metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: distilbert-tweet_eval-emotion
results: []
distilbert-tweet_eval-emotion
This model is a fine-tuned version of distilbert-base-uncased on the tweet_eval dataset. It achieves the following results on the evaluation set:
- Loss: 0.2519
- Accuracy: 0.9212
- Precision: 0.9333
- Recall: 0.7424
- F1: 0.8138
- Auroc: 0.9510
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Auroc |
|---|---|---|---|---|---|---|---|---|
| 0.4845 | 2.5 | 250 | 0.4243 | 0.8061 | 0.2000 | 0.0500 | 0.0800 | 0.9209 |
| 0.2692 | 5.0 | 500 | 0.2946 | 0.9151 | 0.9333 | 0.7091 | 0.7871 | 0.9469 |
| 0.192 | 7.5 | 750 | 0.2599 | 0.9151 | 0.9333 | 0.7091 | 0.7871 | 0.9500 |
| 0.1502 | 10.0 | 1000 | 0.2519 | 0.9212 | 0.9333 | 0.7424 | 0.8138 | 0.9510 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.2
- Datasets 2.17.0
- Tokenizers 0.15.1