metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- tweet_eval
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-tweet_hate
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: tweet_eval
type: tweet_eval
args: hate
metrics:
- name: Accuracy
type: accuracy
value: 0.77
- name: F1
type: f1
value: 0.7711956429754464
distilbert-base-uncased-finetuned-tweet_hate
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: 0.6390
- Accuracy: 0.77
- F1: 0.7712
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.5003 | 1.0 | 282 | 0.4716 | 0.76 | 0.7613 |
| 0.3428 | 2.0 | 564 | 0.4767 | 0.771 | 0.7721 |
| 0.2559 | 3.0 | 846 | 0.5256 | 0.778 | 0.7789 |
| 0.1811 | 4.0 | 1128 | 0.5839 | 0.774 | 0.7748 |
| 0.134 | 5.0 | 1410 | 0.6390 | 0.77 | 0.7712 |
Framework versions
- Transformers 4.16.2
- Pytorch 2.1.0+cu121
- Datasets 1.16.1
- Tokenizers 0.15.0