metadata
language:
- en
license: mit
tags:
- generated_from_trainer
- image-to-text
- image-captioning
base_model: microsoft/git-base
pipeline_tag: image-to-text
model-index:
- name: git-base-instagram-cap
results: []
git-base-instagram-cap
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: 0.2581
- Wer Score: 3.1462
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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 |
|---|---|---|---|---|
| 7.3639 | 3.45 | 50 | 4.5936 | 0.9495 |
| 2.389 | 6.9 | 100 | 0.6192 | 0.9387 |
| 0.2242 | 10.34 | 150 | 0.2274 | 0.9036 |
| 0.0883 | 13.79 | 200 | 0.2271 | 0.9084 |
| 0.0643 | 17.24 | 250 | 0.2319 | 0.9387 |
| 0.0493 | 20.69 | 300 | 0.2388 | 0.9501 |
| 0.0409 | 24.14 | 350 | 0.2435 | 0.9522 |
| 0.0344 | 27.59 | 400 | 0.2458 | 0.9616 |
| 0.0311 | 31.03 | 450 | 0.2492 | 1.0027 |
| 0.028 | 34.48 | 500 | 0.2519 | 1.3565 |
| 0.0255 | 37.93 | 550 | 0.2540 | 2.0640 |
| 0.0227 | 41.38 | 600 | 0.2554 | 2.1813 |
| 0.0189 | 44.83 | 650 | 0.2575 | 2.8416 |
| 0.0154 | 48.28 | 700 | 0.2581 | 3.1462 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0