SChem5Labels-google-t5-v1_1-large-intra_model-shuffle-model_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: 1.1455

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
20.1373	1.0	25	23.9902
19.3278	2.0	50	23.0330
18.61	3.0	75	19.3564
16.6643	4.0	100	12.7192
15.008	5.0	125	10.2820
12.6828	6.0	150	9.4364
11.5627	7.0	175	9.0709
9.5974	8.0	200	8.8406
8.7995	9.0	225	8.5809
8.1331	10.0	250	8.4198
7.9315	11.0	275	8.3298
7.8545	12.0	300	8.2475
7.7219	13.0	325	8.1188
7.4693	14.0	350	7.8444
7.3416	15.0	375	7.5661
6.958	16.0	400	7.3479
6.9627	17.0	425	7.2154
6.9852	18.0	450	7.1438
6.7137	19.0	475	7.0960
6.7186	20.0	500	7.0620
6.704	21.0	525	7.0248
6.6092	22.0	550	6.9869
6.665	23.0	575	6.8663
1.2056	24.0	600	1.1299
1.1741	25.0	625	1.1157
1.1548	26.0	650	1.1137
1.1387	27.0	675	1.1143
1.1437	28.0	700	1.1079
1.136	29.0	725	1.1064
1.1503	30.0	750	1.1101
1.1428	31.0	775	1.1096
1.1365	32.0	800	1.1120
1.151	33.0	825	1.1133
1.1469	34.0	850	1.1090

Framework versions

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