cvt-13-finetuned-IDRiD
This model is a fine-tuned version of microsoft/cvt-13 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2520
- Accuracy: 0.4524
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: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 3 | 1.6800 | 0.1190 |
| No log | 2.0 | 6 | 1.6686 | 0.2143 |
| No log | 3.0 | 9 | 1.5528 | 0.3333 |
| 1.6061 | 4.0 | 12 | 1.4874 | 0.3333 |
| 1.6061 | 5.0 | 15 | 1.4834 | 0.3571 |
| 1.6061 | 6.0 | 18 | 1.4485 | 0.3810 |
| 1.4325 | 7.0 | 21 | 1.4295 | 0.4048 |
| 1.4325 | 8.0 | 24 | 1.4172 | 0.4286 |
| 1.4325 | 9.0 | 27 | 1.3890 | 0.4048 |
| 1.3474 | 10.0 | 30 | 1.3739 | 0.4286 |
| 1.3474 | 11.0 | 33 | 1.3571 | 0.4048 |
| 1.3474 | 12.0 | 36 | 1.3244 | 0.4048 |
| 1.3474 | 13.0 | 39 | 1.3090 | 0.4048 |
| 1.3039 | 14.0 | 42 | 1.3438 | 0.4286 |
| 1.3039 | 15.0 | 45 | 1.3617 | 0.4286 |
| 1.3039 | 16.0 | 48 | 1.3513 | 0.4286 |
| 1.2892 | 17.0 | 51 | 1.3187 | 0.4524 |
| 1.2892 | 18.0 | 54 | 1.3054 | 0.3810 |
| 1.2892 | 19.0 | 57 | 1.2862 | 0.4286 |
| 1.2489 | 20.0 | 60 | 1.2670 | 0.4524 |
| 1.2489 | 21.0 | 63 | 1.2810 | 0.4762 |
| 1.2489 | 22.0 | 66 | 1.2389 | 0.4524 |
| 1.2489 | 23.0 | 69 | 1.2312 | 0.4762 |
| 1.2378 | 24.0 | 72 | 1.2619 | 0.4524 |
| 1.2378 | 25.0 | 75 | 1.2652 | 0.4524 |
| 1.2378 | 26.0 | 78 | 1.2639 | 0.4524 |
| 1.1968 | 27.0 | 81 | 1.2517 | 0.4524 |
| 1.1968 | 28.0 | 84 | 1.2603 | 0.4286 |
| 1.1968 | 29.0 | 87 | 1.2463 | 0.4524 |
| 1.1977 | 30.0 | 90 | 1.2520 | 0.4524 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.13.3