From 64de011a57f5fdc7fabde6b392ecb8e59b0507c8 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 28 Jun 2026 05:22:13 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: hkust-nlp/deita-7b-v1.0-sft Source: Original Platform --- .gitattributes | 37 +++ README.md | 114 +++++++++ config.json | 25 ++ configuration.json | 1 + generation_config.json | 6 + pytorch_model-00001-of-00002.bin | 3 + pytorch_model-00002-of-00002.bin | 3 + pytorch_model.bin.index.json | 298 ++++++++++++++++++++++ special_tokens_map.json | 24 ++ tokenizer.model | 3 + tokenizer_config.json | 43 ++++ trainer_state.json | 424 +++++++++++++++++++++++++++++++ training_args.bin | 3 + 13 files changed, 984 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 pytorch_model-00001-of-00002.bin create mode 100644 pytorch_model-00002-of-00002.bin create mode 100644 pytorch_model.bin.index.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.model create mode 100644 tokenizer_config.json create mode 100644 trainer_state.json create mode 100644 training_args.bin diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e512815 --- /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 +pytorch_model-00001-of-00002.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00002-of-00002.bin filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..67a2653 --- /dev/null +++ b/README.md @@ -0,0 +1,114 @@ +--- +license: apache-2.0 +datasets: +- hkust-nlp/deita-6k-v0 +language: +- en +--- + +Deita banner + +# Model Card for Deita 7B V1.0 SFT + +[GitHub](https://github.com/hkust-nlp/deita) | [Paper](https://arxiv.org/abs/2312.15685) + +Deita is an open-sourced project designed to facilitate **Automatic Data Selection** for instruction tuning in Large Language Models (LLMs). +Deita 7B V1.0 SFT is a fine-tuned version of Mistral-7B-v0.1 that was trained on 6k automatically selected lightweight, high-quality alignment SFT data: [Deita 6K V0](https://huggingface.co/datasets/hkust-nlp/deita-6k-v0). + +## Model description + +- **Model type:** Model fine tuned on automatically selected lightweight, high-quality alignment SFT data. +- **Language(s) (NLP):** Primarily English +- **Finetuned from model:** Mistral-7B-v0.1 + +### Model Sources + +- **Repository:** https://github.com/hkust-nlp/deita +- **Model Family:** Other models and the dataset are found in the [Deita collection](https://huggingface.co/collections/hkust-nlp/deita-6569c198c174808d94cf5bd4). + +## Performance + + + +| Model | Align | Data Size | MT-Bench | AlpacaEval(%) | OpenLLM (Avg.) | +|------------------------------------------------|-----------|------------|----------|---------------|----------------| +| **Proprietary Models** | | | | | | +| GPT-4-Turbo | ? | -- | 9.32 | 97.70 | -- | +| GPT-4 | SFT + PPO | -- | 8.99 | 95.03 | -- | +| Claude-2 | SFT + PPO | -- | 8.06 | 91.36 | -- | +| GPT-3.5-turbo | SFT + PPO | -- | 7.94 | 89.37 | -- | +| **Open-sourced Models based on LLaMA-1-13B** | | | | | | +| LIMA | SFT | 1K SFT | 4.29 | 41.98 | 59.82 | +| WizardLM-13B | SFT | 70K SFT | 6.35 | 75.31 | 58.96 | +| Vicuna-13B-v1.3 | SFT | 125K SFT | 6.39 | 82.11 | 60.01 | +| Random | SFT | 10K SFT | 6.03 | 71.52 | 60.14 | +| DEITA-LLaMA1-13B-v1.0-sft | SFT | 10K SFT | 6.60 | 78.01 | 64.27 | +| **Open-sourced Models based on LLaMA-2-13B** | | | | | | +| Tulu-2-13B | SFT | 326K SFT | 6.70 | 78.90 | -- | +| Tulu-2-13B+DPO | SFT + DPO | 326K SFT + 60K DPO | 7.00 | 89.50 | -- | +| LLaMA2-13B-Chat | SFT + PPO | -- | 6.65 | 81.09 | -- | +| WizardLM-13B-v1.2 | SFT | >70K SFT | 7.09 | 89.17 | -- | +| Vicuna-13B-v1.5 | SFT | 125K SFT | 6.57 | 78.80 | 61.63 | +| Random | SFT | 10K SFT | 5.78 | 65.19 | 61.32 | +| DEITA-LLaMA2-13B-v1.0-sft | SFT | 10K SFT | 6.79 | 81.09 | 62.71 | +| **Open-sourced Models based on Mistral-7B** | | | | | | +| Mistral-7B-Instruct-v0.1 | -- | -- | 6.84 | 69.65 | 60.45 | +| Zephyr-7B-sft | SFT | 200K SFT | 5.32 | 75.12 | 60.93 | +| $\text{Zephyr-7B-}\beta$ | SFT + DPO | 200K SFT + 60K DPO | 7.34 | 90.60 | 66.36 | +| OpenChat-3.5 | C-RLFT | >> 70K C-RLFT | 7.81 | 88.51 | -- | +| Starling-7B | C-RLFT + APA | >>70K C-RLFT + 183K APA | 8.09 | 91.99 | -- | +| Random | SFT | 10K SFT | 5.89 | 56.90 | 61.72 | +| DEITA-7B-v1.0-sft (6K) | SFT | 6K SFT | 7.22 | 80.78 | 64.94 | +| DEITA-7B-v1.0-sft (10K) | SFT | 10K SFT | 7.32 | 81.67 | 64.00 | +| DEITA-7B-v1.0 | SFT + DPO | 6K SFT + 10K DPO | 7.55 | 90.06 | 69.86 | + + + + + +## Input Format + +The model is trained using the [vicuna_v1.1 template](https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py) + +``` +A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hello! ASSISTANT: Hi!USER: How are you? ASSISTANT: +``` + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 2e-05 +- train_batch_size: 1 +- eval_batch_size: 1 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 4 +- gradient_accumulation_steps: 128 +- total_train_batch_size: 512 +- total_eval_batch_size: 4 +- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 +- lr_scheduler_type: cosine +- lr_scheduler_warmup_ratio: 0.1 +- num_epochs: 6.0 + +### Framework versions + +- Transformers 4.34.1 +- Pytorch 2.1.0+cu121 +- Datasets 2.14.6 +- Tokenizers 0.14.1 + + +## Citation +If you find the content of this project helpful, please cite our paper as follows: + +``` +@misc{liu2023what, + title={What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning}, + author={Wei Liu and Weihao Zeng and Keqing He and Yong Jiang and Junxian He}, + year={2023}, + eprint={2312.15685}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000..8213102 --- /dev/null +++ b/config.json @@ -0,0 +1,25 @@ +{ + "_name_or_path": "models/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.34.1", + "use_cache": false, + "vocab_size": 32000 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..3c6c66f --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.34.1" +} diff --git a/pytorch_model-00001-of-00002.bin b/pytorch_model-00001-of-00002.bin new file mode 100644 index 0000000..b349e80 --- /dev/null +++ b/pytorch_model-00001-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfbcfa9cd4b317880b35d66e13e0d20ebc6366125b98f55c4981604ecf5c4aae +size 9943028531 diff --git a/pytorch_model-00002-of-00002.bin b/pytorch_model-00002-of-00002.bin new file mode 100644 index 0000000..8b14424 --- /dev/null +++ b/pytorch_model-00002-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e337d66de816657244501ecd3105ca764ac4cf15d09f0338ef4bddbb227910a +size 4540536134 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..520ee2f --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00002-of-00002.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.norm.weight": "pytorch_model-00002-of-00002.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..14761dc --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8b443ef --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..547b622 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,43 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 2048, + "pad_token": "", + "padding_side": "left", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..45bea2d --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,424 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 5.746938775510204, + "eval_steps": 50.0, + "global_step": 66, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.09, + "learning_rate": 2.8571428571428573e-06, + "loss": 1.2891, + "step": 1 + }, + { + "epoch": 0.17, + "learning_rate": 5.7142857142857145e-06, + "loss": 4.6526, + "step": 2 + }, + { + "epoch": 0.26, + "learning_rate": 8.571428571428571e-06, + "loss": 0.8846, + "step": 3 + }, + { + "epoch": 0.35, + "learning_rate": 1.1428571428571429e-05, + "loss": 0.9671, + "step": 4 + }, + { + "epoch": 0.44, + "learning_rate": 1.4285714285714287e-05, + "loss": 0.9281, + "step": 5 + }, + { + "epoch": 0.52, + "learning_rate": 1.7142857142857142e-05, + "loss": 6.2996, + "step": 6 + }, + { + "epoch": 0.61, + "learning_rate": 2e-05, + "loss": 2.0054, + "step": 7 + }, + { + "epoch": 0.7, + "learning_rate": 1.998582695676762e-05, + "loss": 1.838, + "step": 8 + }, + { + "epoch": 0.78, + "learning_rate": 1.9943348002101374e-05, + "loss": 0.7631, + "step": 9 + }, + { + "epoch": 0.87, + "learning_rate": 1.9872683547213446e-05, + "loss": 0.7932, + "step": 10 + }, + { + "epoch": 0.96, + "learning_rate": 1.9774033898178668e-05, + "loss": 2.5757, + "step": 11 + }, + { + "epoch": 1.04, + "learning_rate": 1.9647678688145163e-05, + "loss": 1.5853, + "step": 12 + }, + { + "epoch": 1.13, + "learning_rate": 1.9493976084683814e-05, + "loss": 1.0913, + "step": 13 + }, + { + "epoch": 1.22, + "learning_rate": 1.9313361774523387e-05, + "loss": 1.4119, + "step": 14 + }, + { + "epoch": 1.31, + "learning_rate": 1.9106347728549134e-05, + "loss": 0.6267, + "step": 15 + }, + { + "epoch": 1.39, + "learning_rate": 1.8873520750565716e-05, + "loss": 1.1653, + "step": 16 + }, + { + "epoch": 1.48, + "learning_rate": 1.8615540813938063e-05, + "loss": 2.1158, + "step": 17 + }, + { + "epoch": 1.57, + "learning_rate": 1.833313919082515e-05, + "loss": 2.8904, + "step": 18 + }, + { + "epoch": 1.65, + "learning_rate": 1.8027116379309637e-05, + "loss": 1.1932, + "step": 19 + }, + { + "epoch": 1.74, + "learning_rate": 1.7698339834299064e-05, + "loss": 1.1534, + "step": 20 + }, + { + "epoch": 1.83, + "learning_rate": 1.7347741508630673e-05, + "loss": 0.7375, + "step": 21 + }, + { + "epoch": 1.92, + "learning_rate": 1.6976315211349848e-05, + "loss": 1.4861, + "step": 22 + }, + { + "epoch": 2.0, + "learning_rate": 1.658511379065039e-05, + "loss": 1.9774, + "step": 23 + }, + { + "epoch": 2.09, + "learning_rate": 1.617524614946192e-05, + "loss": 0.7979, + "step": 24 + }, + { + "epoch": 2.18, + "learning_rate": 1.5747874102144073e-05, + "loss": 3.0872, + "step": 25 + }, + { + "epoch": 2.26, + "learning_rate": 1.5304209081197425e-05, + "loss": 0.5659, + "step": 26 + }, + { + "epoch": 2.35, + "learning_rate": 1.4845508703326504e-05, + "loss": 0.6251, + "step": 27 + }, + { + "epoch": 2.44, + "learning_rate": 1.4373073204588556e-05, + "loss": 0.7142, + "step": 28 + }, + { + "epoch": 2.53, + "learning_rate": 1.388824175473321e-05, + "loss": 3.9928, + "step": 29 + }, + { + "epoch": 2.61, + "learning_rate": 1.3392388661180303e-05, + "loss": 1.4159, + "step": 30 + }, + { + "epoch": 2.7, + "learning_rate": 1.2886919473396212e-05, + "loss": 1.1887, + "step": 31 + }, + { + "epoch": 2.79, + "learning_rate": 1.2373266998711152e-05, + "loss": 0.4706, + "step": 32 + }, + { + "epoch": 2.87, + "learning_rate": 1.1852887240871145e-05, + "loss": 0.5645, + "step": 33 + }, + { + "epoch": 2.96, + "learning_rate": 1.1327255272837221e-05, + "loss": 2.2387, + "step": 34 + }, + { + "epoch": 3.05, + "learning_rate": 1.0797861055530832e-05, + "loss": 0.8387, + "step": 35 + }, + { + "epoch": 3.13, + "learning_rate": 1.026620521437775e-05, + "loss": 0.699, + "step": 36 + }, + { + "epoch": 3.22, + "learning_rate": 9.733794785622254e-06, + "loss": 0.7128, + "step": 37 + }, + { + "epoch": 3.31, + "learning_rate": 9.202138944469168e-06, + "loss": 0.2916, + "step": 38 + }, + { + "epoch": 3.4, + "learning_rate": 8.672744727162782e-06, + "loss": 0.6168, + "step": 39 + }, + { + "epoch": 3.48, + "learning_rate": 8.147112759128859e-06, + "loss": 1.1931, + "step": 40 + }, + { + "epoch": 3.57, + "learning_rate": 7.626733001288852e-06, + "loss": 1.814, + "step": 41 + }, + { + "epoch": 3.66, + "learning_rate": 7.113080526603793e-06, + "loss": 0.5896, + "step": 42 + }, + { + "epoch": 3.74, + "learning_rate": 6.607611338819697e-06, + "loss": 0.5257, + "step": 43 + }, + { + "epoch": 3.83, + "learning_rate": 6.111758245266795e-06, + "loss": 0.3599, + "step": 44 + }, + { + "epoch": 3.92, + "learning_rate": 5.626926795411447e-06, + "loss": 0.9672, + "step": 45 + }, + { + "epoch": 4.01, + "learning_rate": 5.1544912966735e-06, + "loss": 0.8661, + "step": 46 + }, + { + "epoch": 4.09, + "learning_rate": 4.695790918802577e-06, + "loss": 0.4246, + "step": 47 + }, + { + "epoch": 4.18, + "learning_rate": 4.2521258978559324e-06, + "loss": 1.5274, + "step": 48 + }, + { + "epoch": 4.27, + "learning_rate": 3.824753850538082e-06, + "loss": 0.2455, + "step": 49 + }, + { + "epoch": 4.35, + "learning_rate": 3.414886209349615e-06, + "loss": 0.2901, + "step": 50 + }, + { + "epoch": 4.44, + "learning_rate": 3.023684788650154e-06, + "loss": 0.3549, + "step": 51 + }, + { + "epoch": 4.53, + "learning_rate": 2.6522584913693295e-06, + "loss": 1.7412, + "step": 52 + }, + { + "epoch": 4.61, + "learning_rate": 2.3016601657009364e-06, + "loss": 0.5993, + "step": 53 + }, + { + "epoch": 4.7, + "learning_rate": 1.972883620690366e-06, + "loss": 0.6416, + "step": 54 + }, + { + "epoch": 4.79, + "learning_rate": 1.6668608091748495e-06, + "loss": 0.242, + "step": 55 + }, + { + "epoch": 4.88, + "learning_rate": 1.3844591860619382e-06, + "loss": 0.2643, + "step": 56 + }, + { + "epoch": 4.96, + "learning_rate": 1.1264792494342858e-06, + "loss": 0.9819, + "step": 57 + }, + { + "epoch": 5.05, + "learning_rate": 8.936522714508678e-07, + "loss": 0.3697, + "step": 58 + }, + { + "epoch": 5.14, + "learning_rate": 6.866382254766158e-07, + "loss": 0.3612, + "step": 59 + }, + { + "epoch": 5.22, + "learning_rate": 5.060239153161872e-07, + "loss": 0.3287, + "step": 60 + }, + { + "epoch": 5.31, + "learning_rate": 3.5232131185484075e-07, + "loss": 0.1475, + "step": 61 + }, + { + "epoch": 5.4, + "learning_rate": 2.2596610182133328e-07, + "loss": 0.3517, + "step": 62 + }, + { + "epoch": 5.49, + "learning_rate": 1.2731645278655448e-07, + "loss": 1.0021, + "step": 63 + }, + { + "epoch": 5.57, + "learning_rate": 5.665199789862907e-08, + "loss": 0.9394, + "step": 64 + }, + { + "epoch": 5.66, + "learning_rate": 1.4173043232380557e-08, + "loss": 0.3404, + "step": 65 + }, + { + "epoch": 5.75, + "learning_rate": 0.0, + "loss": 0.3139, + "step": 66 + }, + { + "epoch": 5.75, + "step": 66, + "total_flos": 2.952602738246025e+18, + "train_loss": 1.1671814448905713, + "train_runtime": 5613.6362, + "train_samples_per_second": 6.285, + "train_steps_per_second": 0.012 + } + ], + "logging_steps": 1.0, + "max_steps": 66, + "num_train_epochs": 6, + "save_steps": 100.0, + "total_flos": 2.952602738246025e+18, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..f4da0a5 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd18979ea3e09295cd4a1b39b3679c9b5f018fed7457aa65d86544c8c7f366fe +size 6072