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
4.093	1.0	2256	3.8133	0.3607
3.4493	2.0	4512	3.3059	0.4091
3.132	3.0	6768	3.0989	0.4295
2.9232	4.0	9024	2.9917	0.4401
2.8445	5.0	11280	2.9270	0.4466
2.7872	6.0	13536	2.8861	0.4510
2.7438	7.0	15792	2.8637	0.4541
2.7139	8.0	18048	2.8414	0.4565
2.6887	9.0	20304	2.8274	0.4580
2.6686	10.0	22560	2.8194	0.4590
2.65	11.0	24816	2.8066	0.4605
2.6481	12.0	27072	2.8002	0.4611
2.6382	13.0	29328	2.7956	0.4618
2.6285	14.0	31584	2.7968	0.4619
2.6116	15.0	33840	2.7692	0.4650
2.5677	16.0	36096	2.7446	0.4684
2.5197	17.0	38352	2.7191	0.4717
2.462	18.0	40608	2.7010	0.4747
2.3973	19.0	42864	2.6860	0.4773
2.324	19.9915	45100	2.6845	0.4787

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

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