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	3707615313920.0	0.8001	0.7941
10246269405466.38	2.0	690	3082649862144.0	0.8102	0.8120
10246269405466.38	3.0	1035	2345435922432.0	0.7995	0.7916
4449967928158.003	4.0	1380	1583186313216.0	0.8106	0.8127
4449967928158.003	5.0	1725	1339034435584.0	0.8288	0.8288
2728623034148.0405	6.0	2070	1129240068096.0	0.8143	0.8163
2728623034148.0405	7.0	2415	995725737984.0	0.8200	0.8213
1923306341707.4253	8.0	2760	878839922688.0	0.8161	0.8175

ttqdunggg/hybrid_lexical_hosting_64_15_8_7_2026_2

hybrid_lexical_hosting_64_15_8_7_2026_2