<!-- 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_medium
This model is a fine-tuned version of muhtasham/bert-medium-mlm-finetuned-emotion on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.2805
- Accuracy: 0.9542
- F1: 0.9765
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: 128
- eval_batch_size: 128
- 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 |
---|---|---|---|---|---|
0.2318 | 2.55 | 500 | 0.1428 | 0.9512 | 0.9750 |
0.0777 | 5.1 | 1000 | 0.1976 | 0.9513 | 0.9750 |
0.0362 | 7.65 | 1500 | 0.2704 | 0.9388 | 0.9684 |
0.0234 | 10.2 | 2000 | 0.2245 | 0.9578 | 0.9784 |
0.0181 | 12.76 | 2500 | 0.3703 | 0.9310 | 0.9643 |
0.0158 | 15.31 | 3000 | 0.6137 | 0.9001 | 0.9474 |
0.013 | 17.86 | 3500 | 0.2805 | 0.9542 | 0.9765 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2