learning_rate: 0.0005
train_batch_size: 16
eval_batch_size: 16
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: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
4.2022	1.0	125	3.8106	0.132	0.1190	0.1385	0.0908
2.6442	2.0	250	2.2022	0.405	0.4258	0.4145	0.3772
2.1982	3.0	375	1.7984	0.495	0.5307	0.5046	0.4798
1.7721	4.0	500	1.5778	0.557	0.5734	0.5654	0.5452
1.6367	5.0	625	1.4217	0.599	0.6173	0.6007	0.5859
1.4437	6.0	750	1.3486	0.63	0.6574	0.6330	0.6214
1.3602	7.0	875	1.2996	0.635	0.6554	0.6363	0.6242
1.3112	8.0	1000	1.2792	0.643	0.6487	0.6458	0.6289
1.2492	9.0	1125	1.2267	0.66	0.6699	0.6605	0.6481
1.1791	10.0	1250	1.2563	0.657	0.6605	0.6572	0.6430

zkdeng/10-resnet-50-finetuned-spiderTraining100-100

10-resnet-50-finetuned-spiderTraining100-100