led-large-16384-BASE-Attention3ep-ASPRPreACE3ep

This model is a fine-tuned version of rosadecsai/led-large-16384-BASE-Attention3ep on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.0840
• Rouge1: 43.346
• Rouge2: 16.7726
• Rougel: 20.0253
• Rougelsum: 41.5716
• 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
2.241	1.0	1132	2.0571	43.9276	14.7668	20.4134	42.1189	1.0
2.1562	2.0	2264	2.0433	34.9296	15.2542	18.5915	34.3662	1.0
2.0703	2.9978	3393	2.0840	43.346	16.7726	20.0253	41.5716	1.0

Framework versions

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