bert-base-uncased-rte-lora-epochs-10-lr-0.0005
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: 2.0542
- Accuracy: 0.63
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: 0.0005
- 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 | 0.6901 | 0.56 |
| No log | 2.0 | 150 | 0.6403 | 0.66 |
| No log | 3.0 | 225 | 0.6422 | 0.71 |
| No log | 4.0 | 300 | 0.7092 | 0.65 |
| No log | 5.0 | 375 | 0.8987 | 0.67 |
| No log | 6.0 | 450 | 1.2375 | 0.65 |
| 0.4488 | 7.0 | 525 | 1.7709 | 0.61 |
| 0.4488 | 8.0 | 600 | 1.7151 | 0.63 |
| 0.4488 | 9.0 | 675 | 1.9559 | 0.62 |
| 0.4488 | 10.0 | 750 | 2.0542 | 0.63 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.
Model tree for prateeky2806/bert-base-uncased-rte-lora-epochs-10-lr-0.0005
Base model
google-bert/bert-base-uncased