metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilroberta-base
results: []
distilroberta-base
This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2660
- Accuracy: 0.7504
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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2373 | 1.0 | 2355 | 1.1927 | 0.6802 |
| 0.9192 | 2.0 | 4710 | 1.0538 | 0.7118 |
| 0.6782 | 3.0 | 7065 | 0.9921 | 0.7288 |
| 0.5687 | 4.0 | 9420 | 1.0542 | 0.7421 |
| 0.4598 | 5.0 | 11775 | 1.2043 | 0.7384 |
| 0.3557 | 6.0 | 14130 | 1.2833 | 0.7459 |
| 0.3126 | 7.0 | 16485 | 1.4286 | 0.7459 |
| 0.2541 | 8.0 | 18840 | 1.5076 | 0.7419 |
| 0.1948 | 9.0 | 21195 | 1.6771 | 0.7371 |
| 0.1576 | 10.0 | 23550 | 1.8419 | 0.7429 |
| 0.1071 | 11.0 | 25905 | 1.9164 | 0.7467 |
| 0.0977 | 12.0 | 28260 | 1.9773 | 0.7466 |
| 0.0652 | 13.0 | 30615 | 2.0582 | 0.7486 |
| 0.0752 | 14.0 | 32970 | 2.1108 | 0.7482 |
| 0.0594 | 15.0 | 35325 | 2.1406 | 0.7492 |
| 0.049 | 16.0 | 37680 | 2.1958 | 0.7485 |
| 0.0267 | 17.0 | 40035 | 2.1858 | 0.7499 |
| 0.0339 | 18.0 | 42390 | 2.2162 | 0.7503 |
| 0.0137 | 19.0 | 44745 | 2.2699 | 0.7503 |
| 0.0083 | 20.0 | 47100 | 2.2660 | 0.7504 |
Framework versions
- Transformers 4.28.1
- Pytorch 1.13.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3