metadata
license: mit
base_model: microsoft/git-base
tags:
- generated_from_trainer
model-index:
- name: GenerativeImage2Text-naruto
results: []
GenerativeImage2Text-naruto
This model is a fine-tuned version of microsoft/git-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0551
- Wer Score: 9.8
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|---|---|---|---|---|
| 5.6909 | 3.7037 | 50 | 2.9342 | 11.0167 |
| 1.1195 | 7.4074 | 100 | 0.1202 | 11.05 |
| 0.036 | 11.1111 | 150 | 0.0471 | 0.3833 |
| 0.0128 | 14.8148 | 200 | 0.0492 | 0.45 |
| 0.0101 | 18.5185 | 250 | 0.0508 | 4.35 |
| 0.0087 | 22.2222 | 300 | 0.0501 | 9.4 |
| 0.0081 | 25.9259 | 350 | 0.0531 | 10.35 |
| 0.0075 | 29.6296 | 400 | 0.0535 | 9.7833 |
| 0.0068 | 33.3333 | 450 | 0.0525 | 7.0333 |
| 0.0064 | 37.0370 | 500 | 0.0545 | 9.7333 |
| 0.0059 | 40.7407 | 550 | 0.0537 | 9.7333 |
| 0.0055 | 44.4444 | 600 | 0.0550 | 9.7833 |
| 0.0051 | 48.1481 | 650 | 0.0551 | 9.8 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1