metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad_v2_yash
model-index:
- name: distilbert-base-cased-distilled-squad-finetuned-squad
results: []
distilbert-base-cased-distilled-squad-finetuned-squad
This model is a fine-tuned version of distilbert-base-cased-distilled-squad on the squad_v2_yash dataset. It achieves the following results on the evaluation set:
- Loss: 0.0088
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 198 | 0.5409 |
| No log | 2.0 | 396 | 0.3048 |
| 0.9541 | 3.0 | 594 | 0.1764 |
| 0.9541 | 4.0 | 792 | 0.1117 |
| 0.9541 | 5.0 | 990 | 0.0634 |
| 0.3052 | 6.0 | 1188 | 0.0345 |
| 0.3052 | 7.0 | 1386 | 0.0229 |
| 0.1129 | 8.0 | 1584 | 0.0152 |
| 0.1129 | 9.0 | 1782 | 0.0101 |
| 0.1129 | 10.0 | 1980 | 0.0088 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1