3

This model is a fine-tuned version of google-t5/t5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4228
• Precision: 0.5633
• Recall: 0.5878
• F1: 0.5753

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: 0.0003
• train_batch_size: 32
• eval_batch_size: 32
• seed: 3
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
No log	1.0	40	0.3359	0.3503	0.3807	0.3648
No log	2.0	80	0.2741	0.4154	0.4892	0.4493
No log	3.0	120	0.2745	0.5337	0.5306	0.5321
No log	4.0	160	0.2924	0.514	0.5779	0.5441
No log	5.0	200	0.2881	0.5224	0.574	0.547
No log	6.0	240	0.3193	0.5667	0.5779	0.5723
No log	7.0	280	0.3285	0.582	0.5878	0.5849
No log	8.0	320	0.3365	0.5668	0.5858	0.5761
No log	9.0	360	0.3622	0.5585	0.5838	0.5709
No log	10.0	400	0.3638	0.5584	0.5937	0.5755
No log	11.0	440	0.3779	0.5471	0.5838	0.5649
No log	12.0	480	0.3725	0.5605	0.5661	0.5633
0.1667	13.0	520	0.3873	0.5662	0.5819	0.5739
0.1667	14.0	560	0.4065	0.548	0.5858	0.5663
0.1667	15.0	600	0.4097	0.5642	0.5897	0.5767
0.1667	16.0	640	0.4095	0.5687	0.5878	0.5781
0.1667	17.0	680	0.4182	0.5508	0.5878	0.5687
0.1667	18.0	720	0.4195	0.5634	0.5957	0.5791
0.1667	19.0	760	0.4189	0.5684	0.5897	0.5789
0.1667	20.0	800	0.4228	0.5633	0.5878	0.5753

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1