<!-- 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. -->
mini-mlm-tweet
This model is a fine-tuned version of google/bert_uncased_L-4_H-256_A-4 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.1171
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 |
---|---|---|---|
3.9227 | 11.11 | 500 | 3.8377 |
3.4825 | 22.22 | 1000 | 3.7411 |
3.2903 | 33.33 | 1500 | 3.8864 |
3.1026 | 44.44 | 2000 | 3.6987 |
2.9438 | 55.56 | 2500 | 3.9807 |
2.8075 | 66.67 | 3000 | 3.8835 |
2.6951 | 77.78 | 3500 | 4.1171 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2