Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen2.5-3B-Instruct
+library_name: transformers
+model_name: Qwen2.5-3B-WebArena-Lite-SFT-epoch-1-no-sys
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen2.5-3B-WebArena-Lite-SFT-epoch-1-no-sys
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-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="weizhepei/Qwen2.5-3B-WebArena-Lite-SFT-epoch-1-no-sys", 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/uva-llm/huggingface/runs/hhbuw1lm) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.16.0.dev0
+- Transformers: 4.49.0
+- Pytorch: 2.5.1
+- Datasets: 3.4.1
+- 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": 109874636652544.0,
+    "train_loss": 0.25139871642396255,
+    "train_runtime": 1349.1734,
+    "train_samples": 9460,
+    "train_samples_per_second": 7.012,
+    "train_steps_per_second": 0.055
+}

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": "4.49.0"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 109874636652544.0,
+    "train_loss": 0.25139871642396255,
+    "train_runtime": 1349.1734,
+    "train_samples": 9460,
+    "train_samples_per_second": 7.012,
+    "train_steps_per_second": 0.055
+}

trainer_state.json

@@ -0,0 +1,140 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 74,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06756756756756757,
+      "grad_norm": 3.6427194357256854,
+      "learning_rate": 4.9977343997179584e-05,
+      "loss": 0.9661,
+      "step": 5
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 1.7552581485291558,
+      "learning_rate": 4.91891643656567e-05,
+      "loss": 0.359,
+      "step": 10
+    },
+    {
+      "epoch": 0.20270270270270271,
+      "grad_norm": 1.6747978976981994,
+      "learning_rate": 4.731339946677661e-05,
+      "loss": 0.2818,
+      "step": 15
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 1.2689258407097461,
+      "learning_rate": 4.444410798508125e-05,
+      "loss": 0.2288,
+      "step": 20
+    },
+    {
+      "epoch": 0.33783783783783783,
+      "grad_norm": 1.376943391293494,
+      "learning_rate": 4.072516817658065e-05,
+      "loss": 0.1905,
+      "step": 25
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 1.682458902725447,
+      "learning_rate": 3.634306321221328e-05,
+      "loss": 0.2185,
+      "step": 30
+    },
+    {
+      "epoch": 0.47297297297297297,
+      "grad_norm": 44.450116180248855,
+      "learning_rate": 3.1517530132969326e-05,
+      "loss": 0.2003,
+      "step": 35
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.7718036212010672,
+      "learning_rate": 2.6490541317113427e-05,
+      "loss": 0.1907,
+      "step": 40
+    },
+    {
+      "epoch": 0.6081081081081081,
+      "grad_norm": 0.9784107778853152,
+      "learning_rate": 2.1514170974749814e-05,
+      "loss": 0.1784,
+      "step": 45
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.8473633960215592,
+      "learning_rate": 1.6837955094357533e-05,
+      "loss": 0.1618,
+      "step": 50
+    },
+    {
+      "epoch": 0.7432432432432432,
+      "grad_norm": 0.7215726163389997,
+      "learning_rate": 1.2696378666356468e-05,
+      "loss": 0.1647,
+      "step": 55
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.7924473498293266,
+      "learning_rate": 9.297117626563687e-06,
+      "loss": 0.1669,
+      "step": 60
+    },
+    {
+      "epoch": 0.8783783783783784,
+      "grad_norm": 0.8106883780712614,
+      "learning_rate": 6.810625117592363e-06,
+      "loss": 0.1644,
+      "step": 65
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.677254672377957,
+      "learning_rate": 5.361584256530833e-06,
+      "loss": 0.1462,
+      "step": 70
+    },
+    {
+      "epoch": 1.0,
+      "step": 74,
+      "total_flos": 109874636652544.0,
+      "train_loss": 0.25139871642396255,
+      "train_runtime": 1349.1734,
+      "train_samples_per_second": 7.012,
+      "train_steps_per_second": 0.055
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 74,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 109874636652544.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}