classification_bart

This model is a fine-tuned version of facebook/bart-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6395
• Rouge1: 61.878
• Rouge2: 49.9283
• Rougel: 59.6423
• Rougelsum: 59.7142
• Gen Len: 21.0

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
• 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	341	0.7811	60.1042	48.0406	58.0511	58.1495	21.0
0.834	2.0	682	0.7603	61.3673	48.0906	58.5343	58.6285	21.0
0.549	3.0	1023	0.6395	61.878	49.9283	59.6423	59.7142	21.0
0.549	4.0	1364	0.6827	62.0219	50.1238	59.7593	59.8346	21.0
0.4279	5.0	1705	0.6626	62.2247	50.4714	59.962	60.0911	21.0

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 2.20.0
• Tokenizers 0.21.0