rating_prediction_model
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8407
- Accuracy: 0.4345
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: 0.0002
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.5453 | 0.5 | 110 | 1.4598 | 0.4315 |
1.447 | 1.0 | 220 | 1.3949 | 0.4406 |
1.3657 | 1.5 | 330 | 1.3861 | 0.4353 |
1.3621 | 1.99 | 440 | 1.3520 | 0.4625 |
1.2232 | 2.49 | 550 | 1.4279 | 0.4357 |
1.2381 | 2.99 | 660 | 1.3662 | 0.4628 |
0.9821 | 3.49 | 770 | 1.4817 | 0.4525 |
0.9642 | 3.99 | 880 | 1.5474 | 0.4270 |
0.6797 | 4.49 | 990 | 1.8160 | 0.4294 |
0.6574 | 4.99 | 1100 | 1.8407 | 0.4345 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2
- Downloads last month
- 1