SBIC-google-t5-v1_1-large-intra_model-sorted-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
7.6138	1.0	392	8.1643
0.4543	2.0	784	0.3929
0.3959	3.0	1176	0.3619
0.3931	4.0	1568	0.3631
0.3428	5.0	1960	0.3201
0.3521	6.0	2352	0.3129
0.3306	7.0	2744	0.3007
0.348	8.0	3136	0.2991
0.3254	9.0	3528	0.2963
0.3055	10.0	3920	0.2918
0.2827	11.0	4312	0.2891
0.3178	12.0	4704	0.2854
0.2993	13.0	5096	0.2815
0.2825	14.0	5488	0.2779
0.2974	15.0	5880	0.2824
0.2857	16.0	6272	0.2691
0.2684	17.0	6664	0.2795
0.2779	18.0	7056	0.2722
0.2578	19.0	7448	0.2625
0.3068	20.0	7840	0.2582
0.2484	21.0	8232	0.2576
0.2334	22.0	8624	0.2590
0.2748	23.0	9016	0.2548
0.2593	24.0	9408	0.2575
0.2752	25.0	9800	0.2552
0.2683	26.0	10192	0.2550
0.263	27.0	10584	0.2550
0.2605	28.0	10976	0.2550

Framework versions

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