metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.9345
- name: F1
type: f1
value: 0.9343606042371106
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: 0.2145
- Accuracy: 0.9345
- F1: 0.9344
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 |
|---|---|---|---|---|---|
| 0.1703 | 1.0 | 250 | 0.1791 | 0.932 | 0.9308 |
| 0.1183 | 2.0 | 500 | 0.1599 | 0.936 | 0.9358 |
| 0.103 | 3.0 | 750 | 0.1645 | 0.9345 | 0.9348 |
| 0.0827 | 4.0 | 1000 | 0.1698 | 0.9335 | 0.9326 |
| 0.0671 | 5.0 | 1250 | 0.1648 | 0.931 | 0.9308 |
| 0.0535 | 6.0 | 1500 | 0.1843 | 0.936 | 0.9354 |
| 0.0453 | 7.0 | 1750 | 0.2021 | 0.935 | 0.9350 |
| 0.0342 | 8.0 | 2000 | 0.2042 | 0.939 | 0.9390 |
| 0.0296 | 9.0 | 2250 | 0.2120 | 0.9345 | 0.9344 |
| 0.0239 | 10.0 | 2500 | 0.2145 | 0.9345 | 0.9344 |
Framework versions
- Transformers 4.16.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2