<!-- 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-mnli
This model is a fine-tuned version of bert-base-uncased on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.4218
- Accuracy: 0.8488
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: 5e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.5194 | 1.0 | 3068 | 0.4468 | 0.8307 |
0.3445 | 2.0 | 6136 | 0.4384 | 0.8428 |
0.2341 | 3.0 | 9204 | 0.4946 | 0.8415 |
0.1625 | 4.0 | 12272 | 0.5479 | 0.8388 |
0.1218 | 5.0 | 15340 | 0.6348 | 0.8358 |
0.0968 | 6.0 | 18408 | 0.6620 | 0.8315 |
0.0799 | 7.0 | 21476 | 0.7072 | 0.8287 |
0.0675 | 8.0 | 24544 | 0.7659 | 0.8307 |
0.0592 | 9.0 | 27612 | 0.7978 | 0.8305 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2