metadata
license: mit
tags:
- generated_from_trainer
datasets:
- tweet_eval
metrics:
- accuracy
- f1
model-index:
- name: tweet_eval-sentiment-finetuned
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: sentiment
type: sentiment
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.7
- name: f1
type: f1
value: 0.7
tweet_eval-sentiment-finetuned
This model is a fine-tuned version of microsoft/deberta-v3-small on the tweet_eval dataset. It achieves the following results on the evaluation set:
- Loss: 0.8369
- Accuracy: 0.7305
- F1: 0.7297
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: 8e-05
- train_batch_size: 128
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.7269 | 1.0 | 357 | 0.6057 | 0.733 | 0.7323 |
| 0.522 | 2.0 | 714 | 0.6115 | 0.7415 | 0.7416 |
| 0.359 | 3.0 | 1071 | 0.6970 | 0.744 | 0.7445 |
| 0.2386 | 4.0 | 1428 | 0.8369 | 0.7305 | 0.7297 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.9.1
- Datasets 2.1.0
- Tokenizers 0.12.1