 0.612500011920929, + "rewards/chosen": -14.446874618530273, + "rewards/margins": 7.897851467132568, + "rewards/rejected": -22.343358993530273, + "rewards/weighted_accuracies": 0.606249988079071, + "rewards/weighted_chosen": -0.2553466856479645, + "rewards/weighted_margins": 0.21260376274585724, + "rewards/weighted_rejected": -0.46800535917282104, + "step": 220 + }, + { + "epoch": 0.12038733315885894, + "grad_norm": 437.028564453125, + "learning_rate": 9.988573164927884e-07, + "logits/chosen": -0.3824310302734375, + "logits/rejected": -0.4174056947231293, + "logps/chosen": -282.2710876464844, + "logps/rejected": -277.2734375, + "logps/weighted_chosen": -2.547900438308716, + "logps/weighted_rejected": -2.85693359375, + "loss": 0.7367, + "rewards/accuracies": 0.675000011920929, + "rewards/chosen": -13.438867568969727, + "rewards/margins": 12.128320693969727, + "rewards/rejected": -25.565820693969727, + "rewards/weighted_accuracies": 0.621874988079071, + "rewards/weighted_chosen": -0.24434813857078552, + "rewards/weighted_margins": 0.2164306640625, + "rewards/weighted_rejected": -0.4607299864292145, + "step": 230 + }, + { + "epoch": 0.12562156503533106, + "grad_norm": 139.88975524902344, + "learning_rate": 9.98156612329838e-07, + "logits/chosen": -0.4804244935512543, + "logits/rejected": -0.527056872844696, + "logps/chosen": -279.6773376464844, + "logps/rejected": -310.64532470703125, + "logps/weighted_chosen": -2.464794874191284, + "logps/weighted_rejected": -3.058520555496216, + "loss": 0.6735, + "rewards/accuracies": 0.637499988079071, + "rewards/chosen": -14.966699600219727, + "rewards/margins": 13.450976371765137, + "rewards/rejected": -28.419336318969727, + "rewards/weighted_accuracies": 0.6625000238418579, + "rewards/weighted_chosen": -0.11341552436351776, + "rewards/weighted_margins": 0.26569825410842896, + "rewards/weighted_rejected": -0.37919312715530396, + "step": 240 + }, + { + "epoch": 0.13085579691180318, + "grad_norm": 939.5078125, + "learning_rate": 9.97289527905053e-07, + "logits/chosen": -0.4899856448173523, + "logits/rejected": -0.4979141354560852, + "logps/chosen": -281.9039001464844, + "logps/rejected": -282.93438720703125, + "logps/weighted_chosen": -2.8607420921325684, + "logps/weighted_rejected": -3.0235595703125, + "loss": 0.7231, + "rewards/accuracies": 0.6343749761581421, + "rewards/chosen": -17.384668350219727, + "rewards/margins": 9.600194931030273, + "rewards/rejected": -26.986328125, + "rewards/weighted_accuracies": 0.5843750238418579, + "rewards/weighted_chosen": -0.20379944145679474, + "rewards/weighted_margins": 0.18174438178539276, + "rewards/weighted_rejected": -0.3856750428676605, + "step": 250 + }, + { + "epoch": 0.1360900287882753, + "grad_norm": 24.300647735595703, + "learning_rate": 9.962563528175875e-07, + "logits/chosen": -0.4584365785121918, + "logits/rejected": -0.4911254942417145, + "logps/chosen": -317.06329345703125, + "logps/rejected": -289.06561279296875, + "logps/weighted_chosen": -2.4532713890075684, + "logps/weighted_rejected": -3.330212354660034, + "loss": 0.6636, + "rewards/accuracies": 0.590624988079071, + "rewards/chosen": -18.153711318969727, + "rewards/margins": 10.150195121765137, + "rewards/rejected": -28.3046875, + "rewards/weighted_accuracies": 0.6187499761581421, + "rewards/weighted_chosen": -0.18357238173484802, + "rewards/weighted_margins": 0.269927978515625, + "rewards/weighted_rejected": -0.4535202085971832, + "step": 260 + }, + { + "epoch": 0.14132426066474746, + "grad_norm": 228.46092224121094, + "learning_rate": 9.950574321395277e-07, + "logits/chosen": -0.4871993958950043, + "logits/rejected": -0.5071777105331421, + "logps/chosen": -310.2124938964844, + "logps/rejected": -291.5687561035156, + "logps/weighted_chosen": -2.747607469558716, + "logps/weighted_rejected": -3.0499024391174316, + "loss": 0.6525, + "rewards/accuracies": 0.6156250238418579, + "rewards/chosen": -20.7822265625, + "rewards/margins": 7.598730564117432, + "rewards/rejected": -28.382030487060547, + "rewards/weighted_accuracies": 0.6499999761581421, + "rewards/weighted_chosen": -0.2510986328125, + "rewards/weighted_margins": 0.2596893310546875, + "rewards/weighted_rejected": -0.5105804204940796, + "step": 270 + }, + { + "epoch": 0.14655849254121958, + "grad_norm": 713.1409912109375, + "learning_rate": 9.936931663006413e-07, + "logits/chosen": -0.4856887757778168, + "logits/rejected": -0.4791274964809418, + "logps/chosen": -323.875, + "logps/rejected": -312.1109313964844, + "logps/weighted_chosen": -2.7660155296325684, + "logps/weighted_rejected": -3.293591260910034, + "loss": 0.6155, + "rewards/accuracies": 0.671875, + "rewards/chosen": -20.981639862060547, + "rewards/margins": 11.869140625, + "rewards/rejected": -32.850975036621094, + "rewards/weighted_accuracies": 0.675000011920929, + "rewards/weighted_chosen": -0.13939818739891052, + "rewards/weighted_margins": 0.34244996309280396, + "rewards/weighted_rejected": -0.48178404569625854, + "step": 280 + }, + { + "epoch": 0.1517927244176917, + "grad_norm": 10845.4873046875, + "learning_rate": 9.921640109546357e-07, + "logits/chosen": -0.433615118265152, + "logits/rejected": -0.5038871765136719, + "logps/chosen": -285.6937561035156, + "logps/rejected": -280.76251220703125, + "logps/weighted_chosen": -2.63427734375, + "logps/weighted_rejected": -3.711669921875, + "loss": 0.65, + "rewards/accuracies": 0.6625000238418579, + "rewards/chosen": -18.829492568969727, + "rewards/margins": 10.345703125, + "rewards/rejected": -29.1728515625, + "rewards/weighted_accuracies": 0.6187499761581421, + "rewards/weighted_chosen": -0.12302856147289276, + "rewards/weighted_margins": 0.3319152891635895, + "rewards/weighted_rejected": -0.45494383573532104, + "step": 290 + }, + { + "epoch": 0.15702695629416383, + "grad_norm": 47.70283889770508, + "learning_rate": 9.90470476826975e-07, + "logits/chosen": -0.4355606138706207, + "logits/rejected": -0.4278717041015625, + "logps/chosen": -288.78045654296875, + "logps/rejected": -296.9765625, + "logps/weighted_chosen": -2.532849073410034, + "logps/weighted_rejected": -3.0221924781799316, + "loss": 0.6674, + "rewards/accuracies": 0.6625000238418579, + "rewards/chosen": -19.346094131469727, + "rewards/margins": 10.255078315734863, + "rewards/rejected": -29.59765625, + "rewards/weighted_accuracies": 0.6187499761581421, + "rewards/weighted_chosen": -0.21412047743797302, + "rewards/weighted_margins": 0.2544006407260895, + "rewards/weighted_rejected": -0.4681999087333679, + "step": 300 + }, + { + "epoch": 0.16226118817063595, + "grad_norm": 644.2051391601562, + "learning_rate": 9.886131295443002e-07, + "logits/chosen": -0.462362676858902, + "logits/rejected": -0.5182906985282898, + "logps/chosen": -301.2421875, + "logps/rejected": -280.125, + "logps/weighted_chosen": -2.5293211936950684, + "logps/weighted_rejected": -2.9417481422424316, + "loss": 0.6339, + "rewards/accuracies": 0.668749988079071, + "rewards/chosen": -19.940235137939453, + "rewards/margins": 9.952539443969727, + "rewards/rejected": -29.892187118530273, + "rewards/weighted_accuracies": 0.65625, + "rewards/weighted_chosen": 0.0126800537109375, + "rewards/weighted_margins": 0.4334716796875, + "rewards/weighted_rejected": -0.42060548067092896, + "step": 310 + }, + { + "epoch": 0.16749542004710807, + "grad_norm": 42.43592834472656, + "learning_rate": 9.865925894455166e-07, + "logits/chosen": -0.538470447063446, + "logits/rejected": -0.5473419427871704, + "logps/chosen": -323.84686279296875, + "logps/rejected": -290.7406311035156, + "logps/weighted_chosen": -2.8351807594299316, + "logps/weighted_rejected": -3.2470703125, + "loss": 0.6762, + "rewards/accuracies": 0.637499988079071, + "rewards/chosen": -23.906444549560547, + "rewards/margins": 9.430078506469727, + "rewards/rejected": -33.3359375, + "rewards/weighted_accuracies": 0.6187499761581421, + "rewards/weighted_chosen": -0.23797301948070526, + "rewards/weighted_margins": 0.272064208984375, + "rewards/weighted_rejected": -0.5102294683456421, + "step": 320 + }, + { + "epoch": 0.17272965192358022, + "grad_norm": 46.229000091552734, + "learning_rate": 9.84409531374603e-07, + "logits/chosen": -0.5096954107284546, + "logits/rejected": -0.4907272458076477, + "logps/chosen": -332.18280029296875, + "logps/rejected": -298.5718688964844, + "logps/weighted_chosen": -2.775341749191284, + "logps/weighted_rejected": -3.165026903152466, + "loss": 0.6741, + "rewards/accuracies": 0.637499988079071, + "rewards/chosen": -27.408203125, + "rewards/margins": 8.212109565734863, + "rewards/rejected": -35.61640548706055, + "rewards/weighted_accuracies": 0.6312500238418579, + "rewards/weighted_chosen": -0.17764969170093536, + "rewards/weighted_margins": 0.241455078125, + "rewards/weighted_rejected": -0.41897353529930115, + "step": 330 + }, + { + "epoch": 0.17796388380005235, + "grad_norm": 70.134521484375, + "learning_rate": 9.820646844552219e-07, + "logits/chosen": -0.5079803466796875, + "logits/rejected": -0.5622657537460327, + "logps/chosen": -301.3257751464844, + "logps/rejected": -303.1468811035156, + "logps/weighted_chosen": -2.852612257003784, + "logps/weighted_rejected": -3.0445556640625, + "loss": 0.6485, + "rewards/accuracies": 0.6968749761581421, + "rewards/chosen": -24.6875, + "rewards/margins": 12.933984756469727, + "rewards/rejected": -37.61992263793945, + "rewards/weighted_accuracies": 0.65625, + "rewards/weighted_chosen": -0.19311293959617615, + "rewards/weighted_margins": 0.3020080626010895, + "rewards/weighted_rejected": -0.4951171875, + "step": 340 + }, + { + "epoch": 0.18319811567652447, + "grad_norm": 37.5682373046875, + "learning_rate": 9.795588318471964e-07, + "logits/chosen": -0.5787566900253296, + "logits/rejected": -0.5869846343994141, + "logps/chosen": -283.0796813964844, + "logps/rejected": -310.00469970703125, + "logps/weighted_chosen": -2.5658936500549316, + "logps/weighted_rejected": -2.95947265625, + "loss": 0.6307, + "rewards/accuracies": 0.625, + "rewards/chosen": -23.71875, + "rewards/margins": 9.896288871765137, + "rewards/rejected": -33.61249923706055, + "rewards/weighted_accuracies": 0.6468750238418579, + "rewards/weighted_chosen": -0.1531631499528885, + "rewards/weighted_margins": 0.32664793729782104, + "rewards/weighted_rejected": -0.479653924703598, + "step": 350 + }, + { + "epoch": 0.1884323475529966, + "grad_norm": 145.69015502929688, + "learning_rate": 9.768928104849415e-07, + "logits/chosen": -0.6053832769393921, + "logits/rejected": -0.6036437749862671, + "logps/chosen": -306.9140625, + "logps/rejected": -283.77655029296875, + "logps/weighted_chosen": -2.835888624191284, + "logps/weighted_rejected": -2.9885010719299316, + "loss": 0.6741, + "rewards/accuracies": 0.612500011920929, + "rewards/chosen": -24.237499237060547, + "rewards/margins": 10.624218940734863, + "rewards/rejected": -34.85859298706055, + "rewards/weighted_accuracies": 0.640625, + "rewards/weighted_chosen": -0.1663818359375, + "rewards/weighted_margins": 0.3080078065395355, + "rewards/weighted_rejected": -0.4744934141635895, + "step": 360 + }, + { + "epoch": 0.19366657942946872, + "grad_norm": 1347.0242919921875, + "learning_rate": 9.740675107979355e-07, + "logits/chosen": -0.5699676275253296, + "logits/rejected": -0.5878998041152954, + "logps/chosen": -342.36248779296875, + "logps/rejected": -311.7203063964844, + "logps/weighted_chosen": -2.303784132003784, + "logps/weighted_rejected": -3.164013624191284, + "loss": 0.6624, + "rewards/accuracies": 0.6312500238418579, + "rewards/chosen": -27.253124237060547, + "rewards/margins": 9.823046684265137, + "rewards/rejected": -37.07597732543945, + "rewards/weighted_accuracies": 0.643750011920929, + "rewards/weighted_chosen": -0.24745483696460724, + "rewards/weighted_margins": 0.27247315645217896, + "rewards/weighted_rejected": -0.5200088620185852, + "step": 370 + }, + { + "epoch": 0.19890081130594087, + "grad_norm": 1152.541748046875, + "learning_rate": 9.71083876413323e-07, + "logits/chosen": -0.5426742434501648, + "logits/rejected": -0.5510879755020142, + "logps/chosen": -331.25390625, + "logps/rejected": -310.33123779296875, + "logps/weighted_chosen": -2.4026856422424316, + "logps/weighted_rejected": -3.172229051589966, + "loss": 0.6676, + "rewards/accuracies": 0.621874988079071, + "rewards/chosen": -28.869922637939453, + "rewards/margins": 11.865234375, + "rewards/rejected": -40.73320388793945, + "rewards/weighted_accuracies": 0.6187499761581421, + "rewards/weighted_chosen": -0.24112549424171448, + "rewards/weighted_margins": 0.2662292420864105, + "rewards/weighted_rejected": -0.5070465207099915, + "step": 380 + }, + { + "epoch": 0.204135043182413, + "grad_norm": 69.06751251220703, + "learning_rate": 9.67942903840751e-07, + "logits/chosen": -0.5844222903251648, + "logits/rejected": -0.6357940435409546, + "logps/chosen": -331.53436279296875, + "logps/rejected": -316.50469970703125, + "logps/weighted_chosen": -2.523181200027466, + "logps/weighted_rejected": -3.170581102371216, + "loss": 0.6281, + "rewards/accuracies": 0.659375011920929, + "rewards/chosen": -27.312108993530273, + "rewards/margins": 14.989062309265137, + "rewards/rejected": -42.309181213378906, + "rewards/weighted_accuracies": 0.675000011920929, + "rewards/weighted_chosen": -0.17550353705883026, + "rewards/weighted_margins": 0.357177734375, + "rewards/weighted_rejected": -0.532818615436554, + "step": 390 + }, + { + "epoch": 0.2093692750588851, + "grad_norm": 64.58200073242188, + "learning_rate": 9.646456421395447e-07, + "logits/chosen": -0.573455810546875, + "logits/rejected": -0.5838836431503296, + "logps/chosen": -348.1484375, + "logps/rejected": -349.8687438964844, + "logps/weighted_chosen": -2.479809522628784, + "logps/weighted_rejected": -3.226489305496216, + "loss": 0.6551, + "rewards/accuracies": 0.65625, + "rewards/chosen": -29.957422256469727, + "rewards/margins": 16.478321075439453, + "rewards/rejected": -46.43476486206055, + "rewards/weighted_accuracies": 0.640625, + "rewards/weighted_chosen": -0.203724667429924, + "rewards/weighted_margins": 0.254974365234375, + "rewards/weighted_rejected": -0.4586502015590668, + "step": 400 + }, + { + "epoch": 0.21460350693535724, + "grad_norm": 19.509164810180664, + "learning_rate": 9.611931925683266e-07, + "logits/chosen": -0.5067977905273438, + "logits/rejected": -0.5407257080078125, + "logps/chosen": -337.97967529296875, + "logps/rejected": -311.12811279296875, + "logps/weighted_chosen": -2.369091749191284, + "logps/weighted_rejected": -2.994799852371216, + "loss": 0.5919, + "rewards/accuracies": 0.6656249761581421, + "rewards/chosen": -31.741016387939453, + "rewards/margins": 15.541796684265137, + "rewards/rejected": -47.293357849121094, + "rewards/weighted_accuracies": 0.6937500238418579, + "rewards/weighted_chosen": -0.17744140326976776, + "rewards/weighted_margins": 0.386505126953125, + "rewards/weighted_rejected": -0.563507080078125, + "step": 410 + }, + { + "epoch": 0.21983773881182936, + "grad_norm": 29.50520133972168, + "learning_rate": 9.575867082172085e-07, + "logits/chosen": -0.5286194086074829, + "logits/rejected": -0.5688308477401733, + "logps/chosen": -344.96563720703125, + "logps/rejected": -328.64532470703125, + "logps/weighted_chosen": -2.8730225563049316, + "logps/weighted_rejected": -2.930432081222534, + "loss": 0.6442, + "rewards/accuracies": 0.675000011920929, + "rewards/chosen": -40.091796875, + "rewards/margins": 18.596485137939453, + "rewards/rejected": -58.685935974121094, + "rewards/weighted_accuracies": 0.628125011920929, + "rewards/weighted_chosen": -0.38405150175094604, + "rewards/weighted_margins": 0.39207762479782104, + "rewards/weighted_rejected": -0.7763046026229858, + "step": 420 + }, + { + "epoch": 0.22507197068830148, + "grad_norm": 15.081392288208008, + "learning_rate": 9.538273936226673e-07, + "logits/chosen": -0.5923309326171875, + "logits/rejected": -0.625653088092804, + "logps/chosen": -301.640625, + "logps/rejected": -313.77032470703125, + "logps/weighted_chosen": -3.0785889625549316, + "logps/weighted_rejected": -3.5872559547424316, + "loss": 0.668, + "rewards/accuracies": 0.628125011920929, + "rewards/chosen": -36.12675857543945, + "rewards/margins": 13.111328125, + "rewards/rejected": -49.236328125, + "rewards/weighted_accuracies": 0.6312500238418579, + "rewards/weighted_chosen": -0.28452759981155396, + "rewards/weighted_margins": 0.3635620176792145, + "rewards/weighted_rejected": -0.64788818359375, + "step": 430 + }, + { + "epoch": 0.23030620256477363, + "grad_norm": 23.0412540435791, + "learning_rate": 9.499165043652391e-07, + "logits/chosen": -0.5760772824287415, + "logits/rejected": -0.5774017572402954, + "logps/chosen": -328.1015625, + "logps/rejected": -318.84454345703125, + "logps/weighted_chosen": -3.0999755859375, + "logps/weighted_rejected": -3.371142625808716, + "loss": 0.6452, + "rewards/accuracies": 0.640625, + "rewards/chosen": -36.97431564331055, + "rewards/margins": 15.057812690734863, + "rewards/rejected": -52.0390625, + "rewards/weighted_accuracies": 0.628125011920929, + "rewards/weighted_chosen": -0.39061737060546875, + "rewards/weighted_margins": 0.3595825135707855, + "rewards/weighted_rejected": -0.7500244379043579, + "step": 440 + }, + { + "epoch": 0.23554043444124576, + "grad_norm": 22.85993003845215, + "learning_rate": 9.458553466501665e-07, + "logits/chosen": -0.6301513910293579, + "logits/rejected": -0.6610687375068665, + "logps/chosen": -324.77032470703125, + "logps/rejected": -298.57501220703125, + "logps/weighted_chosen": -3.1078124046325684, + "logps/weighted_rejected": -3.38037109375, + "loss": 0.6501, + "rewards/accuracies": 0.640625, + "rewards/chosen": -38.617774963378906, + "rewards/margins": 16.141407012939453, + "rewards/rejected": -54.763671875, + "rewards/weighted_accuracies": 0.653124988079071, + "rewards/weighted_chosen": -0.4693542420864105, + "rewards/weighted_margins": 0.4438629150390625, + "rewards/weighted_rejected": -0.9127838015556335, + "step": 450 + }, + { + "epoch": 0.24077466631771788, + "grad_norm": 11.338366508483887, + "learning_rate": 9.416452768711366e-07, + "logits/chosen": -0.6437957882881165, + "logits/rejected": -0.674633800983429, + "logps/chosen": -333.87188720703125, + "logps/rejected": -318.10467529296875, + "logps/weighted_chosen": -2.8603515625, + "logps/weighted_rejected": -3.472119092941284, + "loss": 0.6881, + "rewards/accuracies": 0.6468750238418579, + "rewards/chosen": -41.862693786621094, + "rewards/margins": 16.437694549560547, + "rewards/rejected": -58.305076599121094, + "rewards/weighted_accuracies": 0.653124988079071, + "rewards/weighted_chosen": -0.43403321504592896, + "rewards/weighted_margins": 0.4345336854457855, + "rewards/weighted_rejected": -0.8688415288925171, + "step": 460 + }, + { + "epoch": 0.24600889819419, + "grad_norm": 35.14228057861328, + "learning_rate": 9.372877011572557e-07, + "logits/chosen": -0.5738860964775085, + "logits/rejected": -0.5953949093818665, + "logps/chosen": -350.23046875, + "logps/rejected": -329.484375, + "logps/weighted_chosen": -2.7630372047424316, + "logps/weighted_rejected": -3.2092041969299316, + "loss": 0.6424, + "rewards/accuracies": 0.6187499761581421, + "rewards/chosen": -39.640037536621094, + "rewards/margins": 15.155468940734863, + "rewards/rejected": -54.796485900878906, + "rewards/weighted_accuracies": 0.671875, + "rewards/weighted_chosen": -0.338470458984375, + "rewards/weighted_margins": 0.4430099427700043, + "rewards/weighted_rejected": -0.781768798828125, + "step": 470 + }, + { + "epoch": 0.2512431300706621, + "grad_norm": 55.78861618041992, + "learning_rate": 9.327840749034141e-07, + "logits/chosen": -0.6301849484443665, + "logits/rejected": -0.6710245013237, + "logps/chosen": -324.8578186035156, + "logps/rejected": -336.734375, + "logps/weighted_chosen": -2.5625243186950684, + "logps/weighted_rejected": -3.774975538253784, + "loss": 0.636, + "rewards/accuracies": 0.668749988079071, + "rewards/chosen": -37.658203125, + "rewards/margins": 22.687694549560547, + "rewards/rejected": -60.357421875, + "rewards/weighted_accuracies": 0.6812499761581421, + "rewards/weighted_chosen": -0.2594970762729645, + "rewards/weighted_margins": 0.48378294706344604, + "rewards/weighted_rejected": -0.7435302734375, + "step": 480 + }, + { + "epoch": 0.2564773619471343, + "grad_norm": 38.52030563354492, + "learning_rate": 9.281359022841965e-07, + "logits/chosen": -0.5341835021972656, + "logits/rejected": -0.550585925579071, + "logps/chosen": -320.76171875, + "logps/rejected": -314.70391845703125, + "logps/weighted_chosen": -2.91943359375, + "logps/weighted_rejected": -4.169653415679932, + "loss": 0.6375, + "rewards/accuracies": 0.653124988079071, + "rewards/chosen": -45.831443786621094, + "rewards/margins": 24.026952743530273, + "rewards/rejected": -69.88359069824219, + "rewards/weighted_accuracies": 0.668749988079071, + "rewards/weighted_chosen": -0.516644299030304, + "rewards/weighted_margins": 0.518634021282196, + "rewards/weighted_rejected": -1.0354125499725342, + "step": 490 + }, + { + "epoch": 0.26171159382360637, + "grad_norm": 15.318764686584473, + "learning_rate": 9.233447357514989e-07, + "logits/chosen": -0.5592590570449829, + "logits/rejected": -0.6022475957870483, + "logps/chosen": -347.77423095703125, + "logps/rejected": -342.21875, + "logps/weighted_chosen": -3.2605223655700684, + "logps/weighted_rejected": -3.667773485183716, + "loss": 0.6494, + "rewards/accuracies": 0.659375011920929, + "rewards/chosen": -49.72968673706055, + "rewards/margins": 22.665430068969727, + "rewards/rejected": -72.4097671508789, + "rewards/weighted_accuracies": 0.65625, + "rewards/weighted_chosen": -0.4633804261684418, + "rewards/weighted_margins": 0.527294933795929, + "rewards/weighted_rejected": -0.990936279296875, + "step": 500 + }, + { + "epoch": 0.26171159382360637, + "eval_logits/chosen": -0.6649160385131836, + "eval_logits/rejected": -0.682785153388977, + "eval_logps/chosen": -345.551513671875, + "eval_logps/rejected": -345.9989929199219, + "eval_logps/weighted_chosen": -2.992426872253418, + "eval_logps/weighted_rejected": -3.637266159057617, + "eval_loss": 0.6663314700126648, + "eval_rewards/accuracies": 0.6305000185966492, + "eval_rewards/chosen": -56.88743591308594, + "eval_rewards/margins": 21.448062896728516, + "eval_rewards/rejected": -78.32637786865234, + "eval_rewards/weighted_accuracies": 0.6480000019073486, + "eval_rewards/weighted_chosen": -0.5315031409263611, + "eval_rewards/weighted_margins": 0.43671876192092896, + "eval_rewards/weighted_rejected": -0.9682218432426453, + "eval_runtime": 1455.1048, + "eval_samples_per_second": 1.374, + "eval_steps_per_second": 0.344, + "step": 500 + } + ], + "logging_steps": 10, + "max_steps": 1911, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-500/training_args.bin b/checkpoint-500/training_args.bin new file mode 100644 index 0000000..2a96666 --- /dev/null +++ b/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af898db701df81d78da638b0a1b962531f0493f59e9b2be3d881d4701a7c223a +size 8721 diff --git a/checkpoint-500/zero_to_fp32.py b/checkpoint-500/zero_to_fp32.py new file mode 100644 index 0000000..0e75914 --- /dev/null +++ b/checkpoint-500/zero_to_fp32.py @@ -0,0 +1,760 @@ +#!/usr/bin/env python + +# Copyright (c) Microsoft Corporation. +# SPDX-License-Identifier: Apache-2.0 + +# DeepSpeed Team + +# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets +# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in +# the future. Once extracted, the weights don't require DeepSpeed and can be used in any +# application. +# +# example: +# python zero_to_fp32.py . output_dir/ +# or +# python zero_to_fp32.py . output_dir/ --safe_serialization + +import argparse +import torch +import glob +import math +import os +import re +import gc +import json +import numpy as np +from tqdm import tqdm +from collections import OrderedDict +from dataclasses import dataclass + +# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with +# DeepSpeed data structures it has to be available in the current python environment. +from deepspeed.utils import logger +from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS, + FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES, + FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS) + + +@dataclass +class zero_model_state: + buffers: dict() + param_shapes: dict() + shared_params: list + ds_version: int + frozen_param_shapes: dict() + frozen_param_fragments: dict() + + +debug = 0 + +# load to cpu +device = torch.device('cpu') + + +def atoi(text): + return int(text) if text.isdigit() else text + + +def natural_keys(text): + ''' + alist.sort(key=natural_keys) sorts in human order + http://nedbatchelder.com/blog/200712/human_sorting.html + (See Toothy's implementation in the comments) + ''' + return [atoi(c) for c in re.split(r'(\d+)', text)] + + +def get_model_state_file(checkpoint_dir, zero_stage): + if not os.path.isdir(checkpoint_dir): + raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist") + + # there should be only one file + if zero_stage <= 2: + file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt") + elif zero_stage == 3: + file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt") + + if not os.path.exists(file): + raise FileNotFoundError(f"can't find model states file at '{file}'") + + return file + + +def get_checkpoint_files(checkpoint_dir, glob_pattern): + # XXX: need to test that this simple glob rule works for multi-node setup too + ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys) + + if len(ckpt_files) == 0: + raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'") + + return ckpt_files + + +def get_optim_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt") + + +def get_model_state_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_model_states.pt") + + +def parse_model_states(files): + zero_model_states = [] + for file in files: + state_dict = torch.load(file, map_location=device, weights_only=False) + + if BUFFER_NAMES not in state_dict: + raise ValueError(f"{file} is not a model state checkpoint") + buffer_names = state_dict[BUFFER_NAMES] + if debug: + print("Found buffers:", buffer_names) + + # recover just the buffers while restoring them to fp32 if they were saved in fp16 + buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names} + param_shapes = state_dict[PARAM_SHAPES] + + # collect parameters that are included in param_shapes + param_names = [] + for s in param_shapes: + for name in s.keys(): + param_names.append(name) + + # update with frozen parameters + frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None) + if frozen_param_shapes is not None: + if debug: + print(f"Found frozen_param_shapes: {frozen_param_shapes}") + param_names += list(frozen_param_shapes.keys()) + + # handle shared params + shared_params = [[k, v] for k, v in state_dict["shared_params"].items()] + + ds_version = state_dict.get(DS_VERSION, None) + + frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None) + + z_model_state = zero_model_state(buffers=buffers, + param_shapes=param_shapes, + shared_params=shared_params, + ds_version=ds_version, + frozen_param_shapes=frozen_param_shapes, + frozen_param_fragments=frozen_param_fragments) + zero_model_states.append(z_model_state) + + return zero_model_states + + +def parse_optim_states(files, ds_checkpoint_dir): + total_files = len(files) + state_dicts = [] + for f in tqdm(files, desc='Loading checkpoint shards'): + state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False) + # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights + # and also handle the case where it was already removed by another helper script + state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None) + state_dicts.append(state_dict) + + if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]: + raise ValueError(f"{files[0]} is not a zero checkpoint") + zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE] + world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT] + + # For ZeRO-2 each param group can have different partition_count as data parallelism for expert + # parameters can be different from data parallelism for non-expert parameters. So we can just + # use the max of the partition_count to get the dp world_size. + + if type(world_size) is list: + world_size = max(world_size) + + if world_size != total_files: + raise ValueError( + f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. " + "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes." + ) + + # the groups are named differently in each stage + if zero_stage <= 2: + fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS + elif zero_stage == 3: + fp32_groups_key = FP32_FLAT_GROUPS + else: + raise ValueError(f"unknown zero stage {zero_stage}") + + fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))] + return zero_stage, world_size, fp32_flat_groups + + +def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters): + """ + Returns fp32 state_dict reconstructed from ds checkpoint + + Args: + - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are) + + """ + print(f"Processing zero checkpoint '{ds_checkpoint_dir}'") + + optim_files = get_optim_files(ds_checkpoint_dir) + zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir) + print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}") + + model_files = get_model_state_files(ds_checkpoint_dir) + + zero_model_states = parse_model_states(model_files) + print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}') + + if zero_stage <= 2: + return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + elif zero_stage == 3: + return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + + +def _zero2_merge_frozen_params(state_dict, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + frozen_param_fragments = zero_model_states[0].frozen_param_fragments + + if debug: + num_elem = sum(s.numel() for s in frozen_param_shapes.values()) + print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in frozen_param_fragments.values()]) + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + state_dict[name] = frozen_param_fragments[name] + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +def _has_callable(obj, fn): + attr = getattr(obj, fn, None) + return callable(attr) + + +def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + + # Reconstruction protocol: + # + # XXX: document this + + if debug: + for i in range(world_size): + for j in range(len(fp32_flat_groups[0])): + print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}") + + # XXX: memory usage doubles here (zero2) + num_param_groups = len(fp32_flat_groups[0]) + merged_single_partition_of_fp32_groups = [] + for i in range(num_param_groups): + merged_partitions = [sd[i] for sd in fp32_flat_groups] + full_single_fp32_vector = torch.cat(merged_partitions, 0) + merged_single_partition_of_fp32_groups.append(full_single_fp32_vector) + avail_numel = sum( + [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups]) + + if debug: + wanted_params = sum([len(shapes) for shapes in param_shapes]) + wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes]) + # not asserting if there is a mismatch due to possible padding + print(f"Have {avail_numel} numels to process.") + print(f"Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + total_numel = 0 + total_params = 0 + for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups): + offset = 0 + avail_numel = full_single_fp32_vector.numel() + for name, shape in shapes.items(): + + unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape) + total_numel += unpartitioned_numel + total_params += 1 + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape) + offset += unpartitioned_numel + + # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and + # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex + # paddings performed in the code it's almost impossible to predict the exact numbers w/o the + # live optimizer object, so we are checking that the numbers are within the right range + align_to = 2 * world_size + + def zero2_align(x): + return align_to * math.ceil(x / align_to) + + if debug: + print(f"original offset={offset}, avail_numel={avail_numel}") + + offset = zero2_align(offset) + avail_numel = zero2_align(avail_numel) + + if debug: + print(f"aligned offset={offset}, avail_numel={avail_numel}") + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero2_merge_frozen_params(state_dict, zero_model_states) + + _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def zero3_partitioned_param_info(unpartitioned_numel, world_size): + remainder = unpartitioned_numel % world_size + padding_numel = (world_size - remainder) if remainder else 0 + partitioned_numel = math.ceil(unpartitioned_numel / world_size) + return partitioned_numel, padding_numel + + +def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + if debug: + for i in range(world_size): + num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values()) + print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in zero_model_states[0].frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states) + state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape) + + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +class GatheredTensor: + """ + A pseudo tensor that collects partitioned weights. + It is more memory efficient when there are multiple groups. + """ + + def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape): + self.flat_groups = flat_groups + self.flat_groups_offset = flat_groups_offset + self.offset = offset + self.partitioned_numel = partitioned_numel + self.shape = shape + self.dtype = self.flat_groups[0][0].dtype + + def contiguous(self): + """ + Merge partitioned weights from flat_groups into a single tensor. + """ + end_idx = self.offset + self.partitioned_numel + world_size = len(self.flat_groups) + pad_flat_param_chunks = [] + + for rank_i in range(world_size): + # for each rank, we need to collect weights from related group/groups + flat_groups_at_rank_i = self.flat_groups[rank_i] + start_group_id = None + end_group_id = None + for group_id in range(len(self.flat_groups_offset)): + if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]: + start_group_id = group_id + if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]: + end_group_id = group_id + break + # collect weights from related group/groups + for group_id in range(start_group_id, end_group_id + 1): + flat_tensor = flat_groups_at_rank_i[group_id] + start_offset = self.offset - self.flat_groups_offset[group_id] + end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id] + pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset]) + + # collect weights from all ranks + pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0) + param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous() + return param + + +def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size + + # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each + # param, re-consolidating each param, while dealing with padding if any + + # merge list of dicts, preserving order + param_shapes = {k: v for d in param_shapes for k, v in d.items()} + + if debug: + for i in range(world_size): + print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}") + + wanted_params = len(param_shapes) + wanted_numel = sum(shape.numel() for shape in param_shapes.values()) + # not asserting if there is a mismatch due to possible padding + avail_numel = fp32_flat_groups[0].numel() * world_size + print(f"Trainable params: Have {avail_numel} numels to process.") + print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + offset = 0 + total_numel = 0 + total_params = 0 + flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]])) + for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'): + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + total_params += 1 + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + # memory efficient tensor + tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape) + state_dict[name] = tensor + offset += partitioned_numel + + offset *= world_size + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero3_merge_frozen_params(state_dict, world_size, zero_model_states) + + _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def to_torch_tensor(state_dict, return_empty_tensor=False): + """ + Convert state_dict of GatheredTensor to torch tensor + """ + torch_state_dict = {} + converted_tensors = {} + for name, tensor in state_dict.items(): + tensor_id = id(tensor) + if tensor_id in converted_tensors: # shared tensors + shared_tensor = torch_state_dict[converted_tensors[tensor_id]] + torch_state_dict[name] = shared_tensor + else: + converted_tensors[tensor_id] = name + if return_empty_tensor: + torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype) + else: + torch_state_dict[name] = tensor.contiguous() + return torch_state_dict + + +def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, + tag=None, + exclude_frozen_parameters=False, + lazy_mode=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with + ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example + via a model hub. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient. + Convert the pesduo tensor to torch tensor by ``.contiguous()`` + + Returns: + - pytorch ``state_dict`` + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint + # do the training and checkpoint saving + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu + model = model.cpu() # move to cpu + model.load_state_dict(state_dict) + # submit to model hub or save the model to share with others + + In this example the ``model`` will no longer be usable in the deepspeed context of the same + application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead. + + Note: the above usage may not work if your application doesn't have sufficient free CPU memory. + You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with + the checkpoint. Or you can load state_dict in lazy mode :: + + from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu + for name, lazy_tensor in state_dict.item(): + tensor = lazy_tensor.contiguous() # to cpu + print(name, tensor) + # del tensor to release memory if it no longer in use + """ + if tag is None: + latest_path = os.path.join(checkpoint_dir, 'latest') + if os.path.isfile(latest_path): + with open(latest_path, 'r') as fd: + tag = fd.read().strip() + else: + raise ValueError(f"Unable to find 'latest' file at {latest_path}") + + ds_checkpoint_dir = os.path.join(checkpoint_dir, tag) + + if not os.path.isdir(ds_checkpoint_dir): + raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist") + + state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters) + if lazy_mode: + return state_dict + else: + return to_torch_tensor(state_dict) + + +def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, + output_dir, + max_shard_size="5GB", + safe_serialization=False, + tag=None, + exclude_frozen_parameters=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be + loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``output_dir``: directory to the pytorch fp32 state_dict output files + - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB + - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`). + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + """ + + # Dependency pre-check + if safe_serialization: + try: + from safetensors.torch import save_file + except ImportError: + print('If you want to use `safe_serialization`, please `pip install safetensors`') + raise + if max_shard_size is not None: + try: + from huggingface_hub import split_torch_state_dict_into_shards + except ImportError: + print('If you want to use `max_shard_size`, please `pip install huggingface_hub`') + raise + + # Convert zero checkpoint to state_dict + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, + tag, + exclude_frozen_parameters, + lazy_mode=True) + + # Shard the model if it is too big. + weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin" + if max_shard_size is not None: + filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors") + # an memory-efficient approach for sharding + empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True) + state_dict_split = split_torch_state_dict_into_shards(empty_state_dict, + filename_pattern=filename_pattern, + max_shard_size=max_shard_size) + else: + from collections import namedtuple + StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"]) + state_dict_split = StateDictSplit(is_sharded=False, + filename_to_tensors={weights_name: list(state_dict.keys())}) + + # Save the model by shard + os.makedirs(output_dir, exist_ok=True) + filename_to_tensors = state_dict_split.filename_to_tensors.items() + for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"): + shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors} + shard_state_dict = to_torch_tensor(shard_state_dict) + output_path = os.path.join(output_dir, shard_file) + if safe_serialization: + save_file(shard_state_dict, output_path, metadata={"format": "pt"}) + else: + torch.save(shard_state_dict, output_path) + # release the memory of current shard + for tensor_name in list(shard_state_dict.keys()): + del state_dict[tensor_name] + del shard_state_dict[tensor_name] + del shard_state_dict + gc.collect() + + # Save index if sharded + if state_dict_split.is_sharded: + index = { + "metadata": state_dict_split.metadata, + "weight_map": state_dict_split.tensor_to_filename, + } + save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json" + save_index_file = os.path.join(output_dir, save_index_file) + with open(save_index_file, "w", encoding="utf-8") as f: + content = json.dumps(index, indent=2, sort_keys=True) + "\n" + f.write(content) + + +def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None): + """ + 1. Put the provided model to cpu + 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` + 3. Load it into the provided model + + Args: + - ``model``: the model object to update + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + + Returns: + - ``model`: modified model + + Make sure you have plenty of CPU memory available before you call this function. If you don't + have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it + conveniently placed for you in the checkpoint folder. + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint + model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir) + # submit to model hub or save the model to share with others + + Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context + of the same application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + """ + logger.info(f"Extracting fp32 weights") + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag) + + logger.info(f"Overwriting model with fp32 weights") + model = model.cpu() + model.load_state_dict(state_dict, strict=False) + + return model + + +if __name__ == "__main__": + parser = argparse.ArgumentParser() + parser.add_argument("checkpoint_dir", + type=str, + help="path to the desired checkpoint folder, e.g., path/checkpoint-12") + parser.add_argument("output_dir", + type=str, + help="directory to the pytorch fp32 state_dict output files" + "(e.g. path/checkpoint-12-output/)") + parser.add_argument( + "--max_shard_size", + type=str, + default="5GB", + help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size" + "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`" + "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances" + "without CPU OOM issues.") + parser.add_argument( + "--safe_serialization", + default=False, + action='store_true', + help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).") + parser.add_argument("-t", + "--tag", + type=str, + default=None, + help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1") + parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters") + parser.add_argument("-d", "--debug", action='store_true', help="enable debug") + args = parser.parse_args() + + debug = args.debug + + convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, + args.output_dir, + max_shard_size=args.max_shard_size, + safe_serialization=args.safe_serialization, + tag=args.tag, + exclude_frozen_parameters=args.exclude_frozen_parameters) diff --git a/config.json b/config.json new file mode 100644 index 0000000..3f8f5c0 --- /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": "bfloat16", + "transformers_version": "4.54.1", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..58a7ef4 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,299 @@ +{ + "metadata": { + "total_parameters": 266240, + "total_size": 16060522496 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..e5b39b6 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "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": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..03aa64f --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0968dcc0ee8e56c7dccd34a7f51f8065ea0cb9e2cc529e3243d1e5c0a4bdaa0c +size 17208754 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..877a9a9 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "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|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|end_of_text|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 32768, + "pad_token": "<|end_of_text|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..2a96666 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af898db701df81d78da638b0a1b962531f0493f59e9b2be3d881d4701a7c223a +size 8721