model2-bart-reverse

This model is a fine-tuned version of theojolliffe/model-2-bart-reverse-raw on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5768
• Rouge1: 50.0024
• Rouge2: 44.5149
• Rougel: 50.408
• Rougelsum: 50.0015
• Gen Len: 20.0

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	160	0.5107	54.2246	50.7271	51.1954	54.4944	20.0
No log	2.0	320	0.5895	48.1317	43.4207	48.6594	48.4308	20.0
No log	3.0	480	0.5833	51.7747	46.8312	52.47	52.1239	20.0
0.4286	4.0	640	0.5768	50.0024	44.5149	50.408	50.0015	20.0

Framework versions

• Transformers 4.22.1
• Pytorch 1.12.1+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1