learning_rate: 0.001
train_batch_size: 32
eval_batch_size: 64
seed: 1024
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
4.0976	1.0	2264	3.8103	0.3607
3.4447	2.0	4528	3.2977	0.4097
3.1266	3.0	6792	3.0873	0.4300
2.9206	4.0	9056	2.9802	0.4412
2.839	5.0	11320	2.9201	0.4471
2.785	6.0	13584	2.8801	0.4516
2.7376	7.0	15848	2.8532	0.4545
2.7088	8.0	18112	2.8310	0.4569
2.6833	9.0	20376	2.8196	0.4584
2.6631	10.0	22640	2.8089	0.4595
2.6439	11.0	24904	2.8001	0.4604
2.6426	12.0	27168	2.7931	0.4613
2.632	13.0	29432	2.7888	0.4621
2.6204	14.0	31696	2.7885	0.4617
2.6043	15.0	33960	2.7619	0.4654
2.5616	16.0	36224	2.7378	0.4687
2.5124	17.0	38488	2.7151	0.4718
2.4554	18.0	40752	2.6965	0.4749
2.3891	19.0	43016	2.6810	0.4776
2.321	19.9914	45260	2.6779	0.4789

kanishka/opt-babylm2-clean-spacy-earlystop-bpe_seed-1024_1e-3

opt-babylm2-clean-spacy-earlystop-bpe_seed-1024_1e-3