metadata
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert_distilbert-base-uncased-15-epoch
results: []
distilbert_distilbert-base-uncased-15-epoch
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.3248
- Accuracy: 0.4133
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3078 | 1.0 | 2857 | 1.3426 | 0.3356 |
| 1.1327 | 2.0 | 5714 | 1.4079 | 0.3560 |
| 0.911 | 3.0 | 8571 | 1.5413 | 0.3789 |
| 0.7139 | 4.0 | 11428 | 1.7088 | 0.3942 |
| 0.548 | 5.0 | 14285 | 1.9117 | 0.3902 |
| 0.4389 | 6.0 | 17142 | 2.1179 | 0.3971 |
| 0.3422 | 7.0 | 19999 | 2.5687 | 0.4002 |
| 0.2707 | 8.0 | 22856 | 2.6006 | 0.4019 |
| 0.2258 | 9.0 | 25713 | 2.8582 | 0.4069 |
| 0.1817 | 10.0 | 28570 | 3.2135 | 0.4031 |
| 0.1506 | 11.0 | 31427 | 3.2640 | 0.4074 |
| 0.1285 | 12.0 | 34284 | 3.6061 | 0.4086 |
| 0.1067 | 13.0 | 37141 | 3.7931 | 0.4141 |
| 0.088 | 14.0 | 39998 | 4.1130 | 0.4129 |
| 0.0772 | 15.0 | 42855 | 4.3248 | 0.4133 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.0