thesis-led-finetuned-on-wcep

This model is a fine-tuned version of allenai/led-base-16384 on the wcep-10 dataset. It achieves the following results on the evaluation set:

• Loss: 1.6816
• Rouge1: 43.4358
• Rouge2: 21.8159
• Rougel: 35.0411
• Rougelsum: 36.1007
• Gen Len: 27.2843

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• 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
1.6843	1.0	2040	1.6753	42.8519	21.8933	35.0226	35.9911	25.6647
1.4083	2.0	4080	1.6672	43.5166	22.0845	35.283	36.4006	26.4098
1.1981	3.0	6120	1.6816	43.4358	21.8159	35.0411	36.1007	27.2843

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2