<!-- 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-cased-distilled-squad-finetuned-lr1e-05-epochs15
This model is a fine-tuned version of distilbert-base-cased-distilled-squad on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1170
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|
| No log | 1.0 | 8 | 3.7990 |
| No log | 2.0 | 16 | 2.9391 |
| No log | 3.0 | 24 | 2.4317 |
| No log | 4.0 | 32 | 2.0786 |
| No log | 5.0 | 40 | 1.8341 |
| No log | 6.0 | 48 | 1.5765 |
| No log | 7.0 | 56 | 1.4683 |
| No log | 8.0 | 64 | 1.3924 |
| No log | 9.0 | 72 | 1.2687 |
| No log | 10.0 | 80 | 1.2166 |
| No log | 11.0 | 88 | 1.1920 |
| No log | 12.0 | 96 | 1.1699 |
| No log | 13.0 | 104 | 1.1354 |
| No log | 14.0 | 112 | 1.1209 |
| No log | 15.0 | 120 | 1.1170 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
