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
lr_scheduler_warmup_steps: 0.1
num_epochs: 3

Training Loss	Epoch	Step	Validation Loss	Mae	Rmse	R Squared
0.0708	0.32	1000	0.0623	0.2129	0.2497	0.0138
0.0642	0.64	2000	0.0595	0.206	0.2439	0.0592
0.0617	0.96	3000	0.0593	0.2036	0.2435	0.0621
0.0573	1.28	4000	0.0594	0.2017	0.2436	0.061
0.0563	1.6	5000	0.0577	0.202	0.2403	0.0864
0.0596	1.92	6000	0.0571	0.2002	0.2389	0.0971
0.0540	2.24	7000	0.0577	0.1993	0.2401	0.0878
0.0522	2.56	8000	0.0581	0.1993	0.241	0.0813
0.0529	2.88	9000	0.0586	0.1999	0.2421	0.0727

EvelienUU/deberta-valence-title_training1

deberta-valence-title_training1