Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: transformers
+model_name: oR1-Qwen-7B-Coder-Agentic-e9-lr5-b8
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for oR1-Qwen-7B-Coder-Agentic-e9-lr5-b8
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-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="akseljoonas/oR1-Qwen-7B-Coder-Agentic-e9-lr5-b8", 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/akseljoonas-university-of-groningen/huggingface/runs/so6tyny1) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.16.0
+- Transformers: 4.50.0
+- Pytorch: 2.6.0
+- Datasets: 3.5.0
+- 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": 70898833948672.0,
+    "train_loss": 0.48625098499986863,
+    "train_runtime": 731.1833,
+    "train_samples": 1928,
+    "train_samples_per_second": 6.634,
+    "train_steps_per_second": 0.098
+}

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": "4.50.0"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 70898833948672.0,
+    "train_loss": 0.48625098499986863,
+    "train_runtime": 731.1833,
+    "train_samples": 1928,
+    "train_samples_per_second": 6.634,
+    "train_steps_per_second": 0.098
+}

trainer_state.json

@@ -0,0 +1,171 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 72,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 1.453149383018604,
+      "learning_rate": 3.125e-05,
+      "loss": 1.1323,
+      "mean_token_accuracy": 0.758558577299118,
+      "num_tokens": 2505918.0,
+      "step": 5
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.8843952108301645,
+      "learning_rate": 4.8437500000000005e-05,
+      "loss": 0.9418,
+      "mean_token_accuracy": 0.786483476559321,
+      "num_tokens": 4791423.0,
+      "step": 10
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.35303048389497826,
+      "learning_rate": 4.453125e-05,
+      "loss": 0.7428,
+      "mean_token_accuracy": 0.8249349921941758,
+      "num_tokens": 7330272.0,
+      "step": 15
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 0.3908112032783539,
+      "learning_rate": 4.0625000000000005e-05,
+      "loss": 0.6935,
+      "mean_token_accuracy": 0.8370609614584181,
+      "num_tokens": 9618952.0,
+      "step": 20
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 0.22079369830396672,
+      "learning_rate": 3.671875e-05,
+      "loss": 0.5392,
+      "mean_token_accuracy": 0.866364911198616,
+      "num_tokens": 12114377.0,
+      "step": 25
+    },
+    {
+      "epoch": 3.3529411764705883,
+      "grad_norm": 0.22167112596094207,
+      "learning_rate": 3.2812500000000005e-05,
+      "loss": 0.4885,
+      "mean_token_accuracy": 0.8808583782778846,
+      "num_tokens": 14409009.0,
+      "step": 30
+    },
+    {
+      "epoch": 3.9411764705882355,
+      "grad_norm": 0.9782959114884348,
+      "learning_rate": 2.890625e-05,
+      "loss": 0.4183,
+      "mean_token_accuracy": 0.8973524689674377,
+      "num_tokens": 16918082.0,
+      "step": 35
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 0.4095276244792195,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3897,
+      "mean_token_accuracy": 0.9068596760431925,
+      "num_tokens": 19217454.0,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.21972425572371848,
+      "learning_rate": 2.109375e-05,
+      "loss": 0.2675,
+      "mean_token_accuracy": 0.9311207168632083,
+      "num_tokens": 21475135.0,
+      "step": 45
+    },
+    {
+      "epoch": 5.588235294117647,
+      "grad_norm": 0.22803635719329346,
+      "learning_rate": 1.71875e-05,
+      "loss": 0.2681,
+      "mean_token_accuracy": 0.9340837925672532,
+      "num_tokens": 23999790.0,
+      "step": 50
+    },
+    {
+      "epoch": 6.117647058823529,
+      "grad_norm": 0.3459891609100074,
+      "learning_rate": 1.3281250000000001e-05,
+      "loss": 0.2211,
+      "mean_token_accuracy": 0.9482026563750373,
+      "num_tokens": 26264984.0,
+      "step": 55
+    },
+    {
+      "epoch": 6.705882352941177,
+      "grad_norm": 0.2374700982971719,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.1483,
+      "mean_token_accuracy": 0.9612507849931717,
+      "num_tokens": 28792279.0,
+      "step": 60
+    },
+    {
+      "epoch": 7.235294117647059,
+      "grad_norm": 0.276768438905862,
+      "learning_rate": 5.46875e-06,
+      "loss": 0.2467,
+      "mean_token_accuracy": 0.9479848013983833,
+      "num_tokens": 31085796.0,
+      "step": 65
+    },
+    {
+      "epoch": 7.823529411764706,
+      "grad_norm": 0.18403035516539035,
+      "learning_rate": 1.5625e-06,
+      "loss": 0.1465,
+      "mean_token_accuracy": 0.9668508440256118,
+      "num_tokens": 33579925.0,
+      "step": 70
+    },
+    {
+      "epoch": 8.0,
+      "mean_token_accuracy": 0.955658088127772,
+      "num_tokens": 34358154.0,
+      "step": 72,
+      "total_flos": 70898833948672.0,
+      "train_loss": 0.48625098499986863,
+      "train_runtime": 731.1833,
+      "train_samples_per_second": 6.634,
+      "train_steps_per_second": 0.098
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 72,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 70898833948672.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}