<!-- 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. -->
finetuned-mlm_base
This model is a fine-tuned version of muhtasham/bert-base-mlm-finetuned-emotion on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.4151
- Accuracy: 0.9222
- F1: 0.9595
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: 50
- eval_batch_size: 50
- 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 | Accuracy | F1 |
---|---|---|---|---|---|
0.2541 | 1.0 | 500 | 0.1943 | 0.9303 | 0.9639 |
0.1381 | 2.0 | 1000 | 0.1107 | 0.9602 | 0.9797 |
0.0674 | 3.0 | 1500 | 0.1674 | 0.9352 | 0.9665 |
0.0442 | 4.0 | 2000 | 0.2692 | 0.9305 | 0.9640 |
0.0334 | 5.0 | 2500 | 0.4151 | 0.9222 | 0.9595 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2