SBIC-google-t5-v1_1-large-inter_model-frequency-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: 0.3635

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
7.7146	1.0	392	8.2917
0.5241	2.0	784	0.4371
0.4312	3.0	1176	0.4278
0.4359	4.0	1568	0.4084
0.3616	5.0	1960	0.3634
0.397	6.0	2352	0.3568
0.3647	7.0	2744	0.3387
0.3936	8.0	3136	0.3365
0.3614	9.0	3528	0.3341
0.3403	10.0	3920	0.3278
0.3048	11.0	4312	0.3227
0.347	12.0	4704	0.3218
0.337	13.0	5096	0.3136
0.3166	14.0	5488	0.3112
0.3021	15.0	5880	0.3119
0.3155	16.0	6272	0.3051
0.2965	17.0	6664	0.3054
0.3196	18.0	7056	0.2989
0.2857	19.0	7448	0.2964
0.3776	20.0	7840	0.2905
0.288	21.0	8232	0.2889
0.2632	22.0	8624	0.2911
0.3014	23.0	9016	0.2862
0.3015	24.0	9408	0.2869
0.3254	25.0	9800	0.2858
0.3178	26.0	10192	0.2860
0.2994	27.0	10584	0.2860
0.2893	28.0	10976	0.2860

Framework versions

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