t5-small-finetuned-poem

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

• Loss: 0.1360

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: 25
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	282	0.1745
0.2047	2.0	564	0.1575
0.2047	3.0	846	0.1455
0.1506	4.0	1128	0.1429
0.1506	5.0	1410	0.1398
0.1383	6.0	1692	0.1385
0.1383	7.0	1974	0.1369
0.1328	8.0	2256	0.1417
0.1292	9.0	2538	0.1383
0.1292	10.0	2820	0.1370
0.1259	11.0	3102	0.1364
0.1259	12.0	3384	0.1342
0.1253	13.0	3666	0.1335
0.1253	14.0	3948	0.1315
0.1218	15.0	4230	0.1408
0.1223	16.0	4512	0.1337
0.1223	17.0	4794	0.1323
0.1204	18.0	5076	0.1372
0.1204	19.0	5358	0.1330
0.1202	20.0	5640	0.1378
0.1202	21.0	5922	0.1405
0.1191	22.0	6204	0.1386
0.1191	23.0	6486	0.1376
0.1193	24.0	6768	0.1343
0.1185	25.0	7050	0.1360

Framework versions

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