metadata
license: mit
base_model: microsoft/deberta-v3-large
datasets:
- imdb
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: deberta-v3-large-imdb
results: []
deberta-v3-large-imdb
This model is a fine-tuned version of microsoft/deberta-v3-large on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.1906
- Accuracy: 0.9646
- F1: 0.9645
- Precision: 0.9679
- Recall: 0.9610
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: 16
- eval_batch_size: 16
- 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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.2471 | 1.0 | 3125 | 0.2004 | 0.9487 | 0.9474 | 0.9710 | 0.9250 |
| 0.2029 | 2.0 | 6250 | 0.1715 | 0.9603 | 0.9600 | 0.9664 | 0.9537 |
| 0.0631 | 3.0 | 9375 | 0.2049 | 0.9566 | 0.9555 | 0.9793 | 0.9329 |
| 0.0432 | 4.0 | 12500 | 0.1906 | 0.9646 | 0.9645 | 0.9679 | 0.9610 |
Framework versions
- Transformers 4.39.2
- Pytorch 2.2.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2