SBIC-google-t5-v1_1-large-inter_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
7.244	1.0	392	7.3922
5.8979	2.0	784	6.1032
0.4199	3.0	1176	0.4008
0.4443	4.0	1568	0.4013
0.4228	5.0	1960	0.3946
0.4336	6.0	2352	0.3940
0.4081	7.0	2744	0.4408
0.4224	8.0	3136	0.4507
0.3985	9.0	3528	0.3976
0.4133	10.0	3920	0.3935
0.4117	11.0	4312	0.3920
0.4209	12.0	4704	0.3963
0.4197	13.0	5096	0.3932
0.3975	14.0	5488	0.3915
0.3912	15.0	5880	0.3914
0.4029	16.0	6272	0.3903
0.3973	17.0	6664	0.3904
0.388	18.0	7056	0.3926
0.4023	19.0	7448	0.3908
0.3911	20.0	7840	0.3893
0.4102	21.0	8232	0.3895
0.396	22.0	8624	0.3891
0.3899	23.0	9016	0.3895
0.3941	24.0	9408	0.3885
0.3813	25.0	9800	0.3890
0.3883	26.0	10192	0.3889
0.4008	27.0	10584	0.3889
0.3892	28.0	10976	0.3889
0.4184	29.0	11368	0.3889

Framework versions

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