metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- dataset
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: distilbert-base-multilingual-cased-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: 0.6005528680027643
- name: F1
type: f1
value: 0.5980973383983778
- name: Precision
type: precision
value: 0.6008849518067042
- name: Recall
type: recall
value: 0.5962561389203832
distilbert-base-multilingual-cased-finetuned-with-spanish-tweets-clf
This model is a fine-tuned version of distilbert-base-multilingual-cased on the dataset dataset. It achieves the following results on the evaluation set:
- Loss: 1.4692
- Accuracy: 0.6006
- F1: 0.5981
- Precision: 0.6009
- Recall: 0.5963
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 |
|---|---|---|---|---|---|---|---|
| 1.0168 | 1.0 | 543 | 0.9144 | 0.5563 | 0.5012 | 0.5240 | 0.5251 |
| 0.8197 | 2.0 | 1086 | 0.9133 | 0.5764 | 0.5476 | 0.5815 | 0.5462 |
| 0.5574 | 3.0 | 1629 | 1.0629 | 0.6151 | 0.6150 | 0.6227 | 0.6112 |
| 0.3487 | 4.0 | 2172 | 1.4692 | 0.6006 | 0.5981 | 0.6009 | 0.5963 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1
- Datasets 2.8.0
- Tokenizers 0.13.2