mobilebert_100exs_10timesteps_run0
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: 886719.8125
- Accuracy: 0.3
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: 16
- eval_batch_size: 16
- 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 | 7 | 3096381.5 | 0.3 |
| No log | 2.0 | 14 | 2705231.0 | 0.3 |
| No log | 3.0 | 21 | 2380465.5 | 0.3 |
| No log | 4.0 | 28 | 2136194.5 | 0.3 |
| No log | 5.0 | 35 | 1909053.75 | 0.3 |
| No log | 6.0 | 42 | 1667145.0 | 0.3 |
| No log | 7.0 | 49 | 1493787.75 | 0.3 |
| No log | 8.0 | 56 | 1344492.5 | 0.3 |
| No log | 9.0 | 63 | 1218353.25 | 0.3 |
| No log | 10.0 | 70 | 1119155.375 | 0.3 |
| No log | 11.0 | 77 | 1045936.5 | 0.3 |
| No log | 12.0 | 84 | 987271.5 | 0.3 |
| No log | 13.0 | 91 | 942506.0 | 0.3 |
| No log | 14.0 | 98 | 911861.0 | 0.3 |
| No log | 15.0 | 105 | 893725.875 | 0.3 |
| No log | 16.0 | 112 | 886719.8125 | 0.3 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu118
- Datasets 2.17.1
- Tokenizers 0.15.2