learning_rate: 0.0001
train_batch_size: 32
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 256
optimizer: Use OptimizerNames.ADAMW_TORCH 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: 500
num_epochs: 20.0

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.8857	1.0	1659	3.9011	0.3332
3.553	2.0	3318	3.5920	0.3604
3.4021	3.0	4977	3.4457	0.3744
3.2955	4.0	6636	3.3591	0.3832
3.2272	5.0	8295	3.3037	0.3888
3.1643	6.0	9954	3.2646	0.3926
3.1206	7.0	11613	3.2355	0.3957
3.0781	8.0	13272	3.2125	0.3980
3.0467	9.0	14931	3.1951	0.3999
3.023	10.0	16590	3.1822	0.4012
2.985	11.0	18249	3.1736	0.4023
2.9666	12.0	19908	3.1633	0.4035
2.9494	13.0	21567	3.1590	0.4041
2.9322	14.0	23226	3.1527	0.4048
2.9092	15.0	24885	3.1487	0.4054
2.8954	16.0	26544	3.1451	0.4059
2.8763	17.0	28203	3.1436	0.4061
2.8644	18.0	29862	3.1418	0.4065
2.8584	19.0	31521	3.1403	0.4067
2.8417	20.0	33180	3.1396	0.4068

qing-yao/nobinomial-babylm-base_seed-42_1e-4

nobinomial-babylm-base_seed-42_1e-4