learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
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: 32
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.5615	1.6129	100	0.4912	0.7664	0.7472	0.7879	0.7664
0.4755	3.2258	200	0.4393	0.8186	0.8181	0.8226	0.8186
0.3978	4.8387	300	0.3931	0.8345	0.8344	0.8356	0.8345
0.364	6.4516	400	0.3698	0.8413	0.8392	0.8395	0.8413
0.338	8.0645	500	0.4049	0.8345	0.8358	0.8421	0.8345
0.3049	9.6774	600	0.4135	0.8299	0.8268	0.8385	0.8299
0.2644	11.2903	700	0.3848	0.8413	0.8423	0.8499	0.8413
0.234	12.9032	800	0.3597	0.8685	0.8703	0.8770	0.8685
0.1951	14.5161	900	0.3355	0.8798	0.8807	0.8830	0.8798
0.1935	16.1290	1000	0.4081	0.8390	0.8410	0.8503	0.8390
0.1604	17.7419	1100	0.3828	0.8730	0.8737	0.8753	0.8730
0.144	19.3548	1200	0.3970	0.8571	0.8578	0.8593	0.8571
0.1257	20.9677	1300	0.3712	0.8730	0.8723	0.8729	0.8730
0.1036	22.5806	1400	0.3932	0.8685	0.8688	0.8703	0.8685
0.1094	24.1935	1500	0.3800	0.8798	0.8790	0.8805	0.8798
0.0836	25.8065	1600	0.3981	0.8662	0.8674	0.8706	0.8662
0.0803	27.4194	1700	0.4010	0.8707	0.8724	0.8779	0.8707
0.0789	29.0323	1800	0.3938	0.8753	0.8762	0.8786	0.8753
0.0872	30.6452	1900	0.4085	0.8662	0.8675	0.8713	0.8662

BTX24/hiera-finetuned-stroke-all-pat

hiera-finetuned-stroke-all-pat