You can deploy this model and start earning money today!

sercetexam9/
cs221-deberta-base-multi-label-classifier-eng-finetuned-30-epochs-tapt

Name: cs221-deberta-base-multi-label-classifier-eng-finetuned-30-epochs-tapt
Availability: InStock

Views

No views yet

cs221-deberta-base-multi-label-classifier-eng-finetuned-30-epochs-tapt

This model is a fine-tuned version of Azma-AI/deberta-base-multi-label-classifier on the None dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 30

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.568	1.0	73	0.4940	0.5344	0.6753	0.2513
0.3996	2.0	146	0.4065	0.7004	0.7781	0.3865
0.3133	3.0	219	0.3520	0.7582	0.8224	0.4627
0.2422	4.0	292	0.3428	0.7538	0.8161	0.4627
0.181	5.0	365	0.3690	0.7634	0.8251	0.4835
0.1492	6.0	438	0.3650	0.7729	0.8283	0.5026
0.1196	7.0	511	0.3871	0.7764	0.8327	0.5095
0.0955	8.0	584	0.4034	0.7761	0.8341	0.4957
0.0677	9.0	657	0.4269	0.7743	0.8294	0.4957
0.0591	10.0	730	0.4565	0.7623	0.8222	0.4714
0.0349	11.0	803	0.4820	0.7787	0.8349	0.4974
0.0281	12.0	876	0.5068	0.7736	0.8338	0.4766
0.0211	13.0	949	0.5179	0.7792	0.8358	0.4905
0.0176	14.0	1022	0.5384	0.7747	0.8320	0.4853
0.0188	15.0	1095	0.5407	0.7816	0.8374	0.4887
0.0123	16.0	1168	0.5577	0.7733	0.8286	0.4887
0.0103	17.0	1241	0.5766	0.7760	0.8337	0.4835
0.0093	18.0	1314	0.5886	0.7757	0.8331	0.4783
0.0067	19.0	1387	0.5877	0.7797	0.8371	0.4835