Hyperparameters
{
"num_train_epochs": 3,
"seed": 7,
"summary_column": "output_text",
"text_column": "text",
"encoder_max_length" : 512,
"decoder_max_length" :36,
"batch_size" : 256
}
Usage
Results
| key | value |
|---|---|
| eval loss | 4.539857387542725 |
| eval_rouge1 | 23.7478 |
| eval_rouge2 | 7.3616 |
| eval_rougeL | 20.6615 |
| eval_rougeLsum | 20.7371 |
| eval_gen_len | 16.1806 |
| test loss | 4.515065670013428 |
| test_rouge1 | 23.7415 |
| test_rouge2 | 7.3548 |
| test_rougeL | 20.746 |
| test_rougeLsum | 20.8149 |
| test_gen_len | 16.1926 |
- Downloads last month
- 34
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Dataset used to train LeoCordoba/beto2beto-cc-news-es-titles
Space using LeoCordoba/beto2beto-cc-news-es-titles 1
Evaluation results
- Validation ROGUE-1 on CCNEWS-ES-titlesself-reported23.748
- Validation ROGUE-2 on CCNEWS-ES-titlesself-reported7.362
- Validation ROGUE-L on CCNEWS-ES-titlesself-reported20.662
- Validation ROGUE-Lsum on CCNEWS-ES-titlesself-reported20.737
- Test ROGUE-1 on CCNEWS-ES-titlesself-reported23.741
- Test ROGUE-2 on CCNEWS-ES-titlesself-reported7.355
- Test ROGUE-L on CCNEWS-ES-titlesself-reported20.746
- Test ROGUE-Lsum on CCNEWS-ES-titlesself-reported20.815