learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
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
num_epochs: 3

Training Loss	Epoch	Step	Validation Loss
0.3269	0.1188	500	0.2757
0.2531	0.2375	1000	0.2638
0.2245	0.3563	1500	0.2498
0.216	0.4751	2000	0.4060
0.2022	0.5938	2500	0.2778
0.203	0.7126	3000	0.2594
0.1944	0.8314	3500	0.2754
0.178	0.9501	4000	0.2519
0.138	1.0689	4500	0.3387
0.1248	1.1876	5000	0.3581
0.1226	1.3064	5500	0.3078
0.1158	1.4252	6000	0.3009
0.1224	1.5439	6500	0.2841
0.1191	1.6627	7000	0.2869
0.1149	1.7815	7500	0.2897
0.1304	1.9002	8000	0.2990
0.1081	2.0190	8500	0.3510
0.0767	2.1378	9000	0.3429
0.0705	2.2565	9500	0.3920
0.0781	2.3753	10000	0.3734
0.0725	2.4941	10500	0.3804
0.0792	2.6128	11000	0.3614
0.0807	2.7316	11500	0.3483
0.0746	2.8504	12000	0.3596
0.0719	2.9691	12500	0.3575

Nouserenabel/my_awesome_model

my_awesome_model