t5-base-finetuned-poemV2

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

• Loss: 0.1041

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	282	0.1235
0.1391	2.0	564	0.1177
0.1391	3.0	846	0.1142
0.1209	4.0	1128	0.1133
0.1209	5.0	1410	0.1106
0.1141	6.0	1692	0.1137
0.1141	7.0	1974	0.1099
0.1113	8.0	2256	0.1059
0.1088	9.0	2538	0.1064
0.1088	10.0	2820	0.1070
0.1087	11.0	3102	0.1059
0.1087	12.0	3384	0.1054
0.1059	13.0	3666	0.1053
0.1059	14.0	3948	0.1050
0.1052	15.0	4230	0.1057
0.1049	16.0	4512	0.1044
0.1049	17.0	4794	0.1049
0.1035	18.0	5076	0.1044
0.1035	19.0	5358	0.1039
0.1034	20.0	5640	0.1041

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1