metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- tweet_eval
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-tweets-sentiment
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: tweet_eval
type: tweet_eval
args: sentiment
metrics:
- name: Accuracy
type: accuracy
value: 0.7295
- name: F1
type: f1
value: 0.7303196028048928
distilbert-base-uncased-finetuned-tweets-sentiment
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: 0.8192
- Accuracy: 0.7295
- F1: 0.7303
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.7126 | 1.0 | 713 | 0.6578 | 0.7185 | 0.7181 |
| 0.5514 | 2.0 | 1426 | 0.6249 | 0.7005 | 0.7046 |
| 0.4406 | 3.0 | 2139 | 0.7053 | 0.731 | 0.7296 |
| 0.3511 | 4.0 | 2852 | 0.7580 | 0.718 | 0.7180 |
| 0.2809 | 5.0 | 3565 | 0.8192 | 0.7295 | 0.7303 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0
- Datasets 1.16.1
- Tokenizers 0.10.3