<!-- 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-snli-from-scratch-target-rotten_tomatoes
This model is a fine-tuned version of muhtasham/tiny-mlm-snli-from-scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7400
- Accuracy: 0.7448
- F1: 0.7441
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 |
---|---|---|---|---|---|
0.693 | 1.87 | 500 | 0.6913 | 0.5038 | 0.3480 |
0.6626 | 3.75 | 1000 | 0.6427 | 0.6379 | 0.6351 |
0.5259 | 5.62 | 1500 | 0.5793 | 0.7223 | 0.7222 |
0.3566 | 7.49 | 2000 | 0.5842 | 0.7467 | 0.7467 |
0.2709 | 9.36 | 2500 | 0.6819 | 0.7355 | 0.7343 |
0.2148 | 11.24 | 3000 | 0.7748 | 0.7420 | 0.7410 |
0.1936 | 13.11 | 3500 | 0.7400 | 0.7448 | 0.7441 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2