bart-cnn-samsum-finetuned

This model is a fine-tuned version of facebook/bart-large-cnn on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2177

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: 1e-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: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	6	0.3206
1.4764	2.0	12	0.2261
1.4764	3.0	18	0.2178
0.2188	4.0	24	0.2113
0.2077	5.0	30	0.2105
0.2077	6.0	36	0.2146
0.1529	7.0	42	0.2058
0.1529	8.0	48	0.2216
0.1482	9.0	54	0.2060
0.1433	10.0	60	0.2049
0.1433	11.0	66	0.2040
0.1153	12.0	72	0.2117
0.1153	13.0	78	0.2181
0.1022	14.0	84	0.2220
0.1145	15.0	90	0.2177

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cpu
• Datasets 2.18.0
• Tokenizers 0.15.2