qaharoldv1

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

• Loss: 0.1674
• Rouge1: 0.9279
• Rouge2: 0.8593
• Rougel: 0.9205
• Gen Len: 70.0435

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: 0.0004
• train_batch_size: 12
• eval_batch_size: 12
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Gen Len
No log	0.76	100	0.2700	0.8771	0.7606	0.8652	70.0435
No log	1.52	200	0.2165	0.9031	0.8152	0.895	70.0435
No log	2.27	300	0.2012	0.905	0.818	0.8978	70.0435
No log	3.03	400	0.1828	0.9113	0.8278	0.9027	70.0435
No log	3.79	500	0.1774	0.9095	0.8246	0.9013	70.0435
No log	4.55	600	0.1732	0.9145	0.8371	0.9084	70.0435
No log	5.3	700	0.1654	0.9177	0.8423	0.9101	70.0435
No log	6.06	800	0.1694	0.9187	0.8397	0.9115	70.0435
No log	6.82	900	0.1690	0.92	0.8467	0.913	70.0435
No log	7.58	1000	0.1674	0.9198	0.846	0.9129	70.0435
No log	8.33	1100	0.1664	0.9262	0.8552	0.919	70.0435
No log	9.09	1200	0.1682	0.9267	0.8568	0.9195	70.0435
No log	9.85	1300	0.1674	0.9279	0.8593	0.9205	70.0435

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.2