DNADebertaK6_Worm

This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.6161

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: 5e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 600001
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.5653	7.26	20000	1.8704
1.8664	14.53	40000	1.7762
1.7803	21.79	60000	1.7429
1.7502	29.06	80000	1.7305
1.7329	36.32	100000	1.7185
1.7191	43.59	120000	1.7073
1.7065	50.85	140000	1.6925
1.6945	58.12	160000	1.6877
1.6862	65.38	180000	1.6792
1.6788	72.65	200000	1.6712
1.6729	79.91	220000	1.6621
1.6679	87.18	240000	1.6608
1.6632	94.44	260000	1.6586
1.6582	101.71	280000	1.6585
1.6551	108.97	300000	1.6564
1.6507	116.24	320000	1.6449
1.6481	123.5	340000	1.6460
1.6448	130.77	360000	1.6411
1.6425	138.03	380000	1.6408
1.6387	145.3	400000	1.6358
1.6369	152.56	420000	1.6373
1.6337	159.83	440000	1.6364
1.6312	167.09	460000	1.6303
1.6298	174.36	480000	1.6346
1.6273	181.62	500000	1.6272
1.6244	188.88	520000	1.6268
1.6225	196.15	540000	1.6295
1.6207	203.41	560000	1.6206
1.6186	210.68	580000	1.6277
1.6171	217.94	600000	1.6161

Framework versions

• Transformers 4.19.2
• Pytorch 1.11.0
• Datasets 2.2.2
• Tokenizers 0.12.1