learning_rate: 0.0001
train_batch_size: 128
eval_batch_size: 128
seed: 42
distributed_type: multi-GPU
num_devices: 2
total_train_batch_size: 256
total_eval_batch_size: 256
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: 10000
training_steps: 55177

Training Loss	Epoch	Step	Validation Loss
6.314	0.0906	5000	6.2932
5.2109	0.1812	10000	4.9949
3.2468	0.2718	15000	3.0871
2.922	0.3625	20000	2.7691
2.7663	0.4531	25000	2.6115
2.6594	0.5437	30000	2.5044
2.5777	0.6343	35000	2.4308
2.5149	0.7249	40000	2.3741
2.4536	0.8155	45000	2.3367
2.4271	0.9062	50000	2.3103
2.4554	0.9968	55000	2.2934

shirzady1934/results5

results5