Model save

README.md

@@ -0,0 +1,57 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: transformers
+model_name: gemma-2-9b-it-star-code-v1_10-5-3Rounds-iter-1
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for gemma-2-9b-it-star-code-v1_10-5-3Rounds-iter-1
+
+This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it).
+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="TongZheng1999/gemma-2-9b-it-star-code-v1_10-5-3Rounds-iter-1", 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/kidzheng/huggingface/runs/99rj3hgy)
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.12.0
+- Transformers: 4.49.0
+- Pytorch: 2.6.0
+- 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 +1,9 @@
+{
+    "epoch": 4.0,
+    "total_flos": 9.994818287147418e+16,
+    "train_loss": 0.3279022932052612,
+    "train_runtime": 3201.833,
+    "train_samples": 534,
+    "train_samples_per_second": 0.834,
+    "train_steps_per_second": 0.006
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.49.0"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "total_flos": 9.994818287147418e+16,
+    "train_loss": 0.3279022932052612,
+    "train_runtime": 3201.833,
+    "train_samples": 534,
+    "train_samples_per_second": 0.834,
+    "train_steps_per_second": 0.006
+}

trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23880597014925373,
+      "grad_norm": 29.275244557684626,
+      "learning_rate": 4.9692208514878445e-06,
+      "loss": 1.492,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.877218753196121,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.4997,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7924658588380961,
+      "learning_rate": 2.5e-06,
+      "loss": 0.2348,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6495439150180484,
+      "learning_rate": 7.322330470336314e-07,
+      "loss": 0.1975,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.5855051339722586,
+      "learning_rate": 0.0,
+      "loss": 0.1812,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "step": 20,
+      "total_flos": 9.994818287147418e+16,
+      "train_loss": 0.3279022932052612,
+      "train_runtime": 3201.833,
+      "train_samples_per_second": 0.834,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.994818287147418e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}