learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use 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: 100
training_steps: 1500
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.5723	5.1613	100	0.5148
0.5244	10.3226	200	0.4888
0.5008	15.4839	300	0.4817
0.4873	20.6452	400	0.4742
0.4769	25.8065	500	0.4700
0.4741	30.9677	600	0.4667
0.4612	36.1290	700	0.4600
0.4522	41.2903	800	0.4593
0.4526	46.4516	900	0.4601
0.4447	51.6129	1000	0.4584
0.4489	56.7742	1100	0.4604
0.4373	61.9355	1200	0.4577
0.4332	67.0968	1300	0.4592
0.4338	72.2581	1400	0.4598
0.4328	77.4194	1500	0.4588

Mohsen21/The_700_data_model

The_700_data_model