metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- tweet_eval
metrics:
- f1
model-index:
- name: hate_trained_final
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: tweet_eval
type: tweet_eval
args: hate
metrics:
- name: F1
type: f1
value: 0.7697890540753396
hate_trained_final
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: 0.5543
- F1: 0.7698
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: 5.460503761236833e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 0
- 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 | F1 |
|---|---|---|---|---|
| 0.463 | 1.0 | 1125 | 0.5213 | 0.7384 |
| 0.3943 | 2.0 | 2250 | 0.5134 | 0.7534 |
| 0.3407 | 3.0 | 3375 | 0.5400 | 0.7666 |
| 0.3121 | 4.0 | 4500 | 0.5543 | 0.7698 |
Framework versions
- Transformers 4.12.5
- Pytorch 1.9.1
- Datasets 1.16.1
- Tokenizers 0.10.3