learning_rate: 5e-06
train_batch_size: 32
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 256
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.05
num_epochs: 20.0

Training Loss	Epoch	Step	Validation Loss
5.3114	0.4205	1000	5.2579
4.7341	0.8410	2000	4.7159
4.2812	1.2616	3000	4.2622
3.9189	1.6821	4000	3.9133
3.6108	2.1026	5000	3.6182
3.4498	2.5231	6000	3.4399
3.3405	2.9437	7000	3.3348
3.2445	3.3642	8000	3.2656
3.2033	3.7847	9000	3.2112
3.127	4.2052	10000	3.1730
3.1097	4.6257	11000	3.1359
3.0418	5.0463	12000	3.1157
3.0406	5.4668	13000	3.0917
3.0321	5.8873	14000	3.0724
2.9845	6.3078	15000	3.0641
2.9796	6.7283	16000	3.0452
2.9335	7.1489	17000	3.0357
2.9363	7.5694	18000	3.0250
2.9382	7.9899	19000	3.0147
2.8968	8.4104	20000	3.0108
2.9006	8.8310	21000	2.9963
2.8606	9.2515	22000	2.9965
2.8668	9.6720	23000	2.9876
2.8193	10.0925	24000	2.9852
2.8388	10.5130	25000	2.9796
2.8508	10.9336	26000	2.9708
2.8131	11.3541	27000	2.9714
2.8225	11.7746	28000	2.9669
2.7836	12.1951	29000	2.9671
2.7942	12.6156	30000	2.9603
2.7588	13.0362	31000	2.9596
2.7702	13.4567	32000	2.9564
2.7753	13.8772	33000	2.9532
2.7489	14.2977	34000	2.9534
2.7545	14.7183	35000	2.9494
2.728	15.1388	36000	2.9522
2.7334	15.5593	37000	2.9466
2.7382	15.9798	38000	2.9425
2.7161	16.4003	39000	2.9455
2.7241	16.8209	40000	2.9420
2.7014	17.2414	41000	2.9447
2.6998	17.6619	42000	2.9415
2.6804	18.0824	43000	2.9419
2.6972	18.5029	44000	2.9411
2.6931	18.9235	45000	2.9395
2.6832	19.3440	46000	2.9406
2.6778	19.7645	47000	2.9399

kanishka/opt-babylm1_more_entrenchment_laugh_seed-42_5e-6

opt-babylm1_more_entrenchment_laugh_seed-42_5e-6