metadata
library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-11B-Vision
tags:
- generated_from_trainer
model-index:
- name: llama-32-11b-vlm_peft_output33
results: []
llama-32-11b-vlm_peft_output33
This model is a fine-tuned version of meta-llama/Llama-3.2-11B-Vision on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4173
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5815 | 0.1 | 5 | 1.4947 |
| 1.2372 | 0.2 | 10 | 1.4967 |
| 1.2151 | 0.3 | 15 | 1.4176 |
| 1.0996 | 0.4 | 20 | 1.3943 |
| 1.0703 | 0.5 | 25 | 1.3741 |
| 0.8924 | 0.6 | 30 | 1.3785 |
| 1.1963 | 0.7 | 35 | 1.3736 |
| 1.038 | 0.8 | 40 | 1.3599 |
| 1.2125 | 0.9 | 45 | 1.3479 |
| 1.1221 | 1.0 | 50 | 1.3357 |
| 0.7035 | 1.1 | 55 | 1.3408 |
| 1.0136 | 1.2 | 60 | 1.3743 |
| 1.0031 | 1.3 | 65 | 1.4109 |
| 0.7483 | 1.4 | 70 | 1.4218 |
| 0.8856 | 1.5 | 75 | 1.4173 |
Framework versions
- PEFT 0.15.1
- Transformers 4.48.3
- Pytorch 2.7.0a0+7c8ec84dab.nv25.03
- Datasets 3.5.0
- Tokenizers 0.21.1