metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-osdg
results: []
distilbert-base-uncased-finetuned-osdg
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8231
- Acc: 0.7696
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: 6e-06
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Acc |
|---|---|---|---|---|
| 1.072 | 1.0 | 904 | 1.0274 | 0.7242 |
| 0.8997 | 2.0 | 1808 | 0.9168 | 0.7481 |
| 0.8137 | 3.0 | 2712 | 0.8687 | 0.7547 |
| 0.7966 | 4.0 | 3616 | 0.8400 | 0.7618 |
| 0.7209 | 5.0 | 4520 | 0.8280 | 0.7677 |
| 0.6666 | 6.0 | 5424 | 0.8300 | 0.7671 |
| 0.6655 | 7.0 | 6328 | 0.8231 | 0.7696 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.2.0
- Tokenizers 0.12.1