***** Running Evaluation *****
Num examples = 1812
Batch size = 2
Validation Results:
eval_loss: 0.6362
eval_accuracy: 0.6394
eval_f1: 0.6393
eval_precision: 0.6392
eval_recall: 0.6394
eval_runtime: 87.7347
eval_samples_per_second: 20.6420
eval_steps_per_second: 10.3270
epoch: 1.0000
Evaluating on test set...
Test Results:
eval_loss: 0.6437
eval_accuracy: 0.6209
eval_f1: 0.6205
eval_precision: 0.6212
eval_recall: 0.6209
eval_runtime: 89.4202
eval_samples_per_second: 20.2640
eval_steps_per_second: 10.1320
epoch: 1.0000