diff --git a/5m-s0-bpe4096-step-bytes3-v10-nocount.inc.cmp-noinc.rev.sumd-noadd.count.find-norunmax.inc.find-nosumd.rev.cmp-noinc.runmax.cmp-none-docmask/ckpt.pt b/5m-s0-bpe4096-step-bytes3-v10-nocount.inc.cmp-noinc.rev.sumd-noadd.count.find-norunmax.inc.find-nosumd.rev.cmp-noinc.runmax.cmp-none-docmask/ckpt.pt new file mode 100644 index 0000000000000000000000000000000000000000..44656732e2562ac2890c01b3647898433ea81a56 --- /dev/null +++ b/5m-s0-bpe4096-step-bytes3-v10-nocount.inc.cmp-noinc.rev.sumd-noadd.count.find-norunmax.inc.find-nosumd.rev.cmp-noinc.runmax.cmp-none-docmask/ckpt.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3e3b8d219e9a276a575601ff3e1beddb13140f91332ccf167e1192b18dc270b +size 23171663 diff --git a/5m-s0-bpe4096-step-bytes3-v10-nocount.inc.cmp-noinc.rev.sumd-noadd.count.find-norunmax.inc.find-nosumd.rev.cmp-noinc.runmax.cmp-none-docmask/config.json b/5m-s0-bpe4096-step-bytes3-v10-nocount.inc.cmp-noinc.rev.sumd-noadd.count.find-norunmax.inc.find-nosumd.rev.cmp-noinc.runmax.cmp-none-docmask/config.json new file mode 100644 index 0000000000000000000000000000000000000000..f81b28cbf49180fc2f2e6037bb12fae0f4275fcf --- /dev/null +++ b/5m-s0-bpe4096-step-bytes3-v10-nocount.inc.cmp-noinc.rev.sumd-noadd.count.find-norunmax.inc.find-nosumd.rev.cmp-noinc.runmax.cmp-none-docmask/config.json @@ -0,0 +1,35 @@ +{ + "size": "5m", + "name": "5m-s0-bpe4096-step-bytes3-v10-nocount.inc.cmp-noinc.rev.sumd-noadd.count.find-norunmax.inc.find-nosumd.rev.cmp-noinc.runmax.cmp-none-docmask", + "seed": 0, + "tokens": 400000000.0, + "batch_size": 64, + "block_size": 512, + "lr": 0.0006, + "eval_every": 1000, + "vocab": "bpe4096", + "pos": "none", + "reason": "step", + "reason_codec": "bytes", + "per_chunk": 3, + "docmask": true, + "holdout": [ + "count.inc.cmp", + "inc.rev.sumd", + "add.count.find", + "runmax.inc.find", + "sumd.rev.cmp", + "inc.runmax.cmp" + ], + "dataset": "v10", + "vocab_size": 4096, + "n_layer": 6, + "n_head": 4, + "d_model": 256, + "loops": 1, + "params": 5787648, + "flops_per_token": 44163072, + "steps": 12207, + "n_docs": 1175505, + "stream_tokens": 217096403 +} \ No newline at end of file diff --git a/5m-s0-bpe4096-step-bytes3-v10-nocount.inc.cmp-noinc.rev.sumd-noadd.count.find-norunmax.inc.find-nosumd.rev.cmp-noinc.runmax.cmp-none-docmask/log.jsonl b/5m-s0-bpe4096-step-bytes3-v10-nocount.inc.cmp-noinc.rev.sumd-noadd.count.find-norunmax.inc.find-nosumd.rev.cmp-noinc.runmax.cmp-none-docmask/log.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5b29ddd5c31c1e429a19d6d36776891b373d9c9e --- /dev/null +++ b/5m-s0-bpe4096-step-bytes3-v10-nocount.inc.cmp-noinc.rev.sumd-noadd.count.find-norunmax.inc.find-nosumd.rev.cmp-noinc.runmax.cmp-none-docmask/log.jsonl @@ -0,0 +1,625 @@ +{"step": 0, "tokens": 0, "val_loss": 8.364864063262939, "val_bpb": 3.0153975970876363, "lr": 0.0, "elapsed": 1.1139953136444092, "peak_mem_gb": 1.1237632, "add8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5255405568.0}, "add9": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5829525504.0}, "add10": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6403645440.0}, "reach14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5299568640.0}, "reach16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5939403227.136}, "reach18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6493031497.728}, "parity24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8170168320.0}, "parity28": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9406734336.0}, "parity32": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10643300352.0}, "cmp8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 2558278434.816}, "cmp9": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 2381626146.816}, "cmp10": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 2469952290.816}, "runmax12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4460470272.0}, "runmax14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5078753280.0}, "runmax16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5697036288.0}, "count16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5034590208.0}, "count18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5564547072.0}, "count20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6137607094.272}, "brackets16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5480460582.912}, "brackets18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6006177792.0}, "brackets20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6581357641.728}, "sumd8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 3753861120.0}, "sumd9": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4151328768.0}, "sumd10": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4548796416.0}, "inc8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4107165696.0}, "inc9": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4548796416.0}, "inc10": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4990427136.0}, "add.cmp6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6211094446.08}, "add.cmp7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7018042097.664}, "add.cmp8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7748675960.832}, "add.runmax6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7021928448.0}, "add.runmax7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7905189888.0}, "add.runmax8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8788451328.0}, "add.count6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6801113088.0}, "add.count7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7640211456.0}, "add.count8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8479309824.0}, "add.find6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7021928448.0}, "add.find7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7905189888.0}, "add.find8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8788451328.0}, "add.rev6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7331069952.0}, "add.rev7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8479309824.0}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9671712768.0}, "add.sumd6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7330010038.272}, "add.sumd7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8303717449.728}, "add.sumd8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9273185206.272}, "add.inc6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7640211456.0}, "add.inc7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8655962112.0}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9671712768.0}, "runmax.cmp12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5432057856.0}, "runmax.cmp14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6050340864.0}, "runmax.cmp16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6668623872.0}, "runmax.runmax12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5520384000.0}, "runmax.runmax14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6138667008.0}, "runmax.runmax16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6756950016.0}, "runmax.count12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5564547072.0}, "runmax.count14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6182830080.0}, "runmax.count16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6801113088.0}, "runmax.find12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5520384000.0}, "runmax.find14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6138667008.0}, "runmax.find16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6756950016.0}, "runmax.rev12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5167079424.0}, "runmax.rev14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5785362432.0}, "runmax.rev16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6403645440.0}, "runmax.sumd12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5343731712.0}, "runmax.sumd14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5962014720.0}, "runmax.sumd16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6580297728.0}, "runmax.inc12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5387894784.0}, "runmax.inc14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6006177792.0}, "runmax.inc16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6624460800.0}, "count.cmp16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6006177792.0}, "count.cmp18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6536929591.296}, "count.cmp20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7066974781.44}, "count.runmax16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6094503936.0}, "count.runmax18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6624460800.0}, "count.runmax20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7348381876.224}, "count.count16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6138667008.0}, "count.count18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6668623872.0}, "count.count20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7726417772.544}, "count.find16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6094503936.0}, "count.find18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6624460800.0}, "count.find20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7154417664.0}, "count.rev16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5741199360.0}, "count.rev18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6271156224.0}, "count.rev20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6995077300.224}, "count.sumd16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5917851648.0}, "count.sumd18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6447808512.0}, "count.sumd20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7171729588.224}, "count.inc16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5940463140.864}, "count.inc18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6470420004.864}, "count.inc20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7258995818.496}, "parity.cmp16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6668623872.0}, "parity.cmp20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7905189888.0}, "parity.cmp24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9141755904.0}, "parity.runmax16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6756950016.0}, "parity.runmax20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7993516032.0}, "parity.runmax24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9230082048.0}, "parity.count16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6801113088.0}, "parity.count20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8037679104.0}, "parity.count24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9274245120.0}, "parity.find16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6756950016.0}, "parity.find20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7993516032.0}, "parity.find24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9230082048.0}, "parity.rev16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6403645440.0}, "parity.rev20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7640211456.0}, "parity.rev24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8876777472.0}, "parity.sumd16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6580297728.0}, "parity.sumd20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7816863744.0}, "parity.sumd24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9053429760.0}, "parity.inc16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6580297728.0}, "parity.inc20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7816863744.0}, "parity.inc24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9053429760.0}, "sumd.cmp6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4324624662.528}, "sumd.cmp7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4725448704.0}, "sumd.cmp8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5120884850.688}, "sumd.runmax6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4327981056.0}, "sumd.runmax7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4725448704.0}, "sumd.runmax8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5122916352.0}, "sumd.count6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4327981056.0}, "sumd.count7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4725448704.0}, "sumd.count8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5122916352.0}, "sumd.find6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4327981056.0}, "sumd.find7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4725448704.0}, "sumd.find8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5122916352.0}, "sumd.rev6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 3974676480.0}, "sumd.rev7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4372144128.0}, "sumd.rev8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4769611776.0}, "sumd.sumd6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4239654912.0}, "sumd.sumd7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4637122560.0}, "sumd.sumd8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5034590208.0}, "sumd.inc6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4283817984.0}, "sumd.inc7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4681285632.0}, "sumd.inc8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5078753280.0}, "inc.cmp6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5523563741.184}, "inc.cmp7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6097683677.184}, "inc.cmp8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6930422562.816}, "inc.runmax6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5829525504.0}, "inc.runmax7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6580297728.0}, "inc.runmax8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7331069952.0}, "inc.count6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5652873216.0}, "inc.count7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6359482368.0}, "inc.count8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7066091520.0}, "inc.find6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5829525504.0}, "inc.find7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6580297728.0}, "inc.find8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7331069952.0}, "inc.rev6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5917851648.0}, "inc.rev7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6889439232.0}, "inc.rev8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7905189888.0}, "inc.sumd6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6094503936.0}, "inc.sumd7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6933602304.0}, "inc.sumd8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7772700672.0}, "inc.inc6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6315319296.0}, "inc.inc7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7198580736.0}, "inc.inc8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8081842176.0}, "runmax.runmax.cmp12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6491971584.0}, "runmax.runmax.cmp14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7110254592.0}, "runmax.runmax.cmp16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7728537600.0}, "sumd.runmax.cmp6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5299568640.0}, "sumd.runmax.cmp7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5697036288.0}, "sumd.runmax.cmp8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6094503936.0}, "add.runmax.cmp6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7993516032.0}, "add.runmax.cmp7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8876777472.0}, "add.runmax.cmp8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9760038912.0}, "count.runmax.runmax16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7154417664.0}, "count.runmax.runmax18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7684374528.0}, "count.runmax.runmax20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8408295604.224}, "add.runmax.runmax6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8081842176.0}, "add.runmax.runmax7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8965103616.0}, "add.runmax.runmax8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9848365056.0}, "parity.runmax.runmax16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7816863744.0}, "parity.runmax.runmax20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9053429760.0}, "parity.runmax.runmax24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10289995776.0}, "parity.runmax.count16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7861026816.0}, "parity.runmax.count20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9097592832.0}, "parity.runmax.count24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10334158848.0}, "inc.runmax.count6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6933602304.0}, "inc.runmax.count7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7684374528.0}, "inc.runmax.count8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8435146752.0}, "sumd.runmax.count6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5432057856.0}, "sumd.runmax.count7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5829525504.0}, "sumd.runmax.count8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6226993152.0}, "runmax.runmax.find12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6580297728.0}, "runmax.runmax.find14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7198580736.0}, "runmax.runmax.find16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7816863744.0}, "add.runmax.find6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8081842176.0}, "add.runmax.find7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8965103616.0}, "add.runmax.find8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9848365056.0}, "parity.runmax.find16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7816863744.0}, "parity.runmax.find20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9053429760.0}, "parity.runmax.find24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10289995776.0}, "add.runmax.rev6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7728537600.0}, "add.runmax.rev7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8611799040.0}, "add.runmax.rev8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9495060480.0}, "parity.runmax.rev16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7463559168.0}, "parity.runmax.rev20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8700125184.0}, "parity.runmax.rev24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9936691200.0}, "sumd.runmax.rev6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5034590208.0}, "sumd.runmax.rev7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5432057856.0}, "sumd.runmax.rev8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5829525504.0}, "sumd.runmax.sumd6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5211242496.0}, "sumd.runmax.sumd7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5608710144.0}, "sumd.runmax.sumd8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6006177792.0}, "add.runmax.sumd6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7905189888.0}, "add.runmax.sumd7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8788451328.0}, "add.runmax.sumd8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9671712768.0}, "parity.runmax.sumd16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7640211456.0}, "parity.runmax.sumd20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8876777472.0}, "parity.runmax.sumd24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10113343488.0}, "count.runmax.inc16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7000376868.864}, "count.runmax.inc18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7530333732.864}, "count.runmax.inc20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8254254809.088}, "runmax.runmax.inc12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6447808512.0}, "runmax.runmax.inc14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7066091520.0}, "runmax.runmax.inc16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7684374528.0}, "add.runmax.inc6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7949352960.0}, "add.runmax.inc7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8832614400.0}, "add.runmax.inc8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9715875840.0}, "count.count.cmp16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7110254592.0}, "count.count.cmp18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7866326384.64}, "count.count.cmp20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8342580953.088}, "add.count.cmp6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7772700672.0}, "add.count.cmp7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8611799040.0}, "add.count.cmp8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9450897408.0}, "sumd.count.cmp6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5299568640.0}, "sumd.count.cmp7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5697036288.0}, "sumd.count.cmp8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6094503936.0}, "add.count.runmax6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7861026816.0}, "add.count.runmax7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8700125184.0}, "add.count.runmax8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9539223552.0}, "sumd.count.runmax6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5387894784.0}, "sumd.count.runmax7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5785362432.0}, "sumd.count.runmax8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6182830080.0}, "inc.count.runmax6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6712786944.0}, "inc.count.runmax7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7419396096.0}, "inc.count.runmax8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8126005248.0}, "parity.count.count16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7905189888.0}, "parity.count.count20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9141755904.0}, "parity.count.count24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10378321920.0}, "runmax.count.count12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6668623872.0}, "runmax.count.count14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7286906880.0}, "runmax.count.count16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7905189888.0}, "inc.count.count6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6756950016.0}, "inc.count.count7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7463559168.0}, "inc.count.count8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8170168320.0}, "inc.count.find6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6712786944.0}, "inc.count.find7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7419396096.0}, "inc.count.find8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8126005248.0}, "add.count.find6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7861026816.0}, "add.count.find7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8700125184.0}, "add.count.find8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9539223552.0}, "runmax.count.find12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6624460800.0}, "runmax.count.find14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7242743808.0}, "runmax.count.find16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7861026816.0}, "parity.count.rev16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7507722240.0}, "parity.count.rev20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8744288256.0}, "parity.count.rev24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9980854272.0}, "inc.count.rev6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6359482368.0}, "inc.count.rev7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7066091520.0}, "inc.count.rev8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7772700672.0}, "runmax.count.rev12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6271156224.0}, "runmax.count.rev14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6889439232.0}, "runmax.count.rev16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7507722240.0}, "count.count.sumd16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7021928448.0}, "count.count.sumd18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7551885312.0}, "count.count.sumd20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8609679212.544}, "runmax.count.sumd12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6447808512.0}, "runmax.count.sumd14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7066091520.0}, "runmax.count.sumd16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7684374528.0}, "sumd.count.sumd6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5211242496.0}, "sumd.count.sumd7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5608710144.0}, "sumd.count.sumd8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6006177792.0}, "parity.count.inc16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7684374528.0}, "parity.count.inc20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8920940544.0}, "parity.count.inc24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10157506560.0}, "count.count.inc16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7021928448.0}, "count.count.inc18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7551885312.0}, "count.count.inc20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8609679212.544}, "add.count.inc6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7684374528.0}, "add.count.inc7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8523472896.0}, "add.count.inc8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9362571264.0}, "parity.rev.cmp16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7375233024.0}, "parity.rev.cmp20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8611799040.0}, "parity.rev.cmp24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9848365056.0}, "sumd.rev.cmp6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5339138752.512}, "sumd.rev.cmp7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5741199360.0}, "sumd.rev.cmp8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6136017223.68}, "add.rev.cmp6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9374583619.584}, "add.rev.cmp7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10556917383.168}, "add.rev.cmp8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 12028607594.496}, "runmax.rev.runmax12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6226993152.0}, "runmax.rev.runmax14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6845276160.0}, "runmax.rev.runmax16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7463559168.0}, "count.rev.runmax16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6801113088.0}, "count.rev.runmax18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7331069952.0}, "count.rev.runmax20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8205852082.176}, "add.rev.runmax6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10245832704.0}, "add.rev.runmax7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 11703214080.0}, "add.rev.runmax8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 13204758528.0}, "inc.rev.count6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8346820608.0}, "inc.rev.count7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9583386624.0}, "inc.rev.count8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10864115712.0}, "count.rev.count16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6845276160.0}, "count.rev.count18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7375233024.0}, "count.rev.count20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8742168428.544}, "parity.rev.count16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7507722240.0}, "parity.rev.count20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8744288256.0}, "parity.rev.count24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9980854272.0}, "sumd.rev.find6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5343731712.0}, "sumd.rev.find7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5741199360.0}, "sumd.rev.find8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6138667008.0}, "runmax.rev.find12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6226993152.0}, "runmax.rev.find14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6845276160.0}, "runmax.rev.find16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7463559168.0}, "count.rev.find16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6801113088.0}, "count.rev.find18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7331069952.0}, "count.rev.find20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7861026816.0}, "count.rev.rev16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6447808512.0}, "count.rev.rev18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6977765376.0}, "count.rev.rev20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7852547506.176}, "sumd.rev.rev6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 4990427136.0}, "sumd.rev.rev7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5387894784.0}, "sumd.rev.rev8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5785362432.0}, "parity.rev.rev16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7110254592.0}, "parity.rev.rev20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8346820608.0}, "parity.rev.rev24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9583386624.0}, "sumd.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5255405568.0}, "sumd.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5652873216.0}, "sumd.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6050340864.0}, "parity.rev.sumd16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7286906880.0}, "parity.rev.sumd20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8523472896.0}, "parity.rev.sumd24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9760038912.0}, "add.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10599137280.0}, "add.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 12144844800.0}, "add.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 13734715392.0}, "parity.rev.inc16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7286906880.0}, "parity.rev.inc20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8523472896.0}, "parity.rev.inc24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9760038912.0}, "runmax.rev.inc12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6094503936.0}, "runmax.rev.inc14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6712786944.0}, "runmax.rev.inc16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7331069952.0}, "inc.rev.inc6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9009266688.0}, "inc.rev.inc7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10422484992.0}, "inc.rev.inc8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 11879866368.0}, "parity.sumd.cmp16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7551885312.0}, "parity.sumd.cmp20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8788451328.0}, "parity.sumd.cmp24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10025017344.0}, "runmax.sumd.cmp12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6315319296.0}, "runmax.sumd.cmp14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6933602304.0}, "runmax.sumd.cmp16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7551885312.0}, "count.sumd.cmp16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6889439232.0}, "count.sumd.cmp18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7699566624.768}, "count.sumd.cmp20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8346820608.0}, "sumd.sumd.runmax6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5608710144.0}, "sumd.sumd.runmax7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6006177792.0}, "sumd.sumd.runmax8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6403645440.0}, "count.sumd.runmax16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6977765376.0}, "count.sumd.runmax18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7507722240.0}, "count.sumd.runmax20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8231643316.224}, "add.sumd.runmax6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8699065270.272}, "add.sumd.runmax7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9672772681.728}, "add.sumd.runmax8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10642240438.272}, "parity.sumd.count16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7684374528.0}, "parity.sumd.count20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8920940544.0}, "parity.sumd.count24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10157506560.0}, "sumd.sumd.count6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5608710144.0}, "sumd.sumd.count7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6006177792.0}, "sumd.sumd.count8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6403645440.0}, "add.sumd.count6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8699065270.272}, "add.sumd.count7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9715875840.0}, "add.sumd.count8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10687463424.0}, "runmax.sumd.find12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6403645440.0}, "runmax.sumd.find14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7021928448.0}, "runmax.sumd.find16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7640211456.0}, "sumd.sumd.find6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5608710144.0}, "sumd.sumd.find7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6006177792.0}, "sumd.sumd.find8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6403645440.0}, "parity.sumd.find16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7640211456.0}, "parity.sumd.find20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8876777472.0}, "parity.sumd.find24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10113343488.0}, "count.sumd.rev16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6624460800.0}, "count.sumd.rev18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7154417664.0}, "count.sumd.rev20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7878338740.224}, "parity.sumd.rev16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7286906880.0}, "parity.sumd.rev20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8523472896.0}, "parity.sumd.rev24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9760038912.0}, "add.sumd.rev6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8345760694.272}, "add.sumd.rev7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9319468105.728}, "add.sumd.rev8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10288935862.272}, "parity.sumd.sumd16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7463559168.0}, "parity.sumd.sumd20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8700125184.0}, "parity.sumd.sumd24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9936691200.0}, "add.sumd.sumd6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8567635968.0}, "add.sumd.sumd7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9584446537.728}, "add.sumd.sumd8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10510811136.0}, "count.sumd.sumd16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6801113088.0}, "count.sumd.sumd18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7331069952.0}, "count.sumd.sumd20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8054991028.224}, "inc.sumd.inc6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7419396096.0}, "inc.sumd.inc7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8258494464.0}, "inc.sumd.inc8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9097592832.0}, "sumd.sumd.inc6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5564547072.0}, "sumd.sumd.inc7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5962014720.0}, "sumd.sumd.inc8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6359482368.0}, "parity.sumd.inc16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7463559168.0}, "parity.sumd.inc20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8700125184.0}, "parity.sumd.inc24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9936691200.0}, "inc.inc.cmp6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8614978781.184}, "inc.inc.cmp7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9630729437.184}, "inc.inc.cmp8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10905099042.816}, "runmax.inc.cmp12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6627993845.76}, "runmax.inc.cmp14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7286906880.0}, "runmax.inc.cmp16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7917555548.16}, "sumd.inc.cmp6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5647750299.648}, "sumd.inc.cmp7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6050340864.0}, "sumd.inc.cmp8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6447808512.0}, "sumd.inc.runmax6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5652873216.0}, "sumd.inc.runmax7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6050340864.0}, "sumd.inc.runmax8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6447808512.0}, "runmax.inc.runmax12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6756950016.0}, "runmax.inc.runmax14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7375233024.0}, "runmax.inc.runmax16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7993516032.0}, "add.inc.runmax6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10554974208.0}, "add.inc.runmax7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 11879866368.0}, "add.inc.runmax8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 13204758528.0}, "runmax.inc.count12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6756950016.0}, "runmax.inc.count14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7375233024.0}, "runmax.inc.count16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7993516032.0}, "sumd.inc.count6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5652873216.0}, "sumd.inc.count7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6050340864.0}, "sumd.inc.count8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6447808512.0}, "inc.inc.count6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8744288256.0}, "inc.inc.count7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9892528128.0}, "inc.inc.count8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 11040768000.0}, "parity.inc.find16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7640211456.0}, "parity.inc.find20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8876777472.0}, "parity.inc.find24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10113343488.0}, "sumd.inc.find6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5652873216.0}, "sumd.inc.find7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6050340864.0}, "sumd.inc.find8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6447808512.0}, "count.inc.find16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6977765376.0}, "count.inc.find18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7507722240.0}, "count.inc.find20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8390983680.0}, "sumd.inc.rev6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5299568640.0}, "sumd.inc.rev7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5697036288.0}, "sumd.inc.rev8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6094503936.0}, "count.inc.rev16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6805352742.912}, "count.inc.rev18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7335309606.912}, "count.inc.rev20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8274746474.496}, "parity.inc.rev16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7286906880.0}, "parity.inc.rev20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8523472896.0}, "parity.inc.rev24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9760038912.0}, "count.inc.sumd16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6982005030.912}, "count.inc.sumd18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7511961894.912}, "count.inc.sumd20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8451398762.496}, "sumd.inc.sumd6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5564547072.0}, "sumd.inc.sumd7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5962014720.0}, "sumd.inc.sumd8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6359482368.0}, "add.inc.sumd6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10863055798.272}, "add.inc.sumd7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 12278393929.728}, "add.inc.sumd8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 13689492406.272}, "parity.inc.inc16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7463559168.0}, "parity.inc.inc20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8700125184.0}, "parity.inc.inc24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9936691200.0}, "sumd.inc.inc6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5608710144.0}, "sumd.inc.inc7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6006177792.0}, "sumd.inc.inc8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6403645440.0}, "runmax.inc.inc12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6712786944.0}, "runmax.inc.inc14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7331069952.0}, "runmax.inc.inc16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7949352960.0}, "count.inc.cmp16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6889439232.0}, "count.inc.cmp18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7422752489.472}, "count.inc.cmp20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7955977420.8}, "inc.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8788451328.0}, "inc.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10157506560.0}, "inc.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 11570724864.0}, "runmax.inc.find12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6756950016.0}, "runmax.inc.find14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7375233024.0}, "runmax.inc.find16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7993516032.0}, "inc.runmax.cmp6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6801113088.0}, "inc.runmax.cmp7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7551885312.0}, "inc.runmax.cmp8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8302657536.0}} +{"step": 0, "train_loss": 8.356449127197266} +{"step": 20, "train_loss": 7.299837112426758} +{"step": 40, "train_loss": 6.432406902313232} +{"step": 60, "train_loss": 5.616025924682617} +{"step": 80, "train_loss": 4.82023811340332} +{"step": 100, "train_loss": 4.120187282562256} +{"step": 120, "train_loss": 3.572293281555176} +{"step": 140, "train_loss": 3.1042511463165283} +{"step": 160, "train_loss": 2.852914571762085} +{"step": 180, "train_loss": 2.688288688659668} +{"step": 200, "train_loss": 2.469468355178833} +{"step": 220, "train_loss": 2.465846538543701} +{"step": 240, "train_loss": 2.253645420074463} +{"step": 260, "train_loss": 2.253572702407837} +{"step": 280, "train_loss": 2.132700204849243} +{"step": 300, "train_loss": 2.051690101623535} +{"step": 320, "train_loss": 2.07602596282959} +{"step": 340, "train_loss": 2.0652952194213867} +{"step": 360, "train_loss": 1.866837501525879} +{"step": 380, "train_loss": 2.0184288024902344} +{"step": 400, "train_loss": 1.8939106464385986} +{"step": 420, "train_loss": 1.9123241901397705} +{"step": 440, "train_loss": 1.9981212615966797} +{"step": 460, "train_loss": 1.799407958984375} +{"step": 480, "train_loss": 1.806652545928955} +{"step": 500, "train_loss": 1.8665001392364502} +{"step": 520, "train_loss": 1.8216373920440674} +{"step": 540, "train_loss": 1.8686764240264893} +{"step": 560, "train_loss": 1.7172534465789795} +{"step": 580, "train_loss": 1.6870002746582031} +{"step": 600, "train_loss": 1.7051501274108887} +{"step": 620, "train_loss": 1.7446837425231934} +{"step": 640, "train_loss": 1.7253317832946777} +{"step": 660, "train_loss": 1.749529480934143} +{"step": 680, "train_loss": 1.702523946762085} +{"step": 700, "train_loss": 1.6983882188796997} +{"step": 720, "train_loss": 1.5568915605545044} +{"step": 740, "train_loss": 1.641326904296875} +{"step": 760, "train_loss": 1.655491590499878} +{"step": 780, "train_loss": 1.417184591293335} +{"step": 800, "train_loss": 1.6797271966934204} +{"step": 820, "train_loss": 1.6120717525482178} +{"step": 840, "train_loss": 1.5911378860473633} +{"step": 860, "train_loss": 1.47019624710083} +{"step": 880, "train_loss": 1.5411350727081299} +{"step": 900, "train_loss": 1.6203701496124268} +{"step": 920, "train_loss": 1.688065528869629} +{"step": 940, "train_loss": 1.5280756950378418} +{"step": 960, "train_loss": 1.483188271522522} +{"step": 980, "train_loss": 1.461903691291809} +{"step": 1000, "tokens": 32768000, "val_loss": 2.960443687438965, "val_bpb": 1.0671918531972575, "lr": 0.0005946964099287039, "elapsed": 357.6747603416443, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.0, "reasoning_bytes": 70.054, "flops_per_problem": 4482551808.0}, "add9": {"acc": 0.0, "reasoning_bytes": 79.2, "flops_per_problem": 5019044806.656}, "add10": {"acc": 0.0, "reasoning_bytes": 87.8, "flops_per_problem": 5518087520.256}, "reach14": {"acc": 0.008, "reasoning_bytes": 0.074, "flops_per_problem": 5000761294.848}, "reach16": {"acc": 0.066, "reasoning_bytes": 1.212, "flops_per_problem": 5825904132.096}, "reach18": {"acc": 0.09, "reasoning_bytes": 2.64, "flops_per_problem": 6344113618.944}, "parity24": {"acc": 0.026, "reasoning_bytes": 146.98, "flops_per_problem": 8163455533.056}, "parity28": {"acc": 0.002, "reasoning_bytes": 170.996, "flops_per_problem": 9406027726.848}, "parity32": {"acc": 0.0, "reasoning_bytes": 195.0, "flops_per_problem": 10643300352.0}, "cmp8": {"acc": 0.776, "reasoning_bytes": 5.072, "flops_per_problem": 1328071901.184}, "cmp9": {"acc": 0.734, "reasoning_bytes": 5.108, "flops_per_problem": 1417987915.776}, "cmp10": {"acc": 0.74, "reasoning_bytes": 5.216, "flops_per_problem": 1511083671.552}, "runmax12": {"acc": 0.98, "reasoning_bytes": 69.736, "flops_per_problem": 4095506644.992}, "runmax14": {"acc": 0.942, "reasoning_bytes": 81.868, "flops_per_problem": 4719619178.496}, "runmax16": {"acc": 0.894, "reasoning_bytes": 94.484, "flops_per_problem": 5365636595.712}, "count16": {"acc": 0.0, "reasoning_bytes": 87.0, "flops_per_problem": 5034590208.0}, "count18": {"acc": 0.0, "reasoning_bytes": 97.0, "flops_per_problem": 5564547072.0}, "count20": {"acc": 0.0, "reasoning_bytes": 107.0, "flops_per_problem": 6137607094.272}, "brackets16": {"acc": 0.466, "reasoning_bytes": 7.44, "flops_per_problem": 1626084311.04}, "brackets18": {"acc": 0.47, "reasoning_bytes": 4.918, "flops_per_problem": 1716000325.632}, "brackets20": {"acc": 0.398, "reasoning_bytes": 5.232, "flops_per_problem": 2076900950.016}, "sumd8": {"acc": 0.058, "reasoning_bytes": 53.01, "flops_per_problem": 3137962917.888}, "sumd9": {"acc": 0.038, "reasoning_bytes": 59.306, "flops_per_problem": 3462031540.224}, "sumd10": {"acc": 0.02, "reasoning_bytes": 64.826, "flops_per_problem": 3755450990.592}, "inc8": {"acc": 0.0, "reasoning_bytes": 55.312, "flops_per_problem": 3406916026.368}, "inc9": {"acc": 0.0, "reasoning_bytes": 63.07, "flops_per_problem": 3830528212.992}, "inc10": {"acc": 0.0, "reasoning_bytes": 67.096, "flops_per_problem": 4075014979.584}, "add.cmp6": {"acc": 0.628, "reasoning_bytes": 89.466, "flops_per_problem": 5393547657.216}, "add.cmp7": {"acc": 0.596, "reasoning_bytes": 100.752, "flops_per_problem": 6020839931.904}, "add.cmp8": {"acc": 0.57, "reasoning_bytes": 111.97, "flops_per_problem": 6655198298.112}, "add.runmax6": {"acc": 0.494, "reasoning_bytes": 119.806, "flops_per_problem": 6528273629.184}, "add.runmax7": {"acc": 0.546, "reasoning_bytes": 132.326, "flops_per_problem": 7171464609.792}, "add.runmax8": {"acc": 0.482, "reasoning_bytes": 146.652, "flops_per_problem": 7892824227.84}, "add.count6": {"acc": 0.44, "reasoning_bytes": 114.474, "flops_per_problem": 6373437898.752}, "add.count7": {"acc": 0.42, "reasoning_bytes": 126.978, "flops_per_problem": 6994723995.648}, "add.count8": {"acc": 0.376, "reasoning_bytes": 140.016, "flops_per_problem": 7651870507.008}, "add.find6": {"acc": 0.354, "reasoning_bytes": 111.038, "flops_per_problem": 6155713953.792}, "add.find7": {"acc": 0.302, "reasoning_bytes": 124.706, "flops_per_problem": 6834677022.72}, "add.find8": {"acc": 0.236, "reasoning_bytes": 138.444, "flops_per_problem": 7526800687.104}, "add.rev6": {"acc": 0.002, "reasoning_bytes": 111.08, "flops_per_problem": 6234765852.672}, "add.rev7": {"acc": 0.0, "reasoning_bytes": 124.54, "flops_per_problem": 6950560923.648}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 143.52, "flops_per_problem": 7911991001.088}, "add.sumd6": {"acc": 0.04, "reasoning_bytes": 125.532, "flops_per_problem": 6746615857.152}, "add.sumd7": {"acc": 0.022, "reasoning_bytes": 143.174, "flops_per_problem": 7597373276.16}, "add.sumd8": {"acc": 0.012, "reasoning_bytes": 157.746, "flops_per_problem": 8345584041.984}, "add.inc6": {"acc": 0.0, "reasoning_bytes": 121.968, "flops_per_problem": 6692471930.88}, "add.inc7": {"acc": 0.0, "reasoning_bytes": 132.06, "flops_per_problem": 7251841400.832}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 146.752, "flops_per_problem": 8016569155.584}, "runmax.cmp12": {"acc": 0.868, "reasoning_bytes": 87.048, "flops_per_problem": 5125036179.456}, "runmax.cmp14": {"acc": 0.864, "reasoning_bytes": 99.324, "flops_per_problem": 5755508195.328}, "runmax.cmp16": {"acc": 0.72, "reasoning_bytes": 111.796, "flops_per_problem": 6536311308.288}, "runmax.runmax12": {"acc": 0.982, "reasoning_bytes": 87.648, "flops_per_problem": 5195697094.656}, "runmax.runmax14": {"acc": 0.98, "reasoning_bytes": 99.604, "flops_per_problem": 5812036927.488}, "runmax.runmax16": {"acc": 0.942, "reasoning_bytes": 111.252, "flops_per_problem": 6419014189.056}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 87.94, "flops_per_problem": 5252755783.68}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 99.988, "flops_per_problem": 5873158619.136}, "runmax.count16": {"acc": 0.922, "reasoning_bytes": 112.002, "flops_per_problem": 6503189004.288}, "runmax.find12": {"acc": 0.938, "reasoning_bytes": 88.156, "flops_per_problem": 5218131935.232}, "runmax.find14": {"acc": 0.954, "reasoning_bytes": 100.908, "flops_per_problem": 5870420508.672}, "runmax.find16": {"acc": 0.834, "reasoning_bytes": 114.026, "flops_per_problem": 6546822119.424}, "runmax.rev12": {"acc": 0.984, "reasoning_bytes": 83.072, "flops_per_problem": 4861117661.184}, "runmax.rev14": {"acc": 0.962, "reasoning_bytes": 95.276, "flops_per_problem": 5488409935.872}, "runmax.rev16": {"acc": 0.93, "reasoning_bytes": 107.514, "flops_per_problem": 6117733711.872}, "runmax.sumd12": {"acc": 0.986, "reasoning_bytes": 86.0, "flops_per_problem": 5035826774.016}, "runmax.sumd14": {"acc": 0.926, "reasoning_bytes": 98.06, "flops_per_problem": 5673718185.984}, "runmax.sumd16": {"acc": 0.572, "reasoning_bytes": 107.276, "flops_per_problem": 6328038260.736}, "runmax.inc12": {"acc": 0.952, "reasoning_bytes": 86.856, "flops_per_problem": 5057466679.296}, "runmax.inc14": {"acc": 0.84, "reasoning_bytes": 98.816, "flops_per_problem": 5672481619.968}, "runmax.inc16": {"acc": 0.736, "reasoning_bytes": 110.588, "flops_per_problem": 6280960425.984}, "count.cmp16": {"acc": 0.03, "reasoning_bytes": 99.044, "flops_per_problem": 6000701571.072}, "count.cmp18": {"acc": 0.006, "reasoning_bytes": 106.868, "flops_per_problem": 6536399634.432}, "count.cmp20": {"acc": 0.0, "reasoning_bytes": 117.372, "flops_per_problem": 7066974781.44}, "count.runmax16": {"acc": 0.002, "reasoning_bytes": 99.392, "flops_per_problem": 6091500847.104}, "count.runmax18": {"acc": 0.0, "reasoning_bytes": 108.474, "flops_per_problem": 6622694277.12}, "count.runmax20": {"acc": 0.016, "reasoning_bytes": 122.49, "flops_per_problem": 7320294162.432}, "count.count16": {"acc": 0.028, "reasoning_bytes": 99.968, "flops_per_problem": 6136547180.544}, "count.count18": {"acc": 0.014, "reasoning_bytes": 108.076, "flops_per_problem": 6667917262.848}, "count.count20": {"acc": 0.762, "reasoning_bytes": 130.594, "flops_per_problem": 7572111998.976}, "count.find16": {"acc": 0.02, "reasoning_bytes": 99.526, "flops_per_problem": 6091059216.384}, "count.find18": {"acc": 0.008, "reasoning_bytes": 107.142, "flops_per_problem": 6623224233.984}, "count.find20": {"acc": 0.006, "reasoning_bytes": 117.462, "flops_per_problem": 7153534402.56}, "count.rev16": {"acc": 0.0, "reasoning_bytes": 95.898, "flops_per_problem": 5740492750.848}, "count.rev18": {"acc": 0.0, "reasoning_bytes": 106.588, "flops_per_problem": 6270626267.136}, "count.rev20": {"acc": 0.008, "reasoning_bytes": 120.088, "flops_per_problem": 6985714728.96}, "count.sumd16": {"acc": 0.0, "reasoning_bytes": 97.444, "flops_per_problem": 5917056712.704}, "count.sumd18": {"acc": 0.0, "reasoning_bytes": 107.606, "flops_per_problem": 6441890660.352}, "count.sumd20": {"acc": 0.0, "reasoning_bytes": 120.944, "flops_per_problem": 7134455955.456}, "count.inc16": {"acc": 0.004, "reasoning_bytes": 97.218, "flops_per_problem": 5939226574.848}, "count.inc18": {"acc": 0.002, "reasoning_bytes": 107.994, "flops_per_problem": 6469713395.712}, "count.inc20": {"acc": 0.01, "reasoning_bytes": 124.82, "flops_per_problem": 7224018665.472}, "parity.cmp16": {"acc": 0.932, "reasoning_bytes": 105.192, "flops_per_problem": 6102983245.824}, "parity.cmp20": {"acc": 0.942, "reasoning_bytes": 130.976, "flops_per_problem": 7418336182.272}, "parity.cmp24": {"acc": 0.74, "reasoning_bytes": 159.858, "flops_per_problem": 8879692234.752}, "parity.runmax16": {"acc": 0.524, "reasoning_bytes": 106.228, "flops_per_problem": 6192899260.416}, "parity.runmax20": {"acc": 0.546, "reasoning_bytes": 130.468, "flops_per_problem": 7440064413.696}, "parity.runmax24": {"acc": 0.466, "reasoning_bytes": 157.096, "flops_per_problem": 8796400680.96}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 107.2, "flops_per_problem": 6279988838.4}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 131.008, "flops_per_problem": 7508075544.576}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 155.956, "flops_per_problem": 8786508152.832}, "parity.find16": {"acc": 0.864, "reasoning_bytes": 110.464, "flops_per_problem": 6379974033.408}, "parity.find20": {"acc": 0.868, "reasoning_bytes": 135.304, "flops_per_problem": 7653637029.888}, "parity.find24": {"acc": 0.756, "reasoning_bytes": 161.528, "flops_per_problem": 9041240752.128}, "parity.rev16": {"acc": 0.56, "reasoning_bytes": 102.956, "flops_per_problem": 5915908472.832}, "parity.rev20": {"acc": 0.508, "reasoning_bytes": 128.066, "flops_per_problem": 7201495498.752}, "parity.rev24": {"acc": 0.416, "reasoning_bytes": 155.12, "flops_per_problem": 8602348142.592}, "parity.sumd16": {"acc": 0.536, "reasoning_bytes": 105.464, "flops_per_problem": 6070832529.408}, "parity.sumd20": {"acc": 0.506, "reasoning_bytes": 130.622, "flops_per_problem": 7359422644.224}, "parity.sumd24": {"acc": 0.482, "reasoning_bytes": 159.19, "flops_per_problem": 8812211060.736}, "parity.inc16": {"acc": 0.574, "reasoning_bytes": 107.688, "flops_per_problem": 6124888129.536}, "parity.inc20": {"acc": 0.492, "reasoning_bytes": 132.724, "flops_per_problem": 7407118761.984}, "parity.inc24": {"acc": 0.366, "reasoning_bytes": 161.212, "flops_per_problem": 8849573019.648}, "sumd.cmp6": {"acc": 0.796, "reasoning_bytes": 61.17, "flops_per_problem": 3672866045.952}, "sumd.cmp7": {"acc": 0.758, "reasoning_bytes": 68.368, "flops_per_problem": 4035091562.496}, "sumd.cmp8": {"acc": 0.734, "reasoning_bytes": 74.018, "flops_per_problem": 4328775991.296}, "sumd.runmax6": {"acc": 0.532, "reasoning_bytes": 66.698, "flops_per_problem": 3917176160.256}, "sumd.runmax7": {"acc": 0.286, "reasoning_bytes": 73.272, "flops_per_problem": 4251667267.584}, "sumd.runmax8": {"acc": 0.148, "reasoning_bytes": 78.746, "flops_per_problem": 4537578995.712}, "sumd.count6": {"acc": 0.926, "reasoning_bytes": 65.562, "flops_per_problem": 3911169982.464}, "sumd.count7": {"acc": 0.902, "reasoning_bytes": 72.356, "flops_per_problem": 4255376965.632}, "sumd.count8": {"acc": 0.856, "reasoning_bytes": 78.344, "flops_per_problem": 4563900186.624}, "sumd.find6": {"acc": 0.696, "reasoning_bytes": 66.63, "flops_per_problem": 3914173071.36}, "sumd.find7": {"acc": 0.69, "reasoning_bytes": 74.152, "flops_per_problem": 4290530770.944}, "sumd.find8": {"acc": 0.66, "reasoning_bytes": 80.446, "flops_per_problem": 4612567891.968}, "sumd.rev6": {"acc": 0.406, "reasoning_bytes": 61.028, "flops_per_problem": 3576413896.704}, "sumd.rev7": {"acc": 0.176, "reasoning_bytes": 67.722, "flops_per_problem": 3917529464.832}, "sumd.rev8": {"acc": 0.06, "reasoning_bytes": 73.32, "flops_per_problem": 4208564109.312}, "sumd.sumd6": {"acc": 0.45, "reasoning_bytes": 65.332, "flops_per_problem": 3776207634.432}, "sumd.sumd7": {"acc": 0.2, "reasoning_bytes": 72.424, "flops_per_problem": 4132426973.184}, "sumd.sumd8": {"acc": 0.092, "reasoning_bytes": 77.838, "flops_per_problem": 4416748830.72}, "sumd.inc6": {"acc": 0.344, "reasoning_bytes": 68.274, "flops_per_problem": 3898186039.296}, "sumd.inc7": {"acc": 0.118, "reasoning_bytes": 74.864, "flops_per_problem": 4234355343.36}, "sumd.inc8": {"acc": 0.052, "reasoning_bytes": 80.314, "flops_per_problem": 4516027416.576}, "inc.cmp6": {"acc": 0.722, "reasoning_bytes": 76.698, "flops_per_problem": 4492179357.696}, "inc.cmp7": {"acc": 0.642, "reasoning_bytes": 86.184, "flops_per_problem": 4999789707.264}, "inc.cmp8": {"acc": 0.542, "reasoning_bytes": 98.988, "flops_per_problem": 5665768833.024}, "inc.runmax6": {"acc": 0.934, "reasoning_bytes": 102.212, "flops_per_problem": 5441420427.264}, "inc.runmax7": {"acc": 0.846, "reasoning_bytes": 112.87, "flops_per_problem": 5956096868.352}, "inc.runmax8": {"acc": 0.768, "reasoning_bytes": 125.15, "flops_per_problem": 6542759116.8}, "inc.count6": {"acc": 0.474, "reasoning_bytes": 97.008, "flops_per_problem": 5290559373.312}, "inc.count7": {"acc": 0.442, "reasoning_bytes": 108.82, "flops_per_problem": 5838534770.688}, "inc.count8": {"acc": 0.434, "reasoning_bytes": 121.066, "flops_per_problem": 6417335992.32}, "inc.find6": {"acc": 0.346, "reasoning_bytes": 91.89, "flops_per_problem": 4988042330.112}, "inc.find7": {"acc": 0.266, "reasoning_bytes": 102.058, "flops_per_problem": 5482315431.936}, "inc.find8": {"acc": 0.202, "reasoning_bytes": 117.06, "flops_per_problem": 6187952996.352}, "inc.rev6": {"acc": 0.058, "reasoning_bytes": 96.774, "flops_per_problem": 5278017060.864}, "inc.rev7": {"acc": 0.0, "reasoning_bytes": 106.86, "flops_per_problem": 5798081396.736}, "inc.rev8": {"acc": 0.0, "reasoning_bytes": 120.502, "flops_per_problem": 6478810988.544}, "inc.sumd6": {"acc": 0.102, "reasoning_bytes": 107.216, "flops_per_problem": 5620899151.872}, "inc.sumd7": {"acc": 0.042, "reasoning_bytes": 118.13, "flops_per_problem": 6143878250.496}, "inc.sumd8": {"acc": 0.03, "reasoning_bytes": 129.632, "flops_per_problem": 6696446607.36}, "inc.inc6": {"acc": 0.0, "reasoning_bytes": 109.366, "flops_per_problem": 5809652121.6}, "inc.inc7": {"acc": 0.0, "reasoning_bytes": 118.896, "flops_per_problem": 6296417501.184}, "inc.inc8": {"acc": 0.0, "reasoning_bytes": 131.76, "flops_per_problem": 6935722131.456}, "runmax.runmax.cmp12": {"acc": 0.944, "reasoning_bytes": 104.14, "flops_per_problem": 6188836257.792}, "runmax.runmax.cmp14": {"acc": 0.942, "reasoning_bytes": 115.522, "flops_per_problem": 6780003139.584}, "runmax.runmax.cmp16": {"acc": 0.946, "reasoning_bytes": 122.2, "flops_per_problem": 7163161952.256}, "sumd.runmax.cmp6": {"acc": 0.64, "reasoning_bytes": 82.554, "flops_per_problem": 4882404261.888}, "sumd.runmax.cmp7": {"acc": 0.506, "reasoning_bytes": 89.294, "flops_per_problem": 5223961460.736}, "sumd.runmax.cmp8": {"acc": 0.456, "reasoning_bytes": 94.89, "flops_per_problem": 5515437735.936}, "add.runmax.cmp6": {"acc": 0.706, "reasoning_bytes": 123.408, "flops_per_problem": 6951620837.376}, "add.runmax.cmp7": {"acc": 0.63, "reasoning_bytes": 142.044, "flops_per_problem": 7862969991.168}, "add.runmax.cmp8": {"acc": 0.666, "reasoning_bytes": 157.216, "flops_per_problem": 8621338263.552}, "count.runmax.runmax16": {"acc": 0.014, "reasoning_bytes": 118.354, "flops_per_problem": 7144525135.872}, "count.runmax.runmax18": {"acc": 0.006, "reasoning_bytes": 127.316, "flops_per_problem": 7675718565.888}, "count.runmax.runmax20": {"acc": 0.032, "reasoning_bytes": 140.08, "flops_per_problem": 8314846543.872}, "add.runmax.runmax6": {"acc": 0.482, "reasoning_bytes": 130.05, "flops_per_problem": 7289115033.6}, "add.runmax.runmax7": {"acc": 0.572, "reasoning_bytes": 143.26, "flops_per_problem": 7960835358.72}, "add.runmax.runmax8": {"acc": 0.496, "reasoning_bytes": 161.644, "flops_per_problem": 8860967092.224}, "parity.runmax.runmax16": {"acc": 0.536, "reasoning_bytes": 123.072, "flops_per_problem": 7245923549.184}, "parity.runmax.runmax20": {"acc": 0.53, "reasoning_bytes": 146.964, "flops_per_problem": 8477719953.408}, "parity.runmax.runmax24": {"acc": 0.434, "reasoning_bytes": 168.228, "flops_per_problem": 9593455804.416}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 123.398, "flops_per_problem": 7304483782.656}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 147.116, "flops_per_problem": 8528595812.352}, "parity.runmax.count24": {"acc": 0.53, "reasoning_bytes": 162.206, "flops_per_problem": 9537722007.552}, "inc.runmax.count6": {"acc": 1.0, "reasoning_bytes": 112.71, "flops_per_problem": 6258348933.12}, "inc.runmax.count7": {"acc": 0.998, "reasoning_bytes": 125.752, "flops_per_problem": 6879105073.152}, "inc.runmax.count8": {"acc": 1.0, "reasoning_bytes": 141.242, "flops_per_problem": 7606735847.424}, "sumd.runmax.count6": {"acc": 1.0, "reasoning_bytes": 83.938, "flops_per_problem": 5031852097.536}, "sumd.runmax.count7": {"acc": 0.998, "reasoning_bytes": 90.744, "flops_per_problem": 5376500711.424}, "sumd.runmax.count8": {"acc": 0.998, "reasoning_bytes": 96.878, "flops_per_problem": 5691825045.504}, "runmax.runmax.find12": {"acc": 0.946, "reasoning_bytes": 105.24, "flops_per_problem": 6281755361.28}, "runmax.runmax.find14": {"acc": 0.914, "reasoning_bytes": 115.722, "flops_per_problem": 6832910499.84}, "runmax.runmax.find16": {"acc": 0.918, "reasoning_bytes": 120.634, "flops_per_problem": 7138165653.504}, "add.runmax.find6": {"acc": 0.734, "reasoning_bytes": 130.788, "flops_per_problem": 7321530728.448}, "add.runmax.find7": {"acc": 0.738, "reasoning_bytes": 143.966, "flops_per_problem": 7991926161.408}, "add.runmax.find8": {"acc": 0.628, "reasoning_bytes": 161.986, "flops_per_problem": 8876159188.992}, "parity.runmax.find16": {"acc": 0.848, "reasoning_bytes": 124.824, "flops_per_problem": 7323297251.328}, "parity.runmax.find20": {"acc": 0.854, "reasoning_bytes": 148.136, "flops_per_problem": 8529479073.792}, "parity.runmax.find24": {"acc": 0.876, "reasoning_bytes": 172.764, "flops_per_problem": 9793779499.008}, "add.runmax.rev6": {"acc": 0.486, "reasoning_bytes": 122.694, "flops_per_problem": 6831585607.68}, "add.runmax.rev7": {"acc": 0.56, "reasoning_bytes": 138.172, "flops_per_problem": 7603644432.384}, "add.runmax.rev8": {"acc": 0.476, "reasoning_bytes": 157.152, "flops_per_problem": 8530185682.944}, "parity.runmax.rev16": {"acc": 0.562, "reasoning_bytes": 115.684, "flops_per_problem": 6787157557.248}, "parity.runmax.rev20": {"acc": 0.572, "reasoning_bytes": 137.734, "flops_per_problem": 7937605582.848}, "parity.runmax.rev24": {"acc": 0.442, "reasoning_bytes": 161.932, "flops_per_problem": 9182915887.104}, "sumd.runmax.rev6": {"acc": 0.542, "reasoning_bytes": 78.872, "flops_per_problem": 4631469686.784}, "sumd.runmax.rev7": {"acc": 0.3, "reasoning_bytes": 85.782, "flops_per_problem": 4980711260.16}, "sumd.runmax.rev8": {"acc": 0.162, "reasoning_bytes": 91.716, "flops_per_problem": 5287379632.128}, "sumd.runmax.sumd6": {"acc": 0.542, "reasoning_bytes": 81.972, "flops_per_problem": 4812538281.984}, "sumd.runmax.sumd7": {"acc": 0.298, "reasoning_bytes": 89.242, "flops_per_problem": 5177678561.28}, "sumd.runmax.sumd8": {"acc": 0.13, "reasoning_bytes": 95.54, "flops_per_problem": 5500068986.88}, "add.runmax.sumd6": {"acc": 0.488, "reasoning_bytes": 129.424, "flops_per_problem": 7173849415.68}, "add.runmax.sumd7": {"acc": 0.578, "reasoning_bytes": 142.164, "flops_per_problem": 7824106487.808}, "add.runmax.sumd8": {"acc": 0.466, "reasoning_bytes": 160.236, "flops_per_problem": 8714963976.192}, "parity.runmax.sumd16": {"acc": 0.522, "reasoning_bytes": 121.36, "flops_per_problem": 7081990225.92}, "parity.runmax.sumd20": {"acc": 0.48, "reasoning_bytes": 144.98, "flops_per_problem": 8301774274.56}, "parity.runmax.sumd24": {"acc": 0.466, "reasoning_bytes": 168.502, "flops_per_problem": 9517230342.144}, "count.runmax.inc16": {"acc": 0.004, "reasoning_bytes": 115.636, "flops_per_problem": 6996932149.248}, "count.runmax.inc18": {"acc": 0.006, "reasoning_bytes": 124.95, "flops_per_problem": 7526094077.952}, "count.runmax.inc20": {"acc": 0.02, "reasoning_bytes": 139.366, "flops_per_problem": 8191278268.416}, "runmax.runmax.inc12": {"acc": 0.544, "reasoning_bytes": 106.648, "flops_per_problem": 6222576844.8}, "runmax.runmax.inc14": {"acc": 0.396, "reasoning_bytes": 118.862, "flops_per_problem": 6848279248.896}, "runmax.runmax.inc16": {"acc": 0.628, "reasoning_bytes": 124.666, "flops_per_problem": 7205823479.808}, "add.runmax.inc6": {"acc": 0.492, "reasoning_bytes": 130.592, "flops_per_problem": 7198050779.136}, "add.runmax.inc7": {"acc": 0.558, "reasoning_bytes": 142.262, "flops_per_problem": 7804321431.552}, "add.runmax.inc8": {"acc": 0.418, "reasoning_bytes": 160.414, "flops_per_problem": 8692970766.336}, "count.count.cmp16": {"acc": 0.73, "reasoning_bytes": 112.67, "flops_per_problem": 6874070482.944}, "count.count.cmp18": {"acc": 0.736, "reasoning_bytes": 125.722, "flops_per_problem": 7527242317.824}, "count.count.cmp20": {"acc": 0.778, "reasoning_bytes": 136.12, "flops_per_problem": 8073097887.744}, "add.count.cmp6": {"acc": 0.86, "reasoning_bytes": 119.624, "flops_per_problem": 6830790672.384}, "add.count.cmp7": {"acc": 0.844, "reasoning_bytes": 135.506, "flops_per_problem": 7618394898.432}, "add.count.cmp8": {"acc": 0.792, "reasoning_bytes": 151.284, "flops_per_problem": 8403525992.448}, "sumd.count.cmp6": {"acc": 0.96, "reasoning_bytes": 79.934, "flops_per_problem": 4810860085.248}, "sumd.count.cmp7": {"acc": 0.908, "reasoning_bytes": 83.202, "flops_per_problem": 4999348076.544}, "sumd.count.cmp8": {"acc": 0.894, "reasoning_bytes": 88.218, "flops_per_problem": 5265033117.696}, "add.count.runmax6": {"acc": 0.494, "reasoning_bytes": 127.33, "flops_per_problem": 7213596180.48}, "add.count.runmax7": {"acc": 0.466, "reasoning_bytes": 137.582, "flops_per_problem": 7755388747.776}, "add.count.runmax8": {"acc": 0.43, "reasoning_bytes": 153.416, "flops_per_problem": 8554387046.4}, "sumd.count.runmax6": {"acc": 0.926, "reasoning_bytes": 82.868, "flops_per_problem": 4984597610.496}, "sumd.count.runmax7": {"acc": 0.898, "reasoning_bytes": 89.92, "flops_per_problem": 5340022013.952}, "sumd.count.runmax8": {"acc": 0.85, "reasoning_bytes": 95.68, "flops_per_problem": 5638652706.816}, "inc.count.runmax6": {"acc": 0.552, "reasoning_bytes": 107.996, "flops_per_problem": 6050694168.576}, "inc.count.runmax7": {"acc": 0.486, "reasoning_bytes": 119.404, "flops_per_problem": 6598139609.088}, "inc.count.runmax8": {"acc": 0.48, "reasoning_bytes": 133.654, "flops_per_problem": 7272774696.96}, "parity.count.count16": {"acc": 1.0, "reasoning_bytes": 123.6, "flops_per_problem": 7357567795.2}, "parity.count.count20": {"acc": 1.0, "reasoning_bytes": 147.024, "flops_per_problem": 8568695881.728}, "parity.count.count24": {"acc": 0.744, "reasoning_bytes": 163.538, "flops_per_problem": 9564308176.896}, "runmax.count.count12": {"acc": 1.0, "reasoning_bytes": 105.372, "flops_per_problem": 6375911030.784}, "runmax.count.count14": {"acc": 1.0, "reasoning_bytes": 117.48, "flops_per_problem": 6998963650.56}, "runmax.count.count16": {"acc": 0.646, "reasoning_bytes": 131.282, "flops_per_problem": 7705484476.416}, "inc.count.count6": {"acc": 0.976, "reasoning_bytes": 113.146, "flops_per_problem": 6324681867.264}, "inc.count.count7": {"acc": 0.996, "reasoning_bytes": 120.794, "flops_per_problem": 6705809178.624}, "inc.count.count8": {"acc": 1.0, "reasoning_bytes": 134.49, "flops_per_problem": 7352709857.28}, "inc.count.find6": {"acc": 0.888, "reasoning_bytes": 112.318, "flops_per_problem": 6241037008.896}, "inc.count.find7": {"acc": 0.86, "reasoning_bytes": 119.984, "flops_per_problem": 6623754190.848}, "inc.count.find8": {"acc": 0.846, "reasoning_bytes": 133.89, "flops_per_problem": 7282048942.08}, "add.count.find6": {"acc": 0.87, "reasoning_bytes": 129.088, "flops_per_problem": 7290793230.336}, "add.count.find7": {"acc": 0.818, "reasoning_bytes": 139.498, "flops_per_problem": 7839916867.584}, "add.count.find8": {"acc": 0.824, "reasoning_bytes": 153.272, "flops_per_problem": 8535661903.872}, "runmax.count.find12": {"acc": 1.0, "reasoning_bytes": 105.826, "flops_per_problem": 6351797993.472}, "runmax.count.find14": {"acc": 0.986, "reasoning_bytes": 118.76, "flops_per_problem": 7013095833.6}, "runmax.count.find16": {"acc": 0.312, "reasoning_bytes": 128.314, "flops_per_problem": 7595695079.424}, "parity.count.rev16": {"acc": 1.0, "reasoning_bytes": 118.66, "flops_per_problem": 6962749931.52}, "parity.count.rev20": {"acc": 1.0, "reasoning_bytes": 142.084, "flops_per_problem": 8173878018.048}, "parity.count.rev24": {"acc": 0.998, "reasoning_bytes": 163.812, "flops_per_problem": 9310105534.464}, "inc.count.rev6": {"acc": 0.54, "reasoning_bytes": 103.716, "flops_per_problem": 5745615667.2}, "inc.count.rev7": {"acc": 0.448, "reasoning_bytes": 115.514, "flops_per_problem": 6310373031.936}, "inc.count.rev8": {"acc": 0.298, "reasoning_bytes": 131.676, "flops_per_problem": 7222693773.312}, "runmax.count.rev12": {"acc": 1.0, "reasoning_bytes": 100.888, "flops_per_problem": 6001231527.936}, "runmax.count.rev14": {"acc": 0.978, "reasoning_bytes": 113.564, "flops_per_problem": 6650252034.048}, "runmax.count.rev16": {"acc": 0.708, "reasoning_bytes": 123.736, "flops_per_problem": 7214656094.208}, "count.count.sumd16": {"acc": 0.2, "reasoning_bytes": 114.63, "flops_per_problem": 6988452839.424}, "count.count.sumd18": {"acc": 0.296, "reasoning_bytes": 123.508, "flops_per_problem": 7497476407.296}, "count.count.sumd20": {"acc": 0.57, "reasoning_bytes": 139.268, "flops_per_problem": 8189158440.96}, "runmax.count.sumd12": {"acc": 1.0, "reasoning_bytes": 103.912, "flops_per_problem": 6178943729.664}, "runmax.count.sumd14": {"acc": 0.988, "reasoning_bytes": 116.398, "flops_per_problem": 6822664667.136}, "runmax.count.sumd16": {"acc": 0.74, "reasoning_bytes": 129.826, "flops_per_problem": 7573701869.568}, "sumd.count.sumd6": {"acc": 0.928, "reasoning_bytes": 81.174, "flops_per_problem": 4821459222.528}, "sumd.count.sumd7": {"acc": 0.894, "reasoning_bytes": 88.596, "flops_per_problem": 5193223962.624}, "sumd.count.sumd8": {"acc": 0.846, "reasoning_bytes": 94.814, "flops_per_problem": 5511904690.176}, "parity.count.inc16": {"acc": 1.0, "reasoning_bytes": 122.48, "flops_per_problem": 7131452866.56}, "parity.count.inc20": {"acc": 1.0, "reasoning_bytes": 146.024, "flops_per_problem": 8347880521.728}, "parity.count.inc24": {"acc": 0.994, "reasoning_bytes": 167.754, "flops_per_problem": 9484196364.288}, "count.count.inc16": {"acc": 0.026, "reasoning_bytes": 115.19, "flops_per_problem": 6994017386.496}, "count.count.inc18": {"acc": 0.026, "reasoning_bytes": 124.776, "flops_per_problem": 7506838978.56}, "count.count.inc20": {"acc": 0.202, "reasoning_bytes": 140.584, "flops_per_problem": 8181032435.712}, "add.count.inc6": {"acc": 0.324, "reasoning_bytes": 126.08, "flops_per_problem": 7030054453.248}, "add.count.inc7": {"acc": 0.324, "reasoning_bytes": 137.222, "flops_per_problem": 7607530782.72}, "add.count.inc8": {"acc": 0.264, "reasoning_bytes": 152.648, "flops_per_problem": 8389658787.84}, "parity.rev.cmp16": {"acc": 0.95, "reasoning_bytes": 117.252, "flops_per_problem": 6812242182.144}, "parity.rev.cmp20": {"acc": 0.954, "reasoning_bytes": 142.132, "flops_per_problem": 8087671701.504}, "parity.rev.cmp24": {"acc": 0.672, "reasoning_bytes": 163.39, "flops_per_problem": 9204732444.672}, "sumd.rev.cmp6": {"acc": 0.596, "reasoning_bytes": 80.886, "flops_per_problem": 4720237461.504}, "sumd.rev.cmp7": {"acc": 0.568, "reasoning_bytes": 88.508, "flops_per_problem": 5101188120.576}, "sumd.rev.cmp8": {"acc": 0.494, "reasoning_bytes": 94.548, "flops_per_problem": 5412096147.456}, "add.rev.cmp6": {"acc": 0.528, "reasoning_bytes": 150.82, "flops_per_problem": 8289761918.976}, "add.rev.cmp7": {"acc": 0.348, "reasoning_bytes": 177.74, "flops_per_problem": 9644684967.936}, "add.rev.cmp8": {"acc": 0.19, "reasoning_bytes": 211.708, "flops_per_problem": 11372520996.864}, "runmax.rev.runmax12": {"acc": 0.994, "reasoning_bytes": 100.012, "flops_per_problem": 5918381604.864}, "runmax.rev.runmax14": {"acc": 0.99, "reasoning_bytes": 112.176, "flops_per_problem": 6543907356.672}, "runmax.rev.runmax16": {"acc": 0.61, "reasoning_bytes": 124.096, "flops_per_problem": 7158657318.912}, "count.rev.runmax16": {"acc": 0.0, "reasoning_bytes": 111.626, "flops_per_problem": 6798463303.68}, "count.rev.runmax18": {"acc": 0.004, "reasoning_bytes": 120.76, "flops_per_problem": 7327978536.96}, "count.rev.runmax20": {"acc": 0.026, "reasoning_bytes": 136.528, "flops_per_problem": 8025225117.696}, "add.rev.runmax6": {"acc": 0.414, "reasoning_bytes": 168.562, "flops_per_problem": 8857699024.896}, "add.rev.runmax7": {"acc": 0.442, "reasoning_bytes": 192.926, "flops_per_problem": 10022102581.248}, "add.rev.runmax8": {"acc": 0.26, "reasoning_bytes": 221.702, "flops_per_problem": 11382943481.856}, "inc.rev.count6": {"acc": 0.55, "reasoning_bytes": 142.848, "flops_per_problem": 7458701230.08}, "inc.rev.count7": {"acc": 0.454, "reasoning_bytes": 160.486, "flops_per_problem": 8285522264.064}, "inc.rev.count8": {"acc": 0.376, "reasoning_bytes": 186.94, "flops_per_problem": 9515640471.552}, "count.rev.count16": {"acc": 0.062, "reasoning_bytes": 111.196, "flops_per_problem": 6844127920.128}, "count.rev.count18": {"acc": 0.03, "reasoning_bytes": 119.588, "flops_per_problem": 7369845129.216}, "count.rev.count20": {"acc": 0.604, "reasoning_bytes": 137.88, "flops_per_problem": 8154269614.08}, "parity.rev.count16": {"acc": 1.0, "reasoning_bytes": 119.366, "flops_per_problem": 6993929060.352}, "parity.rev.count20": {"acc": 1.0, "reasoning_bytes": 142.292, "flops_per_problem": 8183063937.024}, "parity.rev.count24": {"acc": 1.0, "reasoning_bytes": 166.276, "flops_per_problem": 9418923343.872}, "sumd.rev.find6": {"acc": 0.758, "reasoning_bytes": 85.216, "flops_per_problem": 4911640215.552}, "sumd.rev.find7": {"acc": 0.68, "reasoning_bytes": 93.148, "flops_per_problem": 5305928122.368}, "sumd.rev.find8": {"acc": 0.64, "reasoning_bytes": 99.794, "flops_per_problem": 5643863949.312}, "runmax.rev.find12": {"acc": 0.952, "reasoning_bytes": 102.688, "flops_per_problem": 6036561985.536}, "runmax.rev.find14": {"acc": 0.93, "reasoning_bytes": 115.594, "flops_per_problem": 6694856736.768}, "runmax.rev.find16": {"acc": 0.914, "reasoning_bytes": 123.886, "flops_per_problem": 7149206421.504}, "count.rev.find16": {"acc": 0.276, "reasoning_bytes": 112.03, "flops_per_problem": 6766577565.696}, "count.rev.find18": {"acc": 0.26, "reasoning_bytes": 122.0, "flops_per_problem": 7292913057.792}, "count.rev.find20": {"acc": 0.206, "reasoning_bytes": 130.794, "flops_per_problem": 7827109576.704}, "count.rev.rev16": {"acc": 0.004, "reasoning_bytes": 108.192, "flops_per_problem": 6445865336.832}, "count.rev.rev18": {"acc": 0.002, "reasoning_bytes": 118.034, "flops_per_problem": 6975733874.688}, "count.rev.rev20": {"acc": 0.016, "reasoning_bytes": 133.448, "flops_per_problem": 7703806279.68}, "sumd.rev.rev6": {"acc": 0.398, "reasoning_bytes": 80.356, "flops_per_problem": 4605855105.024}, "sumd.rev.rev7": {"acc": 0.148, "reasoning_bytes": 87.47, "flops_per_problem": 4954831699.968}, "sumd.rev.rev8": {"acc": 0.05, "reasoning_bytes": 93.502, "flops_per_problem": 5258673635.328}, "parity.rev.rev16": {"acc": 0.534, "reasoning_bytes": 114.884, "flops_per_problem": 6619337883.648}, "parity.rev.rev20": {"acc": 0.548, "reasoning_bytes": 137.504, "flops_per_problem": 7794958860.288}, "parity.rev.rev24": {"acc": 0.534, "reasoning_bytes": 161.612, "flops_per_problem": 9036294488.064}, "sumd.rev.sumd6": {"acc": 0.418, "reasoning_bytes": 84.488, "flops_per_problem": 4800790904.832}, "sumd.rev.sumd7": {"acc": 0.246, "reasoning_bytes": 92.036, "flops_per_problem": 5176530321.408}, "sumd.rev.sumd8": {"acc": 0.132, "reasoning_bytes": 98.06, "flops_per_problem": 5483993628.672}, "parity.rev.sumd16": {"acc": 0.536, "reasoning_bytes": 116.96, "flops_per_problem": 6755183493.12}, "parity.rev.sumd20": {"acc": 0.544, "reasoning_bytes": 139.796, "flops_per_problem": 7940343693.312}, "parity.rev.sumd24": {"acc": 0.476, "reasoning_bytes": 164.978, "flops_per_problem": 9230170374.144}, "add.rev.sumd6": {"acc": 0.04, "reasoning_bytes": 169.876, "flops_per_problem": 8869269749.76}, "add.rev.sumd7": {"acc": 0.026, "reasoning_bytes": 195.756, "flops_per_problem": 10105040830.464}, "add.rev.sumd8": {"acc": 0.018, "reasoning_bytes": 223.832, "flops_per_problem": 11439648866.304}, "parity.rev.inc16": {"acc": 0.546, "reasoning_bytes": 118.848, "flops_per_problem": 6794400301.056}, "parity.rev.inc20": {"acc": 0.54, "reasoning_bytes": 141.516, "flops_per_problem": 7972141105.152}, "parity.rev.inc24": {"acc": 0.496, "reasoning_bytes": 166.104, "flops_per_problem": 9234675007.488}, "runmax.rev.inc12": {"acc": 0.678, "reasoning_bytes": 101.702, "flops_per_problem": 5883139473.408}, "runmax.rev.inc14": {"acc": 0.708, "reasoning_bytes": 112.778, "flops_per_problem": 6464060522.496}, "runmax.rev.inc16": {"acc": 0.82, "reasoning_bytes": 121.086, "flops_per_problem": 6923444797.44}, "inc.rev.inc6": {"acc": 0.0, "reasoning_bytes": 153.87, "flops_per_problem": 7903864995.84}, "inc.rev.inc7": {"acc": 0.0, "reasoning_bytes": 176.198, "flops_per_problem": 8962277179.392}, "inc.rev.inc8": {"acc": 0.0, "reasoning_bytes": 199.496, "flops_per_problem": 10141077897.216}, "parity.sumd.cmp16": {"acc": 0.934, "reasoning_bytes": 120.084, "flops_per_problem": 6981475074.048}, "parity.sumd.cmp20": {"acc": 0.946, "reasoning_bytes": 145.484, "flops_per_problem": 8279869390.848}, "parity.sumd.cmp24": {"acc": 0.94, "reasoning_bytes": 169.148, "flops_per_problem": 9501508288.512}, "runmax.sumd.cmp12": {"acc": 0.87, "reasoning_bytes": 102.204, "flops_per_problem": 6014922080.256}, "runmax.sumd.cmp14": {"acc": 0.936, "reasoning_bytes": 107.964, "flops_per_problem": 6360807260.16}, "runmax.sumd.cmp16": {"acc": 0.942, "reasoning_bytes": 119.86, "flops_per_problem": 6972554133.504}, "count.sumd.cmp16": {"acc": 0.088, "reasoning_bytes": 111.958, "flops_per_problem": 6858083450.88}, "count.sumd.cmp18": {"acc": 0.22, "reasoning_bytes": 126.9, "flops_per_problem": 7605057650.688}, "count.sumd.cmp20": {"acc": 0.184, "reasoning_bytes": 136.448, "flops_per_problem": 8245068890.112}, "sumd.sumd.runmax6": {"acc": 0.47, "reasoning_bytes": 83.422, "flops_per_problem": 4876574736.384}, "sumd.sumd.runmax7": {"acc": 0.264, "reasoning_bytes": 90.132, "flops_per_problem": 5217072021.504}, "sumd.sumd.runmax8": {"acc": 0.154, "reasoning_bytes": 96.582, "flops_per_problem": 5546086907.904}, "count.sumd.runmax16": {"acc": 0.014, "reasoning_bytes": 114.95, "flops_per_problem": 6927949430.784}, "count.sumd.runmax18": {"acc": 0.008, "reasoning_bytes": 122.832, "flops_per_problem": 7411711721.472}, "count.sumd.runmax20": {"acc": 0.028, "reasoning_bytes": 135.788, "flops_per_problem": 8044126912.512}, "add.sumd.runmax6": {"acc": 0.2, "reasoning_bytes": 140.524, "flops_per_problem": 7663441231.872}, "add.sumd.runmax7": {"acc": 0.142, "reasoning_bytes": 155.568, "flops_per_problem": 8416598261.76}, "add.sumd.runmax8": {"acc": 0.112, "reasoning_bytes": 175.466, "flops_per_problem": 9387655888.896}, "parity.sumd.count16": {"acc": 1.0, "reasoning_bytes": 121.382, "flops_per_problem": 7127124885.504}, "parity.sumd.count20": {"acc": 1.0, "reasoning_bytes": 145.072, "flops_per_problem": 8350000349.184}, "parity.sumd.count24": {"acc": 0.648, "reasoning_bytes": 160.404, "flops_per_problem": 9328124067.84}, "sumd.sumd.count6": {"acc": 0.94, "reasoning_bytes": 83.912, "flops_per_problem": 4942377713.664}, "sumd.sumd.count7": {"acc": 0.894, "reasoning_bytes": 91.046, "flops_per_problem": 5301600141.312}, "sumd.sumd.count8": {"acc": 0.82, "reasoning_bytes": 96.928, "flops_per_problem": 5605883707.392}, "add.sumd.count6": {"acc": 0.798, "reasoning_bytes": 144.402, "flops_per_problem": 7879133675.52}, "add.sumd.count7": {"acc": 0.71, "reasoning_bytes": 158.186, "flops_per_problem": 8576556908.544}, "add.sumd.count8": {"acc": 0.674, "reasoning_bytes": 174.928, "flops_per_problem": 9405321117.696}, "runmax.sumd.find12": {"acc": 0.96, "reasoning_bytes": 101.404, "flops_per_problem": 6024019673.088}, "runmax.sumd.find14": {"acc": 0.952, "reasoning_bytes": 109.724, "flops_per_problem": 6479782576.128}, "runmax.sumd.find16": {"acc": 0.926, "reasoning_bytes": 121.952, "flops_per_problem": 7108134764.544}, "sumd.sumd.find6": {"acc": 0.836, "reasoning_bytes": 83.438, "flops_per_problem": 4877281345.536}, "sumd.sumd.find7": {"acc": 0.76, "reasoning_bytes": 90.774, "flops_per_problem": 5245424713.728}, "sumd.sumd.find8": {"acc": 0.704, "reasoning_bytes": 95.364, "flops_per_problem": 5492296286.208}, "parity.sumd.find16": {"acc": 0.864, "reasoning_bytes": 122.992, "flops_per_problem": 7154064359.424}, "parity.sumd.find20": {"acc": 0.864, "reasoning_bytes": 145.636, "flops_per_problem": 8330745249.792}, "parity.sumd.find24": {"acc": 0.882, "reasoning_bytes": 169.424, "flops_per_problem": 9557948694.528}, "count.sumd.rev16": {"acc": 0.006, "reasoning_bytes": 109.616, "flops_per_problem": 6612801748.992}, "count.sumd.rev18": {"acc": 0.002, "reasoning_bytes": 119.792, "flops_per_problem": 7135162564.608}, "count.sumd.rev20": {"acc": 0.01, "reasoning_bytes": 133.146, "flops_per_problem": 7801406668.8}, "parity.sumd.rev16": {"acc": 0.534, "reasoning_bytes": 116.444, "flops_per_problem": 6732395347.968}, "parity.sumd.rev20": {"acc": 0.524, "reasoning_bytes": 140.06, "flops_per_problem": 7952002744.32}, "parity.sumd.rev24": {"acc": 0.468, "reasoning_bytes": 162.536, "flops_per_problem": 9121794195.456}, "add.sumd.rev6": {"acc": 0.038, "reasoning_bytes": 132.92, "flops_per_problem": 7230819778.56}, "add.sumd.rev7": {"acc": 0.024, "reasoning_bytes": 149.028, "flops_per_problem": 8031584600.064}, "add.sumd.rev8": {"acc": 0.034, "reasoning_bytes": 167.848, "flops_per_problem": 8956447653.888}, "parity.sumd.sumd16": {"acc": 0.498, "reasoning_bytes": 119.336, "flops_per_problem": 6904278024.192}, "parity.sumd.sumd20": {"acc": 0.522, "reasoning_bytes": 143.06, "flops_per_problem": 8128655032.32}, "parity.sumd.sumd24": {"acc": 0.466, "reasoning_bytes": 165.002, "flops_per_problem": 9274333446.144}, "add.sumd.sumd6": {"acc": 0.094, "reasoning_bytes": 140.428, "flops_per_problem": 7579266416.64}, "add.sumd.sumd7": {"acc": 0.084, "reasoning_bytes": 155.314, "flops_per_problem": 8327653834.752}, "add.sumd.sumd8": {"acc": 0.064, "reasoning_bytes": 170.88, "flops_per_problem": 9160922677.248}, "count.sumd.sumd16": {"acc": 0.006, "reasoning_bytes": 112.462, "flops_per_problem": 6799258238.976}, "count.sumd.sumd18": {"acc": 0.018, "reasoning_bytes": 122.258, "flops_per_problem": 7324268838.912}, "count.sumd.sumd20": {"acc": 0.016, "reasoning_bytes": 134.974, "flops_per_problem": 8012241174.528}, "inc.sumd.inc6": {"acc": 0.068, "reasoning_bytes": 129.972, "flops_per_problem": 6789277384.704}, "inc.sumd.inc7": {"acc": 0.022, "reasoning_bytes": 139.762, "flops_per_problem": 7264648691.712}, "inc.sumd.inc8": {"acc": 0.01, "reasoning_bytes": 154.276, "flops_per_problem": 7947321458.688}, "sumd.sumd.inc6": {"acc": 0.462, "reasoning_bytes": 83.234, "flops_per_problem": 4748943458.304}, "sumd.sumd.inc7": {"acc": 0.242, "reasoning_bytes": 90.304, "flops_per_problem": 5102954643.456}, "sumd.sumd.inc8": {"acc": 0.132, "reasoning_bytes": 95.762, "flops_per_problem": 5385774956.544}, "parity.sumd.inc16": {"acc": 0.502, "reasoning_bytes": 120.288, "flops_per_problem": 6902158196.736}, "parity.sumd.inc20": {"acc": 0.528, "reasoning_bytes": 144.024, "flops_per_problem": 8127065161.728}, "parity.sumd.inc24": {"acc": 0.408, "reasoning_bytes": 166.346, "flops_per_problem": 9289525542.912}, "inc.inc.cmp6": {"acc": 0.472, "reasoning_bytes": 143.566, "flops_per_problem": 7636148453.376}, "inc.inc.cmp7": {"acc": 0.42, "reasoning_bytes": 154.932, "flops_per_problem": 8230671728.64}, "inc.inc.cmp8": {"acc": 0.324, "reasoning_bytes": 162.302, "flops_per_problem": 8674598928.384}, "runmax.inc.cmp12": {"acc": 0.864, "reasoning_bytes": 107.208, "flops_per_problem": 6223283453.952}, "runmax.inc.cmp14": {"acc": 0.214, "reasoning_bytes": 111.294, "flops_per_problem": 6496122912.768}, "runmax.inc.cmp16": {"acc": 0.366, "reasoning_bytes": 125.938, "flops_per_problem": 7252018053.12}, "sumd.inc.cmp6": {"acc": 0.804, "reasoning_bytes": 87.948, "flops_per_problem": 5032028749.824}, "sumd.inc.cmp7": {"acc": 0.772, "reasoning_bytes": 95.554, "flops_per_problem": 5412361125.888}, "sumd.inc.cmp8": {"acc": 0.74, "reasoning_bytes": 100.254, "flops_per_problem": 5665592180.736}, "sumd.inc.runmax6": {"acc": 0.536, "reasoning_bytes": 93.048, "flops_per_problem": 5257613721.6}, "sumd.inc.runmax7": {"acc": 0.292, "reasoning_bytes": 99.836, "flops_per_problem": 5603410575.36}, "sumd.inc.runmax8": {"acc": 0.188, "reasoning_bytes": 105.538, "flops_per_problem": 5898773200.896}, "runmax.inc.runmax12": {"acc": 0.978, "reasoning_bytes": 108.088, "flops_per_problem": 6275042574.336}, "runmax.inc.runmax14": {"acc": 0.824, "reasoning_bytes": 119.69, "flops_per_problem": 6875748679.68}, "runmax.inc.runmax16": {"acc": 0.524, "reasoning_bytes": 125.372, "flops_per_problem": 7229318234.112}, "add.inc.runmax6": {"acc": 0.38, "reasoning_bytes": 176.142, "flops_per_problem": 9193161719.808}, "add.inc.runmax7": {"acc": 0.426, "reasoning_bytes": 196.234, "flops_per_problem": 10169165611.008}, "add.inc.runmax8": {"acc": 0.348, "reasoning_bytes": 221.986, "flops_per_problem": 11395750772.736}, "runmax.inc.count12": {"acc": 0.998, "reasoning_bytes": 108.462, "flops_per_problem": 6335722635.264}, "runmax.inc.count14": {"acc": 0.974, "reasoning_bytes": 115.016, "flops_per_problem": 6714818445.312}, "runmax.inc.count16": {"acc": 0.7, "reasoning_bytes": 117.886, "flops_per_problem": 6941021700.096}, "sumd.inc.count6": {"acc": 0.926, "reasoning_bytes": 92.474, "flops_per_problem": 5276338864.128}, "sumd.inc.count7": {"acc": 0.894, "reasoning_bytes": 99.668, "flops_per_problem": 5639624294.4}, "sumd.inc.count8": {"acc": 0.9, "reasoning_bytes": 105.302, "flops_per_problem": 5931630526.464}, "inc.inc.count6": {"acc": 0.448, "reasoning_bytes": 152.732, "flops_per_problem": 7897505513.472}, "inc.inc.count7": {"acc": 0.432, "reasoning_bytes": 167.924, "flops_per_problem": 8611799040.0}, "inc.inc.count8": {"acc": 0.358, "reasoning_bytes": 190.484, "flops_per_problem": 9668709679.104}, "parity.inc.find16": {"acc": 0.868, "reasoning_bytes": 124.436, "flops_per_problem": 7173672763.392}, "parity.inc.find20": {"acc": 0.864, "reasoning_bytes": 147.38, "flops_per_problem": 8363602575.36}, "parity.inc.find24": {"acc": 0.846, "reasoning_bytes": 171.604, "flops_per_problem": 9610061119.488}, "sumd.inc.find6": {"acc": 0.726, "reasoning_bytes": 93.588, "flops_per_problem": 5281373454.336}, "sumd.inc.find7": {"acc": 0.674, "reasoning_bytes": 101.104, "flops_per_problem": 5657377849.344}, "sumd.inc.find8": {"acc": 0.616, "reasoning_bytes": 106.134, "flops_per_problem": 5923769499.648}, "count.inc.find16": {"acc": 0.444, "reasoning_bytes": 114.928, "flops_per_problem": 6843156332.544}, "count.inc.find18": {"acc": 0.472, "reasoning_bytes": 124.722, "flops_per_problem": 7362602385.408}, "count.inc.find20": {"acc": 0.636, "reasoning_bytes": 137.456, "flops_per_problem": 7992456118.272}, "sumd.inc.rev6": {"acc": 0.446, "reasoning_bytes": 87.262, "flops_per_problem": 4913318412.288}, "sumd.inc.rev7": {"acc": 0.19, "reasoning_bytes": 94.326, "flops_per_problem": 5272010883.072}, "sumd.inc.rev8": {"acc": 0.078, "reasoning_bytes": 99.96, "flops_per_problem": 5558540894.208}, "count.inc.rev16": {"acc": 0.036, "reasoning_bytes": 115.976, "flops_per_problem": 6749000663.04}, "count.inc.rev18": {"acc": 0.036, "reasoning_bytes": 125.326, "flops_per_problem": 7268005085.184}, "count.inc.rev20": {"acc": 0.06, "reasoning_bytes": 138.79, "flops_per_problem": 7935397429.248}, "parity.inc.rev16": {"acc": 0.558, "reasoning_bytes": 117.612, "flops_per_problem": 6739814744.064}, "parity.inc.rev20": {"acc": 0.522, "reasoning_bytes": 141.12, "flops_per_problem": 7954652528.64}, "parity.inc.rev24": {"acc": 0.422, "reasoning_bytes": 164.388, "flops_per_problem": 9158891175.936}, "count.inc.sumd16": {"acc": 0.03, "reasoning_bytes": 117.042, "flops_per_problem": 6919470120.96}, "count.inc.sumd18": {"acc": 0.018, "reasoning_bytes": 126.372, "flops_per_problem": 7445187330.048}, "count.inc.sumd20": {"acc": 0.038, "reasoning_bytes": 139.544, "flops_per_problem": 8083520372.736}, "sumd.inc.sumd6": {"acc": 0.394, "reasoning_bytes": 91.408, "flops_per_problem": 5102513012.736}, "sumd.inc.sumd7": {"acc": 0.24, "reasoning_bytes": 98.696, "flops_per_problem": 5466946682.88}, "sumd.inc.sumd8": {"acc": 0.112, "reasoning_bytes": 104.696, "flops_per_problem": 5774498316.288}, "add.inc.sumd6": {"acc": 0.048, "reasoning_bytes": 177.626, "flops_per_problem": 9212505145.344}, "add.inc.sumd7": {"acc": 0.042, "reasoning_bytes": 198.652, "flops_per_problem": 10233202065.408}, "add.inc.sumd8": {"acc": 0.028, "reasoning_bytes": 223.206, "flops_per_problem": 11416949047.296}, "parity.inc.inc16": {"acc": 0.524, "reasoning_bytes": 121.804, "flops_per_problem": 6924946341.888}, "parity.inc.inc20": {"acc": 0.53, "reasoning_bytes": 145.072, "flops_per_problem": 8129184989.184}, "parity.inc.inc24": {"acc": 0.504, "reasoning_bytes": 168.676, "flops_per_problem": 9348262428.672}, "sumd.inc.inc6": {"acc": 0.304, "reasoning_bytes": 94.328, "flops_per_problem": 5218308587.52}, "sumd.inc.inc7": {"acc": 0.106, "reasoning_bytes": 101.522, "flops_per_problem": 5577442689.024}, "sumd.inc.inc8": {"acc": 0.044, "reasoning_bytes": 107.232, "flops_per_problem": 5868035702.784}, "runmax.inc.inc12": {"acc": 0.914, "reasoning_bytes": 109.936, "flops_per_problem": 6260998717.44}, "runmax.inc.inc14": {"acc": 0.654, "reasoning_bytes": 120.34, "flops_per_problem": 6800848109.568}, "runmax.inc.inc16": {"acc": 0.064, "reasoning_bytes": 118.392, "flops_per_problem": 6811270594.56}, "count.inc.cmp16": {"acc": 0.314, "reasoning_bytes": 113.2, "flops_per_problem": 6755448471.552}, "count.inc.cmp18": {"acc": 0.334, "reasoning_bytes": 123.29, "flops_per_problem": 7293884645.376}, "count.inc.cmp20": {"acc": 0.24, "reasoning_bytes": 132.778, "flops_per_problem": 7866149732.352}, "inc.rev.sumd6": {"acc": 0.052, "reasoning_bytes": 152.272, "flops_per_problem": 7783034830.848}, "inc.rev.sumd7": {"acc": 0.032, "reasoning_bytes": 175.182, "flops_per_problem": 8849396367.36}, "inc.rev.sumd8": {"acc": 0.016, "reasoning_bytes": 199.124, "flops_per_problem": 10018746187.776}, "runmax.inc.find12": {"acc": 0.756, "reasoning_bytes": 97.984, "flops_per_problem": 5828818894.848}, "runmax.inc.find14": {"acc": 0.764, "reasoning_bytes": 107.836, "flops_per_problem": 6352239624.192}, "runmax.inc.find16": {"acc": 0.754, "reasoning_bytes": 119.92, "flops_per_problem": 6974232330.24}, "inc.runmax.cmp6": {"acc": 0.794, "reasoning_bytes": 108.254, "flops_per_problem": 5973232140.288}, "inc.runmax.cmp7": {"acc": 0.728, "reasoning_bytes": 124.06, "flops_per_problem": 6715436728.32}, "inc.runmax.cmp8": {"acc": 0.726, "reasoning_bytes": 136.78, "flops_per_problem": 7321354076.16}} +{"step": 1000, "train_loss": 1.487887978553772} +{"step": 1020, "train_loss": 1.3392025232315063} +{"step": 1040, "train_loss": 1.4668185710906982} +{"step": 1060, "train_loss": 1.327368974685669} +{"step": 1080, "train_loss": 1.5004302263259888} +{"step": 1100, "train_loss": 1.4645016193389893} +{"step": 1120, "train_loss": 1.5332791805267334} +{"step": 1140, "train_loss": 1.5329192876815796} +{"step": 1160, "train_loss": 1.4094481468200684} +{"step": 1180, "train_loss": 1.5052944421768188} +{"step": 1200, "train_loss": 1.4908428192138672} +{"step": 1220, "train_loss": 1.465378999710083} +{"step": 1240, "train_loss": 1.3998417854309082} +{"step": 1260, "train_loss": 1.393520712852478} +{"step": 1280, "train_loss": 1.46268630027771} +{"step": 1300, "train_loss": 1.4271783828735352} +{"step": 1320, "train_loss": 1.3719671964645386} +{"step": 1340, "train_loss": 1.3283358812332153} +{"step": 1360, "train_loss": 1.2758166790008545} +{"step": 1380, "train_loss": 1.4375898838043213} +{"step": 1400, "train_loss": 1.3065447807312012} +{"step": 1420, "train_loss": 1.3767015933990479} +{"step": 1440, "train_loss": 1.3919942378997803} +{"step": 1460, "train_loss": 1.3899407386779785} +{"step": 1480, "train_loss": 1.3490993976593018} +{"step": 1500, "train_loss": 1.2198078632354736} +{"step": 1520, "train_loss": 1.3886488676071167} +{"step": 1540, "train_loss": 1.3442597389221191} +{"step": 1560, "train_loss": 1.4095239639282227} +{"step": 1580, "train_loss": 1.32695734500885} +{"step": 1600, "train_loss": 1.342714786529541} +{"step": 1620, "train_loss": 1.3619472980499268} +{"step": 1640, "train_loss": 1.3414276838302612} +{"step": 1660, "train_loss": 1.3014036417007446} +{"step": 1680, "train_loss": 1.357635259628296} +{"step": 1700, "train_loss": 1.307172179222107} +{"step": 1720, "train_loss": 1.3464953899383545} +{"step": 1740, "train_loss": 1.2024890184402466} +{"step": 1760, "train_loss": 1.3093574047088623} +{"step": 1780, "train_loss": 1.308793544769287} +{"step": 1800, "train_loss": 1.3026654720306396} +{"step": 1820, "train_loss": 1.2786787748336792} +{"step": 1840, "train_loss": 1.2828985452651978} +{"step": 1860, "train_loss": 1.2278727293014526} +{"step": 1880, "train_loss": 1.2327367067337036} +{"step": 1900, "train_loss": 1.2773535251617432} +{"step": 1920, "train_loss": 1.198409080505371} +{"step": 1940, "train_loss": 1.3259412050247192} +{"step": 1960, "train_loss": 1.3408176898956299} +{"step": 1980, "train_loss": 1.3625870943069458} +{"step": 2000, "tokens": 65536000, "val_loss": 2.4004600048065186, "val_bpb": 0.8653268332462348, "lr": 0.0005717971803204413, "elapsed": 678.6034173965454, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.07, "reasoning_bytes": 79.0, "flops_per_problem": 4940699516.928}, "add9": {"acc": 0.0, "reasoning_bytes": 88.82, "flops_per_problem": 5515261083.648}, "add10": {"acc": 0.0, "reasoning_bytes": 97.382, "flops_per_problem": 6025256239.104}, "reach14": {"acc": 0.466, "reasoning_bytes": 4.486, "flops_per_problem": 4485996527.616}, "reach16": {"acc": 0.478, "reasoning_bytes": 4.552, "flops_per_problem": 5037504970.752}, "reach18": {"acc": 0.472, "reasoning_bytes": 4.204, "flops_per_problem": 5558540894.208}, "parity24": {"acc": 0.322, "reasoning_bytes": 145.064, "flops_per_problem": 7982033633.28}, "parity28": {"acc": 0.26, "reasoning_bytes": 168.392, "flops_per_problem": 9202965921.792}, "parity32": {"acc": 0.142, "reasoning_bytes": 193.416, "flops_per_problem": 10504539979.776}, "cmp8": {"acc": 0.844, "reasoning_bytes": 8.348, "flops_per_problem": 1478314672.128}, "cmp9": {"acc": 0.752, "reasoning_bytes": 9.248, "flops_per_problem": 1609655648.256}, "cmp10": {"acc": 0.628, "reasoning_bytes": 11.748, "flops_per_problem": 1814307323.904}, "runmax12": {"acc": 0.988, "reasoning_bytes": 71.012, "flops_per_problem": 4151858724.864}, "runmax14": {"acc": 0.914, "reasoning_bytes": 82.064, "flops_per_problem": 4728275140.608}, "runmax16": {"acc": 0.91, "reasoning_bytes": 90.888, "flops_per_problem": 5205854601.216}, "count16": {"acc": 0.636, "reasoning_bytes": 80.836, "flops_per_problem": 4806443778.048}, "count18": {"acc": 0.516, "reasoning_bytes": 90.976, "flops_per_problem": 5342141841.408}, "count20": {"acc": 0.362, "reasoning_bytes": 100.516, "flops_per_problem": 5851518713.856}, "brackets16": {"acc": 0.49, "reasoning_bytes": 58.728, "flops_per_problem": 3874337980.416}, "brackets18": {"acc": 0.5, "reasoning_bytes": 61.22, "flops_per_problem": 4072718499.84}, "brackets20": {"acc": 0.478, "reasoning_bytes": 66.65, "flops_per_problem": 4400850124.8}, "sumd8": {"acc": 0.384, "reasoning_bytes": 58.592, "flops_per_problem": 3384569511.936}, "sumd9": {"acc": 0.108, "reasoning_bytes": 66.098, "flops_per_problem": 3761545494.528}, "sumd10": {"acc": 0.04, "reasoning_bytes": 72.868, "flops_per_problem": 4107342348.288}, "inc8": {"acc": 0.464, "reasoning_bytes": 63.024, "flops_per_problem": 3811273113.6}, "inc9": {"acc": 0.038, "reasoning_bytes": 70.952, "flops_per_problem": 4246102720.512}, "inc10": {"acc": 0.0, "reasoning_bytes": 77.112, "flops_per_problem": 4614069436.416}, "add.cmp6": {"acc": 0.81, "reasoning_bytes": 95.204, "flops_per_problem": 5650223431.68}, "add.cmp7": {"acc": 0.794, "reasoning_bytes": 109.552, "flops_per_problem": 6420339081.216}, "add.cmp8": {"acc": 0.854, "reasoning_bytes": 122.64, "flops_per_problem": 7132071149.568}, "add.runmax6": {"acc": 0.934, "reasoning_bytes": 121.88, "flops_per_problem": 6617218056.192}, "add.runmax7": {"acc": 0.796, "reasoning_bytes": 140.562, "flops_per_problem": 7529097166.848}, "add.runmax8": {"acc": 0.502, "reasoning_bytes": 159.3, "flops_per_problem": 8444685975.552}, "add.count6": {"acc": 0.62, "reasoning_bytes": 117.47, "flops_per_problem": 6468035198.976}, "add.count7": {"acc": 0.492, "reasoning_bytes": 135.512, "flops_per_problem": 7353593118.72}, "add.count8": {"acc": 0.298, "reasoning_bytes": 153.84, "flops_per_problem": 8258052833.28}, "add.find6": {"acc": 0.49, "reasoning_bytes": 113.564, "flops_per_problem": 6251194515.456}, "add.find7": {"acc": 0.264, "reasoning_bytes": 132.55, "flops_per_problem": 7190189752.32}, "add.find8": {"acc": 0.156, "reasoning_bytes": 149.532, "flops_per_problem": 8043508629.504}, "add.rev6": {"acc": 0.332, "reasoning_bytes": 126.044, "flops_per_problem": 6919735099.392}, "add.rev7": {"acc": 0.046, "reasoning_bytes": 149.034, "flops_per_problem": 8063470338.048}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 168.244, "flops_per_problem": 9055196282.88}, "add.sumd6": {"acc": 0.634, "reasoning_bytes": 127.972, "flops_per_problem": 6844216246.272}, "add.sumd7": {"acc": 0.186, "reasoning_bytes": 148.634, "flops_per_problem": 7844774805.504}, "add.sumd8": {"acc": 0.028, "reasoning_bytes": 169.696, "flops_per_problem": 8863175245.824}, "add.inc6": {"acc": 0.452, "reasoning_bytes": 131.066, "flops_per_problem": 7144790114.304}, "add.inc7": {"acc": 0.06, "reasoning_bytes": 148.552, "flops_per_problem": 8043773607.936}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 162.774, "flops_per_problem": 8799050465.28}, "runmax.cmp12": {"acc": 0.94, "reasoning_bytes": 87.084, "flops_per_problem": 5126626050.048}, "runmax.cmp14": {"acc": 0.906, "reasoning_bytes": 99.044, "flops_per_problem": 5743054209.024}, "runmax.cmp16": {"acc": 0.884, "reasoning_bytes": 108.972, "flops_per_problem": 6269919657.984}, "runmax.runmax12": {"acc": 0.996, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.runmax14": {"acc": 0.97, "reasoning_bytes": 99.332, "flops_per_problem": 5800024571.904}, "runmax.runmax16": {"acc": 0.944, "reasoning_bytes": 107.548, "flops_per_problem": 6251194515.456}, "runmax.count12": {"acc": 0.992, "reasoning_bytes": 88.048, "flops_per_problem": 5259998527.488}, "runmax.count14": {"acc": 0.95, "reasoning_bytes": 99.952, "flops_per_problem": 5887025823.744}, "runmax.count16": {"acc": 0.946, "reasoning_bytes": 108.938, "flops_per_problem": 6378119184.384}, "runmax.find12": {"acc": 0.976, "reasoning_bytes": 88.288, "flops_per_problem": 5223961460.736}, "runmax.find14": {"acc": 0.898, "reasoning_bytes": 100.064, "flops_per_problem": 5834471768.064}, "runmax.find16": {"acc": 0.784, "reasoning_bytes": 111.148, "flops_per_problem": 6426345259.008}, "runmax.rev12": {"acc": 0.996, "reasoning_bytes": 83.012, "flops_per_problem": 4858467876.864}, "runmax.rev14": {"acc": 0.952, "reasoning_bytes": 94.452, "flops_per_problem": 5452019564.544}, "runmax.rev16": {"acc": 0.938, "reasoning_bytes": 102.332, "flops_per_problem": 5888262389.76}, "runmax.sumd12": {"acc": 0.992, "reasoning_bytes": 86.012, "flops_per_problem": 5035120164.864}, "runmax.sumd14": {"acc": 0.92, "reasoning_bytes": 97.616, "flops_per_problem": 5635914596.352}, "runmax.sumd16": {"acc": 0.908, "reasoning_bytes": 106.312, "flops_per_problem": 6108812771.328}, "runmax.inc12": {"acc": 0.978, "reasoning_bytes": 87.156, "flops_per_problem": 5073453711.36}, "runmax.inc14": {"acc": 0.904, "reasoning_bytes": 98.952, "flops_per_problem": 5689263587.328}, "runmax.inc16": {"acc": 0.9, "reasoning_bytes": 107.912, "flops_per_problem": 6176205619.2}, "count.cmp16": {"acc": 0.908, "reasoning_bytes": 97.538, "flops_per_problem": 5809033838.592}, "count.cmp18": {"acc": 0.876, "reasoning_bytes": 107.422, "flops_per_problem": 6334132764.672}, "count.cmp20": {"acc": 0.818, "reasoning_bytes": 117.11, "flops_per_problem": 6849780793.344}, "count.runmax16": {"acc": 0.69, "reasoning_bytes": 99.462, "flops_per_problem": 5937990008.832}, "count.runmax18": {"acc": 0.632, "reasoning_bytes": 109.752, "flops_per_problem": 6480400859.136}, "count.runmax20": {"acc": 0.472, "reasoning_bytes": 119.844, "flops_per_problem": 7013802442.752}, "count.count16": {"acc": 0.972, "reasoning_bytes": 100.202, "flops_per_problem": 6014392123.392}, "count.count18": {"acc": 0.956, "reasoning_bytes": 110.208, "flops_per_problem": 6543819030.528}, "count.count20": {"acc": 0.982, "reasoning_bytes": 120.19, "flops_per_problem": 7074482503.68}, "count.find16": {"acc": 0.834, "reasoning_bytes": 100.426, "flops_per_problem": 5979856601.088}, "count.find18": {"acc": 0.772, "reasoning_bytes": 110.59, "flops_per_problem": 6514759729.152}, "count.find20": {"acc": 0.756, "reasoning_bytes": 120.232, "flops_per_problem": 7033764151.296}, "count.rev16": {"acc": 0.716, "reasoning_bytes": 93.556, "flops_per_problem": 5544850341.888}, "count.rev18": {"acc": 0.646, "reasoning_bytes": 103.616, "flops_per_problem": 6077280337.92}, "count.rev20": {"acc": 0.516, "reasoning_bytes": 113.032, "flops_per_problem": 6580916011.008}, "count.sumd16": {"acc": 0.66, "reasoning_bytes": 97.884, "flops_per_problem": 5779709558.784}, "count.sumd18": {"acc": 0.614, "reasoning_bytes": 107.996, "flops_per_problem": 6314259382.272}, "count.sumd20": {"acc": 0.472, "reasoning_bytes": 117.75, "flops_per_problem": 6834765348.864}, "count.inc16": {"acc": 0.656, "reasoning_bytes": 98.734, "flops_per_problem": 5774498316.288}, "count.inc18": {"acc": 0.566, "reasoning_bytes": 109.024, "flops_per_problem": 6318322384.896}, "count.inc20": {"acc": 0.436, "reasoning_bytes": 118.912, "flops_per_problem": 6844657876.992}, "parity.cmp16": {"acc": 0.952, "reasoning_bytes": 111.024, "flops_per_problem": 6360542281.728}, "parity.cmp20": {"acc": 0.936, "reasoning_bytes": 135.004, "flops_per_problem": 7597196623.872}, "parity.cmp24": {"acc": 0.786, "reasoning_bytes": 159.578, "flops_per_problem": 8891792916.48}, "parity.runmax16": {"acc": 0.57, "reasoning_bytes": 112.012, "flops_per_problem": 6448338468.864}, "parity.runmax20": {"acc": 0.406, "reasoning_bytes": 137.202, "flops_per_problem": 7735515365.376}, "parity.runmax24": {"acc": 0.234, "reasoning_bytes": 161.786, "flops_per_problem": 9091233349.632}, "parity.count16": {"acc": 0.586, "reasoning_bytes": 112.014, "flops_per_problem": 6612006813.696}, "parity.count20": {"acc": 0.516, "reasoning_bytes": 135.732, "flops_per_problem": 7871184322.56}, "parity.count24": {"acc": 0.36, "reasoning_bytes": 160.97, "flops_per_problem": 9157301305.344}, "parity.find16": {"acc": 0.924, "reasoning_bytes": 112.024, "flops_per_problem": 6448868425.728}, "parity.find20": {"acc": 0.876, "reasoning_bytes": 136.036, "flops_per_problem": 7685964398.592}, "parity.find24": {"acc": 0.768, "reasoning_bytes": 160.588, "flops_per_problem": 8961482244.096}, "parity.rev16": {"acc": 0.702, "reasoning_bytes": 107.0, "flops_per_problem": 6094503936.0}, "parity.rev20": {"acc": 0.53, "reasoning_bytes": 130.904, "flops_per_problem": 7326830297.088}, "parity.rev24": {"acc": 0.382, "reasoning_bytes": 155.528, "flops_per_problem": 8594222137.344}, "parity.sumd16": {"acc": 0.6, "reasoning_bytes": 110.0, "flops_per_problem": 6271156224.0}, "parity.sumd20": {"acc": 0.486, "reasoning_bytes": 133.88, "flops_per_problem": 7502422671.36}, "parity.sumd24": {"acc": 0.42, "reasoning_bytes": 158.458, "flops_per_problem": 8802495184.896}, "parity.inc16": {"acc": 0.562, "reasoning_bytes": 111.0, "flops_per_problem": 6271156224.0}, "parity.inc20": {"acc": 0.492, "reasoning_bytes": 134.916, "flops_per_problem": 7504012541.952}, "parity.inc24": {"acc": 0.458, "reasoning_bytes": 159.296, "flops_per_problem": 8757272199.168}, "sumd.cmp6": {"acc": 0.956, "reasoning_bytes": 62.13, "flops_per_problem": 3715262595.072}, "sumd.cmp7": {"acc": 0.926, "reasoning_bytes": 69.994, "flops_per_problem": 4106900717.568}, "sumd.cmp8": {"acc": 0.904, "reasoning_bytes": 76.974, "flops_per_problem": 4461883490.304}, "sumd.runmax6": {"acc": 0.944, "reasoning_bytes": 67.554, "flops_per_problem": 3954979749.888}, "sumd.runmax7": {"acc": 0.814, "reasoning_bytes": 75.43, "flops_per_problem": 4346971176.96}, "sumd.runmax8": {"acc": 0.55, "reasoning_bytes": 82.28, "flops_per_problem": 4693651292.16}, "sumd.count6": {"acc": 0.904, "reasoning_bytes": 66.554, "flops_per_problem": 3960190992.384}, "sumd.count7": {"acc": 0.786, "reasoning_bytes": 74.06, "flops_per_problem": 4345469632.512}, "sumd.count8": {"acc": 0.588, "reasoning_bytes": 81.238, "flops_per_problem": 4711404847.104}, "sumd.find6": {"acc": 0.966, "reasoning_bytes": 66.278, "flops_per_problem": 3898627670.016}, "sumd.find7": {"acc": 0.904, "reasoning_bytes": 74.284, "flops_per_problem": 4296360296.448}, "sumd.find8": {"acc": 0.814, "reasoning_bytes": 81.182, "flops_per_problem": 4645071912.96}, "sumd.rev6": {"acc": 0.932, "reasoning_bytes": 61.568, "flops_per_problem": 3602028478.464}, "sumd.rev7": {"acc": 0.764, "reasoning_bytes": 69.472, "flops_per_problem": 3995609776.128}, "sumd.rev8": {"acc": 0.486, "reasoning_bytes": 76.678, "flops_per_problem": 4359955120.128}, "sumd.sumd6": {"acc": 0.91, "reasoning_bytes": 65.78, "flops_per_problem": 3797052604.416}, "sumd.sumd7": {"acc": 0.756, "reasoning_bytes": 73.65, "flops_per_problem": 4190722228.224}, "sumd.sumd8": {"acc": 0.472, "reasoning_bytes": 80.542, "flops_per_problem": 4538727235.584}, "sumd.inc6": {"acc": 0.92, "reasoning_bytes": 68.568, "flops_per_problem": 3911346634.752}, "sumd.inc7": {"acc": 0.746, "reasoning_bytes": 76.512, "flops_per_problem": 4308549304.32}, "sumd.inc8": {"acc": 0.402, "reasoning_bytes": 83.802, "flops_per_problem": 4676339367.936}, "inc.cmp6": {"acc": 0.912, "reasoning_bytes": 79.558, "flops_per_problem": 4617602482.176}, "inc.cmp7": {"acc": 0.886, "reasoning_bytes": 91.046, "flops_per_problem": 5213450649.6}, "inc.cmp8": {"acc": 0.844, "reasoning_bytes": 102.556, "flops_per_problem": 5809828773.888}, "inc.runmax6": {"acc": 0.998, "reasoning_bytes": 104.086, "flops_per_problem": 5524182024.192}, "inc.runmax7": {"acc": 0.98, "reasoning_bytes": 120.068, "flops_per_problem": 6273717682.176}, "inc.runmax8": {"acc": 0.85, "reasoning_bytes": 134.914, "flops_per_problem": 6973702373.376}, "inc.count6": {"acc": 0.726, "reasoning_bytes": 99.488, "flops_per_problem": 5365194964.992}, "inc.count7": {"acc": 0.578, "reasoning_bytes": 114.232, "flops_per_problem": 6060498370.56}, "inc.count8": {"acc": 0.43, "reasoning_bytes": 126.718, "flops_per_problem": 6656258211.84}, "inc.find6": {"acc": 0.58, "reasoning_bytes": 95.092, "flops_per_problem": 5126979354.624}, "inc.find7": {"acc": 0.546, "reasoning_bytes": 108.536, "flops_per_problem": 5763987505.152}, "inc.find8": {"acc": 0.326, "reasoning_bytes": 124.04, "flops_per_problem": 6503807287.296}, "inc.rev6": {"acc": 0.486, "reasoning_bytes": 104.504, "flops_per_problem": 5621517434.88}, "inc.rev7": {"acc": 0.09, "reasoning_bytes": 123.868, "flops_per_problem": 6561395933.184}, "inc.rev8": {"acc": 0.002, "reasoning_bytes": 141.818, "flops_per_problem": 7411800047.616}, "inc.sumd6": {"acc": 0.608, "reasoning_bytes": 109.984, "flops_per_problem": 5743760818.176}, "inc.sumd7": {"acc": 0.294, "reasoning_bytes": 127.69, "flops_per_problem": 6571111809.024}, "inc.sumd8": {"acc": 0.046, "reasoning_bytes": 144.988, "flops_per_problem": 7377176199.168}, "inc.inc6": {"acc": 0.644, "reasoning_bytes": 112.88, "flops_per_problem": 6005206204.416}, "inc.inc7": {"acc": 0.292, "reasoning_bytes": 129.54, "flops_per_problem": 6826727669.76}, "inc.inc8": {"acc": 0.002, "reasoning_bytes": 142.088, "flops_per_problem": 7459672817.664}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 0.998, "reasoning_bytes": 115.976, "flops_per_problem": 6800053174.272}, "runmax.runmax.cmp16": {"acc": 0.978, "reasoning_bytes": 125.806, "flops_per_problem": 7322502316.032}, "sumd.runmax.cmp6": {"acc": 0.942, "reasoning_bytes": 83.344, "flops_per_problem": 4917293088.768}, "sumd.runmax.cmp7": {"acc": 0.908, "reasoning_bytes": 91.086, "flops_per_problem": 5303366664.192}, "sumd.runmax.cmp8": {"acc": 0.746, "reasoning_bytes": 95.218, "flops_per_problem": 5530011549.696}, "add.runmax.cmp6": {"acc": 0.918, "reasoning_bytes": 137.952, "flops_per_problem": 7591808729.088}, "add.runmax.cmp7": {"acc": 0.876, "reasoning_bytes": 156.16, "flops_per_problem": 8484609392.64}, "add.runmax.cmp8": {"acc": 0.788, "reasoning_bytes": 170.108, "flops_per_problem": 9191306870.784}, "count.runmax.runmax16": {"acc": 0.714, "reasoning_bytes": 114.77, "flops_per_problem": 6923444797.44}, "count.runmax.runmax18": {"acc": 0.628, "reasoning_bytes": 125.282, "flops_per_problem": 7475924828.16}, "count.runmax.runmax20": {"acc": 0.514, "reasoning_bytes": 135.672, "flops_per_problem": 8022928637.952}, "add.runmax.runmax6": {"acc": 0.942, "reasoning_bytes": 138.826, "flops_per_problem": 7675011956.736}, "add.runmax.runmax7": {"acc": 0.804, "reasoning_bytes": 157.55, "flops_per_problem": 8590689091.584}, "add.runmax.runmax8": {"acc": 0.49, "reasoning_bytes": 176.666, "flops_per_problem": 9524208107.52}, "parity.runmax.runmax16": {"acc": 0.618, "reasoning_bytes": 129.008, "flops_per_problem": 7508075544.576}, "parity.runmax.runmax20": {"acc": 0.508, "reasoning_bytes": 155.106, "flops_per_problem": 8842418601.984}, "parity.runmax.runmax24": {"acc": 0.266, "reasoning_bytes": 178.924, "flops_per_problem": 10148055662.592}, "parity.runmax.count16": {"acc": 0.834, "reasoning_bytes": 129.024, "flops_per_problem": 7552945225.728}, "parity.runmax.count20": {"acc": 0.912, "reasoning_bytes": 153.74, "flops_per_problem": 8851604520.96}, "parity.runmax.count24": {"acc": 0.534, "reasoning_bytes": 177.594, "flops_per_problem": 10181531271.168}, "inc.runmax.count6": {"acc": 0.986, "reasoning_bytes": 121.258, "flops_per_problem": 6635501568.0}, "inc.runmax.count7": {"acc": 0.968, "reasoning_bytes": 137.146, "flops_per_problem": 7380885897.216}, "inc.runmax.count8": {"acc": 0.926, "reasoning_bytes": 147.452, "flops_per_problem": 7879928610.816}, "sumd.runmax.count6": {"acc": 0.916, "reasoning_bytes": 84.42, "flops_per_problem": 5053138698.24}, "sumd.runmax.count7": {"acc": 0.836, "reasoning_bytes": 92.262, "flops_per_problem": 5443628580.864}, "sumd.runmax.count8": {"acc": 0.536, "reasoning_bytes": 97.584, "flops_per_problem": 5722827522.048}, "runmax.runmax.find12": {"acc": 0.996, "reasoning_bytes": 105.012, "flops_per_problem": 6271686180.864}, "runmax.runmax.find14": {"acc": 0.99, "reasoning_bytes": 117.02, "flops_per_problem": 6890234167.296}, "runmax.runmax.find16": {"acc": 0.98, "reasoning_bytes": 127.928, "flops_per_problem": 7460291100.672}, "add.runmax.find6": {"acc": 0.956, "reasoning_bytes": 138.794, "flops_per_problem": 7673863716.864}, "add.runmax.find7": {"acc": 0.882, "reasoning_bytes": 157.56, "flops_per_problem": 8591219048.448}, "add.runmax.find8": {"acc": 0.726, "reasoning_bytes": 175.122, "flops_per_problem": 9462998089.728}, "parity.runmax.find16": {"acc": 0.9, "reasoning_bytes": 129.036, "flops_per_problem": 7509312110.592}, "parity.runmax.find20": {"acc": 0.784, "reasoning_bytes": 153.268, "flops_per_problem": 8804615012.352}, "parity.runmax.find24": {"acc": 0.426, "reasoning_bytes": 178.436, "flops_per_problem": 10155563384.832}, "add.runmax.rev6": {"acc": 0.932, "reasoning_bytes": 133.754, "flops_per_problem": 7318086008.832}, "add.runmax.rev7": {"acc": 0.832, "reasoning_bytes": 152.266, "flops_per_problem": 8224753876.992}, "add.runmax.rev8": {"acc": 0.502, "reasoning_bytes": 170.792, "flops_per_problem": 9130185179.136}, "parity.runmax.rev16": {"acc": 0.712, "reasoning_bytes": 124.0, "flops_per_problem": 7154417664.0}, "parity.runmax.rev20": {"acc": 0.488, "reasoning_bytes": 148.096, "flops_per_problem": 8395841617.92}, "parity.runmax.rev24": {"acc": 0.3, "reasoning_bytes": 174.504, "flops_per_problem": 9777615814.656}, "sumd.runmax.rev6": {"acc": 0.958, "reasoning_bytes": 79.548, "flops_per_problem": 4661323923.456}, "sumd.runmax.rev7": {"acc": 0.854, "reasoning_bytes": 87.422, "flops_per_problem": 5053227024.384}, "sumd.runmax.rev8": {"acc": 0.544, "reasoning_bytes": 93.142, "flops_per_problem": 5350091194.368}, "sumd.runmax.sumd6": {"acc": 0.914, "reasoning_bytes": 82.578, "flops_per_problem": 4839301103.616}, "sumd.runmax.sumd7": {"acc": 0.802, "reasoning_bytes": 90.346, "flops_per_problem": 5226522918.912}, "sumd.runmax.sumd8": {"acc": 0.482, "reasoning_bytes": 95.784, "flops_per_problem": 5510844776.448}, "add.runmax.sumd6": {"acc": 0.932, "reasoning_bytes": 136.96, "flops_per_problem": 7505160781.824}, "add.runmax.sumd7": {"acc": 0.846, "reasoning_bytes": 155.798, "flops_per_problem": 8427550703.616}, "add.runmax.sumd8": {"acc": 0.484, "reasoning_bytes": 175.25, "flops_per_problem": 9374406967.296}, "parity.runmax.sumd16": {"acc": 0.632, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.runmax.sumd20": {"acc": 0.492, "reasoning_bytes": 151.264, "flops_per_problem": 8586361110.528}, "parity.runmax.sumd24": {"acc": 0.266, "reasoning_bytes": 176.868, "flops_per_problem": 9969725177.856}, "count.runmax.inc16": {"acc": 0.692, "reasoning_bytes": 115.244, "flops_per_problem": 6812153856.0}, "count.runmax.inc18": {"acc": 0.652, "reasoning_bytes": 125.724, "flops_per_problem": 7363927277.568}, "count.runmax.inc20": {"acc": 0.526, "reasoning_bytes": 135.716, "flops_per_problem": 7894060793.856}, "runmax.runmax.inc12": {"acc": 0.998, "reasoning_bytes": 104.0, "flops_per_problem": 6125771390.976}, "runmax.runmax.inc14": {"acc": 0.964, "reasoning_bytes": 115.732, "flops_per_problem": 6736811655.168}, "runmax.runmax.inc16": {"acc": 0.926, "reasoning_bytes": 125.07, "flops_per_problem": 7241772220.416}, "add.runmax.inc6": {"acc": 0.752, "reasoning_bytes": 137.232, "flops_per_problem": 7486965596.16}, "add.runmax.inc7": {"acc": 0.404, "reasoning_bytes": 155.546, "flops_per_problem": 8378706345.984}, "add.runmax.inc8": {"acc": 0.244, "reasoning_bytes": 174.918, "flops_per_problem": 9328742350.848}, "count.count.cmp16": {"acc": 0.968, "reasoning_bytes": 115.694, "flops_per_problem": 6963898171.392}, "count.count.cmp18": {"acc": 0.952, "reasoning_bytes": 125.51, "flops_per_problem": 7486877270.016}, "count.count.cmp20": {"acc": 0.914, "reasoning_bytes": 135.4, "flops_per_problem": 8018777309.184}, "add.count.cmp6": {"acc": 0.91, "reasoning_bytes": 133.008, "flops_per_problem": 7421162618.88}, "add.count.cmp7": {"acc": 0.858, "reasoning_bytes": 151.334, "flops_per_problem": 8320411090.944}, "add.count.cmp8": {"acc": 0.78, "reasoning_bytes": 163.44, "flops_per_problem": 8958390829.056}, "sumd.count.cmp6": {"acc": 0.988, "reasoning_bytes": 82.482, "flops_per_problem": 4923387592.704}, "sumd.count.cmp7": {"acc": 0.976, "reasoning_bytes": 89.72, "flops_per_problem": 5287202979.84}, "sumd.count.cmp8": {"acc": 0.94, "reasoning_bytes": 93.292, "flops_per_problem": 5489469849.6}, "add.count.runmax6": {"acc": 0.638, "reasoning_bytes": 134.342, "flops_per_problem": 7522561032.192}, "add.count.runmax7": {"acc": 0.492, "reasoning_bytes": 152.044, "flops_per_problem": 8397784793.088}, "add.count.runmax8": {"acc": 0.286, "reasoning_bytes": 169.772, "flops_per_problem": 9299153092.608}, "sumd.count.runmax6": {"acc": 0.932, "reasoning_bytes": 83.428, "flops_per_problem": 5009328930.816}, "sumd.count.runmax7": {"acc": 0.846, "reasoning_bytes": 91.072, "flops_per_problem": 5390986199.04}, "sumd.count.runmax8": {"acc": 0.564, "reasoning_bytes": 95.99, "flops_per_problem": 5652343259.136}, "inc.count.runmax6": {"acc": 0.76, "reasoning_bytes": 116.518, "flops_per_problem": 6426433585.152}, "inc.count.runmax7": {"acc": 0.61, "reasoning_bytes": 131.394, "flops_per_problem": 7127478190.08}, "inc.count.runmax8": {"acc": 0.442, "reasoning_bytes": 138.444, "flops_per_problem": 7483079245.824}, "parity.count.count16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7596048384.0}, "parity.count.count20": {"acc": 0.982, "reasoning_bytes": 152.94, "flops_per_problem": 8838178947.072}, "parity.count.count24": {"acc": 0.952, "reasoning_bytes": 175.6, "flops_per_problem": 10008323702.784}, "runmax.count.count12": {"acc": 1.0, "reasoning_bytes": 105.024, "flops_per_problem": 6360542281.728}, "runmax.count.count14": {"acc": 1.0, "reasoning_bytes": 117.024, "flops_per_problem": 6978825289.728}, "runmax.count.count16": {"acc": 1.0, "reasoning_bytes": 127.616, "flops_per_problem": 7534926692.352}, "inc.count.count6": {"acc": 0.802, "reasoning_bytes": 116.972, "flops_per_problem": 6490028408.832}, "inc.count.count7": {"acc": 0.738, "reasoning_bytes": 131.288, "flops_per_problem": 7166783324.16}, "inc.count.count8": {"acc": 0.648, "reasoning_bytes": 136.288, "flops_per_problem": 7431938408.448}, "inc.count.find6": {"acc": 0.916, "reasoning_bytes": 117.07, "flops_per_problem": 6450369970.176}, "inc.count.find7": {"acc": 0.894, "reasoning_bytes": 131.292, "flops_per_problem": 7122973556.736}, "inc.count.find8": {"acc": 0.854, "reasoning_bytes": 136.036, "flops_per_problem": 7376822894.592}, "add.count.find6": {"acc": 0.906, "reasoning_bytes": 134.374, "flops_per_problem": 7526094077.952}, "add.count.find7": {"acc": 0.79, "reasoning_bytes": 153.102, "flops_per_problem": 8453871894.528}, "add.count.find8": {"acc": 0.674, "reasoning_bytes": 166.992, "flops_per_problem": 9169666965.504}, "runmax.count.find12": {"acc": 1.0, "reasoning_bytes": 105.072, "flops_per_problem": 6318499037.184}, "runmax.count.find14": {"acc": 0.986, "reasoning_bytes": 117.108, "flops_per_problem": 6938371915.776}, "runmax.count.find16": {"acc": 0.97, "reasoning_bytes": 129.04, "flops_per_problem": 7553386856.448}, "parity.count.rev16": {"acc": 0.974, "reasoning_bytes": 124.0, "flops_per_problem": 7198580736.0}, "parity.count.rev20": {"acc": 1.0, "reasoning_bytes": 147.988, "flops_per_problem": 8434616795.136}, "parity.count.rev24": {"acc": 0.908, "reasoning_bytes": 171.588, "flops_per_problem": 9654400843.776}, "inc.count.rev6": {"acc": 0.766, "reasoning_bytes": 111.604, "flops_per_problem": 6076838707.2}, "inc.count.rev7": {"acc": 0.63, "reasoning_bytes": 126.188, "flops_per_problem": 6765252673.536}, "inc.count.rev8": {"acc": 0.45, "reasoning_bytes": 131.97, "flops_per_problem": 7070154522.624}, "runmax.count.rev12": {"acc": 1.0, "reasoning_bytes": 100.012, "flops_per_problem": 5962544676.864}, "runmax.count.rev14": {"acc": 0.998, "reasoning_bytes": 111.964, "flops_per_problem": 6578707857.408}, "runmax.count.rev16": {"acc": 0.996, "reasoning_bytes": 121.368, "flops_per_problem": 7082166878.208}, "count.count.sumd16": {"acc": 0.976, "reasoning_bytes": 115.088, "flops_per_problem": 6892883951.616}, "count.count.sumd18": {"acc": 0.96, "reasoning_bytes": 125.296, "flops_per_problem": 7431055147.008}, "count.count.sumd20": {"acc": 0.98, "reasoning_bytes": 135.416, "flops_per_problem": 7967724797.952}, "runmax.count.sumd12": {"acc": 1.0, "reasoning_bytes": 103.036, "flops_per_problem": 6140256878.592}, "runmax.count.sumd14": {"acc": 1.0, "reasoning_bytes": 114.916, "flops_per_problem": 6753240317.952}, "runmax.count.sumd16": {"acc": 0.998, "reasoning_bytes": 124.632, "flops_per_problem": 7270566543.36}, "sumd.count.sumd6": {"acc": 0.94, "reasoning_bytes": 81.448, "flops_per_problem": 4833559904.256}, "sumd.count.sumd7": {"acc": 0.82, "reasoning_bytes": 89.208, "flops_per_problem": 5220428414.976}, "sumd.count.sumd8": {"acc": 0.552, "reasoning_bytes": 95.25, "flops_per_problem": 5531336441.856}, "parity.count.inc16": {"acc": 0.976, "reasoning_bytes": 128.012, "flops_per_problem": 7375762980.864}, "parity.count.inc20": {"acc": 0.936, "reasoning_bytes": 151.852, "flops_per_problem": 8605262905.344}, "parity.count.inc24": {"acc": 0.844, "reasoning_bytes": 175.926, "flops_per_problem": 9849689948.16}, "count.count.inc16": {"acc": 0.986, "reasoning_bytes": 116.048, "flops_per_problem": 6891912364.032}, "count.count.inc18": {"acc": 0.962, "reasoning_bytes": 126.16, "flops_per_problem": 7427963731.968}, "count.count.inc20": {"acc": 0.98, "reasoning_bytes": 136.25, "flops_per_problem": 7960393728.0}, "add.count.inc6": {"acc": 0.658, "reasoning_bytes": 133.668, "flops_per_problem": 7360129253.376}, "add.count.inc7": {"acc": 0.458, "reasoning_bytes": 151.73, "flops_per_problem": 8247718674.432}, "add.count.inc8": {"acc": 0.284, "reasoning_bytes": 167.046, "flops_per_problem": 9014919561.216}, "parity.rev.cmp16": {"acc": 0.964, "reasoning_bytes": 123.0, "flops_per_problem": 7066091520.0}, "parity.rev.cmp20": {"acc": 0.934, "reasoning_bytes": 147.52, "flops_per_problem": 8325622333.44}, "parity.rev.cmp24": {"acc": 0.844, "reasoning_bytes": 172.044, "flops_per_problem": 9599991939.072}, "sumd.rev.cmp6": {"acc": 0.908, "reasoning_bytes": 81.144, "flops_per_problem": 4731631534.08}, "sumd.rev.cmp7": {"acc": 0.872, "reasoning_bytes": 88.972, "flops_per_problem": 5121679785.984}, "sumd.rev.cmp8": {"acc": 0.768, "reasoning_bytes": 93.518, "flops_per_problem": 5366696509.44}, "add.rev.cmp6": {"acc": 0.776, "reasoning_bytes": 163.698, "flops_per_problem": 8861850353.664}, "add.rev.cmp7": {"acc": 0.612, "reasoning_bytes": 186.258, "flops_per_problem": 10021219319.808}, "add.rev.cmp8": {"acc": 0.58, "reasoning_bytes": 206.574, "flops_per_problem": 11039354781.696}, "runmax.rev.runmax12": {"acc": 1.0, "reasoning_bytes": 99.928, "flops_per_problem": 5914671906.816}, "runmax.rev.runmax14": {"acc": 0.984, "reasoning_bytes": 111.012, "flops_per_problem": 6492501540.864}, "runmax.rev.runmax16": {"acc": 0.944, "reasoning_bytes": 119.868, "flops_per_problem": 6971847524.352}, "count.rev.runmax16": {"acc": 0.754, "reasoning_bytes": 109.65, "flops_per_problem": 6564840652.8}, "count.rev.runmax18": {"acc": 0.674, "reasoning_bytes": 120.03, "flops_per_problem": 7111402831.872}, "count.rev.runmax20": {"acc": 0.556, "reasoning_bytes": 130.182, "flops_per_problem": 7647895830.528}, "add.rev.runmax6": {"acc": 0.758, "reasoning_bytes": 184.574, "flops_per_problem": 9575613923.328}, "add.rev.runmax7": {"acc": 0.748, "reasoning_bytes": 190.182, "flops_per_problem": 9907631898.624}, "add.rev.runmax8": {"acc": 0.492, "reasoning_bytes": 191.976, "flops_per_problem": 10071476895.744}, "inc.rev.count6": {"acc": 0.47, "reasoning_bytes": 157.398, "flops_per_problem": 8105336930.304}, "inc.rev.count7": {"acc": 0.348, "reasoning_bytes": 184.89, "flops_per_problem": 9364602765.312}, "inc.rev.count8": {"acc": 0.268, "reasoning_bytes": 197.372, "flops_per_problem": 9958772736.0}, "count.rev.count16": {"acc": 0.99, "reasoning_bytes": 111.45, "flops_per_problem": 6688497254.4}, "count.rev.count18": {"acc": 0.972, "reasoning_bytes": 121.532, "flops_per_problem": 7221457207.296}, "count.rev.count20": {"acc": 0.992, "reasoning_bytes": 131.35, "flops_per_problem": 7743994675.2}, "parity.rev.count16": {"acc": 0.884, "reasoning_bytes": 124.0, "flops_per_problem": 7198580736.0}, "parity.rev.count20": {"acc": 0.978, "reasoning_bytes": 149.008, "flops_per_problem": 8479663128.576}, "parity.rev.count24": {"acc": 0.788, "reasoning_bytes": 173.066, "flops_per_problem": 9764985176.064}, "sumd.rev.find6": {"acc": 0.97, "reasoning_bytes": 85.216, "flops_per_problem": 4911640215.552}, "sumd.rev.find7": {"acc": 0.912, "reasoning_bytes": 93.348, "flops_per_problem": 5315379019.776}, "sumd.rev.find8": {"acc": 0.764, "reasoning_bytes": 97.682, "flops_per_problem": 5550503215.104}, "runmax.rev.find12": {"acc": 1.0, "reasoning_bytes": 100.084, "flops_per_problem": 5921561346.048}, "runmax.rev.find14": {"acc": 0.986, "reasoning_bytes": 112.052, "flops_per_problem": 6538342809.6}, "runmax.rev.find16": {"acc": 0.964, "reasoning_bytes": 123.088, "flops_per_problem": 7113875963.904}, "count.rev.find16": {"acc": 0.932, "reasoning_bytes": 110.666, "flops_per_problem": 6609622007.808}, "count.rev.find18": {"acc": 0.888, "reasoning_bytes": 120.786, "flops_per_problem": 7144790114.304}, "count.rev.find20": {"acc": 0.868, "reasoning_bytes": 130.608, "flops_per_problem": 7666620973.056}, "count.rev.rev16": {"acc": 0.78, "reasoning_bytes": 104.06, "flops_per_problem": 6185479864.32}, "count.rev.rev18": {"acc": 0.694, "reasoning_bytes": 114.006, "flops_per_problem": 6712963596.288}, "count.rev.rev20": {"acc": 0.572, "reasoning_bytes": 123.656, "flops_per_problem": 7227375058.944}, "sumd.rev.rev6": {"acc": 0.926, "reasoning_bytes": 80.728, "flops_per_problem": 4625463508.992}, "sumd.rev.rev7": {"acc": 0.748, "reasoning_bytes": 88.62, "flops_per_problem": 5018779828.224}, "sumd.rev.rev8": {"acc": 0.33, "reasoning_bytes": 94.106, "flops_per_problem": 5306369753.088}, "parity.rev.rev16": {"acc": 0.792, "reasoning_bytes": 119.0, "flops_per_problem": 6801113088.0}, "parity.rev.rev20": {"acc": 0.526, "reasoning_bytes": 142.452, "flops_per_problem": 8013477740.544}, "parity.rev.rev24": {"acc": 0.394, "reasoning_bytes": 166.64, "flops_per_problem": 9256844869.632}, "sumd.rev.sumd6": {"acc": 0.936, "reasoning_bytes": 84.754, "flops_per_problem": 4811831672.832}, "sumd.rev.sumd7": {"acc": 0.798, "reasoning_bytes": 92.676, "flops_per_problem": 5208592711.68}, "sumd.rev.sumd8": {"acc": 0.5, "reasoning_bytes": 98.628, "flops_per_problem": 5512787951.616}, "parity.rev.sumd16": {"acc": 0.724, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.rev.sumd20": {"acc": 0.51, "reasoning_bytes": 145.76, "flops_per_problem": 8203732254.72}, "parity.rev.sumd24": {"acc": 0.372, "reasoning_bytes": 171.776, "flops_per_problem": 9558566977.536}, "add.rev.sumd6": {"acc": 0.064, "reasoning_bytes": 197.746, "flops_per_problem": 10115551641.6}, "add.rev.sumd7": {"acc": 0.028, "reasoning_bytes": 232.47, "flops_per_problem": 11738721189.888}, "add.rev.sumd8": {"acc": 0.008, "reasoning_bytes": 264.08, "flops_per_problem": 13223483670.528}, "parity.rev.inc16": {"acc": 0.686, "reasoning_bytes": 123.0, "flops_per_problem": 6977765376.0}, "parity.rev.inc20": {"acc": 0.468, "reasoning_bytes": 147.116, "flops_per_problem": 8219454308.352}, "parity.rev.inc24": {"acc": 0.452, "reasoning_bytes": 171.636, "flops_per_problem": 9486846148.608}, "runmax.rev.inc12": {"acc": 0.996, "reasoning_bytes": 99.012, "flops_per_problem": 5773085097.984}, "runmax.rev.inc14": {"acc": 0.942, "reasoning_bytes": 110.712, "flops_per_problem": 6383860383.744}, "runmax.rev.inc16": {"acc": 0.904, "reasoning_bytes": 119.48, "flops_per_problem": 6863647997.952}, "inc.rev.inc6": {"acc": 0.024, "reasoning_bytes": 167.724, "flops_per_problem": 8588657590.272}, "inc.rev.inc7": {"acc": 0.002, "reasoning_bytes": 196.538, "flops_per_problem": 9951883296.768}, "inc.rev.inc8": {"acc": 0.0, "reasoning_bytes": 219.28, "flops_per_problem": 11007822348.288}, "parity.sumd.cmp16": {"acc": 0.944, "reasoning_bytes": 126.0, "flops_per_problem": 7242743808.0}, "parity.sumd.cmp20": {"acc": 0.948, "reasoning_bytes": 149.964, "flops_per_problem": 8477719953.408}, "parity.sumd.cmp24": {"acc": 0.866, "reasoning_bytes": 174.844, "flops_per_problem": 9760833847.296}, "runmax.sumd.cmp12": {"acc": 0.996, "reasoning_bytes": 102.0, "flops_per_problem": 6006177792.0}, "runmax.sumd.cmp14": {"acc": 0.992, "reasoning_bytes": 113.94, "flops_per_problem": 6621811015.68}, "runmax.sumd.cmp16": {"acc": 0.958, "reasoning_bytes": 123.208, "flops_per_problem": 7119440510.976}, "count.sumd.cmp16": {"acc": 0.934, "reasoning_bytes": 112.69, "flops_per_problem": 6699096391.68}, "count.sumd.cmp18": {"acc": 0.91, "reasoning_bytes": 122.482, "flops_per_problem": 7219690684.416}, "count.sumd.cmp20": {"acc": 0.876, "reasoning_bytes": 132.34, "flops_per_problem": 7743553044.48}, "sumd.sumd.runmax6": {"acc": 0.896, "reasoning_bytes": 84.394, "flops_per_problem": 4919501242.368}, "sumd.sumd.runmax7": {"acc": 0.784, "reasoning_bytes": 92.558, "flops_per_problem": 5324476612.608}, "sumd.sumd.runmax8": {"acc": 0.446, "reasoning_bytes": 97.194, "flops_per_problem": 5573114707.968}, "count.sumd.runmax16": {"acc": 0.708, "reasoning_bytes": 113.236, "flops_per_problem": 6767284174.848}, "count.sumd.runmax18": {"acc": 0.642, "reasoning_bytes": 123.814, "flops_per_problem": 7322590642.176}, "count.sumd.runmax20": {"acc": 0.508, "reasoning_bytes": 134.066, "flops_per_problem": 7863411621.888}, "add.sumd.runmax6": {"acc": 0.662, "reasoning_bytes": 153.67, "flops_per_problem": 8244362280.96}, "add.sumd.runmax7": {"acc": 0.322, "reasoning_bytes": 175.414, "flops_per_problem": 9295620046.848}, "add.sumd.runmax8": {"acc": 0.162, "reasoning_bytes": 196.828, "flops_per_problem": 10332922281.984}, "parity.sumd.count16": {"acc": 0.846, "reasoning_bytes": 127.0, "flops_per_problem": 7375233024.0}, "parity.sumd.count20": {"acc": 0.98, "reasoning_bytes": 150.966, "flops_per_problem": 8610297495.552}, "parity.sumd.count24": {"acc": 0.862, "reasoning_bytes": 175.694, "flops_per_problem": 9897209413.632}, "sumd.sumd.count6": {"acc": 0.922, "reasoning_bytes": 84.078, "flops_per_problem": 4949708783.616}, "sumd.sumd.count7": {"acc": 0.778, "reasoning_bytes": 91.902, "flops_per_problem": 5339580383.232}, "sumd.sumd.count8": {"acc": 0.538, "reasoning_bytes": 97.002, "flops_per_problem": 5608621817.856}, "add.sumd.count6": {"acc": 0.584, "reasoning_bytes": 152.31, "flops_per_problem": 8228640227.328}, "add.sumd.count7": {"acc": 0.398, "reasoning_bytes": 173.586, "flops_per_problem": 9259936284.672}, "add.sumd.count8": {"acc": 0.26, "reasoning_bytes": 194.254, "flops_per_problem": 10261466431.488}, "runmax.sumd.find12": {"acc": 1.0, "reasoning_bytes": 103.072, "flops_per_problem": 6097683677.184}, "runmax.sumd.find14": {"acc": 0.988, "reasoning_bytes": 115.016, "flops_per_problem": 6713493553.152}, "runmax.sumd.find16": {"acc": 0.966, "reasoning_bytes": 125.692, "flops_per_problem": 7273216327.68}, "sumd.sumd.find6": {"acc": 0.962, "reasoning_bytes": 83.97, "flops_per_problem": 4900776099.84}, "sumd.sumd.find7": {"acc": 0.916, "reasoning_bytes": 91.666, "flops_per_problem": 5285083152.384}, "sumd.sumd.find8": {"acc": 0.804, "reasoning_bytes": 95.796, "flops_per_problem": 5511374733.312}, "parity.sumd.find16": {"acc": 0.914, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.sumd.find20": {"acc": 0.862, "reasoning_bytes": 151.012, "flops_per_problem": 8568165924.864}, "parity.sumd.find24": {"acc": 0.79, "reasoning_bytes": 175.828, "flops_per_problem": 9855342821.376}, "count.sumd.rev16": {"acc": 0.74, "reasoning_bytes": 108.13, "flops_per_problem": 6409386639.36}, "count.sumd.rev18": {"acc": 0.67, "reasoning_bytes": 118.368, "flops_per_problem": 6949677662.208}, "count.sumd.rev20": {"acc": 0.546, "reasoning_bytes": 128.388, "flops_per_problem": 7480164483.072}, "parity.sumd.rev16": {"acc": 0.726, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.sumd.rev20": {"acc": 0.504, "reasoning_bytes": 145.22, "flops_per_problem": 8179884195.84}, "parity.sumd.rev24": {"acc": 0.474, "reasoning_bytes": 168.708, "flops_per_problem": 9395251937.28}, "add.sumd.rev6": {"acc": 0.586, "reasoning_bytes": 147.7, "flops_per_problem": 7892029292.544}, "add.sumd.rev7": {"acc": 0.132, "reasoning_bytes": 169.356, "flops_per_problem": 8935249379.328}, "add.sumd.rev8": {"acc": 0.016, "reasoning_bytes": 186.018, "flops_per_problem": 9756770844.672}, "parity.sumd.sumd16": {"acc": 0.668, "reasoning_bytes": 125.0, "flops_per_problem": 7154417664.0}, "parity.sumd.sumd20": {"acc": 0.53, "reasoning_bytes": 148.376, "flops_per_problem": 8363425923.072}, "parity.sumd.sumd24": {"acc": 0.462, "reasoning_bytes": 173.152, "flops_per_problem": 9643978358.784}, "add.sumd.sumd6": {"acc": 0.574, "reasoning_bytes": 152.358, "flops_per_problem": 8104983625.728}, "add.sumd.sumd7": {"acc": 0.154, "reasoning_bytes": 174.048, "flops_per_problem": 9156948000.768}, "add.sumd.sumd8": {"acc": 0.074, "reasoning_bytes": 194.682, "flops_per_problem": 10154238492.672}, "count.sumd.sumd16": {"acc": 0.692, "reasoning_bytes": 111.946, "flops_per_problem": 6621987667.968}, "count.sumd.sumd18": {"acc": 0.636, "reasoning_bytes": 122.176, "flops_per_problem": 7161748733.952}, "count.sumd.sumd20": {"acc": 0.5, "reasoning_bytes": 132.056, "flops_per_problem": 7685787746.304}, "inc.sumd.inc6": {"acc": 0.664, "reasoning_bytes": 136.364, "flops_per_problem": 7082078552.064}, "inc.sumd.inc7": {"acc": 0.326, "reasoning_bytes": 154.624, "flops_per_problem": 7936192364.544}, "inc.sumd.inc8": {"acc": 0.022, "reasoning_bytes": 171.418, "flops_per_problem": 8732717531.136}, "sumd.sumd.inc6": {"acc": 0.886, "reasoning_bytes": 83.744, "flops_per_problem": 4772703191.04}, "sumd.sumd.inc7": {"acc": 0.724, "reasoning_bytes": 91.944, "flops_per_problem": 5179180105.728}, "sumd.sumd.inc8": {"acc": 0.41, "reasoning_bytes": 97.082, "flops_per_problem": 5446278365.184}, "parity.sumd.inc16": {"acc": 0.624, "reasoning_bytes": 126.0, "flops_per_problem": 7154417664.0}, "parity.sumd.inc20": {"acc": 0.502, "reasoning_bytes": 149.928, "flops_per_problem": 8387803938.816}, "parity.sumd.inc24": {"acc": 0.516, "reasoning_bytes": 173.896, "flops_per_problem": 9622956736.512}, "inc.inc.cmp6": {"acc": 0.832, "reasoning_bytes": 147.018, "flops_per_problem": 7781268307.968}, "inc.inc.cmp7": {"acc": 0.814, "reasoning_bytes": 168.702, "flops_per_problem": 8828021440.512}, "inc.inc.cmp8": {"acc": 0.746, "reasoning_bytes": 189.77, "flops_per_problem": 9859229171.712}, "runmax.inc.cmp12": {"acc": 0.98, "reasoning_bytes": 106.55, "flops_per_problem": 6194135826.432}, "runmax.inc.cmp14": {"acc": 0.938, "reasoning_bytes": 119.372, "flops_per_problem": 6852695556.096}, "runmax.inc.cmp16": {"acc": 0.888, "reasoning_bytes": 131.758, "flops_per_problem": 7489703706.624}, "sumd.inc.cmp6": {"acc": 0.928, "reasoning_bytes": 88.174, "flops_per_problem": 5042097930.24}, "sumd.inc.cmp7": {"acc": 0.936, "reasoning_bytes": 95.878, "flops_per_problem": 5426669961.216}, "sumd.inc.cmp8": {"acc": 0.902, "reasoning_bytes": 101.022, "flops_per_problem": 5699597746.176}, "sumd.inc.runmax6": {"acc": 0.906, "reasoning_bytes": 93.528, "flops_per_problem": 5278723670.016}, "sumd.inc.runmax7": {"acc": 0.782, "reasoning_bytes": 101.41, "flops_per_problem": 5671510032.384}, "sumd.inc.runmax8": {"acc": 0.462, "reasoning_bytes": 106.7, "flops_per_problem": 5949207429.12}, "runmax.inc.runmax12": {"acc": 0.998, "reasoning_bytes": 110.12, "flops_per_problem": 6364781936.64}, "runmax.inc.runmax14": {"acc": 0.964, "reasoning_bytes": 124.808, "flops_per_problem": 7101775282.176}, "runmax.inc.runmax16": {"acc": 0.872, "reasoning_bytes": 136.302, "flops_per_problem": 7694620360.704}, "add.inc.runmax6": {"acc": 0.792, "reasoning_bytes": 195.448, "flops_per_problem": 10039944462.336}, "add.inc.runmax7": {"acc": 0.674, "reasoning_bytes": 222.632, "flops_per_problem": 11331361013.76}, "add.inc.runmax8": {"acc": 0.442, "reasoning_bytes": 247.426, "flops_per_problem": 12523852283.904}, "runmax.inc.count12": {"acc": 0.988, "reasoning_bytes": 110.682, "flops_per_problem": 6433764655.104}, "runmax.inc.count14": {"acc": 0.922, "reasoning_bytes": 124.838, "flops_per_problem": 7147263246.336}, "runmax.inc.count16": {"acc": 0.864, "reasoning_bytes": 136.978, "flops_per_problem": 7771640758.272}, "sumd.inc.count6": {"acc": 0.926, "reasoning_bytes": 92.394, "flops_per_problem": 5273247449.088}, "sumd.inc.count7": {"acc": 0.79, "reasoning_bytes": 100.01, "flops_per_problem": 5653226520.576}, "sumd.inc.count8": {"acc": 0.562, "reasoning_bytes": 105.396, "flops_per_problem": 5935516876.8}, "inc.inc.count6": {"acc": 0.562, "reasoning_bytes": 167.11, "flops_per_problem": 8528242507.776}, "inc.inc.count7": {"acc": 0.428, "reasoning_bytes": 191.716, "flops_per_problem": 9660407021.568}, "inc.inc.count8": {"acc": 0.272, "reasoning_bytes": 200.308, "flops_per_problem": 10086845644.8}, "parity.inc.find16": {"acc": 0.91, "reasoning_bytes": 128.0, "flops_per_problem": 7331069952.0}, "parity.inc.find20": {"acc": 0.892, "reasoning_bytes": 152.024, "flops_per_problem": 8568695881.728}, "parity.inc.find24": {"acc": 0.772, "reasoning_bytes": 176.57, "flops_per_problem": 9848100077.568}, "sumd.inc.find6": {"acc": 0.974, "reasoning_bytes": 92.614, "flops_per_problem": 5238181969.92}, "sumd.inc.find7": {"acc": 0.904, "reasoning_bytes": 100.696, "flops_per_problem": 5639182663.68}, "sumd.inc.find8": {"acc": 0.788, "reasoning_bytes": 105.242, "flops_per_problem": 5884376039.424}, "count.inc.find16": {"acc": 0.866, "reasoning_bytes": 115.448, "flops_per_problem": 6820544839.68}, "count.inc.find18": {"acc": 0.826, "reasoning_bytes": 125.81, "flops_per_problem": 7365693800.448}, "count.inc.find20": {"acc": 0.856, "reasoning_bytes": 135.776, "flops_per_problem": 7895297359.872}, "sumd.inc.rev6": {"acc": 0.944, "reasoning_bytes": 87.598, "flops_per_problem": 4928333856.768}, "sumd.inc.rev7": {"acc": 0.754, "reasoning_bytes": 95.614, "flops_per_problem": 5327214723.072}, "sumd.inc.rev8": {"acc": 0.434, "reasoning_bytes": 101.37, "flops_per_problem": 5627170308.096}, "count.inc.rev16": {"acc": 0.712, "reasoning_bytes": 109.09, "flops_per_problem": 6407620116.48}, "count.inc.rev18": {"acc": 0.654, "reasoning_bytes": 119.444, "flops_per_problem": 6953122381.824}, "count.inc.rev20": {"acc": 0.542, "reasoning_bytes": 129.166, "flops_per_problem": 7470890237.952}, "parity.inc.rev16": {"acc": 0.688, "reasoning_bytes": 123.0, "flops_per_problem": 6977765376.0}, "parity.inc.rev20": {"acc": 0.474, "reasoning_bytes": 146.712, "flops_per_problem": 8201612427.264}, "parity.inc.rev24": {"acc": 0.478, "reasoning_bytes": 170.08, "flops_per_problem": 9413093818.368}, "count.inc.sumd16": {"acc": 0.69, "reasoning_bytes": 113.46, "flops_per_problem": 6644599160.832}, "count.inc.sumd18": {"acc": 0.638, "reasoning_bytes": 123.706, "flops_per_problem": 7185420140.544}, "count.inc.sumd20": {"acc": 0.512, "reasoning_bytes": 133.588, "flops_per_problem": 7710342414.336}, "sumd.inc.sumd6": {"acc": 0.928, "reasoning_bytes": 91.778, "flops_per_problem": 5123622961.152}, "sumd.inc.sumd7": {"acc": 0.782, "reasoning_bytes": 99.748, "flops_per_problem": 5521532239.872}, "sumd.inc.sumd8": {"acc": 0.44, "reasoning_bytes": 105.784, "flops_per_problem": 5831733657.6}, "add.inc.sumd6": {"acc": 0.096, "reasoning_bytes": 203.292, "flops_per_problem": 10344316354.56}, "add.inc.sumd7": {"acc": 0.054, "reasoning_bytes": 232.56, "flops_per_problem": 11728563683.328}, "add.inc.sumd8": {"acc": 0.012, "reasoning_bytes": 254.706, "flops_per_problem": 12794395262.976}, "parity.inc.inc16": {"acc": 0.604, "reasoning_bytes": 127.0, "flops_per_problem": 7154417664.0}, "parity.inc.inc20": {"acc": 0.484, "reasoning_bytes": 152.064, "flops_per_problem": 8437973188.608}, "parity.inc.inc24": {"acc": 0.452, "reasoning_bytes": 176.712, "flops_per_problem": 9702980222.976}, "sumd.inc.inc6": {"acc": 0.886, "reasoning_bytes": 94.544, "flops_per_problem": 5235355533.312}, "sumd.inc.inc7": {"acc": 0.578, "reasoning_bytes": 102.366, "flops_per_problem": 5625227132.928}, "sumd.inc.inc8": {"acc": 0.182, "reasoning_bytes": 108.472, "flops_per_problem": 5941523054.592}, "runmax.inc.inc12": {"acc": 0.98, "reasoning_bytes": 110.292, "flops_per_problem": 6280607121.408}, "runmax.inc.inc14": {"acc": 0.532, "reasoning_bytes": 126.62, "flops_per_problem": 7077043961.856}, "runmax.inc.inc16": {"acc": 0.18, "reasoning_bytes": 139.676, "flops_per_problem": 7764309688.32}, "count.inc.cmp16": {"acc": 0.922, "reasoning_bytes": 113.586, "flops_per_problem": 6694415106.048}, "count.inc.cmp18": {"acc": 0.874, "reasoning_bytes": 123.572, "flops_per_problem": 7223577034.752}, "count.inc.cmp20": {"acc": 0.84, "reasoning_bytes": 133.7, "flops_per_problem": 7759363424.256}, "inc.rev.sumd6": {"acc": 0.048, "reasoning_bytes": 168.704, "flops_per_problem": 8514286977.024}, "inc.rev.sumd7": {"acc": 0.038, "reasoning_bytes": 198.806, "flops_per_problem": 9892881432.576}, "inc.rev.sumd8": {"acc": 0.022, "reasoning_bytes": 224.758, "flops_per_problem": 11087757508.608}, "runmax.inc.find12": {"acc": 0.978, "reasoning_bytes": 110.34, "flops_per_problem": 6374762790.912}, "runmax.inc.find14": {"acc": 0.952, "reasoning_bytes": 124.22, "flops_per_problem": 7075807395.84}, "runmax.inc.find16": {"acc": 0.864, "reasoning_bytes": 136.582, "flops_per_problem": 7709547479.04}, "inc.runmax.cmp6": {"acc": 0.99, "reasoning_bytes": 120.124, "flops_per_problem": 6497271152.64}, "inc.runmax.cmp7": {"acc": 0.936, "reasoning_bytes": 132.52, "flops_per_problem": 7088438034.432}, "inc.runmax.cmp8": {"acc": 0.944, "reasoning_bytes": 137.678, "flops_per_problem": 7360924188.672}} +{"step": 2000, "train_loss": 1.3465492725372314} +{"step": 2020, "train_loss": 1.271345853805542} +{"step": 2040, "train_loss": 1.311570644378662} +{"step": 2060, "train_loss": 1.25307297706604} +{"step": 2080, "train_loss": 1.2580406665802002} +{"step": 2100, "train_loss": 1.2902355194091797} +{"step": 2120, "train_loss": 1.2673624753952026} +{"step": 2140, "train_loss": 1.1919528245925903} +{"step": 2160, "train_loss": 1.2956554889678955} +{"step": 2180, "train_loss": 1.2343381643295288} +{"step": 2200, "train_loss": 1.2903823852539062} +{"step": 2220, "train_loss": 1.215002179145813} +{"step": 2240, "train_loss": 1.2884584665298462} +{"step": 2260, "train_loss": 1.1785526275634766} +{"step": 2280, "train_loss": 1.2306575775146484} +{"step": 2300, "train_loss": 1.217063546180725} +{"step": 2320, "train_loss": 1.2101562023162842} +{"step": 2340, "train_loss": 1.2266912460327148} +{"step": 2360, "train_loss": 1.1469178199768066} +{"step": 2380, "train_loss": 1.141397476196289} +{"step": 2400, "train_loss": 1.2269048690795898} +{"step": 2420, "train_loss": 1.200951099395752} +{"step": 2440, "train_loss": 1.2611777782440186} +{"step": 2460, "train_loss": 1.1385207176208496} +{"step": 2480, "train_loss": 1.2469091415405273} +{"step": 2500, "train_loss": 1.1200627088546753} +{"step": 2520, "train_loss": 1.2019667625427246} +{"step": 2540, "train_loss": 1.246002197265625} +{"step": 2560, "train_loss": 1.2402541637420654} +{"step": 2580, "train_loss": 1.2556363344192505} +{"step": 2600, "train_loss": 1.2120726108551025} +{"step": 2620, "train_loss": 1.2711842060089111} +{"step": 2640, "train_loss": 1.1793221235275269} +{"step": 2660, "train_loss": 1.2353814840316772} +{"step": 2680, "train_loss": 1.2521754503250122} +{"step": 2700, "train_loss": 1.1974023580551147} +{"step": 2720, "train_loss": 1.268203854560852} +{"step": 2740, "train_loss": 1.1249181032180786} +{"step": 2760, "train_loss": 1.1481053829193115} +{"step": 2780, "train_loss": 1.2653744220733643} +{"step": 2800, "train_loss": 1.1648004055023193} +{"step": 2820, "train_loss": 1.1666626930236816} +{"step": 2840, "train_loss": 1.152754783630371} +{"step": 2860, "train_loss": 1.1797984838485718} +{"step": 2880, "train_loss": 1.3256359100341797} +{"step": 2900, "train_loss": 1.1181153059005737} +{"step": 2920, "train_loss": 1.2457548379898071} +{"step": 2940, "train_loss": 1.1168391704559326} +{"step": 2960, "train_loss": 1.1435823440551758} +{"step": 2980, "train_loss": 1.1393918991088867} +{"step": 3000, "tokens": 98304000, "val_loss": 2.1916741013526915, "val_bpb": 0.7900629070402589, "lr": 0.0005323183730895466, "elapsed": 1028.3454194068909, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.072, "reasoning_bytes": 78.914, "flops_per_problem": 4940169560.064}, "add9": {"acc": 0.0, "reasoning_bytes": 84.062, "flops_per_problem": 5300893532.16}, "add10": {"acc": 0.0, "reasoning_bytes": 90.414, "flops_per_problem": 5717616279.552}, "reach14": {"acc": 0.502, "reasoning_bytes": 9.102, "flops_per_problem": 4693827944.448}, "reach16": {"acc": 0.468, "reasoning_bytes": 9.524, "flops_per_problem": 5294004092.928}, "reach18": {"acc": 0.462, "reasoning_bytes": 9.84, "flops_per_problem": 5927655849.984}, "parity24": {"acc": 0.508, "reasoning_bytes": 136.604, "flops_per_problem": 7578559807.488}, "parity28": {"acc": 0.51, "reasoning_bytes": 158.9, "flops_per_problem": 8739871948.8}, "parity32": {"acc": 0.518, "reasoning_bytes": 182.132, "flops_per_problem": 9942520725.504}, "cmp8": {"acc": 0.938, "reasoning_bytes": 5.604, "flops_per_problem": 1351478329.344}, "cmp9": {"acc": 0.96, "reasoning_bytes": 5.484, "flops_per_problem": 1434593230.848}, "cmp10": {"acc": 0.952, "reasoning_bytes": 5.424, "flops_per_problem": 1520269590.528}, "runmax12": {"acc": 0.998, "reasoning_bytes": 71.024, "flops_per_problem": 4152388681.728}, "runmax14": {"acc": 0.998, "reasoning_bytes": 81.464, "flops_per_problem": 4701777297.408}, "runmax16": {"acc": 0.984, "reasoning_bytes": 89.396, "flops_per_problem": 5140404928.512}, "count16": {"acc": 0.768, "reasoning_bytes": 78.21, "flops_per_problem": 4690559877.12}, "count18": {"acc": 0.59, "reasoning_bytes": 86.964, "flops_per_problem": 5171319078.912}, "count20": {"acc": 0.4, "reasoning_bytes": 95.852, "flops_per_problem": 5678841102.336}, "brackets16": {"acc": 0.414, "reasoning_bytes": 50.12, "flops_per_problem": 3493740625.92}, "brackets18": {"acc": 0.576, "reasoning_bytes": 55.282, "flops_per_problem": 3814187876.352}, "brackets20": {"acc": 0.658, "reasoning_bytes": 66.332, "flops_per_problem": 4391045922.816}, "sumd8": {"acc": 0.508, "reasoning_bytes": 58.578, "flops_per_problem": 3381566423.04}, "sumd9": {"acc": 0.222, "reasoning_bytes": 66.358, "flops_per_problem": 3769141542.912}, "sumd10": {"acc": 0.082, "reasoning_bytes": 73.858, "flops_per_problem": 4144527654.912}, "inc8": {"acc": 0.476, "reasoning_bytes": 63.002, "flops_per_problem": 3812333027.328}, "inc9": {"acc": 0.068, "reasoning_bytes": 69.768, "flops_per_problem": 4200438104.064}, "inc10": {"acc": 0.0, "reasoning_bytes": 71.428, "flops_per_problem": 4333987233.792}, "add.cmp6": {"acc": 0.976, "reasoning_bytes": 92.39, "flops_per_problem": 5521797218.304}, "add.cmp7": {"acc": 0.9, "reasoning_bytes": 105.852, "flops_per_problem": 6249074688.0}, "add.cmp8": {"acc": 0.752, "reasoning_bytes": 118.386, "flops_per_problem": 6949412683.776}, "add.runmax6": {"acc": 0.988, "reasoning_bytes": 120.742, "flops_per_problem": 6568903655.424}, "add.runmax7": {"acc": 0.886, "reasoning_bytes": 138.36, "flops_per_problem": 7436001411.072}, "add.runmax8": {"acc": 0.526, "reasoning_bytes": 149.964, "flops_per_problem": 8036089233.408}, "add.count6": {"acc": 0.88, "reasoning_bytes": 115.78, "flops_per_problem": 6393929564.16}, "add.count7": {"acc": 0.664, "reasoning_bytes": 132.354, "flops_per_problem": 7214214463.488}, "add.count8": {"acc": 0.324, "reasoning_bytes": 147.24, "flops_per_problem": 7959863771.136}, "add.find6": {"acc": 0.568, "reasoning_bytes": 109.924, "flops_per_problem": 6091147542.528}, "add.find7": {"acc": 0.468, "reasoning_bytes": 126.218, "flops_per_problem": 6899950043.136}, "add.find8": {"acc": 0.3, "reasoning_bytes": 138.52, "flops_per_problem": 7534485061.632}, "add.rev6": {"acc": 0.218, "reasoning_bytes": 122.506, "flops_per_problem": 6753240317.952}, "add.rev7": {"acc": 0.016, "reasoning_bytes": 141.558, "flops_per_problem": 7729685839.872}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 148.992, "flops_per_problem": 8182269001.728}, "add.sumd6": {"acc": 0.498, "reasoning_bytes": 125.926, "flops_per_problem": 6753151991.808}, "add.sumd7": {"acc": 0.124, "reasoning_bytes": 143.094, "flops_per_problem": 7599228125.184}, "add.sumd8": {"acc": 0.032, "reasoning_bytes": 152.594, "flops_per_problem": 8108251693.056}, "add.inc6": {"acc": 0.078, "reasoning_bytes": 125.266, "flops_per_problem": 6864089628.672}, "add.inc7": {"acc": 0.002, "reasoning_bytes": 143.162, "flops_per_problem": 7784978006.016}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 154.506, "flops_per_problem": 8410857062.4}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5122916352.0}, "runmax.cmp14": {"acc": 0.988, "reasoning_bytes": 97.38, "flops_per_problem": 5669655183.36}, "runmax.cmp16": {"acc": 0.964, "reasoning_bytes": 105.144, "flops_per_problem": 6100863418.368}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 88.012, "flops_per_problem": 5211772452.864}, "runmax.runmax14": {"acc": 0.994, "reasoning_bytes": 101.212, "flops_per_problem": 5883051147.264}, "runmax.runmax16": {"acc": 0.982, "reasoning_bytes": 108.936, "flops_per_problem": 6312492859.392}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.024, "flops_per_problem": 5256465481.728}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 99.748, "flops_per_problem": 5862559481.856}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 107.008, "flops_per_problem": 6271509528.576}, "runmax.find12": {"acc": 0.99, "reasoning_bytes": 88.108, "flops_per_problem": 5216012107.776}, "runmax.find14": {"acc": 0.974, "reasoning_bytes": 99.748, "flops_per_problem": 5818396409.856}, "runmax.find16": {"acc": 0.914, "reasoning_bytes": 106.832, "flops_per_problem": 6219573755.904}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 83.108, "flops_per_problem": 4862707531.776}, "runmax.rev14": {"acc": 0.994, "reasoning_bytes": 94.664, "flops_per_problem": 5461382135.808}, "runmax.rev16": {"acc": 0.984, "reasoning_bytes": 101.688, "flops_per_problem": 5859909697.536}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 86.012, "flops_per_problem": 5035120164.864}, "runmax.sumd14": {"acc": 0.994, "reasoning_bytes": 97.284, "flops_per_problem": 5621252456.448}, "runmax.sumd16": {"acc": 0.972, "reasoning_bytes": 106.044, "flops_per_problem": 6096447111.168}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 87.108, "flops_per_problem": 5070538948.608}, "runmax.inc14": {"acc": 0.992, "reasoning_bytes": 98.7, "flops_per_problem": 5673983164.416}, "runmax.inc16": {"acc": 0.978, "reasoning_bytes": 105.876, "flops_per_problem": 6081343340.544}, "count.cmp16": {"acc": 0.966, "reasoning_bytes": 94.23, "flops_per_problem": 5663030722.56}, "count.cmp18": {"acc": 0.916, "reasoning_bytes": 101.75, "flops_per_problem": 6083551494.144}, "count.cmp20": {"acc": 0.854, "reasoning_bytes": 109.85, "flops_per_problem": 6529686847.488}, "count.runmax16": {"acc": 0.804, "reasoning_bytes": 95.08, "flops_per_problem": 5744732405.76}, "count.runmax18": {"acc": 0.654, "reasoning_bytes": 102.98, "flops_per_problem": 6181946818.56}, "count.runmax20": {"acc": 0.538, "reasoning_bytes": 111.23, "flops_per_problem": 6634618306.56}, "count.count16": {"acc": 0.996, "reasoning_bytes": 95.52, "flops_per_problem": 5808327229.44}, "count.count18": {"acc": 0.976, "reasoning_bytes": 103.368, "flops_per_problem": 6243245162.496}, "count.count20": {"acc": 0.948, "reasoning_bytes": 111.05, "flops_per_problem": 6670832025.6}, "count.find16": {"acc": 0.946, "reasoning_bytes": 95.7, "flops_per_problem": 5772113510.4}, "count.find18": {"acc": 0.884, "reasoning_bytes": 103.63, "flops_per_problem": 6210652815.36}, "count.find20": {"acc": 0.866, "reasoning_bytes": 111.448, "flops_per_problem": 6644775813.12}, "count.rev16": {"acc": 0.82, "reasoning_bytes": 89.97, "flops_per_problem": 5386569891.84}, "count.rev18": {"acc": 0.688, "reasoning_bytes": 97.65, "flops_per_problem": 5814068428.8}, "count.rev20": {"acc": 0.556, "reasoning_bytes": 105.9, "flops_per_problem": 6266739916.8}, "count.sumd16": {"acc": 0.83, "reasoning_bytes": 93.22, "flops_per_problem": 5574262947.84}, "count.sumd18": {"acc": 0.668, "reasoning_bytes": 101.0, "flops_per_problem": 6006177792.0}, "count.sumd20": {"acc": 0.536, "reasoning_bytes": 109.21, "flops_per_problem": 6457082757.12}, "count.inc16": {"acc": 0.83, "reasoning_bytes": 94.1, "flops_per_problem": 5568963379.2}, "count.inc18": {"acc": 0.688, "reasoning_bytes": 101.95, "flops_per_problem": 6004057964.544}, "count.inc20": {"acc": 0.566, "reasoning_bytes": 110.06, "flops_per_problem": 6450458296.32}, "parity.cmp16": {"acc": 0.946, "reasoning_bytes": 110.472, "flops_per_problem": 6336164265.984}, "parity.cmp20": {"acc": 0.956, "reasoning_bytes": 129.012, "flops_per_problem": 7331599908.864}, "parity.cmp24": {"acc": 0.94, "reasoning_bytes": 147.9, "flops_per_problem": 8342404300.8}, "parity.runmax16": {"acc": 0.658, "reasoning_bytes": 111.028, "flops_per_problem": 6404882006.016}, "parity.runmax20": {"acc": 0.512, "reasoning_bytes": 130.096, "flops_per_problem": 7423635750.912}, "parity.runmax24": {"acc": 0.562, "reasoning_bytes": 152.44, "flops_per_problem": 8587067719.68}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 111.748, "flops_per_problem": 6480842489.856}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 130.192, "flops_per_problem": 7472038477.824}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 151.268, "flops_per_problem": 8579471671.296}, "parity.find16": {"acc": 0.892, "reasoning_bytes": 111.88, "flops_per_problem": 6442508943.36}, "parity.find20": {"acc": 0.92, "reasoning_bytes": 130.228, "flops_per_problem": 7429465276.416}, "parity.find24": {"acc": 0.876, "reasoning_bytes": 150.868, "flops_per_problem": 8517643370.496}, "parity.rev16": {"acc": 0.636, "reasoning_bytes": 106.676, "flops_per_problem": 6080195100.672}, "parity.rev20": {"acc": 0.562, "reasoning_bytes": 125.012, "flops_per_problem": 7066621476.864}, "parity.rev24": {"acc": 0.486, "reasoning_bytes": 146.356, "flops_per_problem": 8185890373.632}, "parity.sumd16": {"acc": 0.616, "reasoning_bytes": 109.376, "flops_per_problem": 6243598467.072}, "parity.sumd20": {"acc": 0.536, "reasoning_bytes": 128.168, "flops_per_problem": 7250163204.096}, "parity.sumd24": {"acc": 0.526, "reasoning_bytes": 149.684, "flops_per_problem": 8377028149.248}, "parity.inc16": {"acc": 0.646, "reasoning_bytes": 110.892, "flops_per_problem": 6266386612.224}, "parity.inc20": {"acc": 0.536, "reasoning_bytes": 129.496, "flops_per_problem": 7264648691.712}, "parity.inc24": {"acc": 0.53, "reasoning_bytes": 152.884, "flops_per_problem": 8474186907.648}, "sumd.cmp6": {"acc": 0.978, "reasoning_bytes": 61.912, "flops_per_problem": 3705635045.376}, "sumd.cmp7": {"acc": 0.948, "reasoning_bytes": 69.642, "flops_per_problem": 4091355316.224}, "sumd.cmp8": {"acc": 0.924, "reasoning_bytes": 75.494, "flops_per_problem": 4393872359.424}, "sumd.runmax6": {"acc": 0.954, "reasoning_bytes": 67.492, "flops_per_problem": 3952241639.424}, "sumd.runmax7": {"acc": 0.902, "reasoning_bytes": 75.06, "flops_per_problem": 4330630840.32}, "sumd.runmax8": {"acc": 0.6, "reasoning_bytes": 81.014, "flops_per_problem": 4637740843.008}, "sumd.count6": {"acc": 0.948, "reasoning_bytes": 66.428, "flops_per_problem": 3949415202.816}, "sumd.count7": {"acc": 0.89, "reasoning_bytes": 74.366, "flops_per_problem": 4344144740.352}, "sumd.count8": {"acc": 0.706, "reasoning_bytes": 80.906, "flops_per_problem": 4677134303.232}, "sumd.find6": {"acc": 0.97, "reasoning_bytes": 66.304, "flops_per_problem": 3899775909.888}, "sumd.find7": {"acc": 0.946, "reasoning_bytes": 74.276, "flops_per_problem": 4296006991.872}, "sumd.find8": {"acc": 0.808, "reasoning_bytes": 80.892, "flops_per_problem": 4632352948.224}, "sumd.rev6": {"acc": 0.948, "reasoning_bytes": 61.542, "flops_per_problem": 3601056890.88}, "sumd.rev7": {"acc": 0.862, "reasoning_bytes": 69.35, "flops_per_problem": 3988720336.896}, "sumd.rev8": {"acc": 0.514, "reasoning_bytes": 76.832, "flops_per_problem": 4357128683.52}, "sumd.sumd6": {"acc": 0.93, "reasoning_bytes": 65.684, "flops_per_problem": 3792459644.928}, "sumd.sumd7": {"acc": 0.876, "reasoning_bytes": 73.54, "flops_per_problem": 4185952616.448}, "sumd.sumd8": {"acc": 0.52, "reasoning_bytes": 80.298, "flops_per_problem": 4528216424.448}, "sumd.inc6": {"acc": 0.968, "reasoning_bytes": 68.536, "flops_per_problem": 3909933416.448}, "sumd.inc7": {"acc": 0.9, "reasoning_bytes": 76.41, "flops_per_problem": 4301659865.088}, "sumd.inc8": {"acc": 0.58, "reasoning_bytes": 83.804, "flops_per_problem": 4671393103.872}, "inc.cmp6": {"acc": 0.972, "reasoning_bytes": 78.374, "flops_per_problem": 4565313404.928}, "inc.cmp7": {"acc": 0.934, "reasoning_bytes": 88.062, "flops_per_problem": 5081491390.464}, "inc.cmp8": {"acc": 0.718, "reasoning_bytes": 95.766, "flops_per_problem": 5510049841.152}, "inc.runmax6": {"acc": 0.99, "reasoning_bytes": 104.0, "flops_per_problem": 5520384000.0}, "inc.runmax7": {"acc": 0.96, "reasoning_bytes": 118.234, "flops_per_problem": 6193164238.848}, "inc.runmax8": {"acc": 0.82, "reasoning_bytes": 121.01, "flops_per_problem": 6359923998.72}, "inc.count6": {"acc": 0.89, "reasoning_bytes": 99.13, "flops_per_problem": 5349472911.36}, "inc.count7": {"acc": 0.724, "reasoning_bytes": 111.74, "flops_per_problem": 5950532321.28}, "inc.count8": {"acc": 0.576, "reasoning_bytes": 114.596, "flops_per_problem": 6120825126.912}, "inc.find6": {"acc": 0.618, "reasoning_bytes": 92.5, "flops_per_problem": 5012508672.0}, "inc.find7": {"acc": 0.518, "reasoning_bytes": 104.578, "flops_per_problem": 5589985001.472}, "inc.find8": {"acc": 0.252, "reasoning_bytes": 108.964, "flops_per_problem": 5828112285.696}, "inc.rev6": {"acc": 0.578, "reasoning_bytes": 104.058, "flops_per_problem": 5607561904.128}, "inc.rev7": {"acc": 0.02, "reasoning_bytes": 117.05, "flops_per_problem": 6244570054.656}, "inc.rev8": {"acc": 0.0, "reasoning_bytes": 121.208, "flops_per_problem": 6484728840.192}, "inc.sumd6": {"acc": 0.696, "reasoning_bytes": 109.6, "flops_per_problem": 5723534131.2}, "inc.sumd7": {"acc": 0.264, "reasoning_bytes": 124.3, "flops_per_problem": 6416629383.168}, "inc.sumd8": {"acc": 0.02, "reasoning_bytes": 126.618, "flops_per_problem": 6563250782.208}, "inc.inc6": {"acc": 0.588, "reasoning_bytes": 112.072, "flops_per_problem": 5969345789.952}, "inc.inc7": {"acc": 0.004, "reasoning_bytes": 123.124, "flops_per_problem": 6526330454.016}, "inc.inc8": {"acc": 0.0, "reasoning_bytes": 128.098, "flops_per_problem": 6810210680.832}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 116.692, "flops_per_problem": 6831673933.824}, "runmax.runmax.cmp16": {"acc": 0.99, "reasoning_bytes": 124.892, "flops_per_problem": 7282137268.224}, "sumd.runmax.cmp6": {"acc": 0.96, "reasoning_bytes": 83.304, "flops_per_problem": 4915526565.888}, "sumd.runmax.cmp7": {"acc": 0.926, "reasoning_bytes": 90.828, "flops_per_problem": 5291972591.616}, "sumd.runmax.cmp8": {"acc": 0.692, "reasoning_bytes": 93.236, "flops_per_problem": 5442480340.992}, "add.runmax.cmp6": {"acc": 0.99, "reasoning_bytes": 136.972, "flops_per_problem": 7550648745.984}, "add.runmax.cmp7": {"acc": 0.888, "reasoning_bytes": 144.648, "flops_per_problem": 7977970630.656}, "add.runmax.cmp8": {"acc": 0.902, "reasoning_bytes": 156.226, "flops_per_problem": 8577616822.272}, "count.runmax.runmax16": {"acc": 0.808, "reasoning_bytes": 112.444, "flops_per_problem": 6820721491.968}, "count.runmax.runmax18": {"acc": 0.678, "reasoning_bytes": 119.84, "flops_per_problem": 7235677716.48}, "count.runmax.runmax20": {"acc": 0.582, "reasoning_bytes": 128.074, "flops_per_problem": 7687642595.328}, "add.runmax.runmax6": {"acc": 0.966, "reasoning_bytes": 137.834, "flops_per_problem": 7632880386.048}, "add.runmax.runmax7": {"acc": 0.754, "reasoning_bytes": 155.66, "flops_per_problem": 8508457451.52}, "add.runmax.runmax8": {"acc": 0.52, "reasoning_bytes": 162.214, "flops_per_problem": 8886228369.408}, "parity.runmax.runmax16": {"acc": 0.864, "reasoning_bytes": 128.988, "flops_per_problem": 7507192283.136}, "parity.runmax.runmax20": {"acc": 0.476, "reasoning_bytes": 147.664, "flops_per_problem": 8508634103.808}, "parity.runmax.runmax24": {"acc": 0.54, "reasoning_bytes": 170.5, "flops_per_problem": 9693794304.0}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 129.012, "flops_per_problem": 7552415268.864}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 148.472, "flops_per_problem": 8588480937.984}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 171.472, "flops_per_problem": 9780883881.984}, "inc.runmax.count6": {"acc": 0.996, "reasoning_bytes": 120.892, "flops_per_problem": 6619514535.936}, "inc.runmax.count7": {"acc": 0.994, "reasoning_bytes": 126.27, "flops_per_problem": 6901363261.44}, "inc.runmax.count8": {"acc": 0.99, "reasoning_bytes": 137.366, "flops_per_problem": 7435559780.352}, "sumd.runmax.count6": {"acc": 0.966, "reasoning_bytes": 84.396, "flops_per_problem": 5052078784.512}, "sumd.runmax.count7": {"acc": 0.908, "reasoning_bytes": 92.154, "flops_per_problem": 5438858969.088}, "sumd.runmax.count8": {"acc": 0.77, "reasoning_bytes": 97.618, "flops_per_problem": 5724329066.496}, "runmax.runmax.find12": {"acc": 0.998, "reasoning_bytes": 105.036, "flops_per_problem": 6272746094.592}, "runmax.runmax.find14": {"acc": 0.95, "reasoning_bytes": 117.624, "flops_per_problem": 6916996988.928}, "runmax.runmax.find16": {"acc": 0.83, "reasoning_bytes": 127.584, "flops_per_problem": 7445187330.048}, "add.runmax.find6": {"acc": 0.994, "reasoning_bytes": 138.184, "flops_per_problem": 7648249135.104}, "add.runmax.find7": {"acc": 0.924, "reasoning_bytes": 155.684, "flops_per_problem": 8509075734.528}, "add.runmax.find8": {"acc": 0.838, "reasoning_bytes": 161.028, "flops_per_problem": 8834645901.312}, "parity.runmax.find16": {"acc": 0.952, "reasoning_bytes": 129.0, "flops_per_problem": 7507722240.0}, "parity.runmax.find20": {"acc": 0.884, "reasoning_bytes": 148.532, "flops_per_problem": 8546967650.304}, "parity.runmax.find24": {"acc": 0.888, "reasoning_bytes": 171.232, "flops_per_problem": 9726121672.704}, "add.runmax.rev6": {"acc": 0.986, "reasoning_bytes": 132.846, "flops_per_problem": 7280105766.912}, "add.runmax.rev7": {"acc": 0.792, "reasoning_bytes": 149.674, "flops_per_problem": 8111608086.528}, "add.runmax.rev8": {"acc": 0.518, "reasoning_bytes": 153.216, "flops_per_problem": 8356359831.552}, "parity.runmax.rev16": {"acc": 0.834, "reasoning_bytes": 124.01, "flops_per_problem": 7154859294.72}, "parity.runmax.rev20": {"acc": 0.48, "reasoning_bytes": 142.408, "flops_per_problem": 8144023781.376}, "parity.runmax.rev24": {"acc": 0.532, "reasoning_bytes": 166.01, "flops_per_problem": 9363012894.72}, "sumd.runmax.rev6": {"acc": 0.968, "reasoning_bytes": 79.532, "flops_per_problem": 4660617314.304}, "sumd.runmax.rev7": {"acc": 0.916, "reasoning_bytes": 87.316, "flops_per_problem": 5048545738.752}, "sumd.runmax.rev8": {"acc": 0.59, "reasoning_bytes": 92.844, "flops_per_problem": 5336842272.768}, "sumd.runmax.sumd6": {"acc": 0.97, "reasoning_bytes": 82.494, "flops_per_problem": 4835591405.568}, "sumd.runmax.sumd7": {"acc": 0.912, "reasoning_bytes": 90.28, "flops_per_problem": 5223608156.16}, "sumd.runmax.sumd8": {"acc": 0.594, "reasoning_bytes": 95.382, "flops_per_problem": 5493091221.504}, "add.runmax.sumd6": {"acc": 0.988, "reasoning_bytes": 135.786, "flops_per_problem": 7454108270.592}, "add.runmax.sumd7": {"acc": 0.802, "reasoning_bytes": 153.264, "flops_per_problem": 8314316587.008}, "add.runmax.sumd8": {"acc": 0.486, "reasoning_bytes": 157.848, "flops_per_problem": 8605086253.056}, "parity.runmax.sumd16": {"acc": 0.81, "reasoning_bytes": 126.868, "flops_per_problem": 7325240426.496}, "parity.runmax.sumd20": {"acc": 0.474, "reasoning_bytes": 145.516, "flops_per_problem": 8325445681.152}, "parity.runmax.sumd24": {"acc": 0.568, "reasoning_bytes": 168.588, "flops_per_problem": 9521028366.336}, "count.runmax.inc16": {"acc": 0.838, "reasoning_bytes": 111.394, "flops_per_problem": 6641861050.368}, "count.runmax.inc18": {"acc": 0.698, "reasoning_bytes": 118.83, "flops_per_problem": 7058583797.76}, "count.runmax.inc20": {"acc": 0.612, "reasoning_bytes": 126.95, "flops_per_problem": 7505514086.4}, "runmax.runmax.inc12": {"acc": 1.0, "reasoning_bytes": 104.048, "flops_per_problem": 6127802892.288}, "runmax.runmax.inc14": {"acc": 0.996, "reasoning_bytes": 116.12, "flops_per_problem": 6752445382.656}, "runmax.runmax.inc16": {"acc": 0.988, "reasoning_bytes": 126.696, "flops_per_problem": 7310136655.872}, "add.runmax.inc6": {"acc": 0.934, "reasoning_bytes": 137.05, "flops_per_problem": 7489085423.616}, "add.runmax.inc7": {"acc": 0.736, "reasoning_bytes": 154.938, "flops_per_problem": 8371021971.456}, "add.runmax.inc8": {"acc": 0.53, "reasoning_bytes": 160.782, "flops_per_problem": 8717702086.656}, "count.count.cmp16": {"acc": 0.988, "reasoning_bytes": 111.98, "flops_per_problem": 6800229826.56}, "count.count.cmp18": {"acc": 0.97, "reasoning_bytes": 119.72, "flops_per_problem": 7230378147.84}, "count.count.cmp20": {"acc": 0.97, "reasoning_bytes": 127.368, "flops_per_problem": 7656463466.496}, "add.count.cmp6": {"acc": 0.952, "reasoning_bytes": 131.618, "flops_per_problem": 7358362730.496}, "add.count.cmp7": {"acc": 0.888, "reasoning_bytes": 145.758, "flops_per_problem": 8071154712.576}, "add.count.cmp8": {"acc": 0.826, "reasoning_bytes": 150.92, "flops_per_problem": 8387450634.24}, "sumd.count.cmp6": {"acc": 0.99, "reasoning_bytes": 82.452, "flops_per_problem": 4922062700.544}, "sumd.count.cmp7": {"acc": 0.972, "reasoning_bytes": 89.832, "flops_per_problem": 5292149243.904}, "sumd.count.cmp8": {"acc": 0.944, "reasoning_bytes": 92.464, "flops_per_problem": 5452549521.408}, "add.count.runmax6": {"acc": 0.864, "reasoning_bytes": 132.874, "flops_per_problem": 7457994620.928}, "add.count.runmax7": {"acc": 0.428, "reasoning_bytes": 150.934, "flops_per_problem": 8343817519.104}, "add.count.runmax8": {"acc": 0.272, "reasoning_bytes": 158.352, "flops_per_problem": 8759833657.344}, "sumd.count.runmax6": {"acc": 0.954, "reasoning_bytes": 83.404, "flops_per_problem": 5008269017.088}, "sumd.count.runmax7": {"acc": 0.902, "reasoning_bytes": 91.142, "flops_per_problem": 5394165940.224}, "sumd.count.runmax8": {"acc": 0.664, "reasoning_bytes": 96.526, "flops_per_problem": 5676102991.872}, "inc.count.runmax6": {"acc": 0.906, "reasoning_bytes": 116.23, "flops_per_problem": 6413802946.56}, "inc.count.runmax7": {"acc": 0.658, "reasoning_bytes": 119.996, "flops_per_problem": 6624284147.712}, "inc.count.runmax8": {"acc": 0.514, "reasoning_bytes": 133.258, "flops_per_problem": 7254137880.576}, "parity.count.count16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7596048384.0}, "parity.count.count20": {"acc": 1.0, "reasoning_bytes": 147.204, "flops_per_problem": 8576645234.688}, "parity.count.count24": {"acc": 1.0, "reasoning_bytes": 168.828, "flops_per_problem": 9708279791.616}, "runmax.count.count12": {"acc": 1.0, "reasoning_bytes": 105.004, "flops_per_problem": 6359659020.288}, "runmax.count.count14": {"acc": 1.0, "reasoning_bytes": 116.952, "flops_per_problem": 6975645548.544}, "runmax.count.count16": {"acc": 1.0, "reasoning_bytes": 124.68, "flops_per_problem": 7405263912.96}, "inc.count.count6": {"acc": 0.984, "reasoning_bytes": 115.89, "flops_per_problem": 6442950574.08}, "inc.count.count7": {"acc": 0.886, "reasoning_bytes": 122.028, "flops_per_problem": 6758186582.016}, "inc.count.count8": {"acc": 0.896, "reasoning_bytes": 131.21, "flops_per_problem": 7207854981.12}, "inc.count.find6": {"acc": 0.962, "reasoning_bytes": 116.048, "flops_per_problem": 6405765267.456}, "inc.count.find7": {"acc": 0.9, "reasoning_bytes": 127.094, "flops_per_problem": 6937753632.768}, "inc.count.find8": {"acc": 0.882, "reasoning_bytes": 131.4, "flops_per_problem": 7172082892.8}, "add.count.find6": {"acc": 0.926, "reasoning_bytes": 132.74, "flops_per_problem": 7451988443.136}, "add.count.find7": {"acc": 0.852, "reasoning_bytes": 149.906, "flops_per_problem": 8298241228.8}, "add.count.find8": {"acc": 0.826, "reasoning_bytes": 158.41, "flops_per_problem": 8762571767.808}, "runmax.count.find12": {"acc": 1.0, "reasoning_bytes": 105.012, "flops_per_problem": 6315849252.864}, "runmax.count.find14": {"acc": 1.0, "reasoning_bytes": 116.988, "flops_per_problem": 6933072347.136}, "runmax.count.find16": {"acc": 1.0, "reasoning_bytes": 124.74, "flops_per_problem": 7363750625.28}, "parity.count.rev16": {"acc": 1.0, "reasoning_bytes": 124.012, "flops_per_problem": 7199110692.864}, "parity.count.rev20": {"acc": 1.0, "reasoning_bytes": 142.324, "flops_per_problem": 8184477155.328}, "parity.count.rev24": {"acc": 1.0, "reasoning_bytes": 163.996, "flops_per_problem": 9318231539.712}, "inc.count.rev6": {"acc": 0.904, "reasoning_bytes": 110.95, "flops_per_problem": 6048132710.4}, "inc.count.rev7": {"acc": 0.702, "reasoning_bytes": 114.438, "flops_per_problem": 6246336577.536}, "inc.count.rev8": {"acc": 0.548, "reasoning_bytes": 126.404, "flops_per_problem": 6818954969.088}, "runmax.count.rev12": {"acc": 1.0, "reasoning_bytes": 100.036, "flops_per_problem": 5963604590.592}, "runmax.count.rev14": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6580297728.0}, "runmax.count.rev16": {"acc": 1.0, "reasoning_bytes": 119.788, "flops_per_problem": 7012565876.736}, "count.count.sumd16": {"acc": 0.998, "reasoning_bytes": 110.944, "flops_per_problem": 6710313811.968}, "count.count.sumd18": {"acc": 0.986, "reasoning_bytes": 119.02, "flops_per_problem": 7155300925.44}, "count.count.sumd20": {"acc": 0.97, "reasoning_bytes": 126.38, "flops_per_problem": 7568667279.36}, "runmax.count.sumd12": {"acc": 1.0, "reasoning_bytes": 103.036, "flops_per_problem": 6140256878.592}, "runmax.count.sumd14": {"acc": 1.0, "reasoning_bytes": 115.496, "flops_per_problem": 6778854899.712}, "runmax.count.sumd16": {"acc": 1.0, "reasoning_bytes": 124.3, "flops_per_problem": 7255992729.6}, "sumd.count.sumd6": {"acc": 0.964, "reasoning_bytes": 81.41, "flops_per_problem": 4831881707.52}, "sumd.count.sumd7": {"acc": 0.918, "reasoning_bytes": 89.258, "flops_per_problem": 5222636568.576}, "sumd.count.sumd8": {"acc": 0.75, "reasoning_bytes": 95.688, "flops_per_problem": 5550768193.536}, "parity.count.inc16": {"acc": 1.0, "reasoning_bytes": 128.024, "flops_per_problem": 7376292937.728}, "parity.count.inc20": {"acc": 1.0, "reasoning_bytes": 146.864, "flops_per_problem": 8384977502.208}, "parity.count.inc24": {"acc": 1.0, "reasoning_bytes": 169.912, "flops_per_problem": 9579500273.664}, "count.count.inc16": {"acc": 0.998, "reasoning_bytes": 111.858, "flops_per_problem": 6706515787.776}, "count.count.inc18": {"acc": 0.972, "reasoning_bytes": 119.474, "flops_per_problem": 7131187888.128}, "count.count.inc20": {"acc": 0.944, "reasoning_bytes": 127.05, "flops_per_problem": 7554093465.6}, "add.count.inc6": {"acc": 0.87, "reasoning_bytes": 131.784, "flops_per_problem": 7277367656.448}, "add.count.inc7": {"acc": 0.526, "reasoning_bytes": 148.146, "flops_per_problem": 8089968181.248}, "add.count.inc8": {"acc": 0.32, "reasoning_bytes": 155.478, "flops_per_problem": 8505366036.48}, "parity.rev.cmp16": {"acc": 0.954, "reasoning_bytes": 122.952, "flops_per_problem": 7063971692.544}, "parity.rev.cmp20": {"acc": 0.948, "reasoning_bytes": 141.236, "flops_per_problem": 8048101588.992}, "parity.rev.cmp24": {"acc": 0.956, "reasoning_bytes": 160.836, "flops_per_problem": 9090350088.192}, "sumd.rev.cmp6": {"acc": 0.934, "reasoning_bytes": 81.064, "flops_per_problem": 4728098488.32}, "sumd.rev.cmp7": {"acc": 0.924, "reasoning_bytes": 88.642, "flops_per_problem": 5107105972.224}, "sumd.rev.cmp8": {"acc": 0.688, "reasoning_bytes": 91.428, "flops_per_problem": 5274219036.672}, "add.rev.cmp6": {"acc": 0.836, "reasoning_bytes": 157.718, "flops_per_problem": 8583446347.776}, "add.rev.cmp7": {"acc": 0.738, "reasoning_bytes": 177.082, "flops_per_problem": 9568194527.232}, "add.rev.cmp8": {"acc": 0.71, "reasoning_bytes": 187.858, "flops_per_problem": 10197341650.944}, "runmax.rev.runmax12": {"acc": 1.0, "reasoning_bytes": 100.044, "flops_per_problem": 5919794823.168}, "runmax.rev.runmax14": {"acc": 0.994, "reasoning_bytes": 113.736, "flops_per_problem": 6612713422.848}, "runmax.rev.runmax16": {"acc": 0.988, "reasoning_bytes": 121.75, "flops_per_problem": 7055050752.0}, "count.rev.runmax16": {"acc": 0.836, "reasoning_bytes": 107.14, "flops_per_problem": 6453991342.08}, "count.rev.runmax18": {"acc": 0.724, "reasoning_bytes": 114.16, "flops_per_problem": 6852342251.52}, "count.rev.runmax20": {"acc": 0.608, "reasoning_bytes": 122.524, "flops_per_problem": 7310048329.728}, "add.rev.runmax6": {"acc": 0.716, "reasoning_bytes": 185.994, "flops_per_problem": 9634085830.656}, "add.rev.runmax7": {"acc": 0.556, "reasoning_bytes": 210.41, "flops_per_problem": 10796281233.408}, "add.rev.runmax8": {"acc": 0.36, "reasoning_bytes": 218.852, "flops_per_problem": 11255488856.064}, "inc.rev.count6": {"acc": 0.588, "reasoning_bytes": 154.422, "flops_per_problem": 7974260932.608}, "inc.rev.count7": {"acc": 0.54, "reasoning_bytes": 160.968, "flops_per_problem": 8301244317.696}, "inc.rev.count8": {"acc": 0.466, "reasoning_bytes": 175.42, "flops_per_problem": 8983740432.384}, "count.rev.count16": {"acc": 0.998, "reasoning_bytes": 107.8, "flops_per_problem": 6527302041.6}, "count.rev.count18": {"acc": 1.0, "reasoning_bytes": 114.95, "flops_per_problem": 6931394150.4}, "count.rev.count20": {"acc": 0.992, "reasoning_bytes": 122.764, "flops_per_problem": 7364810539.008}, "parity.rev.count16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7198580736.0}, "parity.rev.count20": {"acc": 0.998, "reasoning_bytes": 143.454, "flops_per_problem": 8234381426.688}, "parity.rev.count24": {"acc": 1.0, "reasoning_bytes": 164.684, "flops_per_problem": 9348615733.248}, "sumd.rev.find6": {"acc": 0.912, "reasoning_bytes": 85.016, "flops_per_problem": 4902807601.152}, "sumd.rev.find7": {"acc": 0.882, "reasoning_bytes": 93.062, "flops_per_problem": 5302306750.464}, "sumd.rev.find8": {"acc": 0.76, "reasoning_bytes": 96.68, "flops_per_problem": 5506251816.96}, "runmax.rev.find12": {"acc": 0.996, "reasoning_bytes": 100.084, "flops_per_problem": 5921561346.048}, "runmax.rev.find14": {"acc": 0.998, "reasoning_bytes": 112.0, "flops_per_problem": 6536134656.0}, "runmax.rev.find16": {"acc": 0.996, "reasoning_bytes": 119.508, "flops_per_problem": 6956037144.576}, "count.rev.find16": {"acc": 0.94, "reasoning_bytes": 107.74, "flops_per_problem": 6480489185.28}, "count.rev.find18": {"acc": 0.9, "reasoning_bytes": 114.87, "flops_per_problem": 6883698032.64}, "count.rev.find20": {"acc": 0.906, "reasoning_bytes": 122.62, "flops_per_problem": 7315612876.8}, "count.rev.rev16": {"acc": 0.828, "reasoning_bytes": 101.73, "flops_per_problem": 6082579906.56}, "count.rev.rev18": {"acc": 0.692, "reasoning_bytes": 108.71, "flops_per_problem": 6479164293.12}, "count.rev.rev20": {"acc": 0.592, "reasoning_bytes": 116.89, "flops_per_problem": 6928744366.08}, "sumd.rev.rev6": {"acc": 0.956, "reasoning_bytes": 80.53, "flops_per_problem": 4616100937.728}, "sumd.rev.rev7": {"acc": 0.818, "reasoning_bytes": 88.416, "flops_per_problem": 5005354254.336}, "sumd.rev.rev8": {"acc": 0.294, "reasoning_bytes": 93.314, "flops_per_problem": 5256465481.728}, "parity.rev.rev16": {"acc": 0.74, "reasoning_bytes": 119.0, "flops_per_problem": 6801113088.0}, "parity.rev.rev20": {"acc": 0.476, "reasoning_bytes": 132.104, "flops_per_problem": 7556478271.488}, "parity.rev.rev24": {"acc": 0.518, "reasoning_bytes": 158.028, "flops_per_problem": 8878014038.016}, "sumd.rev.sumd6": {"acc": 0.908, "reasoning_bytes": 84.646, "flops_per_problem": 4806620430.336}, "sumd.rev.sumd7": {"acc": 0.82, "reasoning_bytes": 92.25, "flops_per_problem": 5188012720.128}, "sumd.rev.sumd8": {"acc": 0.428, "reasoning_bytes": 97.174, "flops_per_problem": 5443893559.296}, "parity.rev.sumd16": {"acc": 0.772, "reasoning_bytes": 122.124, "flops_per_problem": 6983241596.928}, "parity.rev.sumd20": {"acc": 0.446, "reasoning_bytes": 141.126, "flops_per_problem": 7999080579.072}, "parity.rev.sumd24": {"acc": 0.532, "reasoning_bytes": 162.292, "flops_per_problem": 9110488449.024}, "add.rev.sumd6": {"acc": 0.112, "reasoning_bytes": 190.474, "flops_per_problem": 9783886970.88}, "add.rev.sumd7": {"acc": 0.032, "reasoning_bytes": 215.15, "flops_per_problem": 10961009491.968}, "add.rev.sumd8": {"acc": 0.016, "reasoning_bytes": 224.512, "flops_per_problem": 11473566105.6}, "parity.rev.inc16": {"acc": 0.768, "reasoning_bytes": 123.0, "flops_per_problem": 6977765376.0}, "parity.rev.inc20": {"acc": 0.376, "reasoning_bytes": 139.644, "flops_per_problem": 7889467834.368}, "parity.rev.inc24": {"acc": 0.514, "reasoning_bytes": 164.122, "flops_per_problem": 9147143798.784}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 99.12, "flops_per_problem": 5777678057.472}, "runmax.rev.inc14": {"acc": 0.996, "reasoning_bytes": 110.988, "flops_per_problem": 6393311281.152}, "runmax.rev.inc16": {"acc": 0.986, "reasoning_bytes": 118.484, "flops_per_problem": 6814891966.464}, "inc.rev.inc6": {"acc": 0.044, "reasoning_bytes": 169.828, "flops_per_problem": 8680605106.176}, "inc.rev.inc7": {"acc": 0.0, "reasoning_bytes": 177.636, "flops_per_problem": 9105542184.96}, "inc.rev.inc8": {"acc": 0.0, "reasoning_bytes": 189.648, "flops_per_problem": 9707926487.04}, "parity.sumd.cmp16": {"acc": 0.962, "reasoning_bytes": 125.784, "flops_per_problem": 7233204584.448}, "parity.sumd.cmp20": {"acc": 0.948, "reasoning_bytes": 144.06, "flops_per_problem": 8216981176.32}, "parity.sumd.cmp24": {"acc": 0.948, "reasoning_bytes": 163.992, "flops_per_problem": 9273891815.424}, "runmax.sumd.cmp12": {"acc": 1.0, "reasoning_bytes": 102.0, "flops_per_problem": 6006177792.0}, "runmax.sumd.cmp14": {"acc": 0.998, "reasoning_bytes": 113.272, "flops_per_problem": 6592310083.584}, "runmax.sumd.cmp16": {"acc": 0.988, "reasoning_bytes": 120.3, "flops_per_problem": 6991014297.6}, "count.sumd.cmp16": {"acc": 0.968, "reasoning_bytes": 109.53, "flops_per_problem": 6559541084.16}, "count.sumd.cmp18": {"acc": 0.93, "reasoning_bytes": 116.39, "flops_per_problem": 6950825902.08}, "count.sumd.cmp20": {"acc": 0.916, "reasoning_bytes": 124.52, "flops_per_problem": 7398197821.44}, "sumd.sumd.runmax6": {"acc": 0.95, "reasoning_bytes": 84.242, "flops_per_problem": 4912788455.424}, "sumd.sumd.runmax7": {"acc": 0.848, "reasoning_bytes": 92.378, "flops_per_problem": 5316262281.216}, "sumd.sumd.runmax8": {"acc": 0.48, "reasoning_bytes": 97.228, "flops_per_problem": 5574616252.416}, "count.sumd.runmax16": {"acc": 0.846, "reasoning_bytes": 110.29, "flops_per_problem": 6637268090.88}, "count.sumd.runmax18": {"acc": 0.712, "reasoning_bytes": 117.558, "flops_per_problem": 7046571442.176}, "count.sumd.runmax20": {"acc": 0.6, "reasoning_bytes": 125.87, "flops_per_problem": 7501981040.64}, "add.sumd.runmax6": {"acc": 0.52, "reasoning_bytes": 150.882, "flops_per_problem": 8120882331.648}, "add.sumd.runmax7": {"acc": 0.198, "reasoning_bytes": 167.554, "flops_per_problem": 8946201821.184}, "add.sumd.runmax8": {"acc": 0.122, "reasoning_bytes": 170.452, "flops_per_problem": 9163749113.856}, "parity.sumd.count16": {"acc": 1.0, "reasoning_bytes": 127.012, "flops_per_problem": 7375762980.864}, "parity.sumd.count20": {"acc": 1.0, "reasoning_bytes": 145.54, "flops_per_problem": 8370668666.88}, "parity.sumd.count24": {"acc": 0.87, "reasoning_bytes": 166.062, "flops_per_problem": 9453635518.464}, "sumd.sumd.count6": {"acc": 0.972, "reasoning_bytes": 84.072, "flops_per_problem": 4949443805.184}, "sumd.sumd.count7": {"acc": 0.874, "reasoning_bytes": 91.9, "flops_per_problem": 5339315404.8}, "sumd.sumd.count8": {"acc": 0.716, "reasoning_bytes": 98.026, "flops_per_problem": 5654021455.872}, "add.sumd.count6": {"acc": 0.866, "reasoning_bytes": 149.782, "flops_per_problem": 8116377698.304}, "add.sumd.count7": {"acc": 0.786, "reasoning_bytes": 166.362, "flops_per_problem": 8937457532.928}, "add.sumd.count8": {"acc": 0.694, "reasoning_bytes": 174.214, "flops_per_problem": 9373523705.856}, "runmax.sumd.find12": {"acc": 0.986, "reasoning_bytes": 103.036, "flops_per_problem": 6096093806.592}, "runmax.sumd.find14": {"acc": 0.996, "reasoning_bytes": 114.848, "flops_per_problem": 6706074157.056}, "runmax.sumd.find16": {"acc": 0.966, "reasoning_bytes": 122.216, "flops_per_problem": 7119793815.552}, "sumd.sumd.find6": {"acc": 0.946, "reasoning_bytes": 83.736, "flops_per_problem": 4890441940.992}, "sumd.sumd.find7": {"acc": 0.922, "reasoning_bytes": 91.596, "flops_per_problem": 5281726758.912}, "sumd.sumd.find8": {"acc": 0.842, "reasoning_bytes": 97.074, "flops_per_problem": 5567815139.328}, "parity.sumd.find16": {"acc": 0.938, "reasoning_bytes": 126.988, "flops_per_problem": 7330539995.136}, "parity.sumd.find20": {"acc": 0.878, "reasoning_bytes": 145.528, "flops_per_problem": 8325975638.016}, "parity.sumd.find24": {"acc": 0.878, "reasoning_bytes": 167.46, "flops_per_problem": 9471212421.12}, "count.sumd.rev16": {"acc": 0.846, "reasoning_bytes": 105.23, "flops_per_problem": 6281313730.56}, "count.sumd.rev18": {"acc": 0.712, "reasoning_bytes": 112.33, "flops_per_problem": 6683197685.76}, "count.sumd.rev20": {"acc": 0.596, "reasoning_bytes": 120.57, "flops_per_problem": 7135427543.04}, "parity.sumd.rev16": {"acc": 0.774, "reasoning_bytes": 121.964, "flops_per_problem": 6976175505.408}, "parity.sumd.rev20": {"acc": 0.452, "reasoning_bytes": 140.192, "flops_per_problem": 7957832269.824}, "parity.sumd.rev24": {"acc": 0.524, "reasoning_bytes": 159.8, "flops_per_problem": 9000434073.6}, "add.sumd.rev6": {"acc": 0.47, "reasoning_bytes": 144.788, "flops_per_problem": 7758921793.536}, "add.sumd.rev7": {"acc": 0.03, "reasoning_bytes": 158.138, "flops_per_problem": 8426932420.608}, "add.sumd.rev8": {"acc": 0.004, "reasoning_bytes": 161.058, "flops_per_problem": 8630612508.672}, "parity.sumd.sumd16": {"acc": 0.73, "reasoning_bytes": 124.532, "flops_per_problem": 7133749346.304}, "parity.sumd.sumd20": {"acc": 0.422, "reasoning_bytes": 144.504, "flops_per_problem": 8192426508.288}, "parity.sumd.sumd24": {"acc": 0.534, "reasoning_bytes": 165.166, "flops_per_problem": 9281576189.952}, "add.sumd.sumd6": {"acc": 0.502, "reasoning_bytes": 149.178, "flops_per_problem": 7966488231.936}, "add.sumd.sumd7": {"acc": 0.084, "reasoning_bytes": 163.284, "flops_per_problem": 8677602017.28}, "add.sumd.sumd8": {"acc": 0.07, "reasoning_bytes": 165.99, "flops_per_problem": 8881635409.92}, "count.sumd.sumd16": {"acc": 0.844, "reasoning_bytes": 108.06, "flops_per_problem": 6450458296.32}, "count.sumd.sumd18": {"acc": 0.7, "reasoning_bytes": 115.42, "flops_per_problem": 6863824650.24}, "count.sumd.sumd20": {"acc": 0.574, "reasoning_bytes": 123.78, "flops_per_problem": 7321354076.16}, "inc.sumd.inc6": {"acc": 0.206, "reasoning_bytes": 130.676, "flops_per_problem": 6808620810.24}, "inc.sumd.inc7": {"acc": 0.008, "reasoning_bytes": 135.89, "flops_per_problem": 7081901899.776}, "inc.sumd.inc8": {"acc": 0.0, "reasoning_bytes": 145.022, "flops_per_problem": 7523002662.912}, "sumd.sumd.inc6": {"acc": 0.93, "reasoning_bytes": 83.27, "flops_per_problem": 4750091698.176}, "sumd.sumd.inc7": {"acc": 0.83, "reasoning_bytes": 91.486, "flops_per_problem": 5157805178.88}, "sumd.sumd.inc8": {"acc": 0.442, "reasoning_bytes": 97.044, "flops_per_problem": 5443363602.432}, "parity.sumd.inc16": {"acc": 0.778, "reasoning_bytes": 125.988, "flops_per_problem": 7153887707.136}, "parity.sumd.inc20": {"acc": 0.438, "reasoning_bytes": 145.628, "flops_per_problem": 8197902729.216}, "parity.sumd.inc24": {"acc": 0.554, "reasoning_bytes": 167.176, "flops_per_problem": 9326180892.672}, "inc.inc.cmp6": {"acc": 0.962, "reasoning_bytes": 144.768, "flops_per_problem": 7674128695.296}, "inc.inc.cmp7": {"acc": 0.736, "reasoning_bytes": 152.56, "flops_per_problem": 8106573496.32}, "inc.inc.cmp8": {"acc": 0.578, "reasoning_bytes": 166.512, "flops_per_problem": 8822810198.016}, "runmax.inc.cmp12": {"acc": 0.988, "reasoning_bytes": 105.55, "flops_per_problem": 6150061080.576}, "runmax.inc.cmp14": {"acc": 0.986, "reasoning_bytes": 117.704, "flops_per_problem": 6779208204.288}, "runmax.inc.cmp16": {"acc": 0.746, "reasoning_bytes": 120.91, "flops_per_problem": 7019896946.688}, "sumd.inc.cmp6": {"acc": 0.976, "reasoning_bytes": 88.016, "flops_per_problem": 5035120164.864}, "sumd.inc.cmp7": {"acc": 0.96, "reasoning_bytes": 95.762, "flops_per_problem": 5421547044.864}, "sumd.inc.cmp8": {"acc": 0.934, "reasoning_bytes": 99.562, "flops_per_problem": 5633529790.464}, "sumd.inc.runmax6": {"acc": 0.958, "reasoning_bytes": 93.412, "flops_per_problem": 5273600753.664}, "sumd.inc.runmax7": {"acc": 0.884, "reasoning_bytes": 101.074, "flops_per_problem": 5656141283.328}, "sumd.inc.runmax8": {"acc": 0.518, "reasoning_bytes": 105.33, "flops_per_problem": 5889410629.632}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.66, "flops_per_problem": 6344466923.52}, "runmax.inc.runmax14": {"acc": 0.308, "reasoning_bytes": 105.026, "flops_per_problem": 6258437259.264}, "runmax.inc.runmax16": {"acc": 0.22, "reasoning_bytes": 111.256, "flops_per_problem": 6625255735.296}, "add.inc.runmax6": {"acc": 0.736, "reasoning_bytes": 175.75, "flops_per_problem": 9216391495.68}, "add.inc.runmax7": {"acc": 0.266, "reasoning_bytes": 171.302, "flops_per_problem": 9235204964.352}, "add.inc.runmax8": {"acc": 0.184, "reasoning_bytes": 179.136, "flops_per_problem": 9672684355.584}, "runmax.inc.count12": {"acc": 0.696, "reasoning_bytes": 108.964, "flops_per_problem": 6357892497.408}, "runmax.inc.count14": {"acc": 0.242, "reasoning_bytes": 104.432, "flops_per_problem": 6277339054.08}, "runmax.inc.count16": {"acc": 0.314, "reasoning_bytes": 113.476, "flops_per_problem": 6763751129.088}, "sumd.inc.count6": {"acc": 0.95, "reasoning_bytes": 92.342, "flops_per_problem": 5270509338.624}, "sumd.inc.count7": {"acc": 0.878, "reasoning_bytes": 100.256, "flops_per_problem": 5664178962.432}, "sumd.inc.count8": {"acc": 0.638, "reasoning_bytes": 105.586, "flops_per_problem": 5944614469.632}, "inc.inc.count6": {"acc": 0.636, "reasoning_bytes": 161.402, "flops_per_problem": 8274481496.064}, "inc.inc.count7": {"acc": 0.524, "reasoning_bytes": 167.11, "flops_per_problem": 8576998539.264}, "inc.inc.count8": {"acc": 0.488, "reasoning_bytes": 179.1, "flops_per_problem": 9154121564.16}, "parity.inc.find16": {"acc": 0.88, "reasoning_bytes": 127.976, "flops_per_problem": 7330010038.272}, "parity.inc.find20": {"acc": 0.87, "reasoning_bytes": 147.916, "flops_per_problem": 8387273981.952}, "parity.inc.find24": {"acc": 0.848, "reasoning_bytes": 170.436, "flops_per_problem": 9558478651.392}, "sumd.inc.find6": {"acc": 0.982, "reasoning_bytes": 92.09, "flops_per_problem": 5215217172.48}, "sumd.inc.find7": {"acc": 0.946, "reasoning_bytes": 100.28, "flops_per_problem": 5621075804.16}, "sumd.inc.find8": {"acc": 0.782, "reasoning_bytes": 105.672, "flops_per_problem": 5903631138.816}, "count.inc.find16": {"acc": 0.908, "reasoning_bytes": 111.46, "flops_per_problem": 6644775813.12}, "count.inc.find18": {"acc": 0.87, "reasoning_bytes": 118.68, "flops_per_problem": 7051959336.96}, "count.inc.find20": {"acc": 0.866, "reasoning_bytes": 126.52, "flops_per_problem": 7486523965.44}, "sumd.inc.rev6": {"acc": 0.966, "reasoning_bytes": 87.492, "flops_per_problem": 4923652571.136}, "sumd.inc.rev7": {"acc": 0.9, "reasoning_bytes": 95.326, "flops_per_problem": 5313524170.752}, "sumd.inc.rev8": {"acc": 0.476, "reasoning_bytes": 100.6, "flops_per_problem": 5587246891.008}, "count.inc.rev16": {"acc": 0.824, "reasoning_bytes": 105.51, "flops_per_problem": 6249516318.72}, "count.inc.rev18": {"acc": 0.666, "reasoning_bytes": 112.7, "flops_per_problem": 6655374950.4}, "count.inc.rev20": {"acc": 0.522, "reasoning_bytes": 120.8, "flops_per_problem": 7101421977.6}, "parity.inc.rev16": {"acc": 0.768, "reasoning_bytes": 123.0, "flops_per_problem": 6977765376.0}, "parity.inc.rev20": {"acc": 0.43, "reasoning_bytes": 141.232, "flops_per_problem": 7959598792.704}, "parity.inc.rev24": {"acc": 0.502, "reasoning_bytes": 162.852, "flops_per_problem": 9091056697.344}, "count.inc.sumd16": {"acc": 0.838, "reasoning_bytes": 108.85, "flops_per_problem": 6441184051.2}, "count.inc.sumd18": {"acc": 0.696, "reasoning_bytes": 116.04, "flops_per_problem": 6847042682.88}, "count.inc.sumd20": {"acc": 0.546, "reasoning_bytes": 124.43, "flops_per_problem": 7305897000.96}, "sumd.inc.sumd6": {"acc": 0.98, "reasoning_bytes": 91.682, "flops_per_problem": 5119206653.952}, "sumd.inc.sumd7": {"acc": 0.848, "reasoning_bytes": 98.908, "flops_per_problem": 5483640324.096}, "sumd.inc.sumd8": {"acc": 0.454, "reasoning_bytes": 103.584, "flops_per_problem": 5735811465.216}, "add.inc.sumd6": {"acc": 0.11, "reasoning_bytes": 188.168, "flops_per_problem": 9682400231.424}, "add.inc.sumd7": {"acc": 0.026, "reasoning_bytes": 206.292, "flops_per_problem": 10589156425.728}, "add.inc.sumd8": {"acc": 0.024, "reasoning_bytes": 211.798, "flops_per_problem": 10926915600.384}, "parity.inc.inc16": {"acc": 0.77, "reasoning_bytes": 127.0, "flops_per_problem": 7154417664.0}, "parity.inc.inc20": {"acc": 0.422, "reasoning_bytes": 146.592, "flops_per_problem": 8196312858.624}, "parity.inc.inc24": {"acc": 0.302, "reasoning_bytes": 170.136, "flops_per_problem": 9412740513.792}, "sumd.inc.inc6": {"acc": 0.968, "reasoning_bytes": 94.44, "flops_per_problem": 5230144290.816}, "sumd.inc.inc7": {"acc": 0.866, "reasoning_bytes": 102.104, "flops_per_problem": 5612419842.048}, "sumd.inc.inc8": {"acc": 0.37, "reasoning_bytes": 107.66, "flops_per_problem": 5899126505.472}, "runmax.inc.inc12": {"acc": 0.954, "reasoning_bytes": 108.988, "flops_per_problem": 6223018475.52}, "runmax.inc.inc14": {"acc": 0.224, "reasoning_bytes": 102.716, "flops_per_problem": 6035590397.952}, "runmax.inc.inc16": {"acc": 0.142, "reasoning_bytes": 110.096, "flops_per_problem": 6449310056.448}, "count.inc.cmp16": {"acc": 0.94, "reasoning_bytes": 110.17, "flops_per_problem": 6543642378.24}, "count.inc.cmp18": {"acc": 0.912, "reasoning_bytes": 116.82, "flops_per_problem": 6925829603.328}, "count.inc.cmp20": {"acc": 0.848, "reasoning_bytes": 125.04, "flops_per_problem": 7377441177.6}, "inc.rev.sumd6": {"acc": 0.124, "reasoning_bytes": 167.278, "flops_per_problem": 8449278935.04}, "inc.rev.sumd7": {"acc": 0.044, "reasoning_bytes": 172.788, "flops_per_problem": 8734660706.304}, "inc.rev.sumd8": {"acc": 0.018, "reasoning_bytes": 191.822, "flops_per_problem": 9621985148.928}, "runmax.inc.find12": {"acc": 0.95, "reasoning_bytes": 105.942, "flops_per_problem": 6180268621.824}, "runmax.inc.find14": {"acc": 0.876, "reasoning_bytes": 117.214, "flops_per_problem": 6767107522.56}, "runmax.inc.find16": {"acc": 0.42, "reasoning_bytes": 116.048, "flops_per_problem": 6825579429.888}, "inc.runmax.cmp6": {"acc": 0.97, "reasoning_bytes": 107.96, "flops_per_problem": 5960248197.12}, "inc.runmax.cmp7": {"acc": 0.932, "reasoning_bytes": 120.588, "flops_per_problem": 6562102542.336}, "inc.runmax.cmp8": {"acc": 0.968, "reasoning_bytes": 136.154, "flops_per_problem": 7293707993.088}} +{"step": 3000, "train_loss": 1.1340147256851196} +{"step": 3020, "train_loss": 1.2453505992889404} +{"step": 3040, "train_loss": 1.237101435661316} +{"step": 3060, "train_loss": 1.1416198015213013} +{"step": 3080, "train_loss": 1.1083762645721436} +{"step": 3100, "train_loss": 1.1108977794647217} +{"step": 3120, "train_loss": 1.2929213047027588} +{"step": 3140, "train_loss": 1.1602153778076172} +{"step": 3160, "train_loss": 1.069389820098877} +{"step": 3180, "train_loss": 1.2384763956069946} +{"step": 3200, "train_loss": 1.1607578992843628} +{"step": 3220, "train_loss": 1.1593937873840332} +{"step": 3240, "train_loss": 1.1778044700622559} +{"step": 3260, "train_loss": 1.1228612661361694} +{"step": 3280, "train_loss": 1.1820759773254395} +{"step": 3300, "train_loss": 1.1382081508636475} +{"step": 3320, "train_loss": 1.0955851078033447} +{"step": 3340, "train_loss": 1.2009214162826538} +{"step": 3360, "train_loss": 1.1232683658599854} +{"step": 3380, "train_loss": 1.0809800624847412} +{"step": 3400, "train_loss": 1.11627197265625} +{"step": 3420, "train_loss": 1.1144723892211914} +{"step": 3440, "train_loss": 1.1484644412994385} +{"step": 3460, "train_loss": 1.1060869693756104} +{"step": 3480, "train_loss": 1.1731173992156982} +{"step": 3500, "train_loss": 1.0765117406845093} +{"step": 3520, "train_loss": 1.185636281967163} +{"step": 3540, "train_loss": 1.139094352722168} +{"step": 3560, "train_loss": 1.1447114944458008} +{"step": 3580, "train_loss": 1.1938077211380005} +{"step": 3600, "train_loss": 1.230565071105957} +{"step": 3620, "train_loss": 1.189070463180542} +{"step": 3640, "train_loss": 1.1836326122283936} +{"step": 3660, "train_loss": 1.1107375621795654} +{"step": 3680, "train_loss": 1.1273655891418457} +{"step": 3700, "train_loss": 1.0885387659072876} +{"step": 3720, "train_loss": 1.1544969081878662} +{"step": 3740, "train_loss": 1.0254735946655273} +{"step": 3760, "train_loss": 1.100522756576538} +{"step": 3780, "train_loss": 1.167896032333374} +{"step": 3800, "train_loss": 1.1713241338729858} +{"step": 3820, "train_loss": 1.173366665840149} +{"step": 3840, "train_loss": 1.1838226318359375} +{"step": 3860, "train_loss": 1.0932022333145142} +{"step": 3880, "train_loss": 1.0602320432662964} +{"step": 3900, "train_loss": 1.1008220911026} +{"step": 3920, "train_loss": 1.1308631896972656} +{"step": 3940, "train_loss": 1.0848803520202637} +{"step": 3960, "train_loss": 1.1547009944915771} +{"step": 3980, "train_loss": 1.0578866004943848} +{"step": 4000, "tokens": 131072000, "val_loss": 2.114429473876953, "val_bpb": 0.762217473771208, "lr": 0.0004789669757536829, "elapsed": 1326.3513300418854, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.294, "reasoning_bytes": 79.0, "flops_per_problem": 4930188705.792}, "add9": {"acc": 0.0, "reasoning_bytes": 88.632, "flops_per_problem": 5506605121.536}, "add10": {"acc": 0.0, "reasoning_bytes": 92.496, "flops_per_problem": 5818131431.424}, "reach14": {"acc": 0.486, "reasoning_bytes": 4.986, "flops_per_problem": 4504280039.424}, "reach16": {"acc": 0.49, "reasoning_bytes": 6.698, "flops_per_problem": 5110992322.56}, "reach18": {"acc": 0.494, "reasoning_bytes": 7.494, "flops_per_problem": 5681490886.656}, "parity24": {"acc": 0.024, "reasoning_bytes": 147.116, "flops_per_problem": 8167606861.824}, "parity28": {"acc": 0.002, "reasoning_bytes": 171.012, "flops_per_problem": 9406469357.568}, "parity32": {"acc": 0.002, "reasoning_bytes": 195.012, "flops_per_problem": 10643035373.568}, "cmp8": {"acc": 0.894, "reasoning_bytes": 6.16, "flops_per_problem": 1376386301.952}, "cmp9": {"acc": 0.92, "reasoning_bytes": 6.068, "flops_per_problem": 1461179400.192}, "cmp10": {"acc": 0.89, "reasoning_bytes": 6.424, "flops_per_problem": 1564697640.96}, "runmax12": {"acc": 1.0, "reasoning_bytes": 76.304, "flops_per_problem": 4385569701.888}, "runmax14": {"acc": 0.994, "reasoning_bytes": 85.564, "flops_per_problem": 4883110871.04}, "runmax16": {"acc": 0.97, "reasoning_bytes": 95.916, "flops_per_problem": 5428613136.384}, "count16": {"acc": 0.768, "reasoning_bytes": 81.59, "flops_per_problem": 4839831060.48}, "count18": {"acc": 0.604, "reasoning_bytes": 90.33, "flops_per_problem": 5314142453.76}, "count20": {"acc": 0.418, "reasoning_bytes": 100.224, "flops_per_problem": 5847102406.656}, "brackets16": {"acc": 0.836, "reasoning_bytes": 53.952, "flops_per_problem": 3663503474.688}, "brackets18": {"acc": 0.826, "reasoning_bytes": 63.954, "flops_per_problem": 4193460338.688}, "brackets20": {"acc": 0.844, "reasoning_bytes": 68.638, "flops_per_problem": 4488646311.936}, "sumd8": {"acc": 0.698, "reasoning_bytes": 58.84, "flops_per_problem": 3392077234.176}, "sumd9": {"acc": 0.392, "reasoning_bytes": 66.392, "flops_per_problem": 3771261370.368}, "sumd10": {"acc": 0.11, "reasoning_bytes": 73.14, "flops_per_problem": 4116263288.832}, "inc8": {"acc": 0.678, "reasoning_bytes": 63.0, "flops_per_problem": 3797847539.712}, "inc9": {"acc": 0.072, "reasoning_bytes": 71.0, "flops_per_problem": 4239301607.424}, "inc10": {"acc": 0.0, "reasoning_bytes": 78.14, "flops_per_problem": 4640037322.752}, "add.cmp6": {"acc": 0.782, "reasoning_bytes": 92.65, "flops_per_problem": 5533279617.024}, "add.cmp7": {"acc": 0.788, "reasoning_bytes": 105.328, "flops_per_problem": 6222930149.376}, "add.cmp8": {"acc": 0.824, "reasoning_bytes": 118.806, "flops_per_problem": 6952150794.24}, "add.runmax6": {"acc": 0.798, "reasoning_bytes": 122.498, "flops_per_problem": 6646454009.856}, "add.runmax7": {"acc": 0.832, "reasoning_bytes": 141.598, "flops_per_problem": 7577853198.336}, "add.runmax8": {"acc": 0.6, "reasoning_bytes": 158.492, "flops_per_problem": 8411916976.128}, "add.count6": {"acc": 0.76, "reasoning_bytes": 116.486, "flops_per_problem": 6425108692.992}, "add.count7": {"acc": 0.65, "reasoning_bytes": 133.226, "flops_per_problem": 7252724662.272}, "add.count8": {"acc": 0.384, "reasoning_bytes": 150.262, "flops_per_problem": 8093412900.864}, "add.find6": {"acc": 0.52, "reasoning_bytes": 111.766, "flops_per_problem": 6175145705.472}, "add.find7": {"acc": 0.34, "reasoning_bytes": 126.392, "flops_per_problem": 6927154495.488}, "add.find8": {"acc": 0.316, "reasoning_bytes": 146.352, "flops_per_problem": 7895209033.728}, "add.rev6": {"acc": 0.57, "reasoning_bytes": 125.324, "flops_per_problem": 6865502846.976}, "add.rev7": {"acc": 0.206, "reasoning_bytes": 146.502, "flops_per_problem": 7951119482.88}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 166.348, "flops_per_problem": 8944700276.736}, "add.sumd6": {"acc": 0.294, "reasoning_bytes": 128.728, "flops_per_problem": 6875748679.68}, "add.sumd7": {"acc": 0.236, "reasoning_bytes": 148.548, "flops_per_problem": 7839651889.152}, "add.sumd8": {"acc": 0.056, "reasoning_bytes": 166.89, "flops_per_problem": 8739606970.368}, "add.inc6": {"acc": 0.426, "reasoning_bytes": 130.798, "flops_per_problem": 7127654842.368}, "add.inc7": {"acc": 0.074, "reasoning_bytes": 149.558, "flops_per_problem": 8088996593.664}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 163.902, "flops_per_problem": 8838355599.36}, "runmax.cmp12": {"acc": 0.99, "reasoning_bytes": 92.868, "flops_per_problem": 5382065258.496}, "runmax.cmp14": {"acc": 0.96, "reasoning_bytes": 100.416, "flops_per_problem": 5803734269.952}, "runmax.cmp16": {"acc": 0.954, "reasoning_bytes": 110.596, "flops_per_problem": 6341640486.912}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 93.184, "flops_per_problem": 5440183861.248}, "runmax.runmax14": {"acc": 0.998, "reasoning_bytes": 101.296, "flops_per_problem": 5886760845.312}, "runmax.runmax16": {"acc": 0.996, "reasoning_bytes": 111.796, "flops_per_problem": 6438799245.312}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 93.736, "flops_per_problem": 5508724948.992}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 101.308, "flops_per_problem": 5931453874.176}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 111.9, "flops_per_problem": 6487555276.8}, "runmax.find12": {"acc": 0.934, "reasoning_bytes": 93.952, "flops_per_problem": 5474101100.544}, "runmax.find14": {"acc": 0.936, "reasoning_bytes": 102.544, "flops_per_problem": 5941876359.168}, "runmax.find16": {"acc": 0.916, "reasoning_bytes": 112.316, "flops_per_problem": 6461764042.752}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 88.844, "flops_per_problem": 5116026912.768}, "runmax.rev14": {"acc": 0.998, "reasoning_bytes": 96.624, "flops_per_problem": 5547941756.928}, "runmax.rev16": {"acc": 0.994, "reasoning_bytes": 106.62, "flops_per_problem": 6077721968.64}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 91.592, "flops_per_problem": 5281550106.624}, "runmax.sumd14": {"acc": 0.998, "reasoning_bytes": 99.64, "flops_per_problem": 5725300654.08}, "runmax.sumd16": {"acc": 0.996, "reasoning_bytes": 109.904, "flops_per_problem": 6266916569.088}, "runmax.inc12": {"acc": 0.998, "reasoning_bytes": 92.58, "flops_per_problem": 5312199278.592}, "runmax.inc14": {"acc": 0.992, "reasoning_bytes": 100.476, "flops_per_problem": 5752681758.72}, "runmax.inc16": {"acc": 0.992, "reasoning_bytes": 110.788, "flops_per_problem": 6298890633.216}, "count.cmp16": {"acc": 0.946, "reasoning_bytes": 96.302, "flops_per_problem": 5759659524.096}, "count.cmp18": {"acc": 0.892, "reasoning_bytes": 104.934, "flops_per_problem": 6243068510.208}, "count.cmp20": {"acc": 0.8, "reasoning_bytes": 113.96, "flops_per_problem": 6728244019.2}, "count.runmax16": {"acc": 0.814, "reasoning_bytes": 99.23, "flops_per_problem": 5928009154.56}, "count.runmax18": {"acc": 0.76, "reasoning_bytes": 107.11, "flops_per_problem": 6364340305.92}, "count.runmax20": {"acc": 0.594, "reasoning_bytes": 116.15, "flops_per_problem": 6851900620.8}, "count.count16": {"acc": 0.994, "reasoning_bytes": 99.248, "flops_per_problem": 5972967161.856}, "count.count18": {"acc": 0.998, "reasoning_bytes": 107.046, "flops_per_problem": 6405676941.312}, "count.count20": {"acc": 0.984, "reasoning_bytes": 115.86, "flops_per_problem": 6883256401.92}, "count.find16": {"acc": 0.92, "reasoning_bytes": 99.35, "flops_per_problem": 5933308723.2}, "count.find18": {"acc": 0.91, "reasoning_bytes": 107.12, "flops_per_problem": 6364781936.64}, "count.find20": {"acc": 0.872, "reasoning_bytes": 115.91, "flops_per_problem": 6841301483.52}, "count.rev16": {"acc": 0.816, "reasoning_bytes": 93.59, "flops_per_problem": 5546440212.48}, "count.rev18": {"acc": 0.746, "reasoning_bytes": 101.51, "flops_per_problem": 5984537886.72}, "count.rev20": {"acc": 0.604, "reasoning_bytes": 110.19, "flops_per_problem": 6456199495.68}, "count.sumd16": {"acc": 0.836, "reasoning_bytes": 96.72, "flops_per_problem": 5728833699.84}, "count.sumd18": {"acc": 0.76, "reasoning_bytes": 104.73, "flops_per_problem": 6170906050.56}, "count.sumd20": {"acc": 0.604, "reasoning_bytes": 113.76, "flops_per_problem": 6658024734.72}, "count.inc16": {"acc": 0.82, "reasoning_bytes": 97.94, "flops_per_problem": 5738549575.68}, "count.inc18": {"acc": 0.734, "reasoning_bytes": 106.02, "flops_per_problem": 6183713341.44}, "count.inc20": {"acc": 0.572, "reasoning_bytes": 115.102, "flops_per_problem": 6673305157.632}, "parity.cmp16": {"acc": 0.974, "reasoning_bytes": 113.244, "flops_per_problem": 6458584301.568}, "parity.cmp20": {"acc": 0.96, "reasoning_bytes": 135.528, "flops_per_problem": 7619366486.016}, "parity.cmp24": {"acc": 0.942, "reasoning_bytes": 159.308, "flops_per_problem": 8846481604.608}, "parity.runmax16": {"acc": 0.828, "reasoning_bytes": 114.544, "flops_per_problem": 6560159367.168}, "parity.runmax20": {"acc": 0.534, "reasoning_bytes": 138.064, "flops_per_problem": 7775527108.608}, "parity.runmax24": {"acc": 0.492, "reasoning_bytes": 163.384, "flops_per_problem": 9070388379.648}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 113.728, "flops_per_problem": 6568285372.416}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 136.852, "flops_per_problem": 7766164537.344}, "parity.count24": {"acc": 0.994, "reasoning_bytes": 160.67, "flops_per_problem": 8994692874.24}, "parity.find16": {"acc": 0.942, "reasoning_bytes": 115.0, "flops_per_problem": 6580297728.0}, "parity.find20": {"acc": 0.854, "reasoning_bytes": 137.692, "flops_per_problem": 7759098445.824}, "parity.find24": {"acc": 0.836, "reasoning_bytes": 161.816, "flops_per_problem": 9000964030.464}, "parity.rev16": {"acc": 0.726, "reasoning_bytes": 111.14, "flops_per_problem": 6277339054.08}, "parity.rev20": {"acc": 0.486, "reasoning_bytes": 134.6, "flops_per_problem": 7490057011.2}, "parity.rev24": {"acc": 0.518, "reasoning_bytes": 159.272, "flops_per_problem": 8758155460.608}, "parity.sumd16": {"acc": 0.658, "reasoning_bytes": 114.932, "flops_per_problem": 6488968495.104}, "parity.sumd20": {"acc": 0.452, "reasoning_bytes": 139.502, "flops_per_problem": 7751590723.584}, "parity.sumd24": {"acc": 0.46, "reasoning_bytes": 162.922, "flops_per_problem": 8999904116.736}, "parity.inc16": {"acc": 0.688, "reasoning_bytes": 115.32, "flops_per_problem": 6461940695.04}, "parity.inc20": {"acc": 0.426, "reasoning_bytes": 140.124, "flops_per_problem": 7734013820.928}, "parity.inc24": {"acc": 0.438, "reasoning_bytes": 164.876, "flops_per_problem": 8997254332.416}, "sumd.cmp6": {"acc": 0.98, "reasoning_bytes": 63.524, "flops_per_problem": 3776472612.864}, "sumd.cmp7": {"acc": 0.96, "reasoning_bytes": 69.966, "flops_per_problem": 4105664151.552}, "sumd.cmp8": {"acc": 0.926, "reasoning_bytes": 77.566, "flops_per_problem": 4485378244.608}, "sumd.runmax6": {"acc": 0.728, "reasoning_bytes": 69.556, "flops_per_problem": 4035621519.36}, "sumd.runmax7": {"acc": 0.88, "reasoning_bytes": 75.88, "flops_per_problem": 4364724731.904}, "sumd.runmax8": {"acc": 0.804, "reasoning_bytes": 83.552, "flops_per_problem": 4749826719.744}, "sumd.count6": {"acc": 0.786, "reasoning_bytes": 68.36, "flops_per_problem": 4027318861.824}, "sumd.count7": {"acc": 0.91, "reasoning_bytes": 74.796, "flops_per_problem": 4361633316.864}, "sumd.count8": {"acc": 0.804, "reasoning_bytes": 82.564, "flops_per_problem": 4750268350.464}, "sumd.find6": {"acc": 0.762, "reasoning_bytes": 68.77, "flops_per_problem": 4001262649.344}, "sumd.find7": {"acc": 0.878, "reasoning_bytes": 75.21, "flops_per_problem": 4335753756.672}, "sumd.find8": {"acc": 0.822, "reasoning_bytes": 82.888, "flops_per_problem": 4720325787.648}, "sumd.rev6": {"acc": 0.818, "reasoning_bytes": 62.964, "flops_per_problem": 3658380558.336}, "sumd.rev7": {"acc": 0.902, "reasoning_bytes": 69.8, "flops_per_problem": 4008417067.008}, "sumd.rev8": {"acc": 0.794, "reasoning_bytes": 77.548, "flops_per_problem": 4396257165.312}, "sumd.sumd6": {"acc": 0.694, "reasoning_bytes": 68.56, "flops_per_problem": 3918412726.272}, "sumd.sumd7": {"acc": 0.796, "reasoning_bytes": 74.672, "flops_per_problem": 4236210192.384}, "sumd.sumd8": {"acc": 0.598, "reasoning_bytes": 81.858, "flops_per_problem": 4597375795.2}, "sumd.inc6": {"acc": 0.716, "reasoning_bytes": 70.94, "flops_per_problem": 4007445479.424}, "sumd.inc7": {"acc": 0.856, "reasoning_bytes": 77.136, "flops_per_problem": 4330807492.608}, "sumd.inc8": {"acc": 0.756, "reasoning_bytes": 84.554, "flops_per_problem": 4705663647.744}, "inc.cmp6": {"acc": 0.916, "reasoning_bytes": 84.124, "flops_per_problem": 4819162742.784}, "inc.cmp7": {"acc": 0.928, "reasoning_bytes": 92.946, "flops_per_problem": 5297007181.824}, "inc.cmp8": {"acc": 0.812, "reasoning_bytes": 101.586, "flops_per_problem": 5767078920.192}, "inc.runmax6": {"acc": 0.998, "reasoning_bytes": 104.072, "flops_per_problem": 5523563741.184}, "inc.runmax7": {"acc": 0.986, "reasoning_bytes": 120.018, "flops_per_problem": 6271951159.296}, "inc.runmax8": {"acc": 0.888, "reasoning_bytes": 135.406, "flops_per_problem": 6995607257.088}, "inc.count6": {"acc": 0.946, "reasoning_bytes": 99.022, "flops_per_problem": 5344703299.584}, "inc.count7": {"acc": 0.846, "reasoning_bytes": 113.988, "flops_per_problem": 6049810907.136}, "inc.count8": {"acc": 0.56, "reasoning_bytes": 128.5, "flops_per_problem": 6734868480.0}, "inc.find6": {"acc": 0.64, "reasoning_bytes": 93.538, "flops_per_problem": 5058703245.312}, "inc.find7": {"acc": 0.586, "reasoning_bytes": 106.294, "flops_per_problem": 5666387116.032}, "inc.find8": {"acc": 0.424, "reasoning_bytes": 124.288, "flops_per_problem": 6516172947.456}, "inc.rev6": {"acc": 0.896, "reasoning_bytes": 104.154, "flops_per_problem": 5615334604.8}, "inc.rev7": {"acc": 0.69, "reasoning_bytes": 123.698, "flops_per_problem": 6567402110.976}, "inc.rev8": {"acc": 0.006, "reasoning_bytes": 142.616, "flops_per_problem": 7471685173.248}, "inc.sumd6": {"acc": 0.664, "reasoning_bytes": 110.408, "flops_per_problem": 5755773173.76}, "inc.sumd7": {"acc": 0.266, "reasoning_bytes": 127.418, "flops_per_problem": 6553534906.368}, "inc.sumd8": {"acc": 0.068, "reasoning_bytes": 142.974, "flops_per_problem": 7286553575.424}, "inc.inc6": {"acc": 0.596, "reasoning_bytes": 112.76, "flops_per_problem": 5996815220.736}, "inc.inc7": {"acc": 0.08, "reasoning_bytes": 129.936, "flops_per_problem": 6847484313.6}, "inc.inc8": {"acc": 0.002, "reasoning_bytes": 142.3, "flops_per_problem": 7473981652.992}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 109.904, "flops_per_problem": 6443568857.088}, "runmax.runmax.cmp14": {"acc": 0.996, "reasoning_bytes": 117.916, "flops_per_problem": 6885729533.952}, "runmax.runmax.cmp16": {"acc": 0.786, "reasoning_bytes": 124.648, "flops_per_problem": 7271361478.656}, "sumd.runmax.cmp6": {"acc": 0.844, "reasoning_bytes": 84.484, "flops_per_problem": 4963575988.224}, "sumd.runmax.cmp7": {"acc": 0.922, "reasoning_bytes": 91.624, "flops_per_problem": 5326596440.064}, "sumd.runmax.cmp8": {"acc": 0.842, "reasoning_bytes": 99.554, "flops_per_problem": 5721502629.888}, "add.runmax.cmp6": {"acc": 0.974, "reasoning_bytes": 139.47, "flops_per_problem": 7660968099.84}, "add.runmax.cmp7": {"acc": 0.948, "reasoning_bytes": 157.664, "flops_per_problem": 8554122067.968}, "add.runmax.cmp8": {"acc": 0.864, "reasoning_bytes": 166.77, "flops_per_problem": 9043183927.296}, "count.runmax.runmax16": {"acc": 0.77, "reasoning_bytes": 116.47, "flops_per_problem": 6998522019.84}, "count.runmax.runmax18": {"acc": 0.692, "reasoning_bytes": 124.3, "flops_per_problem": 7432645017.6}, "count.runmax.runmax20": {"acc": 0.576, "reasoning_bytes": 133.13, "flops_per_problem": 7910931087.36}, "add.runmax.runmax6": {"acc": 0.828, "reasoning_bytes": 140.668, "flops_per_problem": 7758921793.536}, "add.runmax.runmax7": {"acc": 0.81, "reasoning_bytes": 160.216, "flops_per_problem": 8705071448.064}, "add.runmax.runmax8": {"acc": 0.61, "reasoning_bytes": 176.692, "flops_per_problem": 9522618236.928}, "parity.runmax.runmax16": {"acc": 0.868, "reasoning_bytes": 130.62, "flops_per_problem": 7579266416.64}, "parity.runmax.runmax20": {"acc": 0.568, "reasoning_bytes": 153.12, "flops_per_problem": 8749587824.64}, "parity.runmax.runmax24": {"acc": 0.508, "reasoning_bytes": 175.8, "flops_per_problem": 9927858585.6}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 130.92, "flops_per_problem": 7636678410.24}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 153.168, "flops_per_problem": 8795870724.096}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 175.82, "flops_per_problem": 9972904919.04}, "inc.runmax.count6": {"acc": 0.994, "reasoning_bytes": 121.52, "flops_per_problem": 6647425597.44}, "inc.runmax.count7": {"acc": 0.99, "reasoning_bytes": 138.084, "flops_per_problem": 7423105794.048}, "inc.runmax.count8": {"acc": 0.974, "reasoning_bytes": 153.176, "flops_per_problem": 8133777948.672}, "sumd.runmax.count6": {"acc": 0.738, "reasoning_bytes": 87.532, "flops_per_problem": 5181918216.192}, "sumd.runmax.count7": {"acc": 0.892, "reasoning_bytes": 93.124, "flops_per_problem": 5479312343.04}, "sumd.runmax.count8": {"acc": 0.89, "reasoning_bytes": 100.612, "flops_per_problem": 5856464977.92}, "runmax.runmax.find12": {"acc": 1.0, "reasoning_bytes": 110.896, "flops_per_problem": 6531541696.512}, "runmax.runmax.find14": {"acc": 0.986, "reasoning_bytes": 118.928, "flops_per_problem": 6974585634.816}, "runmax.runmax.find16": {"acc": 0.928, "reasoning_bytes": 127.462, "flops_per_problem": 7439799435.264}, "add.runmax.find6": {"acc": 0.964, "reasoning_bytes": 141.066, "flops_per_problem": 7776587022.336}, "add.runmax.find7": {"acc": 0.978, "reasoning_bytes": 159.526, "flops_per_problem": 8678926909.44}, "add.runmax.find8": {"acc": 0.892, "reasoning_bytes": 175.968, "flops_per_problem": 9493470609.408}, "parity.runmax.find16": {"acc": 0.97, "reasoning_bytes": 131.568, "flops_per_problem": 7621133008.896}, "parity.runmax.find20": {"acc": 0.874, "reasoning_bytes": 153.444, "flops_per_problem": 8763896659.968}, "parity.runmax.find24": {"acc": 0.798, "reasoning_bytes": 176.324, "flops_per_problem": 9951000035.328}, "add.runmax.rev6": {"acc": 0.866, "reasoning_bytes": 134.872, "flops_per_problem": 7369403498.496}, "add.runmax.rev7": {"acc": 0.92, "reasoning_bytes": 153.74, "flops_per_problem": 8293824921.6}, "add.runmax.rev8": {"acc": 0.582, "reasoning_bytes": 169.15, "flops_per_problem": 9073568120.832}, "parity.runmax.rev16": {"acc": 0.87, "reasoning_bytes": 126.664, "flops_per_problem": 7272068087.808}, "parity.runmax.rev20": {"acc": 0.61, "reasoning_bytes": 148.336, "flops_per_problem": 8405822472.192}, "parity.runmax.rev24": {"acc": 0.494, "reasoning_bytes": 171.472, "flops_per_problem": 9604231593.984}, "sumd.runmax.rev6": {"acc": 0.784, "reasoning_bytes": 81.62, "flops_per_problem": 4746205347.84}, "sumd.runmax.rev7": {"acc": 0.898, "reasoning_bytes": 87.98, "flops_per_problem": 5075750191.104}, "sumd.runmax.rev8": {"acc": 0.808, "reasoning_bytes": 95.76, "flops_per_problem": 5465886769.152}, "sumd.runmax.sumd6": {"acc": 0.728, "reasoning_bytes": 84.948, "flops_per_problem": 4936106557.44}, "sumd.runmax.sumd7": {"acc": 0.862, "reasoning_bytes": 91.128, "flops_per_problem": 5258232004.608}, "sumd.runmax.sumd8": {"acc": 0.796, "reasoning_bytes": 98.598, "flops_per_problem": 5634854682.624}, "add.runmax.sumd6": {"acc": 0.786, "reasoning_bytes": 138.704, "flops_per_problem": 7583771049.984}, "add.runmax.sumd7": {"acc": 0.908, "reasoning_bytes": 157.952, "flops_per_problem": 8520999763.968}, "add.runmax.sumd8": {"acc": 0.634, "reasoning_bytes": 174.298, "flops_per_problem": 9331303809.024}, "parity.runmax.sumd16": {"acc": 0.804, "reasoning_bytes": 130.324, "flops_per_problem": 7477868003.328}, "parity.runmax.sumd20": {"acc": 0.568, "reasoning_bytes": 152.2, "flops_per_problem": 8620631654.4}, "parity.runmax.sumd24": {"acc": 0.488, "reasoning_bytes": 175.48, "flops_per_problem": 9825400258.56}, "count.runmax.inc16": {"acc": 0.714, "reasoning_bytes": 115.98, "flops_per_problem": 6844392898.56}, "count.runmax.inc18": {"acc": 0.642, "reasoning_bytes": 123.49, "flops_per_problem": 7264383713.28}, "count.runmax.inc20": {"acc": 0.542, "reasoning_bytes": 132.09, "flops_per_problem": 7732512276.48}, "runmax.runmax.inc12": {"acc": 0.974, "reasoning_bytes": 109.568, "flops_per_problem": 6371583049.728}, "runmax.runmax.inc14": {"acc": 0.796, "reasoning_bytes": 114.746, "flops_per_problem": 6688320602.112}, "runmax.runmax.inc16": {"acc": 0.45, "reasoning_bytes": 119.278, "flops_per_problem": 6965223063.552}, "add.runmax.inc6": {"acc": 0.84, "reasoning_bytes": 138.826, "flops_per_problem": 7565045907.456}, "add.runmax.inc7": {"acc": 0.858, "reasoning_bytes": 157.716, "flops_per_problem": 8490350592.0}, "add.runmax.inc8": {"acc": 0.608, "reasoning_bytes": 174.0, "flops_per_problem": 9300301332.48}, "count.count.cmp16": {"acc": 0.974, "reasoning_bytes": 116.07, "flops_per_problem": 6980856791.04}, "count.count.cmp18": {"acc": 0.938, "reasoning_bytes": 123.35, "flops_per_problem": 7390601773.056}, "count.count.cmp20": {"acc": 0.85, "reasoning_bytes": 131.82, "flops_per_problem": 7854049050.624}, "add.count.cmp6": {"acc": 0.902, "reasoning_bytes": 131.706, "flops_per_problem": 7362249080.832}, "add.count.cmp7": {"acc": 0.86, "reasoning_bytes": 148.578, "flops_per_problem": 8195694575.616}, "add.count.cmp8": {"acc": 0.832, "reasoning_bytes": 157.786, "flops_per_problem": 8690674286.592}, "sumd.count.cmp6": {"acc": 0.948, "reasoning_bytes": 83.122, "flops_per_problem": 4949355479.04}, "sumd.count.cmp7": {"acc": 0.984, "reasoning_bytes": 90.54, "flops_per_problem": 5323416698.88}, "sumd.count.cmp8": {"acc": 0.964, "reasoning_bytes": 98.494, "flops_per_problem": 5718852845.568}, "add.count.runmax6": {"acc": 0.742, "reasoning_bytes": 133.754, "flops_per_problem": 7496858124.288}, "add.count.runmax7": {"acc": 0.704, "reasoning_bytes": 150.242, "flops_per_problem": 8313344999.424}, "add.count.runmax8": {"acc": 0.45, "reasoning_bytes": 166.972, "flops_per_problem": 9140166033.408}, "sumd.count.runmax6": {"acc": 0.774, "reasoning_bytes": 85.544, "flops_per_problem": 5099156619.264}, "sumd.count.runmax7": {"acc": 0.942, "reasoning_bytes": 91.672, "flops_per_problem": 5416865759.232}, "sumd.count.runmax8": {"acc": 0.862, "reasoning_bytes": 99.628, "flops_per_problem": 5813096841.216}, "inc.count.runmax6": {"acc": 0.918, "reasoning_bytes": 116.16, "flops_per_problem": 6410711531.52}, "inc.count.runmax7": {"acc": 0.726, "reasoning_bytes": 131.238, "flops_per_problem": 7120765403.136}, "inc.count.runmax8": {"acc": 0.574, "reasoning_bytes": 144.928, "flops_per_problem": 7769520930.816}, "parity.count.count16": {"acc": 1.0, "reasoning_bytes": 130.14, "flops_per_problem": 7646394286.08}, "parity.count.count20": {"acc": 1.0, "reasoning_bytes": 152.736, "flops_per_problem": 8820955348.992}, "parity.count.count24": {"acc": 1.0, "reasoning_bytes": 173.494, "flops_per_problem": 9914344685.568}, "runmax.count.count12": {"acc": 1.0, "reasoning_bytes": 110.88, "flops_per_problem": 6619161231.36}, "runmax.count.count14": {"acc": 1.0, "reasoning_bytes": 119.22, "flops_per_problem": 7075807395.84}, "runmax.count.count16": {"acc": 1.0, "reasoning_bytes": 129.16, "flops_per_problem": 7603114475.52}, "inc.count.count6": {"acc": 0.968, "reasoning_bytes": 116.156, "flops_per_problem": 6454697951.232}, "inc.count.count7": {"acc": 0.932, "reasoning_bytes": 131.112, "flops_per_problem": 7159363928.064}, "inc.count.count8": {"acc": 0.814, "reasoning_bytes": 145.032, "flops_per_problem": 7818276962.304}, "inc.count.find6": {"acc": 0.908, "reasoning_bytes": 116.0, "flops_per_problem": 6405411962.88}, "inc.count.find7": {"acc": 0.86, "reasoning_bytes": 130.796, "flops_per_problem": 7101245325.312}, "inc.count.find8": {"acc": 0.8, "reasoning_bytes": 144.656, "flops_per_problem": 7757420249.088}, "add.count.find6": {"acc": 0.864, "reasoning_bytes": 133.008, "flops_per_problem": 7463912472.576}, "add.count.find7": {"acc": 0.778, "reasoning_bytes": 150.0, "flops_per_problem": 8302657536.0}, "add.count.find8": {"acc": 0.678, "reasoning_bytes": 165.892, "flops_per_problem": 9100330942.464}, "runmax.count.find12": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6580297728.0}, "runmax.count.find14": {"acc": 1.0, "reasoning_bytes": 120.42, "flops_per_problem": 7084640010.24}, "runmax.count.find16": {"acc": 1.0, "reasoning_bytes": 129.312, "flops_per_problem": 7565664190.464}, "parity.count.rev16": {"acc": 1.0, "reasoning_bytes": 125.896, "flops_per_problem": 7282313920.512}, "parity.count.rev20": {"acc": 1.0, "reasoning_bytes": 148.036, "flops_per_problem": 8436736622.592}, "parity.count.rev24": {"acc": 1.0, "reasoning_bytes": 170.252, "flops_per_problem": 9594515718.144}, "inc.count.rev6": {"acc": 0.942, "reasoning_bytes": 111.032, "flops_per_problem": 6051754082.304}, "inc.count.rev7": {"acc": 0.806, "reasoning_bytes": 126.008, "flops_per_problem": 6757303320.576}, "inc.count.rev8": {"acc": 0.568, "reasoning_bytes": 139.71, "flops_per_problem": 7406588805.12}, "runmax.count.rev12": {"acc": 1.0, "reasoning_bytes": 105.844, "flops_per_problem": 6220103712.768}, "runmax.count.rev14": {"acc": 1.0, "reasoning_bytes": 113.74, "flops_per_problem": 6657141473.28}, "runmax.count.rev16": {"acc": 1.0, "reasoning_bytes": 124.012, "flops_per_problem": 7199110692.864}, "count.count.sumd16": {"acc": 0.976, "reasoning_bytes": 115.2, "flops_per_problem": 6898271846.4}, "count.count.sumd18": {"acc": 0.872, "reasoning_bytes": 122.83, "flops_per_problem": 7323562229.76}, "count.count.sumd20": {"acc": 0.652, "reasoning_bytes": 131.088, "flops_per_problem": 7776587022.336}, "runmax.count.sumd12": {"acc": 1.0, "reasoning_bytes": 108.856, "flops_per_problem": 6397285957.632}, "runmax.count.sumd14": {"acc": 1.0, "reasoning_bytes": 117.076, "flops_per_problem": 6848632553.472}, "runmax.count.sumd16": {"acc": 1.0, "reasoning_bytes": 127.144, "flops_per_problem": 7381592506.368}, "sumd.count.sumd6": {"acc": 0.7, "reasoning_bytes": 84.204, "flops_per_problem": 4950150414.336}, "sumd.count.sumd7": {"acc": 0.918, "reasoning_bytes": 90.062, "flops_per_problem": 5256200503.296}, "sumd.count.sumd8": {"acc": 0.854, "reasoning_bytes": 97.61, "flops_per_problem": 5635649617.92}, "parity.count.inc16": {"acc": 1.0, "reasoning_bytes": 130.1, "flops_per_problem": 7467975475.2}, "parity.count.inc20": {"acc": 1.0, "reasoning_bytes": 152.348, "flops_per_problem": 8627167789.056}, "parity.count.inc24": {"acc": 1.0, "reasoning_bytes": 175.212, "flops_per_problem": 9813564555.264}, "count.count.inc16": {"acc": 0.982, "reasoning_bytes": 115.948, "flops_per_problem": 6887142752.256}, "count.count.inc18": {"acc": 0.92, "reasoning_bytes": 123.58, "flops_per_problem": 7312521461.76}, "count.count.inc20": {"acc": 0.742, "reasoning_bytes": 132.016, "flops_per_problem": 7773407281.152}, "add.count.inc6": {"acc": 0.768, "reasoning_bytes": 132.4, "flops_per_problem": 7304572108.8}, "add.count.inc7": {"acc": 0.676, "reasoning_bytes": 148.724, "flops_per_problem": 8113816240.128}, "add.count.inc8": {"acc": 0.364, "reasoning_bytes": 164.022, "flops_per_problem": 8876689145.856}, "parity.rev.cmp16": {"acc": 0.982, "reasoning_bytes": 124.92, "flops_per_problem": 7150884618.24}, "parity.rev.cmp20": {"acc": 0.946, "reasoning_bytes": 146.784, "flops_per_problem": 8293118312.448}, "parity.rev.cmp24": {"acc": 0.956, "reasoning_bytes": 168.156, "flops_per_problem": 9413623775.232}, "sumd.rev.cmp6": {"acc": 0.9, "reasoning_bytes": 82.148, "flops_per_problem": 4776589541.376}, "sumd.rev.cmp7": {"acc": 0.93, "reasoning_bytes": 89.094, "flops_per_problem": 5126979354.624}, "sumd.rev.cmp8": {"acc": 0.898, "reasoning_bytes": 96.926, "flops_per_problem": 5517027606.528}, "add.rev.cmp6": {"acc": 0.938, "reasoning_bytes": 156.692, "flops_per_problem": 8540608167.936}, "add.rev.cmp7": {"acc": 0.908, "reasoning_bytes": 180.962, "flops_per_problem": 9748291534.848}, "add.rev.cmp8": {"acc": 0.774, "reasoning_bytes": 203.876, "flops_per_problem": 10885755617.28}, "runmax.rev.runmax12": {"acc": 1.0, "reasoning_bytes": 105.868, "flops_per_problem": 6177000554.496}, "runmax.rev.runmax14": {"acc": 1.0, "reasoning_bytes": 114.094, "flops_per_problem": 6628612128.768}, "runmax.rev.runmax16": {"acc": 1.0, "reasoning_bytes": 123.326, "flops_per_problem": 7124651753.472}, "count.rev.runmax16": {"acc": 0.772, "reasoning_bytes": 111.48, "flops_per_problem": 6645659074.56}, "count.rev.runmax18": {"acc": 0.722, "reasoning_bytes": 118.97, "flops_per_problem": 7064766627.84}, "count.rev.runmax20": {"acc": 0.604, "reasoning_bytes": 127.81, "flops_per_problem": 7543494328.32}, "add.rev.runmax6": {"acc": 0.614, "reasoning_bytes": 188.88, "flops_per_problem": 9776202596.352}, "add.rev.runmax7": {"acc": 0.734, "reasoning_bytes": 218.144, "flops_per_problem": 11142431391.744}, "add.rev.runmax8": {"acc": 0.484, "reasoning_bytes": 248.7, "flops_per_problem": 12582942474.24}, "inc.rev.count6": {"acc": 0.64, "reasoning_bytes": 156.464, "flops_per_problem": 8064530251.776}, "inc.rev.count7": {"acc": 0.544, "reasoning_bytes": 183.204, "flops_per_problem": 9284667604.992}, "inc.rev.count8": {"acc": 0.426, "reasoning_bytes": 208.166, "flops_per_problem": 10432554172.416}, "count.rev.count16": {"acc": 1.0, "reasoning_bytes": 112.13, "flops_per_problem": 6718528143.36}, "count.rev.count18": {"acc": 1.0, "reasoning_bytes": 119.53, "flops_per_problem": 7133661020.16}, "count.rev.count20": {"acc": 0.996, "reasoning_bytes": 127.97, "flops_per_problem": 7594723491.84}, "parity.rev.count16": {"acc": 1.0, "reasoning_bytes": 126.1, "flops_per_problem": 7291323187.2}, "parity.rev.count20": {"acc": 1.0, "reasoning_bytes": 148.072, "flops_per_problem": 8438326493.184}, "parity.rev.count24": {"acc": 1.0, "reasoning_bytes": 170.432, "flops_per_problem": 9602465071.104}, "sumd.rev.find6": {"acc": 0.822, "reasoning_bytes": 87.222, "flops_per_problem": 4994755117.056}, "sumd.rev.find7": {"acc": 0.926, "reasoning_bytes": 93.73, "flops_per_problem": 5330924421.12}, "sumd.rev.find8": {"acc": 0.886, "reasoning_bytes": 101.51, "flops_per_problem": 5719559454.72}, "runmax.rev.find12": {"acc": 0.996, "reasoning_bytes": 106.0, "flops_per_problem": 6182830080.0}, "runmax.rev.find14": {"acc": 0.982, "reasoning_bytes": 115.504, "flops_per_problem": 6690882060.288}, "runmax.rev.find16": {"acc": 0.98, "reasoning_bytes": 124.38, "flops_per_problem": 7171199631.36}, "count.rev.find16": {"acc": 0.926, "reasoning_bytes": 111.14, "flops_per_problem": 6630643630.08}, "count.rev.find18": {"acc": 0.92, "reasoning_bytes": 118.74, "flops_per_problem": 7054609121.28}, "count.rev.find20": {"acc": 0.924, "reasoning_bytes": 127.58, "flops_per_problem": 7533336821.76}, "count.rev.rev16": {"acc": 0.788, "reasoning_bytes": 105.63, "flops_per_problem": 6254815887.36}, "count.rev.rev18": {"acc": 0.714, "reasoning_bytes": 113.36, "flops_per_problem": 6684522577.92}, "count.rev.rev20": {"acc": 0.638, "reasoning_bytes": 121.86, "flops_per_problem": 7148234833.92}, "sumd.rev.rev6": {"acc": 0.83, "reasoning_bytes": 81.2, "flops_per_problem": 4645690195.968}, "sumd.rev.rev7": {"acc": 0.544, "reasoning_bytes": 88.634, "flops_per_problem": 5019486437.376}, "sumd.rev.rev8": {"acc": 0.288, "reasoning_bytes": 96.548, "flops_per_problem": 5412361125.888}, "parity.rev.rev16": {"acc": 0.832, "reasoning_bytes": 122.552, "flops_per_problem": 6957980319.744}, "parity.rev.rev20": {"acc": 0.628, "reasoning_bytes": 143.6, "flops_per_problem": 8064176947.2}, "parity.rev.rev24": {"acc": 0.508, "reasoning_bytes": 166.94, "flops_per_problem": 9271595335.68}, "sumd.rev.sumd6": {"acc": 0.704, "reasoning_bytes": 87.06, "flops_per_problem": 4914731630.592}, "sumd.rev.sumd7": {"acc": 0.754, "reasoning_bytes": 93.316, "flops_per_problem": 5237298708.48}, "sumd.rev.sumd8": {"acc": 0.454, "reasoning_bytes": 100.856, "flops_per_problem": 5616747823.104}, "parity.rev.sumd16": {"acc": 0.796, "reasoning_bytes": 126.248, "flops_per_problem": 7165370105.856}, "parity.rev.sumd20": {"acc": 0.618, "reasoning_bytes": 147.752, "flops_per_problem": 8291705094.144}, "parity.rev.sumd24": {"acc": 0.488, "reasoning_bytes": 171.464, "flops_per_problem": 9515552145.408}, "add.rev.sumd6": {"acc": 0.06, "reasoning_bytes": 198.216, "flops_per_problem": 10138428112.896}, "add.rev.sumd7": {"acc": 0.05, "reasoning_bytes": 228.484, "flops_per_problem": 11551381438.464}, "add.rev.sumd8": {"acc": 0.022, "reasoning_bytes": 257.92, "flops_per_problem": 12944726360.064}, "parity.rev.inc16": {"acc": 0.798, "reasoning_bytes": 126.744, "flops_per_problem": 7143111917.568}, "parity.rev.inc20": {"acc": 0.636, "reasoning_bytes": 148.236, "flops_per_problem": 8268916948.992}, "parity.rev.inc24": {"acc": 0.494, "reasoning_bytes": 172.424, "flops_per_problem": 9513785622.528}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 104.952, "flops_per_problem": 6035237093.376}, "runmax.rev.inc14": {"acc": 0.996, "reasoning_bytes": 113.224, "flops_per_problem": 6492678193.152}, "runmax.rev.inc16": {"acc": 0.91, "reasoning_bytes": 122.736, "flops_per_problem": 7019102011.392}, "inc.rev.inc6": {"acc": 0.008, "reasoning_bytes": 170.224, "flops_per_problem": 8723531612.16}, "inc.rev.inc7": {"acc": 0.0, "reasoning_bytes": 198.794, "flops_per_problem": 10097533108.224}, "inc.rev.inc8": {"acc": 0.0, "reasoning_bytes": 217.224, "flops_per_problem": 11001286213.632}, "parity.sumd.cmp16": {"acc": 0.982, "reasoning_bytes": 127.872, "flops_per_problem": 7325417078.784}, "parity.sumd.cmp20": {"acc": 0.928, "reasoning_bytes": 149.916, "flops_per_problem": 8475600125.952}, "parity.sumd.cmp24": {"acc": 0.948, "reasoning_bytes": 172.056, "flops_per_problem": 9630022828.032}, "runmax.sumd.cmp12": {"acc": 0.998, "reasoning_bytes": 107.832, "flops_per_problem": 6263736827.904}, "runmax.sumd.cmp14": {"acc": 0.996, "reasoning_bytes": 115.476, "flops_per_problem": 6689645494.272}, "runmax.sumd.cmp16": {"acc": 0.992, "reasoning_bytes": 125.544, "flops_per_problem": 7222605447.168}, "count.sumd.cmp16": {"acc": 0.948, "reasoning_bytes": 111.852, "flops_per_problem": 6662087737.344}, "count.sumd.cmp18": {"acc": 0.942, "reasoning_bytes": 120.07, "flops_per_problem": 7116437422.08}, "count.sumd.cmp20": {"acc": 0.87, "reasoning_bytes": 129.022, "flops_per_problem": 7597019971.584}, "sumd.sumd.runmax6": {"acc": 0.778, "reasoning_bytes": 86.956, "flops_per_problem": 5030792183.808}, "sumd.sumd.runmax7": {"acc": 0.86, "reasoning_bytes": 93.744, "flops_per_problem": 5375794102.272}, "sumd.sumd.runmax8": {"acc": 0.73, "reasoning_bytes": 101.364, "flops_per_problem": 5757274718.208}, "count.sumd.runmax16": {"acc": 0.79, "reasoning_bytes": 114.08, "flops_per_problem": 6804646133.76}, "count.sumd.runmax18": {"acc": 0.724, "reasoning_bytes": 121.82, "flops_per_problem": 7234794455.04}, "count.sumd.runmax20": {"acc": 0.602, "reasoning_bytes": 130.696, "flops_per_problem": 7715112026.112}, "add.sumd.runmax6": {"acc": 0.326, "reasoning_bytes": 154.12, "flops_per_problem": 8262115835.904}, "add.sumd.runmax7": {"acc": 0.372, "reasoning_bytes": 173.892, "flops_per_problem": 9223015956.48}, "add.sumd.runmax8": {"acc": 0.182, "reasoning_bytes": 192.116, "flops_per_problem": 10118201425.92}, "parity.sumd.count16": {"acc": 1.0, "reasoning_bytes": 129.532, "flops_per_problem": 7487053922.304}, "parity.sumd.count20": {"acc": 1.0, "reasoning_bytes": 151.468, "flops_per_problem": 8632467357.696}, "parity.sumd.count24": {"acc": 1.0, "reasoning_bytes": 174.348, "flops_per_problem": 9819570733.056}, "sumd.sumd.count6": {"acc": 0.874, "reasoning_bytes": 87.482, "flops_per_problem": 5097920053.248}, "sumd.sumd.count7": {"acc": 0.92, "reasoning_bytes": 93.16, "flops_per_problem": 5394165940.224}, "sumd.sumd.count8": {"acc": 0.872, "reasoning_bytes": 100.86, "flops_per_problem": 5779091275.776}, "add.sumd.count6": {"acc": 0.65, "reasoning_bytes": 152.89, "flops_per_problem": 8253459873.792}, "add.sumd.count7": {"acc": 0.53, "reasoning_bytes": 173.046, "flops_per_problem": 9233791746.048}, "add.sumd.count8": {"acc": 0.422, "reasoning_bytes": 191.906, "flops_per_problem": 10153531883.52}, "runmax.sumd.find12": {"acc": 0.998, "reasoning_bytes": 108.952, "flops_per_problem": 6357362540.544}, "runmax.sumd.find14": {"acc": 0.992, "reasoning_bytes": 117.556, "flops_per_problem": 6825667756.032}, "runmax.sumd.find16": {"acc": 0.988, "reasoning_bytes": 127.352, "flops_per_problem": 7346527027.2}, "sumd.sumd.find6": {"acc": 0.85, "reasoning_bytes": 87.694, "flops_per_problem": 5062766247.936}, "sumd.sumd.find7": {"acc": 0.924, "reasoning_bytes": 92.99, "flops_per_problem": 5342671798.272}, "sumd.sumd.find8": {"acc": 0.896, "reasoning_bytes": 100.742, "flops_per_problem": 5729805287.424}, "parity.sumd.find16": {"acc": 0.968, "reasoning_bytes": 130.06, "flops_per_problem": 7466208952.32}, "parity.sumd.find20": {"acc": 0.882, "reasoning_bytes": 151.84, "flops_per_problem": 8604732948.48}, "parity.sumd.find24": {"acc": 0.826, "reasoning_bytes": 174.772, "flops_per_problem": 9794132803.584}, "count.sumd.rev16": {"acc": 0.81, "reasoning_bytes": 108.85, "flops_per_problem": 6441184051.2}, "count.sumd.rev18": {"acc": 0.75, "reasoning_bytes": 116.44, "flops_per_problem": 6864707911.68}, "count.sumd.rev20": {"acc": 0.63, "reasoning_bytes": 125.048, "flops_per_problem": 7333189779.456}, "parity.sumd.rev16": {"acc": 0.822, "reasoning_bytes": 125.72, "flops_per_problem": 7142052003.84}, "parity.sumd.rev20": {"acc": 0.606, "reasoning_bytes": 147.02, "flops_per_problem": 8259377725.44}, "parity.sumd.rev24": {"acc": 0.506, "reasoning_bytes": 170.352, "flops_per_problem": 9466442809.344}, "add.sumd.rev6": {"acc": 0.416, "reasoning_bytes": 147.632, "flops_per_problem": 7886818050.048}, "add.sumd.rev7": {"acc": 0.286, "reasoning_bytes": 167.468, "flops_per_problem": 8850986237.952}, "add.sumd.rev8": {"acc": 0.05, "reasoning_bytes": 182.52, "flops_per_problem": 9605556486.144}, "parity.sumd.sumd16": {"acc": 0.746, "reasoning_bytes": 129.32, "flops_per_problem": 7345202135.04}, "parity.sumd.sumd20": {"acc": 0.53, "reasoning_bytes": 152.072, "flops_per_problem": 8526652637.184}, "parity.sumd.sumd24": {"acc": 0.526, "reasoning_bytes": 175.794, "flops_per_problem": 9751824580.608}, "add.sumd.sumd6": {"acc": 0.248, "reasoning_bytes": 153.142, "flops_per_problem": 8147380174.848}, "add.sumd.sumd7": {"acc": 0.174, "reasoning_bytes": 172.816, "flops_per_problem": 9105188880.384}, "add.sumd.sumd8": {"acc": 0.06, "reasoning_bytes": 190.124, "flops_per_problem": 9953738145.792}, "count.sumd.sumd16": {"acc": 0.824, "reasoning_bytes": 111.79, "flops_per_problem": 6615186554.88}, "count.sumd.sumd18": {"acc": 0.752, "reasoning_bytes": 119.49, "flops_per_problem": 7043568353.28}, "count.sumd.sumd20": {"acc": 0.606, "reasoning_bytes": 128.29, "flops_per_problem": 7523002662.912}, "inc.sumd.inc6": {"acc": 0.568, "reasoning_bytes": 136.778, "flops_per_problem": 7095945756.672}, "inc.sumd.inc7": {"acc": 0.154, "reasoning_bytes": 154.074, "flops_per_problem": 7904394952.704}, "inc.sumd.inc8": {"acc": 0.022, "reasoning_bytes": 169.176, "flops_per_problem": 8619836719.104}, "sumd.sumd.inc6": {"acc": 0.652, "reasoning_bytes": 87.552, "flops_per_problem": 4940876169.216}, "sumd.sumd.inc7": {"acc": 0.79, "reasoning_bytes": 93.474, "flops_per_problem": 5248162824.192}, "sumd.sumd.inc8": {"acc": 0.602, "reasoning_bytes": 100.694, "flops_per_problem": 5612949798.912}, "parity.sumd.inc16": {"acc": 0.804, "reasoning_bytes": 129.804, "flops_per_problem": 7322413989.888}, "parity.sumd.inc20": {"acc": 0.564, "reasoning_bytes": 152.292, "flops_per_problem": 8492205441.024}, "parity.sumd.inc24": {"acc": 0.498, "reasoning_bytes": 176.326, "flops_per_problem": 9730184675.328}, "inc.inc.cmp6": {"acc": 0.81, "reasoning_bytes": 153.088, "flops_per_problem": 8053754462.208}, "inc.inc.cmp7": {"acc": 0.876, "reasoning_bytes": 169.336, "flops_per_problem": 8856550785.024}, "inc.inc.cmp8": {"acc": 0.766, "reasoning_bytes": 182.08, "flops_per_problem": 9498946830.336}, "runmax.inc.cmp12": {"acc": 0.958, "reasoning_bytes": 111.524, "flops_per_problem": 6414862860.288}, "runmax.inc.cmp14": {"acc": 0.962, "reasoning_bytes": 120.268, "flops_per_problem": 6892265668.608}, "runmax.inc.cmp16": {"acc": 0.952, "reasoning_bytes": 129.744, "flops_per_problem": 7400405975.04}, "sumd.inc.cmp6": {"acc": 0.952, "reasoning_bytes": 90.568, "flops_per_problem": 5147647672.32}, "sumd.inc.cmp7": {"acc": 0.948, "reasoning_bytes": 96.226, "flops_per_problem": 5441862057.984}, "sumd.inc.cmp8": {"acc": 0.94, "reasoning_bytes": 103.818, "flops_per_problem": 5821487824.896}, "sumd.inc.runmax6": {"acc": 0.768, "reasoning_bytes": 95.068, "flops_per_problem": 5341965189.12}, "sumd.inc.runmax7": {"acc": 0.856, "reasoning_bytes": 101.98, "flops_per_problem": 5695711395.84}, "sumd.inc.runmax8": {"acc": 0.79, "reasoning_bytes": 109.8, "flops_per_problem": 6085671321.6}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 115.264, "flops_per_problem": 6591956779.008}, "runmax.inc.runmax14": {"acc": 0.994, "reasoning_bytes": 123.752, "flops_per_problem": 7055139078.144}, "runmax.inc.runmax16": {"acc": 0.982, "reasoning_bytes": 134.026, "flops_per_problem": 7597196623.872}, "add.inc.runmax6": {"acc": 0.802, "reasoning_bytes": 193.396, "flops_per_problem": 9954179776.512}, "add.inc.runmax7": {"acc": 0.702, "reasoning_bytes": 221.932, "flops_per_problem": 11302036733.952}, "add.inc.runmax8": {"acc": 0.456, "reasoning_bytes": 241.746, "flops_per_problem": 12266204921.856}, "runmax.inc.count12": {"acc": 0.99, "reasoning_bytes": 114.726, "flops_per_problem": 6611918487.552}, "runmax.inc.count14": {"acc": 0.964, "reasoning_bytes": 122.982, "flops_per_problem": 7064236670.976}, "runmax.inc.count16": {"acc": 0.708, "reasoning_bytes": 133.064, "flops_per_problem": 7598874820.608}, "sumd.inc.count6": {"acc": 0.752, "reasoning_bytes": 94.746, "flops_per_problem": 5370229555.2}, "sumd.inc.count7": {"acc": 0.886, "reasoning_bytes": 100.8, "flops_per_problem": 5687585390.592}, "sumd.inc.count8": {"acc": 0.782, "reasoning_bytes": 108.746, "flops_per_problem": 6083374841.856}, "inc.inc.count6": {"acc": 0.638, "reasoning_bytes": 165.03, "flops_per_problem": 8436471644.16}, "inc.inc.count7": {"acc": 0.534, "reasoning_bytes": 189.128, "flops_per_problem": 9544964751.36}, "inc.inc.count8": {"acc": 0.45, "reasoning_bytes": 208.466, "flops_per_problem": 10444124897.28}, "parity.inc.find16": {"acc": 0.962, "reasoning_bytes": 130.592, "flops_per_problem": 7445540634.624}, "parity.inc.find20": {"acc": 0.884, "reasoning_bytes": 152.6, "flops_per_problem": 8594133811.2}, "parity.inc.find24": {"acc": 0.81, "reasoning_bytes": 175.52, "flops_per_problem": 9783003709.44}, "sumd.inc.find6": {"acc": 0.76, "reasoning_bytes": 95.088, "flops_per_problem": 5339227078.656}, "sumd.inc.find7": {"acc": 0.892, "reasoning_bytes": 101.098, "flops_per_problem": 5655258021.888}, "sumd.inc.find8": {"acc": 0.864, "reasoning_bytes": 108.684, "flops_per_problem": 6036297007.104}, "count.inc.find16": {"acc": 0.92, "reasoning_bytes": 115.0, "flops_per_problem": 6801113088.0}, "count.inc.find18": {"acc": 0.906, "reasoning_bytes": 122.76, "flops_per_problem": 7232144670.72}, "count.inc.find20": {"acc": 0.876, "reasoning_bytes": 131.62, "flops_per_problem": 7711755632.64}, "sumd.inc.rev6": {"acc": 0.842, "reasoning_bytes": 88.78, "flops_per_problem": 4976471605.248}, "sumd.inc.rev7": {"acc": 0.896, "reasoning_bytes": 95.74, "flops_per_problem": 5331454377.984}, "sumd.inc.rev8": {"acc": 0.766, "reasoning_bytes": 103.55, "flops_per_problem": 5721325977.6}, "count.inc.rev16": {"acc": 0.804, "reasoning_bytes": 109.72, "flops_per_problem": 6435442851.84}, "count.inc.rev18": {"acc": 0.686, "reasoning_bytes": 117.37, "flops_per_problem": 6861616496.64}, "count.inc.rev20": {"acc": 0.552, "reasoning_bytes": 126.07, "flops_per_problem": 7334161367.04}, "parity.inc.rev16": {"acc": 0.83, "reasoning_bytes": 126.192, "flops_per_problem": 7118733901.824}, "parity.inc.rev20": {"acc": 0.62, "reasoning_bytes": 147.996, "flops_per_problem": 8258317811.712}, "parity.inc.rev24": {"acc": 0.51, "reasoning_bytes": 171.844, "flops_per_problem": 9488171040.768}, "count.inc.sumd16": {"acc": 0.8, "reasoning_bytes": 113.106, "flops_per_problem": 6629142085.632}, "count.inc.sumd18": {"acc": 0.714, "reasoning_bytes": 120.774, "flops_per_problem": 7056110665.728}, "count.inc.sumd20": {"acc": 0.558, "reasoning_bytes": 129.586, "flops_per_problem": 7533601800.192}, "sumd.inc.sumd6": {"acc": 0.66, "reasoning_bytes": 94.298, "flops_per_problem": 5233324032.0}, "sumd.inc.sumd7": {"acc": 0.652, "reasoning_bytes": 100.414, "flops_per_problem": 5550591541.248}, "sumd.inc.sumd8": {"acc": 0.364, "reasoning_bytes": 108.046, "flops_per_problem": 5931277221.888}, "add.inc.sumd6": {"acc": 0.154, "reasoning_bytes": 199.152, "flops_per_problem": 10164219346.944}, "add.inc.sumd7": {"acc": 0.044, "reasoning_bytes": 228.02, "flops_per_problem": 11541488910.336}, "add.inc.sumd8": {"acc": 0.024, "reasoning_bytes": 247.62, "flops_per_problem": 12543549014.016}, "parity.inc.inc16": {"acc": 0.53, "reasoning_bytes": 130.552, "flops_per_problem": 7311284895.744}, "parity.inc.inc20": {"acc": 0.506, "reasoning_bytes": 153.496, "flops_per_problem": 8501214707.712}, "parity.inc.inc24": {"acc": 0.466, "reasoning_bytes": 178.264, "flops_per_problem": 9771344658.432}, "sumd.inc.inc6": {"acc": 0.672, "reasoning_bytes": 96.934, "flops_per_problem": 5333132574.72}, "sumd.inc.inc7": {"acc": 0.706, "reasoning_bytes": 103.026, "flops_per_problem": 5651548323.84}, "sumd.inc.inc8": {"acc": 0.414, "reasoning_bytes": 110.548, "flops_per_problem": 6030025850.88}, "runmax.inc.inc12": {"acc": 0.662, "reasoning_bytes": 115.952, "flops_per_problem": 6530481782.784}, "runmax.inc.inc14": {"acc": 0.284, "reasoning_bytes": 124.5, "flops_per_problem": 6997727084.544}, "runmax.inc.inc16": {"acc": 0.17, "reasoning_bytes": 134.804, "flops_per_problem": 7540491239.424}, "count.inc.cmp16": {"acc": 0.918, "reasoning_bytes": 112.89, "flops_per_problem": 6663765934.08}, "count.inc.cmp18": {"acc": 0.866, "reasoning_bytes": 121.072, "flops_per_problem": 7113610985.472}, "count.inc.cmp20": {"acc": 0.77, "reasoning_bytes": 129.476, "flops_per_problem": 7573348564.992}, "inc.rev.sumd6": {"acc": 0.076, "reasoning_bytes": 168.102, "flops_per_problem": 8482489565.184}, "inc.rev.sumd7": {"acc": 0.032, "reasoning_bytes": 196.786, "flops_per_problem": 9797842501.632}, "inc.rev.sumd8": {"acc": 0.03, "reasoning_bytes": 223.738, "flops_per_problem": 11035203452.928}, "runmax.inc.find12": {"acc": 0.996, "reasoning_bytes": 114.944, "flops_per_problem": 6577824595.968}, "runmax.inc.find14": {"acc": 0.974, "reasoning_bytes": 123.916, "flops_per_problem": 7062381821.952}, "runmax.inc.find16": {"acc": 0.858, "reasoning_bytes": 134.14, "flops_per_problem": 7602231214.08}, "inc.runmax.cmp6": {"acc": 0.984, "reasoning_bytes": 120.606, "flops_per_problem": 6518734405.632}, "inc.runmax.cmp7": {"acc": 0.982, "reasoning_bytes": 136.854, "flops_per_problem": 7280459071.488}, "inc.runmax.cmp8": {"acc": 0.952, "reasoning_bytes": 151.364, "flops_per_problem": 7965428318.208}} +{"step": 4000, "train_loss": 1.1404742002487183} +{"step": 4020, "train_loss": 1.1737388372421265} +{"step": 4040, "train_loss": 1.1367676258087158} +{"step": 4060, "train_loss": 1.1377817392349243} +{"step": 4080, "train_loss": 1.117644190788269} +{"step": 4100, "train_loss": 1.0263428688049316} +{"step": 4120, "train_loss": 1.1706308126449585} +{"step": 4140, "train_loss": 1.0600682497024536} +{"step": 4160, "train_loss": 1.1548118591308594} +{"step": 4180, "train_loss": 1.0357542037963867} +{"step": 4200, "train_loss": 1.0557913780212402} +{"step": 4220, "train_loss": 1.073935866355896} +{"step": 4240, "train_loss": 1.0696351528167725} +{"step": 4260, "train_loss": 1.1704353094100952} +{"step": 4280, "train_loss": 1.0531597137451172} +{"step": 4300, "train_loss": 1.1051429510116577} +{"step": 4320, "train_loss": 1.1274784803390503} +{"step": 4340, "train_loss": 1.1352955102920532} +{"step": 4360, "train_loss": 1.0675389766693115} +{"step": 4380, "train_loss": 1.01813542842865} +{"step": 4400, "train_loss": 1.096168041229248} +{"step": 4420, "train_loss": 1.1798566579818726} +{"step": 4440, "train_loss": 1.1036826372146606} +{"step": 4460, "train_loss": 1.11936616897583} +{"step": 4480, "train_loss": 1.1386114358901978} +{"step": 4500, "train_loss": 1.1017457246780396} +{"step": 4520, "train_loss": 1.024333119392395} +{"step": 4540, "train_loss": 1.111738920211792} +{"step": 4560, "train_loss": 1.1862937211990356} +{"step": 4580, "train_loss": 1.0466029644012451} +{"step": 4600, "train_loss": 1.1345252990722656} +{"step": 4620, "train_loss": 1.066064476966858} +{"step": 4640, "train_loss": 1.129777431488037} +{"step": 4660, "train_loss": 1.0375078916549683} +{"step": 4680, "train_loss": 1.0513992309570312} +{"step": 4700, "train_loss": 1.0933678150177002} +{"step": 4720, "train_loss": 1.0937435626983643} +{"step": 4740, "train_loss": 1.1030819416046143} +{"step": 4760, "train_loss": 1.0468913316726685} +{"step": 4780, "train_loss": 1.1007198095321655} +{"step": 4800, "train_loss": 1.074209213256836} +{"step": 4820, "train_loss": 1.1681528091430664} +{"step": 4840, "train_loss": 1.2156163454055786} +{"step": 4860, "train_loss": 1.0584214925765991} +{"step": 4880, "train_loss": 1.0616860389709473} +{"step": 4900, "train_loss": 1.1388647556304932} +{"step": 4920, "train_loss": 1.1123409271240234} +{"step": 4940, "train_loss": 1.1444735527038574} +{"step": 4960, "train_loss": 1.1449000835418701} +{"step": 4980, "train_loss": 1.0426809787750244} +{"step": 5000, "tokens": 163840000, "val_loss": 2.0144772827625275, "val_bpb": 0.7261863327232904, "lr": 0.00041540119322753773, "elapsed": 1631.9446365833282, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.0, "reasoning_bytes": 70.32, "flops_per_problem": 4509226303.488}, "add9": {"acc": 0.0, "reasoning_bytes": 79.0, "flops_per_problem": 5024344375.296}, "add10": {"acc": 0.0, "reasoning_bytes": 88.96, "flops_per_problem": 5600407486.464}, "reach14": {"acc": 0.532, "reasoning_bytes": 6.532, "flops_per_problem": 4572291170.304}, "reach16": {"acc": 0.55, "reasoning_bytes": 7.098, "flops_per_problem": 5127244333.056}, "reach18": {"acc": 0.538, "reasoning_bytes": 7.358, "flops_per_problem": 5668683595.776}, "parity24": {"acc": 0.5, "reasoning_bytes": 139.124, "flops_per_problem": 7689850748.928}, "parity28": {"acc": 0.442, "reasoning_bytes": 159.94, "flops_per_problem": 8791807721.472}, "parity32": {"acc": 0.074, "reasoning_bytes": 197.24, "flops_per_problem": 10604348522.496}, "cmp8": {"acc": 0.974, "reasoning_bytes": 5.824, "flops_per_problem": 1361282531.328}, "cmp9": {"acc": 0.954, "reasoning_bytes": 5.74, "flops_per_problem": 1445898977.28}, "cmp10": {"acc": 0.908, "reasoning_bytes": 6.02, "flops_per_problem": 1546502455.296}, "runmax12": {"acc": 1.0, "reasoning_bytes": 69.224, "flops_per_problem": 4072895152.128}, "runmax14": {"acc": 0.982, "reasoning_bytes": 77.012, "flops_per_problem": 4505163300.864}, "runmax16": {"acc": 0.974, "reasoning_bytes": 84.452, "flops_per_problem": 4922062700.544}, "count16": {"acc": 0.776, "reasoning_bytes": 76.08, "flops_per_problem": 4596492533.76}, "count18": {"acc": 0.752, "reasoning_bytes": 85.086, "flops_per_problem": 5083169587.2}, "count20": {"acc": 0.61, "reasoning_bytes": 95.916, "flops_per_problem": 5654993043.456}, "brackets16": {"acc": 0.724, "reasoning_bytes": 61.692, "flops_per_problem": 4005943934.976}, "brackets18": {"acc": 0.686, "reasoning_bytes": 73.84, "flops_per_problem": 4631116382.208}, "brackets20": {"acc": 0.69, "reasoning_bytes": 88.724, "flops_per_problem": 5375617449.984}, "sumd8": {"acc": 0.74, "reasoning_bytes": 57.618, "flops_per_problem": 3339699830.784}, "sumd9": {"acc": 0.302, "reasoning_bytes": 62.944, "flops_per_problem": 3620400316.416}, "sumd10": {"acc": 0.052, "reasoning_bytes": 67.316, "flops_per_problem": 3857556013.056}, "inc8": {"acc": 0.47, "reasoning_bytes": 62.232, "flops_per_problem": 3758365753.344}, "inc9": {"acc": 0.0, "reasoning_bytes": 63.864, "flops_per_problem": 3883965530.112}, "inc10": {"acc": 0.0, "reasoning_bytes": 71.0, "flops_per_problem": 4282493091.84}, "add.cmp6": {"acc": 0.988, "reasoning_bytes": 92.57, "flops_per_problem": 5529923223.552}, "add.cmp7": {"acc": 0.918, "reasoning_bytes": 103.502, "flops_per_problem": 6142288379.904}, "add.cmp8": {"acc": 0.918, "reasoning_bytes": 108.238, "flops_per_problem": 6485435449.344}, "add.runmax6": {"acc": 0.96, "reasoning_bytes": 119.816, "flops_per_problem": 6528008650.752}, "add.runmax7": {"acc": 0.6, "reasoning_bytes": 120.968, "flops_per_problem": 6667210653.696}, "add.runmax8": {"acc": 0.778, "reasoning_bytes": 138.576, "flops_per_problem": 7533160169.472}, "add.count6": {"acc": 0.872, "reasoning_bytes": 115.538, "flops_per_problem": 6383242100.736}, "add.count7": {"acc": 0.388, "reasoning_bytes": 116.578, "flops_per_problem": 6517497839.616}, "add.count8": {"acc": 0.524, "reasoning_bytes": 131.676, "flops_per_problem": 7272598044.672}, "add.find6": {"acc": 0.646, "reasoning_bytes": 108.528, "flops_per_problem": 6029495894.016}, "add.find7": {"acc": 0.37, "reasoning_bytes": 111.466, "flops_per_problem": 6247573143.552}, "add.find8": {"acc": 0.464, "reasoning_bytes": 127.63, "flops_per_problem": 7049751183.36}, "add.rev6": {"acc": 0.586, "reasoning_bytes": 119.068, "flops_per_problem": 6602290937.856}, "add.rev7": {"acc": 0.0, "reasoning_bytes": 123.142, "flops_per_problem": 6878133485.568}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 145.792, "flops_per_problem": 8005175083.008}, "add.sumd6": {"acc": 0.762, "reasoning_bytes": 125.244, "flops_per_problem": 6723386081.28}, "add.sumd7": {"acc": 0.056, "reasoning_bytes": 126.656, "flops_per_problem": 6874158809.088}, "add.sumd8": {"acc": 0.044, "reasoning_bytes": 145.37, "flops_per_problem": 7788952682.496}, "add.inc6": {"acc": 0.582, "reasoning_bytes": 127.794, "flops_per_problem": 6988276187.136}, "add.inc7": {"acc": 0.0, "reasoning_bytes": 130.266, "flops_per_problem": 7189394817.024}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 148.67, "flops_per_problem": 8130244902.912}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 86.64, "flops_per_problem": 5107017646.08}, "runmax.cmp14": {"acc": 0.98, "reasoning_bytes": 93.012, "flops_per_problem": 5476750884.864}, "runmax.cmp16": {"acc": 0.928, "reasoning_bytes": 99.384, "flops_per_problem": 5846484123.648}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 87.16, "flops_per_problem": 5174145515.52}, "runmax.runmax14": {"acc": 0.966, "reasoning_bytes": 94.036, "flops_per_problem": 5566136942.592}, "runmax.runmax16": {"acc": 0.962, "reasoning_bytes": 100.936, "flops_per_problem": 5959188283.392}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 87.436, "flops_per_problem": 5230497595.392}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 94.024, "flops_per_problem": 5609770057.728}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 100.636, "flops_per_problem": 5990102433.792}, "runmax.find12": {"acc": 0.998, "reasoning_bytes": 87.388, "flops_per_problem": 5184214695.936}, "runmax.find14": {"acc": 0.978, "reasoning_bytes": 94.048, "flops_per_problem": 5566666899.456}, "runmax.find16": {"acc": 0.922, "reasoning_bytes": 100.636, "flops_per_problem": 5945939361.792}, "runmax.rev12": {"acc": 0.996, "reasoning_bytes": 81.416, "flops_per_problem": 4787983613.952}, "runmax.rev14": {"acc": 0.972, "reasoning_bytes": 88.988, "flops_per_problem": 5210712539.136}, "runmax.rev16": {"acc": 0.954, "reasoning_bytes": 95.192, "flops_per_problem": 5573026381.824}, "runmax.sumd12": {"acc": 0.998, "reasoning_bytes": 84.692, "flops_per_problem": 4976824909.824}, "runmax.sumd14": {"acc": 0.972, "reasoning_bytes": 92.024, "flops_per_problem": 5388954697.728}, "runmax.sumd16": {"acc": 0.966, "reasoning_bytes": 98.684, "flops_per_problem": 5771406901.248}, "runmax.inc12": {"acc": 0.996, "reasoning_bytes": 85.068, "flops_per_problem": 4980269629.44}, "runmax.inc14": {"acc": 0.972, "reasoning_bytes": 92.976, "flops_per_problem": 5420487131.136}, "runmax.inc16": {"acc": 0.952, "reasoning_bytes": 99.228, "flops_per_problem": 5786598998.016}, "count.cmp16": {"acc": 0.96, "reasoning_bytes": 91.83, "flops_per_problem": 5557039349.76}, "count.cmp18": {"acc": 0.93, "reasoning_bytes": 99.86, "flops_per_problem": 6000083288.064}, "count.cmp20": {"acc": 0.894, "reasoning_bytes": 107.468, "flops_per_problem": 6430408261.632}, "count.runmax16": {"acc": 0.806, "reasoning_bytes": 92.63, "flops_per_problem": 5636532879.36}, "count.runmax18": {"acc": 0.774, "reasoning_bytes": 100.96, "flops_per_problem": 6092737413.12}, "count.runmax20": {"acc": 0.692, "reasoning_bytes": 109.0, "flops_per_problem": 6536134656.0}, "count.count16": {"acc": 0.998, "reasoning_bytes": 92.53, "flops_per_problem": 5676279644.16}, "count.count18": {"acc": 1.0, "reasoning_bytes": 100.78, "flops_per_problem": 6128951132.16}, "count.count20": {"acc": 0.996, "reasoning_bytes": 108.62, "flops_per_problem": 6563515760.64}, "count.find16": {"acc": 0.93, "reasoning_bytes": 92.68, "flops_per_problem": 5638741032.96}, "count.find18": {"acc": 0.874, "reasoning_bytes": 100.82, "flops_per_problem": 6086554583.04}, "count.find20": {"acc": 0.874, "reasoning_bytes": 108.47, "flops_per_problem": 6512728227.84}, "count.rev16": {"acc": 0.792, "reasoning_bytes": 87.5, "flops_per_problem": 5277487104.0}, "count.rev18": {"acc": 0.746, "reasoning_bytes": 95.61, "flops_per_problem": 5723975761.92}, "count.rev20": {"acc": 0.632, "reasoning_bytes": 103.28, "flops_per_problem": 6151032668.16}, "count.sumd16": {"acc": 0.81, "reasoning_bytes": 90.552, "flops_per_problem": 5456435871.744}, "count.sumd18": {"acc": 0.774, "reasoning_bytes": 98.774, "flops_per_problem": 5907870793.728}, "count.sumd20": {"acc": 0.644, "reasoning_bytes": 106.642, "flops_per_problem": 6343671988.224}, "count.inc16": {"acc": 0.8, "reasoning_bytes": 91.29, "flops_per_problem": 5444865146.88}, "count.inc18": {"acc": 0.764, "reasoning_bytes": 99.54, "flops_per_problem": 5897536634.88}, "count.inc20": {"acc": 0.646, "reasoning_bytes": 107.58, "flops_per_problem": 6340933877.76}, "parity.cmp16": {"acc": 0.968, "reasoning_bytes": 107.76, "flops_per_problem": 6216394014.72}, "parity.cmp20": {"acc": 0.964, "reasoning_bytes": 126.9, "flops_per_problem": 7238327500.8}, "parity.cmp24": {"acc": 0.94, "reasoning_bytes": 144.838, "flops_per_problem": 8207176974.336}, "parity.runmax16": {"acc": 0.786, "reasoning_bytes": 107.812, "flops_per_problem": 6262853566.464}, "parity.runmax20": {"acc": 0.73, "reasoning_bytes": 128.944, "flops_per_problem": 7372759891.968}, "parity.runmax24": {"acc": 0.538, "reasoning_bytes": 151.022, "flops_per_problem": 8528330833.92}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 108.964, "flops_per_problem": 6357892497.408}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 129.088, "flops_per_problem": 7423282446.336}, "parity.count24": {"acc": 0.818, "reasoning_bytes": 146.228, "flops_per_problem": 8356889788.416}, "parity.find16": {"acc": 0.93, "reasoning_bytes": 107.956, "flops_per_problem": 6269213048.832}, "parity.find20": {"acc": 0.89, "reasoning_bytes": 128.46, "flops_per_problem": 7351384965.12}, "parity.find24": {"acc": 0.82, "reasoning_bytes": 146.8, "flops_per_problem": 8337987993.6}, "parity.rev16": {"acc": 0.792, "reasoning_bytes": 103.244, "flops_per_problem": 5928627437.568}, "parity.rev20": {"acc": 0.708, "reasoning_bytes": 123.956, "flops_per_problem": 7019985272.832}, "parity.rev24": {"acc": 0.5, "reasoning_bytes": 144.4, "flops_per_problem": 8099507404.8}, "parity.sumd16": {"acc": 0.804, "reasoning_bytes": 106.916, "flops_per_problem": 6134957309.952}, "parity.sumd20": {"acc": 0.748, "reasoning_bytes": 127.63, "flops_per_problem": 7226403471.36}, "parity.sumd24": {"acc": 0.472, "reasoning_bytes": 148.158, "flops_per_problem": 8311048519.68}, "parity.inc16": {"acc": 0.804, "reasoning_bytes": 106.692, "flops_per_problem": 6080901709.824}, "parity.inc20": {"acc": 0.7, "reasoning_bytes": 128.22, "flops_per_problem": 7208296611.84}, "parity.inc24": {"acc": 0.458, "reasoning_bytes": 148.996, "flops_per_problem": 8303187492.864}, "sumd.cmp6": {"acc": 0.994, "reasoning_bytes": 62.11, "flops_per_problem": 3714379333.632}, "sumd.cmp7": {"acc": 0.974, "reasoning_bytes": 69.174, "flops_per_problem": 4070686998.528}, "sumd.cmp8": {"acc": 0.946, "reasoning_bytes": 72.51, "flops_per_problem": 4262089752.576}, "sumd.runmax6": {"acc": 0.996, "reasoning_bytes": 67.546, "flops_per_problem": 3954626445.312}, "sumd.runmax7": {"acc": 0.874, "reasoning_bytes": 74.504, "flops_per_problem": 4306076172.288}, "sumd.runmax8": {"acc": 0.506, "reasoning_bytes": 78.714, "flops_per_problem": 4536165777.408}, "sumd.count6": {"acc": 0.998, "reasoning_bytes": 66.432, "flops_per_problem": 3949591855.104}, "sumd.count7": {"acc": 0.906, "reasoning_bytes": 73.32, "flops_per_problem": 4297950167.04}, "sumd.count8": {"acc": 0.55, "reasoning_bytes": 76.788, "flops_per_problem": 4495270772.736}, "sumd.find6": {"acc": 0.996, "reasoning_bytes": 66.2, "flops_per_problem": 3895182950.4}, "sumd.find7": {"acc": 0.96, "reasoning_bytes": 72.844, "flops_per_problem": 4232765472.768}, "sumd.find8": {"acc": 0.778, "reasoning_bytes": 76.53, "flops_per_problem": 4439713628.16}, "sumd.rev6": {"acc": 0.998, "reasoning_bytes": 61.544, "flops_per_problem": 3601145217.024}, "sumd.rev7": {"acc": 0.886, "reasoning_bytes": 68.728, "flops_per_problem": 3962752450.56}, "sumd.rev8": {"acc": 0.39, "reasoning_bytes": 72.226, "flops_per_problem": 4161132969.984}, "sumd.sumd6": {"acc": 0.996, "reasoning_bytes": 65.744, "flops_per_problem": 3795639386.112}, "sumd.sumd7": {"acc": 0.862, "reasoning_bytes": 72.694, "flops_per_problem": 4147884048.384}, "sumd.sumd8": {"acc": 0.488, "reasoning_bytes": 77.114, "flops_per_problem": 4386894594.048}, "sumd.inc6": {"acc": 0.994, "reasoning_bytes": 68.51, "flops_per_problem": 3908785176.576}, "sumd.inc7": {"acc": 0.862, "reasoning_bytes": 75.376, "flops_per_problem": 4256260227.072}, "sumd.inc8": {"acc": 0.428, "reasoning_bytes": 79.542, "flops_per_problem": 4484406657.024}, "inc.cmp6": {"acc": 0.988, "reasoning_bytes": 78.57, "flops_per_problem": 4573969367.04}, "inc.cmp7": {"acc": 0.968, "reasoning_bytes": 87.6, "flops_per_problem": 5061088051.2}, "inc.cmp8": {"acc": 0.982, "reasoning_bytes": 91.162, "flops_per_problem": 5306723057.664}, "inc.runmax6": {"acc": 0.99, "reasoning_bytes": 103.084, "flops_per_problem": 5479930626.048}, "inc.runmax7": {"acc": 0.814, "reasoning_bytes": 103.896, "flops_per_problem": 5559954112.512}, "inc.runmax8": {"acc": 0.816, "reasoning_bytes": 114.776, "flops_per_problem": 6084611407.872}, "inc.count6": {"acc": 0.91, "reasoning_bytes": 98.716, "flops_per_problem": 5331189399.552}, "inc.count7": {"acc": 0.658, "reasoning_bytes": 99.366, "flops_per_problem": 5404058468.352}, "inc.count8": {"acc": 0.702, "reasoning_bytes": 112.108, "flops_per_problem": 6010947403.776}, "inc.find6": {"acc": 0.68, "reasoning_bytes": 91.306, "flops_per_problem": 4959777964.032}, "inc.find7": {"acc": 0.486, "reasoning_bytes": 91.584, "flops_per_problem": 5016218370.048}, "inc.find8": {"acc": 0.52, "reasoning_bytes": 105.684, "flops_per_problem": 5683080757.248}, "inc.rev6": {"acc": 0.752, "reasoning_bytes": 100.126, "flops_per_problem": 5428613136.384}, "inc.rev7": {"acc": 0.014, "reasoning_bytes": 104.79, "flops_per_problem": 5689705218.048}, "inc.rev8": {"acc": 0.0, "reasoning_bytes": 123.752, "flops_per_problem": 6610681921.536}, "inc.sumd6": {"acc": 0.82, "reasoning_bytes": 108.412, "flops_per_problem": 5671068401.664}, "inc.sumd7": {"acc": 0.062, "reasoning_bytes": 108.932, "flops_per_problem": 5738107944.96}, "inc.sumd8": {"acc": 0.048, "reasoning_bytes": 123.006, "flops_per_problem": 6403822092.288}, "inc.inc6": {"acc": 0.492, "reasoning_bytes": 105.62, "flops_per_problem": 5662412439.552}, "inc.inc7": {"acc": 0.0, "reasoning_bytes": 111.494, "flops_per_problem": 5976676859.904}, "inc.inc8": {"acc": 0.0, "reasoning_bytes": 124.244, "flops_per_problem": 6602644242.432}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 103.916, "flops_per_problem": 6179120381.952}, "runmax.runmax.cmp14": {"acc": 0.992, "reasoning_bytes": 110.444, "flops_per_problem": 6555743059.968}, "runmax.runmax.cmp16": {"acc": 0.988, "reasoning_bytes": 119.54, "flops_per_problem": 7045776506.88}, "sumd.runmax.cmp6": {"acc": 0.998, "reasoning_bytes": 83.256, "flops_per_problem": 4913406738.432}, "sumd.runmax.cmp7": {"acc": 0.912, "reasoning_bytes": 89.378, "flops_per_problem": 5227936137.216}, "sumd.runmax.cmp8": {"acc": 0.688, "reasoning_bytes": 92.0, "flops_per_problem": 5387894784.0}, "add.runmax.cmp6": {"acc": 0.976, "reasoning_bytes": 132.644, "flops_per_problem": 7359510970.368}, "add.runmax.cmp7": {"acc": 0.864, "reasoning_bytes": 136.786, "flops_per_problem": 7630760558.592}, "add.runmax.cmp8": {"acc": 0.942, "reasoning_bytes": 153.804, "flops_per_problem": 8470653861.888}, "count.runmax.runmax16": {"acc": 0.77, "reasoning_bytes": 108.454, "flops_per_problem": 6644510834.688}, "count.runmax.runmax18": {"acc": 0.752, "reasoning_bytes": 117.4, "flops_per_problem": 7127919820.8}, "count.runmax.runmax20": {"acc": 0.666, "reasoning_bytes": 125.15, "flops_per_problem": 7558509772.8}, "add.runmax.runmax6": {"acc": 0.826, "reasoning_bytes": 128.546, "flops_per_problem": 7222693773.312}, "add.runmax.runmax7": {"acc": 0.59, "reasoning_bytes": 137.548, "flops_per_problem": 7708575891.456}, "add.runmax.runmax8": {"acc": 0.79, "reasoning_bytes": 155.424, "flops_per_problem": 8586361110.528}, "parity.runmax.runmax16": {"acc": 0.826, "reasoning_bytes": 124.572, "flops_per_problem": 7312168157.184}, "parity.runmax.runmax20": {"acc": 0.712, "reasoning_bytes": 144.852, "flops_per_problem": 8384447545.344}, "parity.runmax.runmax24": {"acc": 0.526, "reasoning_bytes": 163.944, "flops_per_problem": 9404261203.968}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 126.456, "flops_per_problem": 7439534456.832}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 145.956, "flops_per_problem": 8477366648.832}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 165.12, "flops_per_problem": 9500360048.64}, "inc.runmax.count6": {"acc": 1.0, "reasoning_bytes": 120.322, "flops_per_problem": 6594518237.184}, "inc.runmax.count7": {"acc": 0.96, "reasoning_bytes": 120.278, "flops_per_problem": 6636738134.016}, "inc.runmax.count8": {"acc": 0.96, "reasoning_bytes": 132.194, "flops_per_problem": 7207148371.968}, "sumd.runmax.count6": {"acc": 0.994, "reasoning_bytes": 84.362, "flops_per_problem": 5050577240.064}, "sumd.runmax.count7": {"acc": 0.83, "reasoning_bytes": 90.684, "flops_per_problem": 5373939253.248}, "sumd.runmax.count8": {"acc": 0.492, "reasoning_bytes": 93.706, "flops_per_problem": 5551563128.832}, "runmax.runmax.find12": {"acc": 1.0, "reasoning_bytes": 104.664, "flops_per_problem": 6256317431.808}, "runmax.runmax.find14": {"acc": 0.992, "reasoning_bytes": 111.324, "flops_per_problem": 6638769635.328}, "runmax.runmax.find16": {"acc": 0.982, "reasoning_bytes": 120.324, "flops_per_problem": 7124563427.328}, "add.runmax.find6": {"acc": 0.968, "reasoning_bytes": 134.144, "flops_per_problem": 7469918650.368}, "add.runmax.find7": {"acc": 0.882, "reasoning_bytes": 137.376, "flops_per_problem": 7700979843.072}, "add.runmax.find8": {"acc": 0.942, "reasoning_bytes": 155.39, "flops_per_problem": 8584859566.08}, "parity.runmax.find16": {"acc": 0.958, "reasoning_bytes": 125.136, "flops_per_problem": 7337076129.792}, "parity.runmax.find20": {"acc": 0.916, "reasoning_bytes": 144.936, "flops_per_problem": 8388157243.392}, "parity.runmax.find24": {"acc": 0.836, "reasoning_bytes": 164.028, "flops_per_problem": 9407970902.016}, "add.runmax.rev6": {"acc": 0.874, "reasoning_bytes": 123.312, "flops_per_problem": 6859055038.464}, "add.runmax.rev7": {"acc": 0.572, "reasoning_bytes": 132.596, "flops_per_problem": 7357391142.912}, "add.runmax.rev8": {"acc": 0.79, "reasoning_bytes": 149.878, "flops_per_problem": 8208943497.216}, "parity.runmax.rev16": {"acc": 0.82, "reasoning_bytes": 119.992, "flops_per_problem": 6977412071.424}, "parity.runmax.rev20": {"acc": 0.716, "reasoning_bytes": 139.864, "flops_per_problem": 8031672926.208}, "parity.runmax.rev24": {"acc": 0.554, "reasoning_bytes": 158.352, "flops_per_problem": 9024812089.344}, "sumd.runmax.rev6": {"acc": 0.996, "reasoning_bytes": 79.51, "flops_per_problem": 4659645726.72}, "sumd.runmax.rev7": {"acc": 0.828, "reasoning_bytes": 85.924, "flops_per_problem": 4987070742.528}, "sumd.runmax.rev8": {"acc": 0.366, "reasoning_bytes": 89.166, "flops_per_problem": 5174410493.952}, "sumd.runmax.sumd6": {"acc": 0.976, "reasoning_bytes": 82.35, "flops_per_problem": 4829231923.2}, "sumd.runmax.sumd7": {"acc": 0.75, "reasoning_bytes": 88.156, "flops_per_problem": 5129805791.232}, "sumd.runmax.sumd8": {"acc": 0.348, "reasoning_bytes": 92.054, "flops_per_problem": 5346116517.888}, "add.runmax.sumd6": {"acc": 0.884, "reasoning_bytes": 127.208, "flops_per_problem": 7075277438.976}, "add.runmax.sumd7": {"acc": 0.58, "reasoning_bytes": 135.454, "flops_per_problem": 7527772274.688}, "add.runmax.sumd8": {"acc": 0.788, "reasoning_bytes": 153.63, "flops_per_problem": 8418806415.36}, "parity.runmax.sumd16": {"acc": 0.824, "reasoning_bytes": 123.244, "flops_per_problem": 7165193453.568}, "parity.runmax.sumd20": {"acc": 0.744, "reasoning_bytes": 143.464, "flops_per_problem": 8234823057.408}, "parity.runmax.sumd24": {"acc": 0.58, "reasoning_bytes": 161.98, "flops_per_problem": 9229198786.56}, "count.runmax.inc16": {"acc": 0.8, "reasoning_bytes": 107.98, "flops_per_problem": 6491088322.56}, "count.runmax.inc18": {"acc": 0.74, "reasoning_bytes": 116.46, "flops_per_problem": 6953917317.12}, "count.runmax.inc20": {"acc": 0.64, "reasoning_bytes": 123.91, "flops_per_problem": 7371258347.52}, "runmax.runmax.inc12": {"acc": 1.0, "reasoning_bytes": 103.436, "flops_per_problem": 6100775092.224}, "runmax.runmax.inc14": {"acc": 0.97, "reasoning_bytes": 110.12, "flops_per_problem": 6486672015.36}, "runmax.runmax.inc16": {"acc": 0.96, "reasoning_bytes": 117.748, "flops_per_problem": 6913817247.744}, "add.runmax.inc6": {"acc": 0.88, "reasoning_bytes": 127.702, "flops_per_problem": 7072186023.936}, "add.runmax.inc7": {"acc": 0.568, "reasoning_bytes": 136.564, "flops_per_problem": 7552591921.152}, "add.runmax.inc8": {"acc": 0.778, "reasoning_bytes": 154.14, "flops_per_problem": 8420749590.528}, "count.count.cmp16": {"acc": 1.0, "reasoning_bytes": 108.76, "flops_per_problem": 6658024734.72}, "count.count.cmp18": {"acc": 0.996, "reasoning_bytes": 117.05, "flops_per_problem": 7112462745.6}, "count.count.cmp20": {"acc": 0.996, "reasoning_bytes": 124.868, "flops_per_problem": 7546055786.496}, "add.count.cmp6": {"acc": 0.946, "reasoning_bytes": 130.266, "flops_per_problem": 7298654257.152}, "add.count.cmp7": {"acc": 0.868, "reasoning_bytes": 130.968, "flops_per_problem": 7417982877.696}, "add.count.cmp8": {"acc": 0.852, "reasoning_bytes": 147.286, "flops_per_problem": 8226962030.592}, "sumd.count.cmp6": {"acc": 0.998, "reasoning_bytes": 82.472, "flops_per_problem": 4922945961.984}, "sumd.count.cmp7": {"acc": 0.964, "reasoning_bytes": 87.84, "flops_per_problem": 5204176404.48}, "sumd.count.cmp8": {"acc": 0.938, "reasoning_bytes": 90.802, "flops_per_problem": 5379150495.744}, "add.count.runmax6": {"acc": 0.754, "reasoning_bytes": 127.166, "flops_per_problem": 7205911805.952}, "add.count.runmax7": {"acc": 0.386, "reasoning_bytes": 131.934, "flops_per_problem": 7504807477.248}, "add.count.runmax8": {"acc": 0.52, "reasoning_bytes": 148.378, "flops_per_problem": 8319351177.216}, "sumd.count.runmax6": {"acc": 0.984, "reasoning_bytes": 83.336, "flops_per_problem": 5005265928.192}, "sumd.count.runmax7": {"acc": 0.83, "reasoning_bytes": 89.172, "flops_per_problem": 5307164688.384}, "sumd.count.runmax8": {"acc": 0.44, "reasoning_bytes": 92.132, "flops_per_problem": 5482050453.504}, "inc.count.runmax6": {"acc": 0.86, "reasoning_bytes": 113.326, "flops_per_problem": 6285553385.472}, "inc.count.runmax7": {"acc": 0.674, "reasoning_bytes": 115.98, "flops_per_problem": 6446925250.56}, "inc.count.runmax8": {"acc": 0.714, "reasoning_bytes": 129.03, "flops_per_problem": 7067416412.16}, "parity.count.count16": {"acc": 1.0, "reasoning_bytes": 126.852, "flops_per_problem": 7501186105.344}, "parity.count.count20": {"acc": 1.0, "reasoning_bytes": 146.088, "flops_per_problem": 8527359246.336}, "parity.count.count24": {"acc": 1.0, "reasoning_bytes": 163.536, "flops_per_problem": 9474568814.592}, "runmax.count.count12": {"acc": 1.0, "reasoning_bytes": 104.904, "flops_per_problem": 6355242713.088}, "runmax.count.count14": {"acc": 1.0, "reasoning_bytes": 111.216, "flops_per_problem": 6722326167.552}, "runmax.count.count16": {"acc": 1.0, "reasoning_bytes": 120.86, "flops_per_problem": 7236560977.92}, "inc.count.count6": {"acc": 0.958, "reasoning_bytes": 115.374, "flops_per_problem": 6420162428.928}, "inc.count.count7": {"acc": 0.888, "reasoning_bytes": 115.954, "flops_per_problem": 6489940082.688}, "inc.count.count8": {"acc": 0.872, "reasoning_bytes": 128.614, "flops_per_problem": 7093207646.208}, "inc.count.find6": {"acc": 0.974, "reasoning_bytes": 115.636, "flops_per_problem": 6387570081.792}, "inc.count.find7": {"acc": 0.876, "reasoning_bytes": 115.748, "flops_per_problem": 6436679417.856}, "inc.count.find8": {"acc": 0.912, "reasoning_bytes": 127.81, "flops_per_problem": 7013537464.32}, "add.count.find6": {"acc": 0.934, "reasoning_bytes": 131.656, "flops_per_problem": 7404203999.232}, "add.count.find7": {"acc": 0.82, "reasoning_bytes": 132.124, "flops_per_problem": 7513198460.928}, "add.count.find8": {"acc": 0.87, "reasoning_bytes": 148.446, "flops_per_problem": 8322354266.112}, "runmax.count.find12": {"acc": 1.0, "reasoning_bytes": 104.892, "flops_per_problem": 6310549684.224}, "runmax.count.find14": {"acc": 1.0, "reasoning_bytes": 111.228, "flops_per_problem": 6678693052.416}, "runmax.count.find16": {"acc": 1.0, "reasoning_bytes": 120.48, "flops_per_problem": 7175615938.56}, "parity.count.rev16": {"acc": 1.0, "reasoning_bytes": 121.228, "flops_per_problem": 7076160700.416}, "parity.count.rev20": {"acc": 1.0, "reasoning_bytes": 140.644, "flops_per_problem": 8110283194.368}, "parity.count.rev24": {"acc": 1.0, "reasoning_bytes": 158.084, "flops_per_problem": 9057139458.048}, "inc.count.rev6": {"acc": 0.89, "reasoning_bytes": 108.788, "flops_per_problem": 5952740474.88}, "inc.count.rev7": {"acc": 0.648, "reasoning_bytes": 110.752, "flops_per_problem": 6083551494.144}, "inc.count.rev8": {"acc": 0.708, "reasoning_bytes": 122.918, "flops_per_problem": 6665002500.096}, "runmax.count.rev12": {"acc": 1.0, "reasoning_bytes": 99.748, "flops_per_problem": 5950885625.856}, "runmax.count.rev14": {"acc": 1.0, "reasoning_bytes": 106.084, "flops_per_problem": 6319028994.048}, "runmax.count.rev16": {"acc": 1.0, "reasoning_bytes": 113.764, "flops_per_problem": 6746527531.008}, "count.count.sumd16": {"acc": 0.988, "reasoning_bytes": 106.91, "flops_per_problem": 6532159979.52}, "count.count.sumd18": {"acc": 1.0, "reasoning_bytes": 115.58, "flops_per_problem": 7003379957.76}, "count.count.sumd20": {"acc": 0.992, "reasoning_bytes": 122.964, "flops_per_problem": 7417806225.408}, "runmax.count.sumd12": {"acc": 1.0, "reasoning_bytes": 102.772, "flops_per_problem": 6128597827.584}, "runmax.count.sumd14": {"acc": 1.0, "reasoning_bytes": 109.192, "flops_per_problem": 6500450893.824}, "runmax.count.sumd16": {"acc": 1.0, "reasoning_bytes": 118.096, "flops_per_problem": 6982005030.912}, "sumd.count.sumd6": {"acc": 0.992, "reasoning_bytes": 81.384, "flops_per_problem": 4830733467.648}, "sumd.count.sumd7": {"acc": 0.868, "reasoning_bytes": 87.646, "flops_per_problem": 5151445696.512}, "sumd.count.sumd8": {"acc": 0.476, "reasoning_bytes": 90.81, "flops_per_problem": 5335340728.32}, "parity.count.inc16": {"acc": 1.0, "reasoning_bytes": 124.532, "flops_per_problem": 7222075490.304}, "parity.count.inc20": {"acc": 1.0, "reasoning_bytes": 144.38, "flops_per_problem": 8275276431.36}, "parity.count.inc24": {"acc": 0.956, "reasoning_bytes": 161.966, "flops_per_problem": 9228580503.552}, "count.count.inc16": {"acc": 1.0, "reasoning_bytes": 107.82, "flops_per_problem": 6528185303.04}, "count.count.inc18": {"acc": 1.0, "reasoning_bytes": 116.33, "flops_per_problem": 6992339189.76}, "count.count.inc20": {"acc": 0.994, "reasoning_bytes": 123.548, "flops_per_problem": 7399434387.456}, "add.count.inc6": {"acc": 0.776, "reasoning_bytes": 128.742, "flops_per_problem": 7143023591.424}, "add.count.inc7": {"acc": 0.366, "reasoning_bytes": 130.844, "flops_per_problem": 7324180512.768}, "add.count.inc8": {"acc": 0.494, "reasoning_bytes": 146.85, "flops_per_problem": 8119380787.2}, "parity.rev.cmp16": {"acc": 0.986, "reasoning_bytes": 119.712, "flops_per_problem": 6920883339.264}, "parity.rev.cmp20": {"acc": 0.976, "reasoning_bytes": 137.976, "flops_per_problem": 7904129974.272}, "parity.rev.cmp24": {"acc": 0.94, "reasoning_bytes": 154.836, "flops_per_problem": 8825371656.192}, "sumd.rev.cmp6": {"acc": 0.978, "reasoning_bytes": 81.074, "flops_per_problem": 4728540119.04}, "sumd.rev.cmp7": {"acc": 0.884, "reasoning_bytes": 87.472, "flops_per_problem": 5055435177.984}, "sumd.rev.cmp8": {"acc": 0.666, "reasoning_bytes": 89.474, "flops_per_problem": 5187924393.984}, "add.rev.cmp6": {"acc": 0.98, "reasoning_bytes": 156.634, "flops_per_problem": 8535661903.872}, "add.rev.cmp7": {"acc": 0.904, "reasoning_bytes": 162.984, "flops_per_problem": 8946113495.04}, "add.rev.cmp8": {"acc": 0.818, "reasoning_bytes": 180.808, "flops_per_problem": 9867001872.384}, "runmax.rev.runmax12": {"acc": 1.0, "reasoning_bytes": 99.496, "flops_per_problem": 5895593459.712}, "runmax.rev.runmax14": {"acc": 0.974, "reasoning_bytes": 106.108, "flops_per_problem": 6275925835.776}, "runmax.rev.runmax16": {"acc": 0.966, "reasoning_bytes": 114.028, "flops_per_problem": 6714023510.016}, "count.rev.runmax16": {"acc": 0.804, "reasoning_bytes": 104.24, "flops_per_problem": 6325918433.28}, "count.rev.runmax18": {"acc": 0.754, "reasoning_bytes": 112.68, "flops_per_problem": 6786980904.96}, "count.rev.runmax20": {"acc": 0.652, "reasoning_bytes": 120.31, "flops_per_problem": 7212271288.32}, "add.rev.runmax6": {"acc": 0.824, "reasoning_bytes": 164.174, "flops_per_problem": 8663646486.528}, "add.rev.runmax7": {"acc": 0.56, "reasoning_bytes": 181.722, "flops_per_problem": 9526946217.984}, "add.rev.runmax8": {"acc": 0.606, "reasoning_bytes": 212.48, "flops_per_problem": 10973816782.848}, "inc.rev.count6": {"acc": 0.852, "reasoning_bytes": 153.684, "flops_per_problem": 7935397429.248}, "inc.rev.count7": {"acc": 0.704, "reasoning_bytes": 155.96, "flops_per_problem": 8080075653.12}, "inc.rev.count8": {"acc": 0.598, "reasoning_bytes": 182.504, "flops_per_problem": 9296503308.288}, "count.rev.count16": {"acc": 0.996, "reasoning_bytes": 104.35, "flops_per_problem": 6374939443.2}, "count.rev.count18": {"acc": 0.998, "reasoning_bytes": 112.754, "flops_per_problem": 6834412044.288}, "count.rev.count20": {"acc": 0.998, "reasoning_bytes": 120.05, "flops_per_problem": 7244951961.6}, "parity.rev.count16": {"acc": 1.0, "reasoning_bytes": 121.384, "flops_per_problem": 7083050139.648}, "parity.rev.count20": {"acc": 1.0, "reasoning_bytes": 140.584, "flops_per_problem": 8107633410.048}, "parity.rev.count24": {"acc": 1.0, "reasoning_bytes": 158.076, "flops_per_problem": 9056786153.472}, "sumd.rev.find6": {"acc": 0.994, "reasoning_bytes": 85.158, "flops_per_problem": 4909078757.376}, "sumd.rev.find7": {"acc": 0.922, "reasoning_bytes": 91.712, "flops_per_problem": 5242686603.264}, "sumd.rev.find8": {"acc": 0.7, "reasoning_bytes": 94.344, "flops_per_problem": 5403086880.768}, "runmax.rev.find12": {"acc": 1.0, "reasoning_bytes": 99.676, "flops_per_problem": 5903542812.672}, "runmax.rev.find14": {"acc": 0.992, "reasoning_bytes": 106.144, "flops_per_problem": 6277515706.368}, "runmax.rev.find16": {"acc": 0.982, "reasoning_bytes": 113.44, "flops_per_problem": 6688055623.68}, "count.rev.find16": {"acc": 0.968, "reasoning_bytes": 104.3, "flops_per_problem": 6328568217.6}, "count.rev.find18": {"acc": 0.914, "reasoning_bytes": 112.32, "flops_per_problem": 6771082199.04}, "count.rev.find20": {"acc": 0.89, "reasoning_bytes": 119.41, "flops_per_problem": 7172524523.52}, "count.rev.rev16": {"acc": 0.8, "reasoning_bytes": 99.2, "flops_per_problem": 5970847334.4}, "count.rev.rev18": {"acc": 0.732, "reasoning_bytes": 107.36, "flops_per_problem": 6419544145.92}, "count.rev.rev20": {"acc": 0.634, "reasoning_bytes": 114.36, "flops_per_problem": 6817011793.92}, "sumd.rev.rev6": {"acc": 0.988, "reasoning_bytes": 80.498, "flops_per_problem": 4614864371.712}, "sumd.rev.rev7": {"acc": 0.748, "reasoning_bytes": 86.428, "flops_per_problem": 4921002786.816}, "sumd.rev.rev8": {"acc": 0.168, "reasoning_bytes": 89.108, "flops_per_problem": 5083876196.352}, "parity.rev.rev16": {"acc": 0.802, "reasoning_bytes": 114.584, "flops_per_problem": 6606088962.048}, "parity.rev.rev20": {"acc": 0.666, "reasoning_bytes": 134.54, "flops_per_problem": 7664059514.88}, "parity.rev.rev24": {"acc": 0.562, "reasoning_bytes": 152.768, "flops_per_problem": 8645716279.296}, "sumd.rev.sumd6": {"acc": 0.996, "reasoning_bytes": 84.666, "flops_per_problem": 4807945322.496}, "sumd.rev.sumd7": {"acc": 0.802, "reasoning_bytes": 90.932, "flops_per_problem": 5128745877.504}, "sumd.rev.sumd8": {"acc": 0.342, "reasoning_bytes": 94.248, "flops_per_problem": 5321208545.28}, "parity.rev.sumd16": {"acc": 0.808, "reasoning_bytes": 118.22, "flops_per_problem": 6810828963.84}, "parity.rev.sumd20": {"acc": 0.702, "reasoning_bytes": 138.308, "flops_per_problem": 7874629042.176}, "parity.rev.sumd24": {"acc": 0.592, "reasoning_bytes": 156.896, "flops_per_problem": 8872184512.512}, "add.rev.sumd6": {"acc": 0.11, "reasoning_bytes": 166.368, "flops_per_problem": 8715493933.056}, "add.rev.sumd7": {"acc": 0.022, "reasoning_bytes": 187.74, "flops_per_problem": 9748203208.704}, "add.rev.sumd8": {"acc": 0.02, "reasoning_bytes": 217.704, "flops_per_problem": 11163453014.016}, "parity.rev.inc16": {"acc": 0.78, "reasoning_bytes": 118.116, "flops_per_problem": 6762072932.352}, "parity.rev.inc20": {"acc": 0.636, "reasoning_bytes": 138.096, "flops_per_problem": 7821103398.912}, "parity.rev.inc24": {"acc": 0.554, "reasoning_bytes": 156.904, "flops_per_problem": 8828374745.088}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 98.124, "flops_per_problem": 5733691637.76}, "runmax.rev.inc14": {"acc": 0.968, "reasoning_bytes": 105.012, "flops_per_problem": 6128509501.44}, "runmax.rev.inc16": {"acc": 0.962, "reasoning_bytes": 111.432, "flops_per_problem": 6502394068.992}, "inc.rev.inc6": {"acc": 0.012, "reasoning_bytes": 142.542, "flops_per_problem": 7439092826.112}, "inc.rev.inc7": {"acc": 0.002, "reasoning_bytes": 169.05, "flops_per_problem": 8695620550.656}, "inc.rev.inc8": {"acc": 0.0, "reasoning_bytes": 197.166, "flops_per_problem": 10030493564.928}, "parity.sumd.cmp16": {"acc": 0.99, "reasoning_bytes": 123.06, "flops_per_problem": 7112904376.32}, "parity.sumd.cmp20": {"acc": 0.976, "reasoning_bytes": 141.984, "flops_per_problem": 8125298638.848}, "parity.sumd.cmp24": {"acc": 0.94, "reasoning_bytes": 159.648, "flops_per_problem": 9082047430.656}, "runmax.sumd.cmp12": {"acc": 1.0, "reasoning_bytes": 101.772, "flops_per_problem": 5996108611.584}, "runmax.sumd.cmp14": {"acc": 0.994, "reasoning_bytes": 108.18, "flops_per_problem": 6367431720.96}, "runmax.sumd.cmp16": {"acc": 0.99, "reasoning_bytes": 115.536, "flops_per_problem": 6780621422.592}, "count.sumd.cmp16": {"acc": 0.972, "reasoning_bytes": 106.49, "flops_per_problem": 6425285345.28}, "count.sumd.cmp18": {"acc": 0.938, "reasoning_bytes": 114.64, "flops_per_problem": 6873540526.08}, "count.sumd.cmp20": {"acc": 0.922, "reasoning_bytes": 121.45, "flops_per_problem": 7262617190.4}, "sumd.sumd.runmax6": {"acc": 0.98, "reasoning_bytes": 84.078, "flops_per_problem": 4905545711.616}, "sumd.sumd.runmax7": {"acc": 0.734, "reasoning_bytes": 89.796, "flops_per_problem": 5202233229.312}, "sumd.sumd.runmax8": {"acc": 0.342, "reasoning_bytes": 93.948, "flops_per_problem": 5429761376.256}, "count.sumd.runmax16": {"acc": 0.796, "reasoning_bytes": 106.75, "flops_per_problem": 6480930816.0}, "count.sumd.runmax18": {"acc": 0.746, "reasoning_bytes": 115.45, "flops_per_problem": 6953475686.4}, "count.sumd.runmax20": {"acc": 0.658, "reasoning_bytes": 122.932, "flops_per_problem": 7372229935.104}, "add.sumd.runmax6": {"acc": 0.432, "reasoning_bytes": 140.558, "flops_per_problem": 7664854450.176}, "add.sumd.runmax7": {"acc": 0.15, "reasoning_bytes": 150.726, "flops_per_problem": 8202230710.272}, "add.sumd.runmax8": {"acc": 0.17, "reasoning_bytes": 169.88, "flops_per_problem": 9136456335.36}, "parity.sumd.count16": {"acc": 1.0, "reasoning_bytes": 124.816, "flops_per_problem": 7278780874.752}, "parity.sumd.count20": {"acc": 1.0, "reasoning_bytes": 144.196, "flops_per_problem": 8311313498.112}, "parity.sumd.count24": {"acc": 1.0, "reasoning_bytes": 162.406, "flops_per_problem": 9292175327.232}, "sumd.sumd.count6": {"acc": 0.992, "reasoning_bytes": 84.096, "flops_per_problem": 4950503718.912}, "sumd.sumd.count7": {"acc": 0.85, "reasoning_bytes": 90.394, "flops_per_problem": 5272629166.08}, "sumd.sumd.count8": {"acc": 0.506, "reasoning_bytes": 93.864, "flops_per_problem": 5469596467.2}, "add.sumd.count6": {"acc": 0.778, "reasoning_bytes": 149.11, "flops_per_problem": 8086700113.92}, "add.sumd.count7": {"acc": 0.37, "reasoning_bytes": 150.032, "flops_per_problem": 8215744610.304}, "add.sumd.count8": {"acc": 0.406, "reasoning_bytes": 168.988, "flops_per_problem": 9141225947.136}, "runmax.sumd.find12": {"acc": 1.0, "reasoning_bytes": 102.568, "flops_per_problem": 6075425488.896}, "runmax.sumd.find14": {"acc": 0.99, "reasoning_bytes": 109.156, "flops_per_problem": 6454697951.232}, "runmax.sumd.find16": {"acc": 0.982, "reasoning_bytes": 116.788, "flops_per_problem": 6880076660.736}, "sumd.sumd.find6": {"acc": 0.994, "reasoning_bytes": 84.012, "flops_per_problem": 4902542622.72}, "sumd.sumd.find7": {"acc": 0.908, "reasoning_bytes": 89.678, "flops_per_problem": 5197021986.816}, "sumd.sumd.find8": {"acc": 0.786, "reasoning_bytes": 93.13, "flops_per_problem": 5393635983.36}, "parity.sumd.find16": {"acc": 0.96, "reasoning_bytes": 123.436, "flops_per_problem": 7173672763.392}, "parity.sumd.find20": {"acc": 0.944, "reasoning_bytes": 143.332, "flops_per_problem": 8228993531.904}, "parity.sumd.find24": {"acc": 0.832, "reasoning_bytes": 161.342, "flops_per_problem": 9201022746.624}, "count.sumd.rev16": {"acc": 0.81, "reasoning_bytes": 102.14, "flops_per_problem": 6144849838.08}, "count.sumd.rev18": {"acc": 0.758, "reasoning_bytes": 110.35, "flops_per_problem": 6595754803.2}, "count.sumd.rev20": {"acc": 0.648, "reasoning_bytes": 117.46, "flops_per_problem": 6998080389.12}, "parity.sumd.rev16": {"acc": 0.796, "reasoning_bytes": 118.208, "flops_per_problem": 6810299006.976}, "parity.sumd.rev20": {"acc": 0.71, "reasoning_bytes": 138.344, "flops_per_problem": 7876218912.768}, "parity.sumd.rev24": {"acc": 0.586, "reasoning_bytes": 156.846, "flops_per_problem": 8869976358.912}, "add.sumd.rev6": {"acc": 0.222, "reasoning_bytes": 130.184, "flops_per_problem": 7117762314.24}, "add.sumd.rev7": {"acc": 0.044, "reasoning_bytes": 144.826, "flops_per_problem": 7853342441.472}, "add.sumd.rev8": {"acc": 0.04, "reasoning_bytes": 163.002, "flops_per_problem": 8745524822.016}, "parity.sumd.sumd16": {"acc": 0.818, "reasoning_bytes": 121.268, "flops_per_problem": 6989601079.296}, "parity.sumd.sumd20": {"acc": 0.738, "reasoning_bytes": 141.804, "flops_per_problem": 8073186213.888}, "parity.sumd.sumd24": {"acc": 0.596, "reasoning_bytes": 160.508, "flops_per_problem": 9075864600.576}, "add.sumd.sumd6": {"acc": 0.32, "reasoning_bytes": 136.042, "flops_per_problem": 7384772247.552}, "add.sumd.sumd7": {"acc": 0.122, "reasoning_bytes": 149.206, "flops_per_problem": 8057375834.112}, "add.sumd.sumd8": {"acc": 0.09, "reasoning_bytes": 168.568, "flops_per_problem": 9000699052.032}, "count.sumd.sumd16": {"acc": 0.794, "reasoning_bytes": 104.71, "flops_per_problem": 6302512005.12}, "count.sumd.sumd18": {"acc": 0.732, "reasoning_bytes": 113.07, "flops_per_problem": 6760041431.04}, "count.sumd.sumd20": {"acc": 0.642, "reasoning_bytes": 120.29, "flops_per_problem": 7167224954.88}, "inc.sumd.inc6": {"acc": 0.268, "reasoning_bytes": 122.33, "flops_per_problem": 6462293999.616}, "inc.sumd.inc7": {"acc": 0.1, "reasoning_bytes": 134.358, "flops_per_problem": 7037650501.632}, "inc.sumd.inc8": {"acc": 0.042, "reasoning_bytes": 148.29, "flops_per_problem": 7697093492.736}, "sumd.sumd.inc6": {"acc": 0.992, "reasoning_bytes": 83.624, "flops_per_problem": 4767226970.112}, "sumd.sumd.inc7": {"acc": 0.758, "reasoning_bytes": 89.458, "flops_per_problem": 5067094228.992}, "sumd.sumd.inc8": {"acc": 0.34, "reasoning_bytes": 93.636, "flops_per_problem": 5298508726.272}, "parity.sumd.inc16": {"acc": 0.788, "reasoning_bytes": 121.56, "flops_per_problem": 6958333624.32}, "parity.sumd.inc20": {"acc": 0.688, "reasoning_bytes": 141.828, "flops_per_problem": 8030083055.616}, "parity.sumd.inc24": {"acc": 0.578, "reasoning_bytes": 160.568, "flops_per_problem": 9034351312.896}, "inc.inc.cmp6": {"acc": 0.96, "reasoning_bytes": 144.844, "flops_per_problem": 7677485088.768}, "inc.inc.cmp7": {"acc": 0.818, "reasoning_bytes": 150.404, "flops_per_problem": 8011357913.088}, "inc.inc.cmp8": {"acc": 0.884, "reasoning_bytes": 159.164, "flops_per_problem": 8486552567.808}, "runmax.inc.cmp12": {"acc": 0.98, "reasoning_bytes": 105.49, "flops_per_problem": 6147411296.256}, "runmax.inc.cmp14": {"acc": 0.974, "reasoning_bytes": 111.96, "flops_per_problem": 6525535518.72}, "runmax.inc.cmp16": {"acc": 0.956, "reasoning_bytes": 119.26, "flops_per_problem": 6937488654.336}, "sumd.inc.cmp6": {"acc": 0.972, "reasoning_bytes": 88.238, "flops_per_problem": 5044924366.848}, "sumd.inc.cmp7": {"acc": 0.976, "reasoning_bytes": 94.164, "flops_per_problem": 5350974455.808}, "sumd.inc.cmp8": {"acc": 0.94, "reasoning_bytes": 96.742, "flops_per_problem": 5508989927.424}, "sumd.inc.runmax6": {"acc": 0.978, "reasoning_bytes": 93.366, "flops_per_problem": 5271569252.352}, "sumd.inc.runmax7": {"acc": 0.696, "reasoning_bytes": 98.548, "flops_per_problem": 5544585363.456}, "sumd.inc.runmax8": {"acc": 0.308, "reasoning_bytes": 102.22, "flops_per_problem": 5750915235.84}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 108.928, "flops_per_problem": 6312139554.816}, "runmax.inc.runmax14": {"acc": 0.938, "reasoning_bytes": 116.128, "flops_per_problem": 6718439817.216}, "runmax.inc.runmax16": {"acc": 0.892, "reasoning_bytes": 123.592, "flops_per_problem": 7136399130.624}, "add.inc.runmax6": {"acc": 0.812, "reasoning_bytes": 174.476, "flops_per_problem": 9118614454.272}, "add.inc.runmax7": {"acc": 0.528, "reasoning_bytes": 190.14, "flops_per_problem": 9898887610.368}, "add.inc.runmax8": {"acc": 0.674, "reasoning_bytes": 212.584, "flops_per_problem": 10980264591.36}, "runmax.inc.count12": {"acc": 0.998, "reasoning_bytes": 108.602, "flops_per_problem": 6341905465.344}, "runmax.inc.count14": {"acc": 0.982, "reasoning_bytes": 115.308, "flops_per_problem": 6726389170.176}, "runmax.inc.count16": {"acc": 0.986, "reasoning_bytes": 123.024, "flops_per_problem": 7155477577.728}, "sumd.inc.count6": {"acc": 0.99, "reasoning_bytes": 92.35, "flops_per_problem": 5270862643.2}, "sumd.inc.count7": {"acc": 0.816, "reasoning_bytes": 98.182, "flops_per_problem": 5572584751.104}, "sumd.inc.count8": {"acc": 0.414, "reasoning_bytes": 101.108, "flops_per_problem": 5745968971.776}, "inc.inc.count6": {"acc": 0.696, "reasoning_bytes": 156.842, "flops_per_problem": 8074864410.624}, "inc.inc.count7": {"acc": 0.554, "reasoning_bytes": 164.446, "flops_per_problem": 8454931808.256}, "inc.inc.count8": {"acc": 0.538, "reasoning_bytes": 182.704, "flops_per_problem": 9305512574.976}, "parity.inc.find16": {"acc": 0.95, "reasoning_bytes": 123.032, "flops_per_problem": 7111667810.304}, "parity.inc.find20": {"acc": 0.9, "reasoning_bytes": 142.676, "flops_per_problem": 8155859484.672}, "parity.inc.find24": {"acc": 0.826, "reasoning_bytes": 161.012, "flops_per_problem": 9142285860.864}, "sumd.inc.find6": {"acc": 0.994, "reasoning_bytes": 92.048, "flops_per_problem": 5213362323.456}, "sumd.inc.find7": {"acc": 0.924, "reasoning_bytes": 97.888, "flops_per_problem": 5515437735.936}, "sumd.inc.find8": {"acc": 0.74, "reasoning_bytes": 101.056, "flops_per_problem": 5699509420.032}, "count.inc.find16": {"acc": 0.924, "reasoning_bytes": 107.9, "flops_per_problem": 6487555276.8}, "count.inc.find18": {"acc": 0.85, "reasoning_bytes": 116.1, "flops_per_problem": 6938018611.2}, "count.inc.find20": {"acc": 0.862, "reasoning_bytes": 123.08, "flops_per_problem": 7334602997.76}, "sumd.inc.rev6": {"acc": 0.982, "reasoning_bytes": 87.464, "flops_per_problem": 4922857635.84}, "sumd.inc.rev7": {"acc": 0.714, "reasoning_bytes": 93.332, "flops_per_problem": 5226257940.48}, "sumd.inc.rev8": {"acc": 0.19, "reasoning_bytes": 96.258, "flops_per_problem": 5401055379.456}, "count.inc.rev16": {"acc": 0.804, "reasoning_bytes": 102.99, "flops_per_problem": 6138225377.28}, "count.inc.rev18": {"acc": 0.742, "reasoning_bytes": 111.13, "flops_per_problem": 6586038927.36}, "count.inc.rev20": {"acc": 0.594, "reasoning_bytes": 118.06, "flops_per_problem": 6980415160.32}, "parity.inc.rev16": {"acc": 0.75, "reasoning_bytes": 117.9, "flops_per_problem": 6752533708.8}, "parity.inc.rev20": {"acc": 0.646, "reasoning_bytes": 138.084, "flops_per_problem": 7820573442.048}, "parity.inc.rev24": {"acc": 0.536, "reasoning_bytes": 156.888, "flops_per_problem": 8827668135.936}, "count.inc.sumd16": {"acc": 0.794, "reasoning_bytes": 105.9, "flops_per_problem": 6310902988.8}, "count.inc.sumd18": {"acc": 0.73, "reasoning_bytes": 114.14, "flops_per_problem": 6763132846.08}, "count.inc.sumd20": {"acc": 0.63, "reasoning_bytes": 121.34, "flops_per_problem": 7169433108.48}, "sumd.inc.sumd6": {"acc": 0.986, "reasoning_bytes": 91.578, "flops_per_problem": 5114525368.32}, "sumd.inc.sumd7": {"acc": 0.7, "reasoning_bytes": 97.154, "flops_per_problem": 5402556923.904}, "sumd.inc.sumd8": {"acc": 0.308, "reasoning_bytes": 100.872, "flops_per_problem": 5614804647.936}, "add.inc.sumd6": {"acc": 0.088, "reasoning_bytes": 173.968, "flops_per_problem": 9051221606.4}, "add.inc.sumd7": {"acc": 0.046, "reasoning_bytes": 195.858, "flops_per_problem": 10107425636.352}, "add.inc.sumd8": {"acc": 0.026, "reasoning_bytes": 217.362, "flops_per_problem": 11140488216.576}, "parity.inc.inc16": {"acc": 0.74, "reasoning_bytes": 121.588, "flops_per_problem": 6915407118.336}, "parity.inc.inc20": {"acc": 0.65, "reasoning_bytes": 141.844, "flops_per_problem": 7986626592.768}, "parity.inc.inc24": {"acc": 0.53, "reasoning_bytes": 161.128, "flops_per_problem": 9014919561.216}, "sumd.inc.inc6": {"acc": 0.972, "reasoning_bytes": 94.426, "flops_per_problem": 5230055964.672}, "sumd.inc.inc7": {"acc": 0.666, "reasoning_bytes": 99.9, "flops_per_problem": 5515967692.8}, "sumd.inc.inc8": {"acc": 0.202, "reasoning_bytes": 103.248, "flops_per_problem": 5708077056.0}, "runmax.inc.inc12": {"acc": 0.998, "reasoning_bytes": 108.9, "flops_per_problem": 6219043799.04}, "runmax.inc.inc14": {"acc": 0.966, "reasoning_bytes": 116.592, "flops_per_problem": 6647867228.16}, "runmax.inc.inc16": {"acc": 0.946, "reasoning_bytes": 123.264, "flops_per_problem": 7031909302.272}, "count.inc.cmp16": {"acc": 0.958, "reasoning_bytes": 107.452, "flops_per_problem": 6423607148.544}, "count.inc.cmp18": {"acc": 0.926, "reasoning_bytes": 115.53, "flops_per_problem": 6868859240.448}, "count.inc.cmp20": {"acc": 0.894, "reasoning_bytes": 122.22, "flops_per_problem": 7252901314.56}, "inc.rev.sumd6": {"acc": 0.166, "reasoning_bytes": 149.97, "flops_per_problem": 7682961309.696}, "inc.rev.sumd7": {"acc": 0.088, "reasoning_bytes": 165.798, "flops_per_problem": 8426490789.888}, "inc.rev.sumd8": {"acc": 0.024, "reasoning_bytes": 191.736, "flops_per_problem": 9618010472.448}, "runmax.inc.find12": {"acc": 1.0, "reasoning_bytes": 108.476, "flops_per_problem": 6292177846.272}, "runmax.inc.find14": {"acc": 0.99, "reasoning_bytes": 115.464, "flops_per_problem": 6689115537.408}, "runmax.inc.find16": {"acc": 0.97, "reasoning_bytes": 122.408, "flops_per_problem": 7084110053.376}, "inc.runmax.cmp6": {"acc": 0.992, "reasoning_bytes": 115.328, "flops_per_problem": 6285641711.616}, "inc.runmax.cmp7": {"acc": 0.958, "reasoning_bytes": 119.184, "flops_per_problem": 6500097589.248}, "inc.runmax.cmp8": {"acc": 0.934, "reasoning_bytes": 130.504, "flops_per_problem": 7044186636.288}} +{"step": 5000, "train_loss": 1.1068007946014404} +{"step": 5020, "train_loss": 1.1899383068084717} +{"step": 5040, "train_loss": 1.1584742069244385} +{"step": 5060, "train_loss": 1.1449004411697388} +{"step": 5080, "train_loss": 1.0808378458023071} +{"step": 5100, "train_loss": 0.9514567852020264} +{"step": 5120, "train_loss": 1.1146796941757202} +{"step": 5140, "train_loss": 1.1041148900985718} +{"step": 5160, "train_loss": 1.1175826787948608} +{"step": 5180, "train_loss": 1.0287680625915527} +{"step": 5200, "train_loss": 1.1272556781768799} +{"step": 5220, "train_loss": 1.106780767440796} +{"step": 5240, "train_loss": 1.0500175952911377} +{"step": 5260, "train_loss": 1.045301914215088} +{"step": 5280, "train_loss": 1.1286462545394897} +{"step": 5300, "train_loss": 1.172940969467163} +{"step": 5320, "train_loss": 1.1036207675933838} +{"step": 5340, "train_loss": 0.9767823815345764} +{"step": 5360, "train_loss": 1.0826821327209473} +{"step": 5380, "train_loss": 1.050924301147461} +{"step": 5400, "train_loss": 1.0271813869476318} +{"step": 5420, "train_loss": 1.0632436275482178} +{"step": 5440, "train_loss": 1.0967442989349365} +{"step": 5460, "train_loss": 1.0798677206039429} +{"step": 5480, "train_loss": 1.0505776405334473} +{"step": 5500, "train_loss": 1.0470576286315918} +{"step": 5520, "train_loss": 1.086360216140747} +{"step": 5540, "train_loss": 1.0878551006317139} +{"step": 5560, "train_loss": 1.113328456878662} +{"step": 5580, "train_loss": 1.077436089515686} +{"step": 5600, "train_loss": 1.0906603336334229} +{"step": 5620, "train_loss": 1.0714956521987915} +{"step": 5640, "train_loss": 1.0852714776992798} +{"step": 5660, "train_loss": 1.0546960830688477} +{"step": 5680, "train_loss": 1.111001968383789} +{"step": 5700, "train_loss": 1.111117959022522} +{"step": 5720, "train_loss": 1.1575101613998413} +{"step": 5740, "train_loss": 1.0661569833755493} +{"step": 5760, "train_loss": 0.9991796612739563} +{"step": 5780, "train_loss": 1.0554323196411133} +{"step": 5800, "train_loss": 1.081543207168579} +{"step": 5820, "train_loss": 1.0341172218322754} +{"step": 5840, "train_loss": 1.0139468908309937} +{"step": 5860, "train_loss": 1.1041347980499268} +{"step": 5880, "train_loss": 1.1136376857757568} +{"step": 5900, "train_loss": 0.9900268316268921} +{"step": 5920, "train_loss": 1.0771279335021973} +{"step": 5940, "train_loss": 1.0269464254379272} +{"step": 5960, "train_loss": 1.083235740661621} +{"step": 5980, "train_loss": 1.0286865234375} +{"step": 6000, "tokens": 196608000, "val_loss": 1.9747610211372375, "val_bpb": 0.7118692656479066, "lr": 0.0003459796115961056, "elapsed": 1921.9935388565063, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.114, "reasoning_bytes": 79.964, "flops_per_problem": 4949178826.752}, "add9": {"acc": 0.004, "reasoning_bytes": 89.212, "flops_per_problem": 5492914569.216}, "add10": {"acc": 0.0, "reasoning_bytes": 97.952, "flops_per_problem": 6011300708.352}, "reach14": {"acc": 0.466, "reasoning_bytes": 10.802, "flops_per_problem": 4927008964.608}, "reach16": {"acc": 0.334, "reasoning_bytes": 9.27, "flops_per_problem": 5638122749.952}, "reach18": {"acc": 0.272, "reasoning_bytes": 9.426, "flops_per_problem": 6281755361.28}, "parity24": {"acc": 0.162, "reasoning_bytes": 147.708, "flops_per_problem": 8154534592.512}, "parity28": {"acc": 0.138, "reasoning_bytes": 171.042, "flops_per_problem": 9323707760.64}, "parity32": {"acc": 0.036, "reasoning_bytes": 195.804, "flops_per_problem": 10627843276.8}, "cmp8": {"acc": 0.968, "reasoning_bytes": 5.832, "flops_per_problem": 1362165792.768}, "cmp9": {"acc": 0.982, "reasoning_bytes": 5.712, "flops_per_problem": 1444662411.264}, "cmp10": {"acc": 0.962, "reasoning_bytes": 5.668, "flops_per_problem": 1531045380.096}, "runmax12": {"acc": 1.0, "reasoning_bytes": 71.012, "flops_per_problem": 4151858724.864}, "runmax14": {"acc": 0.992, "reasoning_bytes": 82.976, "flops_per_problem": 4768551862.272}, "runmax16": {"acc": 0.96, "reasoning_bytes": 93.152, "flops_per_problem": 5306193100.8}, "count16": {"acc": 0.924, "reasoning_bytes": 79.08, "flops_per_problem": 4728981749.76}, "count18": {"acc": 0.768, "reasoning_bytes": 89.154, "flops_per_problem": 5281373454.336}, "count20": {"acc": 0.318, "reasoning_bytes": 101.548, "flops_per_problem": 5984007929.856}, "brackets16": {"acc": 0.868, "reasoning_bytes": 55.72, "flops_per_problem": 3741495459.84}, "brackets18": {"acc": 0.878, "reasoning_bytes": 56.178, "flops_per_problem": 3850048290.816}, "brackets20": {"acc": 0.872, "reasoning_bytes": 58.15, "flops_per_problem": 4025464012.8}, "sumd8": {"acc": 0.734, "reasoning_bytes": 58.616, "flops_per_problem": 3382979641.344}, "sumd9": {"acc": 0.422, "reasoning_bytes": 66.488, "flops_per_problem": 3777267548.16}, "sumd10": {"acc": 0.164, "reasoning_bytes": 74.06, "flops_per_problem": 4158218207.232}, "inc8": {"acc": 0.44, "reasoning_bytes": 63.026, "flops_per_problem": 3776207634.432}, "inc9": {"acc": 0.06, "reasoning_bytes": 71.0, "flops_per_problem": 4203352866.816}, "inc10": {"acc": 0.002, "reasoning_bytes": 78.588, "flops_per_problem": 4625816813.568}, "add.cmp6": {"acc": 0.996, "reasoning_bytes": 92.608, "flops_per_problem": 5531689746.432}, "add.cmp7": {"acc": 0.986, "reasoning_bytes": 105.884, "flops_per_problem": 6247396491.264}, "add.cmp8": {"acc": 0.962, "reasoning_bytes": 118.204, "flops_per_problem": 6925564624.896}, "add.runmax6": {"acc": 0.99, "reasoning_bytes": 120.31, "flops_per_problem": 6549825208.32}, "add.runmax7": {"acc": 0.848, "reasoning_bytes": 137.886, "flops_per_problem": 7414361505.792}, "add.runmax8": {"acc": 0.65, "reasoning_bytes": 155.422, "flops_per_problem": 8277131280.384}, "add.count6": {"acc": 0.89, "reasoning_bytes": 115.278, "flops_per_problem": 6372201332.736}, "add.count7": {"acc": 0.644, "reasoning_bytes": 130.83, "flops_per_problem": 7146909941.76}, "add.count8": {"acc": 0.374, "reasoning_bytes": 146.998, "flops_per_problem": 7949264633.856}, "add.find6": {"acc": 0.662, "reasoning_bytes": 110.086, "flops_per_problem": 6098301960.192}, "add.find7": {"acc": 0.536, "reasoning_bytes": 125.978, "flops_per_problem": 6888202665.984}, "add.find8": {"acc": 0.37, "reasoning_bytes": 142.632, "flops_per_problem": 7712197263.36}, "add.rev6": {"acc": 0.74, "reasoning_bytes": 122.568, "flops_per_problem": 6764192759.808}, "add.rev7": {"acc": 0.156, "reasoning_bytes": 143.418, "flops_per_problem": 7815538851.84}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 161.316, "flops_per_problem": 8721853415.424}, "add.sumd6": {"acc": 0.724, "reasoning_bytes": 126.094, "flops_per_problem": 6761013018.624}, "add.sumd7": {"acc": 0.306, "reasoning_bytes": 145.666, "flops_per_problem": 7713787133.952}, "add.sumd8": {"acc": 0.048, "reasoning_bytes": 164.148, "flops_per_problem": 8618335174.656}, "add.inc6": {"acc": 0.122, "reasoning_bytes": 129.962, "flops_per_problem": 7083403444.224}, "add.inc7": {"acc": 0.002, "reasoning_bytes": 148.474, "flops_per_problem": 8025931726.848}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 164.65, "flops_per_problem": 8866090008.576}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5122916352.0}, "runmax.cmp14": {"acc": 0.962, "reasoning_bytes": 98.964, "flops_per_problem": 5739609489.408}, "runmax.cmp16": {"acc": 0.87, "reasoning_bytes": 107.784, "flops_per_problem": 6217453928.448}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.runmax14": {"acc": 0.996, "reasoning_bytes": 100.0, "flops_per_problem": 5829525504.0}, "runmax.runmax16": {"acc": 0.94, "reasoning_bytes": 109.828, "flops_per_problem": 6351886319.616}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5255405568.0}, "runmax.count14": {"acc": 0.956, "reasoning_bytes": 100.0, "flops_per_problem": 5873688576.0}, "runmax.count16": {"acc": 0.828, "reasoning_bytes": 108.94, "flops_per_problem": 6356832583.68}, "runmax.find12": {"acc": 0.946, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.find14": {"acc": 0.872, "reasoning_bytes": 99.988, "flops_per_problem": 5828995547.136}, "runmax.find16": {"acc": 0.774, "reasoning_bytes": 109.852, "flops_per_problem": 6352946233.344}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 83.0, "flops_per_problem": 4857937920.0}, "runmax.rev14": {"acc": 0.994, "reasoning_bytes": 94.988, "flops_per_problem": 5475690971.136}, "runmax.rev16": {"acc": 0.936, "reasoning_bytes": 105.092, "flops_per_problem": 6010240794.624}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 86.0, "flops_per_problem": 5034590208.0}, "runmax.sumd14": {"acc": 0.994, "reasoning_bytes": 97.988, "flops_per_problem": 5652343259.136}, "runmax.sumd16": {"acc": 0.934, "reasoning_bytes": 107.808, "flops_per_problem": 6174350770.176}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5065769336.832}, "runmax.inc14": {"acc": 0.992, "reasoning_bytes": 98.988, "flops_per_problem": 5686525476.864}, "runmax.inc16": {"acc": 0.936, "reasoning_bytes": 110.12, "flops_per_problem": 6266651590.656}, "count.cmp16": {"acc": 0.968, "reasoning_bytes": 95.016, "flops_per_problem": 5697742897.152}, "count.cmp18": {"acc": 0.834, "reasoning_bytes": 104.762, "flops_per_problem": 6216570667.008}, "count.cmp20": {"acc": 0.448, "reasoning_bytes": 113.668, "flops_per_problem": 6698389782.528}, "count.runmax16": {"acc": 0.956, "reasoning_bytes": 95.99, "flops_per_problem": 5784920801.28}, "count.runmax18": {"acc": 0.872, "reasoning_bytes": 105.554, "flops_per_problem": 6295622565.888}, "count.runmax20": {"acc": 0.682, "reasoning_bytes": 114.472, "flops_per_problem": 6777794985.984}, "count.count16": {"acc": 1.0, "reasoning_bytes": 96.03, "flops_per_problem": 5830850396.16}, "count.count18": {"acc": 0.998, "reasoning_bytes": 105.844, "flops_per_problem": 6352592928.768}, "count.count20": {"acc": 0.97, "reasoning_bytes": 115.188, "flops_per_problem": 6853578817.536}, "count.find16": {"acc": 0.94, "reasoning_bytes": 96.04, "flops_per_problem": 5787128954.88}, "count.find18": {"acc": 0.886, "reasoning_bytes": 105.874, "flops_per_problem": 6309754748.928}, "count.find20": {"acc": 0.858, "reasoning_bytes": 114.866, "flops_per_problem": 6794665279.488}, "count.rev16": {"acc": 0.958, "reasoning_bytes": 91.0, "flops_per_problem": 5432057856.0}, "count.rev18": {"acc": 0.868, "reasoning_bytes": 100.632, "flops_per_problem": 5945762709.504}, "count.rev20": {"acc": 0.644, "reasoning_bytes": 109.554, "flops_per_problem": 6427846803.456}, "count.sumd16": {"acc": 0.96, "reasoning_bytes": 94.01, "flops_per_problem": 5609151774.72}, "count.sumd18": {"acc": 0.866, "reasoning_bytes": 103.664, "flops_per_problem": 6123828215.808}, "count.sumd20": {"acc": 0.666, "reasoning_bytes": 112.288, "flops_per_problem": 6592751714.304}, "count.inc16": {"acc": 0.954, "reasoning_bytes": 95.09, "flops_per_problem": 5612684820.48}, "count.inc18": {"acc": 0.86, "reasoning_bytes": 104.83, "flops_per_problem": 6131159285.76}, "count.inc20": {"acc": 0.66, "reasoning_bytes": 114.234, "flops_per_problem": 6632940109.824}, "parity.cmp16": {"acc": 0.994, "reasoning_bytes": 111.864, "flops_per_problem": 6397639262.208}, "parity.cmp20": {"acc": 0.964, "reasoning_bytes": 137.508, "flops_per_problem": 7706809368.576}, "parity.cmp24": {"acc": 0.93, "reasoning_bytes": 160.618, "flops_per_problem": 8912726212.608}, "parity.runmax16": {"acc": 0.946, "reasoning_bytes": 112.876, "flops_per_problem": 6486495363.072}, "parity.runmax20": {"acc": 0.646, "reasoning_bytes": 138.652, "flops_per_problem": 7801494994.944}, "parity.runmax24": {"acc": 0.466, "reasoning_bytes": 160.832, "flops_per_problem": 8983122149.376}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 113.548, "flops_per_problem": 6560336019.456}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 139.048, "flops_per_problem": 7863146643.456}, "parity.count24": {"acc": 0.972, "reasoning_bytes": 160.384, "flops_per_problem": 8996901027.84}, "parity.find16": {"acc": 0.982, "reasoning_bytes": 113.056, "flops_per_problem": 6494444716.032}, "parity.find20": {"acc": 0.918, "reasoning_bytes": 138.808, "flops_per_problem": 7808384434.176}, "parity.find24": {"acc": 0.884, "reasoning_bytes": 160.7, "flops_per_problem": 8958037524.48}, "parity.rev16": {"acc": 0.83, "reasoning_bytes": 109.4, "flops_per_problem": 6200495308.8}, "parity.rev20": {"acc": 0.58, "reasoning_bytes": 135.152, "flops_per_problem": 7514435026.944}, "parity.rev24": {"acc": 0.37, "reasoning_bytes": 155.7, "flops_per_problem": 8656668721.152}, "parity.sumd16": {"acc": 0.888, "reasoning_bytes": 111.908, "flops_per_problem": 6355419365.376}, "parity.sumd20": {"acc": 0.632, "reasoning_bytes": 137.312, "flops_per_problem": 7653990334.464}, "parity.sumd24": {"acc": 0.432, "reasoning_bytes": 158.286, "flops_per_problem": 8833762639.872}, "parity.inc16": {"acc": 0.812, "reasoning_bytes": 113.592, "flops_per_problem": 6385626906.624}, "parity.inc20": {"acc": 0.5, "reasoning_bytes": 140.468, "flops_per_problem": 7748234330.112}, "parity.inc24": {"acc": 0.4, "reasoning_bytes": 161.896, "flops_per_problem": 8862910267.392}, "sumd.cmp6": {"acc": 0.982, "reasoning_bytes": 62.08, "flops_per_problem": 3713054441.472}, "sumd.cmp7": {"acc": 0.982, "reasoning_bytes": 69.836, "flops_per_problem": 4099922952.192}, "sumd.cmp8": {"acc": 0.948, "reasoning_bytes": 77.06, "flops_per_problem": 4463031730.176}, "sumd.runmax6": {"acc": 0.996, "reasoning_bytes": 67.474, "flops_per_problem": 3951446704.128}, "sumd.runmax7": {"acc": 0.952, "reasoning_bytes": 75.214, "flops_per_problem": 4337431953.408}, "sumd.runmax8": {"acc": 0.778, "reasoning_bytes": 82.048, "flops_per_problem": 4683493785.6}, "sumd.count6": {"acc": 0.992, "reasoning_bytes": 66.426, "flops_per_problem": 3949326876.672}, "sumd.count7": {"acc": 0.952, "reasoning_bytes": 74.278, "flops_per_problem": 4340258390.016}, "sumd.count8": {"acc": 0.794, "reasoning_bytes": 82.084, "flops_per_problem": 4730394968.064}, "sumd.find6": {"acc": 0.974, "reasoning_bytes": 66.22, "flops_per_problem": 3896066211.84}, "sumd.find7": {"acc": 0.922, "reasoning_bytes": 74.468, "flops_per_problem": 4304486301.696}, "sumd.find8": {"acc": 0.804, "reasoning_bytes": 81.448, "flops_per_problem": 4657790877.696}, "sumd.rev6": {"acc": 0.982, "reasoning_bytes": 61.544, "flops_per_problem": 3600880238.592}, "sumd.rev7": {"acc": 0.912, "reasoning_bytes": 69.498, "flops_per_problem": 3996228059.136}, "sumd.rev8": {"acc": 0.728, "reasoning_bytes": 77.564, "flops_per_problem": 4395197251.584}, "sumd.sumd6": {"acc": 0.992, "reasoning_bytes": 65.748, "flops_per_problem": 3795816038.4}, "sumd.sumd7": {"acc": 0.922, "reasoning_bytes": 73.612, "flops_per_problem": 4189397336.064}, "sumd.sumd8": {"acc": 0.652, "reasoning_bytes": 80.926, "flops_per_problem": 4555155898.368}, "sumd.inc6": {"acc": 0.984, "reasoning_bytes": 68.502, "flops_per_problem": 3908255219.712}, "sumd.inc7": {"acc": 0.916, "reasoning_bytes": 76.298, "flops_per_problem": 4296095318.016}, "sumd.inc8": {"acc": 0.664, "reasoning_bytes": 83.864, "flops_per_problem": 4672982974.464}, "inc.cmp6": {"acc": 0.982, "reasoning_bytes": 78.492, "flops_per_problem": 4570524647.424}, "inc.cmp7": {"acc": 0.922, "reasoning_bytes": 89.214, "flops_per_problem": 5132367249.408}, "inc.cmp8": {"acc": 0.824, "reasoning_bytes": 99.462, "flops_per_problem": 5673276555.264}, "inc.runmax6": {"acc": 0.998, "reasoning_bytes": 103.888, "flops_per_problem": 5515437735.936}, "inc.runmax7": {"acc": 0.98, "reasoning_bytes": 118.704, "flops_per_problem": 6213920882.688}, "inc.runmax8": {"acc": 0.814, "reasoning_bytes": 129.966, "flops_per_problem": 6755448471.552}, "inc.count6": {"acc": 0.948, "reasoning_bytes": 98.958, "flops_per_problem": 5341876862.976}, "inc.count7": {"acc": 0.794, "reasoning_bytes": 112.996, "flops_per_problem": 6006001139.712}, "inc.count8": {"acc": 0.578, "reasoning_bytes": 122.498, "flops_per_problem": 6469801721.856}, "inc.find6": {"acc": 0.706, "reasoning_bytes": 92.45, "flops_per_problem": 5010300518.4}, "inc.find7": {"acc": 0.658, "reasoning_bytes": 104.648, "flops_per_problem": 5593164742.656}, "inc.find8": {"acc": 0.454, "reasoning_bytes": 115.544, "flops_per_problem": 6118351994.88}, "inc.rev6": {"acc": 0.884, "reasoning_bytes": 104.1, "flops_per_problem": 5612861472.768}, "inc.rev7": {"acc": 0.534, "reasoning_bytes": 123.35, "flops_per_problem": 6549030273.024}, "inc.rev8": {"acc": 0.002, "reasoning_bytes": 134.294, "flops_per_problem": 7083580096.512}, "inc.sumd6": {"acc": 0.87, "reasoning_bytes": 109.51, "flops_per_problem": 5719471128.576}, "inc.sumd7": {"acc": 0.572, "reasoning_bytes": 126.7, "flops_per_problem": 6523239038.976}, "inc.sumd8": {"acc": 0.086, "reasoning_bytes": 140.154, "flops_per_problem": 7161130450.944}, "inc.inc6": {"acc": 0.528, "reasoning_bytes": 112.932, "flops_per_problem": 5998405091.328}, "inc.inc7": {"acc": 0.044, "reasoning_bytes": 129.69, "flops_per_problem": 6816835141.632}, "inc.inc8": {"acc": 0.004, "reasoning_bytes": 141.32, "flops_per_problem": 7397579538.432}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 115.988, "flops_per_problem": 6800583131.136}, "runmax.runmax.cmp16": {"acc": 0.982, "reasoning_bytes": 125.144, "flops_per_problem": 7293266362.368}, "sumd.runmax.cmp6": {"acc": 0.99, "reasoning_bytes": 83.234, "flops_per_problem": 4912435150.848}, "sumd.runmax.cmp7": {"acc": 0.954, "reasoning_bytes": 90.444, "flops_per_problem": 5275013971.968}, "sumd.runmax.cmp8": {"acc": 0.812, "reasoning_bytes": 96.282, "flops_per_problem": 5577001058.304}, "add.runmax.cmp6": {"acc": 0.996, "reasoning_bytes": 136.5, "flops_per_problem": 7529803776.0}, "add.runmax.cmp7": {"acc": 0.936, "reasoning_bytes": 153.154, "flops_per_problem": 8353621721.088}, "add.runmax.cmp8": {"acc": 0.886, "reasoning_bytes": 165.662, "flops_per_problem": 8994339569.664}, "count.runmax.runmax16": {"acc": 0.958, "reasoning_bytes": 112.77, "flops_per_problem": 6835118653.44}, "count.runmax.runmax18": {"acc": 0.88, "reasoning_bytes": 121.81, "flops_per_problem": 7322678968.32}, "count.runmax.runmax20": {"acc": 0.718, "reasoning_bytes": 129.74, "flops_per_problem": 7761218273.28}, "add.runmax.runmax6": {"acc": 0.994, "reasoning_bytes": 137.304, "flops_per_problem": 7609473957.888}, "add.runmax.runmax7": {"acc": 0.884, "reasoning_bytes": 155.062, "flops_per_problem": 8482047934.464}, "add.runmax.runmax8": {"acc": 0.594, "reasoning_bytes": 171.796, "flops_per_problem": 9309398925.312}, "parity.runmax.runmax16": {"acc": 0.976, "reasoning_bytes": 129.0, "flops_per_problem": 7507722240.0}, "parity.runmax.runmax20": {"acc": 0.73, "reasoning_bytes": 151.584, "flops_per_problem": 8681753346.048}, "parity.runmax.runmax24": {"acc": 0.522, "reasoning_bytes": 174.548, "flops_per_problem": 9872566419.456}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 129.156, "flops_per_problem": 7558774751.232}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 154.868, "flops_per_problem": 8870947946.496}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 174.7, "flops_per_problem": 9923442278.4}, "inc.runmax.count6": {"acc": 1.0, "reasoning_bytes": 120.952, "flops_per_problem": 6622340972.544}, "inc.runmax.count7": {"acc": 0.998, "reasoning_bytes": 135.944, "flops_per_problem": 7328596819.968}, "inc.runmax.count8": {"acc": 0.99, "reasoning_bytes": 144.882, "flops_per_problem": 7767489429.504}, "sumd.runmax.count6": {"acc": 0.988, "reasoning_bytes": 84.38, "flops_per_problem": 5051372175.36}, "sumd.runmax.count7": {"acc": 0.966, "reasoning_bytes": 91.926, "flops_per_problem": 5428789788.672}, "sumd.runmax.count8": {"acc": 0.862, "reasoning_bytes": 98.56, "flops_per_problem": 5765754028.032}, "runmax.runmax.find12": {"acc": 0.99, "reasoning_bytes": 105.0, "flops_per_problem": 6271156224.0}, "runmax.runmax.find14": {"acc": 0.926, "reasoning_bytes": 116.964, "flops_per_problem": 6887849361.408}, "runmax.runmax.find16": {"acc": 0.904, "reasoning_bytes": 126.708, "flops_per_problem": 7406500478.976}, "add.runmax.find6": {"acc": 0.996, "reasoning_bytes": 137.572, "flops_per_problem": 7621309661.184}, "add.runmax.find7": {"acc": 0.962, "reasoning_bytes": 154.438, "flops_per_problem": 8454490177.536}, "add.runmax.find8": {"acc": 0.87, "reasoning_bytes": 171.026, "flops_per_problem": 9275305033.728}, "parity.runmax.find16": {"acc": 0.998, "reasoning_bytes": 129.036, "flops_per_problem": 7509312110.592}, "parity.runmax.find20": {"acc": 0.924, "reasoning_bytes": 154.356, "flops_per_problem": 8804173381.632}, "parity.runmax.find24": {"acc": 0.878, "reasoning_bytes": 174.432, "flops_per_problem": 9867443503.104}, "add.runmax.rev6": {"acc": 0.996, "reasoning_bytes": 132.266, "flops_per_problem": 7254491185.152}, "add.runmax.rev7": {"acc": 0.878, "reasoning_bytes": 149.734, "flops_per_problem": 8114257870.848}, "add.runmax.rev8": {"acc": 0.568, "reasoning_bytes": 166.232, "flops_per_problem": 8931186376.704}, "parity.runmax.rev16": {"acc": 0.982, "reasoning_bytes": 124.12, "flops_per_problem": 7159717232.64}, "parity.runmax.rev20": {"acc": 0.676, "reasoning_bytes": 149.836, "flops_per_problem": 8472067080.192}, "parity.runmax.rev24": {"acc": 0.518, "reasoning_bytes": 171.044, "flops_per_problem": 9585329799.168}, "sumd.runmax.rev6": {"acc": 0.998, "reasoning_bytes": 79.528, "flops_per_problem": 4660440662.016}, "sumd.runmax.rev7": {"acc": 0.952, "reasoning_bytes": 87.35, "flops_per_problem": 5050047283.2}, "sumd.runmax.rev8": {"acc": 0.816, "reasoning_bytes": 94.52, "flops_per_problem": 5410859581.44}, "sumd.runmax.sumd6": {"acc": 0.998, "reasoning_bytes": 82.502, "flops_per_problem": 4835944710.144}, "sumd.runmax.sumd7": {"acc": 0.954, "reasoning_bytes": 90.158, "flops_per_problem": 5218220261.376}, "sumd.runmax.sumd8": {"acc": 0.788, "reasoning_bytes": 96.702, "flops_per_problem": 5551386476.544}, "add.runmax.sumd6": {"acc": 0.992, "reasoning_bytes": 135.392, "flops_per_problem": 7436708020.224}, "add.runmax.sumd7": {"acc": 0.898, "reasoning_bytes": 153.172, "flops_per_problem": 8310253584.384}, "add.runmax.sumd8": {"acc": 0.598, "reasoning_bytes": 170.198, "flops_per_problem": 9150500192.256}, "parity.runmax.sumd16": {"acc": 0.978, "reasoning_bytes": 127.012, "flops_per_problem": 7331599908.864}, "parity.runmax.sumd20": {"acc": 0.672, "reasoning_bytes": 149.444, "flops_per_problem": 8513757020.16}, "parity.runmax.sumd24": {"acc": 0.522, "reasoning_bytes": 173.616, "flops_per_problem": 9750499688.448}, "count.runmax.inc16": {"acc": 0.956, "reasoning_bytes": 112.0, "flops_per_problem": 6668623872.0}, "count.runmax.inc18": {"acc": 0.864, "reasoning_bytes": 121.206, "flops_per_problem": 7163515256.832}, "count.runmax.inc20": {"acc": 0.686, "reasoning_bytes": 129.492, "flops_per_problem": 7616805027.84}, "runmax.runmax.inc12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6125683064.832}, "runmax.runmax.inc14": {"acc": 0.996, "reasoning_bytes": 116.0, "flops_per_problem": 6747145814.016}, "runmax.runmax.inc16": {"acc": 0.946, "reasoning_bytes": 126.352, "flops_per_problem": 7293089710.08}, "add.runmax.inc6": {"acc": 0.996, "reasoning_bytes": 136.36, "flops_per_problem": 7456228098.048}, "add.runmax.inc7": {"acc": 0.84, "reasoning_bytes": 153.924, "flops_per_problem": 8320499417.088}, "add.runmax.inc8": {"acc": 0.52, "reasoning_bytes": 170.842, "flops_per_problem": 9154298216.448}, "count.count.cmp16": {"acc": 0.974, "reasoning_bytes": 111.698, "flops_per_problem": 6787775840.256}, "count.count.cmp18": {"acc": 0.706, "reasoning_bytes": 117.248, "flops_per_problem": 7121207033.856}, "count.count.cmp20": {"acc": 0.342, "reasoning_bytes": 120.612, "flops_per_problem": 7358097752.064}, "add.count.cmp6": {"acc": 0.968, "reasoning_bytes": 130.932, "flops_per_problem": 7328066863.104}, "add.count.cmp7": {"acc": 0.888, "reasoning_bytes": 146.562, "flops_per_problem": 8106661822.464}, "add.count.cmp8": {"acc": 0.808, "reasoning_bytes": 158.968, "flops_per_problem": 8742875037.696}, "sumd.count.cmp6": {"acc": 0.998, "reasoning_bytes": 82.496, "flops_per_problem": 4924005875.712}, "sumd.count.cmp7": {"acc": 0.996, "reasoning_bytes": 90.414, "flops_per_problem": 5317852151.808}, "sumd.count.cmp8": {"acc": 0.962, "reasoning_bytes": 96.162, "flops_per_problem": 5615864561.664}, "add.count.runmax6": {"acc": 0.898, "reasoning_bytes": 132.308, "flops_per_problem": 7432821669.888}, "add.count.runmax7": {"acc": 0.698, "reasoning_bytes": 147.808, "flops_per_problem": 8205852082.176}, "add.count.runmax8": {"acc": 0.344, "reasoning_bytes": 162.832, "flops_per_problem": 8957684219.904}, "sumd.count.runmax6": {"acc": 0.994, "reasoning_bytes": 83.428, "flops_per_problem": 5009328930.816}, "sumd.count.runmax7": {"acc": 0.972, "reasoning_bytes": 91.39, "flops_per_problem": 5405118382.08}, "sumd.count.runmax8": {"acc": 0.874, "reasoning_bytes": 99.09, "flops_per_problem": 5789337108.48}, "inc.count.runmax6": {"acc": 0.936, "reasoning_bytes": 115.972, "flops_per_problem": 6402408873.984}, "inc.count.runmax7": {"acc": 0.734, "reasoning_bytes": 129.864, "flops_per_problem": 7060085342.208}, "inc.count.runmax8": {"acc": 0.616, "reasoning_bytes": 135.576, "flops_per_problem": 7356507881.472}, "parity.count.count16": {"acc": 1.0, "reasoning_bytes": 129.492, "flops_per_problem": 7617776615.424}, "parity.count.count20": {"acc": 1.0, "reasoning_bytes": 151.88, "flops_per_problem": 8783151759.36}, "parity.count.count24": {"acc": 1.0, "reasoning_bytes": 174.364, "flops_per_problem": 9952766558.208}, "runmax.count.count12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6359482368.0}, "runmax.count.count14": {"acc": 1.0, "reasoning_bytes": 117.0, "flops_per_problem": 6977765376.0}, "runmax.count.count16": {"acc": 1.0, "reasoning_bytes": 125.77, "flops_per_problem": 7453401661.44}, "inc.count.count6": {"acc": 0.98, "reasoning_bytes": 115.97, "flops_per_problem": 6446483619.84}, "inc.count.count7": {"acc": 0.902, "reasoning_bytes": 129.906, "flops_per_problem": 7106103263.232}, "inc.count.count8": {"acc": 0.842, "reasoning_bytes": 134.672, "flops_per_problem": 7360747536.384}, "inc.count.find6": {"acc": 0.946, "reasoning_bytes": 115.958, "flops_per_problem": 6401790590.976}, "inc.count.find7": {"acc": 0.9, "reasoning_bytes": 130.242, "flops_per_problem": 7076778983.424}, "inc.count.find8": {"acc": 0.854, "reasoning_bytes": 134.316, "flops_per_problem": 7300862410.752}, "add.count.find6": {"acc": 0.944, "reasoning_bytes": 132.052, "flops_per_problem": 7421692575.744}, "add.count.find7": {"acc": 0.874, "reasoning_bytes": 147.87, "flops_per_problem": 8208590192.64}, "add.count.find8": {"acc": 0.806, "reasoning_bytes": 163.134, "flops_per_problem": 8971021467.648}, "runmax.count.find12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6315319296.0}, "runmax.count.find14": {"acc": 1.0, "reasoning_bytes": 116.976, "flops_per_problem": 6932542390.272}, "runmax.count.find16": {"acc": 0.958, "reasoning_bytes": 125.912, "flops_per_problem": 7415509745.664}, "parity.count.rev16": {"acc": 1.0, "reasoning_bytes": 125.068, "flops_per_problem": 7245746896.896}, "parity.count.rev20": {"acc": 1.0, "reasoning_bytes": 150.712, "flops_per_problem": 8554917003.264}, "parity.count.rev24": {"acc": 0.996, "reasoning_bytes": 171.958, "flops_per_problem": 9669857918.976}, "inc.count.rev6": {"acc": 0.958, "reasoning_bytes": 110.986, "flops_per_problem": 6049722580.992}, "inc.count.rev7": {"acc": 0.808, "reasoning_bytes": 125.144, "flops_per_problem": 6719146426.368}, "inc.count.rev8": {"acc": 0.642, "reasoning_bytes": 130.434, "flops_per_problem": 6996932149.248}, "runmax.count.rev12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5962014720.0}, "runmax.count.rev14": {"acc": 0.998, "reasoning_bytes": 112.0, "flops_per_problem": 6580297728.0}, "runmax.count.rev16": {"acc": 0.928, "reasoning_bytes": 121.656, "flops_per_problem": 7095062495.232}, "count.count.sumd16": {"acc": 1.0, "reasoning_bytes": 109.91, "flops_per_problem": 6664649195.52}, "count.count.sumd18": {"acc": 0.996, "reasoning_bytes": 114.208, "flops_per_problem": 6942788222.976}, "count.count.sumd20": {"acc": 0.96, "reasoning_bytes": 121.126, "flops_per_problem": 7336634499.072}, "runmax.count.sumd12": {"acc": 1.0, "reasoning_bytes": 103.0, "flops_per_problem": 6138667008.0}, "runmax.count.sumd14": {"acc": 0.966, "reasoning_bytes": 114.988, "flops_per_problem": 6756420059.136}, "runmax.count.sumd16": {"acc": 0.866, "reasoning_bytes": 124.14, "flops_per_problem": 7248926638.08}, "sumd.count.sumd6": {"acc": 0.994, "reasoning_bytes": 81.428, "flops_per_problem": 4832676642.816}, "sumd.count.sumd7": {"acc": 0.968, "reasoning_bytes": 89.34, "flops_per_problem": 5226257940.48}, "sumd.count.sumd8": {"acc": 0.868, "reasoning_bytes": 96.77, "flops_per_problem": 5603498901.504}, "parity.count.inc16": {"acc": 1.0, "reasoning_bytes": 129.02, "flops_per_problem": 7420279357.44}, "parity.count.inc20": {"acc": 1.0, "reasoning_bytes": 154.724, "flops_per_problem": 8732099248.128}, "parity.count.inc24": {"acc": 0.984, "reasoning_bytes": 175.756, "flops_per_problem": 9837589266.432}, "count.count.inc16": {"acc": 0.922, "reasoning_bytes": 110.752, "flops_per_problem": 6657671430.144}, "count.count.inc18": {"acc": 0.534, "reasoning_bytes": 114.374, "flops_per_problem": 6905956220.928}, "count.count.inc20": {"acc": 0.344, "reasoning_bytes": 121.756, "flops_per_problem": 7319322574.848}, "add.count.inc6": {"acc": 0.888, "reasoning_bytes": 131.23, "flops_per_problem": 7253431271.424}, "add.count.inc7": {"acc": 0.656, "reasoning_bytes": 146.664, "flops_per_problem": 8022840311.808}, "add.count.inc8": {"acc": 0.352, "reasoning_bytes": 161.802, "flops_per_problem": 8779707039.744}, "parity.rev.cmp16": {"acc": 0.998, "reasoning_bytes": 123.444, "flops_per_problem": 7085699923.968}, "parity.rev.cmp20": {"acc": 0.968, "reasoning_bytes": 148.596, "flops_per_problem": 8373141798.912}, "parity.rev.cmp24": {"acc": 0.956, "reasoning_bytes": 168.98, "flops_per_problem": 9450014146.56}, "sumd.rev.cmp6": {"acc": 0.924, "reasoning_bytes": 80.728, "flops_per_problem": 4713259696.128}, "sumd.rev.cmp7": {"acc": 0.91, "reasoning_bytes": 88.646, "flops_per_problem": 5107282624.512}, "sumd.rev.cmp8": {"acc": 0.81, "reasoning_bytes": 94.83, "flops_per_problem": 5424461807.616}, "add.rev.cmp6": {"acc": 0.922, "reasoning_bytes": 156.688, "flops_per_problem": 8538046709.76}, "add.rev.cmp7": {"acc": 0.826, "reasoning_bytes": 180.732, "flops_per_problem": 9732481155.072}, "add.rev.cmp8": {"acc": 0.704, "reasoning_bytes": 204.108, "flops_per_problem": 10896001449.984}, "runmax.rev.runmax12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5917851648.0}, "runmax.rev.runmax14": {"acc": 0.996, "reasoning_bytes": 112.0, "flops_per_problem": 6536134656.0}, "runmax.rev.runmax16": {"acc": 0.946, "reasoning_bytes": 122.096, "flops_per_problem": 7070331174.912}, "count.rev.runmax16": {"acc": 0.96, "reasoning_bytes": 107.91, "flops_per_problem": 6487996907.52}, "count.rev.runmax18": {"acc": 0.88, "reasoning_bytes": 117.162, "flops_per_problem": 6984919793.664}, "count.rev.runmax20": {"acc": 0.716, "reasoning_bytes": 125.182, "flops_per_problem": 7427433775.104}, "add.rev.runmax6": {"acc": 0.906, "reasoning_bytes": 184.298, "flops_per_problem": 9552914104.32}, "add.rev.runmax7": {"acc": 0.736, "reasoning_bytes": 213.032, "flops_per_problem": 10911105220.608}, "add.rev.runmax8": {"acc": 0.468, "reasoning_bytes": 234.412, "flops_per_problem": 11942136299.52}, "inc.rev.count6": {"acc": 0.672, "reasoning_bytes": 156.146, "flops_per_problem": 8043508629.504}, "inc.rev.count7": {"acc": 0.528, "reasoning_bytes": 180.408, "flops_per_problem": 9158979502.08}, "inc.rev.count8": {"acc": 0.488, "reasoning_bytes": 185.542, "flops_per_problem": 9431024025.6}, "count.rev.count16": {"acc": 1.0, "reasoning_bytes": 107.99, "flops_per_problem": 6535693025.28}, "count.rev.count18": {"acc": 0.996, "reasoning_bytes": 117.706, "flops_per_problem": 7053107576.832}, "count.rev.count20": {"acc": 0.964, "reasoning_bytes": 126.086, "flops_per_problem": 7511520264.192}, "parity.rev.count16": {"acc": 1.0, "reasoning_bytes": 124.936, "flops_per_problem": 7239917371.392}, "parity.rev.count20": {"acc": 1.0, "reasoning_bytes": 150.628, "flops_per_problem": 8551207305.216}, "parity.rev.count24": {"acc": 1.0, "reasoning_bytes": 172.014, "flops_per_problem": 9672331051.008}, "sumd.rev.find6": {"acc": 0.974, "reasoning_bytes": 85.038, "flops_per_problem": 4903779188.736}, "sumd.rev.find7": {"acc": 0.928, "reasoning_bytes": 93.072, "flops_per_problem": 5302748381.184}, "sumd.rev.find8": {"acc": 0.816, "reasoning_bytes": 98.49, "flops_per_problem": 5586186977.28}, "runmax.rev.find12": {"acc": 0.994, "reasoning_bytes": 100.0, "flops_per_problem": 5917851648.0}, "runmax.rev.find14": {"acc": 0.924, "reasoning_bytes": 111.988, "flops_per_problem": 6535604699.136}, "runmax.rev.find16": {"acc": 0.884, "reasoning_bytes": 121.924, "flops_per_problem": 7062735126.528}, "count.rev.find16": {"acc": 0.978, "reasoning_bytes": 107.99, "flops_per_problem": 6491529953.28}, "count.rev.find18": {"acc": 0.964, "reasoning_bytes": 117.336, "flops_per_problem": 6992604168.192}, "count.rev.find20": {"acc": 0.906, "reasoning_bytes": 125.24, "flops_per_problem": 7429730254.848}, "count.rev.rev16": {"acc": 0.952, "reasoning_bytes": 102.89, "flops_per_problem": 6133809070.08}, "count.rev.rev18": {"acc": 0.85, "reasoning_bytes": 111.632, "flops_per_problem": 6608208789.504}, "count.rev.rev20": {"acc": 0.65, "reasoning_bytes": 119.674, "flops_per_problem": 7051606032.384}, "sumd.rev.rev6": {"acc": 0.97, "reasoning_bytes": 80.506, "flops_per_problem": 4615129350.144}, "sumd.rev.rev7": {"acc": 0.876, "reasoning_bytes": 88.264, "flops_per_problem": 5001909534.72}, "sumd.rev.rev8": {"acc": 0.69, "reasoning_bytes": 95.718, "flops_per_problem": 5374380883.968}, "parity.rev.rev16": {"acc": 0.932, "reasoning_bytes": 119.96, "flops_per_problem": 6843509637.12}, "parity.rev.rev20": {"acc": 0.644, "reasoning_bytes": 145.724, "flops_per_problem": 8157979312.128}, "parity.rev.rev24": {"acc": 0.486, "reasoning_bytes": 167.264, "flops_per_problem": 9285904171.008}, "sumd.rev.sumd6": {"acc": 0.988, "reasoning_bytes": 84.73, "flops_per_problem": 4810771759.104}, "sumd.rev.sumd7": {"acc": 0.924, "reasoning_bytes": 92.57, "flops_per_problem": 5202498207.744}, "sumd.rev.sumd8": {"acc": 0.692, "reasoning_bytes": 99.622, "flops_per_problem": 5556686045.184}, "parity.rev.sumd16": {"acc": 0.948, "reasoning_bytes": 122.744, "flops_per_problem": 7010622701.568}, "parity.rev.sumd20": {"acc": 0.61, "reasoning_bytes": 148.676, "flops_per_problem": 8332511772.672}, "parity.rev.sumd24": {"acc": 0.476, "reasoning_bytes": 170.108, "flops_per_problem": 9457433542.656}, "add.rev.sumd6": {"acc": 0.16, "reasoning_bytes": 190.282, "flops_per_problem": 9771697963.008}, "add.rev.sumd7": {"acc": 0.024, "reasoning_bytes": 218.84, "flops_per_problem": 11119201615.872}, "add.rev.sumd8": {"acc": 0.026, "reasoning_bytes": 239.236, "flops_per_problem": 12105274687.488}, "parity.rev.inc16": {"acc": 0.908, "reasoning_bytes": 124.14, "flops_per_problem": 7028111278.08}, "parity.rev.inc20": {"acc": 0.414, "reasoning_bytes": 149.76, "flops_per_problem": 8336221470.72}, "parity.rev.inc24": {"acc": 0.31, "reasoning_bytes": 171.628, "flops_per_problem": 9478455164.928}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 99.0, "flops_per_problem": 5772378488.832}, "runmax.rev.inc14": {"acc": 0.994, "reasoning_bytes": 111.0, "flops_per_problem": 6393752911.872}, "runmax.rev.inc16": {"acc": 0.936, "reasoning_bytes": 121.512, "flops_per_problem": 6946409594.88}, "inc.rev.inc6": {"acc": 0.024, "reasoning_bytes": 169.812, "flops_per_problem": 8651369152.512}, "inc.rev.inc7": {"acc": 0.0, "reasoning_bytes": 196.966, "flops_per_problem": 9933688111.104}, "inc.rev.inc8": {"acc": 0.0, "reasoning_bytes": 202.96, "flops_per_problem": 10257756733.44}, "parity.sumd.cmp16": {"acc": 0.998, "reasoning_bytes": 126.168, "flops_per_problem": 7250163204.096}, "parity.sumd.cmp20": {"acc": 0.97, "reasoning_bytes": 151.476, "flops_per_problem": 8544494518.272}, "parity.sumd.cmp24": {"acc": 0.948, "reasoning_bytes": 171.512, "flops_per_problem": 9605998116.864}, "runmax.sumd.cmp12": {"acc": 0.99, "reasoning_bytes": 102.0, "flops_per_problem": 6006177792.0}, "runmax.sumd.cmp14": {"acc": 0.964, "reasoning_bytes": 113.95, "flops_per_problem": 6622252646.4}, "runmax.sumd.cmp16": {"acc": 0.734, "reasoning_bytes": 122.196, "flops_per_problem": 7074747482.112}, "count.sumd.cmp16": {"acc": 0.97, "reasoning_bytes": 109.99, "flops_per_problem": 6579856097.28}, "count.sumd.cmp18": {"acc": 0.918, "reasoning_bytes": 118.86, "flops_per_problem": 7059908689.92}, "count.sumd.cmp20": {"acc": 0.828, "reasoning_bytes": 125.724, "flops_per_problem": 7451105181.696}, "sumd.sumd.runmax6": {"acc": 0.996, "reasoning_bytes": 84.352, "flops_per_problem": 4917646393.344}, "sumd.sumd.runmax7": {"acc": 0.95, "reasoning_bytes": 92.49, "flops_per_problem": 5321208545.28}, "sumd.sumd.runmax8": {"acc": 0.718, "reasoning_bytes": 98.72, "flops_per_problem": 5640507555.84}, "count.sumd.runmax16": {"acc": 0.954, "reasoning_bytes": 110.91, "flops_per_problem": 6664649195.52}, "count.sumd.runmax18": {"acc": 0.85, "reasoning_bytes": 119.812, "flops_per_problem": 7146115006.464}, "count.sumd.runmax20": {"acc": 0.672, "reasoning_bytes": 127.716, "flops_per_problem": 7582799462.4}, "add.sumd.runmax6": {"acc": 0.736, "reasoning_bytes": 150.996, "flops_per_problem": 8125828595.712}, "add.sumd.runmax7": {"acc": 0.36, "reasoning_bytes": 170.428, "flops_per_problem": 9072331554.816}, "add.sumd.runmax8": {"acc": 0.182, "reasoning_bytes": 188.328, "flops_per_problem": 9951618318.336}, "parity.sumd.count16": {"acc": 1.0, "reasoning_bytes": 127.672, "flops_per_problem": 7404910608.384}, "parity.sumd.count20": {"acc": 1.0, "reasoning_bytes": 153.46, "flops_per_problem": 8720440197.12}, "parity.sumd.count24": {"acc": 1.0, "reasoning_bytes": 173.34, "flops_per_problem": 9775054356.48}, "sumd.sumd.count6": {"acc": 0.974, "reasoning_bytes": 84.076, "flops_per_problem": 4949620457.472}, "sumd.sumd.count7": {"acc": 0.896, "reasoning_bytes": 91.798, "flops_per_problem": 5334810771.456}, "sumd.sumd.count8": {"acc": 0.81, "reasoning_bytes": 98.996, "flops_per_problem": 5696859635.712}, "add.sumd.count6": {"acc": 0.77, "reasoning_bytes": 150.23, "flops_per_problem": 8136162754.56}, "add.sumd.count7": {"acc": 0.478, "reasoning_bytes": 169.238, "flops_per_problem": 9064028897.28}, "add.sumd.count8": {"acc": 0.324, "reasoning_bytes": 186.912, "flops_per_problem": 9932893175.808}, "runmax.sumd.find12": {"acc": 0.998, "reasoning_bytes": 103.0, "flops_per_problem": 6094503936.0}, "runmax.sumd.find14": {"acc": 0.946, "reasoning_bytes": 114.924, "flops_per_problem": 6709430550.528}, "runmax.sumd.find16": {"acc": 0.9, "reasoning_bytes": 119.808, "flops_per_problem": 7013449138.176}, "sumd.sumd.find6": {"acc": 0.996, "reasoning_bytes": 83.806, "flops_per_problem": 4893533356.032}, "sumd.sumd.find7": {"acc": 0.968, "reasoning_bytes": 91.704, "flops_per_problem": 5286496370.688}, "sumd.sumd.find8": {"acc": 0.888, "reasoning_bytes": 97.082, "flops_per_problem": 5568168443.904}, "parity.sumd.find16": {"acc": 0.998, "reasoning_bytes": 127.132, "flops_per_problem": 7336899477.504}, "parity.sumd.find20": {"acc": 0.936, "reasoning_bytes": 153.1, "flops_per_problem": 8660378419.2}, "parity.sumd.find24": {"acc": 0.872, "reasoning_bytes": 169.048, "flops_per_problem": 9541343379.456}, "count.sumd.rev16": {"acc": 0.954, "reasoning_bytes": 105.91, "flops_per_problem": 6311344619.52}, "count.sumd.rev18": {"acc": 0.836, "reasoning_bytes": 114.616, "flops_per_problem": 6784154468.352}, "count.sumd.rev20": {"acc": 0.636, "reasoning_bytes": 122.506, "flops_per_problem": 7219690684.416}, "parity.sumd.rev16": {"acc": 0.95, "reasoning_bytes": 122.756, "flops_per_problem": 7011152658.432}, "parity.sumd.rev20": {"acc": 0.63, "reasoning_bytes": 148.736, "flops_per_problem": 8335161556.992}, "parity.sumd.rev24": {"acc": 0.5, "reasoning_bytes": 169.964, "flops_per_problem": 9449307537.408}, "add.sumd.rev6": {"acc": 0.686, "reasoning_bytes": 144.956, "flops_per_problem": 7770580844.544}, "add.sumd.rev7": {"acc": 0.25, "reasoning_bytes": 164.246, "flops_per_problem": 8710812647.424}, "add.sumd.rev8": {"acc": 0.048, "reasoning_bytes": 181.292, "flops_per_problem": 9551235907.584}, "parity.sumd.sumd16": {"acc": 0.968, "reasoning_bytes": 125.24, "flops_per_problem": 7165016801.28}, "parity.sumd.sumd20": {"acc": 0.662, "reasoning_bytes": 148.668, "flops_per_problem": 8376321540.096}, "parity.sumd.sumd24": {"acc": 0.48, "reasoning_bytes": 171.5, "flops_per_problem": 9588509540.352}, "add.sumd.sumd6": {"acc": 0.698, "reasoning_bytes": 149.472, "flops_per_problem": 7978323935.232}, "add.sumd.sumd7": {"acc": 0.256, "reasoning_bytes": 169.068, "flops_per_problem": 8934366117.888}, "add.sumd.sumd8": {"acc": 0.082, "reasoning_bytes": 186.22, "flops_per_problem": 9779205685.248}, "count.sumd.sumd16": {"acc": 0.948, "reasoning_bytes": 108.85, "flops_per_problem": 6485347123.2}, "count.sumd.sumd18": {"acc": 0.828, "reasoning_bytes": 117.53, "flops_per_problem": 6957008732.16}, "count.sumd.sumd20": {"acc": 0.62, "reasoning_bytes": 125.1, "flops_per_problem": 7377087873.024}, "inc.sumd.inc6": {"acc": 0.858, "reasoning_bytes": 135.534, "flops_per_problem": 7045423202.304}, "inc.sumd.inc7": {"acc": 0.412, "reasoning_bytes": 151.908, "flops_per_problem": 7810592587.776}, "inc.sumd.inc8": {"acc": 0.058, "reasoning_bytes": 156.854, "flops_per_problem": 8070271451.136}, "sumd.sumd.inc6": {"acc": 0.962, "reasoning_bytes": 83.494, "flops_per_problem": 4760249204.736}, "sumd.sumd.inc7": {"acc": 0.866, "reasoning_bytes": 91.342, "flops_per_problem": 5150297456.64}, "sumd.sumd.inc8": {"acc": 0.682, "reasoning_bytes": 98.48, "flops_per_problem": 5509078253.568}, "parity.sumd.inc16": {"acc": 0.952, "reasoning_bytes": 126.744, "flops_per_problem": 7187274989.568}, "parity.sumd.inc20": {"acc": 0.592, "reasoning_bytes": 152.664, "flops_per_problem": 8508634103.808}, "parity.sumd.inc24": {"acc": 0.384, "reasoning_bytes": 174.172, "flops_per_problem": 9635057418.24}, "inc.inc.cmp6": {"acc": 0.968, "reasoning_bytes": 144.304, "flops_per_problem": 7653637029.888}, "inc.inc.cmp7": {"acc": 0.904, "reasoning_bytes": 164.946, "flops_per_problem": 8653577306.112}, "inc.inc.cmp8": {"acc": 0.81, "reasoning_bytes": 180.632, "flops_per_problem": 9436765224.96}, "runmax.inc.cmp12": {"acc": 0.968, "reasoning_bytes": 105.294, "flops_per_problem": 6138755334.144}, "runmax.inc.cmp14": {"acc": 0.932, "reasoning_bytes": 117.07, "flops_per_problem": 6751208816.64}, "runmax.inc.cmp16": {"acc": 0.884, "reasoning_bytes": 127.258, "flops_per_problem": 7290704904.192}, "sumd.inc.cmp6": {"acc": 0.972, "reasoning_bytes": 88.072, "flops_per_problem": 5037593296.896}, "sumd.inc.cmp7": {"acc": 0.946, "reasoning_bytes": 95.816, "flops_per_problem": 5423931850.752}, "sumd.inc.cmp8": {"acc": 0.918, "reasoning_bytes": 101.516, "flops_per_problem": 5719824433.152}, "sumd.inc.runmax6": {"acc": 0.998, "reasoning_bytes": 93.522, "flops_per_problem": 5278458691.584}, "sumd.inc.runmax7": {"acc": 0.952, "reasoning_bytes": 101.226, "flops_per_problem": 5662854070.272}, "sumd.inc.runmax8": {"acc": 0.794, "reasoning_bytes": 107.842, "flops_per_problem": 5999200026.624}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.648, "flops_per_problem": 6343936966.656}, "runmax.inc.runmax14": {"acc": 0.996, "reasoning_bytes": 120.248, "flops_per_problem": 6900391673.856}, "runmax.inc.runmax16": {"acc": 0.946, "reasoning_bytes": 126.798, "flops_per_problem": 7277985939.456}, "add.inc.runmax6": {"acc": 0.87, "reasoning_bytes": 191.188, "flops_per_problem": 9856667713.536}, "add.inc.runmax7": {"acc": 0.78, "reasoning_bytes": 215.734, "flops_per_problem": 11028932296.704}, "add.inc.runmax8": {"acc": 0.526, "reasoning_bytes": 235.952, "flops_per_problem": 12016595238.912}, "runmax.inc.count12": {"acc": 1.0, "reasoning_bytes": 108.928, "flops_per_problem": 6356302626.816}, "runmax.inc.count14": {"acc": 1.0, "reasoning_bytes": 121.394, "flops_per_problem": 6995165626.368}, "runmax.inc.count16": {"acc": 0.754, "reasoning_bytes": 129.252, "flops_per_problem": 7430878494.72}, "sumd.inc.count6": {"acc": 0.986, "reasoning_bytes": 92.388, "flops_per_problem": 5272540839.936}, "sumd.inc.count7": {"acc": 0.952, "reasoning_bytes": 100.214, "flops_per_problem": 5662324113.408}, "sumd.inc.count8": {"acc": 0.756, "reasoning_bytes": 107.124, "flops_per_problem": 6011654012.928}, "inc.inc.count6": {"acc": 0.634, "reasoning_bytes": 164.858, "flops_per_problem": 8429140574.208}, "inc.inc.count7": {"acc": 0.502, "reasoning_bytes": 187.566, "flops_per_problem": 9478101860.352}, "inc.inc.count8": {"acc": 0.412, "reasoning_bytes": 195.186, "flops_per_problem": 9857992605.696}, "parity.inc.find16": {"acc": 0.996, "reasoning_bytes": 128.228, "flops_per_problem": 7341139132.416}, "parity.inc.find20": {"acc": 0.95, "reasoning_bytes": 154.352, "flops_per_problem": 8671507513.344}, "parity.inc.find24": {"acc": 0.854, "reasoning_bytes": 175.188, "flops_per_problem": 9768341569.536}, "sumd.inc.find6": {"acc": 0.98, "reasoning_bytes": 92.124, "flops_per_problem": 5216718716.928}, "sumd.inc.find7": {"acc": 0.924, "reasoning_bytes": 100.278, "flops_per_problem": 5620987478.016}, "sumd.inc.find8": {"acc": 0.81, "reasoning_bytes": 106.31, "flops_per_problem": 5931542200.32}, "count.inc.find16": {"acc": 0.904, "reasoning_bytes": 111.97, "flops_per_problem": 6667298979.84}, "count.inc.find18": {"acc": 0.854, "reasoning_bytes": 121.392, "flops_per_problem": 7171729588.224}, "count.inc.find20": {"acc": 0.842, "reasoning_bytes": 129.48, "flops_per_problem": 7617246658.56}, "sumd.inc.rev6": {"acc": 0.976, "reasoning_bytes": 87.524, "flops_per_problem": 4924624158.72}, "sumd.inc.rev7": {"acc": 0.894, "reasoning_bytes": 95.446, "flops_per_problem": 5317940477.952}, "sumd.inc.rev8": {"acc": 0.66, "reasoning_bytes": 102.602, "flops_per_problem": 5674601447.424}, "count.inc.rev16": {"acc": 0.946, "reasoning_bytes": 106.92, "flops_per_problem": 6311786250.24}, "count.inc.rev18": {"acc": 0.85, "reasoning_bytes": 116.026, "flops_per_problem": 6802261327.872}, "count.inc.rev20": {"acc": 0.638, "reasoning_bytes": 124.134, "flops_per_problem": 7247425093.632}, "parity.inc.rev16": {"acc": 0.936, "reasoning_bytes": 123.864, "flops_per_problem": 7015922270.208}, "parity.inc.rev20": {"acc": 0.61, "reasoning_bytes": 149.748, "flops_per_problem": 8335691513.856}, "parity.inc.rev24": {"acc": 0.5, "reasoning_bytes": 171.624, "flops_per_problem": 9478455164.928}, "count.inc.sumd16": {"acc": 0.944, "reasoning_bytes": 109.89, "flops_per_problem": 6487113646.08}, "count.inc.sumd18": {"acc": 0.836, "reasoning_bytes": 118.888, "flops_per_problem": 6972819111.936}, "count.inc.sumd20": {"acc": 0.636, "reasoning_bytes": 127.078, "flops_per_problem": 7420456009.728}, "sumd.inc.sumd6": {"acc": 0.984, "reasoning_bytes": 91.758, "flops_per_problem": 5122651373.568}, "sumd.inc.sumd7": {"acc": 0.886, "reasoning_bytes": 99.572, "flops_per_problem": 5513229582.336}, "sumd.inc.sumd8": {"acc": 0.54, "reasoning_bytes": 106.014, "flops_per_problem": 5841007902.72}, "add.inc.sumd6": {"acc": 0.088, "reasoning_bytes": 196.626, "flops_per_problem": 10052133470.208}, "add.inc.sumd7": {"acc": 0.042, "reasoning_bytes": 222.92, "flops_per_problem": 11301153472.512}, "add.inc.sumd8": {"acc": 0.024, "reasoning_bytes": 241.47, "flops_per_problem": 12215947345.92}, "parity.inc.inc16": {"acc": 0.934, "reasoning_bytes": 127.9, "flops_per_problem": 7194164428.8}, "parity.inc.inc20": {"acc": 0.512, "reasoning_bytes": 153.096, "flops_per_problem": 8492558745.6}, "parity.inc.inc24": {"acc": 0.148, "reasoning_bytes": 166.416, "flops_per_problem": 9409384120.32}, "sumd.inc.inc6": {"acc": 0.968, "reasoning_bytes": 94.524, "flops_per_problem": 5234383945.728}, "sumd.inc.inc7": {"acc": 0.74, "reasoning_bytes": 102.316, "flops_per_problem": 5622312370.176}, "sumd.inc.inc8": {"acc": 0.35, "reasoning_bytes": 109.008, "flops_per_problem": 5958923304.96}, "runmax.inc.inc12": {"acc": 0.936, "reasoning_bytes": 110.06, "flops_per_problem": 6270272962.56}, "runmax.inc.inc14": {"acc": 0.63, "reasoning_bytes": 122.684, "flops_per_problem": 6917350293.504}, "runmax.inc.inc16": {"acc": 0.234, "reasoning_bytes": 132.516, "flops_per_problem": 7437061324.8}, "count.inc.cmp16": {"acc": 0.904, "reasoning_bytes": 110.976, "flops_per_problem": 6579237814.272}, "count.inc.cmp18": {"acc": 0.828, "reasoning_bytes": 119.97, "flops_per_problem": 7064943280.128}, "count.inc.cmp20": {"acc": 0.69, "reasoning_bytes": 127.504, "flops_per_problem": 7492530143.232}, "inc.rev.sumd6": {"acc": 0.206, "reasoning_bytes": 165.908, "flops_per_problem": 8386479046.656}, "inc.rev.sumd7": {"acc": 0.056, "reasoning_bytes": 192.45, "flops_per_problem": 9601051852.8}, "inc.rev.sumd8": {"acc": 0.026, "reasoning_bytes": 196.984, "flops_per_problem": 9845008662.528}, "runmax.inc.find12": {"acc": 0.878, "reasoning_bytes": 105.428, "flops_per_problem": 6157568802.816}, "runmax.inc.find14": {"acc": 0.884, "reasoning_bytes": 117.564, "flops_per_problem": 6781857988.608}, "runmax.inc.find16": {"acc": 0.792, "reasoning_bytes": 126.804, "flops_per_problem": 7278250917.888}, "inc.runmax.cmp6": {"acc": 0.996, "reasoning_bytes": 119.888, "flops_per_problem": 6487025319.936}, "inc.runmax.cmp7": {"acc": 0.964, "reasoning_bytes": 134.19, "flops_per_problem": 7162808647.68}, "inc.runmax.cmp8": {"acc": 0.968, "reasoning_bytes": 136.588, "flops_per_problem": 7312874766.336}} +{"step": 6000, "train_loss": 1.0295262336730957} +{"step": 6020, "train_loss": 1.0913963317871094} +{"step": 6040, "train_loss": 1.0300319194793701} +{"step": 6060, "train_loss": 1.0672409534454346} +{"step": 6080, "train_loss": 1.0837595462799072} +{"step": 6100, "train_loss": 1.1660079956054688} +{"step": 6120, "train_loss": 1.0194432735443115} +{"step": 6140, "train_loss": 1.0590711832046509} +{"step": 6160, "train_loss": 1.0721774101257324} +{"step": 6180, "train_loss": 0.9829245209693909} +{"step": 6200, "train_loss": 1.0618599653244019} +{"step": 6220, "train_loss": 1.0640075206756592} +{"step": 6240, "train_loss": 1.0546753406524658} +{"step": 6260, "train_loss": 1.0576026439666748} +{"step": 6280, "train_loss": 0.9556705951690674} +{"step": 6300, "train_loss": 0.9814130663871765} +{"step": 6320, "train_loss": 1.119065284729004} +{"step": 6340, "train_loss": 1.0177839994430542} +{"step": 6360, "train_loss": 1.158381700515747} +{"step": 6380, "train_loss": 1.0174367427825928} +{"step": 6400, "train_loss": 1.0408071279525757} +{"step": 6420, "train_loss": 1.1114882230758667} +{"step": 6440, "train_loss": 1.0254892110824585} +{"step": 6460, "train_loss": 1.0880712270736694} +{"step": 6480, "train_loss": 1.0700205564498901} +{"step": 6500, "train_loss": 1.0410943031311035} +{"step": 6520, "train_loss": 1.0932451486587524} +{"step": 6540, "train_loss": 1.0472383499145508} +{"step": 6560, "train_loss": 1.0726182460784912} +{"step": 6580, "train_loss": 1.0574568510055542} +{"step": 6600, "train_loss": 1.0087189674377441} +{"step": 6620, "train_loss": 1.0239176750183105} +{"step": 6640, "train_loss": 1.0475621223449707} +{"step": 6660, "train_loss": 1.0052247047424316} +{"step": 6680, "train_loss": 1.0188941955566406} +{"step": 6700, "train_loss": 1.0511137247085571} +{"step": 6720, "train_loss": 1.0376930236816406} +{"step": 6740, "train_loss": 1.1012704372406006} +{"step": 6760, "train_loss": 0.9698520302772522} +{"step": 6780, "train_loss": 1.0524749755859375} +{"step": 6800, "train_loss": 1.0504810810089111} +{"step": 6820, "train_loss": 1.007604718208313} +{"step": 6840, "train_loss": 1.0455809831619263} +{"step": 6860, "train_loss": 1.0489490032196045} +{"step": 6880, "train_loss": 1.0457370281219482} +{"step": 6900, "train_loss": 1.0526655912399292} +{"step": 6920, "train_loss": 1.0277278423309326} +{"step": 6940, "train_loss": 1.0138660669326782} +{"step": 6960, "train_loss": 1.0352776050567627} +{"step": 6980, "train_loss": 1.0209479331970215} +{"step": 7000, "tokens": 229376000, "val_loss": 1.9071482717990875, "val_bpb": 0.6874959679655033, "lr": 0.00027546233806915164, "elapsed": 2228.263265609741, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.698, "reasoning_bytes": 79.0, "flops_per_problem": 4928333856.768}, "add9": {"acc": 0.0, "reasoning_bytes": 88.34, "flops_per_problem": 5473836122.112}, "add10": {"acc": 0.0, "reasoning_bytes": 90.752, "flops_per_problem": 5713023320.064}, "reach14": {"acc": 0.544, "reasoning_bytes": 9.014, "flops_per_problem": 4681903915.008}, "reach16": {"acc": 0.524, "reasoning_bytes": 9.682, "flops_per_problem": 5241185058.816}, "reach18": {"acc": 0.51, "reasoning_bytes": 11.04, "flops_per_problem": 5831821983.744}, "parity24": {"acc": 0.456, "reasoning_bytes": 140.768, "flops_per_problem": 7762454839.296}, "parity28": {"acc": 0.506, "reasoning_bytes": 164.108, "flops_per_problem": 8969873227.776}, "parity32": {"acc": 0.462, "reasoning_bytes": 185.66, "flops_per_problem": 10098328043.52}, "cmp8": {"acc": 0.984, "reasoning_bytes": 5.804, "flops_per_problem": 1360399269.888}, "cmp9": {"acc": 0.984, "reasoning_bytes": 5.72, "flops_per_problem": 1445015715.84}, "cmp10": {"acc": 0.952, "reasoning_bytes": 5.788, "flops_per_problem": 1536698253.312}, "runmax12": {"acc": 0.998, "reasoning_bytes": 71.0, "flops_per_problem": 4151328768.0}, "runmax14": {"acc": 1.0, "reasoning_bytes": 82.76, "flops_per_problem": 4759012638.72}, "runmax16": {"acc": 1.0, "reasoning_bytes": 89.84, "flops_per_problem": 5160013332.48}, "count16": {"acc": 0.948, "reasoning_bytes": 78.43, "flops_per_problem": 4700275752.96}, "count18": {"acc": 0.83, "reasoning_bytes": 85.83, "flops_per_problem": 5116645195.776}, "count20": {"acc": 0.72, "reasoning_bytes": 94.434, "flops_per_problem": 5585303715.84}, "brackets16": {"acc": 0.846, "reasoning_bytes": 55.238, "flops_per_problem": 3720738816.0}, "brackets18": {"acc": 0.85, "reasoning_bytes": 62.272, "flops_per_problem": 4120856248.32}, "brackets20": {"acc": 0.716, "reasoning_bytes": 80.818, "flops_per_problem": 5027524116.48}, "sumd8": {"acc": 0.748, "reasoning_bytes": 57.26, "flops_per_problem": 3323536146.432}, "sumd9": {"acc": 0.27, "reasoning_bytes": 61.122, "flops_per_problem": 3538433654.784}, "sumd10": {"acc": 0.064, "reasoning_bytes": 67.108, "flops_per_problem": 3846515245.056}, "inc8": {"acc": 0.954, "reasoning_bytes": 63.024, "flops_per_problem": 3798995779.584}, "inc9": {"acc": 0.406, "reasoning_bytes": 70.382, "flops_per_problem": 4211213893.632}, "inc10": {"acc": 0.01, "reasoning_bytes": 71.356, "flops_per_problem": 4306782781.44}, "add.cmp6": {"acc": 0.99, "reasoning_bytes": 92.64, "flops_per_problem": 5532837986.304}, "add.cmp7": {"acc": 0.942, "reasoning_bytes": 105.698, "flops_per_problem": 6239093833.728}, "add.cmp8": {"acc": 0.858, "reasoning_bytes": 119.826, "flops_per_problem": 6998257041.408}, "add.runmax6": {"acc": 1.0, "reasoning_bytes": 120.834, "flops_per_problem": 6572966658.048}, "add.runmax7": {"acc": 0.944, "reasoning_bytes": 138.812, "flops_per_problem": 7455256510.464}, "add.runmax8": {"acc": 0.596, "reasoning_bytes": 152.596, "flops_per_problem": 8152326438.912}, "add.count6": {"acc": 0.94, "reasoning_bytes": 115.648, "flops_per_problem": 6388100038.656}, "add.count7": {"acc": 0.77, "reasoning_bytes": 132.058, "flops_per_problem": 7201142194.176}, "add.count8": {"acc": 0.458, "reasoning_bytes": 141.102, "flops_per_problem": 7688879161.344}, "add.find6": {"acc": 0.794, "reasoning_bytes": 108.008, "flops_per_problem": 6007855988.736}, "add.find7": {"acc": 0.648, "reasoning_bytes": 122.47, "flops_per_problem": 6734691827.712}, "add.find8": {"acc": 0.39, "reasoning_bytes": 135.12, "flops_per_problem": 7381857484.8}, "add.rev6": {"acc": 0.924, "reasoning_bytes": 123.23, "flops_per_problem": 6793958670.336}, "add.rev7": {"acc": 0.246, "reasoning_bytes": 145.084, "flops_per_problem": 7890086117.376}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 149.842, "flops_per_problem": 8186067025.92}, "add.sumd6": {"acc": 0.956, "reasoning_bytes": 126.5, "flops_per_problem": 6778943225.856}, "add.sumd7": {"acc": 0.646, "reasoning_bytes": 146.144, "flops_per_problem": 7734720430.08}, "add.sumd8": {"acc": 0.038, "reasoning_bytes": 158.67, "flops_per_problem": 8377381453.824}, "add.inc6": {"acc": 0.768, "reasoning_bytes": 131.04, "flops_per_problem": 7147351572.48}, "add.inc7": {"acc": 0.344, "reasoning_bytes": 150.98, "flops_per_problem": 8165928665.088}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 154.594, "flops_per_problem": 8428963921.92}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5122916352.0}, "runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 98.016, "flops_per_problem": 5697742897.152}, "runmax.cmp16": {"acc": 0.988, "reasoning_bytes": 105.048, "flops_per_problem": 6096623763.456}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.runmax14": {"acc": 1.0, "reasoning_bytes": 99.616, "flops_per_problem": 5812566884.352}, "runmax.runmax16": {"acc": 0.996, "reasoning_bytes": 106.168, "flops_per_problem": 6190249476.096}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5255405568.0}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 99.088, "flops_per_problem": 5833411854.336}, "runmax.count16": {"acc": 0.974, "reasoning_bytes": 106.144, "flops_per_problem": 6233352634.368}, "runmax.find12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.find14": {"acc": 0.976, "reasoning_bytes": 99.556, "flops_per_problem": 5809917100.032}, "runmax.find16": {"acc": 0.932, "reasoning_bytes": 106.144, "flops_per_problem": 6189189562.368}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 83.0, "flops_per_problem": 4857937920.0}, "runmax.rev14": {"acc": 1.0, "reasoning_bytes": 93.584, "flops_per_problem": 5413686018.048}, "runmax.rev16": {"acc": 0.996, "reasoning_bytes": 101.024, "flops_per_problem": 5830585417.728}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 86.0, "flops_per_problem": 5034590208.0}, "runmax.sumd14": {"acc": 1.0, "reasoning_bytes": 97.4, "flops_per_problem": 5626375372.8}, "runmax.sumd16": {"acc": 0.998, "reasoning_bytes": 104.372, "flops_per_problem": 6022606454.784}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5065769336.832}, "runmax.inc14": {"acc": 0.996, "reasoning_bytes": 97.368, "flops_per_problem": 5615157952.512}, "runmax.inc16": {"acc": 0.974, "reasoning_bytes": 105.072, "flops_per_problem": 6045394599.936}, "count.cmp16": {"acc": 0.864, "reasoning_bytes": 94.85, "flops_per_problem": 5690411827.2}, "count.cmp18": {"acc": 0.862, "reasoning_bytes": 100.99, "flops_per_problem": 6049987559.424}, "count.cmp20": {"acc": 0.75, "reasoning_bytes": 109.302, "flops_per_problem": 6504425570.304}, "count.runmax16": {"acc": 0.988, "reasoning_bytes": 95.95, "flops_per_problem": 5783154278.4}, "count.runmax18": {"acc": 0.886, "reasoning_bytes": 103.42, "flops_per_problem": 6201378570.24}, "count.runmax20": {"acc": 0.746, "reasoning_bytes": 110.97, "flops_per_problem": 6623135907.84}, "count.count16": {"acc": 1.0, "reasoning_bytes": 95.93, "flops_per_problem": 5826434088.96}, "count.count18": {"acc": 1.0, "reasoning_bytes": 103.36, "flops_per_problem": 6242891857.92}, "count.count20": {"acc": 0.998, "reasoning_bytes": 110.762, "flops_per_problem": 6658113060.864}, "count.find16": {"acc": 0.97, "reasoning_bytes": 95.95, "flops_per_problem": 5783154278.4}, "count.find18": {"acc": 0.944, "reasoning_bytes": 103.26, "flops_per_problem": 6194312478.72}, "count.find20": {"acc": 0.91, "reasoning_bytes": 110.898, "flops_per_problem": 6619956166.656}, "count.rev16": {"acc": 0.97, "reasoning_bytes": 90.75, "flops_per_problem": 5421017088.0}, "count.rev18": {"acc": 0.838, "reasoning_bytes": 97.27, "flops_per_problem": 5797286461.44}, "count.rev20": {"acc": 0.724, "reasoning_bytes": 105.17, "flops_per_problem": 6234500874.24}, "count.sumd16": {"acc": 0.976, "reasoning_bytes": 93.72, "flops_per_problem": 5596344483.84}, "count.sumd18": {"acc": 0.852, "reasoning_bytes": 100.5, "flops_per_problem": 5984096256.0}, "count.sumd20": {"acc": 0.736, "reasoning_bytes": 108.286, "flops_per_problem": 6416276078.592}, "count.inc16": {"acc": 0.974, "reasoning_bytes": 94.73, "flops_per_problem": 5596786114.56}, "count.inc18": {"acc": 0.846, "reasoning_bytes": 101.53, "flops_per_problem": 5985421148.16}, "count.inc20": {"acc": 0.72, "reasoning_bytes": 109.41, "flops_per_problem": 6422017277.952}, "parity.cmp16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6359482368.0}, "parity.cmp20": {"acc": 0.926, "reasoning_bytes": 129.0, "flops_per_problem": 7331069952.0}, "parity.cmp24": {"acc": 0.94, "reasoning_bytes": 149.25, "flops_per_problem": 8402554404.864}, "parity.runmax16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.runmax20": {"acc": 0.418, "reasoning_bytes": 131.428, "flops_per_problem": 7482460962.816}, "parity.runmax24": {"acc": 0.368, "reasoning_bytes": 153.892, "flops_per_problem": 8651192500.224}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 111.988, "flops_per_problem": 6491441627.136}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 130.132, "flops_per_problem": 7469388693.504}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 151.828, "flops_per_problem": 8604202991.616}, "parity.find16": {"acc": 0.996, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.find20": {"acc": 0.788, "reasoning_bytes": 130.752, "flops_per_problem": 7452606726.144}, "parity.find24": {"acc": 0.848, "reasoning_bytes": 152.154, "flops_per_problem": 8573023862.784}, "parity.rev16": {"acc": 1.0, "reasoning_bytes": 107.0, "flops_per_problem": 6094503936.0}, "parity.rev20": {"acc": 0.438, "reasoning_bytes": 125.228, "flops_per_problem": 7076160700.416}, "parity.rev24": {"acc": 0.392, "reasoning_bytes": 147.956, "flops_per_problem": 8256551288.832}, "parity.sumd16": {"acc": 1.0, "reasoning_bytes": 110.0, "flops_per_problem": 6271156224.0}, "parity.sumd20": {"acc": 0.468, "reasoning_bytes": 129.752, "flops_per_problem": 7320117510.144}, "parity.sumd24": {"acc": 0.43, "reasoning_bytes": 150.948, "flops_per_problem": 8432850272.256}, "parity.inc16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6271156224.0}, "parity.inc20": {"acc": 0.482, "reasoning_bytes": 130.74, "flops_per_problem": 7320824119.296}, "parity.inc24": {"acc": 0.042, "reasoning_bytes": 159.556, "flops_per_problem": 8876070862.848}, "sumd.cmp6": {"acc": 0.996, "reasoning_bytes": 62.1, "flops_per_problem": 3713937702.912}, "sumd.cmp7": {"acc": 0.97, "reasoning_bytes": 70.002, "flops_per_problem": 4107254022.144}, "sumd.cmp8": {"acc": 0.92, "reasoning_bytes": 74.772, "flops_per_problem": 4361986621.44}, "sumd.runmax6": {"acc": 0.998, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.956, "reasoning_bytes": 75.282, "flops_per_problem": 4340435042.304}, "sumd.runmax8": {"acc": 0.512, "reasoning_bytes": 79.19, "flops_per_problem": 4557187399.68}, "sumd.count6": {"acc": 0.994, "reasoning_bytes": 66.428, "flops_per_problem": 3949415202.816}, "sumd.count7": {"acc": 0.966, "reasoning_bytes": 74.124, "flops_per_problem": 4333457276.928}, "sumd.count8": {"acc": 0.632, "reasoning_bytes": 78.164, "flops_per_problem": 4556039159.808}, "sumd.find6": {"acc": 1.0, "reasoning_bytes": 66.24, "flops_per_problem": 3896949473.28}, "sumd.find7": {"acc": 0.966, "reasoning_bytes": 74.202, "flops_per_problem": 4292738924.544}, "sumd.find8": {"acc": 0.826, "reasoning_bytes": 78.502, "flops_per_problem": 4526803206.144}, "sumd.rev6": {"acc": 0.998, "reasoning_bytes": 61.544, "flops_per_problem": 3601145217.024}, "sumd.rev7": {"acc": 0.942, "reasoning_bytes": 69.234, "flops_per_problem": 3985010638.848}, "sumd.rev8": {"acc": 0.394, "reasoning_bytes": 72.784, "flops_per_problem": 4185246007.296}, "sumd.sumd6": {"acc": 0.998, "reasoning_bytes": 65.742, "flops_per_problem": 3795462733.824}, "sumd.sumd7": {"acc": 0.94, "reasoning_bytes": 73.488, "flops_per_problem": 4184097767.424}, "sumd.sumd8": {"acc": 0.484, "reasoning_bytes": 77.676, "flops_per_problem": 4411890892.8}, "sumd.inc6": {"acc": 0.998, "reasoning_bytes": 68.538, "flops_per_problem": 3910021742.592}, "sumd.inc7": {"acc": 0.938, "reasoning_bytes": 76.182, "flops_per_problem": 4291855663.104}, "sumd.inc8": {"acc": 0.452, "reasoning_bytes": 80.372, "flops_per_problem": 4521062006.784}, "inc.cmp6": {"acc": 0.998, "reasoning_bytes": 78.624, "flops_per_problem": 4576354172.928}, "inc.cmp7": {"acc": 0.996, "reasoning_bytes": 89.828, "flops_per_problem": 5159483375.616}, "inc.cmp8": {"acc": 0.924, "reasoning_bytes": 100.598, "flops_per_problem": 5723445805.056}, "inc.runmax6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5520384000.0}, "inc.runmax7": {"acc": 0.996, "reasoning_bytes": 120.0, "flops_per_problem": 6271156224.0}, "inc.runmax8": {"acc": 0.862, "reasoning_bytes": 121.896, "flops_per_problem": 6399052480.512}, "inc.count6": {"acc": 0.974, "reasoning_bytes": 99.0, "flops_per_problem": 5343731712.0}, "inc.count7": {"acc": 0.95, "reasoning_bytes": 113.96, "flops_per_problem": 6048839319.552}, "inc.count8": {"acc": 0.642, "reasoning_bytes": 114.434, "flops_per_problem": 6113670709.248}, "inc.find6": {"acc": 0.858, "reasoning_bytes": 91.858, "flops_per_problem": 4984774262.784}, "inc.find7": {"acc": 0.8, "reasoning_bytes": 102.528, "flops_per_problem": 5500068986.88}, "inc.find8": {"acc": 0.438, "reasoning_bytes": 103.882, "flops_per_problem": 5603498901.504}, "inc.rev6": {"acc": 0.944, "reasoning_bytes": 104.086, "flops_per_problem": 5614098038.784}, "inc.rev7": {"acc": 0.786, "reasoning_bytes": 123.918, "flops_per_problem": 6579944423.424}, "inc.rev8": {"acc": 0.008, "reasoning_bytes": 127.604, "flops_per_problem": 6793517039.616}, "inc.sumd6": {"acc": 0.984, "reasoning_bytes": 109.56, "flops_per_problem": 5721679282.176}, "inc.sumd7": {"acc": 0.764, "reasoning_bytes": 127.366, "flops_per_problem": 6552210014.208}, "inc.sumd8": {"acc": 0.038, "reasoning_bytes": 128.542, "flops_per_problem": 6648308858.88}, "inc.inc6": {"acc": 0.73, "reasoning_bytes": 113.0, "flops_per_problem": 6016423624.704}, "inc.inc7": {"acc": 0.502, "reasoning_bytes": 131.0, "flops_per_problem": 6907104460.8}, "inc.inc8": {"acc": 0.024, "reasoning_bytes": 136.648, "flops_per_problem": 7229318234.112}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 115.88, "flops_per_problem": 6795813519.36}, "runmax.runmax.cmp16": {"acc": 0.998, "reasoning_bytes": 122.192, "flops_per_problem": 7162896973.824}, "sumd.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 83.338, "flops_per_problem": 4917028110.336}, "sumd.runmax.cmp7": {"acc": 0.984, "reasoning_bytes": 91.032, "flops_per_problem": 5300981858.304}, "sumd.runmax.cmp8": {"acc": 0.71, "reasoning_bytes": 93.05, "flops_per_problem": 5434266009.6}, "add.runmax.cmp6": {"acc": 0.998, "reasoning_bytes": 137.04, "flops_per_problem": 7553651834.88}, "add.runmax.cmp7": {"acc": 0.944, "reasoning_bytes": 152.036, "flops_per_problem": 8304247406.592}, "add.runmax.cmp8": {"acc": 0.936, "reasoning_bytes": 155.638, "flops_per_problem": 8551648935.936}, "count.runmax.runmax16": {"acc": 0.974, "reasoning_bytes": 112.836, "flops_per_problem": 6838033416.192}, "count.runmax.runmax18": {"acc": 0.936, "reasoning_bytes": 121.792, "flops_per_problem": 7321884033.024}, "count.runmax.runmax20": {"acc": 0.788, "reasoning_bytes": 128.66, "flops_per_problem": 7713610481.664}, "add.runmax.runmax6": {"acc": 0.958, "reasoning_bytes": 137.928, "flops_per_problem": 7637031714.816}, "add.runmax.runmax7": {"acc": 0.922, "reasoning_bytes": 155.832, "flops_per_problem": 8516053499.904}, "add.runmax.runmax8": {"acc": 0.672, "reasoning_bytes": 165.488, "flops_per_problem": 9030818267.136}, "parity.runmax.runmax16": {"acc": 0.998, "reasoning_bytes": 129.0, "flops_per_problem": 7507722240.0}, "parity.runmax.runmax20": {"acc": 0.428, "reasoning_bytes": 147.42, "flops_per_problem": 8497858314.24}, "parity.runmax.runmax24": {"acc": 0.392, "reasoning_bytes": 168.292, "flops_per_problem": 9596282241.024}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 128.988, "flops_per_problem": 7551355355.136}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 147.204, "flops_per_problem": 8532482162.688}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 166.932, "flops_per_problem": 9580383535.104}, "inc.runmax.count6": {"acc": 1.0, "reasoning_bytes": 121.0, "flops_per_problem": 6624460800.0}, "inc.runmax.count7": {"acc": 0.998, "reasoning_bytes": 136.94, "flops_per_problem": 7372583239.68}, "inc.runmax.count8": {"acc": 0.99, "reasoning_bytes": 137.106, "flops_per_problem": 7424077381.632}, "sumd.runmax.count6": {"acc": 0.998, "reasoning_bytes": 84.424, "flops_per_problem": 5053315350.528}, "sumd.runmax.count7": {"acc": 0.98, "reasoning_bytes": 92.186, "flops_per_problem": 5440272187.392}, "sumd.runmax.count8": {"acc": 0.756, "reasoning_bytes": 94.948, "flops_per_problem": 5606413664.256}, "runmax.runmax.find12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6271156224.0}, "runmax.runmax.find14": {"acc": 1.0, "reasoning_bytes": 116.88, "flops_per_problem": 6884139663.36}, "runmax.runmax.find16": {"acc": 0.992, "reasoning_bytes": 122.978, "flops_per_problem": 7241772220.416}, "add.runmax.find6": {"acc": 1.0, "reasoning_bytes": 138.008, "flops_per_problem": 7640564760.576}, "add.runmax.find7": {"acc": 0.986, "reasoning_bytes": 155.138, "flops_per_problem": 8485404327.936}, "add.runmax.find8": {"acc": 0.916, "reasoning_bytes": 160.976, "flops_per_problem": 8831554486.272}, "parity.runmax.find16": {"acc": 0.998, "reasoning_bytes": 128.988, "flops_per_problem": 7507192283.136}, "parity.runmax.find20": {"acc": 0.844, "reasoning_bytes": 147.096, "flops_per_problem": 8483549478.912}, "parity.runmax.find24": {"acc": 0.856, "reasoning_bytes": 166.532, "flops_per_problem": 9518555234.304}, "add.runmax.rev6": {"acc": 0.972, "reasoning_bytes": 132.928, "flops_per_problem": 7283727138.816}, "add.runmax.rev7": {"acc": 0.874, "reasoning_bytes": 149.862, "flops_per_problem": 8119910744.064}, "add.runmax.rev8": {"acc": 0.696, "reasoning_bytes": 152.86, "flops_per_problem": 8340637777.92}, "parity.runmax.rev16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7154417664.0}, "parity.runmax.rev20": {"acc": 0.458, "reasoning_bytes": 142.084, "flops_per_problem": 8129714946.048}, "parity.runmax.rev24": {"acc": 0.442, "reasoning_bytes": 161.772, "flops_per_problem": 9175849795.584}, "sumd.runmax.rev6": {"acc": 0.998, "reasoning_bytes": 79.542, "flops_per_problem": 4661058945.024}, "sumd.runmax.rev7": {"acc": 0.924, "reasoning_bytes": 86.898, "flops_per_problem": 5030085574.656}, "sumd.runmax.rev8": {"acc": 0.304, "reasoning_bytes": 89.142, "flops_per_problem": 5173350580.224}, "sumd.runmax.sumd6": {"acc": 0.998, "reasoning_bytes": 82.542, "flops_per_problem": 4837711233.024}, "sumd.runmax.sumd7": {"acc": 0.92, "reasoning_bytes": 89.928, "flops_per_problem": 5208062754.816}, "sumd.runmax.sumd8": {"acc": 0.344, "reasoning_bytes": 92.482, "flops_per_problem": 5365636595.712}, "add.runmax.sumd6": {"acc": 0.964, "reasoning_bytes": 135.944, "flops_per_problem": 7461086035.968}, "add.runmax.sumd7": {"acc": 0.912, "reasoning_bytes": 153.8, "flops_per_problem": 8337987993.6}, "add.runmax.sumd8": {"acc": 0.67, "reasoning_bytes": 161.536, "flops_per_problem": 8767959662.592}, "parity.runmax.sumd16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.runmax.sumd20": {"acc": 0.416, "reasoning_bytes": 145.396, "flops_per_problem": 8320146112.512}, "parity.runmax.sumd24": {"acc": 0.422, "reasoning_bytes": 167.336, "flops_per_problem": 9465736200.192}, "count.runmax.inc16": {"acc": 0.984, "reasoning_bytes": 111.916, "flops_per_problem": 6664914173.952}, "count.runmax.inc18": {"acc": 0.896, "reasoning_bytes": 119.886, "flops_per_problem": 7105220001.792}, "count.runmax.inc20": {"acc": 0.744, "reasoning_bytes": 126.778, "flops_per_problem": 7497918038.016}, "runmax.runmax.inc12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6125683064.832}, "runmax.runmax.inc14": {"acc": 1.0, "reasoning_bytes": 115.82, "flops_per_problem": 6739373113.344}, "runmax.runmax.inc16": {"acc": 0.984, "reasoning_bytes": 122.144, "flops_per_problem": 7109636308.992}, "add.runmax.inc6": {"acc": 0.946, "reasoning_bytes": 136.928, "flops_per_problem": 7480429461.504}, "add.runmax.inc7": {"acc": 0.824, "reasoning_bytes": 154.384, "flops_per_problem": 8339401211.904}, "add.runmax.inc8": {"acc": 0.638, "reasoning_bytes": 159.486, "flops_per_problem": 8654372241.408}, "count.count.cmp16": {"acc": 0.998, "reasoning_bytes": 111.988, "flops_per_problem": 6800583131.136}, "count.count.cmp18": {"acc": 0.978, "reasoning_bytes": 120.794, "flops_per_problem": 7277809287.168}, "count.count.cmp20": {"acc": 0.962, "reasoning_bytes": 127.206, "flops_per_problem": 7649309048.832}, "add.count.cmp6": {"acc": 0.982, "reasoning_bytes": 131.374, "flops_per_problem": 7347586940.928}, "add.count.cmp7": {"acc": 0.914, "reasoning_bytes": 143.038, "flops_per_problem": 7951031156.736}, "add.count.cmp8": {"acc": 0.882, "reasoning_bytes": 149.096, "flops_per_problem": 8306897190.912}, "sumd.count.cmp6": {"acc": 1.0, "reasoning_bytes": 82.492, "flops_per_problem": 4923829223.424}, "sumd.count.cmp7": {"acc": 0.982, "reasoning_bytes": 89.478, "flops_per_problem": 5276515516.416}, "sumd.count.cmp8": {"acc": 0.948, "reasoning_bytes": 91.516, "flops_per_problem": 5410682929.152}, "add.count.runmax6": {"acc": 0.904, "reasoning_bytes": 132.76, "flops_per_problem": 7452960030.72}, "add.count.runmax7": {"acc": 0.672, "reasoning_bytes": 148.612, "flops_per_problem": 8241359192.064}, "add.count.runmax8": {"acc": 0.526, "reasoning_bytes": 154.214, "flops_per_problem": 8577263517.696}, "sumd.count.runmax6": {"acc": 0.996, "reasoning_bytes": 83.428, "flops_per_problem": 5009328930.816}, "sumd.count.runmax7": {"acc": 0.924, "reasoning_bytes": 90.766, "flops_per_problem": 5377560625.152}, "sumd.count.runmax8": {"acc": 0.502, "reasoning_bytes": 93.29, "flops_per_problem": 5533191290.88}, "inc.count.runmax6": {"acc": 0.974, "reasoning_bytes": 115.996, "flops_per_problem": 6403468787.712}, "inc.count.runmax7": {"acc": 0.904, "reasoning_bytes": 130.426, "flops_per_problem": 7085169967.104}, "inc.count.runmax8": {"acc": 0.776, "reasoning_bytes": 131.012, "flops_per_problem": 7154947620.864}, "parity.count.count16": {"acc": 1.0, "reasoning_bytes": 128.988, "flops_per_problem": 7595518427.136}, "parity.count.count20": {"acc": 1.0, "reasoning_bytes": 146.976, "flops_per_problem": 8566576054.272}, "parity.count.count24": {"acc": 0.97, "reasoning_bytes": 167.104, "flops_per_problem": 9644508315.648}, "runmax.count.count12": {"acc": 1.0, "reasoning_bytes": 105.008, "flops_per_problem": 6359835672.576}, "runmax.count.count14": {"acc": 1.0, "reasoning_bytes": 116.724, "flops_per_problem": 6965576368.128}, "runmax.count.count16": {"acc": 0.994, "reasoning_bytes": 123.322, "flops_per_problem": 7345113808.896}, "inc.count.count6": {"acc": 0.998, "reasoning_bytes": 116.0, "flops_per_problem": 6447808512.0}, "inc.count.count7": {"acc": 0.992, "reasoning_bytes": 130.256, "flops_per_problem": 7121560338.432}, "inc.count.count8": {"acc": 0.948, "reasoning_bytes": 131.042, "flops_per_problem": 7200347258.88}, "inc.count.find6": {"acc": 0.99, "reasoning_bytes": 115.994, "flops_per_problem": 6403380461.568}, "inc.count.find7": {"acc": 0.974, "reasoning_bytes": 130.684, "flops_per_problem": 7096210735.104}, "inc.count.find8": {"acc": 0.93, "reasoning_bytes": 128.622, "flops_per_problem": 7049397878.784}, "add.count.find6": {"acc": 0.968, "reasoning_bytes": 132.356, "flops_per_problem": 7435118149.632}, "add.count.find7": {"acc": 0.884, "reasoning_bytes": 146.988, "flops_per_problem": 8169638363.136}, "add.count.find8": {"acc": 0.842, "reasoning_bytes": 152.858, "flops_per_problem": 8517996675.072}, "runmax.count.find12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6315319296.0}, "runmax.count.find14": {"acc": 1.0, "reasoning_bytes": 116.73, "flops_per_problem": 6921678274.56}, "runmax.count.find16": {"acc": 0.788, "reasoning_bytes": 120.87, "flops_per_problem": 7192662884.352}, "parity.count.rev16": {"acc": 1.0, "reasoning_bytes": 123.988, "flops_per_problem": 7198050779.136}, "parity.count.rev20": {"acc": 1.0, "reasoning_bytes": 141.988, "flops_per_problem": 8169638363.136}, "parity.count.rev24": {"acc": 0.996, "reasoning_bytes": 161.48, "flops_per_problem": 9207117250.56}, "inc.count.rev6": {"acc": 0.976, "reasoning_bytes": 110.996, "flops_per_problem": 6050164211.712}, "inc.count.rev7": {"acc": 0.918, "reasoning_bytes": 124.432, "flops_per_problem": 6687967297.536}, "inc.count.rev8": {"acc": 0.78, "reasoning_bytes": 125.518, "flops_per_problem": 6779826487.296}, "runmax.count.rev12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5962014720.0}, "runmax.count.rev14": {"acc": 1.0, "reasoning_bytes": 111.652, "flops_per_problem": 6564928978.944}, "runmax.count.rev16": {"acc": 0.998, "reasoning_bytes": 118.16, "flops_per_problem": 6940668395.52}, "count.count.sumd16": {"acc": 1.0, "reasoning_bytes": 110.964, "flops_per_problem": 6711197073.408}, "count.count.sumd18": {"acc": 1.0, "reasoning_bytes": 119.554, "flops_per_problem": 7178884005.888}, "count.count.sumd20": {"acc": 0.998, "reasoning_bytes": 126.284, "flops_per_problem": 7564427624.448}, "runmax.count.sumd12": {"acc": 1.0, "reasoning_bytes": 103.0, "flops_per_problem": 6138667008.0}, "runmax.count.sumd14": {"acc": 0.996, "reasoning_bytes": 114.892, "flops_per_problem": 6752180404.224}, "runmax.count.sumd16": {"acc": 0.922, "reasoning_bytes": 122.75, "flops_per_problem": 7185596792.832}, "sumd.count.sumd6": {"acc": 0.998, "reasoning_bytes": 81.428, "flops_per_problem": 4832676642.816}, "sumd.count.sumd7": {"acc": 0.934, "reasoning_bytes": 88.796, "flops_per_problem": 5202233229.312}, "sumd.count.sumd8": {"acc": 0.59, "reasoning_bytes": 91.786, "flops_per_problem": 5378443886.592}, "parity.count.inc16": {"acc": 1.0, "reasoning_bytes": 127.988, "flops_per_problem": 7374703067.136}, "parity.count.inc20": {"acc": 1.0, "reasoning_bytes": 145.988, "flops_per_problem": 8346290651.136}, "parity.count.inc24": {"acc": 0.404, "reasoning_bytes": 159.734, "flops_per_problem": 9221602738.176}, "count.count.inc16": {"acc": 1.0, "reasoning_bytes": 111.908, "flops_per_problem": 6708723941.376}, "count.count.inc18": {"acc": 1.0, "reasoning_bytes": 120.172, "flops_per_problem": 7162013712.384}, "count.count.inc20": {"acc": 0.98, "reasoning_bytes": 127.078, "flops_per_problem": 7555330031.616}, "add.count.inc6": {"acc": 0.912, "reasoning_bytes": 131.746, "flops_per_problem": 7275777785.856}, "add.count.inc7": {"acc": 0.576, "reasoning_bytes": 145.512, "flops_per_problem": 7971964452.864}, "add.count.inc8": {"acc": 0.52, "reasoning_bytes": 150.556, "flops_per_problem": 8283049132.032}, "parity.rev.cmp16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 7066091520.0}, "parity.rev.cmp20": {"acc": 0.932, "reasoning_bytes": 140.976, "flops_per_problem": 8036619190.272}, "parity.rev.cmp24": {"acc": 0.946, "reasoning_bytes": 159.168, "flops_per_problem": 9016686084.096}, "sumd.rev.cmp6": {"acc": 0.98, "reasoning_bytes": 81.144, "flops_per_problem": 4731631534.08}, "sumd.rev.cmp7": {"acc": 0.906, "reasoning_bytes": 88.702, "flops_per_problem": 5109755756.544}, "sumd.rev.cmp8": {"acc": 0.688, "reasoning_bytes": 90.448, "flops_per_problem": 5230939226.112}, "add.rev.cmp6": {"acc": 0.948, "reasoning_bytes": 157.72, "flops_per_problem": 8583711326.208}, "add.rev.cmp7": {"acc": 0.912, "reasoning_bytes": 181.31, "flops_per_problem": 9756594192.384}, "add.rev.cmp8": {"acc": 0.79, "reasoning_bytes": 196.07, "flops_per_problem": 10541460307.968}, "runmax.rev.runmax12": {"acc": 1.0, "reasoning_bytes": 99.988, "flops_per_problem": 5917321691.136}, "runmax.rev.runmax14": {"acc": 1.0, "reasoning_bytes": 111.82, "flops_per_problem": 6528185303.04}, "runmax.rev.runmax16": {"acc": 0.998, "reasoning_bytes": 118.32, "flops_per_problem": 6903571415.04}, "count.rev.runmax16": {"acc": 0.972, "reasoning_bytes": 107.888, "flops_per_problem": 6487025319.936}, "count.rev.runmax18": {"acc": 0.916, "reasoning_bytes": 116.308, "flops_per_problem": 6947204530.176}, "count.rev.runmax20": {"acc": 0.764, "reasoning_bytes": 123.162, "flops_per_problem": 7338224369.664}, "add.rev.runmax6": {"acc": 0.978, "reasoning_bytes": 185.216, "flops_per_problem": 9592925847.552}, "add.rev.runmax7": {"acc": 0.85, "reasoning_bytes": 214.232, "flops_per_problem": 10962687688.704}, "add.rev.runmax8": {"acc": 0.638, "reasoning_bytes": 220.526, "flops_per_problem": 11328976207.872}, "inc.rev.count6": {"acc": 0.924, "reasoning_bytes": 156.022, "flops_per_problem": 8038650691.584}, "inc.rev.count7": {"acc": 0.746, "reasoning_bytes": 182.174, "flops_per_problem": 9237501444.096}, "inc.rev.count8": {"acc": 0.666, "reasoning_bytes": 183.492, "flops_per_problem": 9340136423.424}, "count.rev.count16": {"acc": 1.0, "reasoning_bytes": 107.946, "flops_per_problem": 6533749850.112}, "count.rev.count18": {"acc": 1.0, "reasoning_bytes": 116.65, "flops_per_problem": 7006471372.8}, "count.rev.count20": {"acc": 0.998, "reasoning_bytes": 123.114, "flops_per_problem": 7380267614.208}, "parity.rev.count16": {"acc": 1.0, "reasoning_bytes": 123.988, "flops_per_problem": 7198050779.136}, "parity.rev.count20": {"acc": 1.0, "reasoning_bytes": 142.012, "flops_per_problem": 8170698276.864}, "parity.rev.count24": {"acc": 1.0, "reasoning_bytes": 160.454, "flops_per_problem": 9161805938.688}, "sumd.rev.find6": {"acc": 0.992, "reasoning_bytes": 85.232, "flops_per_problem": 4912346824.704}, "sumd.rev.find7": {"acc": 0.946, "reasoning_bytes": 92.824, "flops_per_problem": 5291795939.328}, "sumd.rev.find8": {"acc": 0.702, "reasoning_bytes": 95.074, "flops_per_problem": 5435325923.328}, "runmax.rev.find12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5917851648.0}, "runmax.rev.find14": {"acc": 1.0, "reasoning_bytes": 111.808, "flops_per_problem": 6527655346.176}, "runmax.rev.find16": {"acc": 1.0, "reasoning_bytes": 118.08, "flops_per_problem": 6892972277.76}, "count.rev.find16": {"acc": 0.99, "reasoning_bytes": 107.91, "flops_per_problem": 6487996907.52}, "count.rev.find18": {"acc": 0.962, "reasoning_bytes": 115.826, "flops_per_problem": 6925917929.472}, "count.rev.find20": {"acc": 0.932, "reasoning_bytes": 122.778, "flops_per_problem": 7321265750.016}, "count.rev.rev16": {"acc": 0.956, "reasoning_bytes": 102.826, "flops_per_problem": 6130982633.472}, "count.rev.rev18": {"acc": 0.862, "reasoning_bytes": 110.24, "flops_per_problem": 6546733793.28}, "count.rev.rev20": {"acc": 0.716, "reasoning_bytes": 117.41, "flops_per_problem": 6951709163.52}, "sumd.rev.rev6": {"acc": 0.978, "reasoning_bytes": 80.532, "flops_per_problem": 4616365916.16}, "sumd.rev.rev7": {"acc": 0.728, "reasoning_bytes": 87.122, "flops_per_problem": 4951386980.352}, "sumd.rev.rev8": {"acc": 0.112, "reasoning_bytes": 89.07, "flops_per_problem": 5081933021.184}, "parity.rev.rev16": {"acc": 0.998, "reasoning_bytes": 118.964, "flops_per_problem": 6799523217.408}, "parity.rev.rev20": {"acc": 0.528, "reasoning_bytes": 137.0, "flops_per_problem": 7772700672.0}, "parity.rev.rev24": {"acc": 0.436, "reasoning_bytes": 155.36, "flops_per_problem": 8760186961.92}, "sumd.rev.sumd6": {"acc": 0.998, "reasoning_bytes": 84.728, "flops_per_problem": 4810595106.816}, "sumd.rev.sumd7": {"acc": 0.87, "reasoning_bytes": 91.896, "flops_per_problem": 5173350580.224}, "sumd.rev.sumd8": {"acc": 0.286, "reasoning_bytes": 94.196, "flops_per_problem": 5319971979.264}, "parity.rev.sumd16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.rev.sumd20": {"acc": 0.474, "reasoning_bytes": 140.06, "flops_per_problem": 7952002744.32}, "parity.rev.sumd24": {"acc": 0.45, "reasoning_bytes": 160.452, "flops_per_problem": 9029228396.544}, "add.rev.sumd6": {"acc": 0.516, "reasoning_bytes": 190.938, "flops_per_problem": 9801463873.536}, "add.rev.sumd7": {"acc": 0.072, "reasoning_bytes": 217.632, "flops_per_problem": 11068679061.504}, "add.rev.sumd8": {"acc": 0.022, "reasoning_bytes": 223.046, "flops_per_problem": 11394337554.432}, "parity.rev.inc16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 6977765376.0}, "parity.rev.inc20": {"acc": 0.48, "reasoning_bytes": 141.024, "flops_per_problem": 7950412873.728}, "parity.rev.inc24": {"acc": 0.422, "reasoning_bytes": 160.632, "flops_per_problem": 8993014677.504}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 98.988, "flops_per_problem": 5771848531.968}, "runmax.rev.inc14": {"acc": 1.0, "reasoning_bytes": 110.136, "flops_per_problem": 6355860996.096}, "runmax.rev.inc16": {"acc": 0.994, "reasoning_bytes": 117.048, "flops_per_problem": 6751915425.792}, "inc.rev.inc6": {"acc": 0.32, "reasoning_bytes": 170.09, "flops_per_problem": 8698005356.544}, "inc.rev.inc7": {"acc": 0.024, "reasoning_bytes": 199.206, "flops_per_problem": 10070946938.88}, "inc.rev.inc8": {"acc": 0.004, "reasoning_bytes": 201.236, "flops_per_problem": 10224457777.152}, "parity.sumd.cmp16": {"acc": 0.998, "reasoning_bytes": 125.988, "flops_per_problem": 7242213851.136}, "parity.sumd.cmp20": {"acc": 0.92, "reasoning_bytes": 144.0, "flops_per_problem": 8214331392.0}, "parity.sumd.cmp24": {"acc": 0.948, "reasoning_bytes": 161.808, "flops_per_problem": 9177439666.176}, "runmax.sumd.cmp12": {"acc": 1.0, "reasoning_bytes": 102.0, "flops_per_problem": 6006177792.0}, "runmax.sumd.cmp14": {"acc": 1.0, "reasoning_bytes": 113.724, "flops_per_problem": 6612271792.128}, "runmax.sumd.cmp16": {"acc": 1.0, "reasoning_bytes": 120.168, "flops_per_problem": 6985184772.096}, "count.sumd.cmp16": {"acc": 0.992, "reasoning_bytes": 109.94, "flops_per_problem": 6577647943.68}, "count.sumd.cmp18": {"acc": 0.952, "reasoning_bytes": 116.746, "flops_per_problem": 6966547955.712}, "count.sumd.cmp20": {"acc": 0.906, "reasoning_bytes": 124.592, "flops_per_problem": 7401377562.624}, "sumd.sumd.runmax6": {"acc": 0.996, "reasoning_bytes": 84.308, "flops_per_problem": 4915703218.176}, "sumd.sumd.runmax7": {"acc": 0.858, "reasoning_bytes": 91.63, "flops_per_problem": 5283228303.36}, "sumd.sumd.runmax8": {"acc": 0.336, "reasoning_bytes": 94.274, "flops_per_problem": 5445130125.312}, "count.sumd.runmax16": {"acc": 0.984, "reasoning_bytes": 110.886, "flops_per_problem": 6663589281.792}, "count.sumd.runmax18": {"acc": 0.898, "reasoning_bytes": 118.9, "flops_per_problem": 7105838284.8}, "count.sumd.runmax20": {"acc": 0.762, "reasoning_bytes": 126.134, "flops_per_problem": 7513640091.648}, "add.sumd.runmax6": {"acc": 0.844, "reasoning_bytes": 151.534, "flops_per_problem": 8149588328.448}, "add.sumd.runmax7": {"acc": 0.492, "reasoning_bytes": 170.466, "flops_per_problem": 9074009751.552}, "add.sumd.runmax8": {"acc": 0.18, "reasoning_bytes": 177.544, "flops_per_problem": 9475098771.456}, "parity.sumd.count16": {"acc": 1.0, "reasoning_bytes": 126.988, "flops_per_problem": 7374703067.136}, "parity.sumd.count20": {"acc": 1.0, "reasoning_bytes": 145.06, "flops_per_problem": 8349470392.32}, "parity.sumd.count24": {"acc": 1.0, "reasoning_bytes": 164.13, "flops_per_problem": 9368312463.36}, "sumd.sumd.count6": {"acc": 1.0, "reasoning_bytes": 84.168, "flops_per_problem": 4953683460.096}, "sumd.sumd.count7": {"acc": 0.95, "reasoning_bytes": 91.792, "flops_per_problem": 5334545793.024}, "sumd.sumd.count8": {"acc": 0.682, "reasoning_bytes": 94.98, "flops_per_problem": 5519500738.56}, "add.sumd.count6": {"acc": 0.932, "reasoning_bytes": 150.6, "flops_per_problem": 8152503091.2}, "add.sumd.count7": {"acc": 0.728, "reasoning_bytes": 168.462, "flops_per_problem": 9029670027.264}, "add.sumd.count8": {"acc": 0.702, "reasoning_bytes": 174.734, "flops_per_problem": 9395075284.992}, "runmax.sumd.find12": {"acc": 1.0, "reasoning_bytes": 103.0, "flops_per_problem": 6094503936.0}, "runmax.sumd.find14": {"acc": 1.0, "reasoning_bytes": 114.808, "flops_per_problem": 6704307634.176}, "runmax.sumd.find16": {"acc": 0.98, "reasoning_bytes": 121.278, "flops_per_problem": 7078368854.016}, "sumd.sumd.find6": {"acc": 0.998, "reasoning_bytes": 84.046, "flops_per_problem": 4904132493.312}, "sumd.sumd.find7": {"acc": 0.95, "reasoning_bytes": 91.646, "flops_per_problem": 5283934912.512}, "sumd.sumd.find8": {"acc": 0.8, "reasoning_bytes": 94.198, "flops_per_problem": 5440802144.256}, "parity.sumd.find16": {"acc": 0.998, "reasoning_bytes": 126.988, "flops_per_problem": 7330539995.136}, "parity.sumd.find20": {"acc": 0.828, "reasoning_bytes": 145.0, "flops_per_problem": 8302657536.0}, "parity.sumd.find24": {"acc": 0.86, "reasoning_bytes": 163.752, "flops_per_problem": 9307455750.144}, "count.sumd.rev16": {"acc": 0.978, "reasoning_bytes": 105.826, "flops_per_problem": 6307634921.472}, "count.sumd.rev18": {"acc": 0.864, "reasoning_bytes": 113.072, "flops_per_problem": 6715966685.184}, "count.sumd.rev20": {"acc": 0.708, "reasoning_bytes": 120.31, "flops_per_problem": 7123945144.32}, "parity.sumd.rev16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.sumd.rev20": {"acc": 0.468, "reasoning_bytes": 140.036, "flops_per_problem": 7950942830.592}, "parity.sumd.rev24": {"acc": 0.444, "reasoning_bytes": 159.608, "flops_per_problem": 8991954763.776}, "add.sumd.rev6": {"acc": 0.834, "reasoning_bytes": 145.472, "flops_per_problem": 7793280663.552}, "add.sumd.rev7": {"acc": 0.206, "reasoning_bytes": 161.078, "flops_per_problem": 8567459315.712}, "add.sumd.rev8": {"acc": 0.046, "reasoning_bytes": 165.66, "flops_per_problem": 8858052329.472}, "parity.sumd.sumd16": {"acc": 1.0, "reasoning_bytes": 125.0, "flops_per_problem": 7154417664.0}, "parity.sumd.sumd20": {"acc": 0.438, "reasoning_bytes": 143.156, "flops_per_problem": 8132894687.232}, "parity.sumd.sumd24": {"acc": 0.442, "reasoning_bytes": 164.3, "flops_per_problem": 9260024610.816}, "add.sumd.sumd6": {"acc": 0.72, "reasoning_bytes": 149.642, "flops_per_problem": 7984948396.032}, "add.sumd.sumd7": {"acc": 0.152, "reasoning_bytes": 166.736, "flops_per_problem": 8826431569.92}, "add.sumd.sumd8": {"acc": 0.056, "reasoning_bytes": 171.36, "flops_per_problem": 9117731192.832}, "count.sumd.sumd16": {"acc": 0.98, "reasoning_bytes": 108.826, "flops_per_problem": 6484287209.472}, "count.sumd.sumd18": {"acc": 0.864, "reasoning_bytes": 115.994, "flops_per_problem": 6889174253.568}, "count.sumd.sumd20": {"acc": 0.724, "reasoning_bytes": 123.412, "flops_per_problem": 7305102065.664}, "inc.sumd.inc6": {"acc": 0.912, "reasoning_bytes": 135.522, "flops_per_problem": 7044981571.584}, "inc.sumd.inc7": {"acc": 0.476, "reasoning_bytes": 151.53, "flops_per_problem": 7796195426.304}, "inc.sumd.inc8": {"acc": 0.058, "reasoning_bytes": 153.134, "flops_per_problem": 7910842761.216}, "sumd.sumd.inc6": {"acc": 0.998, "reasoning_bytes": 83.726, "flops_per_problem": 4771819929.6}, "sumd.sumd.inc7": {"acc": 0.862, "reasoning_bytes": 91.2, "flops_per_problem": 5147294367.744}, "sumd.sumd.inc8": {"acc": 0.272, "reasoning_bytes": 94.062, "flops_per_problem": 5318470434.816}, "parity.sumd.inc16": {"acc": 1.0, "reasoning_bytes": 126.0, "flops_per_problem": 7154417664.0}, "parity.sumd.inc20": {"acc": 0.426, "reasoning_bytes": 144.04, "flops_per_problem": 8127771770.88}, "parity.sumd.inc24": {"acc": 0.422, "reasoning_bytes": 164.69, "flops_per_problem": 9216391495.68}, "inc.inc.cmp6": {"acc": 0.944, "reasoning_bytes": 145.406, "flops_per_problem": 7702304735.232}, "inc.inc.cmp7": {"acc": 0.934, "reasoning_bytes": 166.75, "flops_per_problem": 8733777444.864}, "inc.inc.cmp8": {"acc": 0.856, "reasoning_bytes": 185.284, "flops_per_problem": 9639827030.016}, "runmax.inc.cmp12": {"acc": 0.964, "reasoning_bytes": 105.568, "flops_per_problem": 6150856015.872}, "runmax.inc.cmp14": {"acc": 0.956, "reasoning_bytes": 117.71, "flops_per_problem": 6779473182.72}, "runmax.inc.cmp16": {"acc": 0.954, "reasoning_bytes": 124.022, "flops_per_problem": 7147793203.2}, "sumd.inc.cmp6": {"acc": 0.988, "reasoning_bytes": 88.192, "flops_per_problem": 5042892865.536}, "sumd.inc.cmp7": {"acc": 0.972, "reasoning_bytes": 95.904, "flops_per_problem": 5427818201.088}, "sumd.inc.cmp8": {"acc": 0.92, "reasoning_bytes": 98.536, "flops_per_problem": 5588218478.592}, "sumd.inc.runmax6": {"acc": 0.99, "reasoning_bytes": 93.506, "flops_per_problem": 5277752082.432}, "sumd.inc.runmax7": {"acc": 0.826, "reasoning_bytes": 100.46, "flops_per_problem": 5629025157.12}, "sumd.inc.runmax8": {"acc": 0.242, "reasoning_bytes": 102.784, "flops_per_problem": 5775823208.448}, "runmax.inc.runmax12": {"acc": 0.996, "reasoning_bytes": 109.644, "flops_per_problem": 6343760314.368}, "runmax.inc.runmax14": {"acc": 0.982, "reasoning_bytes": 121.892, "flops_per_problem": 6972995764.224}, "runmax.inc.runmax16": {"acc": 0.916, "reasoning_bytes": 128.886, "flops_per_problem": 7370198433.792}, "add.inc.runmax6": {"acc": 0.944, "reasoning_bytes": 193.35, "flops_per_problem": 9951529992.192}, "add.inc.runmax7": {"acc": 0.848, "reasoning_bytes": 221.2, "flops_per_problem": 11268737777.664}, "add.inc.runmax8": {"acc": 0.656, "reasoning_bytes": 223.008, "flops_per_problem": 11438588952.576}, "runmax.inc.count12": {"acc": 0.998, "reasoning_bytes": 108.916, "flops_per_problem": 6355772669.952}, "runmax.inc.count14": {"acc": 0.99, "reasoning_bytes": 121.23, "flops_per_problem": 6987922882.56}, "runmax.inc.count16": {"acc": 0.928, "reasoning_bytes": 127.934, "flops_per_problem": 7372318261.248}, "sumd.inc.count6": {"acc": 0.994, "reasoning_bytes": 92.388, "flops_per_problem": 5272540839.936}, "sumd.inc.count7": {"acc": 0.908, "reasoning_bytes": 99.52, "flops_per_problem": 5631674941.44}, "sumd.inc.count8": {"acc": 0.514, "reasoning_bytes": 102.214, "flops_per_problem": 5794813329.408}, "inc.inc.count6": {"acc": 0.876, "reasoning_bytes": 166.002, "flops_per_problem": 8479221497.856}, "inc.inc.count7": {"acc": 0.75, "reasoning_bytes": 189.442, "flops_per_problem": 9558566977.536}, "inc.inc.count8": {"acc": 0.668, "reasoning_bytes": 191.394, "flops_per_problem": 9690172932.096}, "parity.inc.find16": {"acc": 1.0, "reasoning_bytes": 127.988, "flops_per_problem": 7330539995.136}, "parity.inc.find20": {"acc": 0.86, "reasoning_bytes": 146.0, "flops_per_problem": 8302657536.0}, "parity.inc.find24": {"acc": 0.854, "reasoning_bytes": 165.332, "flops_per_problem": 9333070331.904}, "sumd.inc.find6": {"acc": 0.986, "reasoning_bytes": 92.04, "flops_per_problem": 5213009018.88}, "sumd.inc.find7": {"acc": 0.944, "reasoning_bytes": 99.704, "flops_per_problem": 5595637874.688}, "sumd.inc.find8": {"acc": 0.712, "reasoning_bytes": 102.28, "flops_per_problem": 5753565020.16}, "count.inc.find16": {"acc": 0.986, "reasoning_bytes": 111.926, "flops_per_problem": 6665355804.672}, "count.inc.find18": {"acc": 0.96, "reasoning_bytes": 119.622, "flops_per_problem": 7093560950.784}, "count.inc.find20": {"acc": 0.92, "reasoning_bytes": 126.778, "flops_per_problem": 7497918038.016}, "sumd.inc.rev6": {"acc": 0.998, "reasoning_bytes": 87.524, "flops_per_problem": 4925154115.584}, "sumd.inc.rev7": {"acc": 0.808, "reasoning_bytes": 94.314, "flops_per_problem": 5269184446.464}, "sumd.inc.rev8": {"acc": 0.136, "reasoning_bytes": 96.438, "flops_per_problem": 5406796578.816}, "count.inc.rev16": {"acc": 0.978, "reasoning_bytes": 106.878, "flops_per_problem": 6309931401.216}, "count.inc.rev18": {"acc": 0.866, "reasoning_bytes": 114.144, "flops_per_problem": 6719146426.368}, "count.inc.rev20": {"acc": 0.672, "reasoning_bytes": 121.368, "flops_per_problem": 7126506602.496}, "parity.inc.rev16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 6977765376.0}, "parity.inc.rev20": {"acc": 0.528, "reasoning_bytes": 141.024, "flops_per_problem": 7950412873.728}, "parity.inc.rev24": {"acc": 0.362, "reasoning_bytes": 160.12, "flops_per_problem": 8970403184.64}, "count.inc.sumd16": {"acc": 0.98, "reasoning_bytes": 109.926, "flops_per_problem": 6488703516.672}, "count.inc.sumd18": {"acc": 0.858, "reasoning_bytes": 117.286, "flops_per_problem": 6902069870.592}, "count.inc.sumd20": {"acc": 0.7, "reasoning_bytes": 124.662, "flops_per_problem": 7316142833.664}, "sumd.inc.sumd6": {"acc": 0.994, "reasoning_bytes": 91.736, "flops_per_problem": 5121503133.696}, "sumd.inc.sumd7": {"acc": 0.83, "reasoning_bytes": 98.716, "flops_per_problem": 5472952860.672}, "sumd.inc.sumd8": {"acc": 0.22, "reasoning_bytes": 101.058, "flops_per_problem": 5620634173.44}, "add.inc.sumd6": {"acc": 0.536, "reasoning_bytes": 197.698, "flops_per_problem": 10099829587.968}, "add.inc.sumd7": {"acc": 0.1, "reasoning_bytes": 223.002, "flops_per_problem": 11305746432.0}, "add.inc.sumd8": {"acc": 0.026, "reasoning_bytes": 223.632, "flops_per_problem": 11422955225.088}, "parity.inc.inc16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7154417664.0}, "parity.inc.inc20": {"acc": 0.53, "reasoning_bytes": 145.072, "flops_per_problem": 8129184989.184}, "parity.inc.inc24": {"acc": 0.364, "reasoning_bytes": 167.072, "flops_per_problem": 9277424861.184}, "sumd.inc.inc6": {"acc": 0.916, "reasoning_bytes": 94.5, "flops_per_problem": 5233324032.0}, "sumd.inc.inc7": {"acc": 0.74, "reasoning_bytes": 101.38, "flops_per_problem": 5581329039.36}, "sumd.inc.inc8": {"acc": 0.132, "reasoning_bytes": 103.514, "flops_per_problem": 5719647780.864}, "runmax.inc.inc12": {"acc": 0.98, "reasoning_bytes": 110.06, "flops_per_problem": 6269389701.12}, "runmax.inc.inc14": {"acc": 0.838, "reasoning_bytes": 121.448, "flops_per_problem": 6855963623.424}, "runmax.inc.inc16": {"acc": 0.838, "reasoning_bytes": 129.28, "flops_per_problem": 7291764817.92}, "count.inc.cmp16": {"acc": 0.898, "reasoning_bytes": 110.584, "flops_per_problem": 6568727003.136}, "count.inc.cmp18": {"acc": 0.512, "reasoning_bytes": 117.062, "flops_per_problem": 6957097058.304}, "count.inc.cmp20": {"acc": 0.256, "reasoning_bytes": 124.882, "flops_per_problem": 7371081695.232}, "inc.rev.sumd6": {"acc": 0.6, "reasoning_bytes": 166.216, "flops_per_problem": 8405380841.472}, "inc.rev.sumd7": {"acc": 0.104, "reasoning_bytes": 193.354, "flops_per_problem": 9644331663.36}, "inc.rev.sumd8": {"acc": 0.042, "reasoning_bytes": 195.396, "flops_per_problem": 9777704140.8}, "runmax.inc.find12": {"acc": 1.0, "reasoning_bytes": 108.594, "flops_per_problem": 6297389088.768}, "runmax.inc.find14": {"acc": 0.978, "reasoning_bytes": 120.098, "flops_per_problem": 6893767213.056}, "runmax.inc.find16": {"acc": 0.912, "reasoning_bytes": 127.298, "flops_per_problem": 7300067475.456}, "inc.runmax.cmp6": {"acc": 0.984, "reasoning_bytes": 119.99, "flops_per_problem": 6491264974.848}, "inc.runmax.cmp7": {"acc": 0.976, "reasoning_bytes": 135.478, "flops_per_problem": 7219690684.416}, "inc.runmax.cmp8": {"acc": 0.954, "reasoning_bytes": 136.01, "flops_per_problem": 7287348510.72}} +{"step": 7000, "train_loss": 1.0961651802062988} +{"step": 7020, "train_loss": 1.0394514799118042} +{"step": 7040, "train_loss": 1.0584492683410645} +{"step": 7060, "train_loss": 1.1051770448684692} +{"step": 7080, "train_loss": 1.0217559337615967} +{"step": 7100, "train_loss": 1.0196378231048584} +{"step": 7120, "train_loss": 1.0011072158813477} +{"step": 7140, "train_loss": 1.0350234508514404} +{"step": 7160, "train_loss": 1.0275707244873047} +{"step": 7180, "train_loss": 1.0069799423217773} +{"step": 7200, "train_loss": 1.011110544204712} +{"step": 7220, "train_loss": 0.9871113300323486} +{"step": 7240, "train_loss": 1.054813265800476} +{"step": 7260, "train_loss": 0.9937793016433716} +{"step": 7280, "train_loss": 0.9700550436973572} +{"step": 7300, "train_loss": 1.0255132913589478} +{"step": 7320, "train_loss": 1.0630970001220703} +{"step": 7340, "train_loss": 1.076869249343872} +{"step": 7360, "train_loss": 1.0957372188568115} +{"step": 7380, "train_loss": 1.0519564151763916} +{"step": 7400, "train_loss": 1.0756056308746338} +{"step": 7420, "train_loss": 0.9998865723609924} +{"step": 7440, "train_loss": 0.9163455963134766} +{"step": 7460, "train_loss": 0.9900002479553223} +{"step": 7480, "train_loss": 1.0122487545013428} +{"step": 7500, "train_loss": 1.0787081718444824} +{"step": 7520, "train_loss": 1.0686423778533936} +{"step": 7540, "train_loss": 1.0501917600631714} +{"step": 7560, "train_loss": 0.9991856813430786} +{"step": 7580, "train_loss": 1.0416998863220215} +{"step": 7600, "train_loss": 0.993238091468811} +{"step": 7620, "train_loss": 1.0903477668762207} +{"step": 7640, "train_loss": 1.0695164203643799} +{"step": 7660, "train_loss": 1.0205495357513428} +{"step": 7680, "train_loss": 1.0466041564941406} +{"step": 7700, "train_loss": 1.0207974910736084} +{"step": 7720, "train_loss": 0.9873504042625427} +{"step": 7740, "train_loss": 1.0565235614776611} +{"step": 7760, "train_loss": 1.0767802000045776} +{"step": 7780, "train_loss": 1.0042426586151123} +{"step": 7800, "train_loss": 1.0007362365722656} +{"step": 7820, "train_loss": 1.0499167442321777} +{"step": 7840, "train_loss": 1.0527927875518799} +{"step": 7860, "train_loss": 1.0686559677124023} +{"step": 7880, "train_loss": 1.1326566934585571} +{"step": 7900, "train_loss": 1.0398399829864502} +{"step": 7920, "train_loss": 1.012174129486084} +{"step": 7940, "train_loss": 1.0260447263717651} +{"step": 7960, "train_loss": 1.0103733539581299} +{"step": 7980, "train_loss": 1.019756555557251} +{"step": 8000, "tokens": 262144000, "val_loss": 1.866045069694519, "val_bpb": 0.6726789313799288, "lr": 0.00020868460938776225, "elapsed": 2533.2451300621033, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.284, "reasoning_bytes": 79.0, "flops_per_problem": 4963311009.792}, "add9": {"acc": 0.006, "reasoning_bytes": 88.896, "flops_per_problem": 5545556951.04}, "add10": {"acc": 0.0, "reasoning_bytes": 97.594, "flops_per_problem": 6069860941.824}, "reach14": {"acc": 0.532, "reasoning_bytes": 5.344, "flops_per_problem": 4519825440.768}, "reach16": {"acc": 0.514, "reasoning_bytes": 5.608, "flops_per_problem": 5061441355.776}, "reach18": {"acc": 0.488, "reasoning_bytes": 6.166, "flops_per_problem": 5615864561.664}, "parity24": {"acc": 0.492, "reasoning_bytes": 135.944, "flops_per_problem": 7549412179.968}, "parity28": {"acc": 0.466, "reasoning_bytes": 155.048, "flops_per_problem": 8569755795.456}, "parity32": {"acc": 0.478, "reasoning_bytes": 174.716, "flops_per_problem": 9615007383.552}, "cmp8": {"acc": 0.97, "reasoning_bytes": 5.564, "flops_per_problem": 1349800132.608}, "cmp9": {"acc": 0.98, "reasoning_bytes": 5.444, "flops_per_problem": 1432826707.968}, "cmp10": {"acc": 0.978, "reasoning_bytes": 5.584, "flops_per_problem": 1527335682.048}, "runmax12": {"acc": 1.0, "reasoning_bytes": 71.0, "flops_per_problem": 4151328768.0}, "runmax14": {"acc": 0.99, "reasoning_bytes": 82.208, "flops_per_problem": 4734634622.976}, "runmax16": {"acc": 0.97, "reasoning_bytes": 89.048, "flops_per_problem": 5125036179.456}, "count16": {"acc": 0.958, "reasoning_bytes": 78.86, "flops_per_problem": 4719265873.92}, "count18": {"acc": 0.756, "reasoning_bytes": 85.96, "flops_per_problem": 5121149829.12}, "count20": {"acc": 0.554, "reasoning_bytes": 94.458, "flops_per_problem": 5594754613.248}, "brackets16": {"acc": 0.95, "reasoning_bytes": 55.106, "flops_per_problem": 3714467659.776}, "brackets18": {"acc": 0.934, "reasoning_bytes": 57.578, "flops_per_problem": 3912141570.048}, "brackets20": {"acc": 0.92, "reasoning_bytes": 64.75, "flops_per_problem": 4317293592.576}, "sumd8": {"acc": 0.904, "reasoning_bytes": 58.57, "flops_per_problem": 3381478096.896}, "sumd9": {"acc": 0.658, "reasoning_bytes": 66.27, "flops_per_problem": 3766050127.872}, "sumd10": {"acc": 0.256, "reasoning_bytes": 72.424, "flops_per_problem": 4082169397.248}, "inc8": {"acc": 0.766, "reasoning_bytes": 62.56, "flops_per_problem": 3783627030.528}, "inc9": {"acc": 0.234, "reasoning_bytes": 67.642, "flops_per_problem": 4091885273.088}, "inc10": {"acc": 0.0, "reasoning_bytes": 63.866, "flops_per_problem": 3769229869.056}, "add.cmp6": {"acc": 0.996, "reasoning_bytes": 93.094, "flops_per_problem": 5552888020.992}, "add.cmp7": {"acc": 0.984, "reasoning_bytes": 106.108, "flops_per_problem": 6257377345.536}, "add.cmp8": {"acc": 0.97, "reasoning_bytes": 119.224, "flops_per_problem": 6971494219.776}, "add.runmax6": {"acc": 0.996, "reasoning_bytes": 121.546, "flops_per_problem": 6604234113.024}, "add.runmax7": {"acc": 0.87, "reasoning_bytes": 139.452, "flops_per_problem": 7483255898.112}, "add.runmax8": {"acc": 0.562, "reasoning_bytes": 157.194, "flops_per_problem": 8355034939.392}, "add.count6": {"acc": 0.954, "reasoning_bytes": 116.57, "flops_per_problem": 6428818391.04}, "add.count7": {"acc": 0.788, "reasoning_bytes": 132.57, "flops_per_problem": 7223753687.04}, "add.count8": {"acc": 0.318, "reasoning_bytes": 149.062, "flops_per_problem": 8040417214.464}, "add.find6": {"acc": 0.812, "reasoning_bytes": 109.11, "flops_per_problem": 6055198801.92}, "add.find7": {"acc": 0.596, "reasoning_bytes": 124.64, "flops_per_problem": 6829200801.792}, "add.find8": {"acc": 0.344, "reasoning_bytes": 144.818, "flops_per_problem": 7809797652.48}, "add.rev6": {"acc": 0.904, "reasoning_bytes": 123.684, "flops_per_problem": 6812153856.0}, "add.rev7": {"acc": 0.336, "reasoning_bytes": 146.17, "flops_per_problem": 7938665496.576}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 167.352, "flops_per_problem": 8991248154.624}, "add.sumd6": {"acc": 0.876, "reasoning_bytes": 127.942, "flops_per_problem": 6842008092.672}, "add.sumd7": {"acc": 0.572, "reasoning_bytes": 147.178, "flops_per_problem": 7780120068.096}, "add.sumd8": {"acc": 0.048, "reasoning_bytes": 166.728, "flops_per_problem": 8731569291.264}, "add.inc6": {"acc": 0.336, "reasoning_bytes": 131.79, "flops_per_problem": 7200435585.024}, "add.inc7": {"acc": 0.122, "reasoning_bytes": 151.346, "flops_per_problem": 8206823669.76}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 169.73, "flops_per_problem": 9148910321.664}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5122916352.0}, "runmax.cmp14": {"acc": 0.99, "reasoning_bytes": 96.216, "flops_per_problem": 5618249367.552}, "runmax.cmp16": {"acc": 0.976, "reasoning_bytes": 105.0, "flops_per_problem": 6094503936.0}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.runmax14": {"acc": 0.98, "reasoning_bytes": 96.156, "flops_per_problem": 5659762655.232}, "runmax.runmax16": {"acc": 0.98, "reasoning_bytes": 106.0, "flops_per_problem": 6182830080.0}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5255405568.0}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 96.58, "flops_per_problem": 5722650869.76}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 105.996, "flops_per_problem": 6226816499.712}, "runmax.find12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.find14": {"acc": 0.996, "reasoning_bytes": 96.784, "flops_per_problem": 5687497064.448}, "runmax.find16": {"acc": 0.982, "reasoning_bytes": 106.0, "flops_per_problem": 6182830080.0}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 83.0, "flops_per_problem": 4857937920.0}, "runmax.rev14": {"acc": 0.98, "reasoning_bytes": 91.432, "flops_per_problem": 5318647087.104}, "runmax.rev16": {"acc": 0.97, "reasoning_bytes": 101.0, "flops_per_problem": 5829525504.0}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 86.0, "flops_per_problem": 5034590208.0}, "runmax.sumd14": {"acc": 0.986, "reasoning_bytes": 94.432, "flops_per_problem": 5495299375.104}, "runmax.sumd16": {"acc": 0.972, "reasoning_bytes": 104.052, "flops_per_problem": 6008474271.744}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5065769336.832}, "runmax.inc14": {"acc": 0.96, "reasoning_bytes": 94.836, "flops_per_problem": 5506251816.96}, "runmax.inc16": {"acc": 0.812, "reasoning_bytes": 107.104, "flops_per_problem": 6132837482.496}, "count.cmp16": {"acc": 0.996, "reasoning_bytes": 94.97, "flops_per_problem": 5695711395.84}, "count.cmp18": {"acc": 0.938, "reasoning_bytes": 101.07, "flops_per_problem": 6053520605.184}, "count.cmp20": {"acc": 0.886, "reasoning_bytes": 109.658, "flops_per_problem": 6521207537.664}, "count.runmax16": {"acc": 0.982, "reasoning_bytes": 96.02, "flops_per_problem": 5786245693.44}, "count.runmax18": {"acc": 0.798, "reasoning_bytes": 102.75, "flops_per_problem": 6171789312.0}, "count.runmax20": {"acc": 0.648, "reasoning_bytes": 110.836, "flops_per_problem": 6617218056.192}, "count.count16": {"acc": 1.0, "reasoning_bytes": 96.0, "flops_per_problem": 5829525504.0}, "count.count18": {"acc": 1.0, "reasoning_bytes": 102.85, "flops_per_problem": 6220368691.2}, "count.count20": {"acc": 0.998, "reasoning_bytes": 110.908, "flops_per_problem": 6664560869.376}, "count.find16": {"acc": 0.984, "reasoning_bytes": 96.0, "flops_per_problem": 5785362432.0}, "count.find18": {"acc": 0.892, "reasoning_bytes": 102.608, "flops_per_problem": 6165518155.776}, "count.find20": {"acc": 0.866, "reasoning_bytes": 110.938, "flops_per_problem": 6621722689.536}, "count.rev16": {"acc": 0.964, "reasoning_bytes": 90.97, "flops_per_problem": 5430732963.84}, "count.rev18": {"acc": 0.75, "reasoning_bytes": 96.992, "flops_per_problem": 5785009127.424}, "count.rev20": {"acc": 0.556, "reasoning_bytes": 105.366, "flops_per_problem": 6243156836.352}, "count.sumd16": {"acc": 0.97, "reasoning_bytes": 93.97, "flops_per_problem": 5607385251.84}, "count.sumd18": {"acc": 0.738, "reasoning_bytes": 99.966, "flops_per_problem": 5960513175.552}, "count.sumd20": {"acc": 0.554, "reasoning_bytes": 108.388, "flops_per_problem": 6420780711.936}, "count.inc16": {"acc": 0.97, "reasoning_bytes": 94.96, "flops_per_problem": 5606943621.12}, "count.inc18": {"acc": 0.716, "reasoning_bytes": 101.076, "flops_per_problem": 5965371113.472}, "count.inc20": {"acc": 0.558, "reasoning_bytes": 109.63, "flops_per_problem": 6431468175.36}, "parity.cmp16": {"acc": 1.0, "reasoning_bytes": 110.94, "flops_per_problem": 6356832583.68}, "parity.cmp20": {"acc": 0.94, "reasoning_bytes": 128.844, "flops_per_problem": 7324180512.768}, "parity.cmp24": {"acc": 0.932, "reasoning_bytes": 146.16, "flops_per_problem": 8265560555.52}, "parity.runmax16": {"acc": 0.978, "reasoning_bytes": 111.856, "flops_per_problem": 6441449029.632}, "parity.runmax20": {"acc": 0.54, "reasoning_bytes": 129.988, "flops_per_problem": 7418866139.136}, "parity.runmax24": {"acc": 0.368, "reasoning_bytes": 149.414, "flops_per_problem": 8453430263.808}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 111.568, "flops_per_problem": 6472893136.896}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 129.76, "flops_per_problem": 7452960030.72}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 147.04, "flops_per_problem": 8392750202.88}, "parity.find16": {"acc": 0.998, "reasoning_bytes": 111.952, "flops_per_problem": 6445688684.544}, "parity.find20": {"acc": 0.872, "reasoning_bytes": 129.952, "flops_per_problem": 7417276268.544}, "parity.find24": {"acc": 0.854, "reasoning_bytes": 160.72, "flops_per_problem": 8952737955.84}, "parity.rev16": {"acc": 0.984, "reasoning_bytes": 106.892, "flops_per_problem": 6089734324.224}, "parity.rev20": {"acc": 0.62, "reasoning_bytes": 124.976, "flops_per_problem": 7065031606.272}, "parity.rev24": {"acc": 0.44, "reasoning_bytes": 142.916, "flops_per_problem": 8033969405.952}, "parity.sumd16": {"acc": 0.976, "reasoning_bytes": 109.832, "flops_per_problem": 6263736827.904}, "parity.sumd20": {"acc": 0.578, "reasoning_bytes": 127.988, "flops_per_problem": 7242213851.136}, "parity.sumd24": {"acc": 0.48, "reasoning_bytes": 146.066, "flops_per_problem": 8217246154.752}, "parity.inc16": {"acc": 0.982, "reasoning_bytes": 110.892, "flops_per_problem": 6266386612.224}, "parity.inc20": {"acc": 0.614, "reasoning_bytes": 128.988, "flops_per_problem": 7242213851.136}, "parity.inc24": {"acc": 0.346, "reasoning_bytes": 155.728, "flops_per_problem": 8599875010.56}, "sumd.cmp6": {"acc": 0.998, "reasoning_bytes": 62.088, "flops_per_problem": 3713407746.048}, "sumd.cmp7": {"acc": 0.998, "reasoning_bytes": 70.096, "flops_per_problem": 4111405350.912}, "sumd.cmp8": {"acc": 0.988, "reasoning_bytes": 77.906, "flops_per_problem": 4500393689.088}, "sumd.runmax6": {"acc": 0.998, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.982, "reasoning_bytes": 75.48, "flops_per_problem": 4349179330.56}, "sumd.runmax8": {"acc": 0.916, "reasoning_bytes": 83.186, "flops_per_problem": 4733839687.68}, "sumd.count6": {"acc": 0.998, "reasoning_bytes": 66.428, "flops_per_problem": 3949415202.816}, "sumd.count7": {"acc": 0.984, "reasoning_bytes": 74.46, "flops_per_problem": 4348296069.12}, "sumd.count8": {"acc": 0.906, "reasoning_bytes": 82.102, "flops_per_problem": 4729953337.344}, "sumd.find6": {"acc": 0.998, "reasoning_bytes": 66.24, "flops_per_problem": 3896949473.28}, "sumd.find7": {"acc": 0.99, "reasoning_bytes": 74.428, "flops_per_problem": 4302719778.816}, "sumd.find8": {"acc": 0.964, "reasoning_bytes": 82.122, "flops_per_problem": 4686673526.784}, "sumd.rev6": {"acc": 0.994, "reasoning_bytes": 61.544, "flops_per_problem": 3601145217.024}, "sumd.rev7": {"acc": 0.972, "reasoning_bytes": 69.48, "flops_per_problem": 3995874754.56}, "sumd.rev8": {"acc": 0.886, "reasoning_bytes": 77.244, "flops_per_problem": 4382831591.424}, "sumd.sumd6": {"acc": 0.996, "reasoning_bytes": 65.744, "flops_per_problem": 3795639386.112}, "sumd.sumd7": {"acc": 0.974, "reasoning_bytes": 73.696, "flops_per_problem": 4193725317.12}, "sumd.sumd8": {"acc": 0.894, "reasoning_bytes": 81.47, "flops_per_problem": 4582448676.864}, "sumd.inc6": {"acc": 0.996, "reasoning_bytes": 68.538, "flops_per_problem": 3910021742.592}, "sumd.inc7": {"acc": 0.976, "reasoning_bytes": 76.428, "flops_per_problem": 4302984757.248}, "sumd.inc8": {"acc": 0.868, "reasoning_bytes": 84.122, "flops_per_problem": 4687645114.368}, "inc.cmp6": {"acc": 0.996, "reasoning_bytes": 78.642, "flops_per_problem": 4577149108.224}, "inc.cmp7": {"acc": 0.994, "reasoning_bytes": 89.702, "flops_per_problem": 5153918828.544}, "inc.cmp8": {"acc": 0.95, "reasoning_bytes": 100.274, "flops_per_problem": 5709136969.728}, "inc.runmax6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5520384000.0}, "inc.runmax7": {"acc": 0.966, "reasoning_bytes": 117.882, "flops_per_problem": 6177618837.504}, "inc.runmax8": {"acc": 0.872, "reasoning_bytes": 121.13, "flops_per_problem": 6365223567.36}, "inc.count6": {"acc": 0.984, "reasoning_bytes": 99.0, "flops_per_problem": 5343731712.0}, "inc.count7": {"acc": 0.862, "reasoning_bytes": 108.976, "flops_per_problem": 5828465590.272}, "inc.count8": {"acc": 0.736, "reasoning_bytes": 114.078, "flops_per_problem": 6097948655.616}, "inc.find6": {"acc": 0.876, "reasoning_bytes": 91.952, "flops_per_problem": 4988307308.544}, "inc.find7": {"acc": 0.762, "reasoning_bytes": 102.476, "flops_per_problem": 5497242550.272}, "inc.find8": {"acc": 0.246, "reasoning_bytes": 87.334, "flops_per_problem": 4872688386.048}, "inc.rev6": {"acc": 0.994, "reasoning_bytes": 104.01, "flops_per_problem": 5609328427.008}, "inc.rev7": {"acc": 0.626, "reasoning_bytes": 123.14, "flops_per_problem": 6539844354.048}, "inc.rev8": {"acc": 0.002, "reasoning_bytes": 126.256, "flops_per_problem": 6725240930.304}, "inc.sumd6": {"acc": 0.976, "reasoning_bytes": 109.566, "flops_per_problem": 5721855934.464}, "inc.sumd7": {"acc": 0.656, "reasoning_bytes": 126.594, "flops_per_problem": 6517939470.336}, "inc.sumd8": {"acc": 0.076, "reasoning_bytes": 129.814, "flops_per_problem": 6704660938.752}, "inc.inc6": {"acc": 0.678, "reasoning_bytes": 113.0, "flops_per_problem": 6020221648.896}, "inc.inc7": {"acc": 0.286, "reasoning_bytes": 130.306, "flops_per_problem": 6886082838.528}, "inc.inc8": {"acc": 0.01, "reasoning_bytes": 133.972, "flops_per_problem": 7111756136.448}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 0.998, "reasoning_bytes": 114.908, "flops_per_problem": 6752887013.376}, "runmax.runmax.cmp16": {"acc": 0.996, "reasoning_bytes": 122.0, "flops_per_problem": 7154417664.0}, "sumd.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 83.338, "flops_per_problem": 4917028110.336}, "sumd.runmax.cmp7": {"acc": 0.996, "reasoning_bytes": 91.516, "flops_per_problem": 5322356785.152}, "sumd.runmax.cmp8": {"acc": 0.906, "reasoning_bytes": 97.91, "flops_per_problem": 5648898539.52}, "add.runmax.cmp6": {"acc": 0.998, "reasoning_bytes": 137.192, "flops_per_problem": 7560276295.68}, "add.runmax.cmp7": {"acc": 0.924, "reasoning_bytes": 155.194, "flops_per_problem": 8443626061.824}, "add.runmax.cmp8": {"acc": 0.906, "reasoning_bytes": 166.578, "flops_per_problem": 9034704617.472}, "count.runmax.runmax16": {"acc": 0.98, "reasoning_bytes": 113.02, "flops_per_problem": 6846159421.44}, "count.runmax.runmax18": {"acc": 0.924, "reasoning_bytes": 121.89, "flops_per_problem": 7326212014.08}, "count.runmax.runmax20": {"acc": 0.694, "reasoning_bytes": 128.118, "flops_per_problem": 7689585770.496}, "add.runmax.runmax6": {"acc": 0.988, "reasoning_bytes": 138.41, "flops_per_problem": 7657788358.656}, "add.runmax.runmax7": {"acc": 0.82, "reasoning_bytes": 156.4, "flops_per_problem": 8540961472.512}, "add.runmax.runmax8": {"acc": 0.62, "reasoning_bytes": 170.002, "flops_per_problem": 9229905395.712}, "parity.runmax.runmax16": {"acc": 0.884, "reasoning_bytes": 128.256, "flops_per_problem": 7474864914.432}, "parity.runmax.runmax20": {"acc": 0.358, "reasoning_bytes": 146.46, "flops_per_problem": 8455461765.12}, "parity.runmax.runmax24": {"acc": 0.392, "reasoning_bytes": 162.96, "flops_per_problem": 9360804741.12}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 128.568, "flops_per_problem": 7532806864.896}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 146.808, "flops_per_problem": 8514993586.176}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 162.876, "flops_per_problem": 9401258115.072}, "inc.runmax.count6": {"acc": 0.998, "reasoning_bytes": 121.016, "flops_per_problem": 6625079083.008}, "inc.runmax.count7": {"acc": 0.974, "reasoning_bytes": 132.172, "flops_per_problem": 7162013712.384}, "inc.runmax.count8": {"acc": 0.968, "reasoning_bytes": 137.308, "flops_per_problem": 7432998322.176}, "sumd.runmax.count6": {"acc": 1.0, "reasoning_bytes": 84.424, "flops_per_problem": 5053315350.528}, "sumd.runmax.count7": {"acc": 0.99, "reasoning_bytes": 92.46, "flops_per_problem": 5452372869.12}, "sumd.runmax.count8": {"acc": 0.88, "reasoning_bytes": 99.436, "flops_per_problem": 5804617531.392}, "runmax.runmax.find12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6271156224.0}, "runmax.runmax.find14": {"acc": 0.998, "reasoning_bytes": 115.608, "flops_per_problem": 6827964235.776}, "runmax.runmax.find16": {"acc": 0.996, "reasoning_bytes": 123.0, "flops_per_problem": 7242743808.0}, "add.runmax.find6": {"acc": 0.986, "reasoning_bytes": 138.318, "flops_per_problem": 7653637029.888}, "add.runmax.find7": {"acc": 0.974, "reasoning_bytes": 156.224, "flops_per_problem": 8533100445.696}, "add.runmax.find8": {"acc": 0.884, "reasoning_bytes": 169.686, "flops_per_problem": 9216038191.104}, "parity.runmax.find16": {"acc": 0.988, "reasoning_bytes": 128.82, "flops_per_problem": 7499772887.04}, "parity.runmax.find20": {"acc": 0.83, "reasoning_bytes": 146.676, "flops_per_problem": 8465000988.672}, "parity.runmax.find24": {"acc": 0.894, "reasoning_bytes": 162.492, "flops_per_problem": 9340136423.424}, "add.runmax.rev6": {"acc": 0.998, "reasoning_bytes": 133.282, "flops_per_problem": 7299272540.16}, "add.runmax.rev7": {"acc": 0.906, "reasoning_bytes": 151.21, "flops_per_problem": 8179265912.832}, "add.runmax.rev8": {"acc": 0.552, "reasoning_bytes": 161.842, "flops_per_problem": 8737310490.624}, "parity.runmax.rev16": {"acc": 0.938, "reasoning_bytes": 123.568, "flops_per_problem": 7135339216.896}, "parity.runmax.rev20": {"acc": 0.464, "reasoning_bytes": 141.604, "flops_per_problem": 8108516671.488}, "parity.runmax.rev24": {"acc": 0.394, "reasoning_bytes": 158.164, "flops_per_problem": 9016509431.808}, "sumd.runmax.rev6": {"acc": 1.0, "reasoning_bytes": 79.542, "flops_per_problem": 4661058945.024}, "sumd.runmax.rev7": {"acc": 0.984, "reasoning_bytes": 87.48, "flops_per_problem": 5055788482.56}, "sumd.runmax.rev8": {"acc": 0.818, "reasoning_bytes": 94.122, "flops_per_problem": 5393282678.784}, "sumd.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 82.542, "flops_per_problem": 4837711233.024}, "sumd.runmax.sumd7": {"acc": 0.984, "reasoning_bytes": 90.48, "flops_per_problem": 5232440770.56}, "sumd.runmax.sumd8": {"acc": 0.86, "reasoning_bytes": 97.628, "flops_per_problem": 5592281481.216}, "add.runmax.sumd6": {"acc": 0.974, "reasoning_bytes": 136.748, "flops_per_problem": 7495444905.984}, "add.runmax.sumd7": {"acc": 0.816, "reasoning_bytes": 154.522, "flops_per_problem": 8369608753.152}, "add.runmax.sumd8": {"acc": 0.6, "reasoning_bytes": 169.98, "flops_per_problem": 9140519337.984}, "parity.runmax.sumd16": {"acc": 0.916, "reasoning_bytes": 126.472, "flops_per_problem": 7307751849.984}, "parity.runmax.sumd20": {"acc": 0.438, "reasoning_bytes": 144.7, "flops_per_problem": 8289408614.4}, "parity.runmax.sumd24": {"acc": 0.376, "reasoning_bytes": 162.004, "flops_per_problem": 9230258700.288}, "count.runmax.inc16": {"acc": 0.982, "reasoning_bytes": 112.02, "flops_per_problem": 6669507133.44}, "count.runmax.inc18": {"acc": 0.848, "reasoning_bytes": 119.28, "flops_per_problem": 7078457180.16}, "count.runmax.inc20": {"acc": 0.644, "reasoning_bytes": 126.866, "flops_per_problem": 7501804388.352}, "runmax.runmax.inc12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6125683064.832}, "runmax.runmax.inc14": {"acc": 0.984, "reasoning_bytes": 113.692, "flops_per_problem": 6644952465.408}, "runmax.runmax.inc16": {"acc": 0.976, "reasoning_bytes": 122.0, "flops_per_problem": 7102393565.184}, "add.runmax.inc6": {"acc": 0.992, "reasoning_bytes": 137.544, "flops_per_problem": 7508252196.864}, "add.runmax.inc7": {"acc": 0.87, "reasoning_bytes": 155.24, "flops_per_problem": 8381621108.736}, "add.runmax.inc8": {"acc": 0.598, "reasoning_bytes": 169.604, "flops_per_problem": 9105453858.816}, "count.count.cmp16": {"acc": 1.0, "reasoning_bytes": 112.02, "flops_per_problem": 6801996349.44}, "count.count.cmp18": {"acc": 0.996, "reasoning_bytes": 120.76, "flops_per_problem": 7276307742.72}, "count.count.cmp20": {"acc": 0.99, "reasoning_bytes": 127.15, "flops_per_problem": 7646835916.8}, "add.count.cmp6": {"acc": 0.996, "reasoning_bytes": 131.678, "flops_per_problem": 7361012514.816}, "add.count.cmp7": {"acc": 0.92, "reasoning_bytes": 148.452, "flops_per_problem": 8190130028.544}, "add.count.cmp8": {"acc": 0.836, "reasoning_bytes": 159.238, "flops_per_problem": 8754799067.136}, "sumd.count.cmp6": {"acc": 1.0, "reasoning_bytes": 82.492, "flops_per_problem": 4923829223.424}, "sumd.count.cmp7": {"acc": 0.998, "reasoning_bytes": 90.508, "flops_per_problem": 5322003480.576}, "sumd.count.cmp8": {"acc": 0.968, "reasoning_bytes": 94.802, "flops_per_problem": 5555802783.744}, "add.count.runmax6": {"acc": 0.968, "reasoning_bytes": 133.17, "flops_per_problem": 7471066890.24}, "add.count.runmax7": {"acc": 0.84, "reasoning_bytes": 149.47, "flops_per_problem": 8279251107.84}, "add.count.runmax8": {"acc": 0.414, "reasoning_bytes": 160.218, "flops_per_problem": 8842241949.696}, "sumd.count.runmax6": {"acc": 1.0, "reasoning_bytes": 83.428, "flops_per_problem": 5009328930.816}, "sumd.count.runmax7": {"acc": 0.988, "reasoning_bytes": 91.46, "flops_per_problem": 5408209797.12}, "sumd.count.runmax8": {"acc": 0.798, "reasoning_bytes": 97.626, "flops_per_problem": 5724682371.072}, "inc.count.runmax6": {"acc": 0.984, "reasoning_bytes": 116.0, "flops_per_problem": 6403645440.0}, "inc.count.runmax7": {"acc": 0.668, "reasoning_bytes": 121.984, "flops_per_problem": 6712080334.848}, "inc.count.runmax8": {"acc": 0.754, "reasoning_bytes": 131.136, "flops_per_problem": 7160423841.792}, "parity.count.count16": {"acc": 1.0, "reasoning_bytes": 127.992, "flops_per_problem": 7551532007.424}, "parity.count.count20": {"acc": 1.0, "reasoning_bytes": 145.992, "flops_per_problem": 8523119591.424}, "parity.count.count24": {"acc": 1.0, "reasoning_bytes": 158.856, "flops_per_problem": 9267885637.632}, "runmax.count.count12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6359482368.0}, "runmax.count.count14": {"acc": 1.0, "reasoning_bytes": 115.896, "flops_per_problem": 6929009344.512}, "runmax.count.count16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 7331069952.0}, "inc.count.count6": {"acc": 1.0, "reasoning_bytes": 116.002, "flops_per_problem": 6447896838.144}, "inc.count.count7": {"acc": 0.844, "reasoning_bytes": 121.658, "flops_per_problem": 6741846245.376}, "inc.count.count8": {"acc": 0.908, "reasoning_bytes": 131.052, "flops_per_problem": 7200877215.744}, "inc.count.find6": {"acc": 1.0, "reasoning_bytes": 116.0, "flops_per_problem": 6403645440.0}, "inc.count.find7": {"acc": 0.938, "reasoning_bytes": 127.674, "flops_per_problem": 6963368214.528}, "inc.count.find8": {"acc": 0.892, "reasoning_bytes": 124.178, "flops_per_problem": 6853137186.816}, "add.count.find6": {"acc": 0.996, "reasoning_bytes": 132.844, "flops_per_problem": 7456669728.768}, "add.count.find7": {"acc": 0.912, "reasoning_bytes": 149.7, "flops_per_problem": 8289408614.4}, "add.count.find8": {"acc": 0.828, "reasoning_bytes": 162.468, "flops_per_problem": 8941608861.696}, "runmax.count.find12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6315319296.0}, "runmax.count.find14": {"acc": 1.0, "reasoning_bytes": 115.668, "flops_per_problem": 6874777092.096}, "runmax.count.find16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 7286906880.0}, "parity.count.rev16": {"acc": 1.0, "reasoning_bytes": 123.412, "flops_per_problem": 7172612849.664}, "parity.count.rev20": {"acc": 1.0, "reasoning_bytes": 141.328, "flops_per_problem": 8140490735.616}, "parity.count.rev24": {"acc": 1.0, "reasoning_bytes": 156.352, "flops_per_problem": 8980649017.344}, "inc.count.rev6": {"acc": 0.986, "reasoning_bytes": 111.0, "flops_per_problem": 6050340864.0}, "inc.count.rev7": {"acc": 0.78, "reasoning_bytes": 118.218, "flops_per_problem": 6413272989.696}, "inc.count.rev8": {"acc": 0.756, "reasoning_bytes": 126.146, "flops_per_problem": 6807560896.512}, "runmax.count.rev12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5962014720.0}, "runmax.count.rev14": {"acc": 1.0, "reasoning_bytes": 110.584, "flops_per_problem": 6517762818.048}, "runmax.count.rev16": {"acc": 1.0, "reasoning_bytes": 117.996, "flops_per_problem": 6933425651.712}, "count.count.sumd16": {"acc": 1.0, "reasoning_bytes": 111.04, "flops_per_problem": 6714553466.88}, "count.count.sumd18": {"acc": 0.998, "reasoning_bytes": 118.98, "flops_per_problem": 7153534402.56}, "count.count.sumd20": {"acc": 0.996, "reasoning_bytes": 125.988, "flops_per_problem": 7551355355.136}, "runmax.count.sumd12": {"acc": 1.0, "reasoning_bytes": 103.0, "flops_per_problem": 6138667008.0}, "runmax.count.sumd14": {"acc": 1.0, "reasoning_bytes": 113.464, "flops_per_problem": 6689115537.408}, "runmax.count.sumd16": {"acc": 1.0, "reasoning_bytes": 121.0, "flops_per_problem": 7110254592.0}, "sumd.count.sumd6": {"acc": 1.0, "reasoning_bytes": 81.428, "flops_per_problem": 4832676642.816}, "sumd.count.sumd7": {"acc": 0.986, "reasoning_bytes": 89.46, "flops_per_problem": 5231557509.12}, "sumd.count.sumd8": {"acc": 0.848, "reasoning_bytes": 96.388, "flops_per_problem": 5581682343.936}, "parity.count.inc16": {"acc": 1.0, "reasoning_bytes": 127.304, "flops_per_problem": 7344495525.888}, "parity.count.inc20": {"acc": 1.0, "reasoning_bytes": 145.34, "flops_per_problem": 8317672980.48}, "parity.count.inc24": {"acc": 0.984, "reasoning_bytes": 160.92, "flops_per_problem": 9182385930.24}, "count.count.inc16": {"acc": 1.0, "reasoning_bytes": 112.02, "flops_per_problem": 6713670205.44}, "count.count.inc18": {"acc": 1.0, "reasoning_bytes": 119.63, "flops_per_problem": 7138077327.36}, "count.count.inc20": {"acc": 0.996, "reasoning_bytes": 126.952, "flops_per_problem": 7549765484.544}, "add.count.inc6": {"acc": 0.96, "reasoning_bytes": 132.256, "flops_per_problem": 7298300952.576}, "add.count.inc7": {"acc": 0.756, "reasoning_bytes": 148.456, "flops_per_problem": 8101980536.832}, "add.count.inc8": {"acc": 0.402, "reasoning_bytes": 161.766, "flops_per_problem": 8778117169.152}, "parity.rev.cmp16": {"acc": 0.996, "reasoning_bytes": 122.832, "flops_per_problem": 7058672123.904}, "parity.rev.cmp20": {"acc": 0.932, "reasoning_bytes": 140.376, "flops_per_problem": 8010121347.072}, "parity.rev.cmp24": {"acc": 0.946, "reasoning_bytes": 154.704, "flops_per_problem": 8819542130.688}, "sumd.rev.cmp6": {"acc": 0.994, "reasoning_bytes": 81.084, "flops_per_problem": 4728981749.76}, "sumd.rev.cmp7": {"acc": 0.994, "reasoning_bytes": 89.054, "flops_per_problem": 5125301157.888}, "sumd.rev.cmp8": {"acc": 0.89, "reasoning_bytes": 95.22, "flops_per_problem": 5441685405.696}, "add.rev.cmp6": {"acc": 0.964, "reasoning_bytes": 158.356, "flops_per_problem": 8611710713.856}, "add.rev.cmp7": {"acc": 0.858, "reasoning_bytes": 181.972, "flops_per_problem": 9784240275.456}, "add.rev.cmp8": {"acc": 0.728, "reasoning_bytes": 204.246, "flops_per_problem": 10902007627.776}, "runmax.rev.runmax12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5917851648.0}, "runmax.rev.runmax14": {"acc": 0.984, "reasoning_bytes": 110.172, "flops_per_problem": 6455404560.384}, "runmax.rev.runmax16": {"acc": 0.976, "reasoning_bytes": 118.0, "flops_per_problem": 6889439232.0}, "count.rev.runmax16": {"acc": 0.984, "reasoning_bytes": 108.02, "flops_per_problem": 6492854845.44}, "count.rev.runmax18": {"acc": 0.894, "reasoning_bytes": 116.12, "flops_per_problem": 6938901872.64}, "count.rev.runmax20": {"acc": 0.694, "reasoning_bytes": 122.992, "flops_per_problem": 7330716647.424}, "add.rev.runmax6": {"acc": 0.964, "reasoning_bytes": 185.704, "flops_per_problem": 9616862232.576}, "add.rev.runmax7": {"acc": 0.82, "reasoning_bytes": 216.172, "flops_per_problem": 11054105247.744}, "add.rev.runmax8": {"acc": 0.56, "reasoning_bytes": 232.618, "flops_per_problem": 11862642769.92}, "inc.rev.count6": {"acc": 0.932, "reasoning_bytes": 156.008, "flops_per_problem": 8038032408.576}, "inc.rev.count7": {"acc": 0.742, "reasoning_bytes": 172.968, "flops_per_problem": 8831201181.696}, "inc.rev.count8": {"acc": 0.626, "reasoning_bytes": 182.974, "flops_per_problem": 9317259952.128}, "count.rev.count16": {"acc": 1.0, "reasoning_bytes": 108.06, "flops_per_problem": 6538784440.32}, "count.rev.count18": {"acc": 1.0, "reasoning_bytes": 116.52, "flops_per_problem": 7000730173.44}, "count.rev.count20": {"acc": 0.998, "reasoning_bytes": 123.014, "flops_per_problem": 7375851307.008}, "parity.rev.count16": {"acc": 1.0, "reasoning_bytes": 123.7, "flops_per_problem": 7185331814.4}, "parity.rev.count20": {"acc": 1.0, "reasoning_bytes": 141.712, "flops_per_problem": 8157449355.264}, "parity.rev.count24": {"acc": 1.0, "reasoning_bytes": 157.288, "flops_per_problem": 9021985652.736}, "sumd.rev.find6": {"acc": 1.0, "reasoning_bytes": 85.208, "flops_per_problem": 4911286910.976}, "sumd.rev.find7": {"acc": 0.988, "reasoning_bytes": 93.5, "flops_per_problem": 5321650176.0}, "sumd.rev.find8": {"acc": 0.902, "reasoning_bytes": 99.594, "flops_per_problem": 5634943008.768}, "runmax.rev.find12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5917851648.0}, "runmax.rev.find14": {"acc": 1.0, "reasoning_bytes": 110.944, "flops_per_problem": 6489498451.968}, "runmax.rev.find16": {"acc": 0.996, "reasoning_bytes": 118.0, "flops_per_problem": 6889439232.0}, "count.rev.find16": {"acc": 0.996, "reasoning_bytes": 108.02, "flops_per_problem": 6492854845.44}, "count.rev.find18": {"acc": 0.962, "reasoning_bytes": 115.45, "flops_per_problem": 6909312614.4}, "count.rev.find20": {"acc": 0.918, "reasoning_bytes": 123.042, "flops_per_problem": 7332924801.024}, "count.rev.rev16": {"acc": 0.988, "reasoning_bytes": 103.01, "flops_per_problem": 6139108638.72}, "count.rev.rev18": {"acc": 0.816, "reasoning_bytes": 109.54, "flops_per_problem": 6515819642.88}, "count.rev.rev20": {"acc": 0.654, "reasoning_bytes": 117.586, "flops_per_problem": 6959481864.192}, "sumd.rev.rev6": {"acc": 0.998, "reasoning_bytes": 80.53, "flops_per_problem": 4616277590.016}, "sumd.rev.rev7": {"acc": 0.966, "reasoning_bytes": 88.48, "flops_per_problem": 5011713736.704}, "sumd.rev.rev8": {"acc": 0.674, "reasoning_bytes": 94.342, "flops_per_problem": 5314760736.768}, "parity.rev.rev16": {"acc": 0.962, "reasoning_bytes": 118.736, "flops_per_problem": 6789454036.992}, "parity.rev.rev20": {"acc": 0.584, "reasoning_bytes": 136.688, "flops_per_problem": 7758921793.536}, "parity.rev.rev24": {"acc": 0.422, "reasoning_bytes": 153.308, "flops_per_problem": 8669564338.176}, "sumd.rev.sumd6": {"acc": 0.998, "reasoning_bytes": 84.73, "flops_per_problem": 4810771759.104}, "sumd.rev.sumd7": {"acc": 0.976, "reasoning_bytes": 92.74, "flops_per_problem": 5211242496.0}, "sumd.rev.sumd8": {"acc": 0.838, "reasoning_bytes": 99.768, "flops_per_problem": 5565783638.016}, "parity.rev.sumd16": {"acc": 0.962, "reasoning_bytes": 121.748, "flops_per_problem": 6966636281.856}, "parity.rev.sumd20": {"acc": 0.54, "reasoning_bytes": 139.784, "flops_per_problem": 7939813736.448}, "parity.rev.sumd24": {"acc": 0.41, "reasoning_bytes": 157.424, "flops_per_problem": 8895502614.528}, "add.rev.sumd6": {"acc": 0.688, "reasoning_bytes": 193.374, "flops_per_problem": 9908780138.496}, "add.rev.sumd7": {"acc": 0.126, "reasoning_bytes": 226.032, "flops_per_problem": 11440885432.32}, "add.rev.sumd8": {"acc": 0.032, "reasoning_bytes": 247.002, "flops_per_problem": 12457872654.336}, "parity.rev.inc16": {"acc": 0.974, "reasoning_bytes": 122.82, "flops_per_problem": 6969816023.04}, "parity.rev.inc20": {"acc": 0.566, "reasoning_bytes": 140.772, "flops_per_problem": 7939283779.584}, "parity.rev.inc24": {"acc": 0.386, "reasoning_bytes": 158.46, "flops_per_problem": 8897092485.12}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 99.0, "flops_per_problem": 5772378488.832}, "runmax.rev.inc14": {"acc": 0.984, "reasoning_bytes": 109.088, "flops_per_problem": 6309224792.064}, "runmax.rev.inc16": {"acc": 0.972, "reasoning_bytes": 117.0, "flops_per_problem": 6749000663.04}, "inc.rev.inc6": {"acc": 0.434, "reasoning_bytes": 170.046, "flops_per_problem": 8724061569.024}, "inc.rev.inc7": {"acc": 0.042, "reasoning_bytes": 196.244, "flops_per_problem": 9983857360.896}, "inc.rev.inc8": {"acc": 0.008, "reasoning_bytes": 200.99, "flops_per_problem": 10249807380.48}, "parity.sumd.cmp16": {"acc": 0.99, "reasoning_bytes": 125.46, "flops_per_problem": 7218895749.12}, "parity.sumd.cmp20": {"acc": 0.924, "reasoning_bytes": 143.364, "flops_per_problem": 8186243678.208}, "parity.sumd.cmp24": {"acc": 0.942, "reasoning_bytes": 158.76, "flops_per_problem": 9042830622.72}, "runmax.sumd.cmp12": {"acc": 1.0, "reasoning_bytes": 102.0, "flops_per_problem": 6006177792.0}, "runmax.sumd.cmp14": {"acc": 0.998, "reasoning_bytes": 112.284, "flops_per_problem": 6548676968.448}, "runmax.sumd.cmp16": {"acc": 0.996, "reasoning_bytes": 120.0, "flops_per_problem": 6977765376.0}, "count.sumd.cmp16": {"acc": 0.996, "reasoning_bytes": 110.01, "flops_per_problem": 6580739358.72}, "count.sumd.cmp18": {"acc": 0.954, "reasoning_bytes": 116.39, "flops_per_problem": 6950825902.08}, "count.sumd.cmp20": {"acc": 0.918, "reasoning_bytes": 124.718, "flops_per_problem": 7406942109.696}, "sumd.sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 84.36, "flops_per_problem": 4917999697.92}, "sumd.sumd.runmax7": {"acc": 0.98, "reasoning_bytes": 92.838, "flops_per_problem": 5336577294.336}, "sumd.sumd.runmax8": {"acc": 0.834, "reasoning_bytes": 99.862, "flops_per_problem": 5690941784.064}, "count.sumd.runmax16": {"acc": 0.98, "reasoning_bytes": 111.01, "flops_per_problem": 6669065502.72}, "count.sumd.runmax18": {"acc": 0.852, "reasoning_bytes": 118.31, "flops_per_problem": 7079782072.32}, "count.sumd.runmax20": {"acc": 0.644, "reasoning_bytes": 125.82, "flops_per_problem": 7499772887.04}, "add.sumd.runmax6": {"acc": 0.918, "reasoning_bytes": 152.522, "flops_per_problem": 8192691486.72}, "add.sumd.runmax7": {"acc": 0.504, "reasoning_bytes": 171.818, "flops_per_problem": 9133806551.04}, "add.sumd.runmax8": {"acc": 0.17, "reasoning_bytes": 185.952, "flops_per_problem": 9847305142.272}, "parity.sumd.count16": {"acc": 1.0, "reasoning_bytes": 126.376, "flops_per_problem": 7347675267.072}, "parity.sumd.count20": {"acc": 1.0, "reasoning_bytes": 144.58, "flops_per_problem": 8328272117.76}, "parity.sumd.count24": {"acc": 1.0, "reasoning_bytes": 160.672, "flops_per_problem": 9215596560.384}, "sumd.sumd.count6": {"acc": 1.0, "reasoning_bytes": 84.184, "flops_per_problem": 4954390069.248}, "sumd.sumd.count7": {"acc": 0.984, "reasoning_bytes": 92.428, "flops_per_problem": 5362633506.816}, "sumd.sumd.count8": {"acc": 0.864, "reasoning_bytes": 99.532, "flops_per_problem": 5720531042.304}, "add.sumd.count6": {"acc": 0.928, "reasoning_bytes": 151.698, "flops_per_problem": 8200287535.104}, "add.sumd.count7": {"acc": 0.622, "reasoning_bytes": 170.632, "flops_per_problem": 9125415567.36}, "add.sumd.count8": {"acc": 0.418, "reasoning_bytes": 186.926, "flops_per_problem": 9933511458.816}, "runmax.sumd.find12": {"acc": 1.0, "reasoning_bytes": 103.0, "flops_per_problem": 6094503936.0}, "runmax.sumd.find14": {"acc": 0.998, "reasoning_bytes": 112.948, "flops_per_problem": 6622164320.256}, "runmax.sumd.find16": {"acc": 0.998, "reasoning_bytes": 121.0, "flops_per_problem": 7066091520.0}, "sumd.sumd.find6": {"acc": 1.0, "reasoning_bytes": 84.064, "flops_per_problem": 4904927428.608}, "sumd.sumd.find7": {"acc": 0.992, "reasoning_bytes": 92.37, "flops_per_problem": 5315908976.64}, "sumd.sumd.find8": {"acc": 0.942, "reasoning_bytes": 99.458, "flops_per_problem": 5673099902.976}, "parity.sumd.find16": {"acc": 0.972, "reasoning_bytes": 126.484, "flops_per_problem": 7308281806.848}, "parity.sumd.find20": {"acc": 0.85, "reasoning_bytes": 144.232, "flops_per_problem": 8268740296.704}, "parity.sumd.find24": {"acc": 0.89, "reasoning_bytes": 160.216, "flops_per_problem": 9151295127.552}, "count.sumd.rev16": {"acc": 0.978, "reasoning_bytes": 106.0, "flops_per_problem": 6315319296.0}, "count.sumd.rev18": {"acc": 0.798, "reasoning_bytes": 112.24, "flops_per_problem": 6679223009.28}, "count.sumd.rev20": {"acc": 0.608, "reasoning_bytes": 120.302, "flops_per_problem": 7123591839.744}, "parity.sumd.rev16": {"acc": 0.93, "reasoning_bytes": 121.544, "flops_per_problem": 6957627015.168}, "parity.sumd.rev20": {"acc": 0.538, "reasoning_bytes": 139.688, "flops_per_problem": 7935574081.536}, "parity.sumd.rev24": {"acc": 0.408, "reasoning_bytes": 156.908, "flops_per_problem": 8872714469.376}, "add.sumd.rev6": {"acc": 0.898, "reasoning_bytes": 146.288, "flops_per_problem": 7830024339.456}, "add.sumd.rev7": {"acc": 0.48, "reasoning_bytes": 165.86, "flops_per_problem": 8782886780.928}, "add.sumd.rev8": {"acc": 0.044, "reasoning_bytes": 179.466, "flops_per_problem": 9475187097.6}, "parity.sumd.sumd16": {"acc": 0.862, "reasoning_bytes": 124.172, "flops_per_problem": 7117850640.384}, "parity.sumd.sumd20": {"acc": 0.498, "reasoning_bytes": 142.544, "flops_per_problem": 8105866887.168}, "parity.sumd.sumd24": {"acc": 0.414, "reasoning_bytes": 160.16, "flops_per_problem": 9060495851.52}, "add.sumd.sumd6": {"acc": 0.908, "reasoning_bytes": 150.824, "flops_per_problem": 8037855756.288}, "add.sumd.sumd7": {"acc": 0.36, "reasoning_bytes": 169.862, "flops_per_problem": 8970844815.36}, "add.sumd.sumd8": {"acc": 0.072, "reasoning_bytes": 184.748, "flops_per_problem": 9723206909.952}, "count.sumd.sumd16": {"acc": 0.98, "reasoning_bytes": 108.99, "flops_per_problem": 6491529953.28}, "count.sumd.sumd18": {"acc": 0.796, "reasoning_bytes": 115.114, "flops_per_problem": 6850310750.208}, "count.sumd.sumd20": {"acc": 0.596, "reasoning_bytes": 123.08, "flops_per_problem": 7290439925.76}, "inc.sumd.inc6": {"acc": 0.958, "reasoning_bytes": 135.656, "flops_per_problem": 7050634444.8}, "inc.sumd.inc7": {"acc": 0.546, "reasoning_bytes": 152.104, "flops_per_problem": 7821280051.2}, "inc.sumd.inc8": {"acc": 0.064, "reasoning_bytes": 154.764, "flops_per_problem": 7986803245.056}, "sumd.sumd.inc6": {"acc": 1.0, "reasoning_bytes": 83.764, "flops_per_problem": 4773586452.48}, "sumd.sumd.inc7": {"acc": 0.978, "reasoning_bytes": 92.362, "flops_per_problem": 5200201728.0}, "sumd.sumd.inc8": {"acc": 0.862, "reasoning_bytes": 99.668, "flops_per_problem": 5566931877.888}, "parity.sumd.inc16": {"acc": 0.922, "reasoning_bytes": 125.496, "flops_per_problem": 7132159475.712}, "parity.sumd.inc20": {"acc": 0.52, "reasoning_bytes": 143.736, "flops_per_problem": 8114346196.992}, "parity.sumd.inc24": {"acc": 0.412, "reasoning_bytes": 161.484, "flops_per_problem": 9074804686.848}, "inc.inc.cmp6": {"acc": 0.984, "reasoning_bytes": 145.142, "flops_per_problem": 7690645684.224}, "inc.inc.cmp7": {"acc": 0.968, "reasoning_bytes": 166.27, "flops_per_problem": 8712049213.44}, "inc.inc.cmp8": {"acc": 0.944, "reasoning_bytes": 183.342, "flops_per_problem": 9554327322.624}, "runmax.inc.cmp12": {"acc": 1.0, "reasoning_bytes": 105.568, "flops_per_problem": 6150856015.872}, "runmax.inc.cmp14": {"acc": 0.988, "reasoning_bytes": 117.204, "flops_per_problem": 6757126668.288}, "runmax.inc.cmp16": {"acc": 0.972, "reasoning_bytes": 123.784, "flops_per_problem": 7137282392.064}, "sumd.inc.cmp6": {"acc": 0.992, "reasoning_bytes": 88.12, "flops_per_problem": 5039713124.352}, "sumd.inc.cmp7": {"acc": 1.0, "reasoning_bytes": 96.068, "flops_per_problem": 5435060944.896}, "sumd.inc.cmp8": {"acc": 0.98, "reasoning_bytes": 102.618, "flops_per_problem": 5768492138.496}, "sumd.inc.runmax6": {"acc": 1.0, "reasoning_bytes": 93.522, "flops_per_problem": 5278458691.584}, "sumd.inc.runmax7": {"acc": 0.986, "reasoning_bytes": 101.48, "flops_per_problem": 5674071490.56}, "sumd.inc.runmax8": {"acc": 0.796, "reasoning_bytes": 107.884, "flops_per_problem": 6001054875.648}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.648, "flops_per_problem": 6343936966.656}, "runmax.inc.runmax14": {"acc": 0.978, "reasoning_bytes": 119.048, "flops_per_problem": 6847395987.456}, "runmax.inc.runmax16": {"acc": 0.952, "reasoning_bytes": 128.576, "flops_per_problem": 7356507881.472}, "add.inc.runmax6": {"acc": 0.978, "reasoning_bytes": 194.608, "flops_per_problem": 10009206964.224}, "add.inc.runmax7": {"acc": 0.862, "reasoning_bytes": 222.744, "flops_per_problem": 11337897148.416}, "add.inc.runmax8": {"acc": 0.566, "reasoning_bytes": 239.86, "flops_per_problem": 12181676802.048}, "runmax.inc.count12": {"acc": 1.0, "reasoning_bytes": 108.928, "flops_per_problem": 6356302626.816}, "runmax.inc.count14": {"acc": 1.0, "reasoning_bytes": 119.89, "flops_per_problem": 6928744366.08}, "runmax.inc.count16": {"acc": 1.0, "reasoning_bytes": 127.614, "flops_per_problem": 7358186078.208}, "sumd.inc.count6": {"acc": 0.994, "reasoning_bytes": 92.388, "flops_per_problem": 5272540839.936}, "sumd.inc.count7": {"acc": 0.972, "reasoning_bytes": 100.444, "flops_per_problem": 5672481619.968}, "sumd.inc.count8": {"acc": 0.794, "reasoning_bytes": 106.542, "flops_per_problem": 5985951105.024}, "inc.inc.count6": {"acc": 0.934, "reasoning_bytes": 165.288, "flops_per_problem": 8447865716.736}, "inc.inc.count7": {"acc": 0.784, "reasoning_bytes": 182.89, "flops_per_problem": 9269387182.08}, "inc.inc.count8": {"acc": 0.666, "reasoning_bytes": 191.042, "flops_per_problem": 9673567617.024}, "parity.inc.find16": {"acc": 0.988, "reasoning_bytes": 127.592, "flops_per_problem": 7313051418.624}, "parity.inc.find20": {"acc": 0.9, "reasoning_bytes": 145.364, "flops_per_problem": 8274569822.208}, "parity.inc.find24": {"acc": 0.83, "reasoning_bytes": 161.696, "flops_per_problem": 9172493402.112}, "sumd.inc.find6": {"acc": 0.998, "reasoning_bytes": 92.1, "flops_per_problem": 5215658803.2}, "sumd.inc.find7": {"acc": 0.994, "reasoning_bytes": 100.376, "flops_per_problem": 5625315459.072}, "sumd.inc.find8": {"acc": 0.934, "reasoning_bytes": 106.814, "flops_per_problem": 5953800388.608}, "count.inc.find16": {"acc": 0.966, "reasoning_bytes": 112.01, "flops_per_problem": 6669065502.72}, "count.inc.find18": {"acc": 0.92, "reasoning_bytes": 118.63, "flops_per_problem": 7049751183.36}, "count.inc.find20": {"acc": 0.864, "reasoning_bytes": 126.918, "flops_per_problem": 7504100868.096}, "sumd.inc.rev6": {"acc": 0.998, "reasoning_bytes": 87.524, "flops_per_problem": 4925154115.584}, "sumd.inc.rev7": {"acc": 0.942, "reasoning_bytes": 95.482, "flops_per_problem": 5320855240.704}, "sumd.inc.rev8": {"acc": 0.608, "reasoning_bytes": 101.598, "flops_per_problem": 5635561291.776}, "count.inc.rev16": {"acc": 0.97, "reasoning_bytes": 107.0, "flops_per_problem": 6315319296.0}, "count.inc.rev18": {"acc": 0.766, "reasoning_bytes": 113.146, "flops_per_problem": 6675071680.512}, "count.inc.rev20": {"acc": 0.572, "reasoning_bytes": 121.532, "flops_per_problem": 7131276214.272}, "parity.inc.rev16": {"acc": 0.904, "reasoning_bytes": 122.616, "flops_per_problem": 6960806756.352}, "parity.inc.rev20": {"acc": 0.54, "reasoning_bytes": 140.736, "flops_per_problem": 7937693908.992}, "parity.inc.rev24": {"acc": 0.378, "reasoning_bytes": 158.236, "flops_per_problem": 8887199956.992}, "count.inc.sumd16": {"acc": 0.964, "reasoning_bytes": 110.0, "flops_per_problem": 6491971584.0}, "count.inc.sumd18": {"acc": 0.76, "reasoning_bytes": 116.018, "flops_per_problem": 6846071095.296}, "count.inc.sumd20": {"acc": 0.556, "reasoning_bytes": 124.342, "flops_per_problem": 7302010650.624}, "sumd.inc.sumd6": {"acc": 1.0, "reasoning_bytes": 91.758, "flops_per_problem": 5122651373.568}, "sumd.inc.sumd7": {"acc": 0.98, "reasoning_bytes": 99.762, "flops_per_problem": 5522327175.168}, "sumd.inc.sumd8": {"acc": 0.818, "reasoning_bytes": 106.686, "flops_per_problem": 5873423597.568}, "add.inc.sumd6": {"acc": 0.576, "reasoning_bytes": 202.39, "flops_per_problem": 10304304611.328}, "add.inc.sumd7": {"acc": 0.192, "reasoning_bytes": 231.304, "flops_per_problem": 11670533406.72}, "add.inc.sumd8": {"acc": 0.03, "reasoning_bytes": 252.214, "flops_per_problem": 12684782518.272}, "parity.inc.inc16": {"acc": 0.932, "reasoning_bytes": 126.568, "flops_per_problem": 7135339216.896}, "parity.inc.inc20": {"acc": 0.508, "reasoning_bytes": 144.904, "flops_per_problem": 8121765593.088}, "parity.inc.inc24": {"acc": 0.128, "reasoning_bytes": 164.004, "flops_per_problem": 9152531693.568}, "sumd.inc.inc6": {"acc": 0.934, "reasoning_bytes": 94.518, "flops_per_problem": 5234295619.584}, "sumd.inc.inc7": {"acc": 0.794, "reasoning_bytes": 102.482, "flops_per_problem": 5631851593.728}, "sumd.inc.inc8": {"acc": 0.464, "reasoning_bytes": 109.084, "flops_per_problem": 5968374202.368}, "runmax.inc.inc12": {"acc": 1.0, "reasoning_bytes": 110.06, "flops_per_problem": 6270272962.56}, "runmax.inc.inc14": {"acc": 0.916, "reasoning_bytes": 119.656, "flops_per_problem": 6781681336.32}, "runmax.inc.inc16": {"acc": 0.434, "reasoning_bytes": 133.504, "flops_per_problem": 7507898892.288}, "count.inc.cmp16": {"acc": 0.982, "reasoning_bytes": 111.01, "flops_per_problem": 6580739358.72}, "count.inc.cmp18": {"acc": 0.918, "reasoning_bytes": 117.2, "flops_per_problem": 6942611570.688}, "count.inc.cmp20": {"acc": 0.882, "reasoning_bytes": 125.724, "flops_per_problem": 7407648718.848}, "inc.rev.sumd6": {"acc": 0.484, "reasoning_bytes": 169.018, "flops_per_problem": 8517996675.072}, "inc.rev.sumd7": {"acc": 0.104, "reasoning_bytes": 195.786, "flops_per_problem": 9742903640.064}, "inc.rev.sumd8": {"acc": 0.054, "reasoning_bytes": 199.152, "flops_per_problem": 9944552226.816}, "runmax.inc.find12": {"acc": 0.85, "reasoning_bytes": 107.72, "flops_per_problem": 6258790563.84}, "runmax.inc.find14": {"acc": 0.84, "reasoning_bytes": 118.728, "flops_per_problem": 6833263804.416}, "runmax.inc.find16": {"acc": 0.876, "reasoning_bytes": 127.928, "flops_per_problem": 7327890210.816}, "inc.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 120.0, "flops_per_problem": 6491971584.0}, "inc.runmax.cmp7": {"acc": 0.966, "reasoning_bytes": 129.752, "flops_per_problem": 6966812934.144}, "inc.runmax.cmp8": {"acc": 0.964, "reasoning_bytes": 136.2, "flops_per_problem": 7295739494.4}} +{"step": 8000, "train_loss": 1.063136100769043} +{"step": 8020, "train_loss": 1.054950475692749} +{"step": 8040, "train_loss": 0.9863603115081787} +{"step": 8060, "train_loss": 1.1278178691864014} +{"step": 8080, "train_loss": 1.0163090229034424} +{"step": 8100, "train_loss": 1.059125304222107} +{"step": 8120, "train_loss": 1.009204387664795} +{"step": 8140, "train_loss": 1.0065791606903076} +{"step": 8160, "train_loss": 0.9951203465461731} +{"step": 8180, "train_loss": 0.9702593088150024} +{"step": 8200, "train_loss": 1.0526375770568848} +{"step": 8220, "train_loss": 1.1171208620071411} +{"step": 8240, "train_loss": 1.0107611417770386} +{"step": 8260, "train_loss": 1.0921311378479004} +{"step": 8280, "train_loss": 1.0865025520324707} +{"step": 8300, "train_loss": 1.021140694618225} +{"step": 8320, "train_loss": 0.9802880883216858} +{"step": 8340, "train_loss": 1.0451364517211914} +{"step": 8360, "train_loss": 1.0810232162475586} +{"step": 8380, "train_loss": 0.9579354524612427} +{"step": 8400, "train_loss": 0.9942331314086914} +{"step": 8420, "train_loss": 0.989250659942627} +{"step": 8440, "train_loss": 0.9819797277450562} +{"step": 8460, "train_loss": 1.0813302993774414} +{"step": 8480, "train_loss": 1.0205975770950317} +{"step": 8500, "train_loss": 1.0569114685058594} +{"step": 8520, "train_loss": 1.0364928245544434} +{"step": 8540, "train_loss": 1.0793516635894775} +{"step": 8560, "train_loss": 1.030559778213501} +{"step": 8580, "train_loss": 0.9885942935943604} +{"step": 8600, "train_loss": 0.999298095703125} +{"step": 8620, "train_loss": 0.993453860282898} +{"step": 8640, "train_loss": 1.0771253108978271} +{"step": 8660, "train_loss": 0.9793351292610168} +{"step": 8680, "train_loss": 1.0207312107086182} +{"step": 8700, "train_loss": 0.9977939128875732} +{"step": 8720, "train_loss": 0.9907026290893555} +{"step": 8740, "train_loss": 1.018164873123169} +{"step": 8760, "train_loss": 1.0059044361114502} +{"step": 8780, "train_loss": 1.0289465188980103} +{"step": 8800, "train_loss": 0.9330121278762817} +{"step": 8820, "train_loss": 1.0856976509094238} +{"step": 8840, "train_loss": 0.9842898845672607} +{"step": 8860, "train_loss": 1.0283236503601074} +{"step": 8880, "train_loss": 0.9426092505455017} +{"step": 8900, "train_loss": 1.0177723169326782} +{"step": 8920, "train_loss": 0.9551526308059692} +{"step": 8940, "train_loss": 1.0198312997817993} +{"step": 8960, "train_loss": 0.9171415567398071} +{"step": 8980, "train_loss": 0.9429525136947632} +{"step": 9000, "tokens": 294912000, "val_loss": 1.851368361711502, "val_bpb": 0.6673882165935988, "lr": 0.00015022524874031755, "elapsed": 2848.207004070282, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.906, "reasoning_bytes": 79.0, "flops_per_problem": 4927538921.472}, "add9": {"acc": 0.268, "reasoning_bytes": 86.48, "flops_per_problem": 5379768778.752}, "add10": {"acc": 0.0, "reasoning_bytes": 89.184, "flops_per_problem": 5598817615.872}, "reach14": {"acc": 0.558, "reasoning_bytes": 10.71, "flops_per_problem": 4756716158.976}, "reach16": {"acc": 0.522, "reasoning_bytes": 11.454, "flops_per_problem": 5324123308.032}, "reach18": {"acc": 0.552, "reasoning_bytes": 11.914, "flops_per_problem": 5901511311.36}, "parity24": {"acc": 0.23, "reasoning_bytes": 137.0, "flops_per_problem": 7596048384.0}, "parity28": {"acc": 0.584, "reasoning_bytes": 155.988, "flops_per_problem": 8611269083.136}, "parity32": {"acc": 0.506, "reasoning_bytes": 178.936, "flops_per_problem": 9801375547.392}, "cmp8": {"acc": 0.988, "reasoning_bytes": 5.792, "flops_per_problem": 1359869313.024}, "cmp9": {"acc": 0.976, "reasoning_bytes": 5.708, "flops_per_problem": 1444485758.976}, "cmp10": {"acc": 0.978, "reasoning_bytes": 5.752, "flops_per_problem": 1534755078.144}, "runmax12": {"acc": 1.0, "reasoning_bytes": 71.0, "flops_per_problem": 4151328768.0}, "runmax14": {"acc": 0.998, "reasoning_bytes": 82.652, "flops_per_problem": 4754243026.944}, "runmax16": {"acc": 0.95, "reasoning_bytes": 89.108, "flops_per_problem": 5127685963.776}, "count16": {"acc": 0.964, "reasoning_bytes": 78.33, "flops_per_problem": 4695859445.76}, "count18": {"acc": 0.838, "reasoning_bytes": 85.3, "flops_per_problem": 5092002201.6}, "count20": {"acc": 0.81, "reasoning_bytes": 94.07, "flops_per_problem": 5567638487.04}, "brackets16": {"acc": 0.904, "reasoning_bytes": 53.198, "flops_per_problem": 3630204518.4}, "brackets18": {"acc": 0.94, "reasoning_bytes": 54.728, "flops_per_problem": 3786276814.848}, "brackets20": {"acc": 0.92, "reasoning_bytes": 60.918, "flops_per_problem": 4147707396.096}, "sumd8": {"acc": 0.946, "reasoning_bytes": 58.568, "flops_per_problem": 3381389770.752}, "sumd9": {"acc": 0.698, "reasoning_bytes": 66.38, "flops_per_problem": 3776384286.72}, "sumd10": {"acc": 0.242, "reasoning_bytes": 72.032, "flops_per_problem": 4074750001.152}, "inc8": {"acc": 0.988, "reasoning_bytes": 63.026, "flops_per_problem": 3798642475.008}, "inc9": {"acc": 0.468, "reasoning_bytes": 69.64, "flops_per_problem": 4169965584.384}, "inc10": {"acc": 0.0, "reasoning_bytes": 68.258, "flops_per_problem": 4076604850.176}, "add.cmp6": {"acc": 0.996, "reasoning_bytes": 92.644, "flops_per_problem": 5533014638.592}, "add.cmp7": {"acc": 0.994, "reasoning_bytes": 105.524, "flops_per_problem": 6231586111.488}, "add.cmp8": {"acc": 0.948, "reasoning_bytes": 117.168, "flops_per_problem": 6879811682.304}, "add.runmax6": {"acc": 1.0, "reasoning_bytes": 120.832, "flops_per_problem": 6572878331.904}, "add.runmax7": {"acc": 0.986, "reasoning_bytes": 138.848, "flops_per_problem": 7456846381.056}, "add.runmax8": {"acc": 0.532, "reasoning_bytes": 152.558, "flops_per_problem": 8150648242.176}, "add.count6": {"acc": 0.996, "reasoning_bytes": 115.648, "flops_per_problem": 6388100038.656}, "add.count7": {"acc": 0.962, "reasoning_bytes": 132.068, "flops_per_problem": 7201583824.896}, "add.count8": {"acc": 0.326, "reasoning_bytes": 146.496, "flops_per_problem": 7927359750.144}, "add.find6": {"acc": 0.824, "reasoning_bytes": 107.804, "flops_per_problem": 5997521829.888}, "add.find7": {"acc": 0.75, "reasoning_bytes": 121.748, "flops_per_problem": 6701657849.856}, "add.find8": {"acc": 0.352, "reasoning_bytes": 139.122, "flops_per_problem": 7557538185.216}, "add.rev6": {"acc": 0.996, "reasoning_bytes": 123.248, "flops_per_problem": 6794576953.344}, "add.rev7": {"acc": 0.744, "reasoning_bytes": 145.722, "flops_per_problem": 7918262157.312}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 153.392, "flops_per_problem": 8354593308.672}, "add.sumd6": {"acc": 0.992, "reasoning_bytes": 126.476, "flops_per_problem": 6777794985.984}, "add.sumd7": {"acc": 0.934, "reasoning_bytes": 146.318, "flops_per_problem": 7742493130.752}, "add.sumd8": {"acc": 0.058, "reasoning_bytes": 162.204, "flops_per_problem": 8532393836.544}, "add.inc6": {"acc": 1.0, "reasoning_bytes": 131.04, "flops_per_problem": 7138695610.368}, "add.inc7": {"acc": 0.926, "reasoning_bytes": 150.868, "flops_per_problem": 8145701978.112}, "add.inc8": {"acc": 0.002, "reasoning_bytes": 155.674, "flops_per_problem": 8453783568.384}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5122916352.0}, "runmax.cmp14": {"acc": 0.962, "reasoning_bytes": 93.732, "flops_per_problem": 5508548296.704}, "runmax.cmp16": {"acc": 0.866, "reasoning_bytes": 104.868, "flops_per_problem": 6088674410.496}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.runmax14": {"acc": 0.98, "reasoning_bytes": 96.016, "flops_per_problem": 5653579825.152}, "runmax.runmax16": {"acc": 0.96, "reasoning_bytes": 106.0, "flops_per_problem": 6182830080.0}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5255405568.0}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 95.5, "flops_per_problem": 5674954752.0}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 106.0, "flops_per_problem": 6226993152.0}, "runmax.find12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.find14": {"acc": 0.992, "reasoning_bytes": 94.648, "flops_per_problem": 5593164742.656}, "runmax.find16": {"acc": 0.978, "reasoning_bytes": 105.988, "flops_per_problem": 6182300123.136}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 83.0, "flops_per_problem": 4857937920.0}, "runmax.rev14": {"acc": 0.978, "reasoning_bytes": 90.55, "flops_per_problem": 5279695257.6}, "runmax.rev16": {"acc": 0.946, "reasoning_bytes": 101.04, "flops_per_problem": 5831292026.88}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 86.0, "flops_per_problem": 5034590208.0}, "runmax.sumd14": {"acc": 0.98, "reasoning_bytes": 94.052, "flops_per_problem": 5478517407.744}, "runmax.sumd16": {"acc": 0.946, "reasoning_bytes": 104.0, "flops_per_problem": 6006177792.0}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5065769336.832}, "runmax.inc14": {"acc": 0.972, "reasoning_bytes": 93.816, "flops_per_problem": 5457495785.472}, "runmax.inc16": {"acc": 0.94, "reasoning_bytes": 104.988, "flops_per_problem": 6040360009.728}, "count.cmp16": {"acc": 0.992, "reasoning_bytes": 94.61, "flops_per_problem": 5679812689.92}, "count.cmp18": {"acc": 0.954, "reasoning_bytes": 100.52, "flops_per_problem": 6029230915.584}, "count.cmp20": {"acc": 0.934, "reasoning_bytes": 109.81, "flops_per_problem": 6527920324.608}, "count.runmax16": {"acc": 0.99, "reasoning_bytes": 95.74, "flops_per_problem": 5773880033.28}, "count.runmax18": {"acc": 0.864, "reasoning_bytes": 102.1, "flops_per_problem": 6143083315.2}, "count.runmax20": {"acc": 0.804, "reasoning_bytes": 110.98, "flops_per_problem": 6623577538.56}, "count.count16": {"acc": 1.0, "reasoning_bytes": 95.64, "flops_per_problem": 5813626798.08}, "count.count18": {"acc": 1.0, "reasoning_bytes": 102.12, "flops_per_problem": 6188129648.64}, "count.count20": {"acc": 0.998, "reasoning_bytes": 110.99, "flops_per_problem": 6668182241.28}, "count.find16": {"acc": 0.996, "reasoning_bytes": 95.83, "flops_per_problem": 5777854709.76}, "count.find18": {"acc": 0.934, "reasoning_bytes": 102.18, "flops_per_problem": 6146616360.96}, "count.find20": {"acc": 0.884, "reasoning_bytes": 110.98, "flops_per_problem": 6623577538.56}, "count.rev16": {"acc": 0.98, "reasoning_bytes": 90.64, "flops_per_problem": 5416159150.08}, "count.rev18": {"acc": 0.816, "reasoning_bytes": 96.4, "flops_per_problem": 5758864588.8}, "count.rev20": {"acc": 0.79, "reasoning_bytes": 105.82, "flops_per_problem": 6263206871.04}, "count.sumd16": {"acc": 0.986, "reasoning_bytes": 93.71, "flops_per_problem": 5595902853.12}, "count.sumd18": {"acc": 0.846, "reasoning_bytes": 99.76, "flops_per_problem": 5951415582.72}, "count.sumd20": {"acc": 0.812, "reasoning_bytes": 108.91, "flops_per_problem": 6443833835.52}, "count.inc16": {"acc": 0.982, "reasoning_bytes": 94.65, "flops_per_problem": 5593253068.8}, "count.inc18": {"acc": 0.838, "reasoning_bytes": 100.63, "flops_per_problem": 5945674383.36}, "count.inc20": {"acc": 0.796, "reasoning_bytes": 109.9, "flops_per_problem": 6443392204.8}, "parity.cmp16": {"acc": 0.982, "reasoning_bytes": 109.284, "flops_per_problem": 6283698536.448}, "parity.cmp20": {"acc": 0.928, "reasoning_bytes": 128.904, "flops_per_problem": 7326830297.088}, "parity.cmp24": {"acc": 0.94, "reasoning_bytes": 146.94, "flops_per_problem": 8300007751.68}, "parity.runmax16": {"acc": 0.894, "reasoning_bytes": 110.62, "flops_per_problem": 6386863472.64}, "parity.runmax20": {"acc": 0.45, "reasoning_bytes": 129.964, "flops_per_problem": 7417806225.408}, "parity.runmax24": {"acc": 0.352, "reasoning_bytes": 148.0, "flops_per_problem": 8390983680.0}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 109.516, "flops_per_problem": 6382270513.152}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 129.892, "flops_per_problem": 7458789556.224}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 147.976, "flops_per_problem": 8434086838.272}, "parity.find16": {"acc": 0.968, "reasoning_bytes": 110.272, "flops_per_problem": 6371494723.584}, "parity.find20": {"acc": 0.866, "reasoning_bytes": 130.0, "flops_per_problem": 7419396096.0}, "parity.find24": {"acc": 0.854, "reasoning_bytes": 148.0, "flops_per_problem": 8390983680.0}, "parity.rev16": {"acc": 0.934, "reasoning_bytes": 106.268, "flops_per_problem": 6062176567.296}, "parity.rev20": {"acc": 0.424, "reasoning_bytes": 125.0, "flops_per_problem": 7066091520.0}, "parity.rev24": {"acc": 0.338, "reasoning_bytes": 143.0, "flops_per_problem": 8037679104.0}, "parity.sumd16": {"acc": 0.906, "reasoning_bytes": 108.8, "flops_per_problem": 6218160537.6}, "parity.sumd20": {"acc": 0.438, "reasoning_bytes": 128.0, "flops_per_problem": 7242743808.0}, "parity.sumd24": {"acc": 0.36, "reasoning_bytes": 150.41, "flops_per_problem": 8409090539.52}, "parity.inc16": {"acc": 0.894, "reasoning_bytes": 109.812, "flops_per_problem": 6218690494.464}, "parity.inc20": {"acc": 0.468, "reasoning_bytes": 128.988, "flops_per_problem": 7242213851.136}, "parity.inc24": {"acc": 0.326, "reasoning_bytes": 147.0, "flops_per_problem": 8214331392.0}, "sumd.cmp6": {"acc": 1.0, "reasoning_bytes": 62.088, "flops_per_problem": 3713407746.048}, "sumd.cmp7": {"acc": 1.0, "reasoning_bytes": 70.068, "flops_per_problem": 4110168784.896}, "sumd.cmp8": {"acc": 0.97, "reasoning_bytes": 74.988, "flops_per_problem": 4371525844.992}, "sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.994, "reasoning_bytes": 75.48, "flops_per_problem": 4349179330.56}, "sumd.runmax8": {"acc": 0.902, "reasoning_bytes": 82.814, "flops_per_problem": 4717234372.608}, "sumd.count6": {"acc": 1.0, "reasoning_bytes": 66.428, "flops_per_problem": 3949415202.816}, "sumd.count7": {"acc": 0.992, "reasoning_bytes": 74.46, "flops_per_problem": 4348296069.12}, "sumd.count8": {"acc": 0.868, "reasoning_bytes": 80.82, "flops_per_problem": 4673954562.048}, "sumd.find6": {"acc": 1.0, "reasoning_bytes": 66.24, "flops_per_problem": 3896949473.28}, "sumd.find7": {"acc": 0.996, "reasoning_bytes": 74.424, "flops_per_problem": 4302543126.528}, "sumd.find8": {"acc": 0.918, "reasoning_bytes": 80.414, "flops_per_problem": 4611242999.808}, "sumd.rev6": {"acc": 1.0, "reasoning_bytes": 61.544, "flops_per_problem": 3601145217.024}, "sumd.rev7": {"acc": 0.994, "reasoning_bytes": 69.48, "flops_per_problem": 3995874754.56}, "sumd.rev8": {"acc": 0.866, "reasoning_bytes": 76.8, "flops_per_problem": 4363223187.456}, "sumd.sumd6": {"acc": 1.0, "reasoning_bytes": 65.744, "flops_per_problem": 3795639386.112}, "sumd.sumd7": {"acc": 0.992, "reasoning_bytes": 73.742, "flops_per_problem": 4195668492.288}, "sumd.sumd8": {"acc": 0.906, "reasoning_bytes": 81.34, "flops_per_problem": 4575824216.064}, "sumd.inc6": {"acc": 1.0, "reasoning_bytes": 68.538, "flops_per_problem": 3910021742.592}, "sumd.inc7": {"acc": 0.994, "reasoning_bytes": 76.48, "flops_per_problem": 4305016258.56}, "sumd.inc8": {"acc": 0.854, "reasoning_bytes": 83.658, "flops_per_problem": 4665651904.512}, "inc.cmp6": {"acc": 0.996, "reasoning_bytes": 78.624, "flops_per_problem": 4576354172.928}, "inc.cmp7": {"acc": 0.99, "reasoning_bytes": 89.776, "flops_per_problem": 5157186895.872}, "inc.cmp8": {"acc": 0.978, "reasoning_bytes": 97.11, "flops_per_problem": 5569316683.776}, "inc.runmax6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5520384000.0}, "inc.runmax7": {"acc": 0.994, "reasoning_bytes": 119.952, "flops_per_problem": 6269036396.544}, "inc.runmax8": {"acc": 0.926, "reasoning_bytes": 121.466, "flops_per_problem": 6380062359.552}, "inc.count6": {"acc": 0.98, "reasoning_bytes": 99.0, "flops_per_problem": 5343731712.0}, "inc.count7": {"acc": 0.928, "reasoning_bytes": 113.944, "flops_per_problem": 6047867731.968}, "inc.count8": {"acc": 0.752, "reasoning_bytes": 114.164, "flops_per_problem": 6101746679.808}, "inc.find6": {"acc": 0.844, "reasoning_bytes": 91.868, "flops_per_problem": 4984597610.496}, "inc.find7": {"acc": 0.804, "reasoning_bytes": 102.616, "flops_per_problem": 5503425380.352}, "inc.find8": {"acc": 0.542, "reasoning_bytes": 99.302, "flops_per_problem": 5401232031.744}, "inc.rev6": {"acc": 0.998, "reasoning_bytes": 104.0, "flops_per_problem": 5608710144.0}, "inc.rev7": {"acc": 0.91, "reasoning_bytes": 123.958, "flops_per_problem": 6577824595.968}, "inc.rev8": {"acc": 0.004, "reasoning_bytes": 129.658, "flops_per_problem": 6879546703.872}, "inc.sumd6": {"acc": 0.984, "reasoning_bytes": 109.558, "flops_per_problem": 5721590956.032}, "inc.sumd7": {"acc": 0.908, "reasoning_bytes": 127.412, "flops_per_problem": 6554241515.52}, "inc.sumd8": {"acc": 0.094, "reasoning_bytes": 128.584, "flops_per_problem": 6650163707.904}, "inc.inc6": {"acc": 0.994, "reasoning_bytes": 113.0, "flops_per_problem": 6005912813.568}, "inc.inc7": {"acc": 0.942, "reasoning_bytes": 130.836, "flops_per_problem": 6880518291.456}, "inc.inc8": {"acc": 0.006, "reasoning_bytes": 132.464, "flops_per_problem": 6999581933.568}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 0.992, "reasoning_bytes": 112.028, "flops_per_problem": 6625697366.016}, "runmax.runmax.cmp16": {"acc": 0.988, "reasoning_bytes": 121.988, "flops_per_problem": 7153887707.136}, "sumd.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 83.338, "flops_per_problem": 4917028110.336}, "sumd.runmax.cmp7": {"acc": 0.998, "reasoning_bytes": 91.484, "flops_per_problem": 5320943566.848}, "sumd.runmax.cmp8": {"acc": 0.712, "reasoning_bytes": 93.064, "flops_per_problem": 5434884292.608}, "add.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 137.024, "flops_per_problem": 7552945225.728}, "add.runmax.cmp7": {"acc": 0.99, "reasoning_bytes": 154.76, "flops_per_problem": 8424547614.72}, "add.runmax.cmp8": {"acc": 0.914, "reasoning_bytes": 159.662, "flops_per_problem": 8729361137.664}, "count.runmax.runmax16": {"acc": 0.99, "reasoning_bytes": 112.79, "flops_per_problem": 6836001914.88}, "count.runmax.runmax18": {"acc": 0.934, "reasoning_bytes": 120.71, "flops_per_problem": 7274099589.12}, "count.runmax.runmax20": {"acc": 0.806, "reasoning_bytes": 128.01, "flops_per_problem": 7684816158.72}, "add.runmax.runmax6": {"acc": 1.0, "reasoning_bytes": 137.832, "flops_per_problem": 7632792059.904}, "add.runmax.runmax7": {"acc": 0.974, "reasoning_bytes": 155.848, "flops_per_problem": 8516760109.056}, "add.runmax.runmax8": {"acc": 0.608, "reasoning_bytes": 166.362, "flops_per_problem": 9069416792.064}, "parity.runmax.runmax16": {"acc": 0.816, "reasoning_bytes": 126.768, "flops_per_problem": 7409150263.296}, "parity.runmax.runmax20": {"acc": 0.462, "reasoning_bytes": 146.772, "flops_per_problem": 8469240643.584}, "parity.runmax.runmax24": {"acc": 0.364, "reasoning_bytes": 164.772, "flops_per_problem": 9440828227.584}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 127.08, "flops_per_problem": 7467092213.76}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 146.88, "flops_per_problem": 8518173327.36}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 164.844, "flops_per_problem": 9488171040.768}, "inc.runmax.count6": {"acc": 1.0, "reasoning_bytes": 121.0, "flops_per_problem": 6624460800.0}, "inc.runmax.count7": {"acc": 1.0, "reasoning_bytes": 136.76, "flops_per_problem": 7364633886.72}, "inc.runmax.count8": {"acc": 0.994, "reasoning_bytes": 137.0, "flops_per_problem": 7419396096.0}, "sumd.runmax.count6": {"acc": 1.0, "reasoning_bytes": 84.424, "flops_per_problem": 5053315350.528}, "sumd.runmax.count7": {"acc": 0.996, "reasoning_bytes": 92.46, "flops_per_problem": 5452372869.12}, "sumd.runmax.count8": {"acc": 0.764, "reasoning_bytes": 96.902, "flops_per_problem": 5692708306.944}, "runmax.runmax.find12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6271156224.0}, "runmax.runmax.find14": {"acc": 0.994, "reasoning_bytes": 112.728, "flops_per_problem": 6700774588.416}, "runmax.runmax.find16": {"acc": 0.984, "reasoning_bytes": 123.0, "flops_per_problem": 7242743808.0}, "add.runmax.find6": {"acc": 1.0, "reasoning_bytes": 137.928, "flops_per_problem": 7637031714.816}, "add.runmax.find7": {"acc": 0.996, "reasoning_bytes": 155.592, "flops_per_problem": 8505454362.624}, "add.runmax.find8": {"acc": 0.878, "reasoning_bytes": 164.678, "flops_per_problem": 8995046178.816}, "parity.runmax.find16": {"acc": 0.966, "reasoning_bytes": 127.14, "flops_per_problem": 7425578926.08}, "parity.runmax.find20": {"acc": 0.86, "reasoning_bytes": 146.88, "flops_per_problem": 8474010255.36}, "parity.runmax.find24": {"acc": 0.866, "reasoning_bytes": 164.796, "flops_per_problem": 9441888141.312}, "add.runmax.rev6": {"acc": 1.0, "reasoning_bytes": 132.832, "flops_per_problem": 7279487483.904}, "add.runmax.rev7": {"acc": 0.992, "reasoning_bytes": 150.826, "flops_per_problem": 8162483945.472}, "add.runmax.rev8": {"acc": 0.56, "reasoning_bytes": 155.752, "flops_per_problem": 8468357382.144}, "parity.runmax.rev16": {"acc": 0.89, "reasoning_bytes": 122.668, "flops_per_problem": 7095592452.096}, "parity.runmax.rev20": {"acc": 0.436, "reasoning_bytes": 141.916, "flops_per_problem": 8122295549.952}, "parity.runmax.rev24": {"acc": 0.38, "reasoning_bytes": 159.844, "flops_per_problem": 9090703392.768}, "sumd.runmax.rev6": {"acc": 1.0, "reasoning_bytes": 79.542, "flops_per_problem": 4661058945.024}, "sumd.runmax.rev7": {"acc": 0.986, "reasoning_bytes": 87.48, "flops_per_problem": 5055788482.56}, "sumd.runmax.rev8": {"acc": 0.6, "reasoning_bytes": 91.784, "flops_per_problem": 5290029416.448}, "sumd.runmax.sumd6": {"acc": 0.998, "reasoning_bytes": 82.542, "flops_per_problem": 4837711233.024}, "sumd.runmax.sumd7": {"acc": 0.986, "reasoning_bytes": 90.48, "flops_per_problem": 5232440770.56}, "sumd.runmax.sumd8": {"acc": 0.712, "reasoning_bytes": 95.8, "flops_per_problem": 5511551385.6}, "add.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 135.832, "flops_per_problem": 7456139771.904}, "add.runmax.sumd7": {"acc": 0.986, "reasoning_bytes": 153.828, "flops_per_problem": 8339224559.616}, "add.runmax.sumd8": {"acc": 0.614, "reasoning_bytes": 164.364, "flops_per_problem": 8892852830.208}, "parity.runmax.sumd16": {"acc": 0.828, "reasoning_bytes": 124.9, "flops_per_problem": 7238327500.8}, "parity.runmax.sumd20": {"acc": 0.466, "reasoning_bytes": 144.772, "flops_per_problem": 8292588355.584}, "parity.runmax.sumd24": {"acc": 0.376, "reasoning_bytes": 162.868, "flops_per_problem": 9268415594.496}, "count.runmax.inc16": {"acc": 0.994, "reasoning_bytes": 111.84, "flops_per_problem": 6661557780.48}, "count.runmax.inc18": {"acc": 0.906, "reasoning_bytes": 118.92, "flops_per_problem": 7062558474.24}, "count.runmax.inc20": {"acc": 0.802, "reasoning_bytes": 126.98, "flops_per_problem": 7506838978.56}, "runmax.runmax.inc12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6125683064.832}, "runmax.runmax.inc14": {"acc": 0.98, "reasoning_bytes": 112.712, "flops_per_problem": 6601584328.704}, "runmax.runmax.inc16": {"acc": 0.95, "reasoning_bytes": 122.0, "flops_per_problem": 7101245325.312}, "add.runmax.inc6": {"acc": 1.0, "reasoning_bytes": 136.832, "flops_per_problem": 7477161394.176}, "add.runmax.inc7": {"acc": 0.976, "reasoning_bytes": 154.832, "flops_per_problem": 8363867553.792}, "add.runmax.inc8": {"acc": 0.574, "reasoning_bytes": 158.868, "flops_per_problem": 8630259204.096}, "count.count.cmp16": {"acc": 1.0, "reasoning_bytes": 111.84, "flops_per_problem": 6794046996.48}, "count.count.cmp18": {"acc": 1.0, "reasoning_bytes": 119.62, "flops_per_problem": 7225961840.64}, "count.count.cmp20": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7640211456.0}, "add.count.cmp6": {"acc": 0.998, "reasoning_bytes": 131.354, "flops_per_problem": 7346703679.488}, "add.count.cmp7": {"acc": 0.97, "reasoning_bytes": 147.958, "flops_per_problem": 8168313470.976}, "add.count.cmp8": {"acc": 0.872, "reasoning_bytes": 155.23, "flops_per_problem": 8577793474.56}, "sumd.count.cmp6": {"acc": 1.0, "reasoning_bytes": 82.492, "flops_per_problem": 4923829223.424}, "sumd.count.cmp7": {"acc": 0.992, "reasoning_bytes": 89.948, "flops_per_problem": 5297272160.256}, "sumd.count.cmp8": {"acc": 0.946, "reasoning_bytes": 90.686, "flops_per_problem": 5374027579.392}, "add.count.runmax6": {"acc": 0.996, "reasoning_bytes": 132.648, "flops_per_problem": 7448013766.656}, "add.count.runmax7": {"acc": 0.95, "reasoning_bytes": 149.07, "flops_per_problem": 8261585879.04}, "add.count.runmax8": {"acc": 0.464, "reasoning_bytes": 155.518, "flops_per_problem": 8634675511.296}, "sumd.count.runmax6": {"acc": 1.0, "reasoning_bytes": 83.428, "flops_per_problem": 5009328930.816}, "sumd.count.runmax7": {"acc": 0.99, "reasoning_bytes": 91.458, "flops_per_problem": 5408121470.976}, "sumd.count.runmax8": {"acc": 0.65, "reasoning_bytes": 94.952, "flops_per_problem": 5606590316.544}, "inc.count.runmax6": {"acc": 0.984, "reasoning_bytes": 116.0, "flops_per_problem": 6403645440.0}, "inc.count.runmax7": {"acc": 0.802, "reasoning_bytes": 130.572, "flops_per_problem": 7091352797.184}, "inc.count.runmax8": {"acc": 0.808, "reasoning_bytes": 131.0, "flops_per_problem": 7154417664.0}, "parity.count.count16": {"acc": 1.0, "reasoning_bytes": 124.488, "flops_per_problem": 7396784603.136}, "parity.count.count20": {"acc": 1.0, "reasoning_bytes": 146.088, "flops_per_problem": 8527359246.336}, "parity.count.count24": {"acc": 1.0, "reasoning_bytes": 163.44, "flops_per_problem": 9470329159.68}, "runmax.count.count12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6359482368.0}, "runmax.count.count14": {"acc": 1.0, "reasoning_bytes": 112.512, "flops_per_problem": 6779561508.864}, "runmax.count.count16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 7331069952.0}, "inc.count.count6": {"acc": 1.0, "reasoning_bytes": 116.0, "flops_per_problem": 6447808512.0}, "inc.count.count7": {"acc": 0.984, "reasoning_bytes": 129.404, "flops_per_problem": 7083933401.088}, "inc.count.count8": {"acc": 0.988, "reasoning_bytes": 130.974, "flops_per_problem": 7197432496.128}, "inc.count.find6": {"acc": 0.994, "reasoning_bytes": 116.0, "flops_per_problem": 6403645440.0}, "inc.count.find7": {"acc": 0.966, "reasoning_bytes": 130.482, "flops_per_problem": 7087378120.704}, "inc.count.find8": {"acc": 0.938, "reasoning_bytes": 130.89, "flops_per_problem": 7149559726.08}, "add.count.find6": {"acc": 1.0, "reasoning_bytes": 132.33, "flops_per_problem": 7433969909.76}, "add.count.find7": {"acc": 0.984, "reasoning_bytes": 149.114, "flops_per_problem": 8263529054.208}, "add.count.find8": {"acc": 0.832, "reasoning_bytes": 157.2, "flops_per_problem": 8708957798.4}, "runmax.count.find12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6315319296.0}, "runmax.count.find14": {"acc": 1.0, "reasoning_bytes": 112.188, "flops_per_problem": 6721089601.536}, "runmax.count.find16": {"acc": 1.0, "reasoning_bytes": 122.988, "flops_per_problem": 7286376923.136}, "parity.count.rev16": {"acc": 1.0, "reasoning_bytes": 122.428, "flops_per_problem": 7129156386.816}, "parity.count.rev20": {"acc": 1.0, "reasoning_bytes": 141.7, "flops_per_problem": 8156919398.4}, "parity.count.rev24": {"acc": 1.0, "reasoning_bytes": 159.52, "flops_per_problem": 9120557629.44}, "inc.count.rev6": {"acc": 0.982, "reasoning_bytes": 111.0, "flops_per_problem": 6050340864.0}, "inc.count.rev7": {"acc": 0.92, "reasoning_bytes": 125.756, "flops_per_problem": 6746174226.432}, "inc.count.rev8": {"acc": 0.806, "reasoning_bytes": 126.0, "flops_per_problem": 6801113088.0}, "runmax.count.rev12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5962014720.0}, "runmax.count.rev14": {"acc": 1.0, "reasoning_bytes": 108.496, "flops_per_problem": 6425550323.712}, "runmax.count.rev16": {"acc": 1.0, "reasoning_bytes": 118.0, "flops_per_problem": 6933602304.0}, "count.count.sumd16": {"acc": 1.0, "reasoning_bytes": 110.72, "flops_per_problem": 6700421283.84}, "count.count.sumd18": {"acc": 1.0, "reasoning_bytes": 118.25, "flops_per_problem": 7121295360.0}, "count.count.sumd20": {"acc": 0.998, "reasoning_bytes": 126.002, "flops_per_problem": 7551973638.144}, "runmax.count.sumd12": {"acc": 1.0, "reasoning_bytes": 103.0, "flops_per_problem": 6138667008.0}, "runmax.count.sumd14": {"acc": 1.0, "reasoning_bytes": 112.144, "flops_per_problem": 6630820282.368}, "runmax.count.sumd16": {"acc": 1.0, "reasoning_bytes": 121.0, "flops_per_problem": 7110254592.0}, "sumd.count.sumd6": {"acc": 1.0, "reasoning_bytes": 81.428, "flops_per_problem": 4832676642.816}, "sumd.count.sumd7": {"acc": 0.99, "reasoning_bytes": 89.458, "flops_per_problem": 5231469182.976}, "sumd.count.sumd8": {"acc": 0.706, "reasoning_bytes": 93.708, "flops_per_problem": 5463325310.976}, "parity.count.inc16": {"acc": 1.0, "reasoning_bytes": 125.564, "flops_per_problem": 7267651780.608}, "parity.count.inc20": {"acc": 1.0, "reasoning_bytes": 145.544, "flops_per_problem": 8326682247.168}, "parity.count.inc24": {"acc": 1.0, "reasoning_bytes": 163.544, "flops_per_problem": 9298269831.168}, "count.count.inc16": {"acc": 1.0, "reasoning_bytes": 111.74, "flops_per_problem": 6701304545.28}, "count.count.inc18": {"acc": 1.0, "reasoning_bytes": 118.93, "flops_per_problem": 7107163176.96}, "count.count.inc20": {"acc": 0.998, "reasoning_bytes": 126.992, "flops_per_problem": 7551532007.424}, "add.count.inc6": {"acc": 0.998, "reasoning_bytes": 131.648, "flops_per_problem": 7271361478.656}, "add.count.inc7": {"acc": 0.934, "reasoning_bytes": 147.956, "flops_per_problem": 8079899000.832}, "add.count.inc8": {"acc": 0.448, "reasoning_bytes": 151.29, "flops_per_problem": 8315464826.88}, "parity.rev.cmp16": {"acc": 0.982, "reasoning_bytes": 121.404, "flops_per_problem": 6995607257.088}, "parity.rev.cmp20": {"acc": 0.934, "reasoning_bytes": 140.604, "flops_per_problem": 8020190527.488}, "parity.rev.cmp24": {"acc": 0.94, "reasoning_bytes": 157.488, "flops_per_problem": 8942492123.136}, "sumd.rev.cmp6": {"acc": 0.994, "reasoning_bytes": 81.072, "flops_per_problem": 4728451792.896}, "sumd.rev.cmp7": {"acc": 0.988, "reasoning_bytes": 88.968, "flops_per_problem": 5121503133.696}, "sumd.rev.cmp8": {"acc": 0.708, "reasoning_bytes": 90.056, "flops_per_problem": 5213627301.888}, "add.rev.cmp6": {"acc": 0.992, "reasoning_bytes": 157.318, "flops_per_problem": 8566134423.552}, "add.rev.cmp7": {"acc": 0.968, "reasoning_bytes": 181.9, "flops_per_problem": 9781237186.56}, "add.rev.cmp8": {"acc": 0.802, "reasoning_bytes": 196.614, "flops_per_problem": 10565043388.416}, "runmax.rev.runmax12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5917851648.0}, "runmax.rev.runmax14": {"acc": 0.988, "reasoning_bytes": 109.778, "flops_per_problem": 6438004310.016}, "runmax.rev.runmax16": {"acc": 0.952, "reasoning_bytes": 118.66, "flops_per_problem": 6918586859.52}, "count.rev.runmax16": {"acc": 0.99, "reasoning_bytes": 107.83, "flops_per_problem": 6484463861.76}, "count.rev.runmax18": {"acc": 0.924, "reasoning_bytes": 115.31, "flops_per_problem": 6903129784.32}, "count.rev.runmax20": {"acc": 0.816, "reasoning_bytes": 122.98, "flops_per_problem": 7330186690.56}, "add.rev.runmax6": {"acc": 1.0, "reasoning_bytes": 185.078, "flops_per_problem": 9586831343.616}, "add.rev.runmax7": {"acc": 0.978, "reasoning_bytes": 215.46, "flops_per_problem": 11016919941.12}, "add.rev.runmax8": {"acc": 0.598, "reasoning_bytes": 223.094, "flops_per_problem": 11442475302.912}, "inc.rev.count6": {"acc": 0.954, "reasoning_bytes": 155.996, "flops_per_problem": 8037502451.712}, "inc.rev.count7": {"acc": 0.748, "reasoning_bytes": 182.224, "flops_per_problem": 9240239554.56}, "inc.rev.count8": {"acc": 0.654, "reasoning_bytes": 182.812, "flops_per_problem": 9310105534.464}, "count.rev.count16": {"acc": 1.0, "reasoning_bytes": 107.92, "flops_per_problem": 6532601610.24}, "count.rev.count18": {"acc": 1.0, "reasoning_bytes": 115.73, "flops_per_problem": 6965841346.56}, "count.rev.count20": {"acc": 0.998, "reasoning_bytes": 122.99, "flops_per_problem": 7374791393.28}, "parity.rev.count16": {"acc": 1.0, "reasoning_bytes": 122.896, "flops_per_problem": 7149824704.512}, "parity.rev.count20": {"acc": 1.0, "reasoning_bytes": 141.892, "flops_per_problem": 8165398708.224}, "parity.rev.count24": {"acc": 1.0, "reasoning_bytes": 159.748, "flops_per_problem": 9130626809.856}, "sumd.rev.find6": {"acc": 1.0, "reasoning_bytes": 85.208, "flops_per_problem": 4911286910.976}, "sumd.rev.find7": {"acc": 0.994, "reasoning_bytes": 93.436, "flops_per_problem": 5318823739.392}, "sumd.rev.find8": {"acc": 0.758, "reasoning_bytes": 95.504, "flops_per_problem": 5454316044.288}, "runmax.rev.find12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5917851648.0}, "runmax.rev.find14": {"acc": 0.994, "reasoning_bytes": 107.632, "flops_per_problem": 6343230357.504}, "runmax.rev.find16": {"acc": 0.98, "reasoning_bytes": 118.0, "flops_per_problem": 6889439232.0}, "count.rev.find16": {"acc": 1.0, "reasoning_bytes": 107.88, "flops_per_problem": 6486672015.36}, "count.rev.find18": {"acc": 0.97, "reasoning_bytes": 114.84, "flops_per_problem": 6882373140.48}, "count.rev.find20": {"acc": 0.952, "reasoning_bytes": 122.99, "flops_per_problem": 7330628321.28}, "count.rev.rev16": {"acc": 0.99, "reasoning_bytes": 102.77, "flops_per_problem": 6128509501.44}, "count.rev.rev18": {"acc": 0.858, "reasoning_bytes": 109.01, "flops_per_problem": 6492413214.72}, "count.rev.rev20": {"acc": 0.79, "reasoning_bytes": 117.92, "flops_per_problem": 6974232330.24}, "sumd.rev.rev6": {"acc": 1.0, "reasoning_bytes": 80.53, "flops_per_problem": 4616277590.016}, "sumd.rev.rev7": {"acc": 0.98, "reasoning_bytes": 88.448, "flops_per_problem": 5010212192.256}, "sumd.rev.rev8": {"acc": 0.354, "reasoning_bytes": 91.018, "flops_per_problem": 5167786033.152}, "parity.rev.rev16": {"acc": 0.92, "reasoning_bytes": 118.16, "flops_per_problem": 6764016107.52}, "parity.rev.rev20": {"acc": 0.446, "reasoning_bytes": 136.916, "flops_per_problem": 7768990973.952}, "parity.rev.rev24": {"acc": 0.382, "reasoning_bytes": 154.796, "flops_per_problem": 8735278989.312}, "sumd.rev.sumd6": {"acc": 1.0, "reasoning_bytes": 84.73, "flops_per_problem": 4810771759.104}, "sumd.rev.sumd7": {"acc": 0.984, "reasoning_bytes": 92.744, "flops_per_problem": 5211595800.576}, "sumd.rev.sumd8": {"acc": 0.638, "reasoning_bytes": 97.46, "flops_per_problem": 5463060332.544}, "parity.rev.sumd16": {"acc": 0.918, "reasoning_bytes": 121.04, "flops_per_problem": 6935368826.88}, "parity.rev.sumd20": {"acc": 0.452, "reasoning_bytes": 139.928, "flops_per_problem": 7946173218.816}, "parity.rev.sumd24": {"acc": 0.392, "reasoning_bytes": 157.904, "flops_per_problem": 8916700889.088}, "add.rev.sumd6": {"acc": 0.846, "reasoning_bytes": 191.626, "flops_per_problem": 9831671414.784}, "add.rev.sumd7": {"acc": 0.33, "reasoning_bytes": 223.088, "flops_per_problem": 11309632782.336}, "add.rev.sumd8": {"acc": 0.038, "reasoning_bytes": 229.934, "flops_per_problem": 11698797772.8}, "parity.rev.inc16": {"acc": 0.91, "reasoning_bytes": 122.016, "flops_per_problem": 6934308913.152}, "parity.rev.inc20": {"acc": 0.45, "reasoning_bytes": 140.904, "flops_per_problem": 7945113305.088}, "parity.rev.inc24": {"acc": 0.374, "reasoning_bytes": 158.868, "flops_per_problem": 8915111018.496}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 99.0, "flops_per_problem": 5772378488.832}, "runmax.rev.inc14": {"acc": 0.98, "reasoning_bytes": 107.244, "flops_per_problem": 6227611435.008}, "runmax.rev.inc16": {"acc": 0.948, "reasoning_bytes": 117.0, "flops_per_problem": 6747764097.024}, "inc.rev.inc6": {"acc": 0.94, "reasoning_bytes": 170.0, "flops_per_problem": 8695797202.944}, "inc.rev.inc7": {"acc": 0.392, "reasoning_bytes": 199.106, "flops_per_problem": 10068650459.136}, "inc.rev.inc8": {"acc": 0.022, "reasoning_bytes": 198.91, "flops_per_problem": 10101949415.424}, "parity.sumd.cmp16": {"acc": 0.976, "reasoning_bytes": 123.744, "flops_per_problem": 7143111917.568}, "parity.sumd.cmp20": {"acc": 0.938, "reasoning_bytes": 143.484, "flops_per_problem": 8191543246.848}, "parity.sumd.cmp24": {"acc": 0.938, "reasoning_bytes": 160.74, "flops_per_problem": 9130273505.28}, "runmax.sumd.cmp12": {"acc": 1.0, "reasoning_bytes": 102.0, "flops_per_problem": 6006177792.0}, "runmax.sumd.cmp14": {"acc": 0.992, "reasoning_bytes": 109.992, "flops_per_problem": 6447455207.424}, "runmax.sumd.cmp16": {"acc": 0.92, "reasoning_bytes": 119.976, "flops_per_problem": 6976705462.272}, "count.sumd.cmp16": {"acc": 0.996, "reasoning_bytes": 109.77, "flops_per_problem": 6570140221.44}, "count.sumd.cmp18": {"acc": 0.962, "reasoning_bytes": 116.48, "flops_per_problem": 6954800578.56}, "count.sumd.cmp20": {"acc": 0.942, "reasoning_bytes": 124.96, "flops_per_problem": 7417629573.12}, "sumd.sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 84.36, "flops_per_problem": 4917999697.92}, "sumd.sumd.runmax7": {"acc": 0.986, "reasoning_bytes": 92.856, "flops_per_problem": 5337372229.632}, "sumd.sumd.runmax8": {"acc": 0.694, "reasoning_bytes": 97.852, "flops_per_problem": 5602174009.344}, "count.sumd.runmax16": {"acc": 0.992, "reasoning_bytes": 110.82, "flops_per_problem": 6660674519.04}, "count.sumd.runmax18": {"acc": 0.926, "reasoning_bytes": 118.46, "flops_per_problem": 7086406533.12}, "count.sumd.runmax20": {"acc": 0.814, "reasoning_bytes": 125.99, "flops_per_problem": 7507280609.28}, "add.sumd.runmax6": {"acc": 0.996, "reasoning_bytes": 151.444, "flops_per_problem": 8145613651.968}, "add.sumd.runmax7": {"acc": 0.864, "reasoning_bytes": 171.294, "flops_per_problem": 9110576775.168}, "add.sumd.runmax8": {"acc": 0.176, "reasoning_bytes": 181.554, "flops_per_problem": 9652104364.032}, "parity.sumd.count16": {"acc": 1.0, "reasoning_bytes": 125.068, "flops_per_problem": 7289909968.896}, "parity.sumd.count20": {"acc": 1.0, "reasoning_bytes": 144.772, "flops_per_problem": 8336751427.584}, "parity.sumd.count24": {"acc": 1.0, "reasoning_bytes": 162.772, "flops_per_problem": 9308339011.584}, "sumd.sumd.count6": {"acc": 1.0, "reasoning_bytes": 84.184, "flops_per_problem": 4954390069.248}, "sumd.sumd.count7": {"acc": 0.998, "reasoning_bytes": 92.476, "flops_per_problem": 5364753334.272}, "sumd.sumd.count8": {"acc": 0.736, "reasoning_bytes": 96.732, "flops_per_problem": 5596874440.704}, "add.sumd.count6": {"acc": 0.994, "reasoning_bytes": 150.512, "flops_per_problem": 8148616740.864}, "add.sumd.count7": {"acc": 0.934, "reasoning_bytes": 170.12, "flops_per_problem": 9102892400.64}, "add.sumd.count8": {"acc": 0.598, "reasoning_bytes": 181.868, "flops_per_problem": 9710487945.216}, "runmax.sumd.find12": {"acc": 1.0, "reasoning_bytes": 103.0, "flops_per_problem": 6094503936.0}, "runmax.sumd.find14": {"acc": 0.994, "reasoning_bytes": 110.86, "flops_per_problem": 6529951825.92}, "runmax.sumd.find16": {"acc": 0.98, "reasoning_bytes": 121.0, "flops_per_problem": 7066091520.0}, "sumd.sumd.find6": {"acc": 1.0, "reasoning_bytes": 84.064, "flops_per_problem": 4904927428.608}, "sumd.sumd.find7": {"acc": 0.994, "reasoning_bytes": 92.354, "flops_per_problem": 5315202367.488}, "sumd.sumd.find8": {"acc": 0.846, "reasoning_bytes": 95.828, "flops_per_problem": 5512787951.616}, "parity.sumd.find16": {"acc": 0.954, "reasoning_bytes": 124.792, "flops_per_problem": 7233557889.024}, "parity.sumd.find20": {"acc": 0.858, "reasoning_bytes": 144.724, "flops_per_problem": 8290468528.128}, "parity.sumd.find24": {"acc": 0.868, "reasoning_bytes": 162.58, "flops_per_problem": 9255696629.76}, "count.sumd.rev16": {"acc": 0.99, "reasoning_bytes": 105.85, "flops_per_problem": 6308694835.2}, "count.sumd.rev18": {"acc": 0.876, "reasoning_bytes": 112.36, "flops_per_problem": 6684522577.92}, "count.sumd.rev20": {"acc": 0.802, "reasoning_bytes": 120.93, "flops_per_problem": 7151326248.96}, "parity.sumd.rev16": {"acc": 0.904, "reasoning_bytes": 120.98, "flops_per_problem": 6932719042.56}, "parity.sumd.rev20": {"acc": 0.45, "reasoning_bytes": 139.904, "flops_per_problem": 7945113305.088}, "parity.sumd.rev24": {"acc": 0.384, "reasoning_bytes": 157.868, "flops_per_problem": 8915111018.496}, "add.sumd.rev6": {"acc": 0.984, "reasoning_bytes": 145.414, "flops_per_problem": 7790542553.088}, "add.sumd.rev7": {"acc": 0.874, "reasoning_bytes": 165.26, "flops_per_problem": 8755594002.432}, "add.sumd.rev8": {"acc": 0.032, "reasoning_bytes": 170.674, "flops_per_problem": 9082930692.096}, "parity.sumd.sumd16": {"acc": 0.824, "reasoning_bytes": 122.876, "flops_per_problem": 7060615299.072}, "parity.sumd.sumd20": {"acc": 0.48, "reasoning_bytes": 142.676, "flops_per_problem": 8111696412.672}, "parity.sumd.sumd24": {"acc": 0.38, "reasoning_bytes": 160.82, "flops_per_problem": 9089643479.04}, "add.sumd.sumd6": {"acc": 0.996, "reasoning_bytes": 149.642, "flops_per_problem": 7986449940.48}, "add.sumd.sumd7": {"acc": 0.842, "reasoning_bytes": 169.486, "flops_per_problem": 8953002934.272}, "add.sumd.sumd8": {"acc": 0.094, "reasoning_bytes": 178.032, "flops_per_problem": 9420601540.608}, "count.sumd.sumd16": {"acc": 0.99, "reasoning_bytes": 108.81, "flops_per_problem": 6483580600.32}, "count.sumd.sumd18": {"acc": 0.896, "reasoning_bytes": 115.7, "flops_per_problem": 6876190310.4}, "count.sumd.sumd20": {"acc": 0.806, "reasoning_bytes": 123.94, "flops_per_problem": 7328420167.68}, "inc.sumd.inc6": {"acc": 0.992, "reasoning_bytes": 135.538, "flops_per_problem": 7045688180.736}, "inc.sumd.inc7": {"acc": 0.836, "reasoning_bytes": 153.07, "flops_per_problem": 7864118231.04}, "inc.sumd.inc8": {"acc": 0.114, "reasoning_bytes": 153.578, "flops_per_problem": 7930627817.472}, "sumd.sumd.inc6": {"acc": 1.0, "reasoning_bytes": 83.764, "flops_per_problem": 4773586452.48}, "sumd.sumd.inc7": {"acc": 0.974, "reasoning_bytes": 92.384, "flops_per_problem": 5201349967.872}, "sumd.sumd.inc8": {"acc": 0.632, "reasoning_bytes": 96.916, "flops_per_problem": 5443893559.296}, "parity.sumd.inc16": {"acc": 0.86, "reasoning_bytes": 124.38, "flops_per_problem": 7082873487.36}, "parity.sumd.inc20": {"acc": 0.464, "reasoning_bytes": 143.82, "flops_per_problem": 8118055895.04}, "parity.sumd.inc24": {"acc": 0.374, "reasoning_bytes": 161.862, "flops_per_problem": 9091498328.064}, "inc.inc.cmp6": {"acc": 0.99, "reasoning_bytes": 144.698, "flops_per_problem": 7671037280.256}, "inc.inc.cmp7": {"acc": 0.966, "reasoning_bytes": 165.516, "flops_per_problem": 8678750257.152}, "inc.inc.cmp8": {"acc": 0.96, "reasoning_bytes": 175.108, "flops_per_problem": 9190688587.776}, "runmax.inc.cmp12": {"acc": 1.0, "reasoning_bytes": 105.568, "flops_per_problem": 6150856015.872}, "runmax.inc.cmp14": {"acc": 0.99, "reasoning_bytes": 114.468, "flops_per_problem": 6636296503.296}, "runmax.inc.cmp16": {"acc": 0.924, "reasoning_bytes": 123.7, "flops_per_problem": 7133572694.016}, "sumd.inc.cmp6": {"acc": 1.0, "reasoning_bytes": 88.12, "flops_per_problem": 5039713124.352}, "sumd.inc.cmp7": {"acc": 0.996, "reasoning_bytes": 95.94, "flops_per_problem": 5429408071.68}, "sumd.inc.cmp8": {"acc": 0.958, "reasoning_bytes": 97.512, "flops_per_problem": 5542995492.864}, "sumd.inc.runmax6": {"acc": 1.0, "reasoning_bytes": 93.522, "flops_per_problem": 5278458691.584}, "sumd.inc.runmax7": {"acc": 0.988, "reasoning_bytes": 101.48, "flops_per_problem": 5674071490.56}, "sumd.inc.runmax8": {"acc": 0.598, "reasoning_bytes": 105.636, "flops_per_problem": 5901776289.792}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.648, "flops_per_problem": 6343936966.656}, "runmax.inc.runmax14": {"acc": 0.98, "reasoning_bytes": 118.524, "flops_per_problem": 6824254537.728}, "runmax.inc.runmax16": {"acc": 0.948, "reasoning_bytes": 128.356, "flops_per_problem": 7346792005.632}, "add.inc.runmax6": {"acc": 1.0, "reasoning_bytes": 192.872, "flops_per_problem": 9931038326.784}, "add.inc.runmax7": {"acc": 0.976, "reasoning_bytes": 220.732, "flops_per_problem": 11249747656.704}, "add.inc.runmax8": {"acc": 0.636, "reasoning_bytes": 227.978, "flops_per_problem": 11657991094.272}, "runmax.inc.count12": {"acc": 1.0, "reasoning_bytes": 108.928, "flops_per_problem": 6356302626.816}, "runmax.inc.count14": {"acc": 0.996, "reasoning_bytes": 117.59, "flops_per_problem": 6827169300.48}, "runmax.inc.count16": {"acc": 0.998, "reasoning_bytes": 127.432, "flops_per_problem": 7350148399.104}, "sumd.inc.count6": {"acc": 1.0, "reasoning_bytes": 92.388, "flops_per_problem": 5272540839.936}, "sumd.inc.count7": {"acc": 0.99, "reasoning_bytes": 100.396, "flops_per_problem": 5670361792.512}, "sumd.inc.count8": {"acc": 0.672, "reasoning_bytes": 103.274, "flops_per_problem": 5842509447.168}, "inc.inc.count6": {"acc": 0.956, "reasoning_bytes": 165.0, "flops_per_problem": 8435146752.0}, "inc.inc.count7": {"acc": 0.788, "reasoning_bytes": 188.97, "flops_per_problem": 9537898659.84}, "inc.inc.count8": {"acc": 0.702, "reasoning_bytes": 189.996, "flops_per_problem": 9627373043.712}, "parity.inc.find16": {"acc": 0.96, "reasoning_bytes": 125.732, "flops_per_problem": 7230908104.704}, "parity.inc.find20": {"acc": 0.894, "reasoning_bytes": 145.724, "flops_per_problem": 8290468528.128}, "parity.inc.find24": {"acc": 0.832, "reasoning_bytes": 163.7, "flops_per_problem": 9260996198.4}, "sumd.inc.find6": {"acc": 1.0, "reasoning_bytes": 92.1, "flops_per_problem": 5215658803.2}, "sumd.inc.find7": {"acc": 0.998, "reasoning_bytes": 100.356, "flops_per_problem": 5624432197.632}, "sumd.inc.find8": {"acc": 0.786, "reasoning_bytes": 102.914, "flops_per_problem": 5782712647.68}, "count.inc.find16": {"acc": 1.0, "reasoning_bytes": 111.87, "flops_per_problem": 6662882672.64}, "count.inc.find18": {"acc": 0.968, "reasoning_bytes": 118.59, "flops_per_problem": 7047984660.48}, "count.inc.find20": {"acc": 0.932, "reasoning_bytes": 126.98, "flops_per_problem": 7506838978.56}, "sumd.inc.rev6": {"acc": 1.0, "reasoning_bytes": 87.524, "flops_per_problem": 4925154115.584}, "sumd.inc.rev7": {"acc": 0.986, "reasoning_bytes": 95.448, "flops_per_problem": 5319353696.256}, "sumd.inc.rev8": {"acc": 0.44, "reasoning_bytes": 98.674, "flops_per_problem": 5505898512.384}, "count.inc.rev16": {"acc": 0.992, "reasoning_bytes": 106.81, "flops_per_problem": 6306928312.32}, "count.inc.rev18": {"acc": 0.848, "reasoning_bytes": 113.09, "flops_per_problem": 6672598548.48}, "count.inc.rev20": {"acc": 0.744, "reasoning_bytes": 121.93, "flops_per_problem": 7151326248.96}, "parity.inc.rev16": {"acc": 0.898, "reasoning_bytes": 121.896, "flops_per_problem": 6929009344.512}, "parity.inc.rev20": {"acc": 0.45, "reasoning_bytes": 140.88, "flops_per_problem": 7944053391.36}, "parity.inc.rev24": {"acc": 0.352, "reasoning_bytes": 158.796, "flops_per_problem": 8911931277.312}, "count.inc.sumd16": {"acc": 0.99, "reasoning_bytes": 109.8, "flops_per_problem": 6483138969.6}, "count.inc.sumd18": {"acc": 0.886, "reasoning_bytes": 116.42, "flops_per_problem": 6863824650.24}, "count.inc.sumd20": {"acc": 0.808, "reasoning_bytes": 124.91, "flops_per_problem": 7327095275.52}, "sumd.inc.sumd6": {"acc": 1.0, "reasoning_bytes": 91.758, "flops_per_problem": 5122651373.568}, "sumd.inc.sumd7": {"acc": 0.986, "reasoning_bytes": 99.746, "flops_per_problem": 5521620566.016}, "sumd.inc.sumd8": {"acc": 0.626, "reasoning_bytes": 104.16, "flops_per_problem": 5766019006.464}, "add.inc.sumd6": {"acc": 0.898, "reasoning_bytes": 198.518, "flops_per_problem": 10136043307.008}, "add.inc.sumd7": {"acc": 0.504, "reasoning_bytes": 228.056, "flops_per_problem": 11528681619.456}, "add.inc.sumd8": {"acc": 0.052, "reasoning_bytes": 234.966, "flops_per_problem": 11924206092.288}, "parity.inc.inc16": {"acc": 0.826, "reasoning_bytes": 125.056, "flops_per_problem": 7068564652.032}, "parity.inc.inc20": {"acc": 0.496, "reasoning_bytes": 144.796, "flops_per_problem": 8116995981.312}, "parity.inc.inc24": {"acc": 0.332, "reasoning_bytes": 162.856, "flops_per_problem": 9091233349.632}, "sumd.inc.inc6": {"acc": 1.0, "reasoning_bytes": 94.518, "flops_per_problem": 5234118967.296}, "sumd.inc.inc7": {"acc": 0.984, "reasoning_bytes": 102.432, "flops_per_problem": 5627788591.104}, "sumd.inc.inc8": {"acc": 0.49, "reasoning_bytes": 106.13, "flops_per_problem": 5835266703.36}, "runmax.inc.inc12": {"acc": 1.0, "reasoning_bytes": 110.06, "flops_per_problem": 6270272962.56}, "runmax.inc.inc14": {"acc": 0.976, "reasoning_bytes": 117.932, "flops_per_problem": 6707399049.216}, "runmax.inc.inc16": {"acc": 0.93, "reasoning_bytes": 128.734, "flops_per_problem": 7273128001.536}, "count.inc.cmp16": {"acc": 0.998, "reasoning_bytes": 110.76, "flops_per_problem": 6569698590.72}, "count.inc.cmp18": {"acc": 0.962, "reasoning_bytes": 117.19, "flops_per_problem": 6942169939.968}, "count.inc.cmp20": {"acc": 0.926, "reasoning_bytes": 125.952, "flops_per_problem": 7417717899.264}, "inc.rev.sumd6": {"acc": 0.772, "reasoning_bytes": 166.276, "flops_per_problem": 8403084361.728}, "inc.rev.sumd7": {"acc": 0.328, "reasoning_bytes": 195.14, "flops_per_problem": 9721793691.648}, "inc.rev.sumd8": {"acc": 0.062, "reasoning_bytes": 196.288, "flops_per_problem": 9816920948.736}, "runmax.inc.find12": {"acc": 0.976, "reasoning_bytes": 107.552, "flops_per_problem": 6251371167.744}, "runmax.inc.find14": {"acc": 0.984, "reasoning_bytes": 115.836, "flops_per_problem": 6705544200.192}, "runmax.inc.find16": {"acc": 0.97, "reasoning_bytes": 127.244, "flops_per_problem": 7297682669.568}, "inc.runmax.cmp6": {"acc": 0.998, "reasoning_bytes": 120.0, "flops_per_problem": 6491971584.0}, "inc.runmax.cmp7": {"acc": 0.984, "reasoning_bytes": 135.088, "flops_per_problem": 7202467086.336}, "inc.runmax.cmp8": {"acc": 0.972, "reasoning_bytes": 135.984, "flops_per_problem": 7286200270.848}} +{"step": 9000, "train_loss": 0.9719843864440918} +{"step": 9020, "train_loss": 1.025726318359375} +{"step": 9040, "train_loss": 1.0683258771896362} +{"step": 9060, "train_loss": 0.995534360408783} +{"step": 9080, "train_loss": 1.0371356010437012} +{"step": 9100, "train_loss": 1.08146071434021} +{"step": 9120, "train_loss": 1.0305079221725464} +{"step": 9140, "train_loss": 1.0284518003463745} +{"step": 9160, "train_loss": 1.043845772743225} +{"step": 9180, "train_loss": 0.9939771890640259} +{"step": 9200, "train_loss": 1.0559842586517334} +{"step": 9220, "train_loss": 1.0624394416809082} +{"step": 9240, "train_loss": 0.9999403953552246} +{"step": 9260, "train_loss": 1.0314055681228638} +{"step": 9280, "train_loss": 1.0763161182403564} +{"step": 9300, "train_loss": 0.9976549744606018} +{"step": 9320, "train_loss": 0.9664639234542847} +{"step": 9340, "train_loss": 1.089273452758789} +{"step": 9360, "train_loss": 1.0411092042922974} +{"step": 9380, "train_loss": 0.9675300121307373} +{"step": 9400, "train_loss": 1.0141677856445312} +{"step": 9420, "train_loss": 0.9776031970977783} +{"step": 9440, "train_loss": 1.0451377630233765} +{"step": 9460, "train_loss": 0.9731520414352417} +{"step": 9480, "train_loss": 1.01694917678833} +{"step": 9500, "train_loss": 1.0128346681594849} +{"step": 9520, "train_loss": 1.046426773071289} +{"step": 9540, "train_loss": 1.042891502380371} +{"step": 9560, "train_loss": 0.9860252141952515} +{"step": 9580, "train_loss": 1.0236775875091553} +{"step": 9600, "train_loss": 1.0128815174102783} +{"step": 9620, "train_loss": 0.9728927612304688} +{"step": 9640, "train_loss": 1.0091474056243896} +{"step": 9660, "train_loss": 1.0394015312194824} +{"step": 9680, "train_loss": 0.9559230208396912} +{"step": 9700, "train_loss": 1.1031736135482788} +{"step": 9720, "train_loss": 1.0592104196548462} +{"step": 9740, "train_loss": 1.0310202836990356} +{"step": 9760, "train_loss": 0.9968513250350952} +{"step": 9780, "train_loss": 0.9524262547492981} +{"step": 9800, "train_loss": 1.005033016204834} +{"step": 9820, "train_loss": 0.9576445817947388} +{"step": 9840, "train_loss": 1.0388824939727783} +{"step": 9860, "train_loss": 0.9104354381561279} +{"step": 9880, "train_loss": 1.038284420967102} +{"step": 9900, "train_loss": 1.0351779460906982} +{"step": 9920, "train_loss": 1.084693431854248} +{"step": 9940, "train_loss": 1.0043779611587524} +{"step": 9960, "train_loss": 1.0056755542755127} +{"step": 9980, "train_loss": 0.9890419244766235} +{"step": 10000, "tokens": 327680000, "val_loss": 1.8375942766666413, "val_bpb": 0.6624228827122312, "lr": 0.00010409270447323454, "elapsed": 3173.727211713791, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.946, "reasoning_bytes": 79.0, "flops_per_problem": 4928422182.912}, "add9": {"acc": 0.59, "reasoning_bytes": 88.96, "flops_per_problem": 5500422291.456}, "add10": {"acc": 0.0, "reasoning_bytes": 96.298, "flops_per_problem": 5945497731.072}, "reach14": {"acc": 0.514, "reasoning_bytes": 8.178, "flops_per_problem": 4644983586.816}, "reach16": {"acc": 0.502, "reasoning_bytes": 8.662, "flops_per_problem": 5196403703.808}, "reach18": {"acc": 0.478, "reasoning_bytes": 9.402, "flops_per_problem": 5758952914.944}, "parity24": {"acc": 0.644, "reasoning_bytes": 142.604, "flops_per_problem": 7843538239.488}, "parity28": {"acc": 0.512, "reasoning_bytes": 165.14, "flops_per_problem": 9015449518.08}, "parity32": {"acc": 0.514, "reasoning_bytes": 187.118, "flops_per_problem": 10162717802.496}, "cmp8": {"acc": 0.994, "reasoning_bytes": 5.768, "flops_per_problem": 1358809399.296}, "cmp9": {"acc": 0.996, "reasoning_bytes": 5.696, "flops_per_problem": 1443955802.112}, "cmp10": {"acc": 0.99, "reasoning_bytes": 5.744, "flops_per_problem": 1534401773.568}, "runmax12": {"acc": 1.0, "reasoning_bytes": 71.0, "flops_per_problem": 4151328768.0}, "runmax14": {"acc": 0.994, "reasoning_bytes": 82.292, "flops_per_problem": 4738344321.024}, "runmax16": {"acc": 0.98, "reasoning_bytes": 89.06, "flops_per_problem": 5125566136.32}, "count16": {"acc": 0.99, "reasoning_bytes": 79.03, "flops_per_problem": 4726773596.16}, "count18": {"acc": 0.93, "reasoning_bytes": 88.21, "flops_per_problem": 5222371590.144}, "count20": {"acc": 0.738, "reasoning_bytes": 95.454, "flops_per_problem": 5631674941.44}, "brackets16": {"acc": 0.93, "reasoning_bytes": 54.972, "flops_per_problem": 3708549808.128}, "brackets18": {"acc": 0.924, "reasoning_bytes": 58.658, "flops_per_problem": 3959572709.376}, "brackets20": {"acc": 0.894, "reasoning_bytes": 65.982, "flops_per_problem": 4371614171.136}, "sumd8": {"acc": 0.952, "reasoning_bytes": 58.568, "flops_per_problem": 3381389770.752}, "sumd9": {"acc": 0.776, "reasoning_bytes": 66.212, "flops_per_problem": 3763223691.264}, "sumd10": {"acc": 0.286, "reasoning_bytes": 70.178, "flops_per_problem": 3983067463.68}, "inc8": {"acc": 0.98, "reasoning_bytes": 63.024, "flops_per_problem": 3798642475.008}, "inc9": {"acc": 0.466, "reasoning_bytes": 69.904, "flops_per_problem": 4184097767.424}, "inc10": {"acc": 0.0, "reasoning_bytes": 60.778, "flops_per_problem": 3530130997.248}, "add.cmp6": {"acc": 1.0, "reasoning_bytes": 92.616, "flops_per_problem": 5531778072.576}, "add.cmp7": {"acc": 1.0, "reasoning_bytes": 105.466, "flops_per_problem": 6229024653.312}, "add.cmp8": {"acc": 0.994, "reasoning_bytes": 117.882, "flops_per_problem": 6911344115.712}, "add.runmax6": {"acc": 1.0, "reasoning_bytes": 120.832, "flops_per_problem": 6572878331.904}, "add.runmax7": {"acc": 0.988, "reasoning_bytes": 138.77, "flops_per_problem": 7453401661.44}, "add.runmax8": {"acc": 0.546, "reasoning_bytes": 156.028, "flops_per_problem": 8303894102.016}, "add.count6": {"acc": 0.992, "reasoning_bytes": 115.648, "flops_per_problem": 6388100038.656}, "add.count7": {"acc": 0.962, "reasoning_bytes": 132.076, "flops_per_problem": 7201937129.472}, "add.count8": {"acc": 0.41, "reasoning_bytes": 148.314, "flops_per_problem": 8007383236.608}, "add.find6": {"acc": 0.92, "reasoning_bytes": 107.694, "flops_per_problem": 5992663891.968}, "add.find7": {"acc": 0.852, "reasoning_bytes": 121.546, "flops_per_problem": 6692736909.312}, "add.find8": {"acc": 0.508, "reasoning_bytes": 138.312, "flops_per_problem": 7521412792.32}, "add.rev6": {"acc": 0.998, "reasoning_bytes": 123.248, "flops_per_problem": 6794576953.344}, "add.rev7": {"acc": 0.77, "reasoning_bytes": 145.78, "flops_per_problem": 7920823615.488}, "add.rev8": {"acc": 0.002, "reasoning_bytes": 165.352, "flops_per_problem": 8895237636.096}, "add.sumd6": {"acc": 0.998, "reasoning_bytes": 126.476, "flops_per_problem": 6777794985.984}, "add.sumd7": {"acc": 0.93, "reasoning_bytes": 146.046, "flops_per_problem": 7730480775.168}, "add.sumd8": {"acc": 0.054, "reasoning_bytes": 163.784, "flops_per_problem": 8602259816.448}, "add.inc6": {"acc": 0.982, "reasoning_bytes": 131.04, "flops_per_problem": 7138695610.368}, "add.inc7": {"acc": 0.566, "reasoning_bytes": 150.768, "flops_per_problem": 8140844040.192}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 163.098, "flops_per_problem": 8785006608.384}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5122916352.0}, "runmax.cmp14": {"acc": 0.98, "reasoning_bytes": 93.492, "flops_per_problem": 5497949159.424}, "runmax.cmp16": {"acc": 0.886, "reasoning_bytes": 104.952, "flops_per_problem": 6092384108.544}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.runmax14": {"acc": 0.98, "reasoning_bytes": 97.276, "flops_per_problem": 5709225295.872}, "runmax.runmax16": {"acc": 0.984, "reasoning_bytes": 106.0, "flops_per_problem": 6182830080.0}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 87.988, "flops_per_problem": 5254875611.136}, "runmax.count14": {"acc": 0.998, "reasoning_bytes": 94.756, "flops_per_problem": 5642097426.432}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 106.0, "flops_per_problem": 6226993152.0}, "runmax.find12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.find14": {"acc": 0.99, "reasoning_bytes": 94.528, "flops_per_problem": 5587865174.016}, "runmax.find16": {"acc": 0.992, "reasoning_bytes": 105.976, "flops_per_problem": 6181770166.272}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 83.0, "flops_per_problem": 4857937920.0}, "runmax.rev14": {"acc": 0.978, "reasoning_bytes": 90.668, "flops_per_problem": 5284906500.096}, "runmax.rev16": {"acc": 0.97, "reasoning_bytes": 100.988, "flops_per_problem": 5828995547.136}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 86.0, "flops_per_problem": 5034590208.0}, "runmax.sumd14": {"acc": 0.982, "reasoning_bytes": 95.132, "flops_per_problem": 5526213525.504}, "runmax.sumd16": {"acc": 0.98, "reasoning_bytes": 104.0, "flops_per_problem": 6006177792.0}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5065769336.832}, "runmax.inc14": {"acc": 0.97, "reasoning_bytes": 94.032, "flops_per_problem": 5467211661.312}, "runmax.inc16": {"acc": 0.97, "reasoning_bytes": 104.988, "flops_per_problem": 6041596575.744}, "count.cmp16": {"acc": 0.992, "reasoning_bytes": 95.02, "flops_per_problem": 5697919549.44}, "count.cmp18": {"acc": 0.954, "reasoning_bytes": 102.47, "flops_per_problem": 6115348905.984}, "count.cmp20": {"acc": 0.894, "reasoning_bytes": 110.0, "flops_per_problem": 6536311308.288}, "count.runmax16": {"acc": 0.988, "reasoning_bytes": 96.02, "flops_per_problem": 5786245693.44}, "count.runmax18": {"acc": 0.918, "reasoning_bytes": 104.62, "flops_per_problem": 6254374256.64}, "count.runmax20": {"acc": 0.75, "reasoning_bytes": 111.228, "flops_per_problem": 6634529980.416}, "count.count16": {"acc": 1.0, "reasoning_bytes": 96.04, "flops_per_problem": 5831292026.88}, "count.count18": {"acc": 1.0, "reasoning_bytes": 104.53, "flops_per_problem": 6294562652.16}, "count.count20": {"acc": 0.996, "reasoning_bytes": 111.352, "flops_per_problem": 6679311335.424}, "count.find16": {"acc": 0.994, "reasoning_bytes": 96.11, "flops_per_problem": 5790220369.92}, "count.find18": {"acc": 0.93, "reasoning_bytes": 105.05, "flops_per_problem": 6273364377.6}, "count.find20": {"acc": 0.866, "reasoning_bytes": 111.514, "flops_per_problem": 6647160619.008}, "count.rev16": {"acc": 0.992, "reasoning_bytes": 91.01, "flops_per_problem": 5432499486.72}, "count.rev18": {"acc": 0.874, "reasoning_bytes": 98.43, "flops_per_problem": 5848515624.96}, "count.rev20": {"acc": 0.728, "reasoning_bytes": 105.968, "flops_per_problem": 6268594765.824}, "count.sumd16": {"acc": 0.99, "reasoning_bytes": 94.02, "flops_per_problem": 5609593405.44}, "count.sumd18": {"acc": 0.896, "reasoning_bytes": 101.774, "flops_per_problem": 6040360009.728}, "count.sumd20": {"acc": 0.754, "reasoning_bytes": 109.308, "flops_per_problem": 6457789366.272}, "count.inc16": {"acc": 0.996, "reasoning_bytes": 95.03, "flops_per_problem": 5610035036.16}, "count.inc18": {"acc": 0.89, "reasoning_bytes": 103.09, "flops_per_problem": 6054315540.48}, "count.inc20": {"acc": 0.724, "reasoning_bytes": 110.44, "flops_per_problem": 6461410738.176}, "parity.cmp16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6359482368.0}, "parity.cmp20": {"acc": 0.942, "reasoning_bytes": 130.548, "flops_per_problem": 7399434387.456}, "parity.cmp24": {"acc": 0.944, "reasoning_bytes": 152.592, "flops_per_problem": 8549617434.624}, "parity.runmax16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.runmax20": {"acc": 0.586, "reasoning_bytes": 131.74, "flops_per_problem": 7496239841.28}, "parity.runmax24": {"acc": 0.478, "reasoning_bytes": 153.976, "flops_per_problem": 8654902198.272}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6491971584.0}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 130.888, "flops_per_problem": 7502775975.936}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 153.76, "flops_per_problem": 8689526046.72}, "parity.find16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.find20": {"acc": 0.884, "reasoning_bytes": 131.524, "flops_per_problem": 7486700617.728}, "parity.find24": {"acc": 0.852, "reasoning_bytes": 153.928, "flops_per_problem": 8652782370.816}, "parity.rev16": {"acc": 1.0, "reasoning_bytes": 107.0, "flops_per_problem": 6094503936.0}, "parity.rev20": {"acc": 0.664, "reasoning_bytes": 127.856, "flops_per_problem": 7192221253.632}, "parity.rev24": {"acc": 0.418, "reasoning_bytes": 149.0, "flops_per_problem": 8302657536.0}, "parity.sumd16": {"acc": 1.0, "reasoning_bytes": 110.0, "flops_per_problem": 6271156224.0}, "parity.sumd20": {"acc": 0.652, "reasoning_bytes": 130.628, "flops_per_problem": 7358804361.216}, "parity.sumd24": {"acc": 0.436, "reasoning_bytes": 152.0, "flops_per_problem": 8479309824.0}, "parity.inc16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6271156224.0}, "parity.inc20": {"acc": 0.814, "reasoning_bytes": 133.056, "flops_per_problem": 7421869228.032}, "parity.inc24": {"acc": 0.42, "reasoning_bytes": 153.084, "flops_per_problem": 8483019522.048}, "sumd.cmp6": {"acc": 1.0, "reasoning_bytes": 62.088, "flops_per_problem": 3713407746.048}, "sumd.cmp7": {"acc": 1.0, "reasoning_bytes": 70.082, "flops_per_problem": 4110787067.904}, "sumd.cmp8": {"acc": 0.962, "reasoning_bytes": 74.05, "flops_per_problem": 4330100883.456}, "sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.998, "reasoning_bytes": 75.48, "flops_per_problem": 4349179330.56}, "sumd.runmax8": {"acc": 0.842, "reasoning_bytes": 82.152, "flops_per_problem": 4688263397.376}, "sumd.count6": {"acc": 1.0, "reasoning_bytes": 66.428, "flops_per_problem": 3949415202.816}, "sumd.count7": {"acc": 0.994, "reasoning_bytes": 74.46, "flops_per_problem": 4348296069.12}, "sumd.count8": {"acc": 0.792, "reasoning_bytes": 80.028, "flops_per_problem": 4638359126.016}, "sumd.find6": {"acc": 1.0, "reasoning_bytes": 66.24, "flops_per_problem": 3896949473.28}, "sumd.find7": {"acc": 0.998, "reasoning_bytes": 74.44, "flops_per_problem": 4303249735.68}, "sumd.find8": {"acc": 0.902, "reasoning_bytes": 79.758, "flops_per_problem": 4582272024.576}, "sumd.rev6": {"acc": 1.0, "reasoning_bytes": 61.544, "flops_per_problem": 3601145217.024}, "sumd.rev7": {"acc": 1.0, "reasoning_bytes": 69.48, "flops_per_problem": 3995874754.56}, "sumd.rev8": {"acc": 0.726, "reasoning_bytes": 75.362, "flops_per_problem": 4299716689.92}, "sumd.sumd6": {"acc": 1.0, "reasoning_bytes": 65.744, "flops_per_problem": 3795639386.112}, "sumd.sumd7": {"acc": 0.996, "reasoning_bytes": 73.742, "flops_per_problem": 4195668492.288}, "sumd.sumd8": {"acc": 0.848, "reasoning_bytes": 80.452, "flops_per_problem": 4537490669.568}, "sumd.inc6": {"acc": 1.0, "reasoning_bytes": 68.538, "flops_per_problem": 3910021742.592}, "sumd.inc7": {"acc": 0.998, "reasoning_bytes": 76.48, "flops_per_problem": 4305016258.56}, "sumd.inc8": {"acc": 0.81, "reasoning_bytes": 83.032, "flops_per_problem": 4638535778.304}, "inc.cmp6": {"acc": 0.998, "reasoning_bytes": 78.624, "flops_per_problem": 4576354172.928}, "inc.cmp7": {"acc": 0.996, "reasoning_bytes": 89.79, "flops_per_problem": 5157805178.88}, "inc.cmp8": {"acc": 0.972, "reasoning_bytes": 100.54, "flops_per_problem": 5720884346.88}, "inc.runmax6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5520384000.0}, "inc.runmax7": {"acc": 1.0, "reasoning_bytes": 120.0, "flops_per_problem": 6271156224.0}, "inc.runmax8": {"acc": 0.932, "reasoning_bytes": 122.24, "flops_per_problem": 6414244577.28}, "inc.count6": {"acc": 0.99, "reasoning_bytes": 99.0, "flops_per_problem": 5343731712.0}, "inc.count7": {"acc": 0.948, "reasoning_bytes": 114.0, "flops_per_problem": 6050340864.0}, "inc.count8": {"acc": 0.75, "reasoning_bytes": 114.632, "flops_per_problem": 6122414997.504}, "inc.find6": {"acc": 0.964, "reasoning_bytes": 91.88, "flops_per_problem": 4985127567.36}, "inc.find7": {"acc": 0.91, "reasoning_bytes": 102.628, "flops_per_problem": 5503955337.216}, "inc.find8": {"acc": 0.352, "reasoning_bytes": 91.966, "flops_per_problem": 5077251735.552}, "inc.rev6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5608710144.0}, "inc.rev7": {"acc": 0.928, "reasoning_bytes": 124.0, "flops_per_problem": 6580032749.568}, "inc.rev8": {"acc": 0.008, "reasoning_bytes": 126.958, "flops_per_problem": 6755978428.416}, "inc.sumd6": {"acc": 1.0, "reasoning_bytes": 109.558, "flops_per_problem": 5721590956.032}, "inc.sumd7": {"acc": 0.944, "reasoning_bytes": 127.526, "flops_per_problem": 6559276105.728}, "inc.sumd8": {"acc": 0.114, "reasoning_bytes": 131.12, "flops_per_problem": 6762161258.496}, "inc.inc6": {"acc": 0.996, "reasoning_bytes": 113.0, "flops_per_problem": 6006001139.712}, "inc.inc7": {"acc": 0.94, "reasoning_bytes": 130.998, "flops_per_problem": 6888997601.28}, "inc.inc8": {"acc": 0.028, "reasoning_bytes": 134.248, "flops_per_problem": 7083138465.792}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 0.992, "reasoning_bytes": 112.688, "flops_per_problem": 6654844993.536}, "runmax.runmax.cmp16": {"acc": 0.992, "reasoning_bytes": 122.0, "flops_per_problem": 7154417664.0}, "sumd.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 83.338, "flops_per_problem": 4917028110.336}, "sumd.runmax.cmp7": {"acc": 0.994, "reasoning_bytes": 91.388, "flops_per_problem": 5316703911.936}, "sumd.runmax.cmp8": {"acc": 0.694, "reasoning_bytes": 92.632, "flops_per_problem": 5415805845.504}, "add.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 137.024, "flops_per_problem": 7552945225.728}, "add.runmax.cmp7": {"acc": 0.978, "reasoning_bytes": 154.736, "flops_per_problem": 8423487700.992}, "add.runmax.cmp8": {"acc": 0.872, "reasoning_bytes": 163.28, "flops_per_problem": 8889143132.16}, "count.runmax.runmax16": {"acc": 0.98, "reasoning_bytes": 113.03, "flops_per_problem": 6846601052.16}, "count.runmax.runmax18": {"acc": 0.954, "reasoning_bytes": 122.698, "flops_per_problem": 7361895776.256}, "count.runmax.runmax20": {"acc": 0.796, "reasoning_bytes": 128.488, "flops_per_problem": 7705926107.136}, "add.runmax.runmax6": {"acc": 1.0, "reasoning_bytes": 137.832, "flops_per_problem": 7632792059.904}, "add.runmax.runmax7": {"acc": 0.976, "reasoning_bytes": 155.802, "flops_per_problem": 8514728607.744}, "add.runmax.runmax8": {"acc": 0.514, "reasoning_bytes": 171.058, "flops_per_problem": 9276806578.176}, "parity.runmax.runmax16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7507722240.0}, "parity.runmax.runmax20": {"acc": 0.43, "reasoning_bytes": 147.216, "flops_per_problem": 8488849047.552}, "parity.runmax.runmax24": {"acc": 0.442, "reasoning_bytes": 169.356, "flops_per_problem": 9643271749.632}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7551885312.0}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 147.216, "flops_per_problem": 8533012119.552}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 169.596, "flops_per_problem": 9698033958.912}, "inc.runmax.count6": {"acc": 1.0, "reasoning_bytes": 121.0, "flops_per_problem": 6624460800.0}, "inc.runmax.count7": {"acc": 1.0, "reasoning_bytes": 137.0, "flops_per_problem": 7375233024.0}, "inc.runmax.count8": {"acc": 0.996, "reasoning_bytes": 137.26, "flops_per_problem": 7430878494.72}, "sumd.runmax.count6": {"acc": 1.0, "reasoning_bytes": 84.424, "flops_per_problem": 5053315350.528}, "sumd.runmax.count7": {"acc": 1.0, "reasoning_bytes": 92.46, "flops_per_problem": 5452372869.12}, "sumd.runmax.count8": {"acc": 0.852, "reasoning_bytes": 96.448, "flops_per_problem": 5672658272.256}, "runmax.runmax.find12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6271156224.0}, "runmax.runmax.find14": {"acc": 0.994, "reasoning_bytes": 113.436, "flops_per_problem": 6732042043.392}, "runmax.runmax.find16": {"acc": 0.988, "reasoning_bytes": 123.0, "flops_per_problem": 7242743808.0}, "add.runmax.find6": {"acc": 1.0, "reasoning_bytes": 137.928, "flops_per_problem": 7637031714.816}, "add.runmax.find7": {"acc": 0.994, "reasoning_bytes": 155.576, "flops_per_problem": 8504747753.472}, "add.runmax.find8": {"acc": 0.852, "reasoning_bytes": 170.28, "flops_per_problem": 9242447708.16}, "parity.runmax.find16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7507722240.0}, "parity.runmax.find20": {"acc": 0.872, "reasoning_bytes": 147.168, "flops_per_problem": 8486729220.096}, "parity.runmax.find24": {"acc": 0.856, "reasoning_bytes": 168.792, "flops_per_problem": 9618363777.024}, "add.runmax.rev6": {"acc": 1.0, "reasoning_bytes": 132.832, "flops_per_problem": 7279487483.904}, "add.runmax.rev7": {"acc": 0.992, "reasoning_bytes": 150.802, "flops_per_problem": 8161424031.744}, "add.runmax.rev8": {"acc": 0.508, "reasoning_bytes": 163.566, "flops_per_problem": 8813447626.752}, "parity.runmax.rev16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7154417664.0}, "parity.runmax.rev20": {"acc": 0.462, "reasoning_bytes": 142.384, "flops_per_problem": 8142963867.648}, "parity.runmax.rev24": {"acc": 0.46, "reasoning_bytes": 165.16, "flops_per_problem": 9325474283.52}, "sumd.runmax.rev6": {"acc": 1.0, "reasoning_bytes": 79.542, "flops_per_problem": 4661058945.024}, "sumd.runmax.rev7": {"acc": 0.996, "reasoning_bytes": 87.48, "flops_per_problem": 5055788482.56}, "sumd.runmax.rev8": {"acc": 0.498, "reasoning_bytes": 91.012, "flops_per_problem": 5255935524.864}, "sumd.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 82.542, "flops_per_problem": 4837711233.024}, "sumd.runmax.sumd7": {"acc": 0.996, "reasoning_bytes": 90.48, "flops_per_problem": 5232440770.56}, "sumd.runmax.sumd8": {"acc": 0.648, "reasoning_bytes": 95.548, "flops_per_problem": 5500422291.456}, "add.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 135.832, "flops_per_problem": 7456139771.904}, "add.runmax.sumd7": {"acc": 0.99, "reasoning_bytes": 153.752, "flops_per_problem": 8335868166.144}, "add.runmax.sumd8": {"acc": 0.504, "reasoning_bytes": 169.0, "flops_per_problem": 9097592832.0}, "parity.runmax.sumd16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.runmax.sumd20": {"acc": 0.454, "reasoning_bytes": 145.324, "flops_per_problem": 8316966371.328}, "parity.runmax.sumd24": {"acc": 0.494, "reasoning_bytes": 168.136, "flops_per_problem": 9501066657.792}, "count.runmax.inc16": {"acc": 0.982, "reasoning_bytes": 112.04, "flops_per_problem": 6670390394.88}, "count.runmax.inc18": {"acc": 0.948, "reasoning_bytes": 121.34, "flops_per_problem": 7169433108.48}, "count.runmax.inc20": {"acc": 0.768, "reasoning_bytes": 127.188, "flops_per_problem": 7516024897.536}, "runmax.runmax.inc12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6125683064.832}, "runmax.runmax.inc14": {"acc": 0.984, "reasoning_bytes": 113.66, "flops_per_problem": 6643627573.248}, "runmax.runmax.inc16": {"acc": 0.974, "reasoning_bytes": 122.0, "flops_per_problem": 7102216912.896}, "add.runmax.inc6": {"acc": 1.0, "reasoning_bytes": 136.832, "flops_per_problem": 7477161394.176}, "add.runmax.inc7": {"acc": 0.982, "reasoning_bytes": 154.774, "flops_per_problem": 8361217769.472}, "add.runmax.inc8": {"acc": 0.498, "reasoning_bytes": 167.94, "flops_per_problem": 9031701528.576}, "count.count.cmp16": {"acc": 1.0, "reasoning_bytes": 112.03, "flops_per_problem": 6802437980.16}, "count.count.cmp18": {"acc": 0.998, "reasoning_bytes": 121.49, "flops_per_problem": 7308546785.28}, "count.count.cmp20": {"acc": 0.992, "reasoning_bytes": 127.23, "flops_per_problem": 7650368962.56}, "add.count.cmp6": {"acc": 0.998, "reasoning_bytes": 131.354, "flops_per_problem": 7346703679.488}, "add.count.cmp7": {"acc": 0.976, "reasoning_bytes": 147.968, "flops_per_problem": 8168755101.696}, "add.count.cmp8": {"acc": 0.83, "reasoning_bytes": 156.522, "flops_per_problem": 8634852163.584}, "sumd.count.cmp6": {"acc": 1.0, "reasoning_bytes": 82.492, "flops_per_problem": 4923829223.424}, "sumd.count.cmp7": {"acc": 0.982, "reasoning_bytes": 89.486, "flops_per_problem": 5276868820.992}, "sumd.count.cmp8": {"acc": 0.95, "reasoning_bytes": 90.708, "flops_per_problem": 5374999166.976}, "add.count.runmax6": {"acc": 0.994, "reasoning_bytes": 132.648, "flops_per_problem": 7448013766.656}, "add.count.runmax7": {"acc": 0.96, "reasoning_bytes": 149.072, "flops_per_problem": 8261674205.184}, "add.count.runmax8": {"acc": 0.332, "reasoning_bytes": 161.788, "flops_per_problem": 8911577972.736}, "sumd.count.runmax6": {"acc": 1.0, "reasoning_bytes": 83.428, "flops_per_problem": 5009328930.816}, "sumd.count.runmax7": {"acc": 0.992, "reasoning_bytes": 91.46, "flops_per_problem": 5408209797.12}, "sumd.count.runmax8": {"acc": 0.604, "reasoning_bytes": 95.104, "flops_per_problem": 5613303103.488}, "inc.count.runmax6": {"acc": 0.984, "reasoning_bytes": 116.0, "flops_per_problem": 6403645440.0}, "inc.count.runmax7": {"acc": 0.884, "reasoning_bytes": 130.97, "flops_per_problem": 7108929699.84}, "inc.count.runmax8": {"acc": 0.804, "reasoning_bytes": 131.0, "flops_per_problem": 7154417664.0}, "parity.count.count16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7596048384.0}, "parity.count.count20": {"acc": 1.0, "reasoning_bytes": 147.0, "flops_per_problem": 8567635968.0}, "parity.count.count24": {"acc": 1.0, "reasoning_bytes": 168.084, "flops_per_problem": 9675422466.048}, "runmax.count.count12": {"acc": 1.0, "reasoning_bytes": 104.964, "flops_per_problem": 6357892497.408}, "runmax.count.count14": {"acc": 1.0, "reasoning_bytes": 111.756, "flops_per_problem": 6746174226.432}, "runmax.count.count16": {"acc": 1.0, "reasoning_bytes": 122.988, "flops_per_problem": 7330539995.136}, "inc.count.count6": {"acc": 1.0, "reasoning_bytes": 116.0, "flops_per_problem": 6447808512.0}, "inc.count.count7": {"acc": 0.996, "reasoning_bytes": 130.76, "flops_per_problem": 7143818526.72}, "inc.count.count8": {"acc": 0.964, "reasoning_bytes": 130.99, "flops_per_problem": 7198139105.28}, "inc.count.find6": {"acc": 0.998, "reasoning_bytes": 116.0, "flops_per_problem": 6403645440.0}, "inc.count.find7": {"acc": 0.972, "reasoning_bytes": 130.548, "flops_per_problem": 7090292883.456}, "inc.count.find8": {"acc": 0.924, "reasoning_bytes": 126.814, "flops_per_problem": 6969551044.608}, "add.count.find6": {"acc": 1.0, "reasoning_bytes": 132.326, "flops_per_problem": 7433793257.472}, "add.count.find7": {"acc": 0.978, "reasoning_bytes": 149.158, "flops_per_problem": 8265472229.376}, "add.count.find8": {"acc": 0.818, "reasoning_bytes": 161.912, "flops_per_problem": 8917054193.664}, "runmax.count.find12": {"acc": 1.0, "reasoning_bytes": 104.988, "flops_per_problem": 6314789339.136}, "runmax.count.find14": {"acc": 1.0, "reasoning_bytes": 111.564, "flops_per_problem": 6693531844.608}, "runmax.count.find16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 7286906880.0}, "parity.count.rev16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7198580736.0}, "parity.count.rev20": {"acc": 1.0, "reasoning_bytes": 142.288, "flops_per_problem": 8182887284.736}, "parity.count.rev24": {"acc": 1.0, "reasoning_bytes": 164.848, "flops_per_problem": 9355858477.056}, "inc.count.rev6": {"acc": 0.99, "reasoning_bytes": 111.0, "flops_per_problem": 6050340864.0}, "inc.count.rev7": {"acc": 0.938, "reasoning_bytes": 125.968, "flops_per_problem": 6755536797.696}, "inc.count.rev8": {"acc": 0.78, "reasoning_bytes": 126.0, "flops_per_problem": 6801113088.0}, "runmax.count.rev12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5962014720.0}, "runmax.count.rev14": {"acc": 1.0, "reasoning_bytes": 107.788, "flops_per_problem": 6394282868.736}, "runmax.count.rev16": {"acc": 1.0, "reasoning_bytes": 118.0, "flops_per_problem": 6933602304.0}, "count.count.sumd16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6712786944.0}, "count.count.sumd18": {"acc": 1.0, "reasoning_bytes": 120.53, "flops_per_problem": 7221987164.16}, "count.count.sumd20": {"acc": 0.996, "reasoning_bytes": 126.396, "flops_per_problem": 7565310885.888}, "runmax.count.sumd12": {"acc": 1.0, "reasoning_bytes": 103.0, "flops_per_problem": 6138667008.0}, "runmax.count.sumd14": {"acc": 1.0, "reasoning_bytes": 111.892, "flops_per_problem": 6619691188.224}, "runmax.count.sumd16": {"acc": 1.0, "reasoning_bytes": 121.008, "flops_per_problem": 7110607896.576}, "sumd.count.sumd6": {"acc": 1.0, "reasoning_bytes": 81.428, "flops_per_problem": 4832676642.816}, "sumd.count.sumd7": {"acc": 0.994, "reasoning_bytes": 89.46, "flops_per_problem": 5231557509.12}, "sumd.count.sumd8": {"acc": 0.652, "reasoning_bytes": 93.498, "flops_per_problem": 5454051065.856}, "parity.count.inc16": {"acc": 1.0, "reasoning_bytes": 128.0, "flops_per_problem": 7375233024.0}, "parity.count.inc20": {"acc": 1.0, "reasoning_bytes": 146.24, "flops_per_problem": 8357419745.28}, "parity.count.inc24": {"acc": 1.0, "reasoning_bytes": 169.052, "flops_per_problem": 9541520031.744}, "count.count.inc16": {"acc": 1.0, "reasoning_bytes": 112.02, "flops_per_problem": 6713670205.44}, "count.count.inc18": {"acc": 1.0, "reasoning_bytes": 121.33, "flops_per_problem": 7213154549.76}, "count.count.inc20": {"acc": 0.994, "reasoning_bytes": 127.278, "flops_per_problem": 7562926080.0}, "add.count.inc6": {"acc": 0.992, "reasoning_bytes": 131.648, "flops_per_problem": 7271361478.656}, "add.count.inc7": {"acc": 0.95, "reasoning_bytes": 148.046, "flops_per_problem": 8083873677.312}, "add.count.inc8": {"acc": 0.362, "reasoning_bytes": 160.514, "flops_per_problem": 8722825003.008}, "parity.rev.cmp16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 7066091520.0}, "parity.rev.cmp20": {"acc": 0.932, "reasoning_bytes": 141.156, "flops_per_problem": 8044568543.232}, "parity.rev.cmp24": {"acc": 0.924, "reasoning_bytes": 162.72, "flops_per_problem": 9173553315.84}, "sumd.rev.cmp6": {"acc": 0.992, "reasoning_bytes": 81.052, "flops_per_problem": 4727568531.456}, "sumd.rev.cmp7": {"acc": 0.988, "reasoning_bytes": 88.89, "flops_per_problem": 5118058414.08}, "sumd.rev.cmp8": {"acc": 0.69, "reasoning_bytes": 89.808, "flops_per_problem": 5202674860.032}, "add.rev.cmp6": {"acc": 0.996, "reasoning_bytes": 157.268, "flops_per_problem": 8563661291.52}, "add.rev.cmp7": {"acc": 0.984, "reasoning_bytes": 181.576, "flops_per_problem": 9766928351.232}, "add.rev.cmp8": {"acc": 0.796, "reasoning_bytes": 198.26, "flops_per_problem": 10637647478.784}, "runmax.rev.runmax12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5917851648.0}, "runmax.rev.runmax14": {"acc": 0.986, "reasoning_bytes": 110.056, "flops_per_problem": 6450281644.032}, "runmax.rev.runmax16": {"acc": 0.976, "reasoning_bytes": 118.0, "flops_per_problem": 6889439232.0}, "count.rev.runmax16": {"acc": 0.986, "reasoning_bytes": 108.01, "flops_per_problem": 6492413214.72}, "count.rev.runmax18": {"acc": 0.956, "reasoning_bytes": 117.52, "flops_per_problem": 7000730173.44}, "count.rev.runmax20": {"acc": 0.784, "reasoning_bytes": 123.32, "flops_per_problem": 7345202135.04}, "add.rev.runmax6": {"acc": 1.0, "reasoning_bytes": 185.034, "flops_per_problem": 9584888168.448}, "add.rev.runmax7": {"acc": 0.98, "reasoning_bytes": 215.232, "flops_per_problem": 11006850760.704}, "add.rev.runmax8": {"acc": 0.494, "reasoning_bytes": 233.702, "flops_per_problem": 11910427213.824}, "inc.rev.count6": {"acc": 0.97, "reasoning_bytes": 156.0, "flops_per_problem": 8037679104.0}, "inc.rev.count7": {"acc": 0.844, "reasoning_bytes": 182.744, "flops_per_problem": 9262939373.568}, "inc.rev.count8": {"acc": 0.716, "reasoning_bytes": 182.974, "flops_per_problem": 9317259952.128}, "count.rev.count16": {"acc": 1.0, "reasoning_bytes": 108.01, "flops_per_problem": 6536576286.72}, "count.rev.count18": {"acc": 1.0, "reasoning_bytes": 117.57, "flops_per_problem": 7047101399.04}, "count.rev.count20": {"acc": 0.998, "reasoning_bytes": 123.342, "flops_per_problem": 7386273792.0}, "parity.rev.count16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7198580736.0}, "parity.rev.count20": {"acc": 1.0, "reasoning_bytes": 142.528, "flops_per_problem": 8193486422.016}, "parity.rev.count24": {"acc": 1.0, "reasoning_bytes": 165.412, "flops_per_problem": 9380766449.664}, "sumd.rev.find6": {"acc": 1.0, "reasoning_bytes": 85.208, "flops_per_problem": 4911286910.976}, "sumd.rev.find7": {"acc": 0.994, "reasoning_bytes": 93.428, "flops_per_problem": 5318470434.816}, "sumd.rev.find8": {"acc": 0.762, "reasoning_bytes": 95.402, "flops_per_problem": 5449811410.944}, "runmax.rev.find12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5917851648.0}, "runmax.rev.find14": {"acc": 0.994, "reasoning_bytes": 107.836, "flops_per_problem": 6352239624.192}, "runmax.rev.find16": {"acc": 0.984, "reasoning_bytes": 118.0, "flops_per_problem": 6889439232.0}, "count.rev.find16": {"acc": 1.0, "reasoning_bytes": 108.11, "flops_per_problem": 6496829521.92}, "count.rev.find18": {"acc": 0.976, "reasoning_bytes": 117.44, "flops_per_problem": 6997197127.68}, "count.rev.find20": {"acc": 0.938, "reasoning_bytes": 123.42, "flops_per_problem": 7348646854.656}, "count.rev.rev16": {"acc": 0.986, "reasoning_bytes": 103.01, "flops_per_problem": 6139108638.72}, "count.rev.rev18": {"acc": 0.91, "reasoning_bytes": 111.53, "flops_per_problem": 6603704156.16}, "count.rev.rev20": {"acc": 0.774, "reasoning_bytes": 118.026, "flops_per_problem": 6977235419.136}, "sumd.rev.rev6": {"acc": 0.998, "reasoning_bytes": 80.53, "flops_per_problem": 4616277590.016}, "sumd.rev.rev7": {"acc": 0.992, "reasoning_bytes": 88.448, "flops_per_problem": 5010212192.256}, "sumd.rev.rev8": {"acc": 0.3, "reasoning_bytes": 90.504, "flops_per_problem": 5145086214.144}, "parity.rev.rev16": {"acc": 1.0, "reasoning_bytes": 119.0, "flops_per_problem": 6801113088.0}, "parity.rev.rev20": {"acc": 0.498, "reasoning_bytes": 137.792, "flops_per_problem": 7807677825.024}, "parity.rev.rev24": {"acc": 0.438, "reasoning_bytes": 160.724, "flops_per_problem": 8997077680.128}, "sumd.rev.sumd6": {"acc": 1.0, "reasoning_bytes": 84.73, "flops_per_problem": 4810771759.104}, "sumd.rev.sumd7": {"acc": 0.992, "reasoning_bytes": 92.724, "flops_per_problem": 5210535886.848}, "sumd.rev.sumd8": {"acc": 0.528, "reasoning_bytes": 96.41, "flops_per_problem": 5417395716.096}, "parity.rev.sumd16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.rev.sumd20": {"acc": 0.512, "reasoning_bytes": 140.912, "flops_per_problem": 7989629681.664}, "parity.rev.sumd24": {"acc": 0.49, "reasoning_bytes": 163.784, "flops_per_problem": 9176379752.448}, "add.rev.sumd6": {"acc": 0.978, "reasoning_bytes": 191.614, "flops_per_problem": 9831141457.92}, "add.rev.sumd7": {"acc": 0.636, "reasoning_bytes": 222.794, "flops_per_problem": 11297797079.04}, "add.rev.sumd8": {"acc": 0.038, "reasoning_bytes": 242.76, "flops_per_problem": 12268413075.456}, "parity.rev.inc16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 6977765376.0}, "parity.rev.inc20": {"acc": 0.546, "reasoning_bytes": 142.284, "flops_per_problem": 8006058344.448}, "parity.rev.inc24": {"acc": 0.45, "reasoning_bytes": 164.82, "flops_per_problem": 9177969623.04}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 99.0, "flops_per_problem": 5772378488.832}, "runmax.rev.inc14": {"acc": 0.978, "reasoning_bytes": 107.448, "flops_per_problem": 6236620701.696}, "runmax.rev.inc16": {"acc": 0.948, "reasoning_bytes": 117.0, "flops_per_problem": 6747764097.024}, "inc.rev.inc6": {"acc": 0.98, "reasoning_bytes": 170.0, "flops_per_problem": 8695355572.224}, "inc.rev.inc7": {"acc": 0.75, "reasoning_bytes": 199.974, "flops_per_problem": 10107778940.928}, "inc.rev.inc8": {"acc": 0.018, "reasoning_bytes": 199.9, "flops_per_problem": 10149468880.896}, "parity.sumd.cmp16": {"acc": 1.0, "reasoning_bytes": 126.0, "flops_per_problem": 7242743808.0}, "parity.sumd.cmp20": {"acc": 0.934, "reasoning_bytes": 144.06, "flops_per_problem": 8216981176.32}, "parity.sumd.cmp24": {"acc": 0.928, "reasoning_bytes": 165.12, "flops_per_problem": 9323707760.64}, "runmax.sumd.cmp12": {"acc": 1.0, "reasoning_bytes": 102.0, "flops_per_problem": 6006177792.0}, "runmax.sumd.cmp14": {"acc": 0.992, "reasoning_bytes": 110.652, "flops_per_problem": 6476602834.944}, "runmax.sumd.cmp16": {"acc": 0.974, "reasoning_bytes": 120.0, "flops_per_problem": 6977765376.0}, "count.sumd.cmp16": {"acc": 0.998, "reasoning_bytes": 110.04, "flops_per_problem": 6582064250.88}, "count.sumd.cmp18": {"acc": 0.964, "reasoning_bytes": 118.36, "flops_per_problem": 7037827153.92}, "count.sumd.cmp20": {"acc": 0.918, "reasoning_bytes": 125.066, "flops_per_problem": 7421427597.312}, "sumd.sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 84.36, "flops_per_problem": 4917999697.92}, "sumd.sumd.runmax7": {"acc": 0.994, "reasoning_bytes": 92.82, "flops_per_problem": 5335782359.04}, "sumd.sumd.runmax8": {"acc": 0.696, "reasoning_bytes": 98.11, "flops_per_problem": 5613568081.92}, "count.sumd.runmax16": {"acc": 0.984, "reasoning_bytes": 111.02, "flops_per_problem": 6669507133.44}, "count.sumd.runmax18": {"acc": 0.944, "reasoning_bytes": 120.39, "flops_per_problem": 7171641262.08}, "count.sumd.runmax20": {"acc": 0.786, "reasoning_bytes": 126.28, "flops_per_problem": 7520087900.16}, "add.sumd.runmax6": {"acc": 0.982, "reasoning_bytes": 151.428, "flops_per_problem": 8144907042.816}, "add.sumd.runmax7": {"acc": 0.886, "reasoning_bytes": 170.964, "flops_per_problem": 9096002961.408}, "add.sumd.runmax8": {"acc": 0.164, "reasoning_bytes": 186.024, "flops_per_problem": 9849601622.016}, "parity.sumd.count16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7375233024.0}, "parity.sumd.count20": {"acc": 1.0, "reasoning_bytes": 145.24, "flops_per_problem": 8357419745.28}, "parity.sumd.count24": {"acc": 1.0, "reasoning_bytes": 167.992, "flops_per_problem": 9538870247.424}, "sumd.sumd.count6": {"acc": 1.0, "reasoning_bytes": 84.184, "flops_per_problem": 4954390069.248}, "sumd.sumd.count7": {"acc": 0.998, "reasoning_bytes": 92.444, "flops_per_problem": 5363340115.968}, "sumd.sumd.count8": {"acc": 0.754, "reasoning_bytes": 96.658, "flops_per_problem": 5593606373.376}, "add.sumd.count6": {"acc": 0.994, "reasoning_bytes": 150.5, "flops_per_problem": 8148086784.0}, "add.sumd.count7": {"acc": 0.934, "reasoning_bytes": 169.668, "flops_per_problem": 9082930692.096}, "add.sumd.count8": {"acc": 0.536, "reasoning_bytes": 185.382, "flops_per_problem": 9865500327.936}, "runmax.sumd.find12": {"acc": 1.0, "reasoning_bytes": 103.0, "flops_per_problem": 6094503936.0}, "runmax.sumd.find14": {"acc": 0.994, "reasoning_bytes": 111.508, "flops_per_problem": 6558569496.576}, "runmax.sumd.find16": {"acc": 0.992, "reasoning_bytes": 121.0, "flops_per_problem": 7066091520.0}, "sumd.sumd.find6": {"acc": 1.0, "reasoning_bytes": 84.064, "flops_per_problem": 4904927428.608}, "sumd.sumd.find7": {"acc": 0.998, "reasoning_bytes": 92.352, "flops_per_problem": 5315114041.344}, "sumd.sumd.find8": {"acc": 0.854, "reasoning_bytes": 95.7, "flops_per_problem": 5507135078.4}, "parity.sumd.find16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.sumd.find20": {"acc": 0.87, "reasoning_bytes": 145.156, "flops_per_problem": 8309546975.232}, "parity.sumd.find24": {"acc": 0.872, "reasoning_bytes": 167.02, "flops_per_problem": 9451780669.44}, "count.sumd.rev16": {"acc": 0.992, "reasoning_bytes": 106.01, "flops_per_problem": 6315760926.72}, "count.sumd.rev18": {"acc": 0.908, "reasoning_bytes": 114.32, "flops_per_problem": 6771082199.04}, "count.sumd.rev20": {"acc": 0.768, "reasoning_bytes": 121.042, "flops_per_problem": 7154859294.72}, "parity.sumd.rev16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.sumd.rev20": {"acc": 0.486, "reasoning_bytes": 140.696, "flops_per_problem": 7980090458.112}, "parity.sumd.rev24": {"acc": 0.468, "reasoning_bytes": 163.688, "flops_per_problem": 9172140097.536}, "add.sumd.rev6": {"acc": 0.994, "reasoning_bytes": 145.416, "flops_per_problem": 7790895857.664}, "add.sumd.rev7": {"acc": 0.896, "reasoning_bytes": 164.68, "flops_per_problem": 8729979420.672}, "add.sumd.rev8": {"acc": 0.028, "reasoning_bytes": 177.954, "flops_per_problem": 9404702834.688}, "parity.sumd.sumd16": {"acc": 1.0, "reasoning_bytes": 125.0, "flops_per_problem": 7154417664.0}, "parity.sumd.sumd20": {"acc": 0.47, "reasoning_bytes": 143.492, "flops_per_problem": 8147733479.424}, "parity.sumd.sumd24": {"acc": 0.55, "reasoning_bytes": 166.544, "flops_per_problem": 9342432903.168}, "add.sumd.sumd6": {"acc": 0.996, "reasoning_bytes": 149.626, "flops_per_problem": 7985743331.328}, "add.sumd.sumd7": {"acc": 0.922, "reasoning_bytes": 169.282, "flops_per_problem": 8943993667.584}, "add.sumd.sumd8": {"acc": 0.082, "reasoning_bytes": 184.09, "flops_per_problem": 9687699800.064}, "count.sumd.sumd16": {"acc": 0.99, "reasoning_bytes": 109.01, "flops_per_problem": 6492413214.72}, "count.sumd.sumd18": {"acc": 0.92, "reasoning_bytes": 117.64, "flops_per_problem": 6961866670.08}, "count.sumd.sumd20": {"acc": 0.778, "reasoning_bytes": 124.122, "flops_per_problem": 7334691323.904}, "inc.sumd.inc6": {"acc": 1.0, "reasoning_bytes": 135.538, "flops_per_problem": 7045688180.736}, "inc.sumd.inc7": {"acc": 0.862, "reasoning_bytes": 153.386, "flops_per_problem": 7878073761.792}, "inc.sumd.inc8": {"acc": 0.112, "reasoning_bytes": 153.624, "flops_per_problem": 7932747644.928}, "sumd.sumd.inc6": {"acc": 1.0, "reasoning_bytes": 83.764, "flops_per_problem": 4773586452.48}, "sumd.sumd.inc7": {"acc": 0.992, "reasoning_bytes": 92.324, "flops_per_problem": 5198523531.264}, "sumd.sumd.inc8": {"acc": 0.618, "reasoning_bytes": 96.83, "flops_per_problem": 5442215362.56}, "parity.sumd.inc16": {"acc": 1.0, "reasoning_bytes": 126.0, "flops_per_problem": 7154417664.0}, "parity.sumd.inc20": {"acc": 0.512, "reasoning_bytes": 144.864, "flops_per_problem": 8164162142.208}, "parity.sumd.inc24": {"acc": 0.476, "reasoning_bytes": 167.76, "flops_per_problem": 9351972126.72}, "inc.inc.cmp6": {"acc": 0.99, "reasoning_bytes": 144.578, "flops_per_problem": 7665737711.616}, "inc.inc.cmp7": {"acc": 0.982, "reasoning_bytes": 165.642, "flops_per_problem": 8684314804.224}, "inc.inc.cmp8": {"acc": 0.926, "reasoning_bytes": 178.71, "flops_per_problem": 9350823886.848}, "runmax.inc.cmp12": {"acc": 1.0, "reasoning_bytes": 105.556, "flops_per_problem": 6150326059.008}, "runmax.inc.cmp14": {"acc": 0.976, "reasoning_bytes": 115.306, "flops_per_problem": 6673305157.632}, "runmax.inc.cmp16": {"acc": 0.932, "reasoning_bytes": 123.62, "flops_per_problem": 7130039648.256}, "sumd.inc.cmp6": {"acc": 1.0, "reasoning_bytes": 88.12, "flops_per_problem": 5039713124.352}, "sumd.inc.cmp7": {"acc": 1.0, "reasoning_bytes": 96.004, "flops_per_problem": 5432234508.288}, "sumd.inc.cmp8": {"acc": 0.954, "reasoning_bytes": 97.756, "flops_per_problem": 5553771282.432}, "sumd.inc.runmax6": {"acc": 1.0, "reasoning_bytes": 93.522, "flops_per_problem": 5278458691.584}, "sumd.inc.runmax7": {"acc": 0.996, "reasoning_bytes": 101.48, "flops_per_problem": 5674071490.56}, "sumd.inc.runmax8": {"acc": 0.576, "reasoning_bytes": 105.478, "flops_per_problem": 5894798524.416}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.648, "flops_per_problem": 6343936966.656}, "runmax.inc.runmax14": {"acc": 0.982, "reasoning_bytes": 119.588, "flops_per_problem": 6871244046.336}, "runmax.inc.runmax16": {"acc": 0.964, "reasoning_bytes": 128.476, "flops_per_problem": 7352091574.272}, "add.inc.runmax6": {"acc": 1.0, "reasoning_bytes": 192.872, "flops_per_problem": 9931038326.784}, "add.inc.runmax7": {"acc": 0.984, "reasoning_bytes": 220.548, "flops_per_problem": 11241621651.456}, "add.inc.runmax8": {"acc": 0.486, "reasoning_bytes": 229.626, "flops_per_problem": 11738809516.032}, "runmax.inc.count12": {"acc": 1.0, "reasoning_bytes": 108.928, "flops_per_problem": 6356302626.816}, "runmax.inc.count14": {"acc": 1.0, "reasoning_bytes": 117.042, "flops_per_problem": 6802967937.024}, "runmax.inc.count16": {"acc": 1.0, "reasoning_bytes": 127.516, "flops_per_problem": 7353858097.152}, "sumd.inc.count6": {"acc": 1.0, "reasoning_bytes": 92.388, "flops_per_problem": 5272540839.936}, "sumd.inc.count7": {"acc": 0.994, "reasoning_bytes": 100.412, "flops_per_problem": 5671068401.664}, "sumd.inc.count8": {"acc": 0.61, "reasoning_bytes": 103.284, "flops_per_problem": 5842067816.448}, "inc.inc.count6": {"acc": 0.976, "reasoning_bytes": 164.98, "flops_per_problem": 8434263490.56}, "inc.inc.count7": {"acc": 0.872, "reasoning_bytes": 189.778, "flops_per_problem": 9573582422.016}, "inc.inc.count8": {"acc": 0.726, "reasoning_bytes": 189.67, "flops_per_problem": 9612975882.24}, "parity.inc.find16": {"acc": 1.0, "reasoning_bytes": 128.0, "flops_per_problem": 7331069952.0}, "parity.inc.find20": {"acc": 0.896, "reasoning_bytes": 146.468, "flops_per_problem": 8323325853.696}, "parity.inc.find24": {"acc": 0.856, "reasoning_bytes": 169.256, "flops_per_problem": 9506366226.432}, "sumd.inc.find6": {"acc": 1.0, "reasoning_bytes": 92.1, "flops_per_problem": 5215658803.2}, "sumd.inc.find7": {"acc": 0.998, "reasoning_bytes": 100.372, "flops_per_problem": 5625138806.784}, "sumd.inc.find8": {"acc": 0.794, "reasoning_bytes": 102.96, "flops_per_problem": 5783595909.12}, "count.inc.find16": {"acc": 0.984, "reasoning_bytes": 112.14, "flops_per_problem": 6674806702.08}, "count.inc.find18": {"acc": 0.952, "reasoning_bytes": 121.42, "flops_per_problem": 7172966154.24}, "count.inc.find20": {"acc": 0.912, "reasoning_bytes": 127.544, "flops_per_problem": 7530775363.584}, "sumd.inc.rev6": {"acc": 1.0, "reasoning_bytes": 87.524, "flops_per_problem": 4925154115.584}, "sumd.inc.rev7": {"acc": 0.992, "reasoning_bytes": 95.448, "flops_per_problem": 5319353696.256}, "sumd.inc.rev8": {"acc": 0.408, "reasoning_bytes": 98.308, "flops_per_problem": 5489734828.032}, "count.inc.rev16": {"acc": 0.986, "reasoning_bytes": 107.03, "flops_per_problem": 6316644188.16}, "count.inc.rev18": {"acc": 0.92, "reasoning_bytes": 115.74, "flops_per_problem": 6789630689.28}, "count.inc.rev20": {"acc": 0.774, "reasoning_bytes": 122.184, "flops_per_problem": 7161572081.664}, "parity.inc.rev16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 6977765376.0}, "parity.inc.rev20": {"acc": 0.544, "reasoning_bytes": 142.212, "flops_per_problem": 8002878603.264}, "parity.inc.rev24": {"acc": 0.46, "reasoning_bytes": 164.796, "flops_per_problem": 9176909709.312}, "count.inc.sumd16": {"acc": 0.988, "reasoning_bytes": 110.02, "flops_per_problem": 6492854845.44}, "count.inc.sumd18": {"acc": 0.93, "reasoning_bytes": 118.89, "flops_per_problem": 6972907438.08}, "count.inc.sumd20": {"acc": 0.77, "reasoning_bytes": 125.218, "flops_per_problem": 7340344197.12}, "sumd.inc.sumd6": {"acc": 1.0, "reasoning_bytes": 91.758, "flops_per_problem": 5122651373.568}, "sumd.inc.sumd7": {"acc": 0.992, "reasoning_bytes": 99.742, "flops_per_problem": 5521267261.44}, "sumd.inc.sumd8": {"acc": 0.614, "reasoning_bytes": 104.262, "flops_per_problem": 5767432224.768}, "add.inc.sumd6": {"acc": 0.946, "reasoning_bytes": 198.532, "flops_per_problem": 10136661590.016}, "add.inc.sumd7": {"acc": 0.464, "reasoning_bytes": 226.048, "flops_per_problem": 11443358564.352}, "add.inc.sumd8": {"acc": 0.026, "reasoning_bytes": 229.33, "flops_per_problem": 11706393821.184}, "parity.inc.inc16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7154417664.0}, "parity.inc.inc20": {"acc": 0.564, "reasoning_bytes": 146.344, "flops_per_problem": 8185360416.768}, "parity.inc.inc24": {"acc": 0.474, "reasoning_bytes": 168.892, "flops_per_problem": 9357801652.224}, "sumd.inc.inc6": {"acc": 1.0, "reasoning_bytes": 94.518, "flops_per_problem": 5234118967.296}, "sumd.inc.inc7": {"acc": 0.99, "reasoning_bytes": 102.448, "flops_per_problem": 5628495200.256}, "sumd.inc.inc8": {"acc": 0.49, "reasoning_bytes": 106.186, "flops_per_problem": 5837739835.392}, "runmax.inc.inc12": {"acc": 1.0, "reasoning_bytes": 110.06, "flops_per_problem": 6270272962.56}, "runmax.inc.inc14": {"acc": 0.964, "reasoning_bytes": 118.016, "flops_per_problem": 6710932094.976}, "runmax.inc.inc16": {"acc": 0.948, "reasoning_bytes": 128.94, "flops_per_problem": 7282402246.656}, "count.inc.cmp16": {"acc": 0.98, "reasoning_bytes": 111.06, "flops_per_problem": 6582947512.32}, "count.inc.cmp18": {"acc": 0.922, "reasoning_bytes": 119.62, "flops_per_problem": 7049486204.928}, "count.inc.cmp20": {"acc": 0.81, "reasoning_bytes": 126.282, "flops_per_problem": 7431231799.296}, "inc.rev.sumd6": {"acc": 0.928, "reasoning_bytes": 166.246, "flops_per_problem": 8401759469.568}, "inc.rev.sumd7": {"acc": 0.558, "reasoning_bytes": 196.048, "flops_per_problem": 9762070413.312}, "inc.rev.sumd8": {"acc": 0.07, "reasoning_bytes": 196.314, "flops_per_problem": 9817804210.176}, "runmax.inc.find12": {"acc": 0.888, "reasoning_bytes": 105.584, "flops_per_problem": 6164458242.048}, "runmax.inc.find14": {"acc": 0.906, "reasoning_bytes": 113.092, "flops_per_problem": 6584360730.624}, "runmax.inc.find16": {"acc": 0.862, "reasoning_bytes": 124.032, "flops_per_problem": 7155830882.304}, "inc.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 120.0, "flops_per_problem": 6491971584.0}, "inc.runmax.cmp7": {"acc": 0.976, "reasoning_bytes": 133.824, "flops_per_problem": 7146644963.328}, "inc.runmax.cmp8": {"acc": 0.972, "reasoning_bytes": 136.0, "flops_per_problem": 7286906880.0}} +{"step": 10000, "train_loss": 1.058058500289917} +{"step": 10020, "train_loss": 1.004255771636963} +{"step": 10040, "train_loss": 0.9409362077713013} +{"step": 10060, "train_loss": 1.054384469985962} +{"step": 10080, "train_loss": 1.069931983947754} +{"step": 10100, "train_loss": 1.1088109016418457} +{"step": 10120, "train_loss": 0.9420434832572937} +{"step": 10140, "train_loss": 0.9867880344390869} +{"step": 10160, "train_loss": 1.0778818130493164} +{"step": 10180, "train_loss": 0.9880311489105225} +{"step": 10200, "train_loss": 1.0927640199661255} +{"step": 10220, "train_loss": 1.0477099418640137} +{"step": 10240, "train_loss": 0.9870103597640991} +{"step": 10260, "train_loss": 0.958358883857727} +{"step": 10280, "train_loss": 0.9935083389282227} +{"step": 10300, "train_loss": 0.9924904108047485} +{"step": 10320, "train_loss": 0.970413327217102} +{"step": 10340, "train_loss": 1.0284323692321777} +{"step": 10360, "train_loss": 1.0717713832855225} +{"step": 10380, "train_loss": 1.0553034543991089} +{"step": 10400, "train_loss": 1.0210072994232178} +{"step": 10420, "train_loss": 0.9608924388885498} +{"step": 10440, "train_loss": 0.9771848320960999} +{"step": 10460, "train_loss": 1.0158495903015137} +{"step": 10480, "train_loss": 1.01317298412323} +{"step": 10500, "train_loss": 1.0394067764282227} +{"step": 10520, "train_loss": 0.9496654868125916} +{"step": 10540, "train_loss": 0.9778244495391846} +{"step": 10560, "train_loss": 1.0436592102050781} +{"step": 10580, "train_loss": 1.0700469017028809} +{"step": 10600, "train_loss": 1.054396390914917} +{"step": 10620, "train_loss": 0.9818910360336304} +{"step": 10640, "train_loss": 0.9654271006584167} +{"step": 10660, "train_loss": 1.024004578590393} +{"step": 10680, "train_loss": 0.9799771308898926} +{"step": 10700, "train_loss": 0.9218987226486206} +{"step": 10720, "train_loss": 0.8969451189041138} +{"step": 10740, "train_loss": 0.9920420050621033} +{"step": 10760, "train_loss": 1.0234994888305664} +{"step": 10780, "train_loss": 0.9602448344230652} +{"step": 10800, "train_loss": 0.9460084438323975} +{"step": 10820, "train_loss": 1.122286081314087} +{"step": 10840, "train_loss": 0.9640483856201172} +{"step": 10860, "train_loss": 0.942852258682251} +{"step": 10880, "train_loss": 0.9465664625167847} +{"step": 10900, "train_loss": 1.0025811195373535} +{"step": 10920, "train_loss": 1.0833278894424438} +{"step": 10940, "train_loss": 0.9845985174179077} +{"step": 10960, "train_loss": 1.0360603332519531} +{"step": 10980, "train_loss": 1.0430580377578735} +{"step": 11000, "tokens": 360448000, "val_loss": 1.815557163953781, "val_bpb": 0.6544788615998083, "lr": 7.345019833124972e-05, "elapsed": 3552.4178874492645, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.976, "reasoning_bytes": 79.0, "flops_per_problem": 4928775487.488}, "add9": {"acc": 0.434, "reasoning_bytes": 89.0, "flops_per_problem": 5503072075.776}, "add10": {"acc": 0.0, "reasoning_bytes": 98.732, "flops_per_problem": 6066592874.496}, "reach14": {"acc": 0.514, "reasoning_bytes": 8.452, "flops_per_problem": 4657084268.544}, "reach16": {"acc": 0.506, "reasoning_bytes": 9.04, "flops_per_problem": 5213009018.88}, "reach18": {"acc": 0.55, "reasoning_bytes": 9.776, "flops_per_problem": 5776618143.744}, "parity24": {"acc": 0.58, "reasoning_bytes": 142.988, "flops_per_problem": 7860496859.136}, "parity28": {"acc": 0.514, "reasoning_bytes": 166.904, "flops_per_problem": 9093353177.088}, "parity32": {"acc": 0.49, "reasoning_bytes": 189.096, "flops_per_problem": 10250072358.912}, "cmp8": {"acc": 0.992, "reasoning_bytes": 5.792, "flops_per_problem": 1359869313.024}, "cmp9": {"acc": 0.992, "reasoning_bytes": 5.72, "flops_per_problem": 1445015715.84}, "cmp10": {"acc": 0.978, "reasoning_bytes": 5.78, "flops_per_problem": 1535991644.16}, "runmax12": {"acc": 1.0, "reasoning_bytes": 71.0, "flops_per_problem": 4151328768.0}, "runmax14": {"acc": 1.0, "reasoning_bytes": 83.0, "flops_per_problem": 4769611776.0}, "runmax16": {"acc": 0.982, "reasoning_bytes": 91.604, "flops_per_problem": 5237916991.488}, "count16": {"acc": 0.994, "reasoning_bytes": 79.01, "flops_per_problem": 4725890334.72}, "count18": {"acc": 0.962, "reasoning_bytes": 88.98, "flops_per_problem": 5258850287.616}, "count20": {"acc": 0.79, "reasoning_bytes": 97.954, "flops_per_problem": 5749237039.104}, "brackets16": {"acc": 0.946, "reasoning_bytes": 53.76, "flops_per_problem": 3655024164.864}, "brackets18": {"acc": 0.924, "reasoning_bytes": 56.564, "flops_per_problem": 3867095236.608}, "brackets20": {"acc": 0.924, "reasoning_bytes": 61.688, "flops_per_problem": 4181801287.68}, "sumd8": {"acc": 0.972, "reasoning_bytes": 58.566, "flops_per_problem": 3381301444.608}, "sumd9": {"acc": 0.84, "reasoning_bytes": 66.394, "flops_per_problem": 3771261370.368}, "sumd10": {"acc": 0.49, "reasoning_bytes": 73.324, "flops_per_problem": 4123506032.64}, "inc8": {"acc": 0.986, "reasoning_bytes": 63.024, "flops_per_problem": 3798465822.72}, "inc9": {"acc": 0.53, "reasoning_bytes": 70.188, "flops_per_problem": 4184451072.0}, "inc10": {"acc": 0.0, "reasoning_bytes": 63.822, "flops_per_problem": 3656084078.592}, "add.cmp6": {"acc": 1.0, "reasoning_bytes": 92.622, "flops_per_problem": 5532043051.008}, "add.cmp7": {"acc": 0.998, "reasoning_bytes": 105.5, "flops_per_problem": 6230526197.76}, "add.cmp8": {"acc": 0.986, "reasoning_bytes": 118.466, "flops_per_problem": 6937135349.76}, "add.runmax6": {"acc": 1.0, "reasoning_bytes": 120.832, "flops_per_problem": 6572878331.904}, "add.runmax7": {"acc": 0.948, "reasoning_bytes": 138.848, "flops_per_problem": 7456846381.056}, "add.runmax8": {"acc": 0.578, "reasoning_bytes": 156.8, "flops_per_problem": 8337987993.6}, "add.count6": {"acc": 0.998, "reasoning_bytes": 115.648, "flops_per_problem": 6388100038.656}, "add.count7": {"acc": 0.934, "reasoning_bytes": 132.086, "flops_per_problem": 7202378760.192}, "add.count8": {"acc": 0.414, "reasoning_bytes": 148.942, "flops_per_problem": 8035117645.824}, "add.find6": {"acc": 0.87, "reasoning_bytes": 107.784, "flops_per_problem": 5997080199.168}, "add.find7": {"acc": 0.732, "reasoning_bytes": 122.17, "flops_per_problem": 6723121102.848}, "add.find8": {"acc": 0.466, "reasoning_bytes": 138.76, "flops_per_problem": 7542522740.736}, "add.rev6": {"acc": 1.0, "reasoning_bytes": 123.248, "flops_per_problem": 6794576953.344}, "add.rev7": {"acc": 0.748, "reasoning_bytes": 145.878, "flops_per_problem": 7926564814.848}, "add.rev8": {"acc": 0.002, "reasoning_bytes": 168.774, "flops_per_problem": 9064912158.72}, "add.sumd6": {"acc": 1.0, "reasoning_bytes": 126.476, "flops_per_problem": 6777794985.984}, "add.sumd7": {"acc": 0.888, "reasoning_bytes": 146.346, "flops_per_problem": 7743729696.768}, "add.sumd8": {"acc": 0.042, "reasoning_bytes": 166.13, "flops_per_problem": 8705513078.784}, "add.inc6": {"acc": 1.0, "reasoning_bytes": 131.04, "flops_per_problem": 7138695610.368}, "add.inc7": {"acc": 0.876, "reasoning_bytes": 151.06, "flops_per_problem": 8155417853.952}, "add.inc8": {"acc": 0.002, "reasoning_bytes": 170.188, "flops_per_problem": 9129213591.552}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5122916352.0}, "runmax.cmp14": {"acc": 0.998, "reasoning_bytes": 97.656, "flops_per_problem": 5681844191.232}, "runmax.cmp16": {"acc": 0.982, "reasoning_bytes": 105.0, "flops_per_problem": 6094503936.0}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.runmax14": {"acc": 1.0, "reasoning_bytes": 99.88, "flops_per_problem": 5824225935.36}, "runmax.runmax16": {"acc": 0.974, "reasoning_bytes": 106.012, "flops_per_problem": 6183360036.864}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5255405568.0}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 99.748, "flops_per_problem": 5862559481.856}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 106.012, "flops_per_problem": 6227523108.864}, "runmax.find12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.find14": {"acc": 1.0, "reasoning_bytes": 99.592, "flops_per_problem": 5811506970.624}, "runmax.find16": {"acc": 0.988, "reasoning_bytes": 106.036, "flops_per_problem": 6184419950.592}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 83.0, "flops_per_problem": 4857937920.0}, "runmax.rev14": {"acc": 0.998, "reasoning_bytes": 94.784, "flops_per_problem": 5466681704.448}, "runmax.rev16": {"acc": 0.962, "reasoning_bytes": 101.048, "flops_per_problem": 5831645331.456}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 86.0, "flops_per_problem": 5034590208.0}, "runmax.sumd14": {"acc": 1.0, "reasoning_bytes": 97.772, "flops_per_problem": 5642804035.584}, "runmax.sumd16": {"acc": 0.97, "reasoning_bytes": 104.06, "flops_per_problem": 6008827576.32}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5065769336.832}, "runmax.inc14": {"acc": 0.998, "reasoning_bytes": 98.664, "flops_per_problem": 5672569946.112}, "runmax.inc16": {"acc": 0.964, "reasoning_bytes": 105.0, "flops_per_problem": 6041861554.176}, "count.cmp16": {"acc": 0.994, "reasoning_bytes": 95.0, "flops_per_problem": 5697036288.0}, "count.cmp18": {"acc": 0.952, "reasoning_bytes": 104.31, "flops_per_problem": 6196608958.464}, "count.cmp20": {"acc": 0.852, "reasoning_bytes": 110.37, "flops_per_problem": 6552651644.928}, "count.runmax16": {"acc": 0.996, "reasoning_bytes": 96.01, "flops_per_problem": 5785804062.72}, "count.runmax18": {"acc": 0.974, "reasoning_bytes": 105.72, "flops_per_problem": 6302953635.84}, "count.runmax20": {"acc": 0.802, "reasoning_bytes": 111.646, "flops_per_problem": 6652990144.512}, "count.count16": {"acc": 1.0, "reasoning_bytes": 96.0, "flops_per_problem": 5829525504.0}, "count.count18": {"acc": 1.0, "reasoning_bytes": 105.9, "flops_per_problem": 6355066060.8}, "count.count20": {"acc": 0.996, "reasoning_bytes": 114.206, "flops_per_problem": 6810210680.832}, "count.find16": {"acc": 0.946, "reasoning_bytes": 96.0, "flops_per_problem": 5785362432.0}, "count.find18": {"acc": 0.836, "reasoning_bytes": 105.87, "flops_per_problem": 6309578096.64}, "count.find20": {"acc": 0.81, "reasoning_bytes": 112.074, "flops_per_problem": 6671891939.328}, "count.rev16": {"acc": 0.996, "reasoning_bytes": 91.01, "flops_per_problem": 5432499486.72}, "count.rev18": {"acc": 0.954, "reasoning_bytes": 100.26, "flops_per_problem": 5929334046.72}, "count.rev20": {"acc": 0.78, "reasoning_bytes": 106.628, "flops_per_problem": 6298890633.216}, "count.sumd16": {"acc": 0.996, "reasoning_bytes": 94.0, "flops_per_problem": 5608710144.0}, "count.sumd18": {"acc": 0.94, "reasoning_bytes": 103.362, "flops_per_problem": 6110490968.064}, "count.sumd20": {"acc": 0.69, "reasoning_bytes": 110.304, "flops_per_problem": 6504513896.448}, "count.inc16": {"acc": 0.996, "reasoning_bytes": 95.0, "flops_per_problem": 5608710144.0}, "count.inc18": {"acc": 0.96, "reasoning_bytes": 104.7, "flops_per_problem": 6125418086.4}, "count.inc20": {"acc": 0.776, "reasoning_bytes": 110.938, "flops_per_problem": 6489233473.536}, "parity.cmp16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6359482368.0}, "parity.cmp20": {"acc": 0.986, "reasoning_bytes": 133.104, "flops_per_problem": 7512315199.488}, "parity.cmp24": {"acc": 0.958, "reasoning_bytes": 153.0, "flops_per_problem": 8567635968.0}, "parity.runmax16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.runmax20": {"acc": 0.812, "reasoning_bytes": 134.824, "flops_per_problem": 7632438755.328}, "parity.runmax24": {"acc": 0.744, "reasoning_bytes": 154.408, "flops_per_problem": 8676277125.12}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6491971584.0}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 134.824, "flops_per_problem": 7676601827.328}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 154.144, "flops_per_problem": 8706484666.368}, "parity.find16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.find20": {"acc": 0.958, "reasoning_bytes": 135.436, "flops_per_problem": 7659466555.392}, "parity.find24": {"acc": 0.924, "reasoning_bytes": 154.628, "flops_per_problem": 8683696521.216}, "parity.rev16": {"acc": 1.0, "reasoning_bytes": 107.0, "flops_per_problem": 6094503936.0}, "parity.rev20": {"acc": 0.762, "reasoning_bytes": 130.316, "flops_per_problem": 7300862410.752}, "parity.rev24": {"acc": 0.674, "reasoning_bytes": 150.032, "flops_per_problem": 8348852109.312}, "parity.sumd16": {"acc": 1.0, "reasoning_bytes": 110.0, "flops_per_problem": 6271156224.0}, "parity.sumd20": {"acc": 0.786, "reasoning_bytes": 133.136, "flops_per_problem": 7469565345.792}, "parity.sumd24": {"acc": 0.702, "reasoning_bytes": 152.828, "flops_per_problem": 8515876847.616}, "parity.inc16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6271156224.0}, "parity.inc20": {"acc": 0.744, "reasoning_bytes": 134.712, "flops_per_problem": 7495003275.264}, "parity.inc24": {"acc": 0.6, "reasoning_bytes": 155.46, "flops_per_problem": 8587950981.12}, "sumd.cmp6": {"acc": 1.0, "reasoning_bytes": 62.088, "flops_per_problem": 3713407746.048}, "sumd.cmp7": {"acc": 1.0, "reasoning_bytes": 70.084, "flops_per_problem": 4110875394.048}, "sumd.cmp8": {"acc": 0.986, "reasoning_bytes": 77.264, "flops_per_problem": 4472040996.864}, "sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.994, "reasoning_bytes": 75.48, "flops_per_problem": 4349179330.56}, "sumd.runmax8": {"acc": 0.962, "reasoning_bytes": 83.504, "flops_per_problem": 4747706892.288}, "sumd.count6": {"acc": 1.0, "reasoning_bytes": 66.428, "flops_per_problem": 3949415202.816}, "sumd.count7": {"acc": 0.992, "reasoning_bytes": 74.46, "flops_per_problem": 4348296069.12}, "sumd.count8": {"acc": 0.96, "reasoning_bytes": 82.378, "flops_per_problem": 4742142345.216}, "sumd.find6": {"acc": 1.0, "reasoning_bytes": 66.24, "flops_per_problem": 3896949473.28}, "sumd.find7": {"acc": 0.996, "reasoning_bytes": 74.44, "flops_per_problem": 4303249735.68}, "sumd.find8": {"acc": 0.992, "reasoning_bytes": 82.174, "flops_per_problem": 4688970006.528}, "sumd.rev6": {"acc": 1.0, "reasoning_bytes": 61.544, "flops_per_problem": 3601145217.024}, "sumd.rev7": {"acc": 0.996, "reasoning_bytes": 69.48, "flops_per_problem": 3995874754.56}, "sumd.rev8": {"acc": 0.97, "reasoning_bytes": 77.52, "flops_per_problem": 4395020599.296}, "sumd.sumd6": {"acc": 1.0, "reasoning_bytes": 65.744, "flops_per_problem": 3795639386.112}, "sumd.sumd7": {"acc": 0.992, "reasoning_bytes": 73.71, "flops_per_problem": 4194078621.696}, "sumd.sumd8": {"acc": 0.96, "reasoning_bytes": 81.764, "flops_per_problem": 4595255967.744}, "sumd.inc6": {"acc": 1.0, "reasoning_bytes": 68.538, "flops_per_problem": 3910021742.592}, "sumd.inc7": {"acc": 0.996, "reasoning_bytes": 76.48, "flops_per_problem": 4305016258.56}, "sumd.inc8": {"acc": 0.96, "reasoning_bytes": 84.462, "flops_per_problem": 4701600645.12}, "inc.cmp6": {"acc": 1.0, "reasoning_bytes": 78.624, "flops_per_problem": 4576354172.928}, "inc.cmp7": {"acc": 1.0, "reasoning_bytes": 89.792, "flops_per_problem": 5157893505.024}, "inc.cmp8": {"acc": 0.966, "reasoning_bytes": 100.684, "flops_per_problem": 5727243829.248}, "inc.runmax6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5520384000.0}, "inc.runmax7": {"acc": 0.992, "reasoning_bytes": 120.0, "flops_per_problem": 6271156224.0}, "inc.runmax8": {"acc": 0.926, "reasoning_bytes": 135.32, "flops_per_problem": 6991897559.04}, "inc.count6": {"acc": 0.992, "reasoning_bytes": 99.0, "flops_per_problem": 5343731712.0}, "inc.count7": {"acc": 0.968, "reasoning_bytes": 114.0, "flops_per_problem": 6050340864.0}, "inc.count8": {"acc": 0.474, "reasoning_bytes": 113.53, "flops_per_problem": 6073747292.16}, "inc.find6": {"acc": 0.922, "reasoning_bytes": 91.88, "flops_per_problem": 4985127567.36}, "inc.find7": {"acc": 0.864, "reasoning_bytes": 102.6, "flops_per_problem": 5502718771.2}, "inc.find8": {"acc": 0.356, "reasoning_bytes": 95.98, "flops_per_problem": 5254522306.56}, "inc.rev6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5608710144.0}, "inc.rev7": {"acc": 0.976, "reasoning_bytes": 123.994, "flops_per_problem": 6579944423.424}, "inc.rev8": {"acc": 0.026, "reasoning_bytes": 144.114, "flops_per_problem": 7543229349.888}, "inc.sumd6": {"acc": 0.998, "reasoning_bytes": 109.558, "flops_per_problem": 5721590956.032}, "inc.sumd7": {"acc": 0.942, "reasoning_bytes": 127.484, "flops_per_problem": 6557421256.704}, "inc.sumd8": {"acc": 0.102, "reasoning_bytes": 144.426, "flops_per_problem": 7349795094.528}, "inc.inc6": {"acc": 1.0, "reasoning_bytes": 113.0, "flops_per_problem": 6006177792.0}, "inc.inc7": {"acc": 0.99, "reasoning_bytes": 130.98, "flops_per_problem": 6888290992.128}, "inc.inc8": {"acc": 0.236, "reasoning_bytes": 147.93, "flops_per_problem": 7720323268.608}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 115.592, "flops_per_problem": 6783094554.624}, "runmax.runmax.cmp16": {"acc": 0.994, "reasoning_bytes": 122.0, "flops_per_problem": 7154417664.0}, "sumd.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 83.338, "flops_per_problem": 4917028110.336}, "sumd.runmax.cmp7": {"acc": 0.996, "reasoning_bytes": 91.532, "flops_per_problem": 5323063394.304}, "sumd.runmax.cmp8": {"acc": 0.85, "reasoning_bytes": 96.614, "flops_per_problem": 5591663198.208}, "add.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 137.024, "flops_per_problem": 7552945225.728}, "add.runmax.cmp7": {"acc": 0.962, "reasoning_bytes": 154.912, "flops_per_problem": 8431260401.664}, "add.runmax.cmp8": {"acc": 0.904, "reasoning_bytes": 171.71, "flops_per_problem": 9261437829.12}, "count.runmax.runmax16": {"acc": 0.996, "reasoning_bytes": 113.01, "flops_per_problem": 6845717790.72}, "count.runmax.runmax18": {"acc": 0.984, "reasoning_bytes": 122.87, "flops_per_problem": 7369491824.64}, "count.runmax.runmax20": {"acc": 0.822, "reasoning_bytes": 128.73, "flops_per_problem": 7716613570.56}, "add.runmax.runmax6": {"acc": 1.0, "reasoning_bytes": 137.832, "flops_per_problem": 7632792059.904}, "add.runmax.runmax7": {"acc": 0.942, "reasoning_bytes": 155.848, "flops_per_problem": 8516760109.056}, "add.runmax.runmax8": {"acc": 0.598, "reasoning_bytes": 173.672, "flops_per_problem": 9392248848.384}, "parity.runmax.runmax16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7507722240.0}, "parity.runmax.runmax20": {"acc": 0.808, "reasoning_bytes": 148.464, "flops_per_problem": 8543964561.408}, "parity.runmax.runmax24": {"acc": 0.808, "reasoning_bytes": 171.0, "flops_per_problem": 9715875840.0}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7551885312.0}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 149.58, "flops_per_problem": 8637413621.76}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 171.0, "flops_per_problem": 9760038912.0}, "inc.runmax.count6": {"acc": 1.0, "reasoning_bytes": 121.0, "flops_per_problem": 6624460800.0}, "inc.runmax.count7": {"acc": 0.998, "reasoning_bytes": 137.0, "flops_per_problem": 7375233024.0}, "inc.runmax.count8": {"acc": 1.0, "reasoning_bytes": 150.136, "flops_per_problem": 7999522209.792}, "sumd.runmax.count6": {"acc": 1.0, "reasoning_bytes": 84.424, "flops_per_problem": 5053315350.528}, "sumd.runmax.count7": {"acc": 1.0, "reasoning_bytes": 92.46, "flops_per_problem": 5452372869.12}, "sumd.runmax.count8": {"acc": 0.968, "reasoning_bytes": 99.984, "flops_per_problem": 5828818894.848}, "runmax.runmax.find12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6271156224.0}, "runmax.runmax.find14": {"acc": 1.0, "reasoning_bytes": 116.76, "flops_per_problem": 6878840094.72}, "runmax.runmax.find16": {"acc": 0.988, "reasoning_bytes": 123.048, "flops_per_problem": 7244863635.456}, "add.runmax.find6": {"acc": 1.0, "reasoning_bytes": 137.928, "flops_per_problem": 7637031714.816}, "add.runmax.find7": {"acc": 0.99, "reasoning_bytes": 155.608, "flops_per_problem": 8506160971.776}, "add.runmax.find8": {"acc": 0.872, "reasoning_bytes": 173.304, "flops_per_problem": 9375996837.888}, "parity.runmax.find16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7507722240.0}, "parity.runmax.find20": {"acc": 0.956, "reasoning_bytes": 149.64, "flops_per_problem": 8595900334.08}, "parity.runmax.find24": {"acc": 0.934, "reasoning_bytes": 171.012, "flops_per_problem": 9716405796.864}, "add.runmax.rev6": {"acc": 1.0, "reasoning_bytes": 132.832, "flops_per_problem": 7279487483.904}, "add.runmax.rev7": {"acc": 0.968, "reasoning_bytes": 150.848, "flops_per_problem": 8163455533.056}, "add.runmax.rev8": {"acc": 0.58, "reasoning_bytes": 168.408, "flops_per_problem": 9027285221.376}, "parity.runmax.rev16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7154417664.0}, "parity.runmax.rev20": {"acc": 0.814, "reasoning_bytes": 144.34, "flops_per_problem": 8229346836.48}, "parity.runmax.rev24": {"acc": 0.758, "reasoning_bytes": 166.0, "flops_per_problem": 9362571264.0}, "sumd.runmax.rev6": {"acc": 1.0, "reasoning_bytes": 79.542, "flops_per_problem": 4661058945.024}, "sumd.runmax.rev7": {"acc": 0.994, "reasoning_bytes": 87.48, "flops_per_problem": 5055788482.56}, "sumd.runmax.rev8": {"acc": 0.918, "reasoning_bytes": 95.086, "flops_per_problem": 5435855880.192}, "sumd.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 82.542, "flops_per_problem": 4837711233.024}, "sumd.runmax.sumd7": {"acc": 0.992, "reasoning_bytes": 90.48, "flops_per_problem": 5232440770.56}, "sumd.runmax.sumd8": {"acc": 0.924, "reasoning_bytes": 98.326, "flops_per_problem": 5623107305.472}, "add.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 135.832, "flops_per_problem": 7456139771.904}, "add.runmax.sumd7": {"acc": 0.958, "reasoning_bytes": 153.848, "flops_per_problem": 8340107821.056}, "add.runmax.sumd8": {"acc": 0.614, "reasoning_bytes": 171.704, "flops_per_problem": 9217009778.688}, "parity.runmax.sumd16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.runmax.sumd20": {"acc": 0.81, "reasoning_bytes": 146.872, "flops_per_problem": 8385330806.784}, "parity.runmax.sumd24": {"acc": 0.79, "reasoning_bytes": 169.0, "flops_per_problem": 9539223552.0}, "count.runmax.inc16": {"acc": 0.998, "reasoning_bytes": 112.0, "flops_per_problem": 6668623872.0}, "count.runmax.inc18": {"acc": 0.978, "reasoning_bytes": 121.66, "flops_per_problem": 7183565291.52}, "count.runmax.inc20": {"acc": 0.792, "reasoning_bytes": 127.39, "flops_per_problem": 7524945838.08}, "runmax.runmax.inc12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6125683064.832}, "runmax.runmax.inc14": {"acc": 1.0, "reasoning_bytes": 115.784, "flops_per_problem": 6737783242.752}, "runmax.runmax.inc16": {"acc": 0.968, "reasoning_bytes": 122.0, "flops_per_problem": 7101951934.464}, "add.runmax.inc6": {"acc": 1.0, "reasoning_bytes": 136.832, "flops_per_problem": 7477161394.176}, "add.runmax.inc7": {"acc": 0.96, "reasoning_bytes": 154.848, "flops_per_problem": 8364132532.224}, "add.runmax.inc8": {"acc": 0.568, "reasoning_bytes": 172.608, "flops_per_problem": 9238031400.96}, "count.count.cmp16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6801113088.0}, "count.count.cmp18": {"acc": 0.99, "reasoning_bytes": 121.98, "flops_per_problem": 7330186690.56}, "count.count.cmp20": {"acc": 0.96, "reasoning_bytes": 128.442, "flops_per_problem": 7703894605.824}, "add.count.cmp6": {"acc": 0.996, "reasoning_bytes": 131.354, "flops_per_problem": 7346703679.488}, "add.count.cmp7": {"acc": 0.938, "reasoning_bytes": 148.196, "flops_per_problem": 8178824282.112}, "add.count.cmp8": {"acc": 0.852, "reasoning_bytes": 164.09, "flops_per_problem": 8969078292.48}, "sumd.count.cmp6": {"acc": 1.0, "reasoning_bytes": 82.492, "flops_per_problem": 4923829223.424}, "sumd.count.cmp7": {"acc": 1.0, "reasoning_bytes": 90.508, "flops_per_problem": 5322003480.576}, "sumd.count.cmp8": {"acc": 0.958, "reasoning_bytes": 93.168, "flops_per_problem": 5483640324.096}, "add.count.runmax6": {"acc": 0.998, "reasoning_bytes": 132.648, "flops_per_problem": 7448013766.656}, "add.count.runmax7": {"acc": 0.934, "reasoning_bytes": 149.086, "flops_per_problem": 8262292488.192}, "add.count.runmax8": {"acc": 0.456, "reasoning_bytes": 165.846, "flops_per_problem": 9090791718.912}, "sumd.count.runmax6": {"acc": 1.0, "reasoning_bytes": 83.428, "flops_per_problem": 5009328930.816}, "sumd.count.runmax7": {"acc": 0.988, "reasoning_bytes": 91.46, "flops_per_problem": 5408209797.12}, "sumd.count.runmax8": {"acc": 0.878, "reasoning_bytes": 98.734, "flops_per_problem": 5773615054.848}, "inc.count.runmax6": {"acc": 0.992, "reasoning_bytes": 116.0, "flops_per_problem": 6403645440.0}, "inc.count.runmax7": {"acc": 0.802, "reasoning_bytes": 130.972, "flops_per_problem": 7109018025.984}, "inc.count.runmax8": {"acc": 0.664, "reasoning_bytes": 138.596, "flops_per_problem": 7490145337.344}, "parity.count.count16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7596048384.0}, "parity.count.count20": {"acc": 1.0, "reasoning_bytes": 148.116, "flops_per_problem": 8616921956.352}, "parity.count.count24": {"acc": 1.0, "reasoning_bytes": 171.12, "flops_per_problem": 9809501552.64}, "runmax.count.count12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6359482368.0}, "runmax.count.count14": {"acc": 1.0, "reasoning_bytes": 116.928, "flops_per_problem": 6974585634.816}, "runmax.count.count16": {"acc": 1.0, "reasoning_bytes": 123.18, "flops_per_problem": 7339019304.96}, "inc.count.count6": {"acc": 1.0, "reasoning_bytes": 116.0, "flops_per_problem": 6447808512.0}, "inc.count.count7": {"acc": 0.994, "reasoning_bytes": 130.98, "flops_per_problem": 7153534402.56}, "inc.count.count8": {"acc": 0.982, "reasoning_bytes": 131.102, "flops_per_problem": 7203085369.344}, "inc.count.find6": {"acc": 1.0, "reasoning_bytes": 116.0, "flops_per_problem": 6403645440.0}, "inc.count.find7": {"acc": 0.946, "reasoning_bytes": 131.0, "flops_per_problem": 7110254592.0}, "inc.count.find8": {"acc": 0.888, "reasoning_bytes": 120.37, "flops_per_problem": 6684964208.64}, "add.count.find6": {"acc": 0.998, "reasoning_bytes": 132.326, "flops_per_problem": 7433793257.472}, "add.count.find7": {"acc": 0.976, "reasoning_bytes": 149.156, "flops_per_problem": 8265383903.232}, "add.count.find8": {"acc": 0.818, "reasoning_bytes": 165.554, "flops_per_problem": 9077896101.888}, "runmax.count.find12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6315319296.0}, "runmax.count.find14": {"acc": 1.0, "reasoning_bytes": 116.88, "flops_per_problem": 6928302735.36}, "runmax.count.find16": {"acc": 1.0, "reasoning_bytes": 123.084, "flops_per_problem": 7290616578.048}, "parity.count.rev16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7198580736.0}, "parity.count.rev20": {"acc": 1.0, "reasoning_bytes": 145.66, "flops_per_problem": 8331805163.52}, "parity.count.rev24": {"acc": 1.0, "reasoning_bytes": 166.004, "flops_per_problem": 9406910988.288}, "inc.count.rev6": {"acc": 0.994, "reasoning_bytes": 111.0, "flops_per_problem": 6050340864.0}, "inc.count.rev7": {"acc": 0.932, "reasoning_bytes": 125.998, "flops_per_problem": 6756861689.856}, "inc.count.rev8": {"acc": 0.7, "reasoning_bytes": 132.076, "flops_per_problem": 7069447913.472}, "runmax.count.rev12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5962014720.0}, "runmax.count.rev14": {"acc": 1.0, "reasoning_bytes": 111.964, "flops_per_problem": 6578707857.408}, "runmax.count.rev16": {"acc": 1.0, "reasoning_bytes": 118.084, "flops_per_problem": 6937312002.048}, "count.count.sumd16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6712786944.0}, "count.count.sumd18": {"acc": 1.0, "reasoning_bytes": 120.93, "flops_per_problem": 7239652392.96}, "count.count.sumd20": {"acc": 0.996, "reasoning_bytes": 127.29, "flops_per_problem": 7608855674.88}, "runmax.count.sumd12": {"acc": 1.0, "reasoning_bytes": 103.0, "flops_per_problem": 6138667008.0}, "runmax.count.sumd14": {"acc": 1.0, "reasoning_bytes": 114.868, "flops_per_problem": 6751120490.496}, "runmax.count.sumd16": {"acc": 1.0, "reasoning_bytes": 121.132, "flops_per_problem": 7116084117.504}, "sumd.count.sumd6": {"acc": 1.0, "reasoning_bytes": 81.428, "flops_per_problem": 4832676642.816}, "sumd.count.sumd7": {"acc": 0.988, "reasoning_bytes": 89.46, "flops_per_problem": 5231557509.12}, "sumd.count.sumd8": {"acc": 0.894, "reasoning_bytes": 96.928, "flops_per_problem": 5605530402.816}, "parity.count.inc16": {"acc": 1.0, "reasoning_bytes": 128.0, "flops_per_problem": 7375233024.0}, "parity.count.inc20": {"acc": 1.0, "reasoning_bytes": 149.264, "flops_per_problem": 8490968875.008}, "parity.count.inc24": {"acc": 0.982, "reasoning_bytes": 170.048, "flops_per_problem": 9585506451.456}, "count.count.inc16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6712786944.0}, "count.count.inc18": {"acc": 1.0, "reasoning_bytes": 121.92, "flops_per_problem": 7239210762.24}, "count.count.inc20": {"acc": 0.992, "reasoning_bytes": 128.238, "flops_per_problem": 7606559195.136}, "add.count.inc6": {"acc": 0.998, "reasoning_bytes": 131.648, "flops_per_problem": 7271361478.656}, "add.count.inc7": {"acc": 0.908, "reasoning_bytes": 148.096, "flops_per_problem": 8086081830.912}, "add.count.inc8": {"acc": 0.406, "reasoning_bytes": 164.644, "flops_per_problem": 8905218490.368}, "parity.rev.cmp16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 7066091520.0}, "parity.rev.cmp20": {"acc": 0.99, "reasoning_bytes": 142.236, "flops_per_problem": 8092264660.992}, "parity.rev.cmp24": {"acc": 0.972, "reasoning_bytes": 164.904, "flops_per_problem": 9270005465.088}, "sumd.rev.cmp6": {"acc": 1.0, "reasoning_bytes": 81.072, "flops_per_problem": 4728451792.896}, "sumd.rev.cmp7": {"acc": 0.998, "reasoning_bytes": 89.096, "flops_per_problem": 5127156006.912}, "sumd.rev.cmp8": {"acc": 0.816, "reasoning_bytes": 93.01, "flops_per_problem": 5344085016.576}, "add.rev.cmp6": {"acc": 0.998, "reasoning_bytes": 157.302, "flops_per_problem": 8565162835.968}, "add.rev.cmp7": {"acc": 0.982, "reasoning_bytes": 181.788, "flops_per_problem": 9776202596.352}, "add.rev.cmp8": {"acc": 0.792, "reasoning_bytes": 199.654, "flops_per_problem": 10699299127.296}, "runmax.rev.runmax12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5917851648.0}, "runmax.rev.runmax14": {"acc": 1.0, "reasoning_bytes": 111.94, "flops_per_problem": 6533484871.68}, "runmax.rev.runmax16": {"acc": 0.972, "reasoning_bytes": 118.04, "flops_per_problem": 6891205754.88}, "count.rev.runmax16": {"acc": 0.998, "reasoning_bytes": 108.0, "flops_per_problem": 6491971584.0}, "count.rev.runmax18": {"acc": 0.98, "reasoning_bytes": 117.84, "flops_per_problem": 7014862356.48}, "count.rev.runmax20": {"acc": 0.81, "reasoning_bytes": 123.58, "flops_per_problem": 7356684533.76}, "add.rev.runmax6": {"acc": 1.0, "reasoning_bytes": 185.08, "flops_per_problem": 9586919669.76}, "add.rev.runmax7": {"acc": 0.958, "reasoning_bytes": 215.706, "flops_per_problem": 11027784056.832}, "add.rev.runmax8": {"acc": 0.552, "reasoning_bytes": 244.634, "flops_per_problem": 12393571221.504}, "inc.rev.count6": {"acc": 0.972, "reasoning_bytes": 156.0, "flops_per_problem": 8037679104.0}, "inc.rev.count7": {"acc": 0.896, "reasoning_bytes": 182.93, "flops_per_problem": 9271153704.96}, "inc.rev.count8": {"acc": 0.588, "reasoning_bytes": 185.292, "flops_per_problem": 9419629953.024}, "count.rev.count16": {"acc": 1.0, "reasoning_bytes": 108.0, "flops_per_problem": 6536134656.0}, "count.rev.count18": {"acc": 1.0, "reasoning_bytes": 117.97, "flops_per_problem": 7064766627.84}, "count.rev.count20": {"acc": 0.998, "reasoning_bytes": 124.41, "flops_per_problem": 7437502955.52}, "parity.rev.count16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7198580736.0}, "parity.rev.count20": {"acc": 1.0, "reasoning_bytes": 145.696, "flops_per_problem": 8333395034.112}, "parity.rev.count24": {"acc": 1.0, "reasoning_bytes": 166.0, "flops_per_problem": 9406734336.0}, "sumd.rev.find6": {"acc": 1.0, "reasoning_bytes": 85.208, "flops_per_problem": 4911286910.976}, "sumd.rev.find7": {"acc": 0.996, "reasoning_bytes": 93.5, "flops_per_problem": 5321650176.0}, "sumd.rev.find8": {"acc": 0.918, "reasoning_bytes": 99.782, "flops_per_problem": 5643245666.304}, "runmax.rev.find12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5917851648.0}, "runmax.rev.find14": {"acc": 1.0, "reasoning_bytes": 111.88, "flops_per_problem": 6530835087.36}, "runmax.rev.find16": {"acc": 0.99, "reasoning_bytes": 118.06, "flops_per_problem": 6892089016.32}, "count.rev.find16": {"acc": 1.0, "reasoning_bytes": 108.0, "flops_per_problem": 6491971584.0}, "count.rev.find18": {"acc": 0.994, "reasoning_bytes": 117.85, "flops_per_problem": 7015303987.2}, "count.rev.find20": {"acc": 0.944, "reasoning_bytes": 123.47, "flops_per_problem": 7351826595.84}, "count.rev.rev16": {"acc": 0.996, "reasoning_bytes": 103.0, "flops_per_problem": 6138667008.0}, "count.rev.rev18": {"acc": 0.972, "reasoning_bytes": 112.6, "flops_per_problem": 6650958643.2}, "count.rev.rev20": {"acc": 0.788, "reasoning_bytes": 118.394, "flops_per_problem": 6995165626.368}, "sumd.rev.rev6": {"acc": 1.0, "reasoning_bytes": 80.53, "flops_per_problem": 4616277590.016}, "sumd.rev.rev7": {"acc": 0.994, "reasoning_bytes": 88.48, "flops_per_problem": 5011625410.56}, "sumd.rev.rev8": {"acc": 0.772, "reasoning_bytes": 94.888, "flops_per_problem": 5338697121.792}, "parity.rev.rev16": {"acc": 1.0, "reasoning_bytes": 119.0, "flops_per_problem": 6801113088.0}, "parity.rev.rev20": {"acc": 0.77, "reasoning_bytes": 139.784, "flops_per_problem": 7895650664.448}, "parity.rev.rev24": {"acc": 0.7, "reasoning_bytes": 161.0, "flops_per_problem": 9009266688.0}, "sumd.rev.sumd6": {"acc": 1.0, "reasoning_bytes": 84.73, "flops_per_problem": 4810771759.104}, "sumd.rev.sumd7": {"acc": 0.994, "reasoning_bytes": 92.74, "flops_per_problem": 5211242496.0}, "sumd.rev.sumd8": {"acc": 0.892, "reasoning_bytes": 100.258, "flops_per_problem": 5588925087.744}, "parity.rev.sumd16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.rev.sumd20": {"acc": 0.814, "reasoning_bytes": 143.36, "flops_per_problem": 8097740881.92}, "parity.rev.sumd24": {"acc": 0.746, "reasoning_bytes": 164.012, "flops_per_problem": 9186448932.864}, "add.rev.sumd6": {"acc": 0.976, "reasoning_bytes": 191.662, "flops_per_problem": 9833261285.376}, "add.rev.sumd7": {"acc": 0.598, "reasoning_bytes": 224.046, "flops_per_problem": 11354679115.776}, "add.rev.sumd8": {"acc": 0.036, "reasoning_bytes": 253.802, "flops_per_problem": 12758093217.792}, "parity.rev.inc16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 6977765376.0}, "parity.rev.inc20": {"acc": 0.788, "reasoning_bytes": 144.528, "flops_per_problem": 8105160278.016}, "parity.rev.inc24": {"acc": 0.698, "reasoning_bytes": 165.024, "flops_per_problem": 9186978889.728}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 99.0, "flops_per_problem": 5772378488.832}, "runmax.rev.inc14": {"acc": 1.0, "reasoning_bytes": 110.712, "flops_per_problem": 6381298925.568}, "runmax.rev.inc16": {"acc": 0.962, "reasoning_bytes": 117.012, "flops_per_problem": 6748824010.752}, "inc.rev.inc6": {"acc": 0.994, "reasoning_bytes": 170.0, "flops_per_problem": 8695885529.088}, "inc.rev.inc7": {"acc": 0.722, "reasoning_bytes": 199.918, "flops_per_problem": 10108043919.36}, "inc.rev.inc8": {"acc": 0.004, "reasoning_bytes": 220.11, "flops_per_problem": 11077335023.616}, "parity.sumd.cmp16": {"acc": 1.0, "reasoning_bytes": 126.0, "flops_per_problem": 7242743808.0}, "parity.sumd.cmp20": {"acc": 0.99, "reasoning_bytes": 145.14, "flops_per_problem": 8264677294.08}, "parity.sumd.cmp24": {"acc": 0.972, "reasoning_bytes": 167.916, "flops_per_problem": 9447187709.952}, "runmax.sumd.cmp12": {"acc": 1.0, "reasoning_bytes": 102.0, "flops_per_problem": 6006177792.0}, "runmax.sumd.cmp14": {"acc": 1.0, "reasoning_bytes": 113.34, "flops_per_problem": 6595313172.48}, "runmax.sumd.cmp16": {"acc": 0.994, "reasoning_bytes": 120.0, "flops_per_problem": 6977765376.0}, "count.sumd.cmp16": {"acc": 1.0, "reasoning_bytes": 110.0, "flops_per_problem": 6580297728.0}, "count.sumd.cmp18": {"acc": 0.994, "reasoning_bytes": 119.16, "flops_per_problem": 7073157611.52}, "count.sumd.cmp20": {"acc": 0.956, "reasoning_bytes": 125.16, "flops_per_problem": 7426462187.52}, "sumd.sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 84.36, "flops_per_problem": 4917999697.92}, "sumd.sumd.runmax7": {"acc": 0.99, "reasoning_bytes": 92.856, "flops_per_problem": 5337372229.632}, "sumd.sumd.runmax8": {"acc": 0.9, "reasoning_bytes": 100.968, "flops_per_problem": 5739786141.696}, "count.sumd.runmax16": {"acc": 0.998, "reasoning_bytes": 111.01, "flops_per_problem": 6669065502.72}, "count.sumd.runmax18": {"acc": 0.978, "reasoning_bytes": 120.69, "flops_per_problem": 7184890183.68}, "count.sumd.runmax20": {"acc": 0.8, "reasoning_bytes": 126.41, "flops_per_problem": 7525829099.52}, "add.sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 151.444, "flops_per_problem": 8145613651.968}, "add.sumd.runmax7": {"acc": 0.772, "reasoning_bytes": 171.322, "flops_per_problem": 9111813341.184}, "add.sumd.runmax8": {"acc": 0.188, "reasoning_bytes": 190.902, "flops_per_problem": 10065382391.808}, "parity.sumd.count16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7375233024.0}, "parity.sumd.count20": {"acc": 1.0, "reasoning_bytes": 148.036, "flops_per_problem": 8480899694.592}, "parity.sumd.count24": {"acc": 1.0, "reasoning_bytes": 169.0, "flops_per_problem": 9583386624.0}, "sumd.sumd.count6": {"acc": 1.0, "reasoning_bytes": 84.184, "flops_per_problem": 4954390069.248}, "sumd.sumd.count7": {"acc": 0.998, "reasoning_bytes": 92.476, "flops_per_problem": 5364753334.272}, "sumd.sumd.count8": {"acc": 0.932, "reasoning_bytes": 100.142, "flops_per_problem": 5747470516.224}, "add.sumd.count6": {"acc": 0.998, "reasoning_bytes": 150.516, "flops_per_problem": 8148793393.152}, "add.sumd.count7": {"acc": 0.892, "reasoning_bytes": 170.216, "flops_per_problem": 9107573686.272}, "add.sumd.count8": {"acc": 0.44, "reasoning_bytes": 190.738, "flops_per_problem": 10109368811.52}, "runmax.sumd.find12": {"acc": 1.0, "reasoning_bytes": 103.0, "flops_per_problem": 6094503936.0}, "runmax.sumd.find14": {"acc": 1.0, "reasoning_bytes": 114.604, "flops_per_problem": 6695298367.488}, "runmax.sumd.find16": {"acc": 0.99, "reasoning_bytes": 121.036, "flops_per_problem": 7067681390.592}, "sumd.sumd.find6": {"acc": 1.0, "reasoning_bytes": 84.064, "flops_per_problem": 4904927428.608}, "sumd.sumd.find7": {"acc": 0.996, "reasoning_bytes": 92.37, "flops_per_problem": 5315908976.64}, "sumd.sumd.find8": {"acc": 0.968, "reasoning_bytes": 100.158, "flops_per_problem": 5704014053.376}, "parity.sumd.find16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.sumd.find20": {"acc": 0.954, "reasoning_bytes": 147.4, "flops_per_problem": 8408648908.8}, "parity.sumd.find24": {"acc": 0.936, "reasoning_bytes": 169.024, "flops_per_problem": 9540283465.728}, "count.sumd.rev16": {"acc": 0.996, "reasoning_bytes": 106.0, "flops_per_problem": 6315319296.0}, "count.sumd.rev18": {"acc": 0.962, "reasoning_bytes": 115.32, "flops_per_problem": 6815245271.04}, "count.sumd.rev20": {"acc": 0.79, "reasoning_bytes": 121.288, "flops_per_problem": 7167136628.736}, "parity.sumd.rev16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.sumd.rev20": {"acc": 0.806, "reasoning_bytes": 143.384, "flops_per_problem": 8098800795.648}, "parity.sumd.rev24": {"acc": 0.74, "reasoning_bytes": 164.012, "flops_per_problem": 9186448932.864}, "add.sumd.rev6": {"acc": 1.0, "reasoning_bytes": 145.448, "flops_per_problem": 7792309075.968}, "add.sumd.rev7": {"acc": 0.802, "reasoning_bytes": 165.422, "flops_per_problem": 8762395115.52}, "add.sumd.rev8": {"acc": 0.028, "reasoning_bytes": 186.276, "flops_per_problem": 9771521310.72}, "parity.sumd.sumd16": {"acc": 1.0, "reasoning_bytes": 125.0, "flops_per_problem": 7154417664.0}, "parity.sumd.sumd20": {"acc": 0.804, "reasoning_bytes": 145.376, "flops_per_problem": 8230936707.072}, "parity.sumd.sumd24": {"acc": 0.74, "reasoning_bytes": 167.012, "flops_per_problem": 9363101220.864}, "add.sumd.sumd6": {"acc": 1.0, "reasoning_bytes": 149.642, "flops_per_problem": 7986449940.48}, "add.sumd.sumd7": {"acc": 0.752, "reasoning_bytes": 169.602, "flops_per_problem": 8958655807.488}, "add.sumd.sumd8": {"acc": 0.082, "reasoning_bytes": 189.64, "flops_per_problem": 9941195833.344}, "count.sumd.sumd16": {"acc": 0.998, "reasoning_bytes": 109.0, "flops_per_problem": 6491971584.0}, "count.sumd.sumd18": {"acc": 0.972, "reasoning_bytes": 118.33, "flops_per_problem": 6992339189.76}, "count.sumd.sumd20": {"acc": 0.798, "reasoning_bytes": 124.31, "flops_per_problem": 7344760504.32}, "inc.sumd.inc6": {"acc": 1.0, "reasoning_bytes": 135.538, "flops_per_problem": 7045688180.736}, "inc.sumd.inc7": {"acc": 0.79, "reasoning_bytes": 153.436, "flops_per_problem": 7880281915.392}, "inc.sumd.inc8": {"acc": 0.086, "reasoning_bytes": 167.368, "flops_per_problem": 8540166537.216}, "sumd.sumd.inc6": {"acc": 0.998, "reasoning_bytes": 83.764, "flops_per_problem": 4773586452.48}, "sumd.sumd.inc7": {"acc": 0.994, "reasoning_bytes": 92.34, "flops_per_problem": 5199406792.704}, "sumd.sumd.inc8": {"acc": 0.896, "reasoning_bytes": 100.268, "flops_per_problem": 5594489634.816}, "parity.sumd.inc16": {"acc": 1.0, "reasoning_bytes": 126.0, "flops_per_problem": 7154417664.0}, "parity.sumd.inc20": {"acc": 0.778, "reasoning_bytes": 147.3, "flops_per_problem": 8271743385.6}, "parity.sumd.inc24": {"acc": 0.738, "reasoning_bytes": 168.844, "flops_per_problem": 9399844896.768}, "inc.inc.cmp6": {"acc": 1.0, "reasoning_bytes": 144.624, "flops_per_problem": 7667769212.928}, "inc.inc.cmp7": {"acc": 0.992, "reasoning_bytes": 165.626, "flops_per_problem": 8683608195.072}, "inc.inc.cmp8": {"acc": 0.926, "reasoning_bytes": 185.924, "flops_per_problem": 9668356374.528}, "runmax.inc.cmp12": {"acc": 1.0, "reasoning_bytes": 105.568, "flops_per_problem": 6150856015.872}, "runmax.inc.cmp14": {"acc": 1.0, "reasoning_bytes": 117.454, "flops_per_problem": 6768167436.288}, "runmax.inc.cmp16": {"acc": 0.968, "reasoning_bytes": 123.82, "flops_per_problem": 7138872262.656}, "sumd.inc.cmp6": {"acc": 1.0, "reasoning_bytes": 88.12, "flops_per_problem": 5039713124.352}, "sumd.inc.cmp7": {"acc": 1.0, "reasoning_bytes": 96.084, "flops_per_problem": 5435767554.048}, "sumd.inc.cmp8": {"acc": 0.974, "reasoning_bytes": 101.04, "flops_per_problem": 5698802810.88}, "sumd.inc.runmax6": {"acc": 1.0, "reasoning_bytes": 93.522, "flops_per_problem": 5278458691.584}, "sumd.inc.runmax7": {"acc": 0.994, "reasoning_bytes": 101.48, "flops_per_problem": 5674071490.56}, "sumd.inc.runmax8": {"acc": 0.896, "reasoning_bytes": 108.846, "flops_per_problem": 6043539750.912}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.648, "flops_per_problem": 6343936966.656}, "runmax.inc.runmax14": {"acc": 1.0, "reasoning_bytes": 122.136, "flops_per_problem": 6983771553.792}, "runmax.inc.runmax16": {"acc": 0.964, "reasoning_bytes": 128.484, "flops_per_problem": 7352444878.848}, "add.inc.runmax6": {"acc": 1.0, "reasoning_bytes": 192.872, "flops_per_problem": 9931038326.784}, "add.inc.runmax7": {"acc": 0.956, "reasoning_bytes": 220.896, "flops_per_problem": 11256990400.512}, "add.inc.runmax8": {"acc": 0.544, "reasoning_bytes": 245.71, "flops_per_problem": 12448863387.648}, "runmax.inc.count12": {"acc": 1.0, "reasoning_bytes": 108.928, "flops_per_problem": 6356302626.816}, "runmax.inc.count14": {"acc": 1.0, "reasoning_bytes": 121.398, "flops_per_problem": 6995342278.656}, "runmax.inc.count16": {"acc": 1.0, "reasoning_bytes": 127.744, "flops_per_problem": 7363927277.568}, "sumd.inc.count6": {"acc": 1.0, "reasoning_bytes": 92.388, "flops_per_problem": 5272540839.936}, "sumd.inc.count7": {"acc": 0.994, "reasoning_bytes": 100.46, "flops_per_problem": 5673188229.12}, "sumd.inc.count8": {"acc": 0.82, "reasoning_bytes": 106.69, "flops_per_problem": 5992487239.68}, "inc.inc.count6": {"acc": 0.978, "reasoning_bytes": 165.0, "flops_per_problem": 8435146752.0}, "inc.inc.count7": {"acc": 0.892, "reasoning_bytes": 189.982, "flops_per_problem": 9582591688.704}, "inc.inc.count8": {"acc": 0.632, "reasoning_bytes": 196.67, "flops_per_problem": 9922117386.24}, "parity.inc.find16": {"acc": 1.0, "reasoning_bytes": 128.0, "flops_per_problem": 7331069952.0}, "parity.inc.find20": {"acc": 0.96, "reasoning_bytes": 149.696, "flops_per_problem": 8465884250.112}, "parity.inc.find24": {"acc": 0.894, "reasoning_bytes": 170.072, "flops_per_problem": 9542403293.184}, "sumd.inc.find6": {"acc": 1.0, "reasoning_bytes": 92.1, "flops_per_problem": 5215658803.2}, "sumd.inc.find7": {"acc": 0.998, "reasoning_bytes": 100.404, "flops_per_problem": 5626552025.088}, "sumd.inc.find8": {"acc": 0.956, "reasoning_bytes": 107.014, "flops_per_problem": 5962633003.008}, "count.inc.find16": {"acc": 0.996, "reasoning_bytes": 112.0, "flops_per_problem": 6668623872.0}, "count.inc.find18": {"acc": 0.944, "reasoning_bytes": 121.84, "flops_per_problem": 7191514644.48}, "count.inc.find20": {"acc": 0.906, "reasoning_bytes": 127.7, "flops_per_problem": 7538636390.4}, "sumd.inc.rev6": {"acc": 0.998, "reasoning_bytes": 87.524, "flops_per_problem": 4925154115.584}, "sumd.inc.rev7": {"acc": 0.994, "reasoning_bytes": 95.48, "flops_per_problem": 5320766914.56}, "sumd.inc.rev8": {"acc": 0.84, "reasoning_bytes": 102.44, "flops_per_problem": 5672304967.68}, "count.inc.rev16": {"acc": 0.996, "reasoning_bytes": 107.0, "flops_per_problem": 6315319296.0}, "count.inc.rev18": {"acc": 0.97, "reasoning_bytes": 116.66, "flops_per_problem": 6830260715.52}, "count.inc.rev20": {"acc": 0.784, "reasoning_bytes": 122.56, "flops_per_problem": 7179148984.32}, "parity.inc.rev16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 6977765376.0}, "parity.inc.rev20": {"acc": 0.766, "reasoning_bytes": 144.804, "flops_per_problem": 8117349285.888}, "parity.inc.rev24": {"acc": 0.736, "reasoning_bytes": 165.072, "flops_per_problem": 9189098717.184}, "count.inc.sumd16": {"acc": 0.996, "reasoning_bytes": 110.0, "flops_per_problem": 6491971584.0}, "count.inc.sumd18": {"acc": 0.97, "reasoning_bytes": 119.65, "flops_per_problem": 7006471372.8}, "count.inc.sumd20": {"acc": 0.786, "reasoning_bytes": 125.436, "flops_per_problem": 7350325051.392}, "sumd.inc.sumd6": {"acc": 0.998, "reasoning_bytes": 91.758, "flops_per_problem": 5122651373.568}, "sumd.inc.sumd7": {"acc": 0.994, "reasoning_bytes": 99.762, "flops_per_problem": 5522327175.168}, "sumd.inc.sumd8": {"acc": 0.89, "reasoning_bytes": 107.388, "flops_per_problem": 5906104270.848}, "add.inc.sumd6": {"acc": 0.962, "reasoning_bytes": 198.524, "flops_per_problem": 10136308285.44}, "add.inc.sumd7": {"acc": 0.566, "reasoning_bytes": 228.46, "flops_per_problem": 11549703241.728}, "add.inc.sumd8": {"acc": 0.01, "reasoning_bytes": 250.478, "flops_per_problem": 12732920266.752}, "parity.inc.inc16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7154417664.0}, "parity.inc.inc20": {"acc": 0.744, "reasoning_bytes": 148.876, "flops_per_problem": 8297181315.072}, "parity.inc.inc24": {"acc": 0.714, "reasoning_bytes": 169.36, "flops_per_problem": 9378469969.92}, "sumd.inc.inc6": {"acc": 0.998, "reasoning_bytes": 94.518, "flops_per_problem": 5234118967.296}, "sumd.inc.inc7": {"acc": 0.994, "reasoning_bytes": 102.48, "flops_per_problem": 5629908418.56}, "sumd.inc.inc8": {"acc": 0.818, "reasoning_bytes": 109.628, "flops_per_problem": 5989749129.216}, "runmax.inc.inc12": {"acc": 1.0, "reasoning_bytes": 110.06, "flops_per_problem": 6270272962.56}, "runmax.inc.inc14": {"acc": 1.0, "reasoning_bytes": 122.388, "flops_per_problem": 6904543002.624}, "runmax.inc.inc16": {"acc": 0.956, "reasoning_bytes": 129.0, "flops_per_problem": 7285317009.408}, "count.inc.cmp16": {"acc": 0.996, "reasoning_bytes": 111.008, "flops_per_problem": 6580651032.576}, "count.inc.cmp18": {"acc": 0.97, "reasoning_bytes": 120.89, "flops_per_problem": 7106368241.664}, "count.inc.cmp20": {"acc": 0.846, "reasoning_bytes": 128.28, "flops_per_problem": 7523532619.776}, "inc.rev.sumd6": {"acc": 0.938, "reasoning_bytes": 166.26, "flops_per_problem": 8405469167.616}, "inc.rev.sumd7": {"acc": 0.484, "reasoning_bytes": 196.038, "flops_per_problem": 9763571957.76}, "inc.rev.sumd8": {"acc": 0.062, "reasoning_bytes": 218.146, "flops_per_problem": 10782060724.224}, "runmax.inc.find12": {"acc": 0.932, "reasoning_bytes": 106.28, "flops_per_problem": 6195195740.16}, "runmax.inc.find14": {"acc": 0.922, "reasoning_bytes": 117.828, "flops_per_problem": 6793517039.616}, "runmax.inc.find16": {"acc": 0.93, "reasoning_bytes": 125.552, "flops_per_problem": 7222958751.744}, "inc.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 120.0, "flops_per_problem": 6491971584.0}, "inc.runmax.cmp7": {"acc": 0.972, "reasoning_bytes": 136.0, "flops_per_problem": 7242743808.0}, "inc.runmax.cmp8": {"acc": 0.97, "reasoning_bytes": 141.01, "flops_per_problem": 7508163870.72}} +{"step": 11000, "train_loss": 0.9860423803329468} +{"step": 11020, "train_loss": 0.9693198204040527} +{"step": 11040, "train_loss": 1.007258653640747} +{"step": 11060, "train_loss": 0.9142311811447144} +{"step": 11080, "train_loss": 0.971672534942627} +{"step": 11100, "train_loss": 1.0227781534194946} +{"step": 11120, "train_loss": 1.0112299919128418} +{"step": 11140, "train_loss": 0.9776791930198669} +{"step": 11160, "train_loss": 1.0050550699234009} +{"step": 11180, "train_loss": 0.925335168838501} +{"step": 11200, "train_loss": 1.028137445449829} +{"step": 11220, "train_loss": 0.9985470175743103} +{"step": 11240, "train_loss": 1.0536420345306396} +{"step": 11260, "train_loss": 0.9926456212997437} +{"step": 11280, "train_loss": 0.9771921634674072} +{"step": 11300, "train_loss": 0.9659970998764038} +{"step": 11320, "train_loss": 1.0260865688323975} +{"step": 11340, "train_loss": 1.039131999015808} +{"step": 11360, "train_loss": 1.0294592380523682} +{"step": 11380, "train_loss": 0.9058221578598022} +{"step": 11400, "train_loss": 0.9619318246841431} +{"step": 11420, "train_loss": 0.9609333872795105} +{"step": 11440, "train_loss": 1.0938529968261719} +{"step": 11460, "train_loss": 1.0442887544631958} +{"step": 11480, "train_loss": 1.0147194862365723} +{"step": 11500, "train_loss": 1.005934476852417} +{"step": 11520, "train_loss": 1.0162243843078613} +{"step": 11540, "train_loss": 0.985058069229126} +{"step": 11560, "train_loss": 1.0911314487457275} +{"step": 11580, "train_loss": 1.0173141956329346} +{"step": 11600, "train_loss": 0.9787067174911499} +{"step": 11620, "train_loss": 0.9474111795425415} +{"step": 11640, "train_loss": 1.0197561979293823} +{"step": 11660, "train_loss": 0.931082010269165} +{"step": 11680, "train_loss": 0.9816672801971436} +{"step": 11700, "train_loss": 1.0121445655822754} +{"step": 11720, "train_loss": 1.0093494653701782} +{"step": 11740, "train_loss": 0.9808226227760315} +{"step": 11760, "train_loss": 0.9880858659744263} +{"step": 11780, "train_loss": 0.9684246778488159} +{"step": 11800, "train_loss": 0.959318995475769} +{"step": 11820, "train_loss": 0.984038233757019} +{"step": 11840, "train_loss": 0.9783648252487183} +{"step": 11860, "train_loss": 1.0355048179626465} +{"step": 11880, "train_loss": 0.9385703802108765} +{"step": 11900, "train_loss": 1.0321695804595947} +{"step": 11920, "train_loss": 1.0376100540161133} +{"step": 11940, "train_loss": 0.948393702507019} +{"step": 11960, "train_loss": 1.050437569618225} +{"step": 11980, "train_loss": 0.9852586984634399} +{"step": 12000, "tokens": 393216000, "val_loss": 1.8012226045131683, "val_bpb": 0.6493114858043822, "lr": 6.039882929516903e-05, "elapsed": 3917.0084266662598, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.984, "reasoning_bytes": 79.0, "flops_per_problem": 4928775487.488}, "add9": {"acc": 0.646, "reasoning_bytes": 89.0, "flops_per_problem": 5503072075.776}, "add10": {"acc": 0.002, "reasoning_bytes": 98.944, "flops_per_problem": 6075955445.76}, "reach14": {"acc": 0.558, "reasoning_bytes": 9.066, "flops_per_problem": 4684200394.752}, "reach16": {"acc": 0.552, "reasoning_bytes": 9.894, "flops_per_problem": 5253020762.112}, "reach18": {"acc": 0.518, "reasoning_bytes": 10.668, "flops_per_problem": 5814951690.24}, "parity24": {"acc": 0.364, "reasoning_bytes": 143.048, "flops_per_problem": 7863146643.456}, "parity28": {"acc": 0.498, "reasoning_bytes": 167.084, "flops_per_problem": 9101302530.048}, "parity32": {"acc": 0.504, "reasoning_bytes": 191.08, "flops_per_problem": 10337691893.76}, "cmp8": {"acc": 0.996, "reasoning_bytes": 5.804, "flops_per_problem": 1360399269.888}, "cmp9": {"acc": 0.992, "reasoning_bytes": 5.704, "flops_per_problem": 1444309106.688}, "cmp10": {"acc": 0.994, "reasoning_bytes": 5.72, "flops_per_problem": 1533341859.84}, "runmax12": {"acc": 1.0, "reasoning_bytes": 71.0, "flops_per_problem": 4151328768.0}, "runmax14": {"acc": 1.0, "reasoning_bytes": 83.0, "flops_per_problem": 4769611776.0}, "runmax16": {"acc": 0.986, "reasoning_bytes": 91.808, "flops_per_problem": 5246926258.176}, "count16": {"acc": 0.994, "reasoning_bytes": 79.0, "flops_per_problem": 4725448704.0}, "count18": {"acc": 0.96, "reasoning_bytes": 88.84, "flops_per_problem": 5251430891.52}, "count20": {"acc": 0.77, "reasoning_bytes": 95.774, "flops_per_problem": 5646072102.912}, "brackets16": {"acc": 0.906, "reasoning_bytes": 53.812, "flops_per_problem": 3657143992.32}, "brackets18": {"acc": 0.87, "reasoning_bytes": 57.352, "flops_per_problem": 3902337368.064}, "brackets20": {"acc": 0.846, "reasoning_bytes": 65.236, "flops_per_problem": 4339640107.008}, "sumd8": {"acc": 0.958, "reasoning_bytes": 58.55, "flops_per_problem": 3380594835.456}, "sumd9": {"acc": 0.78, "reasoning_bytes": 66.196, "flops_per_problem": 3762340429.824}, "sumd10": {"acc": 0.368, "reasoning_bytes": 71.488, "flops_per_problem": 4040567783.424}, "inc8": {"acc": 0.998, "reasoning_bytes": 63.0, "flops_per_problem": 3797405908.992}, "inc9": {"acc": 0.846, "reasoning_bytes": 70.92, "flops_per_problem": 4230468993.024}, "inc10": {"acc": 0.01, "reasoning_bytes": 73.816, "flops_per_problem": 4184981028.864}, "add.cmp6": {"acc": 1.0, "reasoning_bytes": 92.62, "flops_per_problem": 5531954724.864}, "add.cmp7": {"acc": 0.998, "reasoning_bytes": 105.526, "flops_per_problem": 6231674437.632}, "add.cmp8": {"acc": 0.998, "reasoning_bytes": 118.256, "flops_per_problem": 6927861104.64}, "add.runmax6": {"acc": 1.0, "reasoning_bytes": 120.832, "flops_per_problem": 6572878331.904}, "add.runmax7": {"acc": 0.988, "reasoning_bytes": 138.848, "flops_per_problem": 7456846381.056}, "add.runmax8": {"acc": 0.578, "reasoning_bytes": 156.566, "flops_per_problem": 8328360443.904}, "add.count6": {"acc": 0.998, "reasoning_bytes": 115.648, "flops_per_problem": 6388100038.656}, "add.count7": {"acc": 0.972, "reasoning_bytes": 132.07, "flops_per_problem": 7201672151.04}, "add.count8": {"acc": 0.444, "reasoning_bytes": 148.65, "flops_per_problem": 8022222028.8}, "add.find6": {"acc": 0.86, "reasoning_bytes": 107.852, "flops_per_problem": 5999641657.344}, "add.find7": {"acc": 0.724, "reasoning_bytes": 121.762, "flops_per_problem": 6702276132.864}, "add.find8": {"acc": 0.506, "reasoning_bytes": 138.204, "flops_per_problem": 7516731506.688}, "add.rev6": {"acc": 1.0, "reasoning_bytes": 123.248, "flops_per_problem": 6794576953.344}, "add.rev7": {"acc": 0.606, "reasoning_bytes": 145.854, "flops_per_problem": 7924356661.248}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 168.014, "flops_per_problem": 9015979474.944}, "add.sumd6": {"acc": 1.0, "reasoning_bytes": 126.476, "flops_per_problem": 6777794985.984}, "add.sumd7": {"acc": 0.948, "reasoning_bytes": 146.346, "flops_per_problem": 7743729696.768}, "add.sumd8": {"acc": 0.05, "reasoning_bytes": 165.826, "flops_per_problem": 8693059092.48}, "add.inc6": {"acc": 1.0, "reasoning_bytes": 131.04, "flops_per_problem": 7138695610.368}, "add.inc7": {"acc": 0.912, "reasoning_bytes": 150.968, "flops_per_problem": 8150913220.608}, "add.inc8": {"acc": 0.014, "reasoning_bytes": 167.876, "flops_per_problem": 9017039388.672}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5122916352.0}, "runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 97.752, "flops_per_problem": 5686083846.144}, "runmax.cmp16": {"acc": 0.976, "reasoning_bytes": 105.024, "flops_per_problem": 6095563849.728}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.runmax14": {"acc": 1.0, "reasoning_bytes": 99.868, "flops_per_problem": 5823695978.496}, "runmax.runmax16": {"acc": 0.988, "reasoning_bytes": 106.3, "flops_per_problem": 6196079001.6}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5255405568.0}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 99.376, "flops_per_problem": 5846130819.072}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 106.096, "flops_per_problem": 6231232806.912}, "runmax.find12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.find14": {"acc": 1.0, "reasoning_bytes": 98.812, "flops_per_problem": 5777059774.464}, "runmax.find16": {"acc": 0.994, "reasoning_bytes": 106.072, "flops_per_problem": 6186009821.184}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 83.0, "flops_per_problem": 4857937920.0}, "runmax.rev14": {"acc": 0.998, "reasoning_bytes": 94.544, "flops_per_problem": 5456082567.168}, "runmax.rev16": {"acc": 0.972, "reasoning_bytes": 101.168, "flops_per_problem": 5836944900.096}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 86.0, "flops_per_problem": 5034590208.0}, "runmax.sumd14": {"acc": 1.0, "reasoning_bytes": 97.604, "flops_per_problem": 5635384639.488}, "runmax.sumd16": {"acc": 0.986, "reasoning_bytes": 104.288, "flops_per_problem": 6018896756.736}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5065769336.832}, "runmax.inc14": {"acc": 0.996, "reasoning_bytes": 97.716, "flops_per_problem": 5630615027.712}, "runmax.inc16": {"acc": 0.97, "reasoning_bytes": 105.072, "flops_per_problem": 6045217947.648}, "count.cmp16": {"acc": 1.0, "reasoning_bytes": 95.0, "flops_per_problem": 5697036288.0}, "count.cmp18": {"acc": 0.974, "reasoning_bytes": 103.02, "flops_per_problem": 6139638595.584}, "count.cmp20": {"acc": 0.928, "reasoning_bytes": 110.04, "flops_per_problem": 6538077831.168}, "count.runmax16": {"acc": 0.998, "reasoning_bytes": 96.0, "flops_per_problem": 5785362432.0}, "count.runmax18": {"acc": 0.956, "reasoning_bytes": 105.14, "flops_per_problem": 6277339054.08}, "count.runmax20": {"acc": 0.792, "reasoning_bytes": 111.22, "flops_per_problem": 6634176675.84}, "count.count16": {"acc": 1.0, "reasoning_bytes": 96.0, "flops_per_problem": 5829525504.0}, "count.count18": {"acc": 1.0, "reasoning_bytes": 105.39, "flops_per_problem": 6332542894.08}, "count.count20": {"acc": 0.998, "reasoning_bytes": 111.22, "flops_per_problem": 6678339747.84}, "count.find16": {"acc": 0.996, "reasoning_bytes": 95.99, "flops_per_problem": 5784920801.28}, "count.find18": {"acc": 0.98, "reasoning_bytes": 105.17, "flops_per_problem": 6278663946.24}, "count.find20": {"acc": 0.95, "reasoning_bytes": 111.314, "flops_per_problem": 6638328004.608}, "count.rev16": {"acc": 0.996, "reasoning_bytes": 91.0, "flops_per_problem": 5432057856.0}, "count.rev18": {"acc": 0.924, "reasoning_bytes": 99.07, "flops_per_problem": 5876779991.04}, "count.rev20": {"acc": 0.796, "reasoning_bytes": 106.12, "flops_per_problem": 6276455792.64}, "count.sumd16": {"acc": 0.998, "reasoning_bytes": 94.0, "flops_per_problem": 5608710144.0}, "count.sumd18": {"acc": 0.938, "reasoning_bytes": 102.67, "flops_per_problem": 6079930122.24}, "count.sumd20": {"acc": 0.792, "reasoning_bytes": 109.302, "flops_per_problem": 6460969107.456}, "count.inc16": {"acc": 0.998, "reasoning_bytes": 94.99, "flops_per_problem": 5608268513.28}, "count.inc18": {"acc": 0.938, "reasoning_bytes": 103.71, "flops_per_problem": 6081696645.12}, "count.inc20": {"acc": 0.784, "reasoning_bytes": 110.24, "flops_per_problem": 6458760953.856}, "parity.cmp16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6359482368.0}, "parity.cmp20": {"acc": 0.976, "reasoning_bytes": 134.724, "flops_per_problem": 7583859376.128}, "parity.cmp24": {"acc": 0.956, "reasoning_bytes": 153.156, "flops_per_problem": 8574525407.232}, "parity.runmax16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.runmax20": {"acc": 0.952, "reasoning_bytes": 135.976, "flops_per_problem": 7683314614.272}, "parity.runmax24": {"acc": 0.348, "reasoning_bytes": 156.46, "flops_per_problem": 8769549533.184}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6491971584.0}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 135.928, "flops_per_problem": 7725357858.816}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 156.196, "flops_per_problem": 8797107290.112}, "parity.find16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.find20": {"acc": 0.964, "reasoning_bytes": 135.928, "flops_per_problem": 7681194786.816}, "parity.find24": {"acc": 0.826, "reasoning_bytes": 156.646, "flops_per_problem": 8772817600.512}, "parity.rev16": {"acc": 1.0, "reasoning_bytes": 107.0, "flops_per_problem": 6094503936.0}, "parity.rev20": {"acc": 0.906, "reasoning_bytes": 130.964, "flops_per_problem": 7329480081.408}, "parity.rev24": {"acc": 0.316, "reasoning_bytes": 152.852, "flops_per_problem": 8507397537.792}, "parity.sumd16": {"acc": 1.0, "reasoning_bytes": 110.0, "flops_per_problem": 6271156224.0}, "parity.sumd20": {"acc": 0.948, "reasoning_bytes": 133.976, "flops_per_problem": 7506662326.272}, "parity.sumd24": {"acc": 0.344, "reasoning_bytes": 155.04, "flops_per_problem": 8632732336.128}, "parity.inc16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6271156224.0}, "parity.inc20": {"acc": 0.908, "reasoning_bytes": 134.964, "flops_per_problem": 7506132369.408}, "parity.inc24": {"acc": 0.352, "reasoning_bytes": 156.66, "flops_per_problem": 8641388298.24}, "sumd.cmp6": {"acc": 1.0, "reasoning_bytes": 62.088, "flops_per_problem": 3713407746.048}, "sumd.cmp7": {"acc": 0.998, "reasoning_bytes": 70.084, "flops_per_problem": 4110875394.048}, "sumd.cmp8": {"acc": 0.976, "reasoning_bytes": 76.132, "flops_per_problem": 4422048399.36}, "sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.994, "reasoning_bytes": 75.48, "flops_per_problem": 4349179330.56}, "sumd.runmax8": {"acc": 0.924, "reasoning_bytes": 83.244, "flops_per_problem": 4736224493.568}, "sumd.count6": {"acc": 1.0, "reasoning_bytes": 66.428, "flops_per_problem": 3949415202.816}, "sumd.count7": {"acc": 0.994, "reasoning_bytes": 74.46, "flops_per_problem": 4348296069.12}, "sumd.count8": {"acc": 0.866, "reasoning_bytes": 81.31, "flops_per_problem": 4694976184.32}, "sumd.find6": {"acc": 1.0, "reasoning_bytes": 66.24, "flops_per_problem": 3896949473.28}, "sumd.find7": {"acc": 0.998, "reasoning_bytes": 74.44, "flops_per_problem": 4303249735.68}, "sumd.find8": {"acc": 0.94, "reasoning_bytes": 81.25, "flops_per_problem": 4648163328.0}, "sumd.rev6": {"acc": 1.0, "reasoning_bytes": 61.544, "flops_per_problem": 3601145217.024}, "sumd.rev7": {"acc": 0.994, "reasoning_bytes": 69.48, "flops_per_problem": 3995874754.56}, "sumd.rev8": {"acc": 0.832, "reasoning_bytes": 76.35, "flops_per_problem": 4343349805.056}, "sumd.sumd6": {"acc": 1.0, "reasoning_bytes": 65.744, "flops_per_problem": 3795639386.112}, "sumd.sumd7": {"acc": 0.994, "reasoning_bytes": 73.724, "flops_per_problem": 4194696904.704}, "sumd.sumd8": {"acc": 0.9, "reasoning_bytes": 81.24, "flops_per_problem": 4572291170.304}, "sumd.inc6": {"acc": 1.0, "reasoning_bytes": 68.538, "flops_per_problem": 3910021742.592}, "sumd.inc7": {"acc": 0.994, "reasoning_bytes": 76.48, "flops_per_problem": 4305016258.56}, "sumd.inc8": {"acc": 0.874, "reasoning_bytes": 83.69, "flops_per_problem": 4667595079.68}, "inc.cmp6": {"acc": 1.0, "reasoning_bytes": 78.624, "flops_per_problem": 4576354172.928}, "inc.cmp7": {"acc": 0.998, "reasoning_bytes": 89.792, "flops_per_problem": 5157893505.024}, "inc.cmp8": {"acc": 0.978, "reasoning_bytes": 100.712, "flops_per_problem": 5728480395.264}, "inc.runmax6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5520384000.0}, "inc.runmax7": {"acc": 0.998, "reasoning_bytes": 120.0, "flops_per_problem": 6271156224.0}, "inc.runmax8": {"acc": 0.934, "reasoning_bytes": 133.796, "flops_per_problem": 6924593037.312}, "inc.count6": {"acc": 0.99, "reasoning_bytes": 99.0, "flops_per_problem": 5343731712.0}, "inc.count7": {"acc": 0.988, "reasoning_bytes": 114.0, "flops_per_problem": 6050340864.0}, "inc.count8": {"acc": 0.676, "reasoning_bytes": 119.208, "flops_per_problem": 6324505214.976}, "inc.find6": {"acc": 0.896, "reasoning_bytes": 91.88, "flops_per_problem": 4985127567.36}, "inc.find7": {"acc": 0.836, "reasoning_bytes": 102.624, "flops_per_problem": 5503778684.928}, "inc.find8": {"acc": 0.386, "reasoning_bytes": 98.486, "flops_per_problem": 5365194964.992}, "inc.rev6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5608710144.0}, "inc.rev7": {"acc": 0.916, "reasoning_bytes": 124.0, "flops_per_problem": 6578354552.832}, "inc.rev8": {"acc": 0.0, "reasoning_bytes": 141.72, "flops_per_problem": 7415244767.232}, "inc.sumd6": {"acc": 1.0, "reasoning_bytes": 109.554, "flops_per_problem": 5721414303.744}, "inc.sumd7": {"acc": 0.974, "reasoning_bytes": 127.482, "flops_per_problem": 6557332930.56}, "inc.sumd8": {"acc": 0.178, "reasoning_bytes": 139.638, "flops_per_problem": 7138342305.792}, "inc.inc6": {"acc": 1.0, "reasoning_bytes": 113.0, "flops_per_problem": 6006177792.0}, "inc.inc7": {"acc": 0.994, "reasoning_bytes": 131.0, "flops_per_problem": 6889262579.712}, "inc.inc8": {"acc": 0.292, "reasoning_bytes": 145.462, "flops_per_problem": 7603997736.96}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 115.388, "flops_per_problem": 6774085287.936}, "runmax.runmax.cmp16": {"acc": 0.992, "reasoning_bytes": 119.656, "flops_per_problem": 7050899423.232}, "sumd.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 83.338, "flops_per_problem": 4917028110.336}, "sumd.runmax.cmp7": {"acc": 1.0, "reasoning_bytes": 91.468, "flops_per_problem": 5320236957.696}, "sumd.runmax.cmp8": {"acc": 0.732, "reasoning_bytes": 93.542, "flops_per_problem": 5455994241.024}, "add.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 137.024, "flops_per_problem": 7552945225.728}, "add.runmax.cmp7": {"acc": 0.972, "reasoning_bytes": 154.928, "flops_per_problem": 8431967010.816}, "add.runmax.cmp8": {"acc": 0.88, "reasoning_bytes": 171.444, "flops_per_problem": 9249690451.968}, "count.runmax.runmax16": {"acc": 0.994, "reasoning_bytes": 113.0, "flops_per_problem": 6845276160.0}, "count.runmax.runmax18": {"acc": 0.97, "reasoning_bytes": 122.59, "flops_per_problem": 7357126164.48}, "count.runmax.runmax20": {"acc": 0.792, "reasoning_bytes": 128.37, "flops_per_problem": 7700714864.64}, "add.runmax.runmax6": {"acc": 1.0, "reasoning_bytes": 137.832, "flops_per_problem": 7632792059.904}, "add.runmax.runmax7": {"acc": 0.972, "reasoning_bytes": 155.864, "flops_per_problem": 8517466718.208}, "add.runmax.runmax8": {"acc": 0.554, "reasoning_bytes": 173.588, "flops_per_problem": 9388539150.336}, "parity.runmax.runmax16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7507722240.0}, "parity.runmax.runmax20": {"acc": 0.868, "reasoning_bytes": 151.632, "flops_per_problem": 8683873173.504}, "parity.runmax.runmax24": {"acc": 0.316, "reasoning_bytes": 171.108, "flops_per_problem": 9720645451.776}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7551885312.0}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 152.568, "flops_per_problem": 8769372880.896}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 171.3, "flops_per_problem": 9773287833.6}, "inc.runmax.count6": {"acc": 1.0, "reasoning_bytes": 121.0, "flops_per_problem": 6624460800.0}, "inc.runmax.count7": {"acc": 0.996, "reasoning_bytes": 137.0, "flops_per_problem": 7375233024.0}, "inc.runmax.count8": {"acc": 0.996, "reasoning_bytes": 139.624, "flops_per_problem": 7535279996.928}, "sumd.runmax.count6": {"acc": 1.0, "reasoning_bytes": 84.424, "flops_per_problem": 5053315350.528}, "sumd.runmax.count7": {"acc": 1.0, "reasoning_bytes": 92.46, "flops_per_problem": 5452372869.12}, "sumd.runmax.count8": {"acc": 0.888, "reasoning_bytes": 97.082, "flops_per_problem": 5700657659.904}, "runmax.runmax.find12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6271156224.0}, "runmax.runmax.find14": {"acc": 1.0, "reasoning_bytes": 116.136, "flops_per_problem": 6851282337.792}, "runmax.runmax.find16": {"acc": 0.992, "reasoning_bytes": 123.072, "flops_per_problem": 7245923549.184}, "add.runmax.find6": {"acc": 1.0, "reasoning_bytes": 137.928, "flops_per_problem": 7637031714.816}, "add.runmax.find7": {"acc": 0.996, "reasoning_bytes": 155.64, "flops_per_problem": 8507574190.08}, "add.runmax.find8": {"acc": 0.87, "reasoning_bytes": 173.288, "flops_per_problem": 9375290228.736}, "parity.runmax.find16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7507722240.0}, "parity.runmax.find20": {"acc": 0.974, "reasoning_bytes": 152.352, "flops_per_problem": 8715670585.344}, "parity.runmax.find24": {"acc": 0.842, "reasoning_bytes": 171.258, "flops_per_problem": 9726739955.712}, "add.runmax.rev6": {"acc": 1.0, "reasoning_bytes": 132.832, "flops_per_problem": 7279487483.904}, "add.runmax.rev7": {"acc": 0.986, "reasoning_bytes": 150.864, "flops_per_problem": 8164162142.208}, "add.runmax.rev8": {"acc": 0.57, "reasoning_bytes": 168.532, "flops_per_problem": 9032761442.304}, "parity.runmax.rev16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7154417664.0}, "parity.runmax.rev20": {"acc": 0.824, "reasoning_bytes": 146.884, "flops_per_problem": 8341697691.648}, "parity.runmax.rev24": {"acc": 0.392, "reasoning_bytes": 166.234, "flops_per_problem": 9371315552.256}, "sumd.runmax.rev6": {"acc": 1.0, "reasoning_bytes": 79.542, "flops_per_problem": 4661058945.024}, "sumd.runmax.rev7": {"acc": 0.998, "reasoning_bytes": 87.48, "flops_per_problem": 5055788482.56}, "sumd.runmax.rev8": {"acc": 0.642, "reasoning_bytes": 92.044, "flops_per_problem": 5301511815.168}, "sumd.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 82.542, "flops_per_problem": 4837711233.024}, "sumd.runmax.sumd7": {"acc": 0.996, "reasoning_bytes": 90.48, "flops_per_problem": 5232440770.56}, "sumd.runmax.sumd8": {"acc": 0.754, "reasoning_bytes": 96.344, "flops_per_problem": 5535576096.768}, "add.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 135.832, "flops_per_problem": 7456139771.904}, "add.runmax.sumd7": {"acc": 0.984, "reasoning_bytes": 153.864, "flops_per_problem": 8340814430.208}, "add.runmax.sumd8": {"acc": 0.598, "reasoning_bytes": 171.704, "flops_per_problem": 9217009778.688}, "parity.runmax.sumd16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.runmax.sumd20": {"acc": 0.84, "reasoning_bytes": 149.656, "flops_per_problem": 8508280799.232}, "parity.runmax.sumd24": {"acc": 0.37, "reasoning_bytes": 169.234, "flops_per_problem": 9549027753.984}, "count.runmax.inc16": {"acc": 0.996, "reasoning_bytes": 111.99, "flops_per_problem": 6668182241.28}, "count.runmax.inc18": {"acc": 0.948, "reasoning_bytes": 120.83, "flops_per_problem": 7146909941.76}, "count.runmax.inc20": {"acc": 0.804, "reasoning_bytes": 127.12, "flops_per_problem": 7513198460.928}, "runmax.runmax.inc12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6125683064.832}, "runmax.runmax.inc14": {"acc": 0.998, "reasoning_bytes": 115.436, "flops_per_problem": 6722414493.696}, "runmax.runmax.inc16": {"acc": 0.978, "reasoning_bytes": 122.072, "flops_per_problem": 7105484980.224}, "add.runmax.inc6": {"acc": 1.0, "reasoning_bytes": 136.832, "flops_per_problem": 7477161394.176}, "add.runmax.inc7": {"acc": 0.982, "reasoning_bytes": 154.88, "flops_per_problem": 8365899055.104}, "add.runmax.inc8": {"acc": 0.558, "reasoning_bytes": 172.48, "flops_per_problem": 9232466853.888}, "count.count.cmp16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6801113088.0}, "count.count.cmp18": {"acc": 0.998, "reasoning_bytes": 121.55, "flops_per_problem": 7311196569.6}, "count.count.cmp20": {"acc": 0.996, "reasoning_bytes": 127.26, "flops_per_problem": 7651693854.72}, "add.count.cmp6": {"acc": 1.0, "reasoning_bytes": 131.354, "flops_per_problem": 7346703679.488}, "add.count.cmp7": {"acc": 0.972, "reasoning_bytes": 148.122, "flops_per_problem": 8175556214.784}, "add.count.cmp8": {"acc": 0.836, "reasoning_bytes": 162.836, "flops_per_problem": 8913697800.192}, "sumd.count.cmp6": {"acc": 1.0, "reasoning_bytes": 82.492, "flops_per_problem": 4923829223.424}, "sumd.count.cmp7": {"acc": 0.992, "reasoning_bytes": 89.836, "flops_per_problem": 5292325896.192}, "sumd.count.cmp8": {"acc": 0.938, "reasoning_bytes": 90.872, "flops_per_problem": 5382241910.784}, "add.count.runmax6": {"acc": 0.998, "reasoning_bytes": 132.648, "flops_per_problem": 7448013766.656}, "add.count.runmax7": {"acc": 0.964, "reasoning_bytes": 149.09, "flops_per_problem": 8262469140.48}, "add.count.runmax8": {"acc": 0.398, "reasoning_bytes": 165.61, "flops_per_problem": 9080369233.92}, "sumd.count.runmax6": {"acc": 1.0, "reasoning_bytes": 83.428, "flops_per_problem": 5009328930.816}, "sumd.count.runmax7": {"acc": 0.992, "reasoning_bytes": 91.458, "flops_per_problem": 5408121470.976}, "sumd.count.runmax8": {"acc": 0.688, "reasoning_bytes": 95.89, "flops_per_problem": 5648015278.08}, "inc.count.runmax6": {"acc": 0.988, "reasoning_bytes": 116.0, "flops_per_problem": 6403645440.0}, "inc.count.runmax7": {"acc": 0.796, "reasoning_bytes": 131.002, "flops_per_problem": 7110342918.144}, "inc.count.runmax8": {"acc": 0.802, "reasoning_bytes": 131.798, "flops_per_problem": 7189659795.456}, "parity.count.count16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7596048384.0}, "parity.count.count20": {"acc": 1.0, "reasoning_bytes": 151.83, "flops_per_problem": 8780413648.896}, "parity.count.count24": {"acc": 1.0, "reasoning_bytes": 171.178, "flops_per_problem": 9812063010.816}, "runmax.count.count12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6359482368.0}, "runmax.count.count14": {"acc": 1.0, "reasoning_bytes": 115.704, "flops_per_problem": 6920530034.688}, "runmax.count.count16": {"acc": 1.0, "reasoning_bytes": 123.096, "flops_per_problem": 7335309606.912}, "inc.count.count6": {"acc": 1.0, "reasoning_bytes": 116.0, "flops_per_problem": 6447808512.0}, "inc.count.count7": {"acc": 0.986, "reasoning_bytes": 130.94, "flops_per_problem": 7151767879.68}, "inc.count.count8": {"acc": 0.95, "reasoning_bytes": 131.18, "flops_per_problem": 7206530088.96}, "inc.count.find6": {"acc": 1.0, "reasoning_bytes": 116.0, "flops_per_problem": 6403645440.0}, "inc.count.find7": {"acc": 0.958, "reasoning_bytes": 131.0, "flops_per_problem": 7110254592.0}, "inc.count.find8": {"acc": 0.936, "reasoning_bytes": 128.318, "flops_per_problem": 7035972304.896}, "add.count.find6": {"acc": 1.0, "reasoning_bytes": 132.326, "flops_per_problem": 7433793257.472}, "add.count.find7": {"acc": 0.972, "reasoning_bytes": 149.13, "flops_per_problem": 8264235663.36}, "add.count.find8": {"acc": 0.814, "reasoning_bytes": 164.918, "flops_per_problem": 9049808388.096}, "runmax.count.find12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6315319296.0}, "runmax.count.find14": {"acc": 1.0, "reasoning_bytes": 115.524, "flops_per_problem": 6868417609.728}, "runmax.count.find16": {"acc": 0.998, "reasoning_bytes": 123.084, "flops_per_problem": 7290616578.048}, "parity.count.rev16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7198580736.0}, "parity.count.rev20": {"acc": 1.0, "reasoning_bytes": 147.58, "flops_per_problem": 8416598261.76}, "parity.count.rev24": {"acc": 1.0, "reasoning_bytes": 166.348, "flops_per_problem": 9422103085.056}, "inc.count.rev6": {"acc": 0.988, "reasoning_bytes": 111.0, "flops_per_problem": 6050340864.0}, "inc.count.rev7": {"acc": 0.964, "reasoning_bytes": 126.0, "flops_per_problem": 6756950016.0}, "inc.count.rev8": {"acc": 0.8, "reasoning_bytes": 126.584, "flops_per_problem": 6826904322.048}, "runmax.count.rev12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5962014720.0}, "runmax.count.rev14": {"acc": 1.0, "reasoning_bytes": 111.412, "flops_per_problem": 6554329841.664}, "runmax.count.rev16": {"acc": 1.0, "reasoning_bytes": 118.24, "flops_per_problem": 6944201441.28}, "count.count.sumd16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6712786944.0}, "count.count.sumd18": {"acc": 1.0, "reasoning_bytes": 120.6, "flops_per_problem": 7225078579.2}, "count.count.sumd20": {"acc": 0.992, "reasoning_bytes": 126.27, "flops_per_problem": 7563809341.44}, "runmax.count.sumd12": {"acc": 1.0, "reasoning_bytes": 103.0, "flops_per_problem": 6138667008.0}, "runmax.count.sumd14": {"acc": 1.0, "reasoning_bytes": 114.388, "flops_per_problem": 6729922215.936}, "runmax.count.sumd16": {"acc": 1.0, "reasoning_bytes": 121.252, "flops_per_problem": 7121383686.144}, "sumd.count.sumd6": {"acc": 1.0, "reasoning_bytes": 81.428, "flops_per_problem": 4832676642.816}, "sumd.count.sumd7": {"acc": 0.994, "reasoning_bytes": 89.456, "flops_per_problem": 5231380856.832}, "sumd.count.sumd8": {"acc": 0.722, "reasoning_bytes": 94.334, "flops_per_problem": 5490971394.048}, "parity.count.inc16": {"acc": 1.0, "reasoning_bytes": 128.0, "flops_per_problem": 7375233024.0}, "parity.count.inc20": {"acc": 1.0, "reasoning_bytes": 151.152, "flops_per_problem": 8574348754.944}, "parity.count.inc24": {"acc": 1.0, "reasoning_bytes": 168.462, "flops_per_problem": 9514933862.4}, "count.count.inc16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6712786944.0}, "count.count.inc18": {"acc": 1.0, "reasoning_bytes": 121.25, "flops_per_problem": 7209621504.0}, "count.count.inc20": {"acc": 0.998, "reasoning_bytes": 127.198, "flops_per_problem": 7560629600.256}, "add.count.inc6": {"acc": 0.998, "reasoning_bytes": 131.648, "flops_per_problem": 7271361478.656}, "add.count.inc7": {"acc": 0.942, "reasoning_bytes": 148.092, "flops_per_problem": 8085905178.624}, "add.count.inc8": {"acc": 0.4, "reasoning_bytes": 164.444, "flops_per_problem": 8896385875.968}, "parity.rev.cmp16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 7066091520.0}, "parity.rev.cmp20": {"acc": 0.956, "reasoning_bytes": 145.068, "flops_per_problem": 8217334480.896}, "parity.rev.cmp24": {"acc": 0.938, "reasoning_bytes": 165.054, "flops_per_problem": 9275040055.296}, "sumd.rev.cmp6": {"acc": 1.0, "reasoning_bytes": 81.072, "flops_per_problem": 4728451792.896}, "sumd.rev.cmp7": {"acc": 0.988, "reasoning_bytes": 88.894, "flops_per_problem": 5118235066.368}, "sumd.rev.cmp8": {"acc": 0.718, "reasoning_bytes": 90.178, "flops_per_problem": 5219015196.672}, "add.rev.cmp6": {"acc": 0.994, "reasoning_bytes": 157.346, "flops_per_problem": 8567106011.136}, "add.rev.cmp7": {"acc": 0.958, "reasoning_bytes": 181.806, "flops_per_problem": 9777085857.792}, "add.rev.cmp8": {"acc": 0.842, "reasoning_bytes": 198.046, "flops_per_problem": 10628284907.52}, "runmax.rev.runmax12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5917851648.0}, "runmax.rev.runmax14": {"acc": 1.0, "reasoning_bytes": 111.82, "flops_per_problem": 6528185303.04}, "runmax.rev.runmax16": {"acc": 0.98, "reasoning_bytes": 118.348, "flops_per_problem": 6904807981.056}, "count.rev.runmax16": {"acc": 0.996, "reasoning_bytes": 108.0, "flops_per_problem": 6491971584.0}, "count.rev.runmax18": {"acc": 0.964, "reasoning_bytes": 117.45, "flops_per_problem": 6997638758.4}, "count.rev.runmax20": {"acc": 0.808, "reasoning_bytes": 123.22, "flops_per_problem": 7340785827.84}, "add.rev.runmax6": {"acc": 1.0, "reasoning_bytes": 185.08, "flops_per_problem": 9586919669.76}, "add.rev.runmax7": {"acc": 0.96, "reasoning_bytes": 215.59, "flops_per_problem": 11022661140.48}, "add.rev.runmax8": {"acc": 0.538, "reasoning_bytes": 244.678, "flops_per_problem": 12396485984.256}, "inc.rev.count6": {"acc": 0.98, "reasoning_bytes": 155.998, "flops_per_problem": 8037590777.856}, "inc.rev.count7": {"acc": 0.884, "reasoning_bytes": 182.91, "flops_per_problem": 9270270443.52}, "inc.rev.count8": {"acc": 0.662, "reasoning_bytes": 184.628, "flops_per_problem": 9390305673.216}, "count.rev.count16": {"acc": 1.0, "reasoning_bytes": 108.0, "flops_per_problem": 6536134656.0}, "count.rev.count18": {"acc": 0.996, "reasoning_bytes": 117.522, "flops_per_problem": 7044981571.584}, "count.rev.count20": {"acc": 0.994, "reasoning_bytes": 123.202, "flops_per_problem": 7384153964.544}, "parity.rev.count16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7198580736.0}, "parity.rev.count20": {"acc": 1.0, "reasoning_bytes": 147.736, "flops_per_problem": 8423487700.992}, "parity.rev.count24": {"acc": 0.998, "reasoning_bytes": 166.42, "flops_per_problem": 9425282826.24}, "sumd.rev.find6": {"acc": 1.0, "reasoning_bytes": 85.208, "flops_per_problem": 4911286910.976}, "sumd.rev.find7": {"acc": 0.996, "reasoning_bytes": 93.436, "flops_per_problem": 5318823739.392}, "sumd.rev.find8": {"acc": 0.766, "reasoning_bytes": 96.04, "flops_per_problem": 5477987450.88}, "runmax.rev.find12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5917851648.0}, "runmax.rev.find14": {"acc": 1.0, "reasoning_bytes": 111.316, "flops_per_problem": 6505927114.752}, "runmax.rev.find16": {"acc": 0.994, "reasoning_bytes": 118.226, "flops_per_problem": 6899155107.84}, "count.rev.find16": {"acc": 1.0, "reasoning_bytes": 108.0, "flops_per_problem": 6491971584.0}, "count.rev.find18": {"acc": 0.98, "reasoning_bytes": 117.17, "flops_per_problem": 6985273098.24}, "count.rev.find20": {"acc": 0.944, "reasoning_bytes": 123.2, "flops_per_problem": 7339902566.4}, "count.rev.rev16": {"acc": 0.996, "reasoning_bytes": 103.0, "flops_per_problem": 6138667008.0}, "count.rev.rev18": {"acc": 0.936, "reasoning_bytes": 111.69, "flops_per_problem": 6610770247.68}, "count.rev.rev20": {"acc": 0.802, "reasoning_bytes": 118.12, "flops_per_problem": 6983064944.64}, "sumd.rev.rev6": {"acc": 1.0, "reasoning_bytes": 80.53, "flops_per_problem": 4616277590.016}, "sumd.rev.rev7": {"acc": 0.982, "reasoning_bytes": 88.352, "flops_per_problem": 5005972537.344}, "sumd.rev.rev8": {"acc": 0.344, "reasoning_bytes": 90.778, "flops_per_problem": 5157186895.872}, "parity.rev.rev16": {"acc": 1.0, "reasoning_bytes": 119.0, "flops_per_problem": 6801113088.0}, "parity.rev.rev20": {"acc": 0.73, "reasoning_bytes": 141.656, "flops_per_problem": 7978323935.232}, "parity.rev.rev24": {"acc": 0.436, "reasoning_bytes": 161.168, "flops_per_problem": 9015626170.368}, "sumd.rev.sumd6": {"acc": 1.0, "reasoning_bytes": 84.73, "flops_per_problem": 4810771759.104}, "sumd.rev.sumd7": {"acc": 0.996, "reasoning_bytes": 92.738, "flops_per_problem": 5211065843.712}, "sumd.rev.sumd8": {"acc": 0.61, "reasoning_bytes": 97.12, "flops_per_problem": 5449104801.792}, "parity.rev.sumd16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.rev.sumd20": {"acc": 0.83, "reasoning_bytes": 145.172, "flops_per_problem": 8177764368.384}, "parity.rev.sumd24": {"acc": 0.386, "reasoning_bytes": 164.546, "flops_per_problem": 9208000512.0}, "add.rev.sumd6": {"acc": 0.966, "reasoning_bytes": 191.656, "flops_per_problem": 9832996306.944}, "add.rev.sumd7": {"acc": 0.532, "reasoning_bytes": 224.122, "flops_per_problem": 11355209072.64}, "add.rev.sumd8": {"acc": 0.038, "reasoning_bytes": 253.624, "flops_per_problem": 12746610819.072}, "parity.rev.inc16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 6977765376.0}, "parity.rev.inc20": {"acc": 0.786, "reasoning_bytes": 146.1, "flops_per_problem": 8174584627.2}, "parity.rev.inc24": {"acc": 0.39, "reasoning_bytes": 165.348, "flops_per_problem": 9200227811.328}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 99.0, "flops_per_problem": 5772378488.832}, "runmax.rev.inc14": {"acc": 0.998, "reasoning_bytes": 110.196, "flops_per_problem": 6358510780.416}, "runmax.rev.inc16": {"acc": 0.976, "reasoning_bytes": 117.096, "flops_per_problem": 6753151991.808}, "inc.rev.inc6": {"acc": 0.988, "reasoning_bytes": 170.0, "flops_per_problem": 8695797202.944}, "inc.rev.inc7": {"acc": 0.76, "reasoning_bytes": 199.858, "flops_per_problem": 10101596110.848}, "inc.rev.inc8": {"acc": 0.026, "reasoning_bytes": 206.718, "flops_per_problem": 10457462145.024}, "parity.sumd.cmp16": {"acc": 1.0, "reasoning_bytes": 126.0, "flops_per_problem": 7242743808.0}, "parity.sumd.cmp20": {"acc": 0.958, "reasoning_bytes": 147.744, "flops_per_problem": 8379677933.568}, "parity.sumd.cmp24": {"acc": 0.934, "reasoning_bytes": 168.054, "flops_per_problem": 9451692343.296}, "runmax.sumd.cmp12": {"acc": 1.0, "reasoning_bytes": 102.0, "flops_per_problem": 6006177792.0}, "runmax.sumd.cmp14": {"acc": 1.0, "reasoning_bytes": 113.208, "flops_per_problem": 6589483646.976}, "runmax.sumd.cmp16": {"acc": 0.994, "reasoning_bytes": 120.024, "flops_per_problem": 6978825289.728}, "count.sumd.cmp16": {"acc": 1.0, "reasoning_bytes": 110.0, "flops_per_problem": 6580297728.0}, "count.sumd.cmp18": {"acc": 0.984, "reasoning_bytes": 118.45, "flops_per_problem": 7041801830.4}, "count.sumd.cmp20": {"acc": 0.946, "reasoning_bytes": 125.03, "flops_per_problem": 7420720988.16}, "sumd.sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 84.36, "flops_per_problem": 4917999697.92}, "sumd.sumd.runmax7": {"acc": 0.97, "reasoning_bytes": 92.802, "flops_per_problem": 5334987423.744}, "sumd.sumd.runmax8": {"acc": 0.748, "reasoning_bytes": 98.868, "flops_per_problem": 5647043690.496}, "count.sumd.runmax16": {"acc": 0.996, "reasoning_bytes": 110.99, "flops_per_problem": 6668182241.28}, "count.sumd.runmax18": {"acc": 0.956, "reasoning_bytes": 120.33, "flops_per_problem": 7168991477.76}, "count.sumd.runmax20": {"acc": 0.806, "reasoning_bytes": 126.23, "flops_per_problem": 7517879746.56}, "add.sumd.runmax6": {"acc": 0.998, "reasoning_bytes": 151.426, "flops_per_problem": 8144818716.672}, "add.sumd.runmax7": {"acc": 0.882, "reasoning_bytes": 171.346, "flops_per_problem": 9112873254.912}, "add.sumd.runmax8": {"acc": 0.19, "reasoning_bytes": 190.762, "flops_per_problem": 10058757931.008}, "parity.sumd.count16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7375233024.0}, "parity.sumd.count20": {"acc": 1.0, "reasoning_bytes": 150.508, "flops_per_problem": 8590070808.576}, "parity.sumd.count24": {"acc": 1.0, "reasoning_bytes": 169.396, "flops_per_problem": 9600875200.512}, "sumd.sumd.count6": {"acc": 1.0, "reasoning_bytes": 84.184, "flops_per_problem": 4954390069.248}, "sumd.sumd.count7": {"acc": 0.996, "reasoning_bytes": 92.444, "flops_per_problem": 5363340115.968}, "sumd.sumd.count8": {"acc": 0.804, "reasoning_bytes": 97.454, "flops_per_problem": 5628760178.688}, "add.sumd.count6": {"acc": 0.998, "reasoning_bytes": 150.516, "flops_per_problem": 8148793393.152}, "add.sumd.count7": {"acc": 0.918, "reasoning_bytes": 170.2, "flops_per_problem": 9106425446.4}, "add.sumd.count8": {"acc": 0.396, "reasoning_bytes": 189.63, "flops_per_problem": 10052928405.504}, "runmax.sumd.find12": {"acc": 1.0, "reasoning_bytes": 103.0, "flops_per_problem": 6094503936.0}, "runmax.sumd.find14": {"acc": 1.0, "reasoning_bytes": 113.92, "flops_per_problem": 6665090826.24}, "runmax.sumd.find16": {"acc": 0.994, "reasoning_bytes": 121.096, "flops_per_problem": 7070331174.912}, "sumd.sumd.find6": {"acc": 1.0, "reasoning_bytes": 84.064, "flops_per_problem": 4904927428.608}, "sumd.sumd.find7": {"acc": 0.996, "reasoning_bytes": 92.352, "flops_per_problem": 5315114041.344}, "sumd.sumd.find8": {"acc": 0.866, "reasoning_bytes": 96.756, "flops_per_problem": 5553771282.432}, "parity.sumd.find16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.sumd.find20": {"acc": 0.954, "reasoning_bytes": 150.04, "flops_per_problem": 8524179505.152}, "parity.sumd.find24": {"acc": 0.842, "reasoning_bytes": 169.282, "flops_per_problem": 9551147581.44}, "count.sumd.rev16": {"acc": 0.996, "reasoning_bytes": 105.99, "flops_per_problem": 6314877665.28}, "count.sumd.rev18": {"acc": 0.94, "reasoning_bytes": 114.66, "flops_per_problem": 6786097643.52}, "count.sumd.rev20": {"acc": 0.806, "reasoning_bytes": 121.12, "flops_per_problem": 7159717232.64}, "parity.sumd.rev16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.sumd.rev20": {"acc": 0.838, "reasoning_bytes": 145.064, "flops_per_problem": 8172994756.608}, "parity.sumd.rev24": {"acc": 0.378, "reasoning_bytes": 164.396, "flops_per_problem": 9201906008.064}, "add.sumd.rev6": {"acc": 1.0, "reasoning_bytes": 145.448, "flops_per_problem": 7792309075.968}, "add.sumd.rev7": {"acc": 0.92, "reasoning_bytes": 165.34, "flops_per_problem": 8759215374.336}, "add.sumd.rev8": {"acc": 0.05, "reasoning_bytes": 184.758, "flops_per_problem": 9704393441.28}, "parity.sumd.sumd16": {"acc": 1.0, "reasoning_bytes": 125.0, "flops_per_problem": 7154417664.0}, "parity.sumd.sumd20": {"acc": 0.824, "reasoning_bytes": 147.656, "flops_per_problem": 8331628511.232}, "parity.sumd.sumd24": {"acc": 0.362, "reasoning_bytes": 167.336, "flops_per_problem": 9377410056.192}, "add.sumd.sumd6": {"acc": 1.0, "reasoning_bytes": 149.642, "flops_per_problem": 7986449940.48}, "add.sumd.sumd7": {"acc": 0.858, "reasoning_bytes": 169.582, "flops_per_problem": 8956889284.608}, "add.sumd.sumd8": {"acc": 0.098, "reasoning_bytes": 189.25, "flops_per_problem": 9915581251.584}, "count.sumd.sumd16": {"acc": 0.992, "reasoning_bytes": 108.98, "flops_per_problem": 6491088322.56}, "count.sumd.sumd18": {"acc": 0.952, "reasoning_bytes": 117.93, "flops_per_problem": 6974673960.96}, "count.sumd.sumd20": {"acc": 0.808, "reasoning_bytes": 124.15, "flops_per_problem": 7337694412.8}, "inc.sumd.inc6": {"acc": 1.0, "reasoning_bytes": 135.534, "flops_per_problem": 7045511528.448}, "inc.sumd.inc7": {"acc": 0.858, "reasoning_bytes": 153.438, "flops_per_problem": 7880546893.824}, "inc.sumd.inc8": {"acc": 0.126, "reasoning_bytes": 156.71, "flops_per_problem": 8069299863.552}, "sumd.sumd.inc6": {"acc": 1.0, "reasoning_bytes": 83.764, "flops_per_problem": 4773586452.48}, "sumd.sumd.inc7": {"acc": 0.996, "reasoning_bytes": 92.318, "flops_per_problem": 5198258552.832}, "sumd.sumd.inc8": {"acc": 0.668, "reasoning_bytes": 97.398, "flops_per_problem": 5467123335.168}, "parity.sumd.inc16": {"acc": 1.0, "reasoning_bytes": 126.0, "flops_per_problem": 7154417664.0}, "parity.sumd.inc20": {"acc": 0.848, "reasoning_bytes": 148.98, "flops_per_problem": 8345937346.56}, "parity.sumd.inc24": {"acc": 0.37, "reasoning_bytes": 168.468, "flops_per_problem": 9383239581.696}, "inc.inc.cmp6": {"acc": 0.996, "reasoning_bytes": 144.636, "flops_per_problem": 7668299169.792}, "inc.inc.cmp7": {"acc": 0.99, "reasoning_bytes": 165.818, "flops_per_problem": 8692087504.896}, "inc.inc.cmp8": {"acc": 0.888, "reasoning_bytes": 181.314, "flops_per_problem": 9464676286.464}, "runmax.inc.cmp12": {"acc": 1.0, "reasoning_bytes": 105.568, "flops_per_problem": 6150856015.872}, "runmax.inc.cmp14": {"acc": 1.0, "reasoning_bytes": 117.184, "flops_per_problem": 6756243406.848}, "runmax.inc.cmp16": {"acc": 0.968, "reasoning_bytes": 123.97, "flops_per_problem": 7145496723.456}, "sumd.inc.cmp6": {"acc": 1.0, "reasoning_bytes": 88.12, "flops_per_problem": 5039713124.352}, "sumd.inc.cmp7": {"acc": 0.998, "reasoning_bytes": 95.956, "flops_per_problem": 5430114680.832}, "sumd.inc.cmp8": {"acc": 0.958, "reasoning_bytes": 98.09, "flops_per_problem": 5568521748.48}, "sumd.inc.runmax6": {"acc": 1.0, "reasoning_bytes": 93.522, "flops_per_problem": 5278458691.584}, "sumd.inc.runmax7": {"acc": 0.996, "reasoning_bytes": 101.48, "flops_per_problem": 5674071490.56}, "sumd.inc.runmax8": {"acc": 0.666, "reasoning_bytes": 106.2, "flops_per_problem": 5926684262.4}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.648, "flops_per_problem": 6343936966.656}, "runmax.inc.runmax14": {"acc": 0.998, "reasoning_bytes": 121.692, "flops_per_problem": 6964163149.824}, "runmax.inc.runmax16": {"acc": 0.978, "reasoning_bytes": 128.644, "flops_per_problem": 7359510970.368}, "add.inc.runmax6": {"acc": 1.0, "reasoning_bytes": 192.872, "flops_per_problem": 9931038326.784}, "add.inc.runmax7": {"acc": 0.974, "reasoning_bytes": 220.826, "flops_per_problem": 11253898985.472}, "add.inc.runmax8": {"acc": 0.542, "reasoning_bytes": 241.994, "flops_per_problem": 12282191953.92}, "runmax.inc.count12": {"acc": 1.0, "reasoning_bytes": 108.928, "flops_per_problem": 6356302626.816}, "runmax.inc.count14": {"acc": 1.0, "reasoning_bytes": 120.794, "flops_per_problem": 6968667783.168}, "runmax.inc.count16": {"acc": 1.0, "reasoning_bytes": 127.734, "flops_per_problem": 7363485646.848}, "sumd.inc.count6": {"acc": 1.0, "reasoning_bytes": 92.388, "flops_per_problem": 5272540839.936}, "sumd.inc.count7": {"acc": 0.996, "reasoning_bytes": 100.444, "flops_per_problem": 5672481619.968}, "sumd.inc.count8": {"acc": 0.594, "reasoning_bytes": 103.604, "flops_per_problem": 5856199999.488}, "inc.inc.count6": {"acc": 0.978, "reasoning_bytes": 165.0, "flops_per_problem": 8435146752.0}, "inc.inc.count7": {"acc": 0.888, "reasoning_bytes": 189.768, "flops_per_problem": 9573140791.296}, "inc.inc.count8": {"acc": 0.682, "reasoning_bytes": 189.43, "flops_per_problem": 9602376744.96}, "parity.inc.find16": {"acc": 1.0, "reasoning_bytes": 128.0, "flops_per_problem": 7331069952.0}, "parity.inc.find20": {"acc": 0.962, "reasoning_bytes": 151.412, "flops_per_problem": 8540608167.936}, "parity.inc.find24": {"acc": 0.814, "reasoning_bytes": 170.486, "flops_per_problem": 9560156848.128}, "sumd.inc.find6": {"acc": 1.0, "reasoning_bytes": 92.1, "flops_per_problem": 5215658803.2}, "sumd.inc.find7": {"acc": 0.998, "reasoning_bytes": 100.356, "flops_per_problem": 5624432197.632}, "sumd.inc.find8": {"acc": 0.804, "reasoning_bytes": 103.536, "flops_per_problem": 5809033838.592}, "count.inc.find16": {"acc": 1.0, "reasoning_bytes": 111.99, "flops_per_problem": 6668182241.28}, "count.inc.find18": {"acc": 0.984, "reasoning_bytes": 120.9, "flops_per_problem": 7150001356.8}, "count.inc.find20": {"acc": 0.954, "reasoning_bytes": 127.224, "flops_per_problem": 7517614768.128}, "sumd.inc.rev6": {"acc": 1.0, "reasoning_bytes": 87.524, "flops_per_problem": 4925154115.584}, "sumd.inc.rev7": {"acc": 0.994, "reasoning_bytes": 95.464, "flops_per_problem": 5320060305.408}, "sumd.inc.rev8": {"acc": 0.44, "reasoning_bytes": 98.6, "flops_per_problem": 5502630445.056}, "count.inc.rev16": {"acc": 0.998, "reasoning_bytes": 107.01, "flops_per_problem": 6315760926.72}, "count.inc.rev18": {"acc": 0.942, "reasoning_bytes": 115.61, "flops_per_problem": 6783889489.92}, "count.inc.rev20": {"acc": 0.792, "reasoning_bytes": 122.148, "flops_per_problem": 7159805558.784}, "parity.inc.rev16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 6977765376.0}, "parity.inc.rev20": {"acc": 0.814, "reasoning_bytes": 146.184, "flops_per_problem": 8178294325.248}, "parity.inc.rev24": {"acc": 0.368, "reasoning_bytes": 165.51, "flops_per_problem": 9206852272.128}, "count.inc.sumd16": {"acc": 0.996, "reasoning_bytes": 109.99, "flops_per_problem": 6491529953.28}, "count.inc.sumd18": {"acc": 0.946, "reasoning_bytes": 118.71, "flops_per_problem": 6964958085.12}, "count.inc.sumd20": {"acc": 0.814, "reasoning_bytes": 125.092, "flops_per_problem": 7335132954.624}, "sumd.inc.sumd6": {"acc": 1.0, "reasoning_bytes": 91.758, "flops_per_problem": 5122651373.568}, "sumd.inc.sumd7": {"acc": 0.994, "reasoning_bytes": 99.742, "flops_per_problem": 5521267261.44}, "sumd.inc.sumd8": {"acc": 0.644, "reasoning_bytes": 104.498, "flops_per_problem": 5776883122.176}, "add.inc.sumd6": {"acc": 0.97, "reasoning_bytes": 198.522, "flops_per_problem": 10136219959.296}, "add.inc.sumd7": {"acc": 0.686, "reasoning_bytes": 228.242, "flops_per_problem": 11537160929.28}, "add.inc.sumd8": {"acc": 0.044, "reasoning_bytes": 248.546, "flops_per_problem": 12533921464.32}, "parity.inc.inc16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7154417664.0}, "parity.inc.inc20": {"acc": 0.82, "reasoning_bytes": 149.896, "flops_per_problem": 8342227648.512}, "parity.inc.inc24": {"acc": 0.326, "reasoning_bytes": 169.88, "flops_per_problem": 9398608330.752}, "sumd.inc.inc6": {"acc": 0.998, "reasoning_bytes": 94.518, "flops_per_problem": 5234118967.296}, "sumd.inc.inc7": {"acc": 0.99, "reasoning_bytes": 102.448, "flops_per_problem": 5628495200.256}, "sumd.inc.inc8": {"acc": 0.5, "reasoning_bytes": 106.32, "flops_per_problem": 5843657687.04}, "runmax.inc.inc12": {"acc": 1.0, "reasoning_bytes": 110.06, "flops_per_problem": 6270272962.56}, "runmax.inc.inc14": {"acc": 0.996, "reasoning_bytes": 121.18, "flops_per_problem": 6851105685.504}, "runmax.inc.inc16": {"acc": 0.958, "reasoning_bytes": 129.104, "flops_per_problem": 7289909968.896}, "count.inc.cmp16": {"acc": 0.882, "reasoning_bytes": 110.512, "flops_per_problem": 6596108107.776}, "count.inc.cmp18": {"acc": 0.658, "reasoning_bytes": 120.022, "flops_per_problem": 7159893884.928}, "count.inc.cmp20": {"acc": 0.72, "reasoning_bytes": 130.502, "flops_per_problem": 7620956356.608}, "inc.rev.sumd6": {"acc": 0.928, "reasoning_bytes": 166.262, "flops_per_problem": 8405557493.76}, "inc.rev.sumd7": {"acc": 0.558, "reasoning_bytes": 196.354, "flops_per_problem": 9776997531.648}, "inc.rev.sumd8": {"acc": 0.076, "reasoning_bytes": 201.608, "flops_per_problem": 10053635014.656}, "runmax.inc.find12": {"acc": 0.92, "reasoning_bytes": 105.98, "flops_per_problem": 6181946818.56}, "runmax.inc.find14": {"acc": 0.914, "reasoning_bytes": 116.4, "flops_per_problem": 6730452172.8}, "runmax.inc.find16": {"acc": 0.884, "reasoning_bytes": 124.764, "flops_per_problem": 7188158251.008}, "inc.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 120.0, "flops_per_problem": 6491971584.0}, "inc.runmax.cmp7": {"acc": 0.974, "reasoning_bytes": 136.0, "flops_per_problem": 7242743808.0}, "inc.runmax.cmp8": {"acc": 0.974, "reasoning_bytes": 136.256, "flops_per_problem": 7298212626.432}} +{"step": 12000, "train_loss": 1.0442763566970825} +{"step": 12020, "train_loss": 1.0312539339065552} +{"step": 12040, "train_loss": 1.013219952583313} +{"step": 12060, "train_loss": 0.9609869122505188} +{"step": 12080, "train_loss": 0.9376087784767151} +{"step": 12100, "train_loss": 1.0597087144851685} +{"step": 12120, "train_loss": 1.0114226341247559} +{"step": 12140, "train_loss": 1.0060842037200928} +{"step": 12160, "train_loss": 0.9924350380897522} +{"step": 12180, "train_loss": 0.9773762822151184} +{"step": 12200, "train_loss": 0.9606301188468933} +{"step": 12207, "tokens": 399998976, "val_loss": 1.8132692694664, "val_bpb": 0.6536541128068258, "lr": 5.9999999999999995e-05, "elapsed": 4231.428244829178, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.976, "reasoning_bytes": 79.0, "flops_per_problem": 4928775487.488}, "add9": {"acc": 0.182, "reasoning_bytes": 89.026, "flops_per_problem": 5503778684.928}, "add10": {"acc": 0.0, "reasoning_bytes": 98.776, "flops_per_problem": 6065886265.344}, "reach14": {"acc": 0.526, "reasoning_bytes": 9.116, "flops_per_problem": 4686408548.352}, "reach16": {"acc": 0.516, "reasoning_bytes": 9.338, "flops_per_problem": 5226169614.336}, "reach18": {"acc": 0.53, "reasoning_bytes": 9.676, "flops_per_problem": 5773438402.56}, "parity24": {"acc": 0.784, "reasoning_bytes": 142.988, "flops_per_problem": 7860496859.136}, "parity28": {"acc": 0.498, "reasoning_bytes": 166.736, "flops_per_problem": 9085933780.992}, "parity32": {"acc": 0.502, "reasoning_bytes": 187.142, "flops_per_problem": 10163777716.224}, "cmp8": {"acc": 0.996, "reasoning_bytes": 5.792, "flops_per_problem": 1359869313.024}, "cmp9": {"acc": 0.998, "reasoning_bytes": 5.708, "flops_per_problem": 1444485758.976}, "cmp10": {"acc": 0.998, "reasoning_bytes": 5.732, "flops_per_problem": 1533871816.704}, "runmax12": {"acc": 1.0, "reasoning_bytes": 71.0, "flops_per_problem": 4151328768.0}, "runmax14": {"acc": 1.0, "reasoning_bytes": 82.996, "flops_per_problem": 4769435123.712}, "runmax16": {"acc": 0.976, "reasoning_bytes": 89.624, "flops_per_problem": 5150474108.928}, "count16": {"acc": 0.988, "reasoning_bytes": 79.1, "flops_per_problem": 4729865011.2}, "count18": {"acc": 0.93, "reasoning_bytes": 89.06, "flops_per_problem": 5267682902.016}, "count20": {"acc": 0.672, "reasoning_bytes": 98.72, "flops_per_problem": 5787217281.024}, "brackets16": {"acc": 0.926, "reasoning_bytes": 53.532, "flops_per_problem": 3644866658.304}, "brackets18": {"acc": 0.89, "reasoning_bytes": 57.348, "flops_per_problem": 3901807411.2}, "brackets20": {"acc": 0.9, "reasoning_bytes": 62.428, "flops_per_problem": 4214570287.104}, "sumd8": {"acc": 0.96, "reasoning_bytes": 58.566, "flops_per_problem": 3381301444.608}, "sumd9": {"acc": 0.83, "reasoning_bytes": 66.434, "flops_per_problem": 3774794416.128}, "sumd10": {"acc": 0.184, "reasoning_bytes": 64.944, "flops_per_problem": 3730101387.264}, "inc8": {"acc": 0.996, "reasoning_bytes": 63.0, "flops_per_problem": 3797405908.992}, "inc9": {"acc": 0.528, "reasoning_bytes": 69.612, "flops_per_problem": 4144615981.056}, "inc10": {"acc": 0.0, "reasoning_bytes": 64.158, "flops_per_problem": 3671364501.504}, "add.cmp6": {"acc": 1.0, "reasoning_bytes": 92.622, "flops_per_problem": 5532043051.008}, "add.cmp7": {"acc": 0.996, "reasoning_bytes": 105.494, "flops_per_problem": 6230261219.328}, "add.cmp8": {"acc": 0.998, "reasoning_bytes": 118.198, "flops_per_problem": 6925299646.464}, "add.runmax6": {"acc": 1.0, "reasoning_bytes": 120.832, "flops_per_problem": 6572878331.904}, "add.runmax7": {"acc": 0.866, "reasoning_bytes": 138.848, "flops_per_problem": 7456846381.056}, "add.runmax8": {"acc": 0.562, "reasoning_bytes": 156.758, "flops_per_problem": 8336133144.576}, "add.count6": {"acc": 0.986, "reasoning_bytes": 115.648, "flops_per_problem": 6388100038.656}, "add.count7": {"acc": 0.872, "reasoning_bytes": 132.082, "flops_per_problem": 7202202107.904}, "add.count8": {"acc": 0.37, "reasoning_bytes": 148.892, "flops_per_problem": 8032909492.224}, "add.find6": {"acc": 0.896, "reasoning_bytes": 107.744, "flops_per_problem": 5994872045.568}, "add.find7": {"acc": 0.778, "reasoning_bytes": 121.774, "flops_per_problem": 6702806089.728}, "add.find8": {"acc": 0.482, "reasoning_bytes": 139.268, "flops_per_problem": 7563721015.296}, "add.rev6": {"acc": 1.0, "reasoning_bytes": 123.248, "flops_per_problem": 6794576953.344}, "add.rev7": {"acc": 0.43, "reasoning_bytes": 145.87, "flops_per_problem": 7926123184.128}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 168.612, "flops_per_problem": 9050161692.672}, "add.sumd6": {"acc": 0.998, "reasoning_bytes": 126.476, "flops_per_problem": 6777794985.984}, "add.sumd7": {"acc": 0.692, "reasoning_bytes": 146.322, "flops_per_problem": 7742669783.04}, "add.sumd8": {"acc": 0.046, "reasoning_bytes": 165.992, "flops_per_problem": 8699771879.424}, "add.inc6": {"acc": 1.0, "reasoning_bytes": 131.04, "flops_per_problem": 7138695610.368}, "add.inc7": {"acc": 0.552, "reasoning_bytes": 151.032, "flops_per_problem": 8154092961.792}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 168.926, "flops_per_problem": 9067031986.176}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5122916352.0}, "runmax.cmp14": {"acc": 0.998, "reasoning_bytes": 96.864, "flops_per_problem": 5646867038.208}, "runmax.cmp16": {"acc": 0.966, "reasoning_bytes": 105.012, "flops_per_problem": 6095033892.864}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.runmax14": {"acc": 1.0, "reasoning_bytes": 99.136, "flops_per_problem": 5791368609.792}, "runmax.runmax16": {"acc": 0.97, "reasoning_bytes": 106.0, "flops_per_problem": 6182830080.0}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5255405568.0}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 98.716, "flops_per_problem": 5816983191.552}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 106.072, "flops_per_problem": 6230172893.184}, "runmax.find12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.find14": {"acc": 1.0, "reasoning_bytes": 97.864, "flops_per_problem": 5735193182.208}, "runmax.find16": {"acc": 0.986, "reasoning_bytes": 106.012, "flops_per_problem": 6183360036.864}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 83.0, "flops_per_problem": 4857937920.0}, "runmax.rev14": {"acc": 0.992, "reasoning_bytes": 92.852, "flops_per_problem": 5381358649.344}, "runmax.rev16": {"acc": 0.95, "reasoning_bytes": 101.0, "flops_per_problem": 5829525504.0}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 86.0, "flops_per_problem": 5034590208.0}, "runmax.sumd14": {"acc": 1.0, "reasoning_bytes": 97.064, "flops_per_problem": 5611536580.608}, "runmax.sumd16": {"acc": 0.97, "reasoning_bytes": 104.0, "flops_per_problem": 6006177792.0}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5065769336.832}, "runmax.inc14": {"acc": 0.994, "reasoning_bytes": 96.396, "flops_per_problem": 5572319772.672}, "runmax.inc16": {"acc": 0.956, "reasoning_bytes": 105.0, "flops_per_problem": 6041508249.6}, "count.cmp16": {"acc": 1.0, "reasoning_bytes": 95.01, "flops_per_problem": 5697477918.72}, "count.cmp18": {"acc": 0.988, "reasoning_bytes": 104.48, "flops_per_problem": 6204116680.704}, "count.cmp20": {"acc": 0.906, "reasoning_bytes": 110.456, "flops_per_problem": 6554153189.376}, "count.runmax16": {"acc": 0.996, "reasoning_bytes": 96.03, "flops_per_problem": 5786687324.16}, "count.runmax18": {"acc": 0.976, "reasoning_bytes": 105.85, "flops_per_problem": 6308694835.2}, "count.runmax20": {"acc": 0.734, "reasoning_bytes": 111.69, "flops_per_problem": 6656964820.992}, "count.count16": {"acc": 1.0, "reasoning_bytes": 96.0, "flops_per_problem": 5829525504.0}, "count.count18": {"acc": 1.0, "reasoning_bytes": 105.95, "flops_per_problem": 6357274214.4}, "count.count20": {"acc": 0.99, "reasoning_bytes": 112.776, "flops_per_problem": 6752268730.368}, "count.find16": {"acc": 1.0, "reasoning_bytes": 96.02, "flops_per_problem": 5786245693.44}, "count.find18": {"acc": 0.976, "reasoning_bytes": 105.85, "flops_per_problem": 6308694835.2}, "count.find20": {"acc": 0.9, "reasoning_bytes": 112.234, "flops_per_problem": 6677456486.4}, "count.rev16": {"acc": 0.998, "reasoning_bytes": 91.02, "flops_per_problem": 5432941117.44}, "count.rev18": {"acc": 0.912, "reasoning_bytes": 100.264, "flops_per_problem": 5930747265.024}, "count.rev20": {"acc": 0.672, "reasoning_bytes": 106.966, "flops_per_problem": 6313729425.408}, "count.sumd16": {"acc": 0.996, "reasoning_bytes": 94.014, "flops_per_problem": 5609328427.008}, "count.sumd18": {"acc": 0.836, "reasoning_bytes": 103.59, "flops_per_problem": 6122326671.36}, "count.sumd20": {"acc": 0.426, "reasoning_bytes": 110.71, "flops_per_problem": 6528273629.184}, "count.inc16": {"acc": 0.998, "reasoning_bytes": 95.01, "flops_per_problem": 5609151774.72}, "count.inc18": {"acc": 0.944, "reasoning_bytes": 104.77, "flops_per_problem": 6128509501.44}, "count.inc20": {"acc": 0.704, "reasoning_bytes": 110.67, "flops_per_problem": 6476337856.512}, "parity.cmp16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6359482368.0}, "parity.cmp20": {"acc": 0.988, "reasoning_bytes": 134.808, "flops_per_problem": 7587569074.176}, "parity.cmp24": {"acc": 0.946, "reasoning_bytes": 153.036, "flops_per_problem": 8569225838.592}, "parity.runmax16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.runmax20": {"acc": 0.916, "reasoning_bytes": 135.988, "flops_per_problem": 7683844571.136}, "parity.runmax24": {"acc": 0.494, "reasoning_bytes": 154.216, "flops_per_problem": 8665501335.552}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6491971584.0}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 135.952, "flops_per_problem": 7726417772.544}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 154.456, "flops_per_problem": 8720263544.832}, "parity.find16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.find20": {"acc": 0.952, "reasoning_bytes": 136.0, "flops_per_problem": 7684374528.0}, "parity.find24": {"acc": 0.85, "reasoning_bytes": 155.398, "flops_per_problem": 8717702086.656}, "parity.rev16": {"acc": 1.0, "reasoning_bytes": 107.0, "flops_per_problem": 6094503936.0}, "parity.rev20": {"acc": 0.89, "reasoning_bytes": 130.94, "flops_per_problem": 7328420167.68}, "parity.rev24": {"acc": 0.484, "reasoning_bytes": 151.88, "flops_per_problem": 8434175164.416}, "parity.sumd16": {"acc": 1.0, "reasoning_bytes": 110.0, "flops_per_problem": 6271156224.0}, "parity.sumd20": {"acc": 0.912, "reasoning_bytes": 133.976, "flops_per_problem": 7506662326.272}, "parity.sumd24": {"acc": 0.516, "reasoning_bytes": 153.41, "flops_per_problem": 8542816321.536}, "parity.inc16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6271156224.0}, "parity.inc20": {"acc": 0.872, "reasoning_bytes": 135.0, "flops_per_problem": 7507722240.0}, "parity.inc24": {"acc": 0.54, "reasoning_bytes": 155.928, "flops_per_problem": 8608619298.816}, "sumd.cmp6": {"acc": 1.0, "reasoning_bytes": 62.088, "flops_per_problem": 3713407746.048}, "sumd.cmp7": {"acc": 1.0, "reasoning_bytes": 70.084, "flops_per_problem": 4110875394.048}, "sumd.cmp8": {"acc": 0.986, "reasoning_bytes": 77.696, "flops_per_problem": 4491119443.968}, "sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.998, "reasoning_bytes": 75.48, "flops_per_problem": 4349179330.56}, "sumd.runmax8": {"acc": 0.946, "reasoning_bytes": 83.474, "flops_per_problem": 4746382000.128}, "sumd.count6": {"acc": 1.0, "reasoning_bytes": 66.428, "flops_per_problem": 3949415202.816}, "sumd.count7": {"acc": 0.992, "reasoning_bytes": 74.46, "flops_per_problem": 4348296069.12}, "sumd.count8": {"acc": 0.934, "reasoning_bytes": 82.392, "flops_per_problem": 4742760628.224}, "sumd.find6": {"acc": 1.0, "reasoning_bytes": 66.24, "flops_per_problem": 3896949473.28}, "sumd.find7": {"acc": 0.998, "reasoning_bytes": 74.44, "flops_per_problem": 4303249735.68}, "sumd.find8": {"acc": 0.94, "reasoning_bytes": 81.634, "flops_per_problem": 4665121947.648}, "sumd.rev6": {"acc": 1.0, "reasoning_bytes": 61.544, "flops_per_problem": 3601145217.024}, "sumd.rev7": {"acc": 0.998, "reasoning_bytes": 69.48, "flops_per_problem": 3995874754.56}, "sumd.rev8": {"acc": 0.93, "reasoning_bytes": 77.428, "flops_per_problem": 4390957596.672}, "sumd.sumd6": {"acc": 1.0, "reasoning_bytes": 65.744, "flops_per_problem": 3795639386.112}, "sumd.sumd7": {"acc": 0.994, "reasoning_bytes": 73.742, "flops_per_problem": 4195668492.288}, "sumd.sumd8": {"acc": 0.95, "reasoning_bytes": 81.81, "flops_per_problem": 4597464121.344}, "sumd.inc6": {"acc": 1.0, "reasoning_bytes": 68.538, "flops_per_problem": 3910021742.592}, "sumd.inc7": {"acc": 0.998, "reasoning_bytes": 76.48, "flops_per_problem": 4305016258.56}, "sumd.inc8": {"acc": 0.928, "reasoning_bytes": 84.358, "flops_per_problem": 4697096011.776}, "inc.cmp6": {"acc": 1.0, "reasoning_bytes": 78.624, "flops_per_problem": 4576354172.928}, "inc.cmp7": {"acc": 0.998, "reasoning_bytes": 89.788, "flops_per_problem": 5157716852.736}, "inc.cmp8": {"acc": 0.976, "reasoning_bytes": 100.584, "flops_per_problem": 5722827522.048}, "inc.runmax6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5520384000.0}, "inc.runmax7": {"acc": 0.974, "reasoning_bytes": 120.0, "flops_per_problem": 6271156224.0}, "inc.runmax8": {"acc": 0.926, "reasoning_bytes": 135.38, "flops_per_problem": 6994547343.36}, "inc.count6": {"acc": 0.988, "reasoning_bytes": 99.0, "flops_per_problem": 5343731712.0}, "inc.count7": {"acc": 0.916, "reasoning_bytes": 114.0, "flops_per_problem": 6050340864.0}, "inc.count8": {"acc": 0.602, "reasoning_bytes": 124.286, "flops_per_problem": 6548765294.592}, "inc.find6": {"acc": 0.934, "reasoning_bytes": 91.88, "flops_per_problem": 4985127567.36}, "inc.find7": {"acc": 0.862, "reasoning_bytes": 102.564, "flops_per_problem": 5501128900.608}, "inc.find8": {"acc": 0.26, "reasoning_bytes": 90.538, "flops_per_problem": 5014186868.736}, "inc.rev6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5608710144.0}, "inc.rev7": {"acc": 0.966, "reasoning_bytes": 123.996, "flops_per_problem": 6579237814.272}, "inc.rev8": {"acc": 0.008, "reasoning_bytes": 143.402, "flops_per_problem": 7493236752.384}, "inc.sumd6": {"acc": 0.996, "reasoning_bytes": 109.572, "flops_per_problem": 5722297565.184}, "inc.sumd7": {"acc": 0.942, "reasoning_bytes": 127.454, "flops_per_problem": 6556096364.544}, "inc.sumd8": {"acc": 0.116, "reasoning_bytes": 143.828, "flops_per_problem": 7323473903.616}, "inc.inc6": {"acc": 1.0, "reasoning_bytes": 113.0, "flops_per_problem": 6006177792.0}, "inc.inc7": {"acc": 0.992, "reasoning_bytes": 131.0, "flops_per_problem": 6889350905.856}, "inc.inc8": {"acc": 0.112, "reasoning_bytes": 147.166, "flops_per_problem": 7683756244.992}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 115.22, "flops_per_problem": 6766665891.84}, "runmax.runmax.cmp16": {"acc": 0.992, "reasoning_bytes": 122.036, "flops_per_problem": 7156007534.592}, "sumd.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 83.338, "flops_per_problem": 4917028110.336}, "sumd.runmax.cmp7": {"acc": 0.996, "reasoning_bytes": 91.532, "flops_per_problem": 5323063394.304}, "sumd.runmax.cmp8": {"acc": 0.826, "reasoning_bytes": 96.43, "flops_per_problem": 5583537192.96}, "add.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 137.024, "flops_per_problem": 7552945225.728}, "add.runmax.cmp7": {"acc": 0.946, "reasoning_bytes": 154.928, "flops_per_problem": 8431967010.816}, "add.runmax.cmp8": {"acc": 0.894, "reasoning_bytes": 171.184, "flops_per_problem": 9238208053.248}, "count.runmax.runmax16": {"acc": 0.996, "reasoning_bytes": 113.02, "flops_per_problem": 6846159421.44}, "count.runmax.runmax18": {"acc": 0.976, "reasoning_bytes": 122.85, "flops_per_problem": 7368608563.2}, "count.runmax.runmax20": {"acc": 0.794, "reasoning_bytes": 128.664, "flops_per_problem": 7713698807.808}, "add.runmax.runmax6": {"acc": 1.0, "reasoning_bytes": 137.832, "flops_per_problem": 7632792059.904}, "add.runmax.runmax7": {"acc": 0.832, "reasoning_bytes": 155.848, "flops_per_problem": 8516760109.056}, "add.runmax.runmax8": {"acc": 0.624, "reasoning_bytes": 173.43, "flops_per_problem": 9381561384.96}, "parity.runmax.runmax16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7507722240.0}, "parity.runmax.runmax20": {"acc": 0.878, "reasoning_bytes": 152.052, "flops_per_problem": 8702421663.744}, "parity.runmax.runmax24": {"acc": 0.558, "reasoning_bytes": 171.0, "flops_per_problem": 9715875840.0}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7551885312.0}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 152.856, "flops_per_problem": 8782091845.632}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 171.0, "flops_per_problem": 9760038912.0}, "inc.runmax.count6": {"acc": 1.0, "reasoning_bytes": 121.0, "flops_per_problem": 6624460800.0}, "inc.runmax.count7": {"acc": 0.998, "reasoning_bytes": 137.0, "flops_per_problem": 7375233024.0}, "inc.runmax.count8": {"acc": 0.998, "reasoning_bytes": 148.58, "flops_per_problem": 7930804469.76}, "sumd.runmax.count6": {"acc": 1.0, "reasoning_bytes": 84.424, "flops_per_problem": 5053315350.528}, "sumd.runmax.count7": {"acc": 1.0, "reasoning_bytes": 92.46, "flops_per_problem": 5452372869.12}, "sumd.runmax.count8": {"acc": 0.95, "reasoning_bytes": 99.492, "flops_per_problem": 5807090663.424}, "runmax.runmax.find12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6271156224.0}, "runmax.runmax.find14": {"acc": 1.0, "reasoning_bytes": 115.764, "flops_per_problem": 6834853675.008}, "runmax.runmax.find16": {"acc": 0.984, "reasoning_bytes": 123.0, "flops_per_problem": 7242743808.0}, "add.runmax.find6": {"acc": 1.0, "reasoning_bytes": 137.928, "flops_per_problem": 7637031714.816}, "add.runmax.find7": {"acc": 0.984, "reasoning_bytes": 155.608, "flops_per_problem": 8506160971.776}, "add.runmax.find8": {"acc": 0.872, "reasoning_bytes": 172.934, "flops_per_problem": 9359656501.248}, "parity.runmax.find16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7507722240.0}, "parity.runmax.find20": {"acc": 0.978, "reasoning_bytes": 152.928, "flops_per_problem": 8741108514.816}, "parity.runmax.find24": {"acc": 0.898, "reasoning_bytes": 170.998, "flops_per_problem": 9715787513.856}, "add.runmax.rev6": {"acc": 1.0, "reasoning_bytes": 132.832, "flops_per_problem": 7279487483.904}, "add.runmax.rev7": {"acc": 0.902, "reasoning_bytes": 150.848, "flops_per_problem": 8163455533.056}, "add.runmax.rev8": {"acc": 0.594, "reasoning_bytes": 168.278, "flops_per_problem": 9021544022.016}, "parity.runmax.rev16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7154417664.0}, "parity.runmax.rev20": {"acc": 0.866, "reasoning_bytes": 147.34, "flops_per_problem": 8361836052.48}, "parity.runmax.rev24": {"acc": 0.498, "reasoning_bytes": 165.978, "flops_per_problem": 9361599676.416}, "sumd.runmax.rev6": {"acc": 1.0, "reasoning_bytes": 79.542, "flops_per_problem": 4661058945.024}, "sumd.runmax.rev7": {"acc": 0.996, "reasoning_bytes": 87.478, "flops_per_problem": 5055700156.416}, "sumd.runmax.rev8": {"acc": 0.81, "reasoning_bytes": 94.12, "flops_per_problem": 5393194352.64}, "sumd.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 82.542, "flops_per_problem": 4837711233.024}, "sumd.runmax.sumd7": {"acc": 0.996, "reasoning_bytes": 90.478, "flops_per_problem": 5232352444.416}, "sumd.runmax.sumd8": {"acc": 0.862, "reasoning_bytes": 97.864, "flops_per_problem": 5602703966.208}, "add.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 135.832, "flops_per_problem": 7456139771.904}, "add.runmax.sumd7": {"acc": 0.894, "reasoning_bytes": 153.848, "flops_per_problem": 8340107821.056}, "add.runmax.sumd8": {"acc": 0.632, "reasoning_bytes": 171.516, "flops_per_problem": 9208707121.152}, "parity.runmax.sumd16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.runmax.sumd20": {"acc": 0.862, "reasoning_bytes": 150.16, "flops_per_problem": 8530538987.52}, "parity.runmax.sumd24": {"acc": 0.532, "reasoning_bytes": 169.0, "flops_per_problem": 9539223552.0}, "count.runmax.inc16": {"acc": 0.996, "reasoning_bytes": 112.02, "flops_per_problem": 6669507133.44}, "count.runmax.inc18": {"acc": 0.958, "reasoning_bytes": 121.61, "flops_per_problem": 7181357137.92}, "count.runmax.inc20": {"acc": 0.748, "reasoning_bytes": 127.264, "flops_per_problem": 7519557943.296}, "runmax.runmax.inc12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6125683064.832}, "runmax.runmax.inc14": {"acc": 1.0, "reasoning_bytes": 114.908, "flops_per_problem": 6699096391.68}, "runmax.runmax.inc16": {"acc": 0.966, "reasoning_bytes": 122.0, "flops_per_problem": 7101863608.32}, "add.runmax.inc6": {"acc": 1.0, "reasoning_bytes": 136.832, "flops_per_problem": 7477161394.176}, "add.runmax.inc7": {"acc": 0.858, "reasoning_bytes": 154.848, "flops_per_problem": 8363602575.36}, "add.runmax.inc8": {"acc": 0.62, "reasoning_bytes": 172.452, "flops_per_problem": 9231141961.728}, "count.count.cmp16": {"acc": 1.0, "reasoning_bytes": 112.02, "flops_per_problem": 6801996349.44}, "count.count.cmp18": {"acc": 0.996, "reasoning_bytes": 121.982, "flops_per_problem": 7330275016.704}, "count.count.cmp20": {"acc": 0.976, "reasoning_bytes": 128.658, "flops_per_problem": 7712992198.656}, "add.count.cmp6": {"acc": 0.994, "reasoning_bytes": 131.354, "flops_per_problem": 7346703679.488}, "add.count.cmp7": {"acc": 0.904, "reasoning_bytes": 148.176, "flops_per_problem": 8177941020.672}, "add.count.cmp8": {"acc": 0.866, "reasoning_bytes": 163.29, "flops_per_problem": 8933747834.88}, "sumd.count.cmp6": {"acc": 1.0, "reasoning_bytes": 82.492, "flops_per_problem": 4923829223.424}, "sumd.count.cmp7": {"acc": 1.0, "reasoning_bytes": 90.508, "flops_per_problem": 5322003480.576}, "sumd.count.cmp8": {"acc": 0.956, "reasoning_bytes": 92.646, "flops_per_problem": 5460587200.512}, "add.count.runmax6": {"acc": 0.984, "reasoning_bytes": 132.648, "flops_per_problem": 7448013766.656}, "add.count.runmax7": {"acc": 0.874, "reasoning_bytes": 149.086, "flops_per_problem": 8262292488.192}, "add.count.runmax8": {"acc": 0.462, "reasoning_bytes": 165.602, "flops_per_problem": 9080015929.344}, "sumd.count.runmax6": {"acc": 1.0, "reasoning_bytes": 83.428, "flops_per_problem": 5009328930.816}, "sumd.count.runmax7": {"acc": 0.99, "reasoning_bytes": 91.458, "flops_per_problem": 5408121470.976}, "sumd.count.runmax8": {"acc": 0.82, "reasoning_bytes": 98.156, "flops_per_problem": 5748088799.232}, "inc.count.runmax6": {"acc": 0.988, "reasoning_bytes": 116.0, "flops_per_problem": 6403645440.0}, "inc.count.runmax7": {"acc": 0.68, "reasoning_bytes": 130.972, "flops_per_problem": 7109018025.984}, "inc.count.runmax8": {"acc": 0.722, "reasoning_bytes": 137.374, "flops_per_problem": 7435913084.928}, "parity.count.count16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7596048384.0}, "parity.count.count20": {"acc": 1.0, "reasoning_bytes": 152.592, "flops_per_problem": 8814595866.624}, "parity.count.count24": {"acc": 1.0, "reasoning_bytes": 171.0, "flops_per_problem": 9804201984.0}, "runmax.count.count12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6359482368.0}, "runmax.count.count14": {"acc": 1.0, "reasoning_bytes": 115.692, "flops_per_problem": 6920000077.824}, "runmax.count.count16": {"acc": 1.0, "reasoning_bytes": 123.024, "flops_per_problem": 7332129865.728}, "inc.count.count6": {"acc": 0.998, "reasoning_bytes": 116.0, "flops_per_problem": 6447808512.0}, "inc.count.count7": {"acc": 0.978, "reasoning_bytes": 130.986, "flops_per_problem": 7153799380.992}, "inc.count.count8": {"acc": 0.972, "reasoning_bytes": 132.524, "flops_per_problem": 7265885257.728}, "inc.count.find6": {"acc": 1.0, "reasoning_bytes": 116.0, "flops_per_problem": 6403645440.0}, "inc.count.find7": {"acc": 0.94, "reasoning_bytes": 130.986, "flops_per_problem": 7109636308.992}, "inc.count.find8": {"acc": 0.916, "reasoning_bytes": 129.738, "flops_per_problem": 7098683867.136}, "add.count.find6": {"acc": 0.996, "reasoning_bytes": 132.326, "flops_per_problem": 7433793257.472}, "add.count.find7": {"acc": 0.95, "reasoning_bytes": 149.156, "flops_per_problem": 8265383903.232}, "add.count.find8": {"acc": 0.838, "reasoning_bytes": 165.43, "flops_per_problem": 9072243228.672}, "runmax.count.find12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6315319296.0}, "runmax.count.find14": {"acc": 1.0, "reasoning_bytes": 115.62, "flops_per_problem": 6872657264.64}, "runmax.count.find16": {"acc": 1.0, "reasoning_bytes": 123.012, "flops_per_problem": 7287436836.864}, "parity.count.rev16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7198580736.0}, "parity.count.rev20": {"acc": 1.0, "reasoning_bytes": 147.76, "flops_per_problem": 8424547614.72}, "parity.count.rev24": {"acc": 1.0, "reasoning_bytes": 166.012, "flops_per_problem": 9407264292.864}, "inc.count.rev6": {"acc": 0.988, "reasoning_bytes": 111.0, "flops_per_problem": 6050340864.0}, "inc.count.rev7": {"acc": 0.896, "reasoning_bytes": 125.986, "flops_per_problem": 6756331732.992}, "inc.count.rev8": {"acc": 0.734, "reasoning_bytes": 131.314, "flops_per_problem": 7035795652.608}, "runmax.count.rev12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5962014720.0}, "runmax.count.rev14": {"acc": 1.0, "reasoning_bytes": 111.328, "flops_per_problem": 6550620143.616}, "runmax.count.rev16": {"acc": 1.0, "reasoning_bytes": 118.012, "flops_per_problem": 6934132260.864}, "count.count.sumd16": {"acc": 1.0, "reasoning_bytes": 111.01, "flops_per_problem": 6713228574.72}, "count.count.sumd18": {"acc": 1.0, "reasoning_bytes": 120.91, "flops_per_problem": 7238769131.52}, "count.count.sumd20": {"acc": 0.998, "reasoning_bytes": 127.304, "flops_per_problem": 7609120653.312}, "runmax.count.sumd12": {"acc": 1.0, "reasoning_bytes": 103.0, "flops_per_problem": 6138667008.0}, "runmax.count.sumd14": {"acc": 1.0, "reasoning_bytes": 114.508, "flops_per_problem": 6735221784.576}, "runmax.count.sumd16": {"acc": 1.0, "reasoning_bytes": 121.04, "flops_per_problem": 7112021114.88}, "sumd.count.sumd6": {"acc": 1.0, "reasoning_bytes": 81.428, "flops_per_problem": 4832676642.816}, "sumd.count.sumd7": {"acc": 0.99, "reasoning_bytes": 89.468, "flops_per_problem": 5231910813.696}, "sumd.count.sumd8": {"acc": 0.854, "reasoning_bytes": 96.426, "flops_per_problem": 5583360540.672}, "parity.count.inc16": {"acc": 1.0, "reasoning_bytes": 128.0, "flops_per_problem": 7375233024.0}, "parity.count.inc20": {"acc": 1.0, "reasoning_bytes": 151.772, "flops_per_problem": 8601729859.584}, "parity.count.inc24": {"acc": 1.0, "reasoning_bytes": 170.012, "flops_per_problem": 9583916580.864}, "count.count.inc16": {"acc": 1.0, "reasoning_bytes": 112.01, "flops_per_problem": 6713228574.72}, "count.count.inc18": {"acc": 1.0, "reasoning_bytes": 121.91, "flops_per_problem": 7238769131.52}, "count.count.inc20": {"acc": 0.988, "reasoning_bytes": 128.436, "flops_per_problem": 7612742025.216}, "add.count.inc6": {"acc": 0.988, "reasoning_bytes": 131.648, "flops_per_problem": 7271361478.656}, "add.count.inc7": {"acc": 0.836, "reasoning_bytes": 148.084, "flops_per_problem": 8085551874.048}, "add.count.inc8": {"acc": 0.462, "reasoning_bytes": 164.448, "flops_per_problem": 8896562528.256}, "parity.rev.cmp16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 7066091520.0}, "parity.rev.cmp20": {"acc": 0.984, "reasoning_bytes": 145.62, "flops_per_problem": 8241712496.64}, "parity.rev.cmp24": {"acc": 0.942, "reasoning_bytes": 164.856, "flops_per_problem": 9267885637.632}, "sumd.rev.cmp6": {"acc": 0.998, "reasoning_bytes": 81.06, "flops_per_problem": 4727921836.032}, "sumd.rev.cmp7": {"acc": 0.998, "reasoning_bytes": 89.05, "flops_per_problem": 5125124505.6}, "sumd.rev.cmp8": {"acc": 0.788, "reasoning_bytes": 92.584, "flops_per_problem": 5325271547.904}, "add.rev.cmp6": {"acc": 0.996, "reasoning_bytes": 157.314, "flops_per_problem": 8565692792.832}, "add.rev.cmp7": {"acc": 0.98, "reasoning_bytes": 181.806, "flops_per_problem": 9777085857.792}, "add.rev.cmp8": {"acc": 0.79, "reasoning_bytes": 199.478, "flops_per_problem": 10691526426.624}, "runmax.rev.runmax12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5917851648.0}, "runmax.rev.runmax14": {"acc": 1.0, "reasoning_bytes": 111.496, "flops_per_problem": 6513876467.712}, "runmax.rev.runmax16": {"acc": 0.966, "reasoning_bytes": 118.012, "flops_per_problem": 6889969188.864}, "count.rev.runmax16": {"acc": 0.996, "reasoning_bytes": 108.02, "flops_per_problem": 6492854845.44}, "count.rev.runmax18": {"acc": 0.98, "reasoning_bytes": 117.81, "flops_per_problem": 7013537464.32}, "count.rev.runmax20": {"acc": 0.776, "reasoning_bytes": 123.334, "flops_per_problem": 7345820418.048}, "add.rev.runmax6": {"acc": 1.0, "reasoning_bytes": 185.08, "flops_per_problem": 9586919669.76}, "add.rev.runmax7": {"acc": 0.884, "reasoning_bytes": 215.616, "flops_per_problem": 11023809380.352}, "add.rev.runmax8": {"acc": 0.632, "reasoning_bytes": 243.736, "flops_per_problem": 12354001108.992}, "inc.rev.count6": {"acc": 0.958, "reasoning_bytes": 156.0, "flops_per_problem": 8037679104.0}, "inc.rev.count7": {"acc": 0.824, "reasoning_bytes": 182.774, "flops_per_problem": 9264264265.728}, "inc.rev.count8": {"acc": 0.62, "reasoning_bytes": 191.216, "flops_per_problem": 9681251991.552}, "count.rev.count16": {"acc": 1.0, "reasoning_bytes": 108.01, "flops_per_problem": 6536576286.72}, "count.rev.count18": {"acc": 0.996, "reasoning_bytes": 117.892, "flops_per_problem": 7061321908.224}, "count.rev.count20": {"acc": 0.992, "reasoning_bytes": 124.502, "flops_per_problem": 7438651195.392}, "parity.rev.count16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7198580736.0}, "parity.rev.count20": {"acc": 1.0, "reasoning_bytes": 147.844, "flops_per_problem": 8428257312.768}, "parity.rev.count24": {"acc": 1.0, "reasoning_bytes": 166.012, "flops_per_problem": 9407264292.864}, "sumd.rev.find6": {"acc": 1.0, "reasoning_bytes": 85.208, "flops_per_problem": 4911286910.976}, "sumd.rev.find7": {"acc": 0.998, "reasoning_bytes": 93.482, "flops_per_problem": 5320855240.704}, "sumd.rev.find8": {"acc": 0.854, "reasoning_bytes": 98.508, "flops_per_problem": 5586981912.576}, "runmax.rev.find12": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5917851648.0}, "runmax.rev.find14": {"acc": 1.0, "reasoning_bytes": 111.04, "flops_per_problem": 6493738106.88}, "runmax.rev.find16": {"acc": 0.986, "reasoning_bytes": 118.012, "flops_per_problem": 6889969188.864}, "count.rev.find16": {"acc": 1.0, "reasoning_bytes": 108.01, "flops_per_problem": 6492413214.72}, "count.rev.find18": {"acc": 0.988, "reasoning_bytes": 117.7, "flops_per_problem": 7008679526.4}, "count.rev.find20": {"acc": 0.926, "reasoning_bytes": 123.596, "flops_per_problem": 7355801272.32}, "count.rev.rev16": {"acc": 0.998, "reasoning_bytes": 103.02, "flops_per_problem": 6139550269.44}, "count.rev.rev18": {"acc": 0.93, "reasoning_bytes": 112.24, "flops_per_problem": 6635059937.28}, "count.rev.rev20": {"acc": 0.738, "reasoning_bytes": 118.28, "flops_per_problem": 6989336100.864}, "sumd.rev.rev6": {"acc": 1.0, "reasoning_bytes": 80.53, "flops_per_problem": 4616277590.016}, "sumd.rev.rev7": {"acc": 0.988, "reasoning_bytes": 88.462, "flops_per_problem": 5010830475.264}, "sumd.rev.rev8": {"acc": 0.53, "reasoning_bytes": 92.802, "flops_per_problem": 5246572953.6}, "parity.rev.rev16": {"acc": 1.0, "reasoning_bytes": 119.0, "flops_per_problem": 6801113088.0}, "parity.rev.rev20": {"acc": 0.788, "reasoning_bytes": 141.968, "flops_per_problem": 7992102813.696}, "parity.rev.rev24": {"acc": 0.472, "reasoning_bytes": 160.964, "flops_per_problem": 9007676817.408}, "sumd.rev.sumd6": {"acc": 1.0, "reasoning_bytes": 84.73, "flops_per_problem": 4810771759.104}, "sumd.rev.sumd7": {"acc": 0.994, "reasoning_bytes": 92.738, "flops_per_problem": 5211154169.856}, "sumd.rev.sumd8": {"acc": 0.788, "reasoning_bytes": 99.136, "flops_per_problem": 5538667511.808}, "parity.rev.sumd16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.rev.sumd20": {"acc": 0.866, "reasoning_bytes": 145.508, "flops_per_problem": 8192603160.576}, "parity.rev.sumd24": {"acc": 0.49, "reasoning_bytes": 163.988, "flops_per_problem": 9185389019.136}, "add.rev.sumd6": {"acc": 0.97, "reasoning_bytes": 191.642, "flops_per_problem": 9832378023.936}, "add.rev.sumd7": {"acc": 0.498, "reasoning_bytes": 223.896, "flops_per_problem": 11344609935.36}, "add.rev.sumd8": {"acc": 0.036, "reasoning_bytes": 250.126, "flops_per_problem": 12591510110.208}, "parity.rev.inc16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 6977765376.0}, "parity.rev.inc20": {"acc": 0.844, "reasoning_bytes": 146.7, "flops_per_problem": 8201082470.4}, "parity.rev.inc24": {"acc": 0.466, "reasoning_bytes": 165.0, "flops_per_problem": 9185918976.0}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 99.0, "flops_per_problem": 5772378488.832}, "runmax.rev.inc14": {"acc": 0.994, "reasoning_bytes": 109.236, "flops_per_problem": 6315937579.008}, "runmax.rev.inc16": {"acc": 0.952, "reasoning_bytes": 117.0, "flops_per_problem": 6748029075.456}, "inc.rev.inc6": {"acc": 0.982, "reasoning_bytes": 170.0, "flops_per_problem": 8696150507.52}, "inc.rev.inc7": {"acc": 0.714, "reasoning_bytes": 199.77, "flops_per_problem": 10099564609.536}, "inc.rev.inc8": {"acc": 0.016, "reasoning_bytes": 213.076, "flops_per_problem": 10741430697.984}, "parity.sumd.cmp16": {"acc": 1.0, "reasoning_bytes": 126.0, "flops_per_problem": 7242743808.0}, "parity.sumd.cmp20": {"acc": 0.98, "reasoning_bytes": 148.572, "flops_per_problem": 8416244957.184}, "parity.sumd.cmp24": {"acc": 0.958, "reasoning_bytes": 167.892, "flops_per_problem": 9446127796.224}, "runmax.sumd.cmp12": {"acc": 1.0, "reasoning_bytes": 102.0, "flops_per_problem": 6006177792.0}, "runmax.sumd.cmp14": {"acc": 1.0, "reasoning_bytes": 113.34, "flops_per_problem": 6595313172.48}, "runmax.sumd.cmp16": {"acc": 0.992, "reasoning_bytes": 120.036, "flops_per_problem": 6979355246.592}, "count.sumd.cmp16": {"acc": 1.0, "reasoning_bytes": 110.01, "flops_per_problem": 6580739358.72}, "count.sumd.cmp18": {"acc": 0.988, "reasoning_bytes": 119.18, "flops_per_problem": 7074040872.96}, "count.sumd.cmp20": {"acc": 0.956, "reasoning_bytes": 125.232, "flops_per_problem": 7428670341.12}, "sumd.sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 84.36, "flops_per_problem": 4917999697.92}, "sumd.sumd.runmax7": {"acc": 0.994, "reasoning_bytes": 92.818, "flops_per_problem": 5335694032.896}, "sumd.sumd.runmax8": {"acc": 0.85, "reasoning_bytes": 100.484, "flops_per_problem": 5718411214.848}, "count.sumd.runmax16": {"acc": 0.996, "reasoning_bytes": 111.02, "flops_per_problem": 6669507133.44}, "count.sumd.runmax18": {"acc": 0.964, "reasoning_bytes": 120.59, "flops_per_problem": 7180473876.48}, "count.sumd.runmax20": {"acc": 0.772, "reasoning_bytes": 126.336, "flops_per_problem": 7522561032.192}, "add.sumd.runmax6": {"acc": 0.998, "reasoning_bytes": 151.444, "flops_per_problem": 8145613651.968}, "add.sumd.runmax7": {"acc": 0.54, "reasoning_bytes": 171.272, "flops_per_problem": 9109605187.584}, "add.sumd.runmax8": {"acc": 0.198, "reasoning_bytes": 190.176, "flops_per_problem": 10033320001.536}, "parity.sumd.count16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7375233024.0}, "parity.sumd.count20": {"acc": 1.0, "reasoning_bytes": 150.784, "flops_per_problem": 8602259816.448}, "parity.sumd.count24": {"acc": 1.0, "reasoning_bytes": 169.0, "flops_per_problem": 9583386624.0}, "sumd.sumd.count6": {"acc": 1.0, "reasoning_bytes": 84.184, "flops_per_problem": 4954390069.248}, "sumd.sumd.count7": {"acc": 0.998, "reasoning_bytes": 92.476, "flops_per_problem": 5364753334.272}, "sumd.sumd.count8": {"acc": 0.886, "reasoning_bytes": 99.47, "flops_per_problem": 5717792931.84}, "add.sumd.count6": {"acc": 1.0, "reasoning_bytes": 150.516, "flops_per_problem": 8148793393.152}, "add.sumd.count7": {"acc": 0.818, "reasoning_bytes": 170.07, "flops_per_problem": 9100949225.472}, "add.sumd.count8": {"acc": 0.488, "reasoning_bytes": 189.254, "flops_per_problem": 10037471330.304}, "runmax.sumd.find12": {"acc": 1.0, "reasoning_bytes": 103.0, "flops_per_problem": 6094503936.0}, "runmax.sumd.find14": {"acc": 1.0, "reasoning_bytes": 113.8, "flops_per_problem": 6659791257.6}, "runmax.sumd.find16": {"acc": 0.988, "reasoning_bytes": 121.0, "flops_per_problem": 7066091520.0}, "sumd.sumd.find6": {"acc": 1.0, "reasoning_bytes": 84.064, "flops_per_problem": 4904927428.608}, "sumd.sumd.find7": {"acc": 0.996, "reasoning_bytes": 92.364, "flops_per_problem": 5315643998.208}, "sumd.sumd.find8": {"acc": 0.946, "reasoning_bytes": 99.118, "flops_per_problem": 5658084458.496}, "parity.sumd.find16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.sumd.find20": {"acc": 0.968, "reasoning_bytes": 150.688, "flops_per_problem": 8553857089.536}, "parity.sumd.find24": {"acc": 0.888, "reasoning_bytes": 169.0, "flops_per_problem": 9539223552.0}, "count.sumd.rev16": {"acc": 0.998, "reasoning_bytes": 106.02, "flops_per_problem": 6316202557.44}, "count.sumd.rev18": {"acc": 0.932, "reasoning_bytes": 114.85, "flops_per_problem": 6794488627.2}, "count.sumd.rev20": {"acc": 0.74, "reasoning_bytes": 121.136, "flops_per_problem": 7160158863.36}, "parity.sumd.rev16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.sumd.rev20": {"acc": 0.858, "reasoning_bytes": 145.4, "flops_per_problem": 8187833548.8}, "parity.sumd.rev24": {"acc": 0.49, "reasoning_bytes": 163.976, "flops_per_problem": 9184859062.272}, "add.sumd.rev6": {"acc": 0.994, "reasoning_bytes": 145.448, "flops_per_problem": 7792309075.968}, "add.sumd.rev7": {"acc": 0.554, "reasoning_bytes": 165.316, "flops_per_problem": 8758155460.608}, "add.sumd.rev8": {"acc": 0.054, "reasoning_bytes": 184.476, "flops_per_problem": 9692646064.128}, "parity.sumd.sumd16": {"acc": 1.0, "reasoning_bytes": 125.0, "flops_per_problem": 7154417664.0}, "parity.sumd.sumd20": {"acc": 0.854, "reasoning_bytes": 148.052, "flops_per_problem": 8349117087.744}, "parity.sumd.sumd24": {"acc": 0.53, "reasoning_bytes": 166.976, "flops_per_problem": 9361511350.272}, "add.sumd.sumd6": {"acc": 0.998, "reasoning_bytes": 149.642, "flops_per_problem": 7986449940.48}, "add.sumd.sumd7": {"acc": 0.534, "reasoning_bytes": 169.568, "flops_per_problem": 8957065936.896}, "add.sumd.sumd8": {"acc": 0.088, "reasoning_bytes": 188.302, "flops_per_problem": 9872566419.456}, "count.sumd.sumd16": {"acc": 0.996, "reasoning_bytes": 109.02, "flops_per_problem": 6492854845.44}, "count.sumd.sumd18": {"acc": 0.956, "reasoning_bytes": 118.06, "flops_per_problem": 6980415160.32}, "count.sumd.sumd20": {"acc": 0.73, "reasoning_bytes": 124.256, "flops_per_problem": 7342375698.432}, "inc.sumd.inc6": {"acc": 1.0, "reasoning_bytes": 135.538, "flops_per_problem": 7045688180.736}, "inc.sumd.inc7": {"acc": 0.718, "reasoning_bytes": 153.406, "flops_per_problem": 7878957023.232}, "inc.sumd.inc8": {"acc": 0.078, "reasoning_bytes": 163.558, "flops_per_problem": 8370050383.872}, "sumd.sumd.inc6": {"acc": 1.0, "reasoning_bytes": 83.764, "flops_per_problem": 4773586452.48}, "sumd.sumd.inc7": {"acc": 0.994, "reasoning_bytes": 92.338, "flops_per_problem": 5199141814.272}, "sumd.sumd.inc8": {"acc": 0.804, "reasoning_bytes": 99.122, "flops_per_problem": 5543260471.296}, "parity.sumd.inc16": {"acc": 1.0, "reasoning_bytes": 126.0, "flops_per_problem": 7154417664.0}, "parity.sumd.inc20": {"acc": 0.878, "reasoning_bytes": 149.604, "flops_per_problem": 8373495103.488}, "parity.sumd.inc24": {"acc": 0.5, "reasoning_bytes": 167.988, "flops_per_problem": 9362041307.136}, "inc.inc.cmp6": {"acc": 1.0, "reasoning_bytes": 144.624, "flops_per_problem": 7667769212.928}, "inc.inc.cmp7": {"acc": 0.994, "reasoning_bytes": 165.648, "flops_per_problem": 8684579782.656}, "inc.inc.cmp8": {"acc": 0.918, "reasoning_bytes": 180.254, "flops_per_problem": 9417951756.288}, "runmax.inc.cmp12": {"acc": 1.0, "reasoning_bytes": 105.568, "flops_per_problem": 6150856015.872}, "runmax.inc.cmp14": {"acc": 1.0, "reasoning_bytes": 117.406, "flops_per_problem": 6766047608.832}, "runmax.inc.cmp16": {"acc": 0.964, "reasoning_bytes": 123.778, "flops_per_problem": 7137017413.632}, "sumd.inc.cmp6": {"acc": 1.0, "reasoning_bytes": 88.12, "flops_per_problem": 5039713124.352}, "sumd.inc.cmp7": {"acc": 1.0, "reasoning_bytes": 96.068, "flops_per_problem": 5435060944.896}, "sumd.inc.cmp8": {"acc": 0.968, "reasoning_bytes": 100.382, "flops_per_problem": 5669743509.504}, "sumd.inc.runmax6": {"acc": 1.0, "reasoning_bytes": 93.522, "flops_per_problem": 5278458691.584}, "sumd.inc.runmax7": {"acc": 0.998, "reasoning_bytes": 101.478, "flops_per_problem": 5673983164.416}, "sumd.inc.runmax8": {"acc": 0.804, "reasoning_bytes": 107.848, "flops_per_problem": 5999465005.056}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.648, "flops_per_problem": 6343936966.656}, "runmax.inc.runmax14": {"acc": 1.0, "reasoning_bytes": 121.08, "flops_per_problem": 6937135349.76}, "runmax.inc.runmax16": {"acc": 0.962, "reasoning_bytes": 128.448, "flops_per_problem": 7350855008.256}, "add.inc.runmax6": {"acc": 1.0, "reasoning_bytes": 192.872, "flops_per_problem": 9931038326.784}, "add.inc.runmax7": {"acc": 0.848, "reasoning_bytes": 220.902, "flops_per_problem": 11257255378.944}, "add.inc.runmax8": {"acc": 0.68, "reasoning_bytes": 243.006, "flops_per_problem": 12327679918.08}, "runmax.inc.count12": {"acc": 1.0, "reasoning_bytes": 108.928, "flops_per_problem": 6356302626.816}, "runmax.inc.count14": {"acc": 1.0, "reasoning_bytes": 120.904, "flops_per_problem": 6973525721.088}, "runmax.inc.count16": {"acc": 1.0, "reasoning_bytes": 127.526, "flops_per_problem": 7354299727.872}, "sumd.inc.count6": {"acc": 1.0, "reasoning_bytes": 92.388, "flops_per_problem": 5272540839.936}, "sumd.inc.count7": {"acc": 0.996, "reasoning_bytes": 100.46, "flops_per_problem": 5673188229.12}, "sumd.inc.count8": {"acc": 0.768, "reasoning_bytes": 105.754, "flops_per_problem": 5951150604.288}, "inc.inc.count6": {"acc": 0.978, "reasoning_bytes": 165.0, "flops_per_problem": 8435146752.0}, "inc.inc.count7": {"acc": 0.814, "reasoning_bytes": 189.894, "flops_per_problem": 9578705338.368}, "inc.inc.count8": {"acc": 0.66, "reasoning_bytes": 197.34, "flops_per_problem": 9951706644.48}, "parity.inc.find16": {"acc": 1.0, "reasoning_bytes": 128.0, "flops_per_problem": 7331069952.0}, "parity.inc.find20": {"acc": 0.974, "reasoning_bytes": 151.88, "flops_per_problem": 8562336399.36}, "parity.inc.find24": {"acc": 0.872, "reasoning_bytes": 170.06, "flops_per_problem": 9541873336.32}, "sumd.inc.find6": {"acc": 1.0, "reasoning_bytes": 92.1, "flops_per_problem": 5215658803.2}, "sumd.inc.find7": {"acc": 0.998, "reasoning_bytes": 100.388, "flops_per_problem": 5625845415.936}, "sumd.inc.find8": {"acc": 0.902, "reasoning_bytes": 105.614, "flops_per_problem": 5900804702.208}, "count.inc.find16": {"acc": 1.0, "reasoning_bytes": 112.02, "flops_per_problem": 6669507133.44}, "count.inc.find18": {"acc": 0.988, "reasoning_bytes": 121.68, "flops_per_problem": 7184448552.96}, "count.inc.find20": {"acc": 0.934, "reasoning_bytes": 127.666, "flops_per_problem": 7535015018.496}, "sumd.inc.rev6": {"acc": 1.0, "reasoning_bytes": 87.524, "flops_per_problem": 4925154115.584}, "sumd.inc.rev7": {"acc": 0.994, "reasoning_bytes": 95.464, "flops_per_problem": 5320060305.408}, "sumd.inc.rev8": {"acc": 0.608, "reasoning_bytes": 100.298, "flops_per_problem": 5577707667.456}, "count.inc.rev16": {"acc": 0.996, "reasoning_bytes": 107.02, "flops_per_problem": 6316202557.44}, "count.inc.rev18": {"acc": 0.93, "reasoning_bytes": 116.432, "flops_per_problem": 6820191535.104}, "count.inc.rev20": {"acc": 0.722, "reasoning_bytes": 122.3, "flops_per_problem": 7166606671.872}, "parity.inc.rev16": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 6977765376.0}, "parity.inc.rev20": {"acc": 0.86, "reasoning_bytes": 146.664, "flops_per_problem": 8199492599.808}, "parity.inc.rev24": {"acc": 0.472, "reasoning_bytes": 165.0, "flops_per_problem": 9185918976.0}, "count.inc.sumd16": {"acc": 0.996, "reasoning_bytes": 110.02, "flops_per_problem": 6492854845.44}, "count.inc.sumd18": {"acc": 0.956, "reasoning_bytes": 119.44, "flops_per_problem": 6997197127.68}, "count.inc.sumd20": {"acc": 0.748, "reasoning_bytes": 125.222, "flops_per_problem": 7340874153.984}, "sumd.inc.sumd6": {"acc": 1.0, "reasoning_bytes": 91.758, "flops_per_problem": 5122651373.568}, "sumd.inc.sumd7": {"acc": 0.992, "reasoning_bytes": 99.74, "flops_per_problem": 5521178935.296}, "sumd.inc.sumd8": {"acc": 0.778, "reasoning_bytes": 106.154, "flops_per_problem": 5850458800.128}, "add.inc.sumd6": {"acc": 0.958, "reasoning_bytes": 198.52, "flops_per_problem": 10136131633.152}, "add.inc.sumd7": {"acc": 0.386, "reasoning_bytes": 228.346, "flops_per_problem": 11541753888.768}, "add.inc.sumd8": {"acc": 0.046, "reasoning_bytes": 249.4, "flops_per_problem": 12578526167.04}, "parity.inc.inc16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7154417664.0}, "parity.inc.inc20": {"acc": 0.84, "reasoning_bytes": 150.736, "flops_per_problem": 8379324628.992}, "parity.inc.inc24": {"acc": 0.488, "reasoning_bytes": 169.096, "flops_per_problem": 9366810918.912}, "sumd.inc.inc6": {"acc": 0.998, "reasoning_bytes": 94.518, "flops_per_problem": 5234118967.296}, "sumd.inc.inc7": {"acc": 0.984, "reasoning_bytes": 102.464, "flops_per_problem": 5629201809.408}, "sumd.inc.inc8": {"acc": 0.588, "reasoning_bytes": 107.668, "flops_per_problem": 5903189508.096}, "runmax.inc.inc12": {"acc": 1.0, "reasoning_bytes": 110.06, "flops_per_problem": 6270272962.56}, "runmax.inc.inc14": {"acc": 0.992, "reasoning_bytes": 120.368, "flops_per_problem": 6815156944.896}, "runmax.inc.inc16": {"acc": 0.95, "reasoning_bytes": 128.98, "flops_per_problem": 7284433747.968}, "count.inc.cmp16": {"acc": 0.976, "reasoning_bytes": 111.15, "flops_per_problem": 6593811628.032}, "count.inc.cmp18": {"acc": 0.822, "reasoning_bytes": 121.758, "flops_per_problem": 7183123660.8}, "count.inc.cmp20": {"acc": 0.748, "reasoning_bytes": 129.206, "flops_per_problem": 7566989082.624}, "inc.rev.sumd6": {"acc": 0.95, "reasoning_bytes": 166.246, "flops_per_problem": 8403614318.592}, "inc.rev.sumd7": {"acc": 0.594, "reasoning_bytes": 195.972, "flops_per_problem": 9761982087.168}, "inc.rev.sumd8": {"acc": 0.066, "reasoning_bytes": 215.588, "flops_per_problem": 10670504804.352}, "runmax.inc.find12": {"acc": 0.886, "reasoning_bytes": 105.536, "flops_per_problem": 6162338414.592}, "runmax.inc.find14": {"acc": 0.896, "reasoning_bytes": 116.012, "flops_per_problem": 6713316900.864}, "runmax.inc.find16": {"acc": 0.842, "reasoning_bytes": 123.74, "flops_per_problem": 7142935265.28}, "inc.runmax.cmp6": {"acc": 1.0, "reasoning_bytes": 120.0, "flops_per_problem": 6491971584.0}, "inc.runmax.cmp7": {"acc": 0.97, "reasoning_bytes": 135.984, "flops_per_problem": 7242037198.848}, "inc.runmax.cmp8": {"acc": 0.972, "reasoning_bytes": 142.814, "flops_per_problem": 7587834052.608}} diff --git a/5m-s0-bpe4096-step-bytes3-v10-nocount.inc.cmp-noinc.rev.sumd-noadd.count.find-norunmax.inc.find-nosumd.rev.cmp-noinc.runmax.cmp-none-docmask/summary.json b/5m-s0-bpe4096-step-bytes3-v10-nocount.inc.cmp-noinc.rev.sumd-noadd.count.find-norunmax.inc.find-nosumd.rev.cmp-noinc.runmax.cmp-none-docmask/summary.json new file mode 100644 index 0000000000000000000000000000000000000000..8256a375f2813acb85b3d62ab392ab784697184e --- /dev/null +++ b/5m-s0-bpe4096-step-bytes3-v10-nocount.inc.cmp-noinc.rev.sumd-noadd.count.find-norunmax.inc.find-nosumd.rev.cmp-noinc.runmax.cmp-none-docmask/summary.json @@ -0,0 +1,2410 @@ +{ + "params": 5787648, + "tokens": 399998976, + "train_flops": 17665183577014272, + "wall_s": 4526.376119852066, + "peak_mem_gb": 3.51196672, + "final_val_loss": 1.8132692694664, + "final_val_bpb": 0.6536541128068258, + "bytes_seen": 1600839241.8284984, + "add8": { + "acc": 0.976, + "reasoning_bytes": 79.0, + "flops_per_problem": 4928775487.488 + }, + "add9": { + "acc": 0.182, + "reasoning_bytes": 89.026, + "flops_per_problem": 5503778684.928 + }, + "add10": { + "acc": 0.0, + "reasoning_bytes": 98.776, + "flops_per_problem": 6065886265.344 + }, + "reach14": { + "acc": 0.526, + "reasoning_bytes": 9.116, + "flops_per_problem": 4686408548.352 + }, + "reach16": { + "acc": 0.516, + "reasoning_bytes": 9.338, + "flops_per_problem": 5226169614.336 + }, + "reach18": { + "acc": 0.53, + "reasoning_bytes": 9.676, + "flops_per_problem": 5773438402.56 + }, + "parity24": { + "acc": 0.784, + "reasoning_bytes": 142.988, + "flops_per_problem": 7860496859.136 + }, + "parity28": { + "acc": 0.498, + "reasoning_bytes": 166.736, + "flops_per_problem": 9085933780.992 + }, + "parity32": { + "acc": 0.502, + "reasoning_bytes": 187.142, + "flops_per_problem": 10163777716.224 + }, + "cmp8": { + "acc": 0.996, + "reasoning_bytes": 5.792, + "flops_per_problem": 1359869313.024 + }, + "cmp9": { + "acc": 0.998, + "reasoning_bytes": 5.708, + "flops_per_problem": 1444485758.976 + }, + "cmp10": { + "acc": 0.998, + "reasoning_bytes": 5.732, + "flops_per_problem": 1533871816.704 + }, + "runmax12": { + "acc": 1.0, + "reasoning_bytes": 71.0, + "flops_per_problem": 4151328768.0 + }, + "runmax14": { + "acc": 1.0, + "reasoning_bytes": 82.996, + "flops_per_problem": 4769435123.712 + }, + "runmax16": { + "acc": 0.976, + "reasoning_bytes": 89.624, + "flops_per_problem": 5150474108.928 + }, + "count16": { + "acc": 0.988, + "reasoning_bytes": 79.1, + "flops_per_problem": 4729865011.2 + }, + "count18": { + "acc": 0.93, + "reasoning_bytes": 89.06, + "flops_per_problem": 5267682902.016 + }, + "count20": { + "acc": 0.672, + "reasoning_bytes": 98.72, + "flops_per_problem": 5787217281.024 + }, + "brackets16": { + "acc": 0.926, + "reasoning_bytes": 53.532, + "flops_per_problem": 3644866658.304 + }, + "brackets18": { + "acc": 0.89, + "reasoning_bytes": 57.348, + "flops_per_problem": 3901807411.2 + }, + "brackets20": { + "acc": 0.9, + "reasoning_bytes": 62.428, + "flops_per_problem": 4214570287.104 + }, + "sumd8": { + "acc": 0.96, + "reasoning_bytes": 58.566, + "flops_per_problem": 3381301444.608 + }, + "sumd9": { + "acc": 0.83, + "reasoning_bytes": 66.434, + "flops_per_problem": 3774794416.128 + }, + "sumd10": { + "acc": 0.184, + "reasoning_bytes": 64.944, + "flops_per_problem": 3730101387.264 + }, + "inc8": { + "acc": 0.996, + "reasoning_bytes": 63.0, + "flops_per_problem": 3797405908.992 + }, + "inc9": { + "acc": 0.528, + "reasoning_bytes": 69.612, + "flops_per_problem": 4144615981.056 + }, + "inc10": { + "acc": 0.0, + "reasoning_bytes": 64.158, + "flops_per_problem": 3671364501.504 + }, + "add.cmp6": { + "acc": 1.0, + "reasoning_bytes": 92.622, + "flops_per_problem": 5532043051.008 + }, + "add.cmp7": { + "acc": 0.996, + "reasoning_bytes": 105.494, + "flops_per_problem": 6230261219.328 + }, + "add.cmp8": { + "acc": 0.998, + "reasoning_bytes": 118.198, + "flops_per_problem": 6925299646.464 + }, + "add.runmax6": { + "acc": 1.0, + "reasoning_bytes": 120.832, + "flops_per_problem": 6572878331.904 + }, + "add.runmax7": { + "acc": 0.866, + "reasoning_bytes": 138.848, + "flops_per_problem": 7456846381.056 + }, + "add.runmax8": { + "acc": 0.562, + "reasoning_bytes": 156.758, + "flops_per_problem": 8336133144.576 + }, + "add.count6": { + "acc": 0.986, + "reasoning_bytes": 115.648, + "flops_per_problem": 6388100038.656 + }, + "add.count7": { + "acc": 0.872, + "reasoning_bytes": 132.082, + "flops_per_problem": 7202202107.904 + }, + "add.count8": { + "acc": 0.37, + "reasoning_bytes": 148.892, + "flops_per_problem": 8032909492.224 + }, + "add.find6": { + "acc": 0.896, + "reasoning_bytes": 107.744, + "flops_per_problem": 5994872045.568 + }, + "add.find7": { + "acc": 0.778, + "reasoning_bytes": 121.774, + "flops_per_problem": 6702806089.728 + }, + "add.find8": { + "acc": 0.482, + "reasoning_bytes": 139.268, + "flops_per_problem": 7563721015.296 + }, + "add.rev6": { + "acc": 1.0, + "reasoning_bytes": 123.248, + "flops_per_problem": 6794576953.344 + }, + "add.rev7": { + "acc": 0.43, + "reasoning_bytes": 145.87, + "flops_per_problem": 7926123184.128 + }, + "add.rev8": { + "acc": 0.0, + "reasoning_bytes": 168.612, + "flops_per_problem": 9050161692.672 + }, + "add.sumd6": { + "acc": 0.998, + "reasoning_bytes": 126.476, + "flops_per_problem": 6777794985.984 + }, + "add.sumd7": { + "acc": 0.692, + "reasoning_bytes": 146.322, + "flops_per_problem": 7742669783.04 + }, + "add.sumd8": { + "acc": 0.046, + "reasoning_bytes": 165.992, + "flops_per_problem": 8699771879.424 + }, + "add.inc6": { + "acc": 1.0, + "reasoning_bytes": 131.04, + "flops_per_problem": 7138695610.368 + }, + "add.inc7": { + "acc": 0.552, + "reasoning_bytes": 151.032, + "flops_per_problem": 8154092961.792 + }, + "add.inc8": { + "acc": 0.0, + "reasoning_bytes": 168.926, + "flops_per_problem": 9067031986.176 + }, + "runmax.cmp12": { + "acc": 1.0, + "reasoning_bytes": 87.0, + "flops_per_problem": 5122916352.0 + }, + "runmax.cmp14": { + "acc": 0.998, + "reasoning_bytes": 96.864, + "flops_per_problem": 5646867038.208 + }, + "runmax.cmp16": { + "acc": 0.966, + "reasoning_bytes": 105.012, + "flops_per_problem": 6095033892.864 + }, + "runmax.runmax12": { + "acc": 1.0, + "reasoning_bytes": 88.0, + "flops_per_problem": 5211242496.0 + }, + "runmax.runmax14": { + "acc": 1.0, + "reasoning_bytes": 99.136, + "flops_per_problem": 5791368609.792 + }, + "runmax.runmax16": { + "acc": 0.97, + "reasoning_bytes": 106.0, + "flops_per_problem": 6182830080.0 + }, + "runmax.count12": { + "acc": 1.0, + "reasoning_bytes": 88.0, + "flops_per_problem": 5255405568.0 + }, + "runmax.count14": { + "acc": 1.0, + "reasoning_bytes": 98.716, + "flops_per_problem": 5816983191.552 + }, + "runmax.count16": { + "acc": 1.0, + "reasoning_bytes": 106.072, + "flops_per_problem": 6230172893.184 + }, + "runmax.find12": { + "acc": 1.0, + "reasoning_bytes": 88.0, + "flops_per_problem": 5211242496.0 + }, + "runmax.find14": { + "acc": 1.0, + "reasoning_bytes": 97.864, + "flops_per_problem": 5735193182.208 + }, + "runmax.find16": { + "acc": 0.986, + "reasoning_bytes": 106.012, + "flops_per_problem": 6183360036.864 + }, + "runmax.rev12": { + "acc": 1.0, + "reasoning_bytes": 83.0, + "flops_per_problem": 4857937920.0 + }, + "runmax.rev14": { + "acc": 0.992, + "reasoning_bytes": 92.852, + "flops_per_problem": 5381358649.344 + }, + "runmax.rev16": { + "acc": 0.95, + "reasoning_bytes": 101.0, + "flops_per_problem": 5829525504.0 + }, + "runmax.sumd12": { + "acc": 1.0, + "reasoning_bytes": 86.0, + "flops_per_problem": 5034590208.0 + }, + "runmax.sumd14": { + "acc": 1.0, + "reasoning_bytes": 97.064, + "flops_per_problem": 5611536580.608 + }, + "runmax.sumd16": { + "acc": 0.97, + "reasoning_bytes": 104.0, + "flops_per_problem": 6006177792.0 + }, + "runmax.inc12": { + "acc": 1.0, + "reasoning_bytes": 87.0, + "flops_per_problem": 5065769336.832 + }, + "runmax.inc14": { + "acc": 0.994, + "reasoning_bytes": 96.396, + "flops_per_problem": 5572319772.672 + }, + "runmax.inc16": { + "acc": 0.956, + "reasoning_bytes": 105.0, + "flops_per_problem": 6041508249.6 + }, + "count.cmp16": { + "acc": 1.0, + "reasoning_bytes": 95.01, + "flops_per_problem": 5697477918.72 + }, + "count.cmp18": { + "acc": 0.988, + "reasoning_bytes": 104.48, + "flops_per_problem": 6204116680.704 + }, + "count.cmp20": { + "acc": 0.906, + "reasoning_bytes": 110.456, + "flops_per_problem": 6554153189.376 + }, + "count.runmax16": { + "acc": 0.996, + "reasoning_bytes": 96.03, + "flops_per_problem": 5786687324.16 + }, + "count.runmax18": { + "acc": 0.976, + "reasoning_bytes": 105.85, + "flops_per_problem": 6308694835.2 + }, + "count.runmax20": { + "acc": 0.734, + "reasoning_bytes": 111.69, + "flops_per_problem": 6656964820.992 + }, + "count.count16": { + "acc": 1.0, + "reasoning_bytes": 96.0, + "flops_per_problem": 5829525504.0 + }, + "count.count18": { + "acc": 1.0, + "reasoning_bytes": 105.95, + "flops_per_problem": 6357274214.4 + }, + "count.count20": { + "acc": 0.99, + "reasoning_bytes": 112.776, + "flops_per_problem": 6752268730.368 + }, + "count.find16": { + "acc": 1.0, + "reasoning_bytes": 96.02, + "flops_per_problem": 5786245693.44 + }, + "count.find18": { + "acc": 0.976, + "reasoning_bytes": 105.85, + "flops_per_problem": 6308694835.2 + }, + "count.find20": { + "acc": 0.9, + "reasoning_bytes": 112.234, + "flops_per_problem": 6677456486.4 + }, + "count.rev16": { + "acc": 0.998, + "reasoning_bytes": 91.02, + "flops_per_problem": 5432941117.44 + }, + "count.rev18": { + "acc": 0.912, + "reasoning_bytes": 100.264, + "flops_per_problem": 5930747265.024 + }, + "count.rev20": { + "acc": 0.672, + "reasoning_bytes": 106.966, + "flops_per_problem": 6313729425.408 + }, + "count.sumd16": { + "acc": 0.996, + "reasoning_bytes": 94.014, + "flops_per_problem": 5609328427.008 + }, + "count.sumd18": { + "acc": 0.836, + "reasoning_bytes": 103.59, + "flops_per_problem": 6122326671.36 + }, + "count.sumd20": { + "acc": 0.426, + "reasoning_bytes": 110.71, + "flops_per_problem": 6528273629.184 + }, + "count.inc16": { + "acc": 0.998, + "reasoning_bytes": 95.01, + "flops_per_problem": 5609151774.72 + }, + "count.inc18": { + "acc": 0.944, + "reasoning_bytes": 104.77, + "flops_per_problem": 6128509501.44 + }, + "count.inc20": { + "acc": 0.704, + "reasoning_bytes": 110.67, + "flops_per_problem": 6476337856.512 + }, + "parity.cmp16": { + "acc": 1.0, + "reasoning_bytes": 111.0, + "flops_per_problem": 6359482368.0 + }, + "parity.cmp20": { + "acc": 0.988, + "reasoning_bytes": 134.808, + "flops_per_problem": 7587569074.176 + }, + "parity.cmp24": { + "acc": 0.946, + "reasoning_bytes": 153.036, + "flops_per_problem": 8569225838.592 + }, + "parity.runmax16": { + "acc": 1.0, + "reasoning_bytes": 112.0, + "flops_per_problem": 6447808512.0 + }, + "parity.runmax20": { + "acc": 0.916, + "reasoning_bytes": 135.988, + "flops_per_problem": 7683844571.136 + }, + "parity.runmax24": { + "acc": 0.494, + "reasoning_bytes": 154.216, + "flops_per_problem": 8665501335.552 + }, + "parity.count16": { + "acc": 1.0, + "reasoning_bytes": 112.0, + "flops_per_problem": 6491971584.0 + }, + "parity.count20": { + "acc": 1.0, + "reasoning_bytes": 135.952, + "flops_per_problem": 7726417772.544 + }, + "parity.count24": { + "acc": 1.0, + "reasoning_bytes": 154.456, + "flops_per_problem": 8720263544.832 + }, + "parity.find16": { + "acc": 1.0, + "reasoning_bytes": 112.0, + "flops_per_problem": 6447808512.0 + }, + "parity.find20": { + "acc": 0.952, + "reasoning_bytes": 136.0, + "flops_per_problem": 7684374528.0 + }, + "parity.find24": { + "acc": 0.85, + "reasoning_bytes": 155.398, + "flops_per_problem": 8717702086.656 + }, + "parity.rev16": { + "acc": 1.0, + "reasoning_bytes": 107.0, + "flops_per_problem": 6094503936.0 + }, + "parity.rev20": { + "acc": 0.89, + "reasoning_bytes": 130.94, + "flops_per_problem": 7328420167.68 + }, + "parity.rev24": { + "acc": 0.484, + "reasoning_bytes": 151.88, + "flops_per_problem": 8434175164.416 + }, + "parity.sumd16": { + "acc": 1.0, + "reasoning_bytes": 110.0, + "flops_per_problem": 6271156224.0 + }, + "parity.sumd20": { + "acc": 0.912, + "reasoning_bytes": 133.976, + "flops_per_problem": 7506662326.272 + }, + "parity.sumd24": { + "acc": 0.516, + "reasoning_bytes": 153.41, + "flops_per_problem": 8542816321.536 + }, + "parity.inc16": { + "acc": 1.0, + "reasoning_bytes": 111.0, + "flops_per_problem": 6271156224.0 + }, + "parity.inc20": { + "acc": 0.872, + "reasoning_bytes": 135.0, + "flops_per_problem": 7507722240.0 + }, + "parity.inc24": { + "acc": 0.54, + "reasoning_bytes": 155.928, + "flops_per_problem": 8608619298.816 + }, + "sumd.cmp6": { + "acc": 1.0, + "reasoning_bytes": 62.088, + "flops_per_problem": 3713407746.048 + }, + "sumd.cmp7": { + "acc": 1.0, + "reasoning_bytes": 70.084, + "flops_per_problem": 4110875394.048 + }, + "sumd.cmp8": { + "acc": 0.986, + "reasoning_bytes": 77.696, + "flops_per_problem": 4491119443.968 + }, + "sumd.runmax6": { + "acc": 1.0, + "reasoning_bytes": 67.542, + "flops_per_problem": 3954449793.024 + }, + "sumd.runmax7": { + "acc": 0.998, + "reasoning_bytes": 75.48, + "flops_per_problem": 4349179330.56 + }, + "sumd.runmax8": { + "acc": 0.946, + "reasoning_bytes": 83.474, + "flops_per_problem": 4746382000.128 + }, + "sumd.count6": { + "acc": 1.0, + "reasoning_bytes": 66.428, + "flops_per_problem": 3949415202.816 + }, + "sumd.count7": { + "acc": 0.992, + "reasoning_bytes": 74.46, + "flops_per_problem": 4348296069.12 + }, + "sumd.count8": { + "acc": 0.934, + "reasoning_bytes": 82.392, + "flops_per_problem": 4742760628.224 + }, + "sumd.find6": { + "acc": 1.0, + "reasoning_bytes": 66.24, + "flops_per_problem": 3896949473.28 + }, + "sumd.find7": { + "acc": 0.998, + "reasoning_bytes": 74.44, + "flops_per_problem": 4303249735.68 + }, + "sumd.find8": { + "acc": 0.94, + "reasoning_bytes": 81.634, + "flops_per_problem": 4665121947.648 + }, + "sumd.rev6": { + "acc": 1.0, + "reasoning_bytes": 61.544, + "flops_per_problem": 3601145217.024 + }, + "sumd.rev7": { + "acc": 0.998, + "reasoning_bytes": 69.48, + "flops_per_problem": 3995874754.56 + }, + "sumd.rev8": { + "acc": 0.93, + "reasoning_bytes": 77.428, + "flops_per_problem": 4390957596.672 + }, + "sumd.sumd6": { + "acc": 1.0, + "reasoning_bytes": 65.744, + "flops_per_problem": 3795639386.112 + }, + "sumd.sumd7": { + "acc": 0.994, + "reasoning_bytes": 73.742, + "flops_per_problem": 4195668492.288 + }, + "sumd.sumd8": { + "acc": 0.95, + "reasoning_bytes": 81.81, + "flops_per_problem": 4597464121.344 + }, + "sumd.inc6": { + "acc": 1.0, + "reasoning_bytes": 68.538, + "flops_per_problem": 3910021742.592 + }, + "sumd.inc7": { + "acc": 0.998, + "reasoning_bytes": 76.48, + "flops_per_problem": 4305016258.56 + }, + "sumd.inc8": { + "acc": 0.928, + "reasoning_bytes": 84.358, + "flops_per_problem": 4697096011.776 + }, + "inc.cmp6": { + "acc": 1.0, + "reasoning_bytes": 78.624, + "flops_per_problem": 4576354172.928 + }, + "inc.cmp7": { + "acc": 0.998, + "reasoning_bytes": 89.788, + "flops_per_problem": 5157716852.736 + }, + "inc.cmp8": { + "acc": 0.976, + "reasoning_bytes": 100.584, + "flops_per_problem": 5722827522.048 + }, + "inc.runmax6": { + "acc": 1.0, + "reasoning_bytes": 104.0, + "flops_per_problem": 5520384000.0 + }, + "inc.runmax7": { + "acc": 0.974, + "reasoning_bytes": 120.0, + "flops_per_problem": 6271156224.0 + }, + "inc.runmax8": { + "acc": 0.926, + "reasoning_bytes": 135.38, + "flops_per_problem": 6994547343.36 + }, + "inc.count6": { + "acc": 0.988, + "reasoning_bytes": 99.0, + "flops_per_problem": 5343731712.0 + }, + "inc.count7": { + "acc": 0.916, + "reasoning_bytes": 114.0, + "flops_per_problem": 6050340864.0 + }, + "inc.count8": { + "acc": 0.602, + "reasoning_bytes": 124.286, + "flops_per_problem": 6548765294.592 + }, + "inc.find6": { + "acc": 0.934, + "reasoning_bytes": 91.88, + "flops_per_problem": 4985127567.36 + }, + "inc.find7": { + "acc": 0.862, + "reasoning_bytes": 102.564, + "flops_per_problem": 5501128900.608 + }, + "inc.find8": { + "acc": 0.26, + "reasoning_bytes": 90.538, + "flops_per_problem": 5014186868.736 + }, + "inc.rev6": { + "acc": 1.0, + "reasoning_bytes": 104.0, + "flops_per_problem": 5608710144.0 + }, + "inc.rev7": { + "acc": 0.966, + "reasoning_bytes": 123.996, + "flops_per_problem": 6579237814.272 + }, + "inc.rev8": { + "acc": 0.008, + "reasoning_bytes": 143.402, + "flops_per_problem": 7493236752.384 + }, + "inc.sumd6": { + "acc": 0.996, + "reasoning_bytes": 109.572, + "flops_per_problem": 5722297565.184 + }, + "inc.sumd7": { + "acc": 0.942, + "reasoning_bytes": 127.454, + "flops_per_problem": 6556096364.544 + }, + "inc.sumd8": { + "acc": 0.116, + "reasoning_bytes": 143.828, + "flops_per_problem": 7323473903.616 + }, + "inc.inc6": { + "acc": 1.0, + "reasoning_bytes": 113.0, + "flops_per_problem": 6006177792.0 + }, + "inc.inc7": { + "acc": 0.992, + "reasoning_bytes": 131.0, + "flops_per_problem": 6889350905.856 + }, + "inc.inc8": { + "acc": 0.112, + "reasoning_bytes": 147.166, + "flops_per_problem": 7683756244.992 + }, + "runmax.runmax.cmp12": { + "acc": 1.0, + "reasoning_bytes": 104.0, + "flops_per_problem": 6182830080.0 + }, + "runmax.runmax.cmp14": { + "acc": 1.0, + "reasoning_bytes": 115.22, + "flops_per_problem": 6766665891.84 + }, + "runmax.runmax.cmp16": { + "acc": 0.992, + "reasoning_bytes": 122.036, + "flops_per_problem": 7156007534.592 + }, + "sumd.runmax.cmp6": { + "acc": 1.0, + "reasoning_bytes": 83.338, + "flops_per_problem": 4917028110.336 + }, + "sumd.runmax.cmp7": { + "acc": 0.996, + "reasoning_bytes": 91.532, + "flops_per_problem": 5323063394.304 + }, + "sumd.runmax.cmp8": { + "acc": 0.826, + "reasoning_bytes": 96.43, + "flops_per_problem": 5583537192.96 + }, + "add.runmax.cmp6": { + "acc": 1.0, + "reasoning_bytes": 137.024, + "flops_per_problem": 7552945225.728 + }, + "add.runmax.cmp7": { + "acc": 0.946, + "reasoning_bytes": 154.928, + "flops_per_problem": 8431967010.816 + }, + "add.runmax.cmp8": { + "acc": 0.894, + "reasoning_bytes": 171.184, + "flops_per_problem": 9238208053.248 + }, + "count.runmax.runmax16": { + "acc": 0.996, + "reasoning_bytes": 113.02, + "flops_per_problem": 6846159421.44 + }, + "count.runmax.runmax18": { + "acc": 0.976, + "reasoning_bytes": 122.85, + "flops_per_problem": 7368608563.2 + }, + "count.runmax.runmax20": { + "acc": 0.794, + "reasoning_bytes": 128.664, + "flops_per_problem": 7713698807.808 + }, + "add.runmax.runmax6": { + "acc": 1.0, + "reasoning_bytes": 137.832, + "flops_per_problem": 7632792059.904 + }, + "add.runmax.runmax7": { + "acc": 0.832, + "reasoning_bytes": 155.848, + "flops_per_problem": 8516760109.056 + }, + "add.runmax.runmax8": { + "acc": 0.624, + "reasoning_bytes": 173.43, + "flops_per_problem": 9381561384.96 + }, + "parity.runmax.runmax16": { + "acc": 1.0, + "reasoning_bytes": 129.0, + "flops_per_problem": 7507722240.0 + }, + "parity.runmax.runmax20": { + "acc": 0.878, + "reasoning_bytes": 152.052, + "flops_per_problem": 8702421663.744 + }, + "parity.runmax.runmax24": { + "acc": 0.558, + "reasoning_bytes": 171.0, + "flops_per_problem": 9715875840.0 + }, + "parity.runmax.count16": { + "acc": 1.0, + "reasoning_bytes": 129.0, + "flops_per_problem": 7551885312.0 + }, + "parity.runmax.count20": { + "acc": 1.0, + "reasoning_bytes": 152.856, + "flops_per_problem": 8782091845.632 + }, + "parity.runmax.count24": { + "acc": 1.0, + "reasoning_bytes": 171.0, + "flops_per_problem": 9760038912.0 + }, + "inc.runmax.count6": { + "acc": 1.0, + "reasoning_bytes": 121.0, + "flops_per_problem": 6624460800.0 + }, + "inc.runmax.count7": { + "acc": 0.998, + "reasoning_bytes": 137.0, + "flops_per_problem": 7375233024.0 + }, + "inc.runmax.count8": { + "acc": 0.998, + "reasoning_bytes": 148.58, + "flops_per_problem": 7930804469.76 + }, + "sumd.runmax.count6": { + "acc": 1.0, + "reasoning_bytes": 84.424, + "flops_per_problem": 5053315350.528 + }, + "sumd.runmax.count7": { + "acc": 1.0, + "reasoning_bytes": 92.46, + "flops_per_problem": 5452372869.12 + }, + "sumd.runmax.count8": { + "acc": 0.95, + "reasoning_bytes": 99.492, + "flops_per_problem": 5807090663.424 + }, + "runmax.runmax.find12": { + "acc": 1.0, + "reasoning_bytes": 105.0, + "flops_per_problem": 6271156224.0 + }, + "runmax.runmax.find14": { + "acc": 1.0, + "reasoning_bytes": 115.764, + "flops_per_problem": 6834853675.008 + }, + "runmax.runmax.find16": { + "acc": 0.984, + "reasoning_bytes": 123.0, + "flops_per_problem": 7242743808.0 + }, + "add.runmax.find6": { + "acc": 1.0, + "reasoning_bytes": 137.928, + "flops_per_problem": 7637031714.816 + }, + "add.runmax.find7": { + "acc": 0.984, + "reasoning_bytes": 155.608, + "flops_per_problem": 8506160971.776 + }, + "add.runmax.find8": { + "acc": 0.872, + "reasoning_bytes": 172.934, + "flops_per_problem": 9359656501.248 + }, + "parity.runmax.find16": { + "acc": 1.0, + "reasoning_bytes": 129.0, + "flops_per_problem": 7507722240.0 + }, + "parity.runmax.find20": { + "acc": 0.978, + "reasoning_bytes": 152.928, + "flops_per_problem": 8741108514.816 + }, + "parity.runmax.find24": { + "acc": 0.898, + "reasoning_bytes": 170.998, + "flops_per_problem": 9715787513.856 + }, + "add.runmax.rev6": { + "acc": 1.0, + "reasoning_bytes": 132.832, + "flops_per_problem": 7279487483.904 + }, + "add.runmax.rev7": { + "acc": 0.902, + "reasoning_bytes": 150.848, + "flops_per_problem": 8163455533.056 + }, + "add.runmax.rev8": { + "acc": 0.594, + "reasoning_bytes": 168.278, + "flops_per_problem": 9021544022.016 + }, + "parity.runmax.rev16": { + "acc": 1.0, + "reasoning_bytes": 124.0, + "flops_per_problem": 7154417664.0 + }, + "parity.runmax.rev20": { + "acc": 0.866, + "reasoning_bytes": 147.34, + "flops_per_problem": 8361836052.48 + }, + "parity.runmax.rev24": { + "acc": 0.498, + "reasoning_bytes": 165.978, + "flops_per_problem": 9361599676.416 + }, + "sumd.runmax.rev6": { + "acc": 1.0, + "reasoning_bytes": 79.542, + "flops_per_problem": 4661058945.024 + }, + "sumd.runmax.rev7": { + "acc": 0.996, + "reasoning_bytes": 87.478, + "flops_per_problem": 5055700156.416 + }, + "sumd.runmax.rev8": { + "acc": 0.81, + "reasoning_bytes": 94.12, + "flops_per_problem": 5393194352.64 + }, + "sumd.runmax.sumd6": { + "acc": 1.0, + "reasoning_bytes": 82.542, + "flops_per_problem": 4837711233.024 + }, + "sumd.runmax.sumd7": { + "acc": 0.996, + "reasoning_bytes": 90.478, + "flops_per_problem": 5232352444.416 + }, + "sumd.runmax.sumd8": { + "acc": 0.862, + "reasoning_bytes": 97.864, + "flops_per_problem": 5602703966.208 + }, + "add.runmax.sumd6": { + "acc": 1.0, + "reasoning_bytes": 135.832, + "flops_per_problem": 7456139771.904 + }, + "add.runmax.sumd7": { + "acc": 0.894, + "reasoning_bytes": 153.848, + "flops_per_problem": 8340107821.056 + }, + "add.runmax.sumd8": { + "acc": 0.632, + "reasoning_bytes": 171.516, + "flops_per_problem": 9208707121.152 + }, + "parity.runmax.sumd16": { + "acc": 1.0, + "reasoning_bytes": 127.0, + "flops_per_problem": 7331069952.0 + }, + "parity.runmax.sumd20": { + "acc": 0.862, + "reasoning_bytes": 150.16, + "flops_per_problem": 8530538987.52 + }, + "parity.runmax.sumd24": { + "acc": 0.532, + "reasoning_bytes": 169.0, + "flops_per_problem": 9539223552.0 + }, + "count.runmax.inc16": { + "acc": 0.996, + "reasoning_bytes": 112.02, + "flops_per_problem": 6669507133.44 + }, + "count.runmax.inc18": { + "acc": 0.958, + "reasoning_bytes": 121.61, + "flops_per_problem": 7181357137.92 + }, + "count.runmax.inc20": { + "acc": 0.748, + "reasoning_bytes": 127.264, + "flops_per_problem": 7519557943.296 + }, + "runmax.runmax.inc12": { + "acc": 1.0, + "reasoning_bytes": 104.0, + "flops_per_problem": 6125683064.832 + }, + "runmax.runmax.inc14": { + "acc": 1.0, + "reasoning_bytes": 114.908, + "flops_per_problem": 6699096391.68 + }, + "runmax.runmax.inc16": { + "acc": 0.966, + "reasoning_bytes": 122.0, + "flops_per_problem": 7101863608.32 + }, + "add.runmax.inc6": { + "acc": 1.0, + "reasoning_bytes": 136.832, + "flops_per_problem": 7477161394.176 + }, + "add.runmax.inc7": { + "acc": 0.858, + "reasoning_bytes": 154.848, + "flops_per_problem": 8363602575.36 + }, + "add.runmax.inc8": { + "acc": 0.62, + "reasoning_bytes": 172.452, + "flops_per_problem": 9231141961.728 + }, + "count.count.cmp16": { + "acc": 1.0, + "reasoning_bytes": 112.02, + "flops_per_problem": 6801996349.44 + }, + "count.count.cmp18": { + "acc": 0.996, + "reasoning_bytes": 121.982, + "flops_per_problem": 7330275016.704 + }, + "count.count.cmp20": { + "acc": 0.976, + "reasoning_bytes": 128.658, + "flops_per_problem": 7712992198.656 + }, + "add.count.cmp6": { + "acc": 0.994, + "reasoning_bytes": 131.354, + "flops_per_problem": 7346703679.488 + }, + "add.count.cmp7": { + "acc": 0.904, + "reasoning_bytes": 148.176, + "flops_per_problem": 8177941020.672 + }, + "add.count.cmp8": { + "acc": 0.866, + "reasoning_bytes": 163.29, + "flops_per_problem": 8933747834.88 + }, + "sumd.count.cmp6": { + "acc": 1.0, + "reasoning_bytes": 82.492, + "flops_per_problem": 4923829223.424 + }, + "sumd.count.cmp7": { + "acc": 1.0, + "reasoning_bytes": 90.508, + "flops_per_problem": 5322003480.576 + }, + "sumd.count.cmp8": { + "acc": 0.956, + "reasoning_bytes": 92.646, + "flops_per_problem": 5460587200.512 + }, + "add.count.runmax6": { + "acc": 0.984, + "reasoning_bytes": 132.648, + "flops_per_problem": 7448013766.656 + }, + "add.count.runmax7": { + "acc": 0.874, + "reasoning_bytes": 149.086, + "flops_per_problem": 8262292488.192 + }, + "add.count.runmax8": { + "acc": 0.462, + "reasoning_bytes": 165.602, + "flops_per_problem": 9080015929.344 + }, + "sumd.count.runmax6": { + "acc": 1.0, + "reasoning_bytes": 83.428, + "flops_per_problem": 5009328930.816 + }, + "sumd.count.runmax7": { + "acc": 0.99, + "reasoning_bytes": 91.458, + "flops_per_problem": 5408121470.976 + }, + "sumd.count.runmax8": { + "acc": 0.82, + "reasoning_bytes": 98.156, + "flops_per_problem": 5748088799.232 + }, + "inc.count.runmax6": { + "acc": 0.988, + "reasoning_bytes": 116.0, + "flops_per_problem": 6403645440.0 + }, + "inc.count.runmax7": { + "acc": 0.68, + "reasoning_bytes": 130.972, + "flops_per_problem": 7109018025.984 + }, + "inc.count.runmax8": { + "acc": 0.722, + "reasoning_bytes": 137.374, + "flops_per_problem": 7435913084.928 + }, + "parity.count.count16": { + "acc": 1.0, + "reasoning_bytes": 129.0, + "flops_per_problem": 7596048384.0 + }, + "parity.count.count20": { + "acc": 1.0, + "reasoning_bytes": 152.592, + "flops_per_problem": 8814595866.624 + }, + "parity.count.count24": { + "acc": 1.0, + "reasoning_bytes": 171.0, + "flops_per_problem": 9804201984.0 + }, + "runmax.count.count12": { + "acc": 1.0, + "reasoning_bytes": 105.0, + "flops_per_problem": 6359482368.0 + }, + "runmax.count.count14": { + "acc": 1.0, + "reasoning_bytes": 115.692, + "flops_per_problem": 6920000077.824 + }, + "runmax.count.count16": { + "acc": 1.0, + "reasoning_bytes": 123.024, + "flops_per_problem": 7332129865.728 + }, + "inc.count.count6": { + "acc": 0.998, + "reasoning_bytes": 116.0, + "flops_per_problem": 6447808512.0 + }, + "inc.count.count7": { + "acc": 0.978, + "reasoning_bytes": 130.986, + "flops_per_problem": 7153799380.992 + }, + "inc.count.count8": { + "acc": 0.972, + "reasoning_bytes": 132.524, + "flops_per_problem": 7265885257.728 + }, + "inc.count.find6": { + "acc": 1.0, + "reasoning_bytes": 116.0, + "flops_per_problem": 6403645440.0 + }, + "inc.count.find7": { + "acc": 0.94, + "reasoning_bytes": 130.986, + "flops_per_problem": 7109636308.992 + }, + "inc.count.find8": { + "acc": 0.916, + "reasoning_bytes": 129.738, + "flops_per_problem": 7098683867.136 + }, + "add.count.find6": { + "acc": 0.996, + "reasoning_bytes": 132.326, + "flops_per_problem": 7433793257.472 + }, + "add.count.find7": { + "acc": 0.95, + "reasoning_bytes": 149.156, + "flops_per_problem": 8265383903.232 + }, + "add.count.find8": { + "acc": 0.838, + "reasoning_bytes": 165.43, + "flops_per_problem": 9072243228.672 + }, + "runmax.count.find12": { + "acc": 1.0, + "reasoning_bytes": 105.0, + "flops_per_problem": 6315319296.0 + }, + "runmax.count.find14": { + "acc": 1.0, + "reasoning_bytes": 115.62, + "flops_per_problem": 6872657264.64 + }, + "runmax.count.find16": { + "acc": 1.0, + "reasoning_bytes": 123.012, + "flops_per_problem": 7287436836.864 + }, + "parity.count.rev16": { + "acc": 1.0, + "reasoning_bytes": 124.0, + "flops_per_problem": 7198580736.0 + }, + "parity.count.rev20": { + "acc": 1.0, + "reasoning_bytes": 147.76, + "flops_per_problem": 8424547614.72 + }, + "parity.count.rev24": { + "acc": 1.0, + "reasoning_bytes": 166.012, + "flops_per_problem": 9407264292.864 + }, + "inc.count.rev6": { + "acc": 0.988, + "reasoning_bytes": 111.0, + "flops_per_problem": 6050340864.0 + }, + "inc.count.rev7": { + "acc": 0.896, + "reasoning_bytes": 125.986, + "flops_per_problem": 6756331732.992 + }, + "inc.count.rev8": { + "acc": 0.734, + "reasoning_bytes": 131.314, + "flops_per_problem": 7035795652.608 + }, + "runmax.count.rev12": { + "acc": 1.0, + "reasoning_bytes": 100.0, + "flops_per_problem": 5962014720.0 + }, + "runmax.count.rev14": { + "acc": 1.0, + "reasoning_bytes": 111.328, + "flops_per_problem": 6550620143.616 + }, + "runmax.count.rev16": { + "acc": 1.0, + "reasoning_bytes": 118.012, + "flops_per_problem": 6934132260.864 + }, + "count.count.sumd16": { + "acc": 1.0, + "reasoning_bytes": 111.01, + "flops_per_problem": 6713228574.72 + }, + "count.count.sumd18": { + "acc": 1.0, + "reasoning_bytes": 120.91, + "flops_per_problem": 7238769131.52 + }, + "count.count.sumd20": { + "acc": 0.998, + "reasoning_bytes": 127.304, + "flops_per_problem": 7609120653.312 + }, + "runmax.count.sumd12": { + "acc": 1.0, + "reasoning_bytes": 103.0, + "flops_per_problem": 6138667008.0 + }, + "runmax.count.sumd14": { + "acc": 1.0, + "reasoning_bytes": 114.508, + "flops_per_problem": 6735221784.576 + }, + "runmax.count.sumd16": { + "acc": 1.0, + "reasoning_bytes": 121.04, + "flops_per_problem": 7112021114.88 + }, + "sumd.count.sumd6": { + "acc": 1.0, + "reasoning_bytes": 81.428, + "flops_per_problem": 4832676642.816 + }, + "sumd.count.sumd7": { + "acc": 0.99, + "reasoning_bytes": 89.468, + "flops_per_problem": 5231910813.696 + }, + "sumd.count.sumd8": { + "acc": 0.854, + "reasoning_bytes": 96.426, + "flops_per_problem": 5583360540.672 + }, + "parity.count.inc16": { + "acc": 1.0, + "reasoning_bytes": 128.0, + "flops_per_problem": 7375233024.0 + }, + "parity.count.inc20": { + "acc": 1.0, + "reasoning_bytes": 151.772, + "flops_per_problem": 8601729859.584 + }, + "parity.count.inc24": { + "acc": 1.0, + "reasoning_bytes": 170.012, + "flops_per_problem": 9583916580.864 + }, + "count.count.inc16": { + "acc": 1.0, + "reasoning_bytes": 112.01, + "flops_per_problem": 6713228574.72 + }, + "count.count.inc18": { + "acc": 1.0, + "reasoning_bytes": 121.91, + "flops_per_problem": 7238769131.52 + }, + "count.count.inc20": { + "acc": 0.988, + "reasoning_bytes": 128.436, + "flops_per_problem": 7612742025.216 + }, + "add.count.inc6": { + "acc": 0.988, + "reasoning_bytes": 131.648, + "flops_per_problem": 7271361478.656 + }, + "add.count.inc7": { + "acc": 0.836, + "reasoning_bytes": 148.084, + "flops_per_problem": 8085551874.048 + }, + "add.count.inc8": { + "acc": 0.462, + "reasoning_bytes": 164.448, + "flops_per_problem": 8896562528.256 + }, + "parity.rev.cmp16": { + "acc": 1.0, + "reasoning_bytes": 123.0, + "flops_per_problem": 7066091520.0 + }, + "parity.rev.cmp20": { + "acc": 0.984, + "reasoning_bytes": 145.62, + "flops_per_problem": 8241712496.64 + }, + "parity.rev.cmp24": { + "acc": 0.942, + "reasoning_bytes": 164.856, + "flops_per_problem": 9267885637.632 + }, + "sumd.rev.cmp6": { + "acc": 0.998, + "reasoning_bytes": 81.06, + "flops_per_problem": 4727921836.032 + }, + "sumd.rev.cmp7": { + "acc": 0.998, + "reasoning_bytes": 89.05, + "flops_per_problem": 5125124505.6 + }, + "sumd.rev.cmp8": { + "acc": 0.788, + "reasoning_bytes": 92.584, + "flops_per_problem": 5325271547.904 + }, + "add.rev.cmp6": { + "acc": 0.996, + "reasoning_bytes": 157.314, + "flops_per_problem": 8565692792.832 + }, + "add.rev.cmp7": { + "acc": 0.98, + "reasoning_bytes": 181.806, + "flops_per_problem": 9777085857.792 + }, + "add.rev.cmp8": { + "acc": 0.79, + "reasoning_bytes": 199.478, + "flops_per_problem": 10691526426.624 + }, + "runmax.rev.runmax12": { + "acc": 1.0, + "reasoning_bytes": 100.0, + "flops_per_problem": 5917851648.0 + }, + "runmax.rev.runmax14": { + "acc": 1.0, + "reasoning_bytes": 111.496, + "flops_per_problem": 6513876467.712 + }, + "runmax.rev.runmax16": { + "acc": 0.966, + "reasoning_bytes": 118.012, + "flops_per_problem": 6889969188.864 + }, + "count.rev.runmax16": { + "acc": 0.996, + "reasoning_bytes": 108.02, + "flops_per_problem": 6492854845.44 + }, + "count.rev.runmax18": { + "acc": 0.98, + "reasoning_bytes": 117.81, + "flops_per_problem": 7013537464.32 + }, + "count.rev.runmax20": { + "acc": 0.776, + "reasoning_bytes": 123.334, + "flops_per_problem": 7345820418.048 + }, + "add.rev.runmax6": { + "acc": 1.0, + "reasoning_bytes": 185.08, + "flops_per_problem": 9586919669.76 + }, + "add.rev.runmax7": { + "acc": 0.884, + "reasoning_bytes": 215.616, + "flops_per_problem": 11023809380.352 + }, + "add.rev.runmax8": { + "acc": 0.632, + "reasoning_bytes": 243.736, + "flops_per_problem": 12354001108.992 + }, + "inc.rev.count6": { + "acc": 0.958, + "reasoning_bytes": 156.0, + "flops_per_problem": 8037679104.0 + }, + "inc.rev.count7": { + "acc": 0.824, + "reasoning_bytes": 182.774, + "flops_per_problem": 9264264265.728 + }, + "inc.rev.count8": { + "acc": 0.62, + "reasoning_bytes": 191.216, + "flops_per_problem": 9681251991.552 + }, + "count.rev.count16": { + "acc": 1.0, + "reasoning_bytes": 108.01, + "flops_per_problem": 6536576286.72 + }, + "count.rev.count18": { + "acc": 0.996, + "reasoning_bytes": 117.892, + "flops_per_problem": 7061321908.224 + }, + "count.rev.count20": { + "acc": 0.992, + "reasoning_bytes": 124.502, + "flops_per_problem": 7438651195.392 + }, + "parity.rev.count16": { + "acc": 1.0, + "reasoning_bytes": 124.0, + "flops_per_problem": 7198580736.0 + }, + "parity.rev.count20": { + "acc": 1.0, + "reasoning_bytes": 147.844, + "flops_per_problem": 8428257312.768 + }, + "parity.rev.count24": { + "acc": 1.0, + "reasoning_bytes": 166.012, + "flops_per_problem": 9407264292.864 + }, + "sumd.rev.find6": { + "acc": 1.0, + "reasoning_bytes": 85.208, + "flops_per_problem": 4911286910.976 + }, + "sumd.rev.find7": { + "acc": 0.998, + "reasoning_bytes": 93.482, + "flops_per_problem": 5320855240.704 + }, + "sumd.rev.find8": { + "acc": 0.854, + "reasoning_bytes": 98.508, + "flops_per_problem": 5586981912.576 + }, + "runmax.rev.find12": { + "acc": 1.0, + "reasoning_bytes": 100.0, + "flops_per_problem": 5917851648.0 + }, + "runmax.rev.find14": { + "acc": 1.0, + "reasoning_bytes": 111.04, + "flops_per_problem": 6493738106.88 + }, + "runmax.rev.find16": { + "acc": 0.986, + "reasoning_bytes": 118.012, + "flops_per_problem": 6889969188.864 + }, + "count.rev.find16": { + "acc": 1.0, + "reasoning_bytes": 108.01, + "flops_per_problem": 6492413214.72 + }, + "count.rev.find18": { + "acc": 0.988, + "reasoning_bytes": 117.7, + "flops_per_problem": 7008679526.4 + }, + "count.rev.find20": { + "acc": 0.926, + "reasoning_bytes": 123.596, + "flops_per_problem": 7355801272.32 + }, + "count.rev.rev16": { + "acc": 0.998, + "reasoning_bytes": 103.02, + "flops_per_problem": 6139550269.44 + }, + "count.rev.rev18": { + "acc": 0.93, + "reasoning_bytes": 112.24, + "flops_per_problem": 6635059937.28 + }, + "count.rev.rev20": { + "acc": 0.738, + "reasoning_bytes": 118.28, + "flops_per_problem": 6989336100.864 + }, + "sumd.rev.rev6": { + "acc": 1.0, + "reasoning_bytes": 80.53, + "flops_per_problem": 4616277590.016 + }, + "sumd.rev.rev7": { + "acc": 0.988, + "reasoning_bytes": 88.462, + "flops_per_problem": 5010830475.264 + }, + "sumd.rev.rev8": { + "acc": 0.53, + "reasoning_bytes": 92.802, + "flops_per_problem": 5246572953.6 + }, + "parity.rev.rev16": { + "acc": 1.0, + "reasoning_bytes": 119.0, + "flops_per_problem": 6801113088.0 + }, + "parity.rev.rev20": { + "acc": 0.788, + "reasoning_bytes": 141.968, + "flops_per_problem": 7992102813.696 + }, + "parity.rev.rev24": { + "acc": 0.472, + "reasoning_bytes": 160.964, + "flops_per_problem": 9007676817.408 + }, + "sumd.rev.sumd6": { + "acc": 1.0, + "reasoning_bytes": 84.73, + "flops_per_problem": 4810771759.104 + }, + "sumd.rev.sumd7": { + "acc": 0.994, + "reasoning_bytes": 92.738, + "flops_per_problem": 5211154169.856 + }, + "sumd.rev.sumd8": { + "acc": 0.788, + "reasoning_bytes": 99.136, + "flops_per_problem": 5538667511.808 + }, + "parity.rev.sumd16": { + "acc": 1.0, + "reasoning_bytes": 122.0, + "flops_per_problem": 6977765376.0 + }, + "parity.rev.sumd20": { + "acc": 0.866, + "reasoning_bytes": 145.508, + "flops_per_problem": 8192603160.576 + }, + "parity.rev.sumd24": { + "acc": 0.49, + "reasoning_bytes": 163.988, + "flops_per_problem": 9185389019.136 + }, + "add.rev.sumd6": { + "acc": 0.97, + "reasoning_bytes": 191.642, + "flops_per_problem": 9832378023.936 + }, + "add.rev.sumd7": { + "acc": 0.498, + "reasoning_bytes": 223.896, + "flops_per_problem": 11344609935.36 + }, + "add.rev.sumd8": { + "acc": 0.036, + "reasoning_bytes": 250.126, + "flops_per_problem": 12591510110.208 + }, + "parity.rev.inc16": { + "acc": 1.0, + "reasoning_bytes": 123.0, + "flops_per_problem": 6977765376.0 + }, + "parity.rev.inc20": { + "acc": 0.844, + "reasoning_bytes": 146.7, + "flops_per_problem": 8201082470.4 + }, + "parity.rev.inc24": { + "acc": 0.466, + "reasoning_bytes": 165.0, + "flops_per_problem": 9185918976.0 + }, + "runmax.rev.inc12": { + "acc": 1.0, + "reasoning_bytes": 99.0, + "flops_per_problem": 5772378488.832 + }, + "runmax.rev.inc14": { + "acc": 0.994, + "reasoning_bytes": 109.236, + "flops_per_problem": 6315937579.008 + }, + "runmax.rev.inc16": { + "acc": 0.952, + "reasoning_bytes": 117.0, + "flops_per_problem": 6748029075.456 + }, + "inc.rev.inc6": { + "acc": 0.982, + "reasoning_bytes": 170.0, + "flops_per_problem": 8696150507.52 + }, + "inc.rev.inc7": { + "acc": 0.714, + "reasoning_bytes": 199.77, + "flops_per_problem": 10099564609.536 + }, + "inc.rev.inc8": { + "acc": 0.016, + "reasoning_bytes": 213.076, + "flops_per_problem": 10741430697.984 + }, + "parity.sumd.cmp16": { + "acc": 1.0, + "reasoning_bytes": 126.0, + "flops_per_problem": 7242743808.0 + }, + "parity.sumd.cmp20": { + "acc": 0.98, + "reasoning_bytes": 148.572, + "flops_per_problem": 8416244957.184 + }, + "parity.sumd.cmp24": { + "acc": 0.958, + "reasoning_bytes": 167.892, + "flops_per_problem": 9446127796.224 + }, + "runmax.sumd.cmp12": { + "acc": 1.0, + "reasoning_bytes": 102.0, + "flops_per_problem": 6006177792.0 + }, + "runmax.sumd.cmp14": { + "acc": 1.0, + "reasoning_bytes": 113.34, + "flops_per_problem": 6595313172.48 + }, + "runmax.sumd.cmp16": { + "acc": 0.992, + "reasoning_bytes": 120.036, + "flops_per_problem": 6979355246.592 + }, + "count.sumd.cmp16": { + "acc": 1.0, + "reasoning_bytes": 110.01, + "flops_per_problem": 6580739358.72 + }, + "count.sumd.cmp18": { + "acc": 0.988, + "reasoning_bytes": 119.18, + "flops_per_problem": 7074040872.96 + }, + "count.sumd.cmp20": { + "acc": 0.956, + "reasoning_bytes": 125.232, + "flops_per_problem": 7428670341.12 + }, + "sumd.sumd.runmax6": { + "acc": 1.0, + "reasoning_bytes": 84.36, + "flops_per_problem": 4917999697.92 + }, + "sumd.sumd.runmax7": { + "acc": 0.994, + "reasoning_bytes": 92.818, + "flops_per_problem": 5335694032.896 + }, + "sumd.sumd.runmax8": { + "acc": 0.85, + "reasoning_bytes": 100.484, + "flops_per_problem": 5718411214.848 + }, + "count.sumd.runmax16": { + "acc": 0.996, + "reasoning_bytes": 111.02, + "flops_per_problem": 6669507133.44 + }, + "count.sumd.runmax18": { + "acc": 0.964, + "reasoning_bytes": 120.59, + "flops_per_problem": 7180473876.48 + }, + "count.sumd.runmax20": { + "acc": 0.772, + "reasoning_bytes": 126.336, + "flops_per_problem": 7522561032.192 + }, + "add.sumd.runmax6": { + "acc": 0.998, + "reasoning_bytes": 151.444, + "flops_per_problem": 8145613651.968 + }, + "add.sumd.runmax7": { + "acc": 0.54, + "reasoning_bytes": 171.272, + "flops_per_problem": 9109605187.584 + }, + "add.sumd.runmax8": { + "acc": 0.198, + "reasoning_bytes": 190.176, + "flops_per_problem": 10033320001.536 + }, + "parity.sumd.count16": { + "acc": 1.0, + "reasoning_bytes": 127.0, + "flops_per_problem": 7375233024.0 + }, + "parity.sumd.count20": { + "acc": 1.0, + "reasoning_bytes": 150.784, + "flops_per_problem": 8602259816.448 + }, + "parity.sumd.count24": { + "acc": 1.0, + "reasoning_bytes": 169.0, + "flops_per_problem": 9583386624.0 + }, + "sumd.sumd.count6": { + "acc": 1.0, + "reasoning_bytes": 84.184, + "flops_per_problem": 4954390069.248 + }, + "sumd.sumd.count7": { + "acc": 0.998, + "reasoning_bytes": 92.476, + "flops_per_problem": 5364753334.272 + }, + "sumd.sumd.count8": { + "acc": 0.886, + "reasoning_bytes": 99.47, + "flops_per_problem": 5717792931.84 + }, + "add.sumd.count6": { + "acc": 1.0, + "reasoning_bytes": 150.516, + "flops_per_problem": 8148793393.152 + }, + "add.sumd.count7": { + "acc": 0.818, + "reasoning_bytes": 170.07, + "flops_per_problem": 9100949225.472 + }, + "add.sumd.count8": { + "acc": 0.488, + "reasoning_bytes": 189.254, + "flops_per_problem": 10037471330.304 + }, + "runmax.sumd.find12": { + "acc": 1.0, + "reasoning_bytes": 103.0, + "flops_per_problem": 6094503936.0 + }, + "runmax.sumd.find14": { + "acc": 1.0, + "reasoning_bytes": 113.8, + "flops_per_problem": 6659791257.6 + }, + "runmax.sumd.find16": { + "acc": 0.988, + "reasoning_bytes": 121.0, + "flops_per_problem": 7066091520.0 + }, + "sumd.sumd.find6": { + "acc": 1.0, + "reasoning_bytes": 84.064, + "flops_per_problem": 4904927428.608 + }, + "sumd.sumd.find7": { + "acc": 0.996, + "reasoning_bytes": 92.364, + "flops_per_problem": 5315643998.208 + }, + "sumd.sumd.find8": { + "acc": 0.946, + "reasoning_bytes": 99.118, + "flops_per_problem": 5658084458.496 + }, + "parity.sumd.find16": { + "acc": 1.0, + "reasoning_bytes": 127.0, + "flops_per_problem": 7331069952.0 + }, + "parity.sumd.find20": { + "acc": 0.968, + "reasoning_bytes": 150.688, + "flops_per_problem": 8553857089.536 + }, + "parity.sumd.find24": { + "acc": 0.888, + "reasoning_bytes": 169.0, + "flops_per_problem": 9539223552.0 + }, + "count.sumd.rev16": { + "acc": 0.998, + "reasoning_bytes": 106.02, + "flops_per_problem": 6316202557.44 + }, + "count.sumd.rev18": { + "acc": 0.932, + "reasoning_bytes": 114.85, + "flops_per_problem": 6794488627.2 + }, + "count.sumd.rev20": { + "acc": 0.74, + "reasoning_bytes": 121.136, + "flops_per_problem": 7160158863.36 + }, + "parity.sumd.rev16": { + "acc": 1.0, + "reasoning_bytes": 122.0, + "flops_per_problem": 6977765376.0 + }, + "parity.sumd.rev20": { + "acc": 0.858, + "reasoning_bytes": 145.4, + "flops_per_problem": 8187833548.8 + }, + "parity.sumd.rev24": { + "acc": 0.49, + "reasoning_bytes": 163.976, + "flops_per_problem": 9184859062.272 + }, + "add.sumd.rev6": { + "acc": 0.994, + "reasoning_bytes": 145.448, + "flops_per_problem": 7792309075.968 + }, + "add.sumd.rev7": { + "acc": 0.554, + "reasoning_bytes": 165.316, + "flops_per_problem": 8758155460.608 + }, + "add.sumd.rev8": { + "acc": 0.054, + "reasoning_bytes": 184.476, + "flops_per_problem": 9692646064.128 + }, + "parity.sumd.sumd16": { + "acc": 1.0, + "reasoning_bytes": 125.0, + "flops_per_problem": 7154417664.0 + }, + "parity.sumd.sumd20": { + "acc": 0.854, + "reasoning_bytes": 148.052, + "flops_per_problem": 8349117087.744 + }, + "parity.sumd.sumd24": { + "acc": 0.53, + "reasoning_bytes": 166.976, + "flops_per_problem": 9361511350.272 + }, + "add.sumd.sumd6": { + "acc": 0.998, + "reasoning_bytes": 149.642, + "flops_per_problem": 7986449940.48 + }, + "add.sumd.sumd7": { + "acc": 0.534, + "reasoning_bytes": 169.568, + "flops_per_problem": 8957065936.896 + }, + "add.sumd.sumd8": { + "acc": 0.088, + "reasoning_bytes": 188.302, + "flops_per_problem": 9872566419.456 + }, + "count.sumd.sumd16": { + "acc": 0.996, + "reasoning_bytes": 109.02, + "flops_per_problem": 6492854845.44 + }, + "count.sumd.sumd18": { + "acc": 0.956, + "reasoning_bytes": 118.06, + "flops_per_problem": 6980415160.32 + }, + "count.sumd.sumd20": { + "acc": 0.73, + "reasoning_bytes": 124.256, + "flops_per_problem": 7342375698.432 + }, + "inc.sumd.inc6": { + "acc": 1.0, + "reasoning_bytes": 135.538, + "flops_per_problem": 7045688180.736 + }, + "inc.sumd.inc7": { + "acc": 0.718, + "reasoning_bytes": 153.406, + "flops_per_problem": 7878957023.232 + }, + "inc.sumd.inc8": { + "acc": 0.078, + "reasoning_bytes": 163.558, + "flops_per_problem": 8370050383.872 + }, + "sumd.sumd.inc6": { + "acc": 1.0, + "reasoning_bytes": 83.764, + "flops_per_problem": 4773586452.48 + }, + "sumd.sumd.inc7": { + "acc": 0.994, + "reasoning_bytes": 92.338, + "flops_per_problem": 5199141814.272 + }, + "sumd.sumd.inc8": { + "acc": 0.804, + "reasoning_bytes": 99.122, + "flops_per_problem": 5543260471.296 + }, + "parity.sumd.inc16": { + "acc": 1.0, + "reasoning_bytes": 126.0, + "flops_per_problem": 7154417664.0 + }, + "parity.sumd.inc20": { + "acc": 0.878, + "reasoning_bytes": 149.604, + "flops_per_problem": 8373495103.488 + }, + "parity.sumd.inc24": { + "acc": 0.5, + "reasoning_bytes": 167.988, + "flops_per_problem": 9362041307.136 + }, + "inc.inc.cmp6": { + "acc": 1.0, + "reasoning_bytes": 144.624, + "flops_per_problem": 7667769212.928 + }, + "inc.inc.cmp7": { + "acc": 0.994, + "reasoning_bytes": 165.648, + "flops_per_problem": 8684579782.656 + }, + "inc.inc.cmp8": { + "acc": 0.918, + "reasoning_bytes": 180.254, + "flops_per_problem": 9417951756.288 + }, + "runmax.inc.cmp12": { + "acc": 1.0, + "reasoning_bytes": 105.568, + "flops_per_problem": 6150856015.872 + }, + "runmax.inc.cmp14": { + "acc": 1.0, + "reasoning_bytes": 117.406, + "flops_per_problem": 6766047608.832 + }, + "runmax.inc.cmp16": { + "acc": 0.964, + "reasoning_bytes": 123.778, + "flops_per_problem": 7137017413.632 + }, + "sumd.inc.cmp6": { + "acc": 1.0, + "reasoning_bytes": 88.12, + "flops_per_problem": 5039713124.352 + }, + "sumd.inc.cmp7": { + "acc": 1.0, + "reasoning_bytes": 96.068, + "flops_per_problem": 5435060944.896 + }, + "sumd.inc.cmp8": { + "acc": 0.968, + "reasoning_bytes": 100.382, + "flops_per_problem": 5669743509.504 + }, + "sumd.inc.runmax6": { + "acc": 1.0, + "reasoning_bytes": 93.522, + "flops_per_problem": 5278458691.584 + }, + "sumd.inc.runmax7": { + "acc": 0.998, + "reasoning_bytes": 101.478, + "flops_per_problem": 5673983164.416 + }, + "sumd.inc.runmax8": { + "acc": 0.804, + "reasoning_bytes": 107.848, + "flops_per_problem": 5999465005.056 + }, + "runmax.inc.runmax12": { + "acc": 1.0, + "reasoning_bytes": 109.648, + "flops_per_problem": 6343936966.656 + }, + "runmax.inc.runmax14": { + "acc": 1.0, + "reasoning_bytes": 121.08, + "flops_per_problem": 6937135349.76 + }, + "runmax.inc.runmax16": { + "acc": 0.962, + "reasoning_bytes": 128.448, + "flops_per_problem": 7350855008.256 + }, + "add.inc.runmax6": { + "acc": 1.0, + "reasoning_bytes": 192.872, + "flops_per_problem": 9931038326.784 + }, + "add.inc.runmax7": { + "acc": 0.848, + "reasoning_bytes": 220.902, + "flops_per_problem": 11257255378.944 + }, + "add.inc.runmax8": { + "acc": 0.68, + "reasoning_bytes": 243.006, + "flops_per_problem": 12327679918.08 + }, + "runmax.inc.count12": { + "acc": 1.0, + "reasoning_bytes": 108.928, + "flops_per_problem": 6356302626.816 + }, + "runmax.inc.count14": { + "acc": 1.0, + "reasoning_bytes": 120.904, + "flops_per_problem": 6973525721.088 + }, + "runmax.inc.count16": { + "acc": 1.0, + "reasoning_bytes": 127.526, + "flops_per_problem": 7354299727.872 + }, + "sumd.inc.count6": { + "acc": 1.0, + "reasoning_bytes": 92.388, + "flops_per_problem": 5272540839.936 + }, + "sumd.inc.count7": { + "acc": 0.996, + "reasoning_bytes": 100.46, + "flops_per_problem": 5673188229.12 + }, + "sumd.inc.count8": { + "acc": 0.768, + "reasoning_bytes": 105.754, + "flops_per_problem": 5951150604.288 + }, + "inc.inc.count6": { + "acc": 0.978, + "reasoning_bytes": 165.0, + "flops_per_problem": 8435146752.0 + }, + "inc.inc.count7": { + "acc": 0.814, + "reasoning_bytes": 189.894, + "flops_per_problem": 9578705338.368 + }, + "inc.inc.count8": { + "acc": 0.66, + "reasoning_bytes": 197.34, + "flops_per_problem": 9951706644.48 + }, + "parity.inc.find16": { + "acc": 1.0, + "reasoning_bytes": 128.0, + "flops_per_problem": 7331069952.0 + }, + "parity.inc.find20": { + "acc": 0.974, + "reasoning_bytes": 151.88, + "flops_per_problem": 8562336399.36 + }, + "parity.inc.find24": { + "acc": 0.872, + "reasoning_bytes": 170.06, + "flops_per_problem": 9541873336.32 + }, + "sumd.inc.find6": { + "acc": 1.0, + "reasoning_bytes": 92.1, + "flops_per_problem": 5215658803.2 + }, + "sumd.inc.find7": { + "acc": 0.998, + "reasoning_bytes": 100.388, + "flops_per_problem": 5625845415.936 + }, + "sumd.inc.find8": { + "acc": 0.902, + "reasoning_bytes": 105.614, + "flops_per_problem": 5900804702.208 + }, + "count.inc.find16": { + "acc": 1.0, + "reasoning_bytes": 112.02, + "flops_per_problem": 6669507133.44 + }, + "count.inc.find18": { + "acc": 0.988, + "reasoning_bytes": 121.68, + "flops_per_problem": 7184448552.96 + }, + "count.inc.find20": { + "acc": 0.934, + "reasoning_bytes": 127.666, + "flops_per_problem": 7535015018.496 + }, + "sumd.inc.rev6": { + "acc": 1.0, + "reasoning_bytes": 87.524, + "flops_per_problem": 4925154115.584 + }, + "sumd.inc.rev7": { + "acc": 0.994, + "reasoning_bytes": 95.464, + "flops_per_problem": 5320060305.408 + }, + "sumd.inc.rev8": { + "acc": 0.608, + "reasoning_bytes": 100.298, + "flops_per_problem": 5577707667.456 + }, + "count.inc.rev16": { + "acc": 0.996, + "reasoning_bytes": 107.02, + "flops_per_problem": 6316202557.44 + }, + "count.inc.rev18": { + "acc": 0.93, + "reasoning_bytes": 116.432, + "flops_per_problem": 6820191535.104 + }, + "count.inc.rev20": { + "acc": 0.722, + "reasoning_bytes": 122.3, + "flops_per_problem": 7166606671.872 + }, + "parity.inc.rev16": { + "acc": 1.0, + "reasoning_bytes": 123.0, + "flops_per_problem": 6977765376.0 + }, + "parity.inc.rev20": { + "acc": 0.86, + "reasoning_bytes": 146.664, + "flops_per_problem": 8199492599.808 + }, + "parity.inc.rev24": { + "acc": 0.472, + "reasoning_bytes": 165.0, + "flops_per_problem": 9185918976.0 + }, + "count.inc.sumd16": { + "acc": 0.996, + "reasoning_bytes": 110.02, + "flops_per_problem": 6492854845.44 + }, + "count.inc.sumd18": { + "acc": 0.956, + "reasoning_bytes": 119.44, + "flops_per_problem": 6997197127.68 + }, + "count.inc.sumd20": { + "acc": 0.748, + "reasoning_bytes": 125.222, + "flops_per_problem": 7340874153.984 + }, + "sumd.inc.sumd6": { + "acc": 1.0, + "reasoning_bytes": 91.758, + "flops_per_problem": 5122651373.568 + }, + "sumd.inc.sumd7": { + "acc": 0.992, + "reasoning_bytes": 99.74, + "flops_per_problem": 5521178935.296 + }, + "sumd.inc.sumd8": { + "acc": 0.778, + "reasoning_bytes": 106.154, + "flops_per_problem": 5850458800.128 + }, + "add.inc.sumd6": { + "acc": 0.958, + "reasoning_bytes": 198.52, + "flops_per_problem": 10136131633.152 + }, + "add.inc.sumd7": { + "acc": 0.386, + "reasoning_bytes": 228.346, + "flops_per_problem": 11541753888.768 + }, + "add.inc.sumd8": { + "acc": 0.046, + "reasoning_bytes": 249.4, + "flops_per_problem": 12578526167.04 + }, + "parity.inc.inc16": { + "acc": 1.0, + "reasoning_bytes": 127.0, + "flops_per_problem": 7154417664.0 + }, + "parity.inc.inc20": { + "acc": 0.84, + "reasoning_bytes": 150.736, + "flops_per_problem": 8379324628.992 + }, + "parity.inc.inc24": { + "acc": 0.488, + "reasoning_bytes": 169.096, + "flops_per_problem": 9366810918.912 + }, + "sumd.inc.inc6": { + "acc": 0.998, + "reasoning_bytes": 94.518, + "flops_per_problem": 5234118967.296 + }, + "sumd.inc.inc7": { + "acc": 0.984, + "reasoning_bytes": 102.464, + "flops_per_problem": 5629201809.408 + }, + "sumd.inc.inc8": { + "acc": 0.588, + "reasoning_bytes": 107.668, + "flops_per_problem": 5903189508.096 + }, + "runmax.inc.inc12": { + "acc": 1.0, + "reasoning_bytes": 110.06, + "flops_per_problem": 6270272962.56 + }, + "runmax.inc.inc14": { + "acc": 0.992, + "reasoning_bytes": 120.368, + "flops_per_problem": 6815156944.896 + }, + "runmax.inc.inc16": { + "acc": 0.95, + "reasoning_bytes": 128.98, + "flops_per_problem": 7284433747.968 + }, + "count.inc.cmp16": { + "acc": 0.976, + "reasoning_bytes": 111.15, + "flops_per_problem": 6593811628.032 + }, + "count.inc.cmp18": { + "acc": 0.822, + "reasoning_bytes": 121.758, + "flops_per_problem": 7183123660.8 + }, + "count.inc.cmp20": { + "acc": 0.748, + "reasoning_bytes": 129.206, + "flops_per_problem": 7566989082.624 + }, + "inc.rev.sumd6": { + "acc": 0.95, + "reasoning_bytes": 166.246, + "flops_per_problem": 8403614318.592 + }, + "inc.rev.sumd7": { + "acc": 0.594, + "reasoning_bytes": 195.972, + "flops_per_problem": 9761982087.168 + }, + "inc.rev.sumd8": { + "acc": 0.066, + "reasoning_bytes": 215.588, + "flops_per_problem": 10670504804.352 + }, + "runmax.inc.find12": { + "acc": 0.886, + "reasoning_bytes": 105.536, + "flops_per_problem": 6162338414.592 + }, + "runmax.inc.find14": { + "acc": 0.896, + "reasoning_bytes": 116.012, + "flops_per_problem": 6713316900.864 + }, + "runmax.inc.find16": { + "acc": 0.842, + "reasoning_bytes": 123.74, + "flops_per_problem": 7142935265.28 + }, + "inc.runmax.cmp6": { + "acc": 1.0, + "reasoning_bytes": 120.0, + "flops_per_problem": 6491971584.0 + }, + "inc.runmax.cmp7": { + "acc": 0.97, + "reasoning_bytes": 135.984, + "flops_per_problem": 7242037198.848 + }, + "inc.runmax.cmp8": { + "acc": 0.972, + "reasoning_bytes": 142.814, + "flops_per_problem": 7587834052.608 + } +} \ No newline at end of file