learning_rate: 0.0005
train_batch_size: 8
eval_batch_size: 8
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: cosine
num_epochs: 2

Training Loss	Epoch	Step	Validation Loss
5.0563	0.1049	200	4.6481
4.1767	0.2098	400	4.1629
3.4097	0.3146	600	3.5324
2.8577	0.4195	800	3.0339
2.3377	0.5244	1000	2.4324
1.9681	0.6293	1200	2.1695
1.5335	0.7341	1400	1.8875
1.2387	0.8390	1600	1.7929
1.0361	0.9439	1800	1.8399
0.8009	1.0488	2000	1.5640
0.6279	1.1536	2200	1.7252
0.5633	1.2585	2400	1.4810
0.4755	1.3634	2600	1.3747
0.4306	1.4683	2800	1.4690
0.3499	1.5732	3000	1.4179
0.3671	1.6780	3200	1.3020
0.2884	1.7829	3400	1.4163
0.4006	1.8878	3600	1.3823
0.2706	1.9927	3800	1.3739

denisdrobs/ModernBERT-large-clinc_oos

ModernBERT-large-clinc_oos