<!-- 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. -->
tiny-mlm-rotten_tomatoes-from-scratch-custom-tokenizer-target-rotten_tomatoes
This model is a fine-tuned version of muhtasham/tiny-mlm-rotten_tomatoes-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9536
- Accuracy: 0.7392
- F1: 0.7370
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
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6936 | 1.87 | 500 | 0.6935 | 0.5 | 0.3333 |
| 0.6929 | 3.75 | 1000 | 0.6900 | 0.5178 | 0.4075 |
| 0.6127 | 5.62 | 1500 | 0.5567 | 0.7242 | 0.7240 |
| 0.3648 | 7.49 | 2000 | 0.5705 | 0.7580 | 0.7580 |
| 0.2262 | 9.36 | 2500 | 0.6669 | 0.7523 | 0.7515 |
| 0.1541 | 11.24 | 3000 | 0.7941 | 0.7533 | 0.7532 |
| 0.118 | 13.11 | 3500 | 0.9536 | 0.7392 | 0.7370 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
