micro_base_help_tapt_pretrain_model
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5916
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: 0.0001
- train_batch_size: 21
- eval_batch_size: 21
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 42
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9109 | 0.99 | 40 | 1.6849 |
| 1.7421 | 2.0 | 81 | 1.6620 |
| 1.7411 | 2.99 | 121 | 1.6333 |
| 1.6441 | 4.0 | 162 | 1.6306 |
| 1.6337 | 4.99 | 202 | 1.6137 |
| 1.5774 | 6.0 | 243 | 1.6343 |
| 1.5997 | 6.99 | 283 | 1.5931 |
| 1.5196 | 8.0 | 324 | 1.6018 |
| 1.5416 | 8.99 | 364 | 1.5994 |
| 1.4819 | 10.0 | 405 | 1.5886 |
| 1.5079 | 10.99 | 445 | 1.5938 |
| 1.455 | 12.0 | 486 | 1.5699 |
| 1.4718 | 12.99 | 526 | 1.5947 |
| 1.4157 | 14.0 | 567 | 1.5920 |
| 1.4369 | 14.99 | 607 | 1.5879 |
| 1.3733 | 16.0 | 648 | 1.5745 |
| 1.4017 | 16.99 | 688 | 1.6000 |
| 1.3601 | 18.0 | 729 | 1.5830 |
| 1.3602 | 18.99 | 769 | 1.5846 |
| 1.3152 | 20.0 | 810 | 1.5940 |
| 1.3437 | 20.99 | 850 | 1.5942 |
| 1.2904 | 22.0 | 891 | 1.5787 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2