metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_cm
results: []
bert_cm
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: 0.4443
- Accuracy: 0.9210
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 132 | 0.2634 | 0.8951 |
| No log | 2.0 | 264 | 0.2139 | 0.9195 |
| No log | 3.0 | 396 | 0.3145 | 0.9195 |
| 0.2227 | 4.0 | 528 | 0.3342 | 0.9286 |
| 0.2227 | 5.0 | 660 | 0.3804 | 0.9316 |
| 0.2227 | 6.0 | 792 | 0.3942 | 0.9362 |
| 0.2227 | 7.0 | 924 | 0.4372 | 0.9195 |
| 0.0101 | 8.0 | 1056 | 0.4211 | 0.9255 |
| 0.0101 | 9.0 | 1188 | 0.4334 | 0.9240 |
| 0.0101 | 10.0 | 1320 | 0.4443 | 0.9210 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1