learning_rate: 3e-06
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 16
total_eval_batch_size: 16
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
lr_scheduler_warmup_ratio: 0.03
num_epochs: 2.0

Training Loss	Epoch	Step	Validation Loss
1.1321	0.0594	100	1.0979
1.0204	0.1188	200	1.0132
1.0155	0.1781	300	0.9683
0.9392	0.2375	400	0.9368
0.8472	0.2969	500	0.9136
0.9268	0.3563	600	0.8942
0.8568	0.4157	700	0.8777
0.9049	0.4751	800	0.8637
0.8401	0.5344	900	0.8517
0.8449	0.5938	1000	0.8408
0.8638	0.6532	1100	0.8310
0.8485	0.7126	1200	0.8226
0.8273	0.7720	1300	0.8150
0.8165	0.8314	1400	0.8077
0.824	0.8907	1500	0.8014
0.7944	0.9501	1600	0.7957
0.7492	1.0095	1700	0.7912
0.754	1.0689	1800	0.7873
0.7184	1.1283	1900	0.7835
0.7298	1.1876	2000	0.7802
0.7093	1.2470	2100	0.7777
0.7624	1.3064	2200	0.7744
0.7419	1.3658	2300	0.7723
0.7439	1.4252	2400	0.7704
0.7064	1.4846	2500	0.7688
0.7387	1.5439	2600	0.7675
0.7527	1.6033	2700	0.7664
0.7359	1.6627	2800	0.7656
0.7167	1.7221	2900	0.7650
0.7159	1.7815	3000	0.7646
0.7399	1.8409	3100	0.7644
0.6995	1.9002	3200	0.7642
0.7915	1.9596	3300	0.7642

formalmathatepfl/qwen3-cpt

Qwen3-8B-cpt