metadata
tags:
- generated_from_trainer
datasets:
- dataset
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: >-
dccuchile-distilbert-base-spanish-uncased-finetuned-with-spanish-tweets-clf
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: dataset
type: dataset
config: 60-20-20
split: dev
args: 60-20-20
metrics:
- name: Accuracy
type: accuracy
value: 0.6620594333102972
- name: F1
type: f1
value: 0.6612467747613665
- name: Precision
type: precision
value: 0.6698857111668722
- name: Recall
type: recall
value: 0.6593066578581652
dccuchile-distilbert-base-spanish-uncased-finetuned-with-spanish-tweets-clf
This model is a fine-tuned version of dccuchile/distilbert-base-spanish-uncased on the dataset dataset. It achieves the following results on the evaluation set:
- Loss: 1.5271
- Accuracy: 0.6621
- F1: 0.6612
- Precision: 0.6699
- Recall: 0.6593
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.8515 | 1.0 | 543 | 0.7681 | 0.6565 | 0.6374 | 0.6491 | 0.6363 |
0.5505 | 2.0 | 1086 | 0.8494 | 0.6489 | 0.6431 | 0.6713 | 0.6357 |
0.3302 | 3.0 | 1629 | 1.2386 | 0.6662 | 0.6640 | 0.6667 | 0.6653 |
0.1675 | 4.0 | 2172 | 1.5271 | 0.6621 | 0.6612 | 0.6699 | 0.6593 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1
- Datasets 2.8.0
- Tokenizers 0.13.2