<!-- 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-char-v1
This model is a fine-tuned version of bhagasra-saurav/distilbert-base-uncased-finetuned-char on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4642
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: 256
- eval_batch_size: 256
- 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 |
|---|---|---|---|
| 1.6627 | 0.78 | 500 | 1.5628 |
| 1.6431 | 1.57 | 1000 | 1.5844 |
| 1.628 | 2.35 | 1500 | 1.5463 |
| 1.6066 | 3.13 | 2000 | 1.5415 |
| 1.5939 | 3.92 | 2500 | 1.5221 |
| 1.5788 | 4.7 | 3000 | 1.5116 |
| 1.572 | 5.49 | 3500 | 1.5208 |
| 1.5581 | 6.27 | 4000 | 1.4967 |
| 1.5486 | 7.05 | 4500 | 1.4868 |
| 1.541 | 7.84 | 5000 | 1.4949 |
| 1.5282 | 8.62 | 5500 | 1.4629 |
| 1.5276 | 9.4 | 6000 | 1.4810 |
| 1.5208 | 10.19 | 6500 | 1.4561 |
| 1.5155 | 10.97 | 7000 | 1.4783 |
| 1.5134 | 11.76 | 7500 | 1.4581 |
| 1.5094 | 12.54 | 8000 | 1.4449 |
| 1.5021 | 13.32 | 8500 | 1.4510 |
| 1.501 | 14.11 | 9000 | 1.4625 |
| 1.5004 | 14.89 | 9500 | 1.4255 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
