learning_rate: 0.001
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: 32000
num_epochs: 20.0
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
4.1044	1.0	2256	3.8204	0.3604
3.4457	2.0	4512	3.3046	0.4093
3.13	3.0	6768	3.0945	0.4299
2.9219	4.0	9024	2.9890	0.4404
2.8444	5.0	11280	2.9282	0.4466
2.7883	6.0	13536	2.8910	0.4508
2.7434	7.0	15792	2.8579	0.4545
2.7158	8.0	18048	2.8428	0.4560
2.6905	9.0	20304	2.8298	0.4573
2.6697	10.0	22560	2.8169	0.4592
2.6509	11.0	24816	2.8080	0.4601
2.6494	12.0	27072	2.8020	0.4607
2.6384	13.0	29328	2.7958	0.4616
2.6297	14.0	31584	2.7939	0.4620
2.612	15.0	33840	2.7649	0.4653
2.5667	16.0	36096	2.7425	0.4686
2.5177	17.0	38352	2.7206	0.4714
2.4607	18.0	40608	2.6999	0.4746
2.397	19.0	42864	2.6865	0.4773
2.3241	19.9915	45100	2.6840	0.4787

kanishka/opt-babylm2-rewritten-clean-spacy-earlystop-bpe_seed-42_1e-3

opt-babylm2-rewritten-clean-spacy-earlystop-bpe_seed-42_1e-3