learning_rate: 0.001
train_batch_size: 32
eval_batch_size: 64
seed: 211
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
3.0875	1.0	18042	3.1520	0.4227
2.9734	2.0	36084	3.0482	0.4331
2.9048	3.0	54126	2.9848	0.4394
2.8742	4.0	72168	2.9526	0.4430
2.8494	5.0	90210	2.9296	0.4458
2.819	6.0	108252	2.9178	0.4471
2.8034	7.0	126294	2.8993	0.4489
2.7878	8.0	144336	2.8818	0.4511
2.7688	9.0	162378	2.8669	0.4529
2.7492	10.0	180420	2.8508	0.4546
2.7289	11.0	198462	2.8333	0.4566
2.7045	12.0	216504	2.8186	0.4583
2.682	13.0	234546	2.8000	0.4605
2.6581	14.0	252588	2.7817	0.4626
2.6307	15.0	270630	2.7613	0.4649
2.5966	16.0	288672	2.7396	0.4682
2.5502	17.0	306714	2.7122	0.4716
2.4952	18.0	324756	2.6853	0.4752
2.4283	19.0	342798	2.6560	0.4795
2.3386	20.0	360840	2.6405	0.4824

kanishka/opt-babylm2-rewritten-clean-spacy-earlystop-long-bpe_seed-211_1e-3

opt-babylm2-rewritten-clean-spacy-earlystop-long-bpe_seed-211_1e-3