metadata
tags:
- generated_from_trainer
model-index:
- name: iab_classification-finetuned-mnli-finetuned-mnli
results: []
iab_classification-finetuned-mnli-finetuned-mnli
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.5436
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: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 15 | 5.0579 |
| No log | 2.0 | 30 | 2.5431 |
| No log | 3.0 | 45 | 3.2248 |
| No log | 4.0 | 60 | 3.9195 |
| No log | 5.0 | 75 | 4.2920 |
| No log | 6.0 | 90 | 4.4568 |
| No log | 7.0 | 105 | 4.5005 |
| No log | 8.0 | 120 | 4.8739 |
| No log | 9.0 | 135 | 4.4574 |
| No log | 10.0 | 150 | 4.5635 |
| No log | 11.0 | 165 | 4.3998 |
| No log | 12.0 | 180 | 4.3195 |
| No log | 13.0 | 195 | 3.8431 |
| No log | 14.0 | 210 | 4.2134 |
| No log | 15.0 | 225 | 4.2773 |
| No log | 16.0 | 240 | 4.0859 |
| No log | 17.0 | 255 | 3.7728 |
| No log | 18.0 | 270 | 3.6935 |
| No log | 19.0 | 285 | 4.0160 |
| No log | 20.0 | 300 | 4.3259 |
| No log | 21.0 | 315 | 4.3933 |
| No log | 22.0 | 330 | 4.4054 |
| No log | 23.0 | 345 | 4.3431 |
| No log | 24.0 | 360 | 4.3030 |
| No log | 25.0 | 375 | 4.3601 |
| No log | 26.0 | 390 | 4.3288 |
| No log | 27.0 | 405 | 4.2502 |
| No log | 28.0 | 420 | 4.1835 |
| No log | 29.0 | 435 | 4.2719 |
| No log | 30.0 | 450 | 4.2541 |
| No log | 31.0 | 465 | 4.2910 |
| No log | 32.0 | 480 | 4.3543 |
| No log | 33.0 | 495 | 4.4530 |
| 0.2652 | 34.0 | 510 | 4.3851 |
| 0.2652 | 35.0 | 525 | 4.3539 |
| 0.2652 | 36.0 | 540 | 4.4083 |
| 0.2652 | 37.0 | 555 | 4.3998 |
| 0.2652 | 38.0 | 570 | 4.4422 |
| 0.2652 | 39.0 | 585 | 4.4466 |
| 0.2652 | 40.0 | 600 | 4.4148 |
| 0.2652 | 41.0 | 615 | 4.4509 |
| 0.2652 | 42.0 | 630 | 4.4941 |
| 0.2652 | 43.0 | 645 | 4.5451 |
| 0.2652 | 44.0 | 660 | 4.5409 |
| 0.2652 | 45.0 | 675 | 4.5605 |
| 0.2652 | 46.0 | 690 | 4.5356 |
| 0.2652 | 47.0 | 705 | 4.5376 |
| 0.2652 | 48.0 | 720 | 4.5301 |
| 0.2652 | 49.0 | 735 | 4.5396 |
| 0.2652 | 50.0 | 750 | 4.5436 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.10.0
- Datasets 2.5.1
- Tokenizers 0.12.1