Average Model Cost: $0.0000

Number of Runs: 11,360

Models by this creator




The arabartsummarization model is a model used for text summarization tasks. It has been trained and evaluated on a dataset of 42.21K rows, with 37.52K rows used for training and 4.69K rows used for evaluation. The model achieves a validation loss of 2.3394, Rouge1 score of 1.142, Rouge2 score of 0.227, RougeL score of 1.124, and RougeLsum score of 1.234. The training was performed using a learning rate of 5e-05, a train batch size of 4, and an evaluation batch size of 4. The model was trained for 3 epochs using the Adam optimizer with betas=(0.9,0.999) and epsilon=1e-08, and a linear learning rate scheduler. The framework versions used for training are Transformers 4.25.1, Pytorch 1.13.0+cu116, Datasets 2.7.1, and Tokenizers 0.13.2. More information is needed about the model's intended uses and limitations.

Read more




Similar creators