Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: google/paligemma2-3b-pt-224
+library_name: transformers
+model_name: paligemma2-3b-pt-224-sft-lora-tartandrive-only_rdp
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for paligemma2-3b-pt-224-sft-lora-tartandrive-only_rdp
+
+This model is a fine-tuned version of [google/paligemma2-3b-pt-224](https://huggingface.co/google/paligemma2-3b-pt-224).
+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="mateoguaman/paligemma2-3b-pt-224-sft-lora-tartandrive-only_rdp", 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/mateoguaman/paligemma2-3b-pt-224-sft-lora-tartandrive-only_rdp/runs/eru1egy7) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.2
+- Transformers: 4.49.0
+- Pytorch: 2.6.0
+- 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}}
+}
+```

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba5253ee62eb2a2e170cc07c5c195a78e8a9b17c32e0d7ab868d7e4072688104
+oid sha256:86606b4b54de2705bc2b220623757d77fcb5de51a5ec0e809a02c8b6e25cd81c
 size 95091000

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 1.3027532353411482e+18,
+    "train_loss": 2.5727180697723186,
+    "train_runtime": 17660.899,
+    "train_samples": 63052,
+    "train_samples_per_second": 17.851,
+    "train_steps_per_second": 0.558
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 1.3027532353411482e+18,
+    "train_loss": 2.5727180697723186,
+    "train_runtime": 17660.899,
+    "train_samples": 63052,
+    "train_samples_per_second": 17.851,
+    "train_steps_per_second": 0.558
+}

training.log

@@ -362,3 +362,5 @@ Navigate to x=<loc0636>, y=<loc0320>
 2025-04-26 01:49:52 - INFO - __main__ - Loaded model is not a PeftModel. Getting PEFT config based on model_args.
 2025-04-26 01:49:54 - WARNING - accelerate.utils.other - Detected kernel version 4.18.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher.
 2025-04-26 01:50:22 - INFO - __main__ - *** Train ***
+2025-04-26 06:44:46 - WARNING - huggingface_hub.hf_api - No files have been modified since last commit. Skipping to prevent empty commit.
+2025-04-26 06:44:46 - INFO - __main__ - *** Save model ***