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

bart-large-cnn-samsum-acsi-ami

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: 3.1361
• Rouge1: 39.7563
• Rouge2: 11.1286
• Rougel: 23.2632
• Rougelsum: 36.5664
• Gen Len: 108.15

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: 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	20	3.2095	39.8174	11.5559	24.0296	36.3048	108.5
No log	2.0	40	3.1361	39.7563	11.1286	23.2632	36.5664	108.15
No log	3.0	60	3.1599	41.79	12.0967	23.5336	37.6859	122.95
No log	4.0	80	3.2878	42.3161	12.2801	23.9352	38.2391	122.7
No log	5.0	100	3.3671	40.7968	10.7336	22.9434	36.4383	129.225

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1
• Datasets 2.9.0
• Tokenizers 0.13.2