metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- sentiment140
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: distilbert-base-uncasedv1-finetuned-twitter-sentiment
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: sentiment140
type: sentiment140
config: sentiment140
split: train
args: sentiment140
metrics:
- name: Accuracy
type: accuracy
value: 0.82475
- name: F1
type: f1
value: 0.8246033480256058
- name: Precision
type: precision
value: 0.825087861584212
- name: Recall
type: recall
value: 0.8016811137378513
distilbert-base-uncasedv1-finetuned-twitter-sentiment
This model is a fine-tuned version of distilbert-base-uncased on the sentiment140 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3985
- Accuracy: 0.8247
- F1: 0.8246
- Precision: 0.8251
- Recall: 0.8017
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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 500 | 0.4049 | 0.8181 | 0.8178 | 0.8236 | 0.7862 |
| No log | 2.0 | 1000 | 0.3985 | 0.8247 | 0.8246 | 0.8251 | 0.8017 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.12.1