led-large-16384-BASE3ep

This model is a fine-tuned version of allenai/led-large-16384 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.0538
• Rouge1: 36.1878
• Rouge2: 14.1274
• Rougel: 19.6133
• Rougelsum: 35.9116
• Gen Len: 1.0

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.8959	1.0	1132	2.1458	40.5722	14.0808	20.8062	39.5319	1.0
2.7074	2.0	2264	2.0610	41.3972	16.3424	19.1462	39.8448	1.0
2.5389	2.9978	3393	2.0538	36.1878	14.1274	19.6133	35.9116	1.0

Framework versions

• Transformers 4.48.3
• Pytorch 2.11.0+cu128
• Datasets 4.8.5
• Tokenizers 0.21.4