learning_rate: 3e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
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_ratio: 0.1
num_epochs: 40

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1097	1.0	11	0.1053	1.0
0.1451	2.0	22	0.0801	1.0
0.0707	3.0	33	0.4818	0.8095
0.123	4.0	44	0.3445	0.9048
0.0296	5.0	55	0.5274	0.8571
0.0241	6.0	66	0.0181	1.0
0.2093	7.0	77	0.0144	1.0
0.0162	8.0	88	0.0119	1.0
0.0133	9.0	99	0.0095	1.0
0.0091	10.0	110	0.0078	1.0
0.0086	11.0	121	0.0065	1.0
0.0074	12.0	132	0.0056	1.0
0.0065	13.0	143	0.0048	1.0
0.0057	14.0	154	0.0043	1.0
0.0044	15.0	165	0.0038	1.0
0.0044	16.0	176	0.0034	1.0
0.0041	17.0	187	0.0031	1.0
0.0037	18.0	198	0.0028	1.0
0.0035	19.0	209	0.0026	1.0
0.0028	20.0	220	0.0024	1.0
0.003	21.0	231	0.0023	1.0
0.0028	22.0	242	0.0022	1.0
0.0027	23.0	253	0.0020	1.0
0.0025	24.0	264	0.0019	1.0
0.0022	25.0	275	0.0018	1.0
0.0023	26.0	286	0.0018	1.0
0.0022	27.0	297	0.0017	1.0
0.0021	28.0	308	0.0017	1.0
0.0021	29.0	319	0.0016	1.0
0.0018	30.0	330	0.0016	1.0
0.002	31.0	341	0.0015	1.0
0.0019	32.0	352	0.0015	1.0
0.0019	33.0	363	0.0015	1.0
0.0019	34.0	374	0.0015	1.0
0.0017	35.0	385	0.0015	1.0
0.0018	36.0	396	0.0014	1.0
0.0017	36.3810	400	0.0014	1.0

Rukh29/my_april_12_model

my_april_12_model