bart_nobos

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

• Loss: 3.1325

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: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	16	1.8701
No log	2.0	32	1.8565
No log	3.0	48	1.8991
No log	4.0	64	2.0343
No log	5.0	80	2.1420
No log	6.0	96	2.2855
No log	7.0	112	2.4398
No log	8.0	128	2.5599
No log	9.0	144	2.6860
No log	10.0	160	2.7219
No log	11.0	176	2.8293
No log	12.0	192	2.9307
No log	13.0	208	2.9679
No log	14.0	224	3.0043
No log	15.0	240	3.0355
No log	16.0	256	3.0918
No log	17.0	272	3.0862
No log	18.0	288	3.1294
No log	19.0	304	3.1342
No log	20.0	320	3.1325

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1