learning_rate: 0.0001
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.01
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Complexity Accuracy	Model Accuracy	Overall Accuracy
0.8284	0.6857	300	0.7391	0.7275	0.7475	0.5437
0.7657	1.3703	600	0.7173	0.7408	0.7478	0.5515
0.7398	2.0549	900	0.7099	0.7502	0.748	0.5595
0.7161	2.7406	1200	0.7037	0.7578	0.748	0.5645
0.7057	3.4251	1500	0.6973	0.7635	0.7468	0.569
0.7115	4.1097	1800	0.6927	0.764	0.748	0.5705
0.7214	4.7954	2100	0.6896	0.7672	0.7482	0.5755
0.7034	5.48	2400	0.6886	0.769	0.7472	0.5777
0.6935	6.1646	2700	0.6878	0.769	0.7478	0.577
0.7055	6.8503	3000	0.6867	0.7722	0.7465	0.5787
0.6983	7.5349	3300	0.6858	0.7728	0.7465	0.5797
0.7092	8.2194	3600	0.6849	0.774	0.747	0.5803
0.697	8.9051	3900	0.6851	0.7718	0.747	0.5787
0.6989	9.5897	4200	0.6852	0.772	0.747	0.5793

eternis/eternis_router_encoder_sft_10Sep

eternis_router_encoder_sft_10Sep