<!-- 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-custom-tokenizer-target-rotten_tomatoes
This model is a fine-tuned version of muhtasham/tiny-mlm-snli-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6855
- Accuracy: 0.7148
- F1: 0.7138
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 |
|---|---|---|---|---|---|
| 0.6938 | 1.87 | 500 | 0.6927 | 0.5019 | 0.3375 |
| 0.6842 | 3.75 | 1000 | 0.6678 | 0.6013 | 0.6013 |
| 0.6171 | 5.62 | 1500 | 0.5950 | 0.6811 | 0.6793 |
| 0.4993 | 7.49 | 2000 | 0.5695 | 0.7045 | 0.7045 |
| 0.444 | 9.36 | 2500 | 0.5844 | 0.7176 | 0.7175 |
| 0.4141 | 11.24 | 3000 | 0.5990 | 0.7261 | 0.7260 |
| 0.3856 | 13.11 | 3500 | 0.6320 | 0.7223 | 0.7208 |
| 0.3564 | 14.98 | 4000 | 0.6657 | 0.7129 | 0.7108 |
| 0.3377 | 16.85 | 4500 | 0.6855 | 0.7148 | 0.7138 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
