t5-small-shShootingKP

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.6665
• Rouge1: 34.5267
• Rouge2: 28.0947
• Rougel: 34.5277
• Rougelsum: 34.5954
• Gen Len: 6.4385

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.1889	1.0	6056	1.7462	34.927	28.162	34.9525	35.0176	7.2062
1.0076	2.0	12112	1.7262	34.3953	27.6704	34.393	34.4491	6.8452
0.9798	3.0	18168	1.6861	34.5625	28.0528	34.5541	34.6322	6.6332
0.9324	4.0	24224	1.7051	34.2389	27.9601	34.2154	34.3167	6.8740
0.8892	5.0	30280	1.6665	34.5267	28.0947	34.5277	34.5954	6.4385
0.809	6.0	36336	1.7787	34.0937	27.661	34.0887	34.1515	6.6721
0.7897	7.0	42392	1.7404	33.9073	27.6347	33.9084	33.9455	6.5274
0.7302	8.0	48448	1.7334	33.8327	27.5953	33.836	33.8535	6.4447

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2