metadata
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_distilberta_lm
results: []
my_awesome_distilberta_lm
This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.4099
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- 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 | 282 | 5.3874 |
| 5.4769 | 2.0 | 564 | 5.2643 |
| 5.4769 | 3.0 | 846 | 4.9845 |
| 5.075 | 4.0 | 1128 | 4.9163 |
| 5.075 | 5.0 | 1410 | 4.8219 |
| 4.799 | 6.0 | 1692 | 4.6897 |
| 4.799 | 7.0 | 1974 | 4.5800 |
| 4.5388 | 8.0 | 2256 | 4.5920 |
| 4.3687 | 9.0 | 2538 | 4.5769 |
| 4.3687 | 10.0 | 2820 | 4.4824 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1
- Datasets 2.14.6
- Tokenizers 0.13.3