led-large-16384-finetune-paperLedBASEAttention

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: 2.8741
• Rouge1: 36.6438
• Rouge2: 6.8729
• Rougel: 15.411
• Rougelsum: 33.5616
• 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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• 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
2.9305	0.9993	1128	2.9793	35.8974	8.3168	16.9625	34.714	1.0
2.7387	1.9993	2256	2.8920	31.348	7.3298	14.0021	29.4671	1.0
2.6102	2.9993	3384	2.8741	36.6438	6.8729	15.411	33.5616	1.0

Framework versions

• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.1