<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
assignment2_meher_test1
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4261
- Precision: 0.275
- Recall: 0.0932
- F1: 0.1392
- Accuracy: 0.9417
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 128 | 0.3722 | 0.1143 | 0.0339 | 0.0523 | 0.9402 |
No log | 2.0 | 256 | 0.3779 | 0.2041 | 0.0847 | 0.1198 | 0.9405 |
No log | 3.0 | 384 | 0.4261 | 0.275 | 0.0932 | 0.1392 | 0.9417 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1