mobilebert_run1
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: 7541494.5
- Accuracy: 0.0
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 | 5 | 11089919.0 | 0.0 |
| No log | 2.0 | 10 | 10502712.0 | 0.0 |
| No log | 3.0 | 15 | 10016729.0 | 0.0 |
| No log | 4.0 | 20 | 9591635.0 | 0.0 |
| No log | 5.0 | 25 | 9214009.0 | 0.0 |
| No log | 6.0 | 30 | 8899205.0 | 0.0 |
| No log | 7.0 | 35 | 8633617.0 | 0.0 |
| No log | 8.0 | 40 | 8408112.0 | 0.0 |
| No log | 9.0 | 45 | 8206867.0 | 0.0 |
| No log | 10.0 | 50 | 8033762.5 | 0.0 |
| No log | 11.0 | 55 | 7887077.0 | 0.0 |
| No log | 12.0 | 60 | 7766791.0 | 0.0 |
| No log | 13.0 | 65 | 7670611.0 | 0.0 |
| No log | 14.0 | 70 | 7600864.0 | 0.0 |
| No log | 15.0 | 75 | 7557492.0 | 0.0 |
| No log | 16.0 | 80 | 7541494.5 | 0.0 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu118
- Datasets 2.17.1
- Tokenizers 0.15.2