learning_rate: 2e-05
train_batch_size: 128
eval_batch_size: 128
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: 865
num_epochs: 15

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	345	0.2005	0.8655	0.8665
0.2274	2.0	690	0.1840	0.8833	0.8837
0.2274	3.0	1035	0.1690	0.9020	0.9013
0.1639	4.0	1380	0.1622	0.9008	0.9019
0.1639	5.0	1725	0.1623	0.9027	0.9031
0.1267	6.0	2070	0.1671	0.9081	0.9085
0.1267	7.0	2415	0.1669	0.9084	0.9087
0.1026	8.0	2760	0.1850	0.9049	0.9055
0.1026	9.0	3105	0.2107	0.9060	0.9068
0.0852	10.0	3450	0.2308	0.9017	0.9024

ttqdunggg/hybrid_lexical_hosting_64_15_v5_8_7_2026

hybrid_lexical_hosting_64_15_v5_8_7_2026