metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: SentimentT2_BertBase
results: []
SentimentT2_BertBase
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: 0.3196
- Accuracy: 0.8706
- F1: 0.8670
- Auc Roc: 0.9473
- Log Loss: 0.3196
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 20
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Auc Roc | Log Loss |
|---|---|---|---|---|---|---|---|
| 0.7054 | 1.0 | 101 | 0.6628 | 0.6045 | 0.5047 | 0.7215 | 0.6628 |
| 0.6303 | 2.0 | 203 | 0.5437 | 0.7823 | 0.7842 | 0.8748 | 0.5437 |
| 0.4599 | 3.0 | 304 | 0.3532 | 0.8520 | 0.8449 | 0.9364 | 0.3532 |
| 0.3413 | 4.0 | 406 | 0.3172 | 0.8719 | 0.8733 | 0.9405 | 0.3172 |
| 0.2877 | 4.98 | 505 | 0.3196 | 0.8706 | 0.8670 | 0.9473 | 0.3196 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1