metadata
tags:
- generated_from_trainer
model-index:
- name: img_cap_aibxesck
results: []
img_cap_aibxesck
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.5634
- Bleu score: 0.0030
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: 0.01
- train_batch_size: 18
- eval_batch_size: 18
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu score |
|---|---|---|---|---|
| No log | 1.0 | 157 | 16.3024 | 0.0022 |
| No log | 2.0 | 314 | 5.9833 | 0.0032 |
| No log | 3.0 | 471 | 5.9377 | 0.0030 |
| 8.9191 | 4.0 | 628 | 5.5674 | 0.0032 |
| 8.9191 | 5.0 | 785 | 5.5634 | 0.0030 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1