RuPERTa_base_sentiment_analysis_esThis model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container, The base model is RuPERTa-base (uncased) which is a RoBERTa model trained on a uncased version of big Spanish corpus. It was trained by mrm8488, Manuel Romero.Link to base model
The dataset is a collection of movie reviews in Spanish, about 50,000 reviews. The dataset is balanced and provides every review in english, in spanish and the label in both languages.
Sizes of datasets:
{
"epochs": "4",
"train_batch_size": "32",
"eval_batch_size": "8",
"fp16": "true",
"learning_rate": "3e-05",
"model_name": "\"mrm8488/RuPERTa-base\"",
"sagemaker_container_log_level": "20",
"sagemaker_program": "\"train.py\"",
}
Accuracy = 0.8629333333333333 F1 Score = 0.8648790746582545 Precision = 0.8479381443298969 Recall = 0.8825107296137339
Accuracy = 0.8066666666666666 F1 Score = 0.8057862309134743 Precision = 0.7928307854507116 Recall = 0.8191721132897604
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("edumunozsala/RuPERTa_base_sentiment_analysis_es")
model = AutoModelForSequenceClassification.from_pretrained("edumunozsala/RuPERTa_base_sentiment_analysis_es")
text ="Se trata de una película interesante, con un solido argumento y un gran interpretación de su actor principal"
input_ids = torch.tensor(tokenizer.encode(text)).unsqueeze(0)
outputs = model(input_ids)
output = outputs.logits.argmax(1)
Created by Eduardo Muñoz/@edumunozsala
checkpoint-5316/optimizer.pt 1.0 GBcheckpoint-5316/pytorch_model.bin 504 MBpytorch_model.bin 504 MBcheckpoint-5316/rng_state.pth 14.7 kBcheckpoint-5316/training_args.bin 2.4 kBtraining_args.bin 2.4 kBcheckpoint-5316/scheduler.pt 0.6 kBcheckpoint-5316/scaler.pt 0.6 kB