From c565131838776f387863a37f9cf7674783b93f8c Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 3 May 2026 04:40:40 +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: alwaysgood/qwen3-it Source: Original Platform --- .gitattributes | 36 +++++++++++++ README.md | 59 +++++++++++++++++++++ all_results.json | 12 +++++ config.json | 74 ++++++++++++++++++++++++++ eval_results.json | 7 +++ generation_config.json | 9 ++++ model.safetensors | 3 ++ tokenizer.json | 3 ++ tokenizer_config.json | 15 ++++++ train_results.json | 8 +++ trainer_state.json | 114 +++++++++++++++++++++++++++++++++++++++++ training_args.bin | 3 ++ 12 files changed, 343 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 all_results.json create mode 100644 config.json create mode 100644 eval_results.json create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json create mode 100644 train_results.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..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ad9e0f3 --- /dev/null +++ b/README.md @@ -0,0 +1,59 @@ +--- +base_model: alwaysgood/qwen3-st2 +library_name: transformers +model_name: checkpoints +tags: +- generated_from_trainer +- trl +- unsloth +- sft +licence: license +--- + +# Model Card for checkpoints + +This model is a fine-tuned version of [alwaysgood/qwen3-st2](https://huggingface.co/alwaysgood/qwen3-st2). +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="None", 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/hiloong/instruction-tuning/runs/s9x2uub1) + + +This model was trained with SFT. + +### Framework versions + +- TRL: 0.24.0 +- Transformers: 5.5.4 +- Pytorch: 2.9.0+cu128 +- Datasets: 4.3.0 +- Tokenizers: 0.22.2 + +## Citations + + + +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/all_results.json b/all_results.json new file mode 100644 index 0000000..14ee180 --- /dev/null +++ b/all_results.json @@ -0,0 +1,12 @@ +{ + "epoch": 1.0, + "eval_loss": 1.1405894756317139, + "eval_runtime": 1.8043, + "eval_samples_per_second": 39.906, + "eval_steps_per_second": 4.988, + "total_flos": 8375949913795584.0, + "train_loss": 1.2328018612331815, + "train_runtime": 186.4804, + "train_samples_per_second": 19.107, + "train_steps_per_second": 0.483 +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..2e1a17f --- /dev/null +++ b/config.json @@ -0,0 +1,74 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 36, + "model_name": "alwaysgood/qwen3-st2", + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "pad_token_id": 151669, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.5.4", + "unsloth_fixed": true, + "unsloth_version": "2026.4.6", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/eval_results.json b/eval_results.json new file mode 100644 index 0000000..1964ae5 --- /dev/null +++ b/eval_results.json @@ -0,0 +1,7 @@ +{ + "epoch": 1.0, + "eval_loss": 1.1405894756317139, + "eval_runtime": 1.8043, + "eval_samples_per_second": 39.906, + "eval_steps_per_second": 4.988 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..e08172e --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "eos_token_id": [ + 151643 + ], + "max_length": 32768, + "max_new_tokens": 2048, + "pad_token_id": 151669, + "transformers_version": "5.5.4" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..9ca8f2d --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef9332432965d1dbc02eec320c11fff29cce5d6e9601c746d5377c842313254c +size 8044982080 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..73037fe --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45c4ffda6666cf6d75d0b1f961f25964e2a52a62e78aaecb2f458e9ba9824112 +size 11422840 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..1f1e6cf --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,15 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "errors": "replace", + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "left", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000..2a3ea75 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 1.0, + "total_flos": 8375949913795584.0, + "train_loss": 1.2328018612331815, + "train_runtime": 186.4804, + "train_samples_per_second": 19.107, + "train_steps_per_second": 0.483 +} \ No newline at end of file diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..ddec15c --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,114 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 90, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.11204481792717087, + "grad_norm": 8.3125, + "learning_rate": 1e-05, + "loss": 1.396421241760254, + "step": 10 + }, + { + "epoch": 0.22408963585434175, + "grad_norm": 6.40625, + "learning_rate": 9.628619846344453e-06, + "loss": 1.2572100639343262, + "step": 20 + }, + { + "epoch": 0.33613445378151263, + "grad_norm": 6.4375, + "learning_rate": 8.569648672789496e-06, + "loss": 1.237971878051758, + "step": 30 + }, + { + "epoch": 0.4481792717086835, + "grad_norm": 5.59375, + "learning_rate": 6.980398830195785e-06, + "loss": 1.1971160888671875, + "step": 40 + }, + { + "epoch": 0.5602240896358543, + "grad_norm": 5.71875, + "learning_rate": 5.096956658859122e-06, + "loss": 1.1496850967407226, + "step": 50 + }, + { + "epoch": 0.6722689075630253, + "grad_norm": 6.0, + "learning_rate": 3.1991113759764493e-06, + "loss": 1.241246223449707, + "step": 60 + }, + { + "epoch": 0.7843137254901961, + "grad_norm": 5.625, + "learning_rate": 1.5687918106563326e-06, + "loss": 1.1770063400268556, + "step": 70 + }, + { + "epoch": 0.896358543417367, + "grad_norm": 5.8125, + "learning_rate": 4.481852951692672e-07, + "loss": 1.209663200378418, + "step": 80 + }, + { + "epoch": 1.0, + "grad_norm": 26.0, + "learning_rate": 3.760237478849793e-09, + "loss": 1.2288966178894043, + "step": 90 + }, + { + "epoch": 1.0, + "eval_loss": 1.1395946741104126, + "eval_runtime": 5.7504, + "eval_samples_per_second": 12.521, + "eval_steps_per_second": 1.565, + "step": 90 + }, + { + "epoch": 1.0, + "step": 90, + "total_flos": 8375949913795584.0, + "train_loss": 1.2328018612331815, + "train_runtime": 186.4804, + "train_samples_per_second": 19.107, + "train_steps_per_second": 0.483 + } + ], + "logging_steps": 10, + "max_steps": 90, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 8375949913795584.0, + "train_batch_size": 10, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..8eb31d3 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80b8f4e3d653b6ee86c8ccdf17e454d97e2cfa79075b9f75eb38fd621da8b27a +size 5777