tiny-mlm-glue-qnli-from-scratch-custom-tokenizer-target-glue-mrpc
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: 1.1013
- Accuracy: 0.6593
- F1: 0.7459
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 |
---|---|---|---|---|---|
0.6285 | 4.35 | 500 | 0.6024 | 0.6912 | 0.8006 |
0.517 | 8.7 | 1000 | 0.6725 | 0.6642 | 0.7505 |
0.2829 | 13.04 | 1500 | 0.9562 | 0.6446 | 0.7206 |
0.1728 | 17.39 | 2000 | 1.1013 | 0.6593 | 0.7459 |
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.