SChem5Labels-google-t5-v1_1-large-intra_model-shuffle-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: 1.2617

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
20.6863	1.0	25	23.6720
19.4335	2.0	50	19.9692
18.2125	3.0	75	14.6175
16.4919	4.0	100	11.6548
15.9533	5.0	125	10.4693
14.4388	6.0	150	9.6944
12.4697	7.0	175	9.3650
10.5569	8.0	200	9.1423
9.2725	9.0	225	9.0209
8.4222	10.0	250	8.8843
8.3219	11.0	275	8.8191
8.3309	12.0	300	8.7311
8.1401	13.0	325	8.5687
8.0179	14.0	350	8.2683
7.7326	15.0	375	7.9618
7.606	16.0	400	7.7520
7.4445	17.0	425	7.6258
7.2501	18.0	450	7.5502
7.2915	19.0	475	7.5063
7.2094	20.0	500	7.4555
7.0879	21.0	525	7.3983
7.1268	22.0	550	7.3460
6.623	23.0	575	0.9955
1.0983	24.0	600	0.9945
1.0196	25.0	625	0.9727
0.9822	26.0	650	0.9680
0.9827	27.0	675	0.9678
0.9832	28.0	700	0.9646
0.9983	29.0	725	0.9679
0.982	30.0	750	0.9610
1.0109	31.0	775	0.9632
0.9972	32.0	800	0.9628
0.9906	33.0	825	0.9634
0.9886	34.0	850	0.9634
0.9811	35.0	875	0.9649

Framework versions

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