<!-- 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-finetuned-lr1e-06-epochs25
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: 3.7636
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-06
- 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: 25
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 10 | 5.6433 |
| No log | 2.0 | 20 | 5.2269 |
| No log | 3.0 | 30 | 4.9921 |
| No log | 4.0 | 40 | 4.8316 |
| No log | 5.0 | 50 | 4.6954 |
| No log | 6.0 | 60 | 4.5766 |
| No log | 7.0 | 70 | 4.4717 |
| No log | 8.0 | 80 | 4.3697 |
| No log | 9.0 | 90 | 4.2855 |
| No log | 10.0 | 100 | 4.2092 |
| No log | 11.0 | 110 | 4.1450 |
| No log | 12.0 | 120 | 4.0885 |
| No log | 13.0 | 130 | 4.0374 |
| No log | 14.0 | 140 | 3.9893 |
| No log | 15.0 | 150 | 3.9444 |
| No log | 16.0 | 160 | 3.9073 |
| No log | 17.0 | 170 | 3.8759 |
| No log | 18.0 | 180 | 3.8485 |
| No log | 19.0 | 190 | 3.8255 |
| No log | 20.0 | 200 | 3.8075 |
| No log | 21.0 | 210 | 3.7924 |
| No log | 22.0 | 220 | 3.7800 |
| No log | 23.0 | 230 | 3.7706 |
| No log | 24.0 | 240 | 3.7654 |
| No log | 25.0 | 250 | 3.7636 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
