metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
base_model: distilbert-base-uncased
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: emotion
type: emotion
args: default
metrics:
- type: accuracy
value: 0.934
name: Accuracy
- type: f1
value: 0.9337817808480242
name: F1
distilbert-base-uncased-finetuned-emotion
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: 0.2155
- Accuracy: 0.934
- F1: 0.9338
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 |
|---|---|---|---|---|---|
| 0.1768 | 1.0 | 250 | 0.1867 | 0.924 | 0.9235 |
| 0.1227 | 2.0 | 500 | 0.1588 | 0.934 | 0.9346 |
| 0.1031 | 3.0 | 750 | 0.1656 | 0.931 | 0.9306 |
| 0.0843 | 4.0 | 1000 | 0.1662 | 0.9395 | 0.9392 |
| 0.0662 | 5.0 | 1250 | 0.1714 | 0.9325 | 0.9326 |
| 0.0504 | 6.0 | 1500 | 0.1821 | 0.934 | 0.9338 |
| 0.0429 | 7.0 | 1750 | 0.2038 | 0.933 | 0.9324 |
| 0.0342 | 8.0 | 2000 | 0.2054 | 0.938 | 0.9379 |
| 0.0296 | 9.0 | 2250 | 0.2128 | 0.9345 | 0.9345 |
| 0.0211 | 10.0 | 2500 | 0.2155 | 0.934 | 0.9338 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu113
- Datasets 2.0.0
- Tokenizers 0.11.6