metadata
license: mit
base_model: microsoft/git-base
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: git-base-food
results: []
git-base-food
This model is a fine-tuned version of microsoft/git-base on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0068
- Wer Score: 31.5402
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|---|---|---|---|---|
| No log | 1.21 | 20 | 0.0096 | 46.8391 |
| No log | 2.42 | 40 | 0.0088 | 30.3793 |
| No log | 3.64 | 60 | 0.0071 | 29.5632 |
| No log | 4.85 | 80 | 0.0065 | 34.3793 |
| No log | 6.06 | 100 | 0.0067 | 32.4138 |
| No log | 7.27 | 120 | 0.0072 | 32.4713 |
| No log | 8.48 | 140 | 0.0066 | 28.5977 |
| No log | 9.7 | 160 | 0.0068 | 27.2529 |
| No log | 10.91 | 180 | 0.0063 | 25.2414 |
| No log | 12.12 | 200 | 0.0061 | 35.0575 |
| No log | 13.33 | 220 | 0.0065 | 29.9770 |
| No log | 14.55 | 240 | 0.0068 | 31.1609 |
| No log | 15.76 | 260 | 0.0067 | 28.7356 |
| No log | 16.97 | 280 | 0.0068 | 30.9310 |
| No log | 18.18 | 300 | 0.0068 | 31.4943 |
| No log | 19.39 | 320 | 0.0068 | 31.5402 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1