SummarEaseFocusV3

This model is a fine-tuned version of notBanana/SummarEaseFocusV2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.7999
• Rouge1: 0.2481
• Rouge2: 0.1215
• Rougel: 0.2151
• Rougelsum: 0.2151
• 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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• 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	1	1.8917	0.2091	0.0954	0.1797	0.177	20.0
No log	2.0	2	1.8909	0.2091	0.0954	0.1797	0.177	20.0
No log	3.0	3	1.8290	0.2386	0.1177	0.2084	0.2081	20.0
No log	4.0	4	1.7999	0.2481	0.1215	0.2151	0.2151	20.0

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1