metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert-base-uncased-cosmos-mcqa
results: []
bert-base-uncased-cosmos-mcqa
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0302
- Accuracy: 0.5940
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9652 | 1.0 | 1579 | 0.9947 | 0.5926 |
| 0.6377 | 2.0 | 3158 | 1.0135 | 0.6178 |
| 0.3396 | 3.0 | 4737 | 1.3263 | 0.6010 |
| 0.1965 | 4.0 | 6316 | 1.8585 | 0.5916 |
| 0.1211 | 5.0 | 7895 | 2.0302 | 0.5940 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.6.dev0
- Tokenizers 0.13.3