bert_sentiment_trainer
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: 0.7044
- Accuracy: 0.8857
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: 2.754984679344267e-05
- train_batch_size: 16
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 3000
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.4787 | 0.32 | 250 | 0.4447 | 0.8338 |
0.374 | 0.64 | 500 | 0.3835 | 0.8613 |
0.3681 | 0.96 | 750 | 0.3533 | 0.8696 |
0.2456 | 1.28 | 1000 | 0.4425 | 0.8706 |
0.2092 | 1.6 | 1250 | 0.4393 | 0.8684 |
0.2827 | 1.92 | 1500 | 0.3814 | 0.8812 |
0.1424 | 2.24 | 1750 | 0.5589 | 0.8751 |
0.1791 | 2.56 | 2000 | 0.5869 | 0.8818 |
0.1297 | 2.88 | 2250 | 0.5741 | 0.8744 |
0.0474 | 3.21 | 2500 | 0.6328 | 0.8834 |
0.08 | 3.53 | 2750 | 0.7015 | 0.8748 |
0.088 | 3.85 | 3000 | 0.7044 | 0.8857 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 10
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Artanis1551/bert_sentiment_trainer
Base model
google-bert/bert-base-cased