<!-- 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-glue-sst2-from-scratch-custom-tokenizer-target-glue-qnli
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-sst2-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6498
- Accuracy: 0.6167
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 |
---|---|---|---|---|
0.69 | 0.15 | 500 | 0.6762 | 0.5825 |
0.6738 | 0.31 | 1000 | 0.6644 | 0.5940 |
0.6694 | 0.46 | 1500 | 0.6595 | 0.6026 |
0.6621 | 0.61 | 2000 | 0.6582 | 0.6041 |
0.6602 | 0.76 | 2500 | 0.6543 | 0.6070 |
0.6599 | 0.92 | 3000 | 0.6531 | 0.6110 |
0.6508 | 1.07 | 3500 | 0.6528 | 0.6165 |
0.6511 | 1.22 | 4000 | 0.6508 | 0.6167 |
0.6472 | 1.37 | 4500 | 0.6549 | 0.6096 |
0.6494 | 1.53 | 5000 | 0.6498 | 0.6167 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2