t5-small-pakQuakeKP

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

• Loss: 1.4801
• Rouge1: 43.5664
• Rouge2: 29.643
• Rougel: 43.4587
• Rougelsum: 43.393
• Gen Len: 6.0567

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
1.1732	1.0	6086	1.4855	44.3428	30.4888	44.2809	44.238	6.4530
1.0189	2.0	12172	1.4801	43.5664	29.643	43.4587	43.393	6.0567
0.9379	3.0	18258	1.5378	43.8433	30.4692	43.6996	43.6864	6.9653
0.8248	4.0	24344	1.5389	43.8048	29.4327	43.7467	43.6956	6.5986
0.832	5.0	30430	1.5519	44.9305	30.0435	44.8287	44.7814	6.5894
0.732	6.0	36516	1.5944	42.8063	28.8826	42.7294	42.6553	6.4045
0.778	7.0	42602	1.5845	44.1877	29.1966	44.0738	44.0379	6.4285
0.702	8.0	48688	1.6057	44.2274	29.3567	44.1037	44.0794	6.6088

Framework versions

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