SBIC-google-t5-v1_1-large-intra_model-dataset-frequency-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
6.9506	1.0	392	7.3966
5.9108	2.0	784	6.2364
0.4499	3.0	1176	0.4162
0.4211	4.0	1568	0.4084
0.4066	5.0	1960	0.3981
0.4305	6.0	2352	0.4011
0.386	7.0	2744	0.4107
0.4028	8.0	3136	0.4002
0.4005	9.0	3528	0.3864
0.387	10.0	3920	0.3870
0.3903	11.0	4312	0.3876
0.3943	12.0	4704	0.3832
0.4032	13.0	5096	0.3837
0.3887	14.0	5488	0.3822
0.38	15.0	5880	0.3804
0.3982	16.0	6272	0.3781
0.3941	17.0	6664	0.3795
0.4079	18.0	7056	0.3783
0.3976	19.0	7448	0.3780
0.3705	20.0	7840	0.3764
0.3833	21.0	8232	0.3771
0.3835	22.0	8624	0.3752
0.3786	23.0	9016	0.3764
0.373	24.0	9408	0.3764
0.364	25.0	9800	0.3754
0.3807	26.0	10192	0.3756
0.3914	27.0	10584	0.3756

Framework versions

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