SBIC-google-t5-v1_1-large-intra_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
6.8483	1.0	392	7.2176
5.8232	2.0	784	6.1652
0.842	3.0	1176	0.7614
0.7929	4.0	1568	0.7592
0.7685	5.0	1960	0.7490
0.8076	6.0	2352	0.7472
0.7376	7.0	2744	0.7534
0.7686	8.0	3136	0.7481
0.769	9.0	3528	0.7376
0.7466	10.0	3920	0.7362
0.7677	11.0	4312	0.7305
0.7435	12.0	4704	0.7307
0.773	13.0	5096	0.7294
0.751	14.0	5488	0.7281
0.7256	15.0	5880	0.7233
0.7545	16.0	6272	0.7235
0.7427	17.0	6664	0.7221
0.7851	18.0	7056	0.7219
0.758	19.0	7448	0.7217
0.7081	20.0	7840	0.7205
0.7336	21.0	8232	0.7190
0.7582	22.0	8624	0.7187
0.7475	23.0	9016	0.7186
0.7403	24.0	9408	0.7185
0.7151	25.0	9800	0.7182
0.7322	26.0	10192	0.7182
0.7483	27.0	10584	0.7182
0.7388	28.0	10976	0.7182
0.7496	29.0	11368	0.7182

Framework versions

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