learning_rate: 3e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 0.1
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	4	2.6363	0.0531
No log	2.0	8	2.6384	0.0708
10.0153	3.0	12	2.6383	0.0619
10.0153	4.0	16	2.6435	0.0619
9.7050	5.0	20	2.6518	0.0265
9.7050	6.0	24	2.6575	0.0354
9.7050	7.0	28	2.6601	0.0531
9.9320	8.0	32	2.6575	0.0442
9.9320	9.0	36	2.6574	0.0442
9.6670	10.0	40	2.6560	0.0531

carlosdonado/my_awesome_mind_model

my_awesome_mind_model