SBIC-google-t5-v1_1-large-intra_model-shuffle-human_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
7.7989	1.0	392	8.3528
0.6988	2.0	784	0.5020
0.5046	3.0	1176	0.4843
0.5099	4.0	1568	0.4706
0.4526	5.0	1960	0.4291
0.469	6.0	2352	0.4223
0.4408	7.0	2744	0.4136
0.4763	8.0	3136	0.4142
0.446	9.0	3528	0.4116
0.4315	10.0	3920	0.4035
0.3821	11.0	4312	0.4077
0.4399	12.0	4704	0.4009
0.4285	13.0	5096	0.3962
0.3908	14.0	5488	0.3931
0.3887	15.0	5880	0.3922
0.398	16.0	6272	0.3862
0.3964	17.0	6664	0.3931
0.3939	18.0	7056	0.3892
0.372	19.0	7448	0.3824
0.4364	20.0	7840	0.3779
0.3722	21.0	8232	0.3760
0.343	22.0	8624	0.3804
0.3946	23.0	9016	0.3756
0.3899	24.0	9408	0.3756
0.4195	25.0	9800	0.3762
0.4072	26.0	10192	0.3758
0.379	27.0	10584	0.3758

Framework versions

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