learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 64
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: linear
lr_scheduler_warmup_steps: 500
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	13	0.8062	0.48	0.3114	0.2304	0.48
No log	2.0	26	0.7773	0.48	0.3114	0.2304	0.48
No log	3.0	39	0.7244	0.49	0.3331	0.7527	0.49
No log	4.0	52	0.6792	0.57	0.4850	0.7732	0.57
No log	5.0	65	0.6408	0.67	0.6550	0.7210	0.67
No log	6.0	78	0.6174	0.7	0.6786	0.7952	0.7
No log	7.0	91	0.6121	0.66	0.6269	0.7760	0.66
No log	8.0	104	0.5098	0.76	0.7592	0.7683	0.76
No log	9.0	117	0.5120	0.77	0.7648	0.8077	0.77
No log	10.0	130	0.4524	0.8	0.8	0.8	0.8

eren2222/bert-sst2

bert-sst2