FingerFriend-t5-small

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

• Loss: 0.7464

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
1.6293	1.0	171	1.1671
1.195	2.0	342	1.0246
1.085	3.0	513	0.9553
1.0207	4.0	684	0.9096
0.9631	5.0	855	0.8782
0.9283	6.0	1026	0.8445
0.8987	7.0	1197	0.8352
0.8716	8.0	1368	0.8123
0.8556	9.0	1539	0.7983
0.8375	10.0	1710	0.7923
0.8239	11.0	1881	0.7757
0.8184	12.0	2052	0.7716
0.8053	13.0	2223	0.7642
0.7929	14.0	2394	0.7647
0.7867	15.0	2565	0.7597
0.7817	16.0	2736	0.7529
0.7751	17.0	2907	0.7506
0.7705	18.0	3078	0.7472
0.7657	19.0	3249	0.7467
0.7665	20.0	3420	0.7464

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3