Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: transformers
+model_name: Qwen2.5-7B-Instruct
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen2.5-7B-Instruct
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-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="hzk17/Qwen2.5-7B-Instruct", 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/haozhongkai/huggingface/runs/chotrd31) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.16.0.dev0
+- Transformers: 4.49.0
+- Pytorch: 2.5.1+cu124
+- 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": 7.380890399696486e+16,
+    "train_loss": 0.30586605986883475,
+    "train_runtime": 3675.8825,
+    "train_samples": 22161,
+    "train_samples_per_second": 0.754,
+    "train_steps_per_second": 0.023
+}

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": 7.380890399696486e+16,
+    "train_loss": 0.30586605986883475,
+    "train_runtime": 3675.8825,
+    "train_samples": 22161,
+    "train_samples_per_second": 0.754,
+    "train_steps_per_second": 0.023
+}

trainer_state.json

@@ -0,0 +1,161 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9655172413793105,
+  "eval_steps": 500,
+  "global_step": 86,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11494252873563218,
+      "grad_norm": 3.822647032868502,
+      "learning_rate": 5e-05,
+      "loss": 0.562,
+      "step": 5
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 3.979017243963418,
+      "learning_rate": 4.957824448911616e-05,
+      "loss": 0.4905,
+      "step": 10
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.8114758591310017,
+      "learning_rate": 4.832878930855004e-05,
+      "loss": 0.3903,
+      "step": 15
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.3622560433026008,
+      "learning_rate": 4.629847575679107e-05,
+      "loss": 0.3769,
+      "step": 20
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "grad_norm": 0.3800914208265442,
+      "learning_rate": 4.356341902755273e-05,
+      "loss": 0.3531,
+      "step": 25
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.33355586297162576,
+      "learning_rate": 4.0226154698447124e-05,
+      "loss": 0.32,
+      "step": 30
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "grad_norm": 0.2954148614958112,
+      "learning_rate": 3.6411794735881035e-05,
+      "loss": 0.3209,
+      "step": 35
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.25530923128267685,
+      "learning_rate": 3.226333712516175e-05,
+      "loss": 0.2996,
+      "step": 40
+    },
+    {
+      "epoch": 1.0229885057471264,
+      "grad_norm": 0.4098548246432745,
+      "learning_rate": 2.793630496486605e-05,
+      "loss": 0.2888,
+      "step": 45
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 0.2635419967801862,
+      "learning_rate": 2.359291600249407e-05,
+      "loss": 0.2405,
+      "step": 50
+    },
+    {
+      "epoch": 1.2528735632183907,
+      "grad_norm": 0.2401749479804668,
+      "learning_rate": 1.939600119189402e-05,
+      "loss": 0.2377,
+      "step": 55
+    },
+    {
+      "epoch": 1.367816091954023,
+      "grad_norm": 0.22443674266344824,
+      "learning_rate": 1.5502900261961954e-05,
+      "loss": 0.2431,
+      "step": 60
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 0.22116148983782039,
+      "learning_rate": 1.2059563147953499e-05,
+      "loss": 0.2271,
+      "step": 65
+    },
+    {
+      "epoch": 1.5977011494252875,
+      "grad_norm": 0.20976941774737246,
+      "learning_rate": 9.195078419083233e-06,
+      "loss": 0.2208,
+      "step": 70
+    },
+    {
+      "epoch": 1.7126436781609196,
+      "grad_norm": 0.20468159198600405,
+      "learning_rate": 7.0168338282617025e-06,
+      "loss": 0.2255,
+      "step": 75
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 0.18909828658237993,
+      "learning_rate": 5.6064904119539654e-06,
+      "loss": 0.2002,
+      "step": 80
+    },
+    {
+      "epoch": 1.9425287356321839,
+      "grad_norm": 0.19878948692799125,
+      "learning_rate": 5.016921068654824e-06,
+      "loss": 0.2228,
+      "step": 85
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "step": 86,
+      "total_flos": 7.380890399696486e+16,
+      "train_loss": 0.30586605986883475,
+      "train_runtime": 3675.8825,
+      "train_samples_per_second": 0.754,
+      "train_steps_per_second": 0.023
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 86,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 7.380890399696486e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}