<!-- 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. -->
small-mlm-snli-from-scratch-custom-tokenizer-target-rotten_tomatoes
This model is a fine-tuned version of muhtasham/small-mlm-snli-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1833
- Accuracy: 0.7101
- F1: 0.7090
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 |
|---|---|---|---|---|---|
| 0.6628 | 1.87 | 500 | 0.6389 | 0.6388 | 0.6187 |
| 0.4993 | 3.75 | 1000 | 0.6044 | 0.6970 | 0.6938 |
| 0.4205 | 5.62 | 1500 | 0.6342 | 0.7261 | 0.7251 |
| 0.3604 | 7.49 | 2000 | 0.7069 | 0.7270 | 0.7254 |
| 0.3034 | 9.36 | 2500 | 0.8202 | 0.6989 | 0.6974 |
| 0.2358 | 11.24 | 3000 | 0.8650 | 0.7111 | 0.7103 |
| 0.1804 | 13.11 | 3500 | 1.1833 | 0.7101 | 0.7090 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
