tiny-mlm-snli-plain_text
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.1233
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: 3e-05
- 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: constant
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.665 | 0.4 | 500 | 3.2495 |
| 3.4103 | 0.8 | 1000 | nan |
| 3.2635 | 1.2 | 1500 | 3.1518 |
| 3.1738 | 1.6 | 2000 | 3.1555 |
| 3.0556 | 2.0 | 2500 | 3.0593 |
| 2.9933 | 2.4 | 3000 | 3.0970 |
| 2.9019 | 2.8 | 3500 | 3.0773 |
| 2.876 | 3.2 | 4000 | 3.1233 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1
- Datasets 2.8.0
- Tokenizers 0.13.2