SBIC-google-t5-v1_1-large-inter_model-shuffle-model_annots_str

This model is a fine-tuned version of google/t5-v1_1-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: nan

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 200

Training results

Training Loss	Epoch	Step	Validation Loss
7.0299	1.0	392	7.1712
5.824	2.0	784	6.1194
0.6581	3.0	1176	0.6618
0.7217	4.0	1568	0.6473
0.695	5.0	1960	0.6467
0.7119	6.0	2352	0.6469
0.658	7.0	2744	0.6460
0.6706	8.0	3136	0.6381
0.6564	9.0	3528	0.6413
0.6765	10.0	3920	0.6368
0.6722	11.0	4312	0.6359
0.6749	12.0	4704	0.6369
0.6858	13.0	5096	0.6381
0.6491	14.0	5488	0.6354
0.6631	15.0	5880	0.6341
0.6648	16.0	6272	0.6325
0.6538	17.0	6664	0.6318
0.6389	18.0	7056	0.6341
0.679	19.0	7448	0.6315
0.6495	20.0	7840	0.6314
0.6674	21.0	8232	0.6313
0.6358	22.0	8624	0.6308
0.6215	23.0	9016	0.6305
0.6449	24.0	9408	0.6303
0.6243	25.0	9800	0.6304
0.6454	26.0	10192	0.6303
0.6413	27.0	10584	0.6303
0.627	28.0	10976	0.6303
0.672	29.0	11368	0.6303
0.6064	30.0	11760	0.6303

Framework versions

• Transformers 4.34.0
• Pytorch 2.1.0+cu121
• Datasets 2.14.5
• Tokenizers 0.14.1