COPA_albert_base_finetuned
This model is a fine-tuned version of albert/albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7959
- F1: 0.72
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 63 | 0.5853 | 0.728 |
| No log | 2.0 | 126 | 0.5540 | 0.708 |
| No log | 3.0 | 189 | 0.5356 | 0.74 |
| No log | 4.0 | 252 | 0.5380 | 0.766 |
| No log | 5.0 | 315 | 0.5841 | 0.7580 |
| No log | 6.0 | 378 | 0.6396 | 0.738 |
| No log | 7.0 | 441 | 0.6778 | 0.7420 |
| 0.2823 | 8.0 | 504 | 0.7111 | 0.728 |
| 0.2823 | 9.0 | 567 | 0.7695 | 0.712 |
| 0.2823 | 10.0 | 630 | 0.7959 | 0.72 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1