distilbert_sa_GLUE_Experiment_mnli_96
This model is a fine-tuned version of distilbert-base-uncased on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.9288
- Accuracy: 0.5545
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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0498 | 1.0 | 1534 | 0.9988 | 0.5084 |
| 0.9757 | 2.0 | 3068 | 0.9532 | 0.5303 |
| 0.9458 | 3.0 | 4602 | 0.9435 | 0.5377 |
| 0.9272 | 4.0 | 6136 | 0.9306 | 0.5456 |
| 0.9122 | 5.0 | 7670 | 0.9305 | 0.5474 |
| 0.8992 | 6.0 | 9204 | 0.9294 | 0.5489 |
| 0.8867 | 7.0 | 10738 | 0.9260 | 0.5522 |
| 0.8752 | 8.0 | 12272 | 0.9319 | 0.5559 |
| 0.8645 | 9.0 | 13806 | 0.9336 | 0.5604 |
| 0.8545 | 10.0 | 15340 | 0.9200 | 0.5629 |
| 0.8443 | 11.0 | 16874 | 0.9200 | 0.5664 |
| 0.8338 | 12.0 | 18408 | 0.9298 | 0.5672 |
| 0.8252 | 13.0 | 19942 | 0.9383 | 0.5647 |
| 0.8168 | 14.0 | 21476 | 0.9428 | 0.5691 |
| 0.8084 | 15.0 | 23010 | 0.9325 | 0.5730 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2