<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert-base-uncased-finetuned-char-hangman
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: 1.2830
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: 256
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 11
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.985 | 0.59 | 500 | 1.7507 |
1.7115 | 1.18 | 1000 | 1.6289 |
1.6265 | 1.78 | 1500 | 1.5502 |
1.5716 | 2.37 | 2000 | 1.5237 |
1.5265 | 2.96 | 2500 | 1.4812 |
1.498 | 3.55 | 3000 | 1.4562 |
1.4648 | 4.15 | 3500 | 1.4246 |
1.4463 | 4.74 | 4000 | 1.3875 |
1.4215 | 5.33 | 4500 | 1.3697 |
1.4076 | 5.92 | 5000 | 1.3530 |
1.3901 | 6.52 | 5500 | 1.3404 |
1.3767 | 7.11 | 6000 | 1.3270 |
1.3631 | 7.7 | 6500 | 1.3126 |
1.3573 | 8.29 | 7000 | 1.3212 |
1.3488 | 8.89 | 7500 | 1.3162 |
1.3397 | 9.48 | 8000 | 1.3135 |
1.3318 | 10.07 | 8500 | 1.2941 |
1.336 | 10.66 | 9000 | 1.2842 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3