avid-sponge-222

This model is a fine-tuned version of facebook/convnext-base-224 on an unknown dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 256
eval_batch_size: 256
seed: 42
optimizer: Use OptimizerNames.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_ratio: 0.1
num_epochs: 50

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Roc Auc
1.3883	1.0	17	1.3638	0.1615	0.5315	0.1615	0.1912	0.6131
1.3166	2.0	34	1.2597	0.4622	0.7044	0.4622	0.3777	0.7535
1.1663	3.0	51	1.1127	0.4193	0.6134	0.4193	0.4666	0.7785
0.9862	4.0	68	0.8247	0.5508	0.6135	0.5508	0.5663	0.8250
0.8022	5.0	85	0.6888	0.5417	0.6930	0.5417	0.5632	0.8414
0.6688	6.0	102	0.6198	0.5729	0.7049	0.5729	0.5936	0.8612
0.5649	7.0	119	0.5550	0.6406	0.7094	0.6406	0.6527	0.8871
0.4652	8.0	136	0.4299	0.7253	0.7475	0.7253	0.7265	0.9158
0.3992	9.0	153	0.4714	0.7174	0.8030	0.7174	0.7161	0.9347
0.2838	10.0	170	0.3594	0.7734	0.7821	0.7734	0.7703	0.9419
0.2476	11.0	187	0.3371	0.7747	0.8446	0.7747	0.7716	0.9623
0.1873	12.0	204	0.5076	0.7018	0.7728	0.7018	0.7099	0.9409
0.1933	13.0	221	0.2128	0.8490	0.8705	0.8490	0.8479	0.9800
0.1069	14.0	238	0.1805	0.8971	0.9041	0.8971	0.8980	0.9857
0.0932	15.0	255	0.2421	0.8385	0.8782	0.8385	0.8355	0.9894
0.1033	16.0	272	0.1561	0.9258	0.9307	0.9258	0.9247	0.9936
0.0343	17.0	289	0.1213	0.9531	0.9537	0.9531	0.9531	0.9954
0.0603	18.0	306	0.1270	0.9336	0.9358	0.9336	0.9338	0.9929
0.0325	19.0	323	0.0917	0.9661	0.9672	0.9661	0.9663	0.9975
0.028	20.0	340	0.1041	0.9453	0.9492	0.9453	0.9456	0.9968
0.0283	21.0	357	0.0671	0.9674	0.9675	0.9674	0.9674	0.9968
0.0098	22.0	374	0.0663	0.9635	0.9657	0.9635	0.9638	0.9976
0.0175	23.0	391	0.0669	0.9727	0.9730	0.9727	0.9727	0.9973
0.0106	24.0	408	0.1230	0.9622	0.9626	0.9622	0.9623	0.9950
0.0227	25.0	425	0.0757	0.9596	0.9612	0.9596	0.9599	0.9978
0.0183	26.0	442	0.1207	0.9622	0.9631	0.9622	0.9622	0.9955