Model save

README.md

@@ -0,0 +1,57 @@
+---
+library_name: transformers
+model_name: Qwen3-0.6B-Open-R1-Distill
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen3-0.6B-Open-R1-Distill
+
+This model is a fine-tuned version of [None](https://huggingface.co/None).
+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/Qwen3-0.6B-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
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.2
+- Transformers: 4.52.3
+- Pytorch: 2.5.1
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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": 5.211391058037965e+16,
+    "train_loss": 0.09458173938046872,
+    "train_runtime": 117.3732,
+    "train_samples": 1000,
+    "train_samples_per_second": 164.066,
+    "train_steps_per_second": 1.304
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.3"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3dee87fff88c9f6799d6820e6ef32a6a7ff8a233b88314ff78247af8f2d3464
+oid sha256:eeb8dbfdbed5476a09608aaec303528b621ff55ca5cba3e6b83b39b35b189abd
 size 1192135096

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 5.211391058037965e+16,
+    "train_loss": 0.09458173938046872,
+    "train_runtime": 117.3732,
+    "train_samples": 1000,
+    "train_samples_per_second": 164.066,
+    "train_steps_per_second": 1.304
+}

trainer_state.json

@@ -0,0 +1,253 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 153,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 0.375,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1074,
+      "step": 5
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 0.3359375,
+      "learning_rate": 4.9994719205415894e-05,
+      "loss": 0.099,
+      "step": 10
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.318359375,
+      "learning_rate": 4.981015154140181e-05,
+      "loss": 0.1039,
+      "step": 15
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.298828125,
+      "learning_rate": 4.936401774893088e-05,
+      "loss": 0.1032,
+      "step": 20
+    },
+    {
+      "epoch": 0.49019607843137253,
+      "grad_norm": 0.302734375,
+      "learning_rate": 4.8661548338815794e-05,
+      "loss": 0.1,
+      "step": 25
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.267578125,
+      "learning_rate": 4.771097912261625e-05,
+      "loss": 0.0995,
+      "step": 30
+    },
+    {
+      "epoch": 0.6862745098039216,
+      "grad_norm": 0.287109375,
+      "learning_rate": 4.652345465527847e-05,
+      "loss": 0.1007,
+      "step": 35
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.27734375,
+      "learning_rate": 4.511289757541801e-05,
+      "loss": 0.098,
+      "step": 40
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.271484375,
+      "learning_rate": 4.349584537511159e-05,
+      "loss": 0.0968,
+      "step": 45
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 0.2578125,
+      "learning_rate": 4.16912565129229e-05,
+      "loss": 0.0988,
+      "step": 50
+    },
+    {
+      "epoch": 1.0784313725490196,
+      "grad_norm": 0.279296875,
+      "learning_rate": 3.9720288143309735e-05,
+      "loss": 0.0961,
+      "step": 55
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.271484375,
+      "learning_rate": 3.7606048068332286e-05,
+      "loss": 0.0909,
+      "step": 60
+    },
+    {
+      "epoch": 1.2745098039215685,
+      "grad_norm": 0.30078125,
+      "learning_rate": 3.5373323819801494e-05,
+      "loss": 0.0942,
+      "step": 65
+    },
+    {
+      "epoch": 1.3725490196078431,
+      "grad_norm": 0.267578125,
+      "learning_rate": 3.304829204813215e-05,
+      "loss": 0.09,
+      "step": 70
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.271484375,
+      "learning_rate": 3.065821162505025e-05,
+      "loss": 0.0932,
+      "step": 75
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 0.255859375,
+      "learning_rate": 2.8231104058245068e-05,
+      "loss": 0.0894,
+      "step": 80
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.25390625,
+      "learning_rate": 2.579542496481177e-05,
+      "loss": 0.0964,
+      "step": 85
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.29296875,
+      "learning_rate": 2.3379730455158238e-05,
+      "loss": 0.0897,
+      "step": 90
+    },
+    {
+      "epoch": 1.8627450980392157,
+      "grad_norm": 0.26171875,
+      "learning_rate": 2.101234233871961e-05,
+      "loss": 0.0937,
+      "step": 95
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 0.279296875,
+      "learning_rate": 1.8721016076637528e-05,
+      "loss": 0.0909,
+      "step": 100
+    },
+    {
+      "epoch": 2.0588235294117645,
+      "grad_norm": 0.279296875,
+      "learning_rate": 1.6532615374355324e-05,
+      "loss": 0.0966,
+      "step": 105
+    },
+    {
+      "epoch": 2.156862745098039,
+      "grad_norm": 0.24609375,
+      "learning_rate": 1.4472797229233409e-05,
+      "loss": 0.0882,
+      "step": 110
+    },
+    {
+      "epoch": 2.2549019607843137,
+      "grad_norm": 0.251953125,
+      "learning_rate": 1.2565711125713656e-05,
+      "loss": 0.0869,
+      "step": 115
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.2578125,
+      "learning_rate": 1.0833715904694373e-05,
+      "loss": 0.0909,
+      "step": 120
+    },
+    {
+      "epoch": 2.450980392156863,
+      "grad_norm": 0.26171875,
+      "learning_rate": 9.297117626563687e-06,
+      "loss": 0.0902,
+      "step": 125
+    },
+    {
+      "epoch": 2.549019607843137,
+      "grad_norm": 0.23046875,
+      "learning_rate": 7.973931501207469e-06,
+      "loss": 0.091,
+      "step": 130
+    },
+    {
+      "epoch": 2.6470588235294117,
+      "grad_norm": 0.283203125,
+      "learning_rate": 6.879670676144916e-06,
+      "loss": 0.0914,
+      "step": 135
+    },
+    {
+      "epoch": 2.7450980392156863,
+      "grad_norm": 0.240234375,
+      "learning_rate": 6.027164359057668e-06,
+      "loss": 0.0909,
+      "step": 140
+    },
+    {
+      "epoch": 2.843137254901961,
+      "grad_norm": 0.2333984375,
+      "learning_rate": 5.426407407059619e-06,
+      "loss": 0.0888,
+      "step": 145
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.2431640625,
+      "learning_rate": 5.084443146135623e-06,
+      "loss": 0.0911,
+      "step": 150
+    },
+    {
+      "epoch": 3.0,
+      "step": 153,
+      "total_flos": 5.211391058037965e+16,
+      "train_loss": 0.09458173938046872,
+      "train_runtime": 117.3732,
+      "train_samples_per_second": 164.066,
+      "train_steps_per_second": 1.304
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 153,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 5.211391058037965e+16,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}