metadata
tags:
- generated_from_trainer
datasets:
- go_emotions-es-mt
metrics:
- accuracy
- f1
model-index:
- name: electricidad-base-finetuned-go_emotions-es
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: go_emotions-es-mt
type: go_emotions-es-mt
config: simplified
split: train
args: simplified
metrics:
- name: Accuracy
type: accuracy
value: 0.5934476693051891
- name: F1
type: f1
value: 0.5806237685841615
widget:
- text: Me gusta mucho su forma de ser
- text: Es una persona muy extraña...
- text: El dolor es desesperante
- text: No me esperaba una evolución tan positiva
- text: ¡Dios mío, es enorme!
- text: ¡Agg! Está asqueroso.
electricidad-base-finetuned-go_emotions-es
This model is a fine-tuned version of mrm8488/electricidad-base-discriminator on the go_emotions-es-mt dataset. It achieves the following results on the evaluation set:
- Loss: 1.5111
- Accuracy: 0.5934
- F1: 0.5806
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: 16
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
1.729 | 1.0 | 2270 | 1.5835 | 0.5578 | 0.5044 |
1.4432 | 2.0 | 4540 | 1.4529 | 0.5842 | 0.5538 |
1.2688 | 3.0 | 6810 | 1.4445 | 0.5945 | 0.5770 |
1.1017 | 4.0 | 9080 | 1.4804 | 0.5937 | 0.5781 |
0.9999 | 5.0 | 11350 | 1.5111 | 0.5934 | 0.5806 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1