mobilebert_500exs_10timesteps
This model is a fine-tuned version of google/mobilebert-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7109
- Accuracy: 0.55
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: 2e-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: 16
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 16 | 3126378.25 | 0.45 |
| No log | 2.0 | 32 | 2298910.5 | 0.45 |
| No log | 3.0 | 48 | 1604316.0 | 0.45 |
| No log | 4.0 | 64 | 1062719.5 | 0.45 |
| No log | 5.0 | 80 | 620928.0 | 0.45 |
| No log | 6.0 | 96 | 213084.875 | 0.45 |
| No log | 7.0 | 112 | 11615.9521 | 0.45 |
| No log | 8.0 | 128 | 3076.3987 | 0.45 |
| No log | 9.0 | 144 | 2151.5054 | 0.45 |
| No log | 10.0 | 160 | 1142.7941 | 0.45 |
| No log | 11.0 | 176 | 6.6242 | 0.45 |
| No log | 12.0 | 192 | 1.4116 | 0.45 |
| No log | 13.0 | 208 | 0.8847 | 0.45 |
| No log | 14.0 | 224 | 0.6917 | 0.54 |
| No log | 15.0 | 240 | 0.7124 | 0.55 |
| No log | 16.0 | 256 | 0.7109 | 0.55 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu118
- Datasets 2.17.1
- Tokenizers 0.15.2