Mub1532/23144792-fyp-calendar-tasks

mub-model

This model is a fine-tuned version of google/flan-t5-large on a synthetic custom dataset. It achieves the following results on the evaluation set:

• Loss: 0.6100
• Rouge1: 49.1502
• Rouge2: 42.8078
• Rougel: 48.1908
• Rougelsum: 48.113
• Gen Len: 18.95

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.8378	1.0	67	0.6292	49.191	42.8706	48.4855	48.4017	19.1333
0.5958	2.0	134	0.6100	49.1502	42.8078	48.1908	48.113	18.95
0.4737	3.0	201	0.6255	49.1645	42.6374	48.014	47.9673	19.0
0.4099	4.0	268	0.6412	48.7889	42.6784	47.7285	47.7106	19.0
0.3682	5.0	335	0.6680	48.7577	42.3827	47.7169	47.7005	19.0

Framework versions

• Transformers 5.7.0
• Pytorch 2.8.0+cu128
• Datasets 4.8.5
• Tokenizers 0.22.2