metadata
license: mit
base_model: microsoft/deberta-v3-small
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
- f1
model-index:
- name: deberta-v3-ft-news-sentiment-analisys
results: []
deberta-v3-ft-news-sentiment-analisys
This model is a fine-tuned version of microsoft/deberta-v3-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2868
- Precision: 0.8987
- Recall: 0.8987
- Accuracy: 0.8987
- F1: 0.8987
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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 64 | 0.8396 | 0.7093 | 0.7093 | 0.7093 | 0.7093 |
| No log | 2.0 | 128 | 0.4040 | 0.8194 | 0.8194 | 0.8194 | 0.8194 |
| No log | 3.0 | 192 | 0.4036 | 0.8238 | 0.8238 | 0.8238 | 0.8238 |
| No log | 4.0 | 256 | 0.3208 | 0.8767 | 0.8767 | 0.8767 | 0.8767 |
| No log | 5.0 | 320 | 0.2868 | 0.8987 | 0.8987 | 0.8987 | 0.8987 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0