SChem5Labels-google-t5-v1_1-large-inter_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: 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: 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
19.9516	1.0	25	23.6924
18.985	2.0	50	21.9715
18.5733	3.0	75	19.0631
16.456	4.0	100	14.6944
14.6058	5.0	125	10.3972
11.384	6.0	150	8.9604
10.1534	7.0	175	8.6228
8.6467	8.0	200	8.4688
8.2161	9.0	225	8.3154
7.9229	10.0	250	8.2324
7.8179	11.0	275	8.1809
7.7843	12.0	300	8.0948
7.5714	13.0	325	7.9681
7.2487	14.0	350	7.7352
7.2237	15.0	375	7.4691
6.9821	16.0	400	7.2523
6.8667	17.0	425	7.1151
6.8551	18.0	450	7.0423
6.7468	19.0	475	6.9926
6.6918	20.0	500	6.9466
6.4912	21.0	525	6.9125
6.5704	22.0	550	6.8707
6.4854	23.0	575	6.8123
3.9521	24.0	600	1.5605
1.16	25.0	625	1.0195
1.0643	26.0	650	1.0007
1.0417	27.0	675	1.0069
1.04	28.0	700	0.9974
1.0347	29.0	725	0.9974
1.0375	30.0	750	1.0006
1.0382	31.0	775	0.9958
1.0347	32.0	800	0.9999
1.0198	33.0	825	1.0013
1.0092	34.0	850	1.0044
1.0376	35.0	875	1.0045
1.0245	36.0	900	0.9974

Framework versions

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