SChem5Labels-google-t5-v1_1-large-inter_model-sorted-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: 0.8994

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
20.7228	1.0	25	24.7182
19.7481	2.0	50	23.4091
19.3221	3.0	75	20.7043
17.2262	4.0	100	15.0872
14.7272	5.0	125	10.1222
12.1186	6.0	150	9.0762
10.3305	7.0	175	8.7090
8.8199	8.0	200	8.4070
8.2346	9.0	225	8.2048
7.9113	10.0	250	8.1018
7.6524	11.0	275	8.0398
7.6476	12.0	300	7.9791
7.4487	13.0	325	7.8957
7.3635	14.0	350	7.7393
7.2677	15.0	375	7.4303
7.0316	16.0	400	7.1862
6.7999	17.0	425	7.0031
6.6811	18.0	450	6.8875
6.6207	19.0	475	6.8224
6.4587	20.0	500	6.7708
6.3888	21.0	525	6.7248
6.3971	22.0	550	6.6744
6.3969	23.0	575	6.3850
0.91	24.0	600	0.7331
0.7237	25.0	625	0.6588
0.6831	26.0	650	0.6276
0.6785	27.0	675	0.6266
0.6673	28.0	700	0.6269
0.6728	29.0	725	0.6230
0.6643	30.0	750	0.6204
0.662	31.0	775	0.6187
0.6664	32.0	800	0.6195
0.6568	33.0	825	0.6180
0.6453	34.0	850	0.6187
0.6619	35.0	875	0.6260
0.6539	36.0	900	0.6168
0.6468	37.0	925	0.6188
0.6567	38.0	950	0.6221
0.6521	39.0	975	0.6172
0.6403	40.0	1000	0.6141
0.6505	41.0	1025	0.6147
0.6419	42.0	1050	0.6174
0.6436	43.0	1075	0.6174
0.6381	44.0	1100	0.6130
0.6527	45.0	1125	0.6144
0.6489	46.0	1150	0.6129
0.6395	47.0	1175	0.6141
0.6483	48.0	1200	0.6174
0.6331	49.0	1225	0.6165
0.6454	50.0	1250	0.6141
0.6356	51.0	1275	0.6140

Framework versions

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