metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert-base-uncased-rte-ia3-epochs-10-lr-0.005
results: []
bert-base-uncased-rte-ia3-epochs-10-lr-0.005
This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.6986
- Accuracy: 0.7
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: 0.005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 28
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 75 | 0.6797 | 0.58 |
| No log | 2.0 | 150 | 0.6631 | 0.61 |
| No log | 3.0 | 225 | 0.6239 | 0.62 |
| No log | 4.0 | 300 | 0.5983 | 0.63 |
| No log | 5.0 | 375 | 0.6250 | 0.68 |
| No log | 6.0 | 450 | 0.6487 | 0.67 |
| 0.6417 | 7.0 | 525 | 0.6473 | 0.64 |
| 0.6417 | 8.0 | 600 | 0.6558 | 0.68 |
| 0.6417 | 9.0 | 675 | 0.6865 | 0.69 |
| 0.6417 | 10.0 | 750 | 0.6986 | 0.7 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3