<!-- 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. -->
assignment2_meher_test3
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5370
- Precision: 0.1642
- Recall: 0.4158
- F1: 0.2354
- Accuracy: 0.8892
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: 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 149 | 0.3231 | 0.1406 | 0.2405 | 0.1774 | 0.9098 |
No log | 2.0 | 298 | 0.2897 | 0.1711 | 0.3505 | 0.2300 | 0.9103 |
No log | 3.0 | 447 | 0.3376 | 0.1715 | 0.3849 | 0.2373 | 0.9029 |
0.3658 | 4.0 | 596 | 0.3870 | 0.1669 | 0.4261 | 0.2398 | 0.8887 |
0.3658 | 5.0 | 745 | 0.4245 | 0.1542 | 0.3952 | 0.2218 | 0.8884 |
0.3658 | 6.0 | 894 | 0.4291 | 0.1815 | 0.3986 | 0.2495 | 0.9024 |
0.0735 | 7.0 | 1043 | 0.5257 | 0.1530 | 0.4296 | 0.2256 | 0.8820 |
0.0735 | 8.0 | 1192 | 0.5211 | 0.1680 | 0.4261 | 0.2410 | 0.8900 |
0.0735 | 9.0 | 1341 | 0.5810 | 0.1560 | 0.4502 | 0.2317 | 0.8784 |
0.0735 | 10.0 | 1490 | 0.5370 | 0.1642 | 0.4158 | 0.2354 | 0.8892 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1