tiny-mlm-glue-qnli-from-scratch-custom-tokenizer-target-glue-qqp
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-qnli-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5253
- Accuracy: 0.7422
- F1: 0.6175
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 |
---|---|---|---|---|---|
0.6417 | 0.04 | 500 | 0.6186 | 0.6422 | 0.3915 |
0.6074 | 0.09 | 1000 | 0.5913 | 0.6758 | 0.5148 |
0.5863 | 0.13 | 1500 | 0.5734 | 0.6951 | 0.5694 |
0.5727 | 0.18 | 2000 | 0.5628 | 0.7098 | 0.5369 |
0.5576 | 0.22 | 2500 | 0.5505 | 0.7215 | 0.5756 |
0.5502 | 0.26 | 3000 | 0.5428 | 0.7282 | 0.5839 |
0.545 | 0.31 | 3500 | 0.5368 | 0.7340 | 0.5996 |
0.5368 | 0.35 | 4000 | 0.5328 | 0.7342 | 0.6250 |
0.5385 | 0.4 | 4500 | 0.5300 | 0.7359 | 0.6323 |
0.5316 | 0.44 | 5000 | 0.5253 | 0.7422 | 0.6175 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.