bart-cnn-science-v3-e1-v4-e4-manual

This model is a fine-tuned version of theojolliffe/bart-cnn-science-v3-e1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2615
• Rouge1: 53.36
• Rouge2: 32.0237
• Rougel: 33.2835
• Rougelsum: 50.7455
• Gen Len: 142.0

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	42	1.0675	51.743	31.3774	34.1939	48.7234	142.0
No log	2.0	84	1.0669	49.4166	28.1438	30.188	46.0289	142.0
No log	3.0	126	1.1799	52.6909	31.0174	35.441	50.0351	142.0
No log	4.0	168	1.2615	53.36	32.0237	33.2835	50.7455	142.0

Framework versions

• Transformers 4.20.0
• Pytorch 1.11.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1