commit 5483fb2422af19ce95faee7e7b10520fc2f6596f Author: ModelHub XC Date: Wed Sep 2 06:24:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: m-a-p/CriticLeanGPT-Qwen2.5-7B-Instruct-SFT Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..239ca48 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +library_name: transformers +license: other +base_model: Qwen2.5-7B-Instruct +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: Qwen2.5-7B-Instruct-critic_lean_mix_48k + results: [] +--- + + + +# Qwen2.5-7B-Instruct-critic_lean_mix_48k + +This model is a fine-tuned version of [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen2.5-7B-Instruct) on the critic_lean_mix_48k dataset. +It achieves the following results on the evaluation set: +- Loss: 0.3344 + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-06 +- train_batch_size: 2 +- eval_batch_size: 1 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 8 +- total_train_batch_size: 16 +- total_eval_batch_size: 8 +- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 +- lr_scheduler_type: cosine +- lr_scheduler_warmup_ratio: 0.1 +- num_epochs: 3.0 + +### Training results + +| Training Loss | Epoch | Step | Validation Loss | +|:-------------:|:-----:|:----:|:---------------:| +| 0.3494 | 1.0 | 2970 | 0.3095 | +| 0.2317 | 2.0 | 5940 | 0.3043 | +| 0.1291 | 3.0 | 8910 | 0.3344 | + + +### Framework versions + +- Transformers 4.44.2 +- Pytorch 2.2.1+cu121 +- Datasets 2.21.0 +- Tokenizers 0.19.1 diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..482ced4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,24 @@ +{ + "": 151658, + "": 151657, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..3e81fd9 --- /dev/null +++ b/all_results.json @@ -0,0 +1,14 @@ +{ + "epoch": 3.0, + "eval_loss": 0.33440589904785156, + "eval_runtime": 15.5134, + "eval_samples_per_second": 30.941, + "eval_steps_per_second": 3.868, + "tflops": 0.02876485648795673, + "token/s": 1971.4008815538489, + "total_flos": 372912231022592.0, + "train_loss": 0.24247261672442744, + "train_runtime": 12196.1154, + "train_samples_per_second": 11.689, + "train_steps_per_second": 0.731 +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..5c44ea1 --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "Qwen2.5-7B-Instruct", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "rms_norm_eps": 1e-06, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.44.2", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/eval_results.json b/eval_results.json new file mode 100644 index 0000000..30e2100 --- /dev/null +++ b/eval_results.json @@ -0,0 +1,7 @@ +{ + "epoch": 3.0, + "eval_loss": 0.33440589904785156, + "eval_runtime": 15.5134, + "eval_samples_per_second": 30.941, + "eval_steps_per_second": 3.868 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..64d2760 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "4.44.2" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..8f5eca0 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73a4df7e892f62ee2a8ea02ead929411e1055414d77a78c8147faf40db406820 +size 4877660776 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..95e5a03 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1626185f81b19daeb96a4f538b8dffe5e39b019d565854bc181a4b98d8542114 +size 4932751008 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..7ca0e25 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26b784cb7d459e9206bac51b52868c1eeaa063774b52e5b3662cc029ca1895e7 +size 4330865200 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..24d5290 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97955abcbc294329685dff97ac7055eb5c53b4c57d681002d84e55d55a834141 +size 1089994880 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..a358575 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb +size 27752 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..7ebe282 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8506e7111b80c6d8635951a02eab0f4e1a8e4e5772da83846579e97b16f61bf +size 7031673 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..bcfaf9f --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfb48460eae2f42efb8dbfcdc0288f35736fa3e0939d17614f22e26ebdc4d871 +size 7331 diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000..a8ea88d --- /dev/null +++ b/train_results.json @@ -0,0 +1,10 @@ +{ + "epoch": 3.0, + "tflops": 0.02876485648795673, + "token/s": 1971.4008815538489, + "total_flos": 372912231022592.0, + "train_loss": 0.24247261672442744, + "train_runtime": 12196.1154, + "train_samples_per_second": 11.689, + "train_steps_per_second": 0.731 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..b54358c --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1518c097d1055263a63b6b23a36a151d0d149c0c5ab4019b0d310699e103f2f8 +size 2215 diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..70e236f --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f93d9a13adf78510f9795f138f863a19ae085a0ff04c5e246e2782c1bb5cf728 +size 3136 diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..4375442 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e661077fb985c0d53a0e2ebf2c66830c90dc3282a638b15424016f5e4e40f650 +size 7480 diff --git a/training_eval_loss.png b/training_eval_loss.png new file mode 100644 index 0000000..0563654 --- /dev/null +++ b/training_eval_loss.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87e8f8f7fcfd49010cdc881efbc7054b149cfc6d29aa110637f9a96512cbb466 +size 41024 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..894e9c2 --- /dev/null +++ b/training_loss.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a98757353f88d1536a47497c8b3be6419134e3e6cc53d2b98f5a5c38971f93 +size 39644 diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833