4

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: 0.4220
• Precision: 0.5612
• Recall: 0.5878
• F1: 0.5742

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: 4
• 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	0.3262	0.2665	0.4694	0.34
No log	2.0	80	0.2653	0.489	0.5266	0.5071
No log	3.0	120	0.2798	0.5	0.5444	0.5212
No log	4.0	160	0.3016	0.5318	0.5602	0.5456
No log	5.0	200	0.3045	0.5281	0.5562	0.5418
No log	6.0	240	0.3225	0.5085	0.5325	0.5202
No log	7.0	280	0.3325	0.5288	0.5621	0.5449
No log	8.0	320	0.3459	0.5799	0.5799	0.5799
No log	9.0	360	0.3484	0.5356	0.5641	0.5495
No log	10.0	400	0.3547	0.5725	0.5838	0.5781
No log	11.0	440	0.3921	0.556	0.5976	0.576
No log	12.0	480	0.3872	0.5792	0.5917	0.5854
0.169	13.0	520	0.3888	0.5822	0.5937	0.5879
0.169	14.0	560	0.3822	0.5763	0.5957	0.5858
0.169	15.0	600	0.4070	0.5648	0.6016	0.5826
0.169	16.0	640	0.4115	0.5698	0.5957	0.5824
0.169	17.0	680	0.4161	0.5671	0.5917	0.5792
0.169	18.0	720	0.4135	0.5663	0.5897	0.5778
0.169	19.0	760	0.4213	0.5593	0.5858	0.5723
0.169	20.0	800	0.4220	0.5612	0.5878	0.5742

Framework versions

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