LED-Finetuned-sum-full-note

This model is a fine-tuned version of MingZhong/DialogLED-base-16384 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7979
• Rouge1: 0.4228
• Rouge2: 0.2722
• Rougel: 0.3218

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: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 2
• 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: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel
0.864	1.0	1600	0.8257	0.4202	0.2695	0.3197
0.7586	2.0	3200	0.7979	0.4228	0.2722	0.3218

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1