small-vanilla-target-glue-qnli
This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3458
- Accuracy: 0.8583
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 |
---|---|---|---|---|
0.488 | 0.15 | 500 | 0.3901 | 0.8316 |
0.4449 | 0.31 | 1000 | 0.3826 | 0.8373 |
0.4243 | 0.46 | 1500 | 0.3596 | 0.8448 |
0.4133 | 0.61 | 2000 | 0.3663 | 0.8417 |
0.4102 | 0.76 | 2500 | 0.3459 | 0.8499 |
0.3924 | 0.92 | 3000 | 0.3286 | 0.8585 |
0.3539 | 1.07 | 3500 | 0.3467 | 0.8532 |
0.3202 | 1.22 | 4000 | 0.3478 | 0.8636 |
0.3183 | 1.37 | 4500 | 0.3574 | 0.8514 |
0.3215 | 1.53 | 5000 | 0.3458 | 0.8583 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 2
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.