<!-- 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-vanilla-target-glue-mrpc
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0066
- Accuracy: 0.7206
- F1: 0.8021
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
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.593 | 4.35 | 500 | 0.5612 | 0.7059 | 0.8058 |
| 0.4814 | 8.7 | 1000 | 0.5717 | 0.7377 | 0.8266 |
| 0.3364 | 13.04 | 1500 | 0.6346 | 0.7353 | 0.8188 |
| 0.2104 | 17.39 | 2000 | 0.7927 | 0.7230 | 0.8094 |
| 0.1308 | 21.74 | 2500 | 1.0066 | 0.7206 | 0.8021 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
