<!-- 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. -->
bert-base-uncased-finetuned-mnli-512-10
This model is a fine-tuned version of yy642/bert-base-uncased-finetuned-mnli-512-5 on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.4991
- Accuracy: 0.9356
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.0514 | 1.0 | 16363 | 0.4557 | 0.9265 |
0.0369 | 2.0 | 32726 | 0.4548 | 0.9323 |
0.0249 | 3.0 | 49089 | 0.4376 | 0.9320 |
0.0197 | 4.0 | 65452 | 0.4991 | 0.9356 |
0.0135 | 5.0 | 81815 | 0.5424 | 0.9341 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.11.0a0+17540c5
- Datasets 2.0.0
- Tokenizers 0.11.6