SBIC-google-t5-v1_1-large-inter_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
7.6679	1.0	392	8.1733
3.1285	2.0	784	0.4610
0.4164	3.0	1176	0.3793
0.4073	4.0	1568	0.3457
0.3553	5.0	1960	0.3263
0.3684	6.0	2352	0.3160
0.3346	7.0	2744	0.3073
0.3482	8.0	3136	0.3045
0.3261	9.0	3528	0.3016
0.3255	10.0	3920	0.2960
0.2794	11.0	4312	0.2951
0.318	12.0	4704	0.2920
0.3072	13.0	5096	0.2875
0.2872	14.0	5488	0.2819
0.2912	15.0	5880	0.2774
0.2954	16.0	6272	0.2762
0.2792	17.0	6664	0.2775
0.2763	18.0	7056	0.2736
0.2573	19.0	7448	0.2715
0.3148	20.0	7840	0.2647
0.2599	21.0	8232	0.2621
0.2405	22.0	8624	0.2624
0.2785	23.0	9016	0.2609
0.2652	24.0	9408	0.2601
0.2977	25.0	9800	0.2594
0.2829	26.0	10192	0.2593
0.2757	27.0	10584	0.2593
0.264	28.0	10976	0.2593
0.2758	29.0	11368	0.2593

Framework versions

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