metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
- precision
model-index:
- name: distilbert-base-uncased_emotion_ft_0416
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: 0.9365
- name: F1
type: f1
value: 0.9367095468423076
- name: Precision
type: precision
value: 0.9084962660186648
distilbert-base-uncased_emotion_ft_0416
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: 0.1520
- Accuracy: 0.9365
- F1: 0.9367
- Precision: 0.9085
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision |
|---|---|---|---|---|---|---|
| 0.8004 | 1.0 | 250 | 0.2687 | 0.9185 | 0.9179 | 0.8974 |
| 0.2055 | 2.0 | 500 | 0.1749 | 0.929 | 0.9292 | 0.9032 |
| 0.1386 | 3.0 | 750 | 0.1596 | 0.933 | 0.9332 | 0.9093 |
| 0.1128 | 4.0 | 1000 | 0.1520 | 0.9365 | 0.9367 | 0.9085 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2