learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
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
num_epochs: 12

Training Loss	Epoch	Step	Validation Loss	Rmse
455.0487	1.0	1610	423.3263	20.5749
315.5867	2.0	3220	368.3743	19.1931
306.8605	3.0	4830	335.5825	18.3189
273.2899	4.0	6440	349.3475	18.6908
230.919	5.0	8050	319.4332	17.8727
213.662	6.0	9660	305.9742	17.4921
176.3176	7.0	11270	325.6266	18.0451
156.6416	8.0	12880	296.1061	17.2077
139.9903	9.0	14490	293.8068	17.1408
153.1883	10.0	16100	288.1454	16.9748
135.362	11.0	17710	286.8939	16.9379
111.2071	12.0	19320	282.4043	16.8049

chilllnuu/finetuning2

finetuning2