metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: MTL-bert-base-uncased
results: []
MTL-bert-base-uncased
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2486
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-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|
| No log | 1.0 | 94 | 2.6014 |
| No log | 2.0 | 188 | 2.3898 |
| No log | 3.0 | 282 | 2.3706 |
| No log | 4.0 | 376 | 2.2708 |
| No log | 5.0 | 470 | 2.2666 |
| 2.5403 | 6.0 | 564 | 2.2639 |
| 2.5403 | 7.0 | 658 | 2.3061 |
| 2.5403 | 8.0 | 752 | 2.2659 |
| 2.5403 | 9.0 | 846 | 2.1882 |
| 2.5403 | 10.0 | 940 | 2.2198 |
| 2.2739 | 11.0 | 1034 | 2.1124 |
| 2.2739 | 12.0 | 1128 | 2.1887 |
| 2.2739 | 13.0 | 1222 | 2.1740 |
| 2.2739 | 14.0 | 1316 | 2.1517 |
| 2.2739 | 15.0 | 1410 | 2.1510 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.11.0