Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: google/gemma-3-4b-it
+library_name: transformers
+model_name: gemma-3-4b-it-capybara-test
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for gemma-3-4b-it-capybara-test
+
+This model is a fine-tuned version of [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-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="burtenshaw/gemma-3-4b-it-capybara-test", 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/smartwithfood/huggingface/runs/le76pzhs) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.16.0.dev0
+- Transformers: 4.50.0.dev0
+- Pytorch: 2.4.1
+- Datasets: 3.4.0
+- 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": 3.336499157376e+17,
+    "train_loss": 0.0,
+    "train_runtime": 2859.1765,
+    "train_samples": 15806,
+    "train_samples_per_second": 1.342,
+    "train_steps_per_second": 0.671
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.50.0.dev0"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 3.336499157376e+17,
+    "train_loss": 0.0,
+    "train_runtime": 2859.1765,
+    "train_samples": 15806,
+    "train_samples_per_second": 1.342,
+    "train_steps_per_second": 0.671
+}

trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1918,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.26068821689259647,
+      "grad_norm": NaN,
+      "learning_rate": 7.393117831074036e-06,
+      "loss": 1.1435,
+      "mean_token_accuracy": 0.44466638553142546,
+      "num_tokens": 3999914.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.5213764337851929,
+      "grad_norm": NaN,
+      "learning_rate": 4.7862356621480715e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 0.0,
+      "num_tokens": 7989385.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7820646506777894,
+      "grad_norm": NaN,
+      "learning_rate": 2.1793534932221064e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 0.0,
+      "num_tokens": 3993373.0,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "mean_token_accuracy": 0.0,
+      "num_tokens": 7324027.0,
+      "step": 1918,
+      "total_flos": 3.336499157376e+17,
+      "train_loss": 0.0,
+      "train_runtime": 2859.1765,
+      "train_samples_per_second": 1.342,
+      "train_steps_per_second": 0.671
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1918,
+  "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": 3.336499157376e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}