metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-finetuned
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.9385
- name: F1
type: f1
value: 0.9383538787245842
distilbert-finetuned
This model is a fine-tuned version of distilbert-base-uncased on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.1775
- Accuracy: 0.9385
- F1: 0.9384
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 250 | 0.2451 | 0.9225 | 0.9227 |
| 0.4827 | 2.0 | 500 | 0.1655 | 0.934 | 0.9335 |
| 0.4827 | 3.0 | 750 | 0.1558 | 0.9365 | 0.9372 |
| 0.1191 | 4.0 | 1000 | 0.1482 | 0.9375 | 0.9374 |
| 0.1191 | 5.0 | 1250 | 0.1599 | 0.9365 | 0.9366 |
| 0.0775 | 6.0 | 1500 | 0.1539 | 0.9375 | 0.9378 |
| 0.0775 | 7.0 | 1750 | 0.1657 | 0.937 | 0.9366 |
| 0.0525 | 8.0 | 2000 | 0.1688 | 0.9385 | 0.9385 |
| 0.0525 | 9.0 | 2250 | 0.1811 | 0.9405 | 0.9406 |
| 0.0383 | 10.0 | 2500 | 0.1775 | 0.9385 | 0.9384 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu118
- Datasets 2.19.1
- Tokenizers 0.19.1