OLMo-1B-0724-hf finetuned for 5 epochs with a learning rate of 1e-5 on the Tulu 2 dataset - specifically this version. I used a batch size of 1, 128 grad accumulation steps. Linear warmup for the first 3% of training then linear decay to 0.

I've additionally released an 'instruct' version which has additionally gone through DPO training. This model is generally more performant (see the metrics below), so check it out!

Evals are as follows:

Metric	OLMo-1B-0724-hf	OLMo-1B-0724-SFT-hf (this model!)	OLMo-1B-0724-Instruct-hf
MMLU 0-shot	25.0	36.0	36.7
GSM8k CoT 8-shot	7.0	12.5	12.5
BBH CoT 3-shot	22.5	27.2	30.6
HumanEval P@10	16.0	21.2	22.0
AlpacaEval 1	-	41.5	50.9
AlpacaEval 2 LC	-	2.7	2.5
Toxigen % Toxic	80.3	59.7	14.1
TruthfulQA %Info+True	23.0	40.9	42.2
IFEval Loose Acc	20.5	26.1	24.2
XSTest F1	67.6	81.9	79.8
Average of above metrics	25.2	33.0	38.7

Model training and evaluation was performed using Open-instruct, so check that out for more details on evaluation.

hamishivi/OLMo-1B-0724-SFT-hf

OLMo-1B-0724 SFT

hamishivi/
OLMo-1B-0724-SFT-hf