metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- dataset
metrics:
- accuracy
- f1
- precision
- recall
base_model: distilbert-base-uncased
model-index:
- name: distilbert-base-uncased-finetuned-with-spanish-tweets-clf-cleaned-ds
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: dataset
type: dataset
config: 60-20-20
split: dev
args: 60-20-20
metrics:
- type: accuracy
value: 0.5556323427781618
name: Accuracy
- type: f1
value: 0.5577964748279268
name: F1
- type: precision
value: 0.5682169161320979
name: Precision
- type: recall
value: 0.5539741666889855
name: Recall
distilbert-base-uncased-finetuned-with-spanish-tweets-clf-cleaned-ds
This model is a fine-tuned version of distilbert-base-uncased on the dataset dataset. It achieves the following results on the evaluation set:
- Loss: 1.1229
- Accuracy: 0.5556
- F1: 0.5578
- Precision: 0.5682
- Recall: 0.5540
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 |
|---|---|---|---|---|---|---|---|
| 1.0683 | 1.0 | 543 | 1.0019 | 0.4997 | 0.4041 | 0.4724 | 0.4488 |
| 0.9372 | 2.0 | 1086 | 0.9395 | 0.5425 | 0.5143 | 0.5480 | 0.5123 |
| 0.7283 | 3.0 | 1629 | 0.9674 | 0.5632 | 0.5615 | 0.5658 | 0.5587 |
| 0.5127 | 4.0 | 2172 | 1.1229 | 0.5556 | 0.5578 | 0.5682 | 0.5540 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1
- Datasets 2.8.0
- Tokenizers 0.13.2