<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
roberta-mc-5
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4494
- Accuracy: 0.89
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: 0.001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 60
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.5837 | 1.0 | 25 | 1.5556 | 0.53 |
| 1.5523 | 2.0 | 50 | 1.5001 | 0.51 |
| 1.555 | 3.0 | 75 | 1.4666 | 0.48 |
| 1.4895 | 4.0 | 100 | 1.4224 | 0.49 |
| 1.4951 | 5.0 | 125 | 1.3924 | 0.495 |
| 1.4549 | 6.0 | 150 | 1.3716 | 0.53 |
| 1.4462 | 7.0 | 175 | 1.3372 | 0.51 |
| 1.4262 | 8.0 | 200 | 1.3005 | 0.515 |
| 1.3729 | 9.0 | 225 | 1.2497 | 0.525 |
| 1.4031 | 10.0 | 250 | 1.2854 | 0.535 |
| 1.3962 | 11.0 | 275 | 1.2891 | 0.56 |
| 1.3519 | 12.0 | 300 | 1.2060 | 0.53 |
| 1.362 | 13.0 | 325 | 1.3458 | 0.555 |
| 1.3693 | 14.0 | 350 | 1.1796 | 0.56 |
| 1.346 | 15.0 | 375 | 1.1360 | 0.585 |
| 1.2285 | 16.0 | 400 | 1.0907 | 0.57 |
| 1.2481 | 17.0 | 425 | 1.1393 | 0.56 |
| 1.2568 | 18.0 | 450 | 1.0404 | 0.6 |
| 1.2249 | 19.0 | 475 | 1.0012 | 0.595 |
| 1.1611 | 20.0 | 500 | 1.0123 | 0.615 |
| 1.1416 | 21.0 | 525 | 0.9631 | 0.64 |
| 1.2197 | 22.0 | 550 | 1.0537 | 0.625 |
| 1.2029 | 23.0 | 575 | 0.9518 | 0.66 |
| 1.1971 | 24.0 | 600 | 0.9295 | 0.67 |
| 1.1513 | 25.0 | 625 | 0.9045 | 0.675 |
| 1.0185 | 26.0 | 650 | 0.8620 | 0.71 |
| 1.1352 | 27.0 | 675 | 1.0548 | 0.69 |
| 1.1593 | 28.0 | 700 | 1.0043 | 0.68 |
| 1.1418 | 29.0 | 725 | 0.8569 | 0.7 |
| 1.0534 | 30.0 | 750 | 0.8284 | 0.715 |
| 1.08 | 31.0 | 775 | 0.7953 | 0.73 |
| 1.0148 | 32.0 | 800 | 0.7775 | 0.74 |
| 1.0526 | 33.0 | 825 | 0.8120 | 0.755 |
| 1.03 | 34.0 | 850 | 0.7630 | 0.76 |
| 1.0287 | 35.0 | 875 | 0.7651 | 0.745 |
| 1.0287 | 36.0 | 900 | 0.7174 | 0.765 |
| 0.9901 | 37.0 | 925 | 0.7268 | 0.75 |
| 0.9257 | 38.0 | 950 | 0.7114 | 0.765 |
| 0.9372 | 39.0 | 975 | 0.6691 | 0.805 |
| 0.9582 | 40.0 | 1000 | 0.6650 | 0.795 |
| 0.8728 | 41.0 | 1025 | 0.6588 | 0.78 |
| 0.8925 | 42.0 | 1050 | 0.6426 | 0.81 |
| 0.9357 | 43.0 | 1075 | 0.6302 | 0.815 |
| 0.9257 | 44.0 | 1100 | 0.7645 | 0.795 |
| 0.8763 | 45.0 | 1125 | 0.6034 | 0.815 |
| 0.838 | 46.0 | 1150 | 0.5711 | 0.815 |
| 0.8652 | 47.0 | 1175 | 0.5583 | 0.83 |
| 0.8106 | 48.0 | 1200 | 0.5560 | 0.835 |
| 0.8567 | 49.0 | 1225 | 0.5361 | 0.825 |
| 0.8185 | 50.0 | 1250 | 0.5926 | 0.825 |
| 0.8327 | 51.0 | 1275 | 0.5550 | 0.85 |
| 0.7822 | 52.0 | 1300 | 0.5193 | 0.85 |
| 0.7971 | 53.0 | 1325 | 0.5213 | 0.85 |
| 0.8051 | 54.0 | 1350 | 0.5175 | 0.845 |
| 0.7815 | 55.0 | 1375 | 0.4801 | 0.885 |
| 0.7391 | 56.0 | 1400 | 0.5759 | 0.87 |
| 0.8168 | 57.0 | 1425 | 0.4646 | 0.88 |
| 0.6991 | 58.0 | 1450 | 0.4713 | 0.885 |
| 0.7545 | 59.0 | 1475 | 0.4882 | 0.885 |
| 0.7222 | 60.0 | 1500 | 0.4494 | 0.89 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
