vmarklynn/bart-large-cnn-icsi-ami-v3

bart-large-cnn-samsum-icsi-ami-v3

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

• Loss: 3.2328
• Rouge1: 39.9389
• Rouge2: 12.2256
• Rougel: 23.4739
• Rougelsum: 36.7757
• Gen Len: 155.3529

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: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• 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	135	3.2655	38.2358	11.9547	23.1235	35.1978	163.8824
No log	2.0	270	3.2328	39.9389	12.2256	23.4739	36.7757	155.3529
No log	3.0	405	3.4852	40.8728	11.6505	22.8143	37.3518	144.7647
2.1798	4.0	540	4.0977	40.3307	10.4437	22.6059	36.2414	135.1471
2.1798	5.0	675	4.6537	41.2432	10.7188	22.7868	37.3837	136.1471

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu117
• Datasets 2.10.1
• Tokenizers 0.13.2