metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: olm-bert-tiny-december-2022-target-glue-qnli
results: []
olm-bert-tiny-december-2022-target-glue-qnli
This model is a fine-tuned version of muhtasham/olm-bert-tiny-december-2022 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6358
- Accuracy: 0.6306
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 |
|---|---|---|---|---|
| 0.692 | 0.15 | 500 | 0.6882 | 0.5574 |
| 0.6777 | 0.31 | 1000 | 0.6637 | 0.6059 |
| 0.667 | 0.46 | 1500 | 0.6568 | 0.6064 |
| 0.6609 | 0.61 | 2000 | 0.6517 | 0.6193 |
| 0.6596 | 0.76 | 2500 | 0.6514 | 0.6127 |
| 0.6584 | 0.92 | 3000 | 0.6496 | 0.6202 |
| 0.6514 | 1.07 | 3500 | 0.6487 | 0.6191 |
| 0.652 | 1.22 | 4000 | 0.6420 | 0.6253 |
| 0.6449 | 1.37 | 4500 | 0.6415 | 0.6268 |
| 0.6477 | 1.53 | 5000 | 0.6358 | 0.6306 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2