metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: bert-base-uncased-finetuned-cda
results: []
bert-base-uncased-finetuned-cda
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7391
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2683 | 1.0 | 40 | 2.0325 |
| 2.1143 | 2.0 | 80 | 1.8827 |
| 2.0295 | 3.0 | 120 | 1.8460 |
| 1.9621 | 4.0 | 160 | 1.8493 |
| 1.9158 | 5.0 | 200 | 1.8602 |
| 1.8769 | 6.0 | 240 | 1.7884 |
| 1.8515 | 7.0 | 280 | 1.7654 |
| 1.8289 | 8.0 | 320 | 1.7201 |
| 1.8179 | 9.0 | 360 | 1.7056 |
| 1.8047 | 10.0 | 400 | 1.7364 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1