imdb-prefix-1.0
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1901
- Accuracy: 0.9263
- F1: 0.9263
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: 0.01
- train_batch_size: 80
- eval_batch_size: 80
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.2655 | 1.0 | 313 | 0.2379 | 0.9085 | 0.9084 |
| 0.2325 | 2.0 | 626 | 0.1999 | 0.9214 | 0.9214 |
| 0.205 | 3.0 | 939 | 0.2064 | 0.9188 | 0.9187 |
| 0.1942 | 4.0 | 1252 | 0.1893 | 0.9258 | 0.9258 |
| 0.1828 | 5.0 | 1565 | 0.1901 | 0.9263 | 0.9263 |
Framework versions
- PEFT 0.18.0
- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 4.4.2
- Tokenizers 0.22.1
- Downloads last month
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for laodaImissU/imdb-prefix-1.0
Base model
google-bert/bert-base-uncased