thesis-bart-transfered-on-original-wcep

This model is a fine-tuned version of roofdancer/thesis-bart-finetuned on the wcep-10 dataset. It achieves the following results on the evaluation set:

• Loss: 1.9636
• Rouge1: 37.0523
• Rouge2: 16.3494
• Rougel: 26.5969
• Rougelsum: 30.3484
• Gen Len: 69.6147

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: 16
• eval_batch_size: 16
• 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
2.015	1.0	510	1.9658	36.7717	16.2582	26.3675	30.2708	70.5186
1.7162	2.0	1020	1.9491	36.6604	16.1166	26.2311	29.8851	69.7657
1.5603	3.0	1530	1.9636	37.0523	16.3494	26.5969	30.3484	69.6147

Framework versions

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