metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- tweet_eval
metrics:
- f1
model-index:
- name: presentation_hate_1234567
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: tweet_eval
type: tweet_eval
args: hate
metrics:
- name: F1
type: f1
value: 0.7679568806891273
presentation_hate_1234567
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: 0.8438
- F1: 0.7680
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: 5.436235805743952e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 1234567
- 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 |
---|---|---|---|---|
0.6027 | 1.0 | 282 | 0.5186 | 0.7209 |
0.3537 | 2.0 | 564 | 0.4989 | 0.7619 |
0.0969 | 3.0 | 846 | 0.6405 | 0.7697 |
0.0514 | 4.0 | 1128 | 0.8438 | 0.7680 |
Framework versions
- Transformers 4.12.5
- Pytorch 1.9.1
- Datasets 1.16.1
- Tokenizers 0.10.3