zera09/bart_bos

Bart

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: 3.4379

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: 8
• eval_batch_size: 8
• 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	32	1.9039
No log	2.0	64	1.9118
No log	3.0	96	1.9611
No log	4.0	128	2.1126
No log	5.0	160	2.3234
No log	6.0	192	2.5468
No log	7.0	224	2.6987
No log	8.0	256	2.8041
No log	9.0	288	2.9329
No log	10.0	320	3.0530
No log	11.0	352	3.1344
No log	12.0	384	3.1571
No log	13.0	416	3.2308
No log	14.0	448	3.3060
No log	15.0	480	3.3254
0.55	16.0	512	3.3449
0.55	17.0	544	3.3627
0.55	18.0	576	3.4195
0.55	19.0	608	3.4282
0.55	20.0	640	3.4379

Framework versions

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