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-CoT-QwQ-32B-epoch-1-no-packing
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen2.5-3B-WebArena-Lite-SFT-CoT-QwQ-32B-epoch-1-no-packing
+
+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-CoT-QwQ-32B-epoch-1-no-packing", 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/vl7figk5) 
+
+
+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": 161717585444864.0,
+    "train_loss": 0.8149667881630562,
+    "train_runtime": 2632.7258,
+    "train_samples": 9460,
+    "train_samples_per_second": 3.593,
+    "train_steps_per_second": 0.056
+}

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": 161717585444864.0,
+    "train_loss": 0.8149667881630562,
+    "train_runtime": 2632.7258,
+    "train_samples": 9460,
+    "train_samples_per_second": 3.593,
+    "train_steps_per_second": 0.056
+}

trainer_state.json

@@ -0,0 +1,245 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 148,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.033783783783783786,
+      "grad_norm": 4.081285861070036,
+      "learning_rate": 3.125e-05,
+      "loss": 1.343,
+      "step": 5
+    },
+    {
+      "epoch": 0.06756756756756757,
+      "grad_norm": 2.4767980475317306,
+      "learning_rate": 4.9977343997179584e-05,
+      "loss": 1.0898,
+      "step": 10
+    },
+    {
+      "epoch": 0.10135135135135136,
+      "grad_norm": 1.75418160634778,
+      "learning_rate": 4.97229876633906e-05,
+      "loss": 0.9965,
+      "step": 15
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 1.581608017901505,
+      "learning_rate": 4.91891643656567e-05,
+      "loss": 0.9496,
+      "step": 20
+    },
+    {
+      "epoch": 0.16891891891891891,
+      "grad_norm": 1.457452333355659,
+      "learning_rate": 4.838258724167838e-05,
+      "loss": 0.9404,
+      "step": 25
+    },
+    {
+      "epoch": 0.20270270270270271,
+      "grad_norm": 1.6831247945129768,
+      "learning_rate": 4.731339946677661e-05,
+      "loss": 0.8779,
+      "step": 30
+    },
+    {
+      "epoch": 0.23648648648648649,
+      "grad_norm": 1.538797370066566,
+      "learning_rate": 4.599504669757798e-05,
+      "loss": 0.87,
+      "step": 35
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 1.3334974862534241,
+      "learning_rate": 4.444410798508125e-05,
+      "loss": 0.8516,
+      "step": 40
+    },
+    {
+      "epoch": 0.30405405405405406,
+      "grad_norm": 1.282523609947544,
+      "learning_rate": 4.268008728347168e-05,
+      "loss": 0.8224,
+      "step": 45
+    },
+    {
+      "epoch": 0.33783783783783783,
+      "grad_norm": 1.3334225837945703,
+      "learning_rate": 4.072516817658065e-05,
+      "loss": 0.8235,
+      "step": 50
+    },
+    {
+      "epoch": 0.3716216216216216,
+      "grad_norm": 1.6171426981850356,
+      "learning_rate": 3.860393490644781e-05,
+      "loss": 0.8258,
+      "step": 55
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 1.211882443831182,
+      "learning_rate": 3.634306321221328e-05,
+      "loss": 0.8052,
+      "step": 60
+    },
+    {
+      "epoch": 0.4391891891891892,
+      "grad_norm": 1.2960251498072217,
+      "learning_rate": 3.397098486722039e-05,
+      "loss": 0.8011,
+      "step": 65
+    },
+    {
+      "epoch": 0.47297297297297297,
+      "grad_norm": 1.2312853794344398,
+      "learning_rate": 3.1517530132969326e-05,
+      "loss": 0.7848,
+      "step": 70
+    },
+    {
+      "epoch": 0.5067567567567568,
+      "grad_norm": 1.3787021580163523,
+      "learning_rate": 2.9013552626270894e-05,
+      "loss": 0.8097,
+      "step": 75
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 1.1958489309242977,
+      "learning_rate": 2.6490541317113427e-05,
+      "loss": 0.7474,
+      "step": 80
+    },
+    {
+      "epoch": 0.5743243243243243,
+      "grad_norm": 1.2265018406929975,
+      "learning_rate": 2.3980224536594803e-05,
+      "loss": 0.7643,
+      "step": 85
+    },
+    {
+      "epoch": 0.6081081081081081,
+      "grad_norm": 1.2553476359659121,
+      "learning_rate": 2.1514170974749814e-05,
+      "loss": 0.752,
+      "step": 90
+    },
+    {
+      "epoch": 0.6418918918918919,
+      "grad_norm": 1.1960996698324164,
+      "learning_rate": 1.9123392685956238e-05,
+      "loss": 0.7377,
+      "step": 95
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 1.1286279557451986,
+      "learning_rate": 1.6837955094357533e-05,
+      "loss": 0.728,
+      "step": 100
+    },
+    {
+      "epoch": 0.7094594594594594,
+      "grad_norm": 1.1422328938911805,
+      "learning_rate": 1.468659890370983e-05,
+      "loss": 0.7374,
+      "step": 105
+    },
+    {
+      "epoch": 0.7432432432432432,
+      "grad_norm": 1.1484788185826784,
+      "learning_rate": 1.2696378666356468e-05,
+      "loss": 0.7218,
+      "step": 110
+    },
+    {
+      "epoch": 0.777027027027027,
+      "grad_norm": 1.132142821163549,
+      "learning_rate": 1.0892322556534839e-05,
+      "loss": 0.7063,
+      "step": 115
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 1.073342872082975,
+      "learning_rate": 9.297117626563687e-06,
+      "loss": 0.7104,
+      "step": 120
+    },
+    {
+      "epoch": 0.8445945945945946,
+      "grad_norm": 1.108976138426985,
+      "learning_rate": 7.930824503996856e-06,
+      "loss": 0.7268,
+      "step": 125
+    },
+    {
+      "epoch": 0.8783783783783784,
+      "grad_norm": 1.1335555277239915,
+      "learning_rate": 6.810625117592363e-06,
+      "loss": 0.7072,
+      "step": 130
+    },
+    {
+      "epoch": 0.9121621621621622,
+      "grad_norm": 1.020215002734917,
+      "learning_rate": 5.950606624589065e-06,
+      "loss": 0.7096,
+      "step": 135
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 1.028950150275939,
+      "learning_rate": 5.361584256530833e-06,
+      "loss": 0.693,
+      "step": 140
+    },
+    {
+      "epoch": 0.9797297297297297,
+      "grad_norm": 1.071472930368092,
+      "learning_rate": 5.050965311454739e-06,
+      "loss": 0.6905,
+      "step": 145
+    },
+    {
+      "epoch": 1.0,
+      "step": 148,
+      "total_flos": 161717585444864.0,
+      "train_loss": 0.8149667881630562,
+      "train_runtime": 2632.7258,
+      "train_samples_per_second": 3.593,
+      "train_steps_per_second": 0.056
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 148,
+  "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": 161717585444864.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}