lsg-lsh-mbart-cc25-16384-128-4-4ep

This model is a fine-tuned version of Auruncus/lsg-lsh-mbart-cc25-16384-128-4-2ep on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.5736
• Rouge1: 2.6972
• Rouge2: 1.6893
• Rougel: 2.6528
• Rougelsum: 2.6347
• Gen Len: 135.5

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2.0
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.41.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1