metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert-base-uncased-wnli-ia3-epochs-10-lr-5e-05
results: []
bert-base-uncased-wnli-ia3-epochs-10-lr-5e-05
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: 0.6952
- Accuracy: 0.48
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: 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 | 17 | 0.6792 | 0.57 |
| No log | 2.0 | 34 | 0.6907 | 0.57 |
| No log | 3.0 | 51 | 0.7020 | 0.43 |
| No log | 4.0 | 68 | 0.7008 | 0.44 |
| No log | 5.0 | 85 | 0.6960 | 0.48 |
| No log | 6.0 | 102 | 0.6953 | 0.47 |
| No log | 7.0 | 119 | 0.6933 | 0.5 |
| No log | 8.0 | 136 | 0.6944 | 0.5 |
| No log | 9.0 | 153 | 0.6952 | 0.48 |
| No log | 10.0 | 170 | 0.6952 | 0.48 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3