randomcomb_mlm_ep5_mnli
This model is a fine-tuned version of cuenb on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.4416
- Accuracy: 0.8616
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5569 | 0.41 | 5000 | 0.4415 | 0.8273 |
| 0.4598 | 0.81 | 10000 | 0.4234 | 0.8425 |
| 0.3832 | 1.22 | 15000 | 0.4398 | 0.8475 |
| 0.3314 | 1.63 | 20000 | 0.4137 | 0.8494 |
| 0.3158 | 2.04 | 25000 | 0.4484 | 0.8527 |
| 0.2294 | 2.44 | 30000 | 0.4471 | 0.8552 |
| 0.2283 | 2.85 | 35000 | 0.4541 | 0.8557 |
Framework versions
- Transformers 4.21.0.dev0
- Pytorch 1.8.0
- Datasets 1.18.3
- Tokenizers 0.12.1
- Downloads last month
- 11