Model save

README.md

@@ -1,58 +1,56 @@
 ---
+library_name: peft
+license: gemma
 base_model: google/gemma-3-12b-pt
-library_name: transformers
-model_name: gemma-smart-fine-tuned
 tags:
-- generated_from_trainer
 - trl
 - sft
-licence: license
+- generated_from_trainer
+model-index:
+- name: gemma-smart-fine-tuned
+  results: []
 ---
 
-# Model Card for gemma-smart-fine-tuned
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
 
-This model is a fine-tuned version of [google/gemma-3-12b-pt](https://huggingface.co/google/gemma-3-12b-pt).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/tvaldeca-harvard-university/smart_gemma_ft/runs/dl57s3bv)
+# gemma-smart-fine-tuned
 
-## Quick start
+This model is a fine-tuned version of [google/gemma-3-12b-pt](https://huggingface.co/google/gemma-3-12b-pt) on an unknown dataset.
 
-```python
-from transformers import pipeline
+## Model description
 
-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="tvaldeca/gemma-smart-fine-tuned", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
+More information needed
 
-## Training procedure
+## Intended uses & limitations
 
-[<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/tvaldeca-harvard-university/smart_gemma_ft/runs/gl6z5myf) 
+More information needed
 
+## Training and evaluation data
 
-This model was trained with SFT.
+More information needed
 
-### Framework versions
-
-- TRL: 0.16.0
-- Transformers: 4.51.0.dev0
-- Pytorch: 2.6.0+cu124
-- Datasets: 3.3.2
-- Tokenizers: 0.21.1
+## Training procedure
 
-## Citations
+### Training hyperparameters
 
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 7
 
+### Framework versions
 
-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}}
-}
-```
+- PEFT 0.14.0
+- Transformers 4.51.0.dev0
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:931d6208103242e810adfd925c88716e02c5f249bf693d39befaeea56010ea28
+oid sha256:4de3aa855dcb1ab8350f108bd80ec024531d6f37ece99f08f68ec052ec5bc93d
 size 4324331232