mrm8488/electricidad-small-finetuned-sst2-es

Electricidad (small) fine-tuned on sst2-es-mt for Spanish Sentiment Analysis 👍👎

This model is a fine-tuned version of mrm8488/electricidad-small-discriminator on the sst2-es-mt dataset. A dataset created using Neural Machine Translation on original SST2 (English) dataset.

It achieves the following results on the evaluation set:

• Accuracy: 0.879
• F1: 0.88

Usage

from transformers import pipeline

model_ckpt = "mrm8488/electricidad-small-finetuned-sst2-es"

classifier = pipeline("sentiment-analysis", model=model_ckpt)

classifier("Here your text in Spanish!")

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3.676560994488171e-05
• train_batch_size: 64
• eval_batch_size: 32
• seed: 30
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.3272	1.0	2105	0.3418	0.8567	0.8489
0.2394	2.0	4210	0.3391	0.8796	0.88
0.192	3.0	6315	0.3644	0.8761	0.8770

Framework versions

• Transformers 4.21.2
• Pytorch 1.12.1+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1