<!-- 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. -->
distilbert-base-uncased-finetuned-himani-m
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3556
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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.8945 | 1.0 | 8 | 5.4556 |
| 4.3449 | 2.0 | 16 | 2.6799 |
| 4.4967 | 3.0 | 24 | 3.1203 |
| 4.0367 | 4.0 | 32 | 3.7410 |
| 3.7329 | 5.0 | 40 | 3.9018 |
| 4.3099 | 6.0 | 48 | 2.2667 |
| 3.767 | 7.0 | 56 | 3.9794 |
| 3.5045 | 8.0 | 64 | 2.1890 |
| 3.576 | 9.0 | 72 | 5.1615 |
| 3.2903 | 10.0 | 80 | 2.8625 |
| 3.3835 | 11.0 | 88 | 5.7664 |
| 3.219 | 12.0 | 96 | 2.5192 |
| 3.2197 | 13.0 | 104 | 2.5271 |
| 3.1208 | 14.0 | 112 | 2.7014 |
| 3.3357 | 15.0 | 120 | 3.8341 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.2
- Tokenizers 0.13.3
