SChem5Labels-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: 0.6406

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: 128
• eval_batch_size: 128
• 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
20.8683	1.0	25	25.1590
19.7799	2.0	50	23.9270
19.1307	3.0	75	21.3990
16.8532	4.0	100	15.1632
14.9609	5.0	125	10.2629
12.0411	6.0	150	9.3831
10.5929	7.0	175	8.9785
8.6913	8.0	200	8.6269
8.2386	9.0	225	8.5322
8.0031	10.0	250	8.4694
7.9213	11.0	275	8.3951
7.9263	12.0	300	8.3057
7.742	13.0	325	8.1182
7.5849	14.0	350	7.8158
7.2832	15.0	375	7.5074
7.1925	16.0	400	7.3238
7.0363	17.0	425	7.2074
6.8445	18.0	450	7.1410
6.8735	19.0	475	7.0903
6.7682	20.0	500	7.0306
6.614	21.0	525	6.9683
5.6722	22.0	550	3.0775
0.8621	23.0	575	0.5995
0.6441	24.0	600	0.5709
0.6166	25.0	625	0.5626
0.5931	26.0	650	0.5625
0.5923	27.0	675	0.5618
0.588	28.0	700	0.5583
0.5982	29.0	725	0.5563
0.5837	30.0	750	0.5538
0.5999	31.0	775	0.5536
0.5921	32.0	800	0.5521
0.5878	33.0	825	0.5536
0.5838	34.0	850	0.5534
0.5844	35.0	875	0.5500
0.5853	36.0	900	0.5492
0.5919	37.0	925	0.5481
0.5842	38.0	950	0.5512
0.5883	39.0	975	0.5506
0.5879	40.0	1000	0.5486
0.5811	41.0	1025	0.5505
0.5872	42.0	1050	0.5529

Framework versions

• Transformers 4.34.0
• Pytorch 2.1.0+cu121
• Datasets 2.6.1
• Tokenizers 0.14.1