metadata
license: mit
base_model: microsoft/deberta-v2-xxlarge
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: deberta-v2-xxl-imdb-v0.1
results: []
deberta-v2-xxl-imdb-v0.1
This model is a fine-tuned version of microsoft/deberta-v2-xxlarge on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1684
- Accuracy: 0.9708
- F1: 0.9710
- Precision: 0.9669
- Recall: 0.9750
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: cosine
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.0607 | 1.0 | 6250 | 0.2211 | 0.9616 | 0.9611 | 0.9738 | 0.9487 |
| 0.3056 | 2.0 | 12500 | 0.1855 | 0.9662 | 0.9658 | 0.9770 | 0.9548 |
| 0.0502 | 3.0 | 18750 | 0.1790 | 0.9696 | 0.9697 | 0.9668 | 0.9726 |
| 0.2397 | 4.0 | 25000 | 0.1741 | 0.9705 | 0.9707 | 0.9634 | 0.9782 |
| 0.1207 | 5.0 | 31250 | 0.1662 | 0.9708 | 0.9708 | 0.9713 | 0.9702 |
| 0.0637 | 6.0 | 37500 | 0.1718 | 0.9707 | 0.9707 | 0.9710 | 0.9703 |
| 0.3034 | 7.0 | 43750 | 0.1687 | 0.9706 | 0.9707 | 0.9670 | 0.9745 |
| 0.0013 | 8.0 | 50000 | 0.1683 | 0.9708 | 0.9709 | 0.9668 | 0.9751 |
| 0.0543 | 9.0 | 56250 | 0.1683 | 0.9707 | 0.9708 | 0.9667 | 0.9750 |
| 0.1015 | 10.0 | 62500 | 0.1684 | 0.9708 | 0.9710 | 0.9669 | 0.9750 |
Framework versions
- Transformers 4.39.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2