This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the Blastocyst_ICM dataset. It achieves the following results on the evaluation set:

Loss: 0.4171
Accuracy: 0.8571

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: 0.0002
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 60
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6635	0.7874	100	0.6705	0.7619
0.6585	1.5748	200	0.4977	0.8571
0.8002	2.3622	300	0.6194	0.8095
0.6907	3.1496	400	0.6097	0.7619
0.5806	3.9370	500	0.6073	0.7143
0.6059	4.7244	600	0.4171	0.8571
0.5804	5.5118	700	0.4862	0.8095
0.6223	6.2992	800	0.4292	0.8095
0.6696	7.0866	900	0.4574	0.8095
0.5269	7.8740	1000	0.4643	0.8571
0.5089	8.6614	1100	0.4634	0.8095
0.4782	9.4488	1200	0.5434	0.8095
0.5426	10.2362	1300	0.6587	0.6667
0.5604	11.0236	1400	0.4834	0.7143
0.627	11.8110	1500	0.5787	0.7619
0.4389	12.5984	1600	0.6285	0.7619
0.3936	13.3858	1700	0.7870	0.7619
0.4023	14.1732	1800	0.6466	0.8095
0.4683	14.9606	1900	0.5086	0.7619
0.4502	15.7480	2000	0.4940	0.8095
0.47	16.5354	2100	0.6389	0.8095
0.4109	17.3228	2200	0.4713	0.8571
0.4654	18.1102	2300	0.6457	0.7619
0.3359	18.8976	2400	0.4706	0.8095
0.3343	19.6850	2500	0.6813	0.8095
0.4359	20.4724	2600	0.8620	0.7143
0.446	21.2598	2700	0.5914	0.9048
0.2901	22.0472	2800	0.8846	0.8095
0.3261	22.8346	2900	0.5528	0.8571
0.4159	23.6220	3000	0.6383	0.8095
0.3056	24.4094	3100	0.8316	0.8095
0.27	25.1969	3200	1.0901	0.7619
0.299	25.9843	3300	0.9170	0.7143
0.2433	26.7717	3400	1.0046	0.8095
0.2623	27.5591	3500	0.8359	0.7619
0.2526	28.3465	3600	0.5864	0.8571
0.3307	29.1339	3700	0.6282	0.8571
0.2038	29.9213	3800	1.0462	0.7619
0.3419	30.7087	3900	1.2281	0.7143
0.2625	31.4961	4000	0.9750	0.7619
0.1707	32.2835	4100	1.0191	0.8095
0.2046	33.0709	4200	0.9401	0.8095
0.2009	33.8583	4300	0.9374	0.8571
0.222	34.6457	4400	1.1820	0.8095
0.2469	35.4331	4500	0.8827	0.8571
0.1348	36.2205	4600	0.8871	0.8095
0.2494	37.0079	4700	0.8910	0.8095
0.1272	37.7953	4800	0.9666	0.8095
0.1682	38.5827	4900	0.8490	0.8571
0.1495	39.3701	5000	0.9831	0.8571
0.174	40.1575	5100	1.2082	0.7619
0.1375	40.9449	5200	1.2987	0.7619
0.1043	41.7323	5300	1.1446	0.8095
0.2958	42.5197	5400	1.3286	0.7143
0.1882	43.3071	5500	1.1686	0.8095
0.1322	44.0945	5600	1.3669	0.7619
0.1551	44.8819	5700	1.2882	0.7619
0.1749	45.6693	5800	1.2481	0.8095
0.1064	46.4567	5900	1.3224	0.8095
0.1947	47.2441	6000	1.1225	0.8095
0.1495	48.0315	6100	1.5170	0.7143
0.2192	48.8189	6200	0.9928	0.8571
0.1303	49.6063	6300	1.0310	0.8095
0.2188	50.3937	6400	1.0219	0.8095
0.1485	51.1811	6500	1.0695	0.8095
0.1065	51.9685	6600	1.2479	0.8095
0.1731	52.7559	6700	1.1878	0.8095
0.2507	53.5433	6800	1.1535	0.7619
0.1191	54.3307	6900	1.0544	0.8571
0.1048	55.1181	7000	1.1502	0.8095
0.1715	55.9055	7100	1.2187	0.8095
0.125	56.6929	7200	1.2635	0.8095
0.1022	57.4803	7300	1.2571	0.8095
0.0987	58.2677	7400	1.2676	0.8095
0.0761	59.0551	7500	1.2635	0.8095
0.1184	59.8425	7600	1.2629	0.8095

Framework versions

Transformers 4.41.0
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

ayushi12/finetuned-Blastocyst_ICM

finetuned-Blastocyst_ICM

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

ayushi12/
finetuned-Blastocyst_ICM