metadata
base_model: google/paligemma-3b-pt-224
library_name: peft
license: gemma
tags:
- generated_from_trainer
model-index:
- name: paligemma-cnmc-ft
results: []
paligemma-cnmc-ft
This model is a fine-tuned version of google/paligemma-3b-pt-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1868
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 170
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.9645 | 17 | 1.4167 |
| No log | 1.9858 | 35 | 1.1455 |
| 1.2186 | 2.9504 | 52 | 0.6528 |
| 1.2186 | 3.9716 | 70 | 0.3555 |
| 1.2186 | 4.9929 | 88 | 0.2881 |
| 0.3872 | 5.9574 | 105 | 0.2618 |
| 0.3872 | 6.9787 | 123 | 0.2299 |
| 0.3872 | 8.0 | 141 | 0.1961 |
| 0.2563 | 8.9645 | 158 | 0.1834 |
| 0.2563 | 9.9858 | 176 | 0.1523 |
| 0.2563 | 10.9504 | 193 | 0.1612 |
| 0.2196 | 11.9716 | 211 | 0.1505 |
| 0.2196 | 12.9929 | 229 | 0.1868 |
Framework versions
- PEFT 0.11.1
- Transformers 4.43.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1