metadata
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- recall
- precision
model-index:
- name: Label-classifier
results: []
Label-classifier
This model is a fine-tuned version of google-bert/bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9972
- Accuracy: 0.7284
- Recall: 0.3681
- Precision: 0.5257
- F1 macro: 0.4064
- F1 micro: 0.7284
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1 macro | F1 micro |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 81 | 0.8954 | 0.6852 | 0.2167 | 0.2380 | 0.1919 | 0.6852 |
| No log | 2.0 | 162 | 0.9831 | 0.6667 | 0.2552 | 0.4106 | 0.2485 | 0.6667 |
| No log | 3.0 | 243 | 0.9381 | 0.6728 | 0.3496 | 0.4541 | 0.3670 | 0.6728 |
| No log | 4.0 | 324 | 1.0068 | 0.7284 | 0.3501 | 0.5468 | 0.3915 | 0.7284 |
| No log | 5.0 | 405 | 0.9972 | 0.7284 | 0.3681 | 0.5257 | 0.4064 | 0.7284 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2