Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+library_name: transformers
+model_name: Qwen2.5-0.5B-Open-R1-Distill
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen2.5-0.5B-Open-R1-Distill
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct).
+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="Blancy/Qwen2.5-0.5B-Open-R1-Distill", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/224015062-chinese-university-of-hong-kong-shenzhen/huggingface/runs/2vdrtqap) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.2
+- Transformers: 4.49.0
+- Pytorch: 2.5.1
+- Datasets: 3.3.2
+- Tokenizers: 0.21.0
+
+## 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 Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 4079631728640.0,
+    "train_loss": 1.5182941075029044,
+    "train_runtime": 127.2004,
+    "train_samples": 1000,
+    "train_samples_per_second": 72.728,
+    "train_steps_per_second": 1.14
+}

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": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.49.0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70a0cf8e9668152d355deeafad38baaa98554c85dc088840d68f23a263519524
+oid sha256:a3c39edbff1078192bae4a27cfa917e03fa5eb62fe6ffcd38cde8344746bcb85
 size 988097824

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 4079631728640.0,
+    "train_loss": 1.5182941075029044,
+    "train_runtime": 127.2004,
+    "train_samples": 1000,
+    "train_samples_per_second": 72.728,
+    "train_steps_per_second": 1.14
+}

trainer_state.json

@@ -0,0 +1,245 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 145,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 5.118941856424631,
+      "learning_rate": 3.125e-05,
+      "loss": 1.7914,
+      "step": 5
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 2.9573423689762866,
+      "learning_rate": 4.997634107543713e-05,
+      "loss": 1.666,
+      "step": 10
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 2.039420630897441,
+      "learning_rate": 4.971074924974395e-05,
+      "loss": 1.6124,
+      "step": 15
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 2.1953763522509946,
+      "learning_rate": 4.915349129238729e-05,
+      "loss": 1.5929,
+      "step": 20
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 2.049453928196352,
+      "learning_rate": 4.8311884978689945e-05,
+      "loss": 1.5655,
+      "step": 25
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 1.7738134431283565,
+      "learning_rate": 4.719698207710602e-05,
+      "loss": 1.5665,
+      "step": 30
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 1.7877365606373776,
+      "learning_rate": 4.582342322009812e-05,
+      "loss": 1.5434,
+      "step": 35
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 1.6827790459654124,
+      "learning_rate": 4.4209245646929606e-05,
+      "loss": 1.5528,
+      "step": 40
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 1.6193600867831015,
+      "learning_rate": 4.2375646343046135e-05,
+      "loss": 1.5286,
+      "step": 45
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 1.6304628801910557,
+      "learning_rate": 4.034670368644256e-05,
+      "loss": 1.5466,
+      "step": 50
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 1.5317716414980957,
+      "learning_rate": 3.8149061256287007e-05,
+      "loss": 1.5496,
+      "step": 55
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 1.5527683273021031,
+      "learning_rate": 3.581157795594989e-05,
+      "loss": 1.4883,
+      "step": 60
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 1.593847047843435,
+      "learning_rate": 3.3364949044936924e-05,
+      "loss": 1.5387,
+      "step": 65
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 1.4396115722574465,
+      "learning_rate": 3.084130305624209e-05,
+      "loss": 1.511,
+      "step": 70
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 1.6057921876869088,
+      "learning_rate": 2.8273779892303337e-05,
+      "loss": 1.4434,
+      "step": 75
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 1.5280825241631029,
+      "learning_rate": 2.5696095639901996e-05,
+      "loss": 1.5058,
+      "step": 80
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 1.5666909004892384,
+      "learning_rate": 2.314209981875008e-05,
+      "loss": 1.5186,
+      "step": 85
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 1.4281308841157434,
+      "learning_rate": 2.0645330877869e-05,
+      "loss": 1.4822,
+      "step": 90
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 1.3745413443273744,
+      "learning_rate": 1.8238575776872595e-05,
+      "loss": 1.4529,
+      "step": 95
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 1.5081595406938955,
+      "learning_rate": 1.5953439435625384e-05,
+      "loss": 1.4762,
+      "step": 100
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 1.3768197030526457,
+      "learning_rate": 1.3819929706157959e-05,
+      "loss": 1.4915,
+      "step": 105
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 1.4228532169763397,
+      "learning_rate": 1.1866063316886964e-05,
+      "loss": 1.4761,
+      "step": 110
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 1.3531199760661987,
+      "learning_rate": 1.0117497963783762e-05,
+      "loss": 1.4597,
+      "step": 115
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 1.297275568713758,
+      "learning_rate": 8.597195379780726e-06,
+      "loss": 1.4838,
+      "step": 120
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 1.2780573701142792,
+      "learning_rate": 7.3251198069053465e-06,
+      "loss": 1.4329,
+      "step": 125
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 1.3276253224901293,
+      "learning_rate": 6.317975830732497e-06,
+      "loss": 1.4417,
+      "step": 130
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 1.2548059361443487,
+      "learning_rate": 5.588989019848609e-06,
+      "loss": 1.4287,
+      "step": 135
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 1.2798168590694643,
+      "learning_rate": 5.147732250916841e-06,
+      "loss": 1.462,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2571681575699087,
+      "learning_rate": 5e-06,
+      "loss": 1.4216,
+      "step": 145
+    },
+    {
+      "epoch": 1.0,
+      "step": 145,
+      "total_flos": 4079631728640.0,
+      "train_loss": 1.5182941075029044,
+      "train_runtime": 127.2004,
+      "train_samples_per_second": 72.728,
+      "train_steps_per_second": 1.14
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 145,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4079631728640.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}