metadata
license: mit
base_model: prajjwal1/bert-small
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: assignment3_model
results: []
assignment3_model
This model is a fine-tuned version of prajjwal1/bert-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3004
- Accuracy: 0.9115
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3227 | 1.0 | 4598 | 0.3143 | 0.9062 |
| 0.2899 | 2.0 | 9196 | 0.3004 | 0.9115 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1