diff --git a/5m-s0-bpe4096-step-bytes3-v8-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-v8-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..c39789ba34f7d426c838fff9c34c6c02f92f0760 --- /dev/null +++ b/5m-s0-bpe4096-step-bytes3-v8-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:e0c2cb17c88c542536eae487827dc2e0a62acd848646f745e9c8616aa5c4aa91 +size 23171663 diff --git a/5m-s0-bpe4096-step-bytes3-v8-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-v8-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..6cd413f051afc674b0bcad5f501f5ef8c1e57771 --- /dev/null +++ b/5m-s0-bpe4096-step-bytes3-v8-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-v8-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": "v8", + "vocab_size": 4096, + "n_layer": 6, + "n_head": 4, + "d_model": 256, + "loops": 1, + "params": 5787648, + "flops_per_token": 44163072, + "steps": 12207, + "n_docs": 1175091, + "stream_tokens": 206228414 +} \ No newline at end of file diff --git a/5m-s0-bpe4096-step-bytes3-v8-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-v8-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..8c7c3caf35da735d10648b029936fd3d1710d7aa --- /dev/null +++ b/5m-s0-bpe4096-step-bytes3-v8-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": 1.043130874633789, "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}, "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}, "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}, "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.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}, "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}, "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}, "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}, "inc.sumd.rev6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7110254592.0}, "inc.sumd.rev7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7949352960.0}, "inc.sumd.rev8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8788451328.0}, "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}, "parity.rev.find16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7463559168.0}, "parity.rev.find20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8700125184.0}, "parity.rev.find24": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9936691200.0}, "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.count.count6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5432057856.0}, "sumd.count.count7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 5829525504.0}, "sumd.count.count8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6226993152.0}, "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}, "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}, "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}, "count.runmax.count16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7198580736.0}, "count.runmax.count18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7728537600.0}, "count.runmax.count20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8830494572.544}, "inc.inc.sumd6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9185918976.0}, "inc.inc.sumd7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10466648064.0}, "inc.inc.sumd8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 11747377152.0}, "add.sumd.find6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8655962112.0}, "add.sumd.find7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 9715875840.0}, "add.sumd.find8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10644360265.728}, "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}, "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}, "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}, "inc.runmax.sumd6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6712786944.0}, "inc.runmax.sumd7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7463559168.0}, "inc.runmax.sumd8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8214331392.0}, "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}, "runmax.runmax.count12": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6624460800.0}, "runmax.runmax.count14": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7242743808.0}, "runmax.runmax.count16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7861026816.0}, "count.count.count16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7242743808.0}, "count.count.count18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7953592614.912}, "count.count.count20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 8966163529.728}, "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}, "add.rev.rev6": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 10554974208.0}, "add.rev.rev7": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 12277334016.0}, "add.rev.rev8": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 14088019968.0}, "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}, "count.rev.cmp16": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 6712786944.0}, "count.rev.cmp18": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7244157026.304}, "count.rev.cmp20": {"acc": 0.0, "reasoning_bytes": 0.0, "flops_per_problem": 7774820499.456}} +{"step": 0, "train_loss": 8.351922988891602} +{"step": 20, "train_loss": 7.285041809082031} +{"step": 40, "train_loss": 6.458505630493164} +{"step": 60, "train_loss": 5.658304691314697} +{"step": 80, "train_loss": 4.8401265144348145} +{"step": 100, "train_loss": 4.095819473266602} +{"step": 120, "train_loss": 3.5045485496520996} +{"step": 140, "train_loss": 3.0782721042633057} +{"step": 160, "train_loss": 2.8824307918548584} +{"step": 180, "train_loss": 2.6493372917175293} +{"step": 200, "train_loss": 2.557250499725342} +{"step": 220, "train_loss": 2.545844078063965} +{"step": 240, "train_loss": 2.3058385848999023} +{"step": 260, "train_loss": 2.372734546661377} +{"step": 280, "train_loss": 2.373262643814087} +{"step": 300, "train_loss": 2.30340838432312} +{"step": 320, "train_loss": 2.1923556327819824} +{"step": 340, "train_loss": 2.1871144771575928} +{"step": 360, "train_loss": 2.0100090503692627} +{"step": 380, "train_loss": 2.037736177444458} +{"step": 400, "train_loss": 2.025351047515869} +{"step": 420, "train_loss": 2.134709358215332} +{"step": 440, "train_loss": 2.0636441707611084} +{"step": 460, "train_loss": 1.9538261890411377} +{"step": 480, "train_loss": 2.060725212097168} +{"step": 500, "train_loss": 2.0789096355438232} +{"step": 520, "train_loss": 1.8098868131637573} +{"step": 540, "train_loss": 1.8797721862792969} +{"step": 560, "train_loss": 1.7683188915252686} +{"step": 580, "train_loss": 1.9292933940887451} +{"step": 600, "train_loss": 1.8598790168762207} +{"step": 620, "train_loss": 2.007648468017578} +{"step": 640, "train_loss": 1.7941272258758545} +{"step": 660, "train_loss": 1.7352081537246704} +{"step": 680, "train_loss": 1.6633954048156738} +{"step": 700, "train_loss": 1.7315502166748047} +{"step": 720, "train_loss": 1.7144733667373657} +{"step": 740, "train_loss": 1.758945107460022} +{"step": 760, "train_loss": 1.6652477979660034} +{"step": 780, "train_loss": 1.7091429233551025} +{"step": 800, "train_loss": 1.6527776718139648} +{"step": 820, "train_loss": 1.5918904542922974} +{"step": 840, "train_loss": 1.6961884498596191} +{"step": 860, "train_loss": 1.6207952499389648} +{"step": 880, "train_loss": 1.6866474151611328} +{"step": 900, "train_loss": 1.6429626941680908} +{"step": 920, "train_loss": 1.643233299255371} +{"step": 940, "train_loss": 1.5071132183074951} +{"step": 960, "train_loss": 1.637800693511963} +{"step": 980, "train_loss": 1.6229310035705566} +{"step": 1000, "tokens": 32768000, "val_loss": 2.932892656326294, "val_bpb": 1.0572601540822297, "lr": 0.0005946964099287039, "elapsed": 174.8788731098175, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.0, "reasoning_bytes": 78.212, "flops_per_problem": 4876133105.664}, "add9": {"acc": 0.0, "reasoning_bytes": 84.4, "flops_per_problem": 5284906500.096}, "add10": {"acc": 0.0, "reasoning_bytes": 91.122, "flops_per_problem": 5713199972.352}, "reach14": {"acc": 0.524, "reasoning_bytes": 4.6, "flops_per_problem": 4486968115.2}, "reach16": {"acc": 0.522, "reasoning_bytes": 5.528, "flops_per_problem": 5057908310.016}, "reach18": {"acc": 0.51, "reasoning_bytes": 6.83, "flops_per_problem": 5647573647.36}, "parity24": {"acc": 0.506, "reasoning_bytes": 137.408, "flops_per_problem": 7614066917.376}, "parity28": {"acc": 0.556, "reasoning_bytes": 158.912, "flops_per_problem": 8740401905.664}, "parity32": {"acc": 0.488, "reasoning_bytes": 182.752, "flops_per_problem": 9970166808.576}, "cmp8": {"acc": 0.662, "reasoning_bytes": 5.632, "flops_per_problem": 1353863135.232}, "cmp9": {"acc": 0.62, "reasoning_bytes": 6.568, "flops_per_problem": 1484320849.92}, "cmp10": {"acc": 0.582, "reasoning_bytes": 7.26, "flops_per_problem": 1601176338.432}, "runmax12": {"acc": 0.994, "reasoning_bytes": 67.376, "flops_per_problem": 3991281795.072}, "runmax14": {"acc": 0.982, "reasoning_bytes": 77.772, "flops_per_problem": 4538727235.584}, "runmax16": {"acc": 0.952, "reasoning_bytes": 88.744, "flops_per_problem": 5111610605.568}, "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": 0.64, "reasoning_bytes": 69.758, "flops_per_problem": 4361456664.576}, "brackets18": {"acc": 0.628, "reasoning_bytes": 78.06, "flops_per_problem": 4816424632.32}, "brackets20": {"acc": 0.646, "reasoning_bytes": 86.888, "flops_per_problem": 5294622375.936}, "sumd8": {"acc": 0.046, "reasoning_bytes": 59.424, "flops_per_problem": 3422638080.0}, "sumd9": {"acc": 0.034, "reasoning_bytes": 65.584, "flops_per_problem": 3767551672.32}, "sumd10": {"acc": 0.01, "reasoning_bytes": 71.246, "flops_per_problem": 4070422020.096}, "inc8": {"acc": 0.0, "reasoning_bytes": 55.774, "flops_per_problem": 3441804853.248}, "inc9": {"acc": 0.0, "reasoning_bytes": 63.452, "flops_per_problem": 3863738843.136}, "inc10": {"acc": 0.0, "reasoning_bytes": 66.68, "flops_per_problem": 4061766057.984}, "add.cmp6": {"acc": 0.796, "reasoning_bytes": 89.726, "flops_per_problem": 5404058468.352}, "add.cmp7": {"acc": 0.738, "reasoning_bytes": 102.604, "flops_per_problem": 6102629941.248}, "add.cmp8": {"acc": 0.712, "reasoning_bytes": 115.4, "flops_per_problem": 6801731371.008}, "add.runmax6": {"acc": 0.502, "reasoning_bytes": 112.52, "flops_per_problem": 6205706551.296}, "add.runmax7": {"acc": 0.424, "reasoning_bytes": 131.152, "flops_per_problem": 7116967378.944}, "add.runmax8": {"acc": 0.454, "reasoning_bytes": 149.04, "flops_per_problem": 7995282554.88}, "add.count6": {"acc": 0.506, "reasoning_bytes": 107.314, "flops_per_problem": 6020044996.608}, "add.count7": {"acc": 0.396, "reasoning_bytes": 123.926, "flops_per_problem": 6842008092.672}, "add.count8": {"acc": 0.296, "reasoning_bytes": 137.912, "flops_per_problem": 7547998961.664}, "add.find6": {"acc": 0.326, "reasoning_bytes": 108.68, "flops_per_problem": 6036297007.104}, "add.find7": {"acc": 0.254, "reasoning_bytes": 126.714, "flops_per_problem": 6923974754.304}, "add.find8": {"acc": 0.18, "reasoning_bytes": 143.206, "flops_per_problem": 7746291154.944}, "add.rev6": {"acc": 0.0, "reasoning_bytes": 112.038, "flops_per_problem": 6262235283.456}, "add.rev7": {"acc": 0.0, "reasoning_bytes": 130.552, "flops_per_problem": 7191514644.48}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 149.568, "flops_per_problem": 8156566093.824}, "add.sumd6": {"acc": 0.03, "reasoning_bytes": 113.496, "flops_per_problem": 6203233419.264}, "add.sumd7": {"acc": 0.032, "reasoning_bytes": 132.084, "flops_per_problem": 7113875963.904}, "add.sumd8": {"acc": 0.028, "reasoning_bytes": 149.802, "flops_per_problem": 7986184962.048}, "add.inc6": {"acc": 0.0, "reasoning_bytes": 121.258, "flops_per_problem": 6666769022.976}, "add.inc7": {"acc": 0.0, "reasoning_bytes": 139.908, "flops_per_problem": 7626609229.824}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 157.388, "flops_per_problem": 8528684138.496}, "runmax.cmp12": {"acc": 0.938, "reasoning_bytes": 84.47, "flops_per_problem": 5012243693.568}, "runmax.cmp14": {"acc": 0.954, "reasoning_bytes": 93.228, "flops_per_problem": 5486290108.416}, "runmax.cmp16": {"acc": 0.934, "reasoning_bytes": 104.12, "flops_per_problem": 6056612020.224}, "runmax.runmax12": {"acc": 0.998, "reasoning_bytes": 87.088, "flops_per_problem": 5170965774.336}, "runmax.runmax14": {"acc": 0.984, "reasoning_bytes": 96.064, "flops_per_problem": 5655699652.608}, "runmax.runmax16": {"acc": 0.97, "reasoning_bytes": 106.4, "flops_per_problem": 6200495308.8}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 87.688, "flops_per_problem": 5241626689.536}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 96.832, "flops_per_problem": 5733779963.904}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 106.208, "flops_per_problem": 6236179070.976}, "runmax.find12": {"acc": 0.932, "reasoning_bytes": 87.892, "flops_per_problem": 5206472884.224}, "runmax.find14": {"acc": 0.938, "reasoning_bytes": 98.884, "flops_per_problem": 5780239515.648}, "runmax.find16": {"acc": 0.942, "reasoning_bytes": 107.456, "flops_per_problem": 6247131512.832}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 82.772, "flops_per_problem": 4847868739.584}, "runmax.rev14": {"acc": 0.992, "reasoning_bytes": 91.568, "flops_per_problem": 5324653264.896}, "runmax.rev16": {"acc": 0.976, "reasoning_bytes": 101.228, "flops_per_problem": 5839594684.416}, "runmax.sumd12": {"acc": 0.998, "reasoning_bytes": 85.496, "flops_per_problem": 5012332019.712}, "runmax.sumd14": {"acc": 0.988, "reasoning_bytes": 93.908, "flops_per_problem": 5472157925.376}, "runmax.sumd16": {"acc": 0.976, "reasoning_bytes": 104.244, "flops_per_problem": 6016953581.568}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 86.76, "flops_per_problem": 5055170199.552}, "runmax.inc14": {"acc": 0.978, "reasoning_bytes": 96.528, "flops_per_problem": 5578060972.032}, "runmax.inc16": {"acc": 0.97, "reasoning_bytes": 105.548, "flops_per_problem": 6066946179.072}, "count.cmp16": {"acc": 0.234, "reasoning_bytes": 101.666, "flops_per_problem": 5974203727.872}, "count.cmp18": {"acc": 0.03, "reasoning_bytes": 109.108, "flops_per_problem": 6532866588.672}, "count.cmp20": {"acc": 0.004, "reasoning_bytes": 117.35, "flops_per_problem": 7066444824.576}, "count.runmax16": {"acc": 0.008, "reasoning_bytes": 102.53, "flops_per_problem": 6072775704.576}, "count.runmax18": {"acc": 0.0, "reasoning_bytes": 108.534, "flops_per_problem": 6623400886.272}, "count.runmax20": {"acc": 0.002, "reasoning_bytes": 121.266, "flops_per_problem": 7329656733.696}, "count.count16": {"acc": 0.792, "reasoning_bytes": 100.758, "flops_per_problem": 6051489103.872}, "count.count18": {"acc": 0.266, "reasoning_bytes": 112.626, "flops_per_problem": 6645129117.696}, "count.count20": {"acc": 0.772, "reasoning_bytes": 127.974, "flops_per_problem": 7487230574.592}, "count.find16": {"acc": 0.212, "reasoning_bytes": 102.22, "flops_per_problem": 6065797939.2}, "count.find18": {"acc": 0.02, "reasoning_bytes": 108.464, "flops_per_problem": 6622517624.832}, "count.find20": {"acc": 0.0, "reasoning_bytes": 119.284, "flops_per_problem": 7154417664.0}, "count.rev16": {"acc": 0.006, "reasoning_bytes": 97.896, "flops_per_problem": 5731660136.448}, "count.rev18": {"acc": 0.0, "reasoning_bytes": 106.028, "flops_per_problem": 6270272962.56}, "count.rev20": {"acc": 0.002, "reasoning_bytes": 119.694, "flops_per_problem": 6985803055.104}, "count.sumd16": {"acc": 0.006, "reasoning_bytes": 100.744, "flops_per_problem": 5896035090.432}, "count.sumd18": {"acc": 0.0, "reasoning_bytes": 108.172, "flops_per_problem": 6444275466.24}, "count.sumd20": {"acc": 0.002, "reasoning_bytes": 121.108, "flops_per_problem": 7141698699.264}, "count.inc16": {"acc": 0.008, "reasoning_bytes": 100.082, "flops_per_problem": 5882874494.976}, "count.inc18": {"acc": 0.004, "reasoning_bytes": 108.424, "flops_per_problem": 6451783188.48}, "count.inc20": {"acc": 0.002, "reasoning_bytes": 123.696, "flops_per_problem": 7165458432.0}, "parity.cmp16": {"acc": 0.9, "reasoning_bytes": 106.608, "flops_per_problem": 6165518155.776}, "parity.cmp20": {"acc": 0.94, "reasoning_bytes": 128.784, "flops_per_problem": 7321530728.448}, "parity.cmp24": {"acc": 0.94, "reasoning_bytes": 147.232, "flops_per_problem": 8312903368.704}, "parity.runmax16": {"acc": 0.576, "reasoning_bytes": 108.316, "flops_per_problem": 6285111754.752}, "parity.runmax20": {"acc": 0.518, "reasoning_bytes": 130.672, "flops_per_problem": 7449073680.384}, "parity.runmax24": {"acc": 0.484, "reasoning_bytes": 153.328, "flops_per_problem": 8626284527.616}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 108.256, "flops_per_problem": 6326625042.432}, "parity.count20": {"acc": 0.954, "reasoning_bytes": 130.864, "flops_per_problem": 7501716062.208}, "parity.count24": {"acc": 0.884, "reasoning_bytes": 151.804, "flops_per_problem": 8603143077.888}, "parity.find16": {"acc": 0.876, "reasoning_bytes": 108.484, "flops_per_problem": 6292531150.848}, "parity.find20": {"acc": 0.86, "reasoning_bytes": 131.32, "flops_per_problem": 7477691351.04}, "parity.find24": {"acc": 0.862, "reasoning_bytes": 152.248, "flops_per_problem": 8578588409.856}, "parity.rev16": {"acc": 0.59, "reasoning_bytes": 103.448, "flops_per_problem": 5937636704.256}, "parity.rev20": {"acc": 0.556, "reasoning_bytes": 125.096, "flops_per_problem": 7070331174.912}, "parity.rev24": {"acc": 0.532, "reasoning_bytes": 146.528, "flops_per_problem": 8193486422.016}, "parity.sumd16": {"acc": 0.606, "reasoning_bytes": 105.56, "flops_per_problem": 6075072184.32}, "parity.sumd20": {"acc": 0.552, "reasoning_bytes": 127.952, "flops_per_problem": 7240623980.544}, "parity.sumd24": {"acc": 0.526, "reasoning_bytes": 148.46, "flops_per_problem": 8322972549.12}, "parity.inc16": {"acc": 0.644, "reasoning_bytes": 105.276, "flops_per_problem": 6018366799.872}, "parity.inc20": {"acc": 0.55, "reasoning_bytes": 128.988, "flops_per_problem": 7242213851.136}, "parity.inc24": {"acc": 0.482, "reasoning_bytes": 148.596, "flops_per_problem": 8284815654.912}, "sumd.cmp6": {"acc": 0.782, "reasoning_bytes": 61.184, "flops_per_problem": 3673484328.96}, "sumd.cmp7": {"acc": 0.774, "reasoning_bytes": 68.85, "flops_per_problem": 4056996446.208}, "sumd.cmp8": {"acc": 0.756, "reasoning_bytes": 75.438, "flops_per_problem": 4394667294.72}, "sumd.runmax6": {"acc": 0.128, "reasoning_bytes": 69.072, "flops_per_problem": 4013539983.36}, "sumd.runmax7": {"acc": 0.122, "reasoning_bytes": 77.254, "flops_per_problem": 4418250375.168}, "sumd.runmax8": {"acc": 0.116, "reasoning_bytes": 84.242, "flops_per_problem": 4774734692.352}, "sumd.count6": {"acc": 0.766, "reasoning_bytes": 67.968, "flops_per_problem": 4009476980.736}, "sumd.count7": {"acc": 0.738, "reasoning_bytes": 76.198, "flops_per_problem": 4417102135.296}, "sumd.count8": {"acc": 0.754, "reasoning_bytes": 83.732, "flops_per_problem": 4794519748.608}, "sumd.find6": {"acc": 0.676, "reasoning_bytes": 66.102, "flops_per_problem": 3889000120.32}, "sumd.find7": {"acc": 0.636, "reasoning_bytes": 73.084, "flops_per_problem": 4242481348.608}, "sumd.find8": {"acc": 0.542, "reasoning_bytes": 79.504, "flops_per_problem": 4572291170.304}, "sumd.rev6": {"acc": 0.074, "reasoning_bytes": 63.8, "flops_per_problem": 3688499773.44}, "sumd.rev7": {"acc": 0.07, "reasoning_bytes": 71.334, "flops_per_problem": 4068743823.36}, "sumd.rev8": {"acc": 0.036, "reasoning_bytes": 78.456, "flops_per_problem": 4430792687.616}, "sumd.sumd6": {"acc": 0.108, "reasoning_bytes": 67.054, "flops_per_problem": 3845896962.048}, "sumd.sumd7": {"acc": 0.092, "reasoning_bytes": 74.458, "flops_per_problem": 4216778440.704}, "sumd.sumd8": {"acc": 0.086, "reasoning_bytes": 81.246, "flops_per_problem": 4562486968.32}, "sumd.inc6": {"acc": 0.034, "reasoning_bytes": 70.478, "flops_per_problem": 3978739482.624}, "sumd.inc7": {"acc": 0.014, "reasoning_bytes": 78.312, "flops_per_problem": 4369052712.96}, "sumd.inc8": {"acc": 0.008, "reasoning_bytes": 85.094, "flops_per_problem": 4718294286.336}, "inc.cmp6": {"acc": 0.686, "reasoning_bytes": 76.774, "flops_per_problem": 4495270772.736}, "inc.cmp7": {"acc": 0.666, "reasoning_bytes": 87.482, "flops_per_problem": 5057643331.584}, "inc.cmp8": {"acc": 0.616, "reasoning_bytes": 98.496, "flops_per_problem": 5650046779.392}, "inc.runmax6": {"acc": 0.902, "reasoning_bytes": 98.884, "flops_per_problem": 5294445723.648}, "inc.runmax7": {"acc": 0.868, "reasoning_bytes": 113.77, "flops_per_problem": 5996020285.44}, "inc.runmax8": {"acc": 0.834, "reasoning_bytes": 116.174, "flops_per_problem": 6146881339.392}, "inc.count6": {"acc": 0.57, "reasoning_bytes": 94.438, "flops_per_problem": 5142259777.536}, "inc.count7": {"acc": 0.394, "reasoning_bytes": 102.05, "flops_per_problem": 5522768805.888}, "inc.count8": {"acc": 0.36, "reasoning_bytes": 110.468, "flops_per_problem": 5939138248.704}, "inc.find6": {"acc": 0.332, "reasoning_bytes": 94.0, "flops_per_problem": 5078753280.0}, "inc.find7": {"acc": 0.24, "reasoning_bytes": 100.814, "flops_per_problem": 5424903438.336}, "inc.find8": {"acc": 0.204, "reasoning_bytes": 110.272, "flops_per_problem": 5890558869.504}, "inc.rev6": {"acc": 0.002, "reasoning_bytes": 97.124, "flops_per_problem": 5269096120.32}, "inc.rev7": {"acc": 0.0, "reasoning_bytes": 113.854, "flops_per_problem": 6074277249.024}, "inc.rev8": {"acc": 0.0, "reasoning_bytes": 115.092, "flops_per_problem": 6183625015.296}, "inc.sumd6": {"acc": 0.048, "reasoning_bytes": 101.102, "flops_per_problem": 5347706388.48}, "inc.sumd7": {"acc": 0.042, "reasoning_bytes": 116.716, "flops_per_problem": 6081608318.976}, "inc.sumd8": {"acc": 0.038, "reasoning_bytes": 118.266, "flops_per_problem": 6194842435.584}, "inc.inc6": {"acc": 0.002, "reasoning_bytes": 107.578, "flops_per_problem": 5747735494.656}, "inc.inc7": {"acc": 0.0, "reasoning_bytes": 123.554, "flops_per_problem": 6540727615.488}, "inc.inc8": {"acc": 0.0, "reasoning_bytes": 125.05, "flops_per_problem": 6659349626.88}, "count.inc.cmp16": {"acc": 0.49, "reasoning_bytes": 111.29, "flops_per_problem": 6594694889.472}, "count.inc.cmp18": {"acc": 0.472, "reasoning_bytes": 122.098, "flops_per_problem": 7161042124.8}, "count.inc.cmp20": {"acc": 0.35, "reasoning_bytes": 133.252, "flops_per_problem": 7745054588.928}, "inc.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 143.338, "flops_per_problem": 7526712360.96}, "inc.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 163.834, "flops_per_problem": 8515523543.04}, "inc.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 166.996, "flops_per_problem": 8711784235.008}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 123.852, "flops_per_problem": 7324533817.344}, "parity.runmax.count20": {"acc": 0.99, "reasoning_bytes": 146.088, "flops_per_problem": 8483196174.336}, "parity.runmax.count24": {"acc": 0.97, "reasoning_bytes": 167.34, "flops_per_problem": 9598402068.48}, "add.count.find6": {"acc": 0.69, "reasoning_bytes": 120.03, "flops_per_problem": 6890764124.16}, "add.count.find7": {"acc": 0.686, "reasoning_bytes": 142.402, "flops_per_problem": 7967106514.944}, "add.count.find8": {"acc": 0.598, "reasoning_bytes": 156.242, "flops_per_problem": 8667797815.296}, "runmax.inc.find12": {"acc": 0.412, "reasoning_bytes": 105.96, "flops_per_problem": 6181063557.12}, "runmax.inc.find14": {"acc": 0.104, "reasoning_bytes": 117.396, "flops_per_problem": 6774438592.512}, "runmax.inc.find16": {"acc": 0.156, "reasoning_bytes": 125.494, "flops_per_problem": 7220397293.568}, "parity.sumd.rev16": {"acc": 0.732, "reasoning_bytes": 116.528, "flops_per_problem": 6736105046.016}, "parity.sumd.rev20": {"acc": 0.516, "reasoning_bytes": 138.692, "flops_per_problem": 7891587661.824}, "parity.sumd.rev24": {"acc": 0.5, "reasoning_bytes": 157.76, "flops_per_problem": 8910341406.72}, "parity.rev.sumd16": {"acc": 0.716, "reasoning_bytes": 116.744, "flops_per_problem": 6745644269.568}, "parity.rev.sumd20": {"acc": 0.534, "reasoning_bytes": 139.076, "flops_per_problem": 7908546281.472}, "parity.rev.sumd24": {"acc": 0.502, "reasoning_bytes": 158.288, "flops_per_problem": 8933659508.736}, "count.inc.sumd16": {"acc": 0.02, "reasoning_bytes": 112.64, "flops_per_problem": 6609533681.664}, "count.inc.sumd18": {"acc": 0.018, "reasoning_bytes": 123.28, "flops_per_problem": 7165988388.864}, "count.inc.sumd20": {"acc": 0.016, "reasoning_bytes": 134.672, "flops_per_problem": 7759010119.68}, "inc.sumd.rev6": {"acc": 0.042, "reasoning_bytes": 119.336, "flops_per_problem": 6328303239.168}, "inc.sumd.rev7": {"acc": 0.018, "reasoning_bytes": 129.828, "flops_per_problem": 6834853675.008}, "inc.sumd.rev8": {"acc": 0.018, "reasoning_bytes": 136.408, "flops_per_problem": 7176145895.424}, "count.count.cmp16": {"acc": 0.908, "reasoning_bytes": 113.634, "flops_per_problem": 6873275547.648}, "count.count.cmp18": {"acc": 0.89, "reasoning_bytes": 125.878, "flops_per_problem": 7501892714.496}, "count.count.cmp20": {"acc": 0.85, "reasoning_bytes": 137.266, "flops_per_problem": 8090763116.544}, "parity.rev.find16": {"acc": 0.79, "reasoning_bytes": 119.716, "flops_per_problem": 6965223063.552}, "parity.rev.find20": {"acc": 0.668, "reasoning_bytes": 142.084, "flops_per_problem": 8129714946.048}, "parity.rev.find24": {"acc": 0.67, "reasoning_bytes": 161.968, "flops_per_problem": 9184505757.696}, "count.sumd.cmp16": {"acc": 0.564, "reasoning_bytes": 114.54, "flops_per_problem": 6778236616.704}, "count.sumd.cmp18": {"acc": 0.46, "reasoning_bytes": 126.434, "flops_per_problem": 7387422031.872}, "count.sumd.cmp20": {"acc": 0.526, "reasoning_bytes": 139.046, "flops_per_problem": 8043420303.36}, "sumd.count.count6": {"acc": 0.862, "reasoning_bytes": 84.76, "flops_per_problem": 5107812581.376}, "sumd.count.count7": {"acc": 0.84, "reasoning_bytes": 92.924, "flops_per_problem": 5509961515.008}, "sumd.count.count8": {"acc": 0.892, "reasoning_bytes": 100.434, "flops_per_problem": 5889675608.064}, "runmax.rev.inc12": {"acc": 0.964, "reasoning_bytes": 98.856, "flops_per_problem": 5764694114.304}, "runmax.rev.inc14": {"acc": 0.866, "reasoning_bytes": 110.14, "flops_per_problem": 6350738079.744}, "runmax.rev.inc16": {"acc": 0.872, "reasoning_bytes": 117.966, "flops_per_problem": 6787687514.112}, "parity.sumd.find16": {"acc": 0.78, "reasoning_bytes": 121.18, "flops_per_problem": 7074040872.96}, "parity.sumd.find20": {"acc": 0.66, "reasoning_bytes": 142.872, "flops_per_problem": 8208678518.784}, "parity.sumd.find24": {"acc": 0.556, "reasoning_bytes": 163.144, "flops_per_problem": 9280604602.368}, "runmax.runmax.cmp12": {"acc": 0.87, "reasoning_bytes": 103.632, "flops_per_problem": 6166578069.504}, "runmax.runmax.cmp14": {"acc": 0.862, "reasoning_bytes": 112.832, "flops_per_problem": 6661204475.904}, "runmax.runmax.cmp16": {"acc": 0.826, "reasoning_bytes": 122.504, "flops_per_problem": 7176675852.288}, "count.runmax.count16": {"acc": 0.99, "reasoning_bytes": 115.528, "flops_per_problem": 7001171804.16}, "count.runmax.count18": {"acc": 0.918, "reasoning_bytes": 127.666, "flops_per_problem": 7624666054.656}, "count.runmax.count20": {"acc": 1.0, "reasoning_bytes": 139.788, "flops_per_problem": 8249131892.736}, "inc.inc.sumd6": {"acc": 0.022, "reasoning_bytes": 154.326, "flops_per_problem": 7871449300.992}, "inc.inc.sumd7": {"acc": 0.016, "reasoning_bytes": 169.926, "flops_per_problem": 8606411145.216}, "inc.inc.sumd8": {"acc": 0.014, "reasoning_bytes": 177.006, "flops_per_problem": 8963248766.976}, "add.sumd.find6": {"acc": 0.426, "reasoning_bytes": 139.37, "flops_per_problem": 7612388720.64}, "add.sumd.find7": {"acc": 0.434, "reasoning_bytes": 159.418, "flops_per_problem": 8586096132.096}, "add.sumd.find8": {"acc": 0.486, "reasoning_bytes": 176.686, "flops_per_problem": 9438531747.84}, "sumd.rev.rev6": {"acc": 0.046, "reasoning_bytes": 82.346, "flops_per_problem": 4687645114.368}, "sumd.rev.rev7": {"acc": 0.018, "reasoning_bytes": 90.066, "flops_per_problem": 5082374651.904}, "sumd.rev.rev8": {"acc": 0.01, "reasoning_bytes": 95.624, "flops_per_problem": 5401055379.456}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 105.328, "flops_per_problem": 6153152495.616}, "runmax.inc.runmax14": {"acc": 0.986, "reasoning_bytes": 116.832, "flops_per_problem": 6749530619.904}, "runmax.inc.runmax16": {"acc": 0.96, "reasoning_bytes": 124.806, "flops_per_problem": 7190278078.464}, "parity.inc.find16": {"acc": 0.902, "reasoning_bytes": 122.144, "flops_per_problem": 7072451002.368}, "parity.inc.find20": {"acc": 0.87, "reasoning_bytes": 144.728, "flops_per_problem": 8246482108.416}, "parity.inc.find24": {"acc": 0.844, "reasoning_bytes": 165.12, "flops_per_problem": 9323707760.64}, "inc.runmax.sumd6": {"acc": 0.86, "reasoning_bytes": 113.256, "flops_per_problem": 6149972754.432}, "inc.runmax.sumd7": {"acc": 0.846, "reasoning_bytes": 128.132, "flops_per_problem": 6851105685.504}, "inc.runmax.sumd8": {"acc": 0.822, "reasoning_bytes": 131.378, "flops_per_problem": 7038622089.216}, "sumd.rev.cmp6": {"acc": 0.166, "reasoning_bytes": 80.82, "flops_per_problem": 4748943458.304}, "sumd.rev.cmp7": {"acc": 0.082, "reasoning_bytes": 88.444, "flops_per_problem": 5135988621.312}, "sumd.rev.cmp8": {"acc": 0.044, "reasoning_bytes": 94.298, "flops_per_problem": 5456700850.176}, "runmax.runmax.count12": {"acc": 1.0, "reasoning_bytes": 104.76, "flops_per_problem": 6304720158.72}, "runmax.runmax.count14": {"acc": 1.0, "reasoning_bytes": 114.912, "flops_per_problem": 6841389809.664}, "runmax.runmax.count16": {"acc": 1.0, "reasoning_bytes": 123.216, "flops_per_problem": 7296446103.552}, "count.count.count16": {"acc": 1.0, "reasoning_bytes": 113.342, "flops_per_problem": 6948706074.624}, "count.count.count18": {"acc": 0.998, "reasoning_bytes": 124.756, "flops_per_problem": 7541021196.288}, "count.count.count20": {"acc": 0.994, "reasoning_bytes": 136.71, "flops_per_problem": 8159392530.432}, "add.sumd.rev6": {"acc": 0.034, "reasoning_bytes": 133.408, "flops_per_problem": 7258024230.912}, "add.sumd.rev7": {"acc": 0.03, "reasoning_bytes": 151.806, "flops_per_problem": 8158332616.704}, "add.sumd.rev8": {"acc": 0.02, "reasoning_bytes": 168.306, "flops_per_problem": 8979235799.04}, "add.rev.rev6": {"acc": 0.0, "reasoning_bytes": 161.66, "flops_per_problem": 8626726158.336}, "add.rev.rev7": {"acc": 0.0, "reasoning_bytes": 191.348, "flops_per_problem": 10074833289.216}, "add.rev.rev8": {"acc": 0.0, "reasoning_bytes": 217.016, "flops_per_problem": 11412974370.816}, "inc.runmax.cmp6": {"acc": 0.19, "reasoning_bytes": 103.234, "flops_per_problem": 5751533518.848}, "inc.runmax.cmp7": {"acc": 0.09, "reasoning_bytes": 115.916, "flops_per_problem": 6355772669.952}, "inc.runmax.cmp8": {"acc": 0.09, "reasoning_bytes": 125.268, "flops_per_problem": 6812860465.152}, "count.rev.cmp16": {"acc": 0.534, "reasoning_bytes": 111.802, "flops_per_problem": 6613773336.576}, "count.rev.cmp18": {"acc": 0.308, "reasoning_bytes": 123.204, "flops_per_problem": 7197255843.84}, "count.rev.cmp20": {"acc": 0.13, "reasoning_bytes": 133.022, "flops_per_problem": 7754593812.48}} +{"step": 1000, "train_loss": 1.6224064826965332} +{"step": 1020, "train_loss": 1.669165849685669} +{"step": 1040, "train_loss": 1.5065104961395264} +{"step": 1060, "train_loss": 1.3844091892242432} +{"step": 1080, "train_loss": 1.4812861680984497} +{"step": 1100, "train_loss": 1.6076152324676514} +{"step": 1120, "train_loss": 1.5229015350341797} +{"step": 1140, "train_loss": 1.4577316045761108} +{"step": 1160, "train_loss": 1.5526461601257324} +{"step": 1180, "train_loss": 1.5684962272644043} +{"step": 1200, "train_loss": 1.4778294563293457} +{"step": 1220, "train_loss": 1.5213828086853027} +{"step": 1240, "train_loss": 1.4068156480789185} +{"step": 1260, "train_loss": 1.4349604845046997} +{"step": 1280, "train_loss": 1.5109632015228271} +{"step": 1300, "train_loss": 1.4629735946655273} +{"step": 1320, "train_loss": 1.4711723327636719} +{"step": 1340, "train_loss": 1.4517805576324463} +{"step": 1360, "train_loss": 1.5153734683990479} +{"step": 1380, "train_loss": 1.2910655736923218} +{"step": 1400, "train_loss": 1.3957854509353638} +{"step": 1420, "train_loss": 1.3732141256332397} +{"step": 1440, "train_loss": 1.461937427520752} +{"step": 1460, "train_loss": 1.3763086795806885} +{"step": 1480, "train_loss": 1.4432893991470337} +{"step": 1500, "train_loss": 1.5565599203109741} +{"step": 1520, "train_loss": 1.4811092615127563} +{"step": 1540, "train_loss": 1.5285319089889526} +{"step": 1560, "train_loss": 1.370652198791504} +{"step": 1580, "train_loss": 1.489170789718628} +{"step": 1600, "train_loss": 1.3352628946304321} +{"step": 1620, "train_loss": 1.326570987701416} +{"step": 1640, "train_loss": 1.4850236177444458} +{"step": 1660, "train_loss": 1.4288556575775146} +{"step": 1680, "train_loss": 1.3886241912841797} +{"step": 1700, "train_loss": 1.3495585918426514} +{"step": 1720, "train_loss": 1.4422553777694702} +{"step": 1740, "train_loss": 1.447031855583191} +{"step": 1760, "train_loss": 1.3073391914367676} +{"step": 1780, "train_loss": 1.3735524415969849} +{"step": 1800, "train_loss": 1.332348108291626} +{"step": 1820, "train_loss": 1.3872144222259521} +{"step": 1840, "train_loss": 1.2774791717529297} +{"step": 1860, "train_loss": 1.331425666809082} +{"step": 1880, "train_loss": 1.3210318088531494} +{"step": 1900, "train_loss": 1.2828173637390137} +{"step": 1920, "train_loss": 1.2833114862442017} +{"step": 1940, "train_loss": 1.309104561805725} +{"step": 1960, "train_loss": 1.2765648365020752} +{"step": 1980, "train_loss": 1.318371057510376} +{"step": 2000, "tokens": 65536000, "val_loss": 2.363830900192261, "val_bpb": 0.8521226361185866, "lr": 0.0005717971803204413, "elapsed": 339.60283064842224, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.0, "reasoning_bytes": 80.53, "flops_per_problem": 4981682847.744}, "add9": {"acc": 0.0, "reasoning_bytes": 89.406, "flops_per_problem": 5520825630.72}, "add10": {"acc": 0.0, "reasoning_bytes": 97.594, "flops_per_problem": 6017130233.856}, "reach14": {"acc": 0.478, "reasoning_bytes": 6.286, "flops_per_problem": 4561427054.592}, "reach16": {"acc": 0.514, "reasoning_bytes": 7.08, "flops_per_problem": 5126449397.76}, "reach18": {"acc": 0.554, "reasoning_bytes": 7.986, "flops_per_problem": 5696418004.992}, "parity24": {"acc": 0.0, "reasoning_bytes": 147.0, "flops_per_problem": 8170168320.0}, "parity28": {"acc": 0.0, "reasoning_bytes": 171.0, "flops_per_problem": 9406734336.0}, "parity32": {"acc": 0.0, "reasoning_bytes": 195.732, "flops_per_problem": 10643212025.856}, "cmp8": {"acc": 0.906, "reasoning_bytes": 6.324, "flops_per_problem": 1383275741.184}, "cmp9": {"acc": 0.868, "reasoning_bytes": 6.438, "flops_per_problem": 1478579650.56}, "cmp10": {"acc": 0.85, "reasoning_bytes": 6.62, "flops_per_problem": 1575296778.24}, "runmax12": {"acc": 0.688, "reasoning_bytes": 76.384, "flops_per_problem": 4429909426.176}, "runmax14": {"acc": 0.806, "reasoning_bytes": 88.68, "flops_per_problem": 5042186256.384}, "runmax16": {"acc": 0.85, "reasoning_bytes": 100.808, "flops_per_problem": 5653756477.44}, "count16": {"acc": 0.21, "reasoning_bytes": 85.468, "flops_per_problem": 5005530906.624}, "count18": {"acc": 0.114, "reasoning_bytes": 95.248, "flops_per_problem": 5540434034.688}, "count20": {"acc": 0.06, "reasoning_bytes": 105.394, "flops_per_problem": 6111109251.072}, "brackets16": {"acc": 0.612, "reasoning_bytes": 61.94, "flops_per_problem": 4015659810.816}, "brackets18": {"acc": 0.694, "reasoning_bytes": 63.732, "flops_per_problem": 4183656136.704}, "brackets20": {"acc": 0.724, "reasoning_bytes": 66.57, "flops_per_problem": 4397405405.184}, "sumd8": {"acc": 0.104, "reasoning_bytes": 65.024, "flops_per_problem": 3651579445.248}, "sumd9": {"acc": 0.078, "reasoning_bytes": 71.278, "flops_per_problem": 3982449180.672}, "sumd10": {"acc": 0.044, "reasoning_bytes": 77.586, "flops_per_problem": 4320473333.76}, "inc8": {"acc": 0.0, "reasoning_bytes": 71.12, "flops_per_problem": 4107165696.0}, "inc9": {"acc": 0.0, "reasoning_bytes": 79.164, "flops_per_problem": 4548089806.848}, "inc10": {"acc": 0.0, "reasoning_bytes": 86.79, "flops_per_problem": 4968522252.288}, "add.cmp6": {"acc": 0.868, "reasoning_bytes": 91.158, "flops_per_problem": 5468271575.04}, "add.cmp7": {"acc": 0.828, "reasoning_bytes": 102.694, "flops_per_problem": 6107134574.592}, "add.cmp8": {"acc": 0.696, "reasoning_bytes": 114.852, "flops_per_problem": 6777530007.552}, "add.runmax6": {"acc": 0.612, "reasoning_bytes": 126.862, "flops_per_problem": 6839005003.776}, "add.runmax7": {"acc": 0.462, "reasoning_bytes": 143.506, "flops_per_problem": 7666002690.048}, "add.runmax8": {"acc": 0.444, "reasoning_bytes": 158.14, "flops_per_problem": 8399462989.824}, "add.count6": {"acc": 0.366, "reasoning_bytes": 115.886, "flops_per_problem": 6398875828.224}, "add.count7": {"acc": 0.324, "reasoning_bytes": 129.986, "flops_per_problem": 7109636308.992}, "add.count8": {"acc": 0.274, "reasoning_bytes": 144.32, "flops_per_problem": 7831084253.184}, "add.find6": {"acc": 0.262, "reasoning_bytes": 118.916, "flops_per_problem": 6488173559.808}, "add.find7": {"acc": 0.194, "reasoning_bytes": 134.436, "flops_per_problem": 7270389891.072}, "add.find8": {"acc": 0.13, "reasoning_bytes": 150.194, "flops_per_problem": 8064088621.056}, "add.rev6": {"acc": 0.002, "reasoning_bytes": 132.806, "flops_per_problem": 7151591227.392}, "add.rev7": {"acc": 0.0, "reasoning_bytes": 153.472, "flops_per_problem": 8183947198.464}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 173.772, "flops_per_problem": 9184682409.984}, "add.sumd6": {"acc": 0.052, "reasoning_bytes": 130.664, "flops_per_problem": 6962838257.664}, "add.sumd7": {"acc": 0.042, "reasoning_bytes": 149.018, "flops_per_problem": 7859966902.272}, "add.sumd8": {"acc": 0.034, "reasoning_bytes": 165.086, "flops_per_problem": 8662056615.936}, "add.inc6": {"acc": 0.0, "reasoning_bytes": 132.95, "flops_per_problem": 7215451029.504}, "add.inc7": {"acc": 0.0, "reasoning_bytes": 149.234, "flops_per_problem": 8067533340.672}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 165.008, "flops_per_problem": 8884638498.816}, "runmax.cmp12": {"acc": 0.85, "reasoning_bytes": 91.54, "flops_per_problem": 5394342592.512}, "runmax.cmp14": {"acc": 0.97, "reasoning_bytes": 104.748, "flops_per_problem": 6005736161.28}, "runmax.cmp16": {"acc": 0.986, "reasoning_bytes": 115.032, "flops_per_problem": 6539491049.472}, "runmax.runmax12": {"acc": 0.54, "reasoning_bytes": 88.962, "flops_per_problem": 5496447614.976}, "runmax.runmax14": {"acc": 0.9, "reasoning_bytes": 104.944, "flops_per_problem": 6098655264.768}, "runmax.runmax16": {"acc": 0.968, "reasoning_bytes": 117.674, "flops_per_problem": 6705544200.192}, "runmax.count12": {"acc": 0.768, "reasoning_bytes": 91.448, "flops_per_problem": 5530629832.704}, "runmax.count14": {"acc": 0.96, "reasoning_bytes": 105.676, "flops_per_problem": 6138667008.0}, "runmax.count16": {"acc": 0.992, "reasoning_bytes": 117.406, "flops_per_problem": 6731512086.528}, "runmax.find12": {"acc": 0.406, "reasoning_bytes": 87.562, "flops_per_problem": 5502277140.48}, "runmax.find14": {"acc": 0.8, "reasoning_bytes": 103.984, "flops_per_problem": 6102364962.816}, "runmax.find16": {"acc": 0.92, "reasoning_bytes": 117.676, "flops_per_problem": 6711638704.128}, "runmax.rev12": {"acc": 0.41, "reasoning_bytes": 85.46, "flops_per_problem": 5148972564.48}, "runmax.rev14": {"acc": 0.766, "reasoning_bytes": 99.848, "flops_per_problem": 5750561931.264}, "runmax.rev16": {"acc": 0.878, "reasoning_bytes": 112.696, "flops_per_problem": 6358952411.136}, "runmax.sumd12": {"acc": 0.798, "reasoning_bytes": 90.2, "flops_per_problem": 5308401254.4}, "runmax.sumd14": {"acc": 0.976, "reasoning_bytes": 103.838, "flops_per_problem": 5918558257.152}, "runmax.sumd16": {"acc": 0.978, "reasoning_bytes": 114.69, "flops_per_problem": 6479075966.976}, "runmax.inc12": {"acc": 0.558, "reasoning_bytes": 94.228, "flops_per_problem": 5366519857.152}, "runmax.inc14": {"acc": 0.768, "reasoning_bytes": 105.372, "flops_per_problem": 5966431027.2}, "runmax.inc16": {"acc": 0.734, "reasoning_bytes": 117.042, "flops_per_problem": 6589571973.12}, "count.cmp16": {"acc": 0.664, "reasoning_bytes": 100.678, "flops_per_problem": 5937195073.536}, "count.cmp18": {"acc": 0.606, "reasoning_bytes": 110.704, "flops_per_problem": 6468388503.552}, "count.cmp20": {"acc": 0.57, "reasoning_bytes": 120.268, "flops_per_problem": 6982446661.632}, "count.runmax16": {"acc": 0.406, "reasoning_bytes": 102.066, "flops_per_problem": 6037710225.408}, "count.runmax18": {"acc": 0.246, "reasoning_bytes": 112.178, "flops_per_problem": 6576853008.384}, "count.runmax20": {"acc": 0.29, "reasoning_bytes": 122.872, "flops_per_problem": 7144525135.872}, "count.count16": {"acc": 0.836, "reasoning_bytes": 101.38, "flops_per_problem": 6059880087.552}, "count.count18": {"acc": 0.806, "reasoning_bytes": 111.416, "flops_per_problem": 6591250169.856}, "count.count20": {"acc": 0.876, "reasoning_bytes": 121.908, "flops_per_problem": 7189924773.888}, "count.find16": {"acc": 0.62, "reasoning_bytes": 101.934, "flops_per_problem": 6033382244.352}, "count.find18": {"acc": 0.48, "reasoning_bytes": 112.154, "flops_per_problem": 6573319962.624}, "count.find20": {"acc": 0.522, "reasoning_bytes": 121.834, "flops_per_problem": 7093384298.496}, "count.rev16": {"acc": 0.478, "reasoning_bytes": 96.778, "flops_per_problem": 5675043078.144}, "count.rev18": {"acc": 0.322, "reasoning_bytes": 106.774, "flops_per_problem": 6203940028.416}, "count.rev20": {"acc": 0.274, "reasoning_bytes": 117.094, "flops_per_problem": 6756950016.0}, "count.sumd16": {"acc": 0.482, "reasoning_bytes": 99.626, "flops_per_problem": 5846925754.368}, "count.sumd18": {"acc": 0.346, "reasoning_bytes": 109.42, "flops_per_problem": 6369021591.552}, "count.sumd20": {"acc": 0.29, "reasoning_bytes": 119.464, "flops_per_problem": 6908606005.248}, "count.inc16": {"acc": 0.47, "reasoning_bytes": 100.138, "flops_per_problem": 5850635452.416}, "count.inc18": {"acc": 0.338, "reasoning_bytes": 109.812, "flops_per_problem": 6370169831.424}, "count.inc20": {"acc": 0.282, "reasoning_bytes": 120.242, "flops_per_problem": 6915230466.048}, "parity.cmp16": {"acc": 0.0, "reasoning_bytes": 107.288, "flops_per_problem": 6668623872.0}, "parity.cmp20": {"acc": 0.004, "reasoning_bytes": 131.832, "flops_per_problem": 7905013235.712}, "parity.cmp24": {"acc": 0.236, "reasoning_bytes": 158.136, "flops_per_problem": 9130715136.0}, "parity.runmax16": {"acc": 0.0, "reasoning_bytes": 110.864, "flops_per_problem": 6756950016.0}, "parity.runmax20": {"acc": 0.038, "reasoning_bytes": 136.892, "flops_per_problem": 7993516032.0}, "parity.runmax24": {"acc": 0.152, "reasoning_bytes": 162.236, "flops_per_problem": 9230082048.0}, "parity.count16": {"acc": 0.0, "reasoning_bytes": 107.012, "flops_per_problem": 6801113088.0}, "parity.count20": {"acc": 0.0, "reasoning_bytes": 131.696, "flops_per_problem": 8037679104.0}, "parity.count24": {"acc": 0.094, "reasoning_bytes": 158.148, "flops_per_problem": 9259053023.232}, "parity.find16": {"acc": 0.0, "reasoning_bytes": 108.248, "flops_per_problem": 6756950016.0}, "parity.find20": {"acc": 0.0, "reasoning_bytes": 133.46, "flops_per_problem": 7993516032.0}, "parity.find24": {"acc": 0.014, "reasoning_bytes": 156.35, "flops_per_problem": 9229287112.704}, "parity.rev16": {"acc": 0.0, "reasoning_bytes": 112.208, "flops_per_problem": 6403645440.0}, "parity.rev20": {"acc": 0.0, "reasoning_bytes": 136.16, "flops_per_problem": 7640211456.0}, "parity.rev24": {"acc": 0.0, "reasoning_bytes": 159.776, "flops_per_problem": 8876777472.0}, "parity.sumd16": {"acc": 0.0, "reasoning_bytes": 108.596, "flops_per_problem": 6580297728.0}, "parity.sumd20": {"acc": 0.046, "reasoning_bytes": 134.796, "flops_per_problem": 7816863744.0}, "parity.sumd24": {"acc": 0.064, "reasoning_bytes": 158.412, "flops_per_problem": 9053253107.712}, "parity.inc16": {"acc": 0.0, "reasoning_bytes": 113.924, "flops_per_problem": 6580297728.0}, "parity.inc20": {"acc": 0.0, "reasoning_bytes": 138.54, "flops_per_problem": 7816863744.0}, "parity.inc24": {"acc": 0.0, "reasoning_bytes": 162.94, "flops_per_problem": 9053429760.0}, "sumd.cmp6": {"acc": 0.846, "reasoning_bytes": 63.132, "flops_per_problem": 3759249014.784}, "sumd.cmp7": {"acc": 0.83, "reasoning_bytes": 71.526, "flops_per_problem": 4174293565.44}, "sumd.cmp8": {"acc": 0.806, "reasoning_bytes": 79.13, "flops_per_problem": 4554272636.928}, "sumd.runmax6": {"acc": 0.362, "reasoning_bytes": 72.836, "flops_per_problem": 4175353479.168}, "sumd.runmax7": {"acc": 0.316, "reasoning_bytes": 80.456, "flops_per_problem": 4568758124.544}, "sumd.runmax8": {"acc": 0.214, "reasoning_bytes": 88.182, "flops_per_problem": 4960396247.04}, "sumd.count6": {"acc": 0.77, "reasoning_bytes": 68.352, "flops_per_problem": 4027230535.68}, "sumd.count7": {"acc": 0.678, "reasoning_bytes": 76.638, "flops_per_problem": 4436268908.544}, "sumd.count8": {"acc": 0.574, "reasoning_bytes": 85.176, "flops_per_problem": 4860764356.608}, "sumd.find6": {"acc": 0.67, "reasoning_bytes": 70.228, "flops_per_problem": 4062649319.424}, "sumd.find7": {"acc": 0.622, "reasoning_bytes": 78.53, "flops_per_problem": 4472924258.304}, "sumd.find8": {"acc": 0.61, "reasoning_bytes": 85.852, "flops_per_problem": 4843540758.528}, "sumd.rev6": {"acc": 0.172, "reasoning_bytes": 68.38, "flops_per_problem": 3883347247.104}, "sumd.rev7": {"acc": 0.154, "reasoning_bytes": 76.118, "flops_per_problem": 4269067517.952}, "sumd.rev8": {"acc": 0.116, "reasoning_bytes": 83.438, "flops_per_problem": 4640478953.472}, "sumd.sumd6": {"acc": 0.33, "reasoning_bytes": 70.71, "flops_per_problem": 4015306506.24}, "sumd.sumd7": {"acc": 0.242, "reasoning_bytes": 78.18, "flops_per_problem": 4390427639.808}, "sumd.sumd8": {"acc": 0.168, "reasoning_bytes": 84.804, "flops_per_problem": 4726950248.448}, "sumd.inc6": {"acc": 0.06, "reasoning_bytes": 74.73, "flops_per_problem": 4168110735.36}, "sumd.inc7": {"acc": 0.012, "reasoning_bytes": 81.872, "flops_per_problem": 4530689556.48}, "sumd.inc8": {"acc": 0.01, "reasoning_bytes": 89.138, "flops_per_problem": 4900599447.552}, "inc.cmp6": {"acc": 0.642, "reasoning_bytes": 88.844, "flops_per_problem": 5033618620.416}, "inc.cmp7": {"acc": 0.67, "reasoning_bytes": 98.194, "flops_per_problem": 5531159789.568}, "inc.cmp8": {"acc": 0.678, "reasoning_bytes": 109.334, "flops_per_problem": 6112699121.664}, "inc.runmax6": {"acc": 0.088, "reasoning_bytes": 111.656, "flops_per_problem": 5829525504.0}, "inc.runmax7": {"acc": 0.566, "reasoning_bytes": 126.48, "flops_per_problem": 6580297728.0}, "inc.runmax8": {"acc": 0.406, "reasoning_bytes": 141.962, "flops_per_problem": 7321177423.872}, "inc.count6": {"acc": 0.068, "reasoning_bytes": 106.808, "flops_per_problem": 5652873216.0}, "inc.count7": {"acc": 0.366, "reasoning_bytes": 119.718, "flops_per_problem": 6295092609.024}, "inc.count8": {"acc": 0.404, "reasoning_bytes": 124.81, "flops_per_problem": 6570228547.584}, "inc.find6": {"acc": 0.274, "reasoning_bytes": 102.316, "flops_per_problem": 5432499486.72}, "inc.find7": {"acc": 0.294, "reasoning_bytes": 111.386, "flops_per_problem": 5891088826.368}, "inc.find8": {"acc": 0.29, "reasoning_bytes": 121.386, "flops_per_problem": 6380062359.552}, "inc.rev6": {"acc": 0.0, "reasoning_bytes": 113.884, "flops_per_problem": 5917851648.0}, "inc.rev7": {"acc": 0.0, "reasoning_bytes": 133.7, "flops_per_problem": 6888290992.128}, "inc.rev8": {"acc": 0.0, "reasoning_bytes": 155.252, "flops_per_problem": 7885669810.176}, "inc.sumd6": {"acc": 0.042, "reasoning_bytes": 116.846, "flops_per_problem": 6092560760.832}, "inc.sumd7": {"acc": 0.006, "reasoning_bytes": 134.35, "flops_per_problem": 6926889517.056}, "inc.sumd8": {"acc": 0.038, "reasoning_bytes": 150.032, "flops_per_problem": 7617688289.28}, "inc.inc6": {"acc": 0.0, "reasoning_bytes": 121.952, "flops_per_problem": 6315319296.0}, "inc.inc7": {"acc": 0.0, "reasoning_bytes": 142.992, "flops_per_problem": 7195312668.672}, "inc.inc8": {"acc": 0.0, "reasoning_bytes": 159.062, "flops_per_problem": 8013742718.976}, "count.inc.cmp16": {"acc": 0.392, "reasoning_bytes": 115.862, "flops_per_problem": 6800406478.848}, "count.inc.cmp18": {"acc": 0.342, "reasoning_bytes": 125.102, "flops_per_problem": 7308016828.416}, "count.inc.cmp20": {"acc": 0.316, "reasoning_bytes": 134.084, "flops_per_problem": 7807236194.304}, "inc.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 161.708, "flops_per_problem": 8301332643.84}, "inc.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 179.894, "flops_per_problem": 9195281547.264}, "inc.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 200.774, "flops_per_problem": 10204142764.032}, "parity.runmax.count16": {"acc": 0.002, "reasoning_bytes": 124.022, "flops_per_problem": 7860938489.856}, "parity.runmax.count20": {"acc": 0.022, "reasoning_bytes": 148.242, "flops_per_problem": 9096621244.416}, "parity.runmax.count24": {"acc": 0.436, "reasoning_bytes": 176.808, "flops_per_problem": 10314903748.608}, "add.count.find6": {"acc": 0.094, "reasoning_bytes": 131.342, "flops_per_problem": 7390425120.768}, "add.count.find7": {"acc": 0.094, "reasoning_bytes": 136.272, "flops_per_problem": 7703806279.68}, "add.count.find8": {"acc": 0.03, "reasoning_bytes": 136.762, "flops_per_problem": 7845834719.232}, "runmax.inc.find12": {"acc": 0.682, "reasoning_bytes": 116.724, "flops_per_problem": 6656434864.128}, "runmax.inc.find14": {"acc": 0.722, "reasoning_bytes": 126.494, "flops_per_problem": 7177117483.008}, "runmax.inc.find16": {"acc": 0.636, "reasoning_bytes": 136.052, "flops_per_problem": 7692500533.248}, "parity.sumd.rev16": {"acc": 0.0, "reasoning_bytes": 122.36, "flops_per_problem": 7286906880.0}, "parity.sumd.rev20": {"acc": 0.004, "reasoning_bytes": 146.648, "flops_per_problem": 8523031265.28}, "parity.sumd.rev24": {"acc": 0.132, "reasoning_bytes": 172.376, "flops_per_problem": 9747408273.408}, "parity.rev.sumd16": {"acc": 0.0, "reasoning_bytes": 119.192, "flops_per_problem": 7286906880.0}, "parity.rev.sumd20": {"acc": 0.0, "reasoning_bytes": 143.768, "flops_per_problem": 8523296243.712}, "parity.rev.sumd24": {"acc": 0.096, "reasoning_bytes": 169.868, "flops_per_problem": 9749616427.008}, "count.inc.sumd16": {"acc": 0.538, "reasoning_bytes": 115.858, "flops_per_problem": 6747145814.016}, "count.inc.sumd18": {"acc": 0.436, "reasoning_bytes": 125.458, "flops_per_problem": 7259614101.504}, "count.inc.sumd20": {"acc": 0.342, "reasoning_bytes": 134.54, "flops_per_problem": 7752385658.88}, "inc.sumd.rev6": {"acc": 0.006, "reasoning_bytes": 133.748, "flops_per_problem": 7106809872.384}, "inc.sumd.rev7": {"acc": 0.01, "reasoning_bytes": 151.772, "flops_per_problem": 7920293658.624}, "inc.sumd.rev8": {"acc": 0.014, "reasoning_bytes": 166.38, "flops_per_problem": 8522412982.272}, "count.count.cmp16": {"acc": 0.82, "reasoning_bytes": 117.432, "flops_per_problem": 7034294108.16}, "count.count.cmp18": {"acc": 0.832, "reasoning_bytes": 127.868, "flops_per_problem": 7586244182.016}, "count.count.cmp20": {"acc": 0.84, "reasoning_bytes": 137.554, "flops_per_problem": 8102510493.696}, "parity.rev.find16": {"acc": 0.0, "reasoning_bytes": 119.564, "flops_per_problem": 7463559168.0}, "parity.rev.find20": {"acc": 0.0, "reasoning_bytes": 143.048, "flops_per_problem": 8700125184.0}, "parity.rev.find24": {"acc": 0.296, "reasoning_bytes": 171.028, "flops_per_problem": 9920615841.792}, "count.sumd.cmp16": {"acc": 0.714, "reasoning_bytes": 115.526, "flops_per_problem": 6818071707.648}, "count.sumd.cmp18": {"acc": 0.78, "reasoning_bytes": 125.782, "flops_per_problem": 7361984102.4}, "count.sumd.cmp20": {"acc": 0.85, "reasoning_bytes": 135.418, "flops_per_problem": 7879486980.096}, "sumd.count.count6": {"acc": 0.932, "reasoning_bytes": 84.184, "flops_per_problem": 5083876196.352}, "sumd.count.count7": {"acc": 0.924, "reasoning_bytes": 92.344, "flops_per_problem": 5491236372.48}, "sumd.count.count8": {"acc": 0.952, "reasoning_bytes": 100.954, "flops_per_problem": 5916880060.416}, "runmax.rev.inc12": {"acc": 0.352, "reasoning_bytes": 106.82, "flops_per_problem": 6089910976.512}, "runmax.rev.inc14": {"acc": 0.534, "reasoning_bytes": 118.044, "flops_per_problem": 6688408928.256}, "runmax.rev.inc16": {"acc": 0.754, "reasoning_bytes": 129.224, "flops_per_problem": 7293443014.656}, "parity.sumd.find16": {"acc": 0.0, "reasoning_bytes": 122.048, "flops_per_problem": 7640211456.0}, "parity.sumd.find20": {"acc": 0.114, "reasoning_bytes": 147.32, "flops_per_problem": 8871477903.36}, "parity.sumd.find24": {"acc": 0.28, "reasoning_bytes": 178.82, "flops_per_problem": 10070416982.016}, "runmax.runmax.cmp12": {"acc": 0.662, "reasoning_bytes": 106.64, "flops_per_problem": 6462647304.192}, "runmax.runmax.cmp14": {"acc": 0.918, "reasoning_bytes": 121.216, "flops_per_problem": 7069359587.328}, "runmax.runmax.cmp16": {"acc": 0.982, "reasoning_bytes": 133.652, "flops_per_problem": 7673775390.72}, "count.runmax.count16": {"acc": 0.738, "reasoning_bytes": 118.76, "flops_per_problem": 7133131063.296}, "count.runmax.count18": {"acc": 0.634, "reasoning_bytes": 129.014, "flops_per_problem": 7672362172.416}, "count.runmax.count20": {"acc": 1.0, "reasoning_bytes": 139.838, "flops_per_problem": 8251340046.336}, "inc.inc.sumd6": {"acc": 0.004, "reasoning_bytes": 182.534, "flops_per_problem": 9173641641.984}, "inc.inc.sumd7": {"acc": 0.016, "reasoning_bytes": 204.264, "flops_per_problem": 10245744377.856}, "inc.inc.sumd8": {"acc": 0.04, "reasoning_bytes": 215.998, "flops_per_problem": 10807498653.696}, "add.sumd.find6": {"acc": 0.63, "reasoning_bytes": 154.022, "flops_per_problem": 8258141159.424}, "add.sumd.find7": {"acc": 0.642, "reasoning_bytes": 172.366, "flops_per_problem": 9157742936.064}, "add.sumd.find8": {"acc": 0.588, "reasoning_bytes": 190.184, "flops_per_problem": 10033408327.68}, "sumd.rev.rev6": {"acc": 0.28, "reasoning_bytes": 85.558, "flops_per_problem": 4821724200.96}, "sumd.rev.rev7": {"acc": 0.196, "reasoning_bytes": 93.08, "flops_per_problem": 5200466706.432}, "sumd.rev.rev8": {"acc": 0.094, "reasoning_bytes": 100.356, "flops_per_problem": 5575057883.136}, "runmax.inc.runmax12": {"acc": 0.346, "reasoning_bytes": 116.0, "flops_per_problem": 6703424372.736}, "runmax.inc.runmax14": {"acc": 0.382, "reasoning_bytes": 127.956, "flops_per_problem": 7284433747.968}, "runmax.inc.runmax16": {"acc": 0.538, "reasoning_bytes": 140.008, "flops_per_problem": 7871272648.704}, "parity.inc.find16": {"acc": 0.0, "reasoning_bytes": 123.084, "flops_per_problem": 7640211456.0}, "parity.inc.find20": {"acc": 0.01, "reasoning_bytes": 147.398, "flops_per_problem": 8876159188.992}, "parity.inc.find24": {"acc": 0.04, "reasoning_bytes": 176.762, "flops_per_problem": 10111047008.256}, "inc.runmax.sumd6": {"acc": 0.372, "reasoning_bytes": 121.824, "flops_per_problem": 6712786944.0}, "inc.runmax.sumd7": {"acc": 0.046, "reasoning_bytes": 135.882, "flops_per_problem": 7460379426.816}, "inc.runmax.sumd8": {"acc": 0.492, "reasoning_bytes": 151.926, "flops_per_problem": 8096062685.184}, "sumd.rev.cmp6": {"acc": 0.692, "reasoning_bytes": 81.858, "flops_per_problem": 4763340619.776}, "sumd.rev.cmp7": {"acc": 0.65, "reasoning_bytes": 90.404, "flops_per_problem": 5188277698.56}, "sumd.rev.cmp8": {"acc": 0.456, "reasoning_bytes": 98.98, "flops_per_problem": 5618514345.984}, "runmax.runmax.count12": {"acc": 0.65, "reasoning_bytes": 107.15, "flops_per_problem": 6595754803.2}, "runmax.runmax.count14": {"acc": 0.88, "reasoning_bytes": 121.702, "flops_per_problem": 7203703652.352}, "runmax.runmax.count16": {"acc": 0.984, "reasoning_bytes": 134.742, "flops_per_problem": 7812800741.376}, "count.count.count16": {"acc": 0.892, "reasoning_bytes": 118.314, "flops_per_problem": 7163515256.832}, "count.count.count18": {"acc": 0.936, "reasoning_bytes": 128.558, "flops_per_problem": 7706191085.568}, "count.count.count20": {"acc": 1.0, "reasoning_bytes": 138.434, "flops_per_problem": 8233498165.248}, "add.sumd.rev6": {"acc": 0.052, "reasoning_bytes": 149.666, "flops_per_problem": 7982475264.0}, "add.sumd.rev7": {"acc": 0.026, "reasoning_bytes": 168.246, "flops_per_problem": 8893471113.216}, "add.sumd.rev8": {"acc": 0.006, "reasoning_bytes": 185.728, "flops_per_problem": 9767723286.528}, "add.rev.rev6": {"acc": 0.0, "reasoning_bytes": 198.246, "flops_per_problem": 10216950054.912}, "add.rev.rev7": {"acc": 0.0, "reasoning_bytes": 227.782, "flops_per_problem": 11664968859.648}, "add.rev.rev8": {"acc": 0.0, "reasoning_bytes": 249.488, "flops_per_problem": 12769663942.656}, "inc.runmax.cmp6": {"acc": 0.702, "reasoning_bytes": 120.812, "flops_per_problem": 6541522550.784}, "inc.runmax.cmp7": {"acc": 0.69, "reasoning_bytes": 137.848, "flops_per_problem": 7345202135.04}, "inc.runmax.cmp8": {"acc": 0.718, "reasoning_bytes": 149.928, "flops_per_problem": 7920646963.2}, "count.rev.cmp16": {"acc": 0.66, "reasoning_bytes": 112.67, "flops_per_problem": 6645570748.416}, "count.rev.cmp18": {"acc": 0.594, "reasoning_bytes": 122.846, "flops_per_problem": 7180738854.912}, "count.rev.cmp20": {"acc": 0.642, "reasoning_bytes": 132.326, "flops_per_problem": 7691352293.376}} +{"step": 2000, "train_loss": 1.3348097801208496} +{"step": 2020, "train_loss": 1.264256238937378} +{"step": 2040, "train_loss": 1.243257761001587} +{"step": 2060, "train_loss": 1.376349925994873} +{"step": 2080, "train_loss": 1.2794382572174072} +{"step": 2100, "train_loss": 1.3004014492034912} +{"step": 2120, "train_loss": 1.333446979522705} +{"step": 2140, "train_loss": 1.2933902740478516} +{"step": 2160, "train_loss": 1.4056847095489502} +{"step": 2180, "train_loss": 1.3897055387496948} +{"step": 2200, "train_loss": 1.3239765167236328} +{"step": 2220, "train_loss": 1.3136392831802368} +{"step": 2240, "train_loss": 1.3397611379623413} +{"step": 2260, "train_loss": 1.2606256008148193} +{"step": 2280, "train_loss": 1.2244813442230225} +{"step": 2300, "train_loss": 1.2587831020355225} +{"step": 2320, "train_loss": 1.25813627243042} +{"step": 2340, "train_loss": 1.2558921575546265} +{"step": 2360, "train_loss": 1.294896125793457} +{"step": 2380, "train_loss": 1.222031831741333} +{"step": 2400, "train_loss": 1.233133316040039} +{"step": 2420, "train_loss": 1.2022833824157715} +{"step": 2440, "train_loss": 1.2289817333221436} +{"step": 2460, "train_loss": 1.2587155103683472} +{"step": 2480, "train_loss": 1.2772411108016968} +{"step": 2500, "train_loss": 1.350165605545044} +{"step": 2520, "train_loss": 1.2656880617141724} +{"step": 2540, "train_loss": 1.269048810005188} +{"step": 2560, "train_loss": 1.2815098762512207} +{"step": 2580, "train_loss": 1.2260487079620361} +{"step": 2600, "train_loss": 1.351149559020996} +{"step": 2620, "train_loss": 1.2418465614318848} +{"step": 2640, "train_loss": 1.3156201839447021} +{"step": 2660, "train_loss": 1.3520655632019043} +{"step": 2680, "train_loss": 1.2156424522399902} +{"step": 2700, "train_loss": 1.2783782482147217} +{"step": 2720, "train_loss": 1.3501718044281006} +{"step": 2740, "train_loss": 1.2387374639511108} +{"step": 2760, "train_loss": 1.3044229745864868} +{"step": 2780, "train_loss": 1.2801522016525269} +{"step": 2800, "train_loss": 1.2579717636108398} +{"step": 2820, "train_loss": 1.292932152748108} +{"step": 2840, "train_loss": 1.2087574005126953} +{"step": 2860, "train_loss": 1.246259093284607} +{"step": 2880, "train_loss": 1.292593002319336} +{"step": 2900, "train_loss": 1.214779019355774} +{"step": 2920, "train_loss": 1.3371458053588867} +{"step": 2940, "train_loss": 1.205134391784668} +{"step": 2960, "train_loss": 1.1936137676239014} +{"step": 2980, "train_loss": 1.2849578857421875} +{"step": 3000, "tokens": 98304000, "val_loss": 2.1750993132591248, "val_bpb": 0.7840879652107701, "lr": 0.0005323183730895466, "elapsed": 512.7306132316589, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.0, "reasoning_bytes": 78.996, "flops_per_problem": 4884965720.064}, "add9": {"acc": 0.0, "reasoning_bytes": 89.02, "flops_per_problem": 5443805233.152}, "add10": {"acc": 0.0, "reasoning_bytes": 98.816, "flops_per_problem": 6000171614.208}, "reach14": {"acc": 0.534, "reasoning_bytes": 4.744, "flops_per_problem": 4493327597.568}, "reach16": {"acc": 0.474, "reasoning_bytes": 4.844, "flops_per_problem": 5027700768.768}, "reach18": {"acc": 0.526, "reasoning_bytes": 5.554, "flops_per_problem": 5589013413.888}, "parity24": {"acc": 0.476, "reasoning_bytes": 133.952, "flops_per_problem": 7461439340.544}, "parity28": {"acc": 0.494, "reasoning_bytes": 153.948, "flops_per_problem": 8521176416.256}, "parity32": {"acc": 0.478, "reasoning_bytes": 176.856, "flops_per_problem": 9709604683.776}, "cmp8": {"acc": 0.964, "reasoning_bytes": 5.792, "flops_per_problem": 1359869313.024}, "cmp9": {"acc": 0.962, "reasoning_bytes": 5.768, "flops_per_problem": 1447135543.296}, "cmp10": {"acc": 0.928, "reasoning_bytes": 5.84, "flops_per_problem": 1538641428.48}, "runmax12": {"acc": 0.998, "reasoning_bytes": 69.392, "flops_per_problem": 4080314548.224}, "runmax14": {"acc": 0.978, "reasoning_bytes": 77.16, "flops_per_problem": 4511699435.52}, "runmax16": {"acc": 0.948, "reasoning_bytes": 88.108, "flops_per_problem": 5083522891.776}, "count16": {"acc": 0.868, "reasoning_bytes": 78.7, "flops_per_problem": 4712199782.4}, "count18": {"acc": 0.692, "reasoning_bytes": 87.74, "flops_per_problem": 5200378380.288}, "count20": {"acc": 0.496, "reasoning_bytes": 96.4, "flops_per_problem": 5670538444.8}, "brackets16": {"acc": 0.582, "reasoning_bytes": 42.028, "flops_per_problem": 3136638025.728}, "brackets18": {"acc": 0.574, "reasoning_bytes": 43.306, "flops_per_problem": 3282111184.896}, "brackets20": {"acc": 0.532, "reasoning_bytes": 55.348, "flops_per_problem": 3901719085.056}, "sumd8": {"acc": 0.226, "reasoning_bytes": 59.788, "flops_per_problem": 3518560272.384}, "sumd9": {"acc": 0.022, "reasoning_bytes": 68.23, "flops_per_problem": 4015394832.384}, "sumd10": {"acc": 0.0, "reasoning_bytes": 72.626, "flops_per_problem": 4310050848.768}, "inc8": {"acc": 0.156, "reasoning_bytes": 62.984, "flops_per_problem": 3765078540.288}, "inc9": {"acc": 0.008, "reasoning_bytes": 69.86, "flops_per_problem": 4140111347.712}, "inc10": {"acc": 0.0, "reasoning_bytes": 72.686, "flops_per_problem": 4322416508.928}, "add.cmp6": {"acc": 0.952, "reasoning_bytes": 91.424, "flops_per_problem": 5479135690.752}, "add.cmp7": {"acc": 0.884, "reasoning_bytes": 103.534, "flops_per_problem": 6143701598.208}, "add.cmp8": {"acc": 0.718, "reasoning_bytes": 116.5, "flops_per_problem": 6851017359.36}, "add.runmax6": {"acc": 0.904, "reasoning_bytes": 117.97, "flops_per_problem": 6446483619.84}, "add.runmax7": {"acc": 0.588, "reasoning_bytes": 132.294, "flops_per_problem": 7167401607.168}, "add.runmax8": {"acc": 0.532, "reasoning_bytes": 147.902, "flops_per_problem": 7945024978.944}, "add.count6": {"acc": 0.604, "reasoning_bytes": 112.6, "flops_per_problem": 6253579321.344}, "add.count7": {"acc": 0.478, "reasoning_bytes": 126.006, "flops_per_problem": 6934132260.864}, "add.count8": {"acc": 0.432, "reasoning_bytes": 139.206, "flops_per_problem": 7605410955.264}, "add.find6": {"acc": 0.66, "reasoning_bytes": 107.926, "flops_per_problem": 6003263029.248}, "add.find7": {"acc": 0.4, "reasoning_bytes": 121.68, "flops_per_problem": 6700156305.408}, "add.find8": {"acc": 0.294, "reasoning_bytes": 136.224, "flops_per_problem": 7432909996.032}, "add.rev6": {"acc": 0.38, "reasoning_bytes": 121.934, "flops_per_problem": 6727449083.904}, "add.rev7": {"acc": 0.008, "reasoning_bytes": 141.99, "flops_per_problem": 7740284977.152}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 159.286, "flops_per_problem": 8614360498.176}, "add.sumd6": {"acc": 0.264, "reasoning_bytes": 121.762, "flops_per_problem": 6569521938.432}, "add.sumd7": {"acc": 0.048, "reasoning_bytes": 137.056, "flops_per_problem": 7333896388.608}, "add.sumd8": {"acc": 0.026, "reasoning_bytes": 152.72, "flops_per_problem": 8113197957.12}, "add.inc6": {"acc": 0.142, "reasoning_bytes": 128.136, "flops_per_problem": 6993929060.352}, "add.inc7": {"acc": 0.004, "reasoning_bytes": 142.826, "flops_per_problem": 7743553044.48}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 157.314, "flops_per_problem": 8473833603.072}, "runmax.cmp12": {"acc": 0.998, "reasoning_bytes": 84.096, "flops_per_problem": 4994666790.912}, "runmax.cmp14": {"acc": 0.988, "reasoning_bytes": 93.072, "flops_per_problem": 5479400669.184}, "runmax.cmp16": {"acc": 0.98, "reasoning_bytes": 101.212, "flops_per_problem": 5927214219.264}, "runmax.runmax12": {"acc": 0.998, "reasoning_bytes": 86.716, "flops_per_problem": 5154537111.552}, "runmax.runmax14": {"acc": 0.976, "reasoning_bytes": 94.296, "flops_per_problem": 5577619341.312}, "runmax.runmax16": {"acc": 0.966, "reasoning_bytes": 105.232, "flops_per_problem": 6148912840.704}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 84.244, "flops_per_problem": 5089529069.568}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 94.008, "flops_per_problem": 5609063448.576}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 101.964, "flops_per_problem": 6048750993.408}, "runmax.find12": {"acc": 0.982, "reasoning_bytes": 83.5, "flops_per_problem": 5012508672.0}, "runmax.find14": {"acc": 0.976, "reasoning_bytes": 93.996, "flops_per_problem": 5564370419.712}, "runmax.find16": {"acc": 0.964, "reasoning_bytes": 100.492, "flops_per_problem": 5939579879.424}, "runmax.rev12": {"acc": 0.998, "reasoning_bytes": 81.368, "flops_per_problem": 4785863786.496}, "runmax.rev14": {"acc": 0.972, "reasoning_bytes": 89.096, "flops_per_problem": 5215482150.912}, "runmax.rev16": {"acc": 0.944, "reasoning_bytes": 97.204, "flops_per_problem": 5661882482.688}, "runmax.sumd12": {"acc": 0.996, "reasoning_bytes": 83.336, "flops_per_problem": 4916939784.192}, "runmax.sumd14": {"acc": 0.976, "reasoning_bytes": 92.032, "flops_per_problem": 5389308002.304}, "runmax.sumd16": {"acc": 0.944, "reasoning_bytes": 99.296, "flops_per_problem": 5798434701.312}, "runmax.inc12": {"acc": 0.994, "reasoning_bytes": 83.988, "flops_per_problem": 4932485185.536}, "runmax.inc14": {"acc": 0.97, "reasoning_bytes": 93.024, "flops_per_problem": 5422606958.592}, "runmax.inc16": {"acc": 0.936, "reasoning_bytes": 100.152, "flops_per_problem": 5826699067.392}, "count.cmp16": {"acc": 0.968, "reasoning_bytes": 94.53, "flops_per_problem": 5676279644.16}, "count.cmp18": {"acc": 0.946, "reasoning_bytes": 103.54, "flops_per_problem": 6162603393.024}, "count.cmp20": {"acc": 0.892, "reasoning_bytes": 111.924, "flops_per_problem": 6621281058.816}, "count.runmax16": {"acc": 0.818, "reasoning_bytes": 95.29, "flops_per_problem": 5754006650.88}, "count.runmax18": {"acc": 0.726, "reasoning_bytes": 104.52, "flops_per_problem": 6249957949.44}, "count.runmax20": {"acc": 0.622, "reasoning_bytes": 113.13, "flops_per_problem": 6718528143.36}, "count.count16": {"acc": 1.0, "reasoning_bytes": 94.57, "flops_per_problem": 5766372311.04}, "count.count18": {"acc": 1.0, "reasoning_bytes": 103.538, "flops_per_problem": 6250752884.736}, "count.count20": {"acc": 0.996, "reasoning_bytes": 112.146, "flops_per_problem": 6719323078.656}, "count.find16": {"acc": 0.894, "reasoning_bytes": 94.812, "flops_per_problem": 5732896702.464}, "count.find18": {"acc": 0.866, "reasoning_bytes": 103.622, "flops_per_problem": 6210299510.784}, "count.find20": {"acc": 0.804, "reasoning_bytes": 112.004, "flops_per_problem": 6668800524.288}, "count.rev16": {"acc": 0.872, "reasoning_bytes": 90.19, "flops_per_problem": 5396285767.68}, "count.rev18": {"acc": 0.76, "reasoning_bytes": 99.17, "flops_per_problem": 5881196298.24}, "count.rev20": {"acc": 0.596, "reasoning_bytes": 107.794, "flops_per_problem": 6350384775.168}, "count.sumd16": {"acc": 0.844, "reasoning_bytes": 92.42, "flops_per_problem": 5538932490.24}, "count.sumd18": {"acc": 0.702, "reasoning_bytes": 101.19, "flops_per_problem": 6014568775.68}, "count.sumd20": {"acc": 0.604, "reasoning_bytes": 109.81, "flops_per_problem": 6483580600.32}, "count.inc16": {"acc": 0.852, "reasoning_bytes": 94.146, "flops_per_problem": 5570994880.512}, "count.inc18": {"acc": 0.696, "reasoning_bytes": 102.982, "flops_per_problem": 6049545928.704}, "count.inc20": {"acc": 0.572, "reasoning_bytes": 111.436, "flops_per_problem": 6511226683.392}, "parity.cmp16": {"acc": 0.944, "reasoning_bytes": 105.288, "flops_per_problem": 6107222900.736}, "parity.cmp20": {"acc": 0.934, "reasoning_bytes": 123.996, "flops_per_problem": 7110077939.712}, "parity.cmp24": {"acc": 0.952, "reasoning_bytes": 140.064, "flops_per_problem": 7996342468.608}, "parity.runmax16": {"acc": 0.498, "reasoning_bytes": 106.372, "flops_per_problem": 6199258742.784}, "parity.runmax20": {"acc": 0.478, "reasoning_bytes": 126.976, "flops_per_problem": 7285846966.272}, "parity.runmax24": {"acc": 0.536, "reasoning_bytes": 145.024, "flops_per_problem": 8259554377.728}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 106.264, "flops_per_problem": 6238652203.008}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 126.892, "flops_per_problem": 7326300340.224}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 145.036, "flops_per_problem": 8304247406.592}, "parity.find16": {"acc": 0.87, "reasoning_bytes": 106.072, "flops_per_problem": 6186009821.184}, "parity.find20": {"acc": 0.864, "reasoning_bytes": 124.996, "flops_per_problem": 7198404083.712}, "parity.find24": {"acc": 0.858, "reasoning_bytes": 142.384, "flops_per_problem": 8142963867.648}, "parity.rev16": {"acc": 0.512, "reasoning_bytes": 101.276, "flops_per_problem": 5841714511.872}, "parity.rev20": {"acc": 0.468, "reasoning_bytes": 120.944, "flops_per_problem": 6886966099.968}, "parity.rev24": {"acc": 0.524, "reasoning_bytes": 138.608, "flops_per_problem": 7843714891.776}, "parity.sumd16": {"acc": 0.524, "reasoning_bytes": 104.084, "flops_per_problem": 6009887490.048}, "parity.sumd20": {"acc": 0.454, "reasoning_bytes": 122.696, "flops_per_problem": 7008502874.112}, "parity.sumd24": {"acc": 0.5, "reasoning_bytes": 140.372, "flops_per_problem": 7965781622.784}, "parity.inc16": {"acc": 0.578, "reasoning_bytes": 105.48, "flops_per_problem": 6027376066.56}, "parity.inc20": {"acc": 0.482, "reasoning_bytes": 124.752, "flops_per_problem": 7055139078.144}, "parity.inc24": {"acc": 0.542, "reasoning_bytes": 142.752, "flops_per_problem": 8026726662.144}, "sumd.cmp6": {"acc": 0.956, "reasoning_bytes": 62.048, "flops_per_problem": 3711641223.168}, "sumd.cmp7": {"acc": 0.926, "reasoning_bytes": 69.868, "flops_per_problem": 4101336170.496}, "sumd.cmp8": {"acc": 0.892, "reasoning_bytes": 73.928, "flops_per_problem": 4324624662.528}, "sumd.runmax6": {"acc": 0.938, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.75, "reasoning_bytes": 75.702, "flops_per_problem": 4365607993.344}, "sumd.runmax8": {"acc": 0.392, "reasoning_bytes": 82.14, "flops_per_problem": 4690383224.832}, "sumd.count6": {"acc": 0.974, "reasoning_bytes": 66.466, "flops_per_problem": 3951270051.84}, "sumd.count7": {"acc": 0.888, "reasoning_bytes": 74.848, "flops_per_problem": 4367992799.232}, "sumd.count8": {"acc": 0.76, "reasoning_bytes": 80.422, "flops_per_problem": 4662825467.904}, "sumd.find6": {"acc": 0.968, "reasoning_bytes": 66.434, "flops_per_problem": 3906577022.976}, "sumd.find7": {"acc": 0.834, "reasoning_bytes": 74.99, "flops_per_problem": 4333722255.36}, "sumd.find8": {"acc": 0.652, "reasoning_bytes": 81.814, "flops_per_problem": 4681285632.0}, "sumd.rev6": {"acc": 0.89, "reasoning_bytes": 61.544, "flops_per_problem": 3601145217.024}, "sumd.rev7": {"acc": 0.656, "reasoning_bytes": 69.998, "flops_per_problem": 4018486247.424}, "sumd.rev8": {"acc": 0.348, "reasoning_bytes": 77.68, "flops_per_problem": 4398995275.776}, "sumd.sumd6": {"acc": 0.786, "reasoning_bytes": 65.78, "flops_per_problem": 3797229256.704}, "sumd.sumd7": {"acc": 0.434, "reasoning_bytes": 73.958, "flops_per_problem": 4206620934.144}, "sumd.sumd8": {"acc": 0.12, "reasoning_bytes": 80.158, "flops_per_problem": 4526273249.28}, "sumd.inc6": {"acc": 0.73, "reasoning_bytes": 68.68, "flops_per_problem": 3917352812.544}, "sumd.inc7": {"acc": 0.33, "reasoning_bytes": 76.944, "flops_per_problem": 4340081737.728}, "sumd.inc8": {"acc": 0.042, "reasoning_bytes": 87.586, "flops_per_problem": 4845042302.976}, "inc.cmp6": {"acc": 0.966, "reasoning_bytes": 78.136, "flops_per_problem": 4554802593.792}, "inc.cmp7": {"acc": 0.862, "reasoning_bytes": 88.614, "flops_per_problem": 5105869406.208}, "inc.cmp8": {"acc": 0.732, "reasoning_bytes": 98.476, "flops_per_problem": 5629908418.56}, "inc.runmax6": {"acc": 0.972, "reasoning_bytes": 102.554, "flops_per_problem": 5456524197.888}, "inc.runmax7": {"acc": 0.9, "reasoning_bytes": 115.722, "flops_per_problem": 6082226601.984}, "inc.runmax8": {"acc": 0.84, "reasoning_bytes": 123.202, "flops_per_problem": 6456817778.688}, "inc.count6": {"acc": 0.702, "reasoning_bytes": 96.99, "flops_per_problem": 5254963937.28}, "inc.count7": {"acc": 0.606, "reasoning_bytes": 108.684, "flops_per_problem": 5815569973.248}, "inc.count8": {"acc": 0.58, "reasoning_bytes": 110.322, "flops_per_problem": 5932072157.184}, "inc.find6": {"acc": 0.77, "reasoning_bytes": 90.83, "flops_per_problem": 4938844667.904}, "inc.find7": {"acc": 0.586, "reasoning_bytes": 102.23, "flops_per_problem": 5486378434.56}, "inc.find8": {"acc": 0.62, "reasoning_bytes": 105.138, "flops_per_problem": 5659144372.224}, "inc.rev6": {"acc": 0.492, "reasoning_bytes": 101.946, "flops_per_problem": 5508813275.136}, "inc.rev7": {"acc": 0.072, "reasoning_bytes": 120.064, "flops_per_problem": 6393752911.872}, "inc.rev8": {"acc": 0.0, "reasoning_bytes": 130.722, "flops_per_problem": 6919646773.248}, "inc.sumd6": {"acc": 0.638, "reasoning_bytes": 108.042, "flops_per_problem": 5654463086.592}, "inc.sumd7": {"acc": 0.096, "reasoning_bytes": 119.502, "flops_per_problem": 6206236508.16}, "inc.sumd8": {"acc": 0.044, "reasoning_bytes": 129.35, "flops_per_problem": 6684080947.2}, "inc.inc6": {"acc": 0.626, "reasoning_bytes": 112.204, "flops_per_problem": 5965636091.904}, "inc.inc7": {"acc": 0.16, "reasoning_bytes": 126.818, "flops_per_problem": 6680106270.72}, "inc.inc8": {"acc": 0.004, "reasoning_bytes": 132.264, "flops_per_problem": 6970257653.76}, "count.inc.cmp16": {"acc": 0.026, "reasoning_bytes": 109.244, "flops_per_problem": 6502482395.136}, "count.inc.cmp18": {"acc": 0.01, "reasoning_bytes": 117.86, "flops_per_problem": 6971670872.064}, "count.inc.cmp20": {"acc": 0.04, "reasoning_bytes": 126.394, "flops_per_problem": 7437591281.664}, "inc.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 156.288, "flops_per_problem": 8122913832.96}, "inc.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 178.936, "flops_per_problem": 9193956655.104}, "inc.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 191.602, "flops_per_problem": 9811533053.952}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 123.36, "flops_per_problem": 7302805585.92}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 145.98, "flops_per_problem": 8478426562.56}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 163.248, "flops_per_problem": 9417686777.856}, "add.count.find6": {"acc": 0.022, "reasoning_bytes": 115.904, "flops_per_problem": 6709872181.248}, "add.count.find7": {"acc": 0.01, "reasoning_bytes": 129.752, "flops_per_problem": 7408885284.864}, "add.count.find8": {"acc": 0.002, "reasoning_bytes": 132.518, "flops_per_problem": 7624931033.088}, "runmax.inc.find12": {"acc": 0.946, "reasoning_bytes": 103.396, "flops_per_problem": 6067829440.512}, "runmax.inc.find14": {"acc": 0.964, "reasoning_bytes": 115.4, "flops_per_problem": 6686289100.8}, "runmax.inc.find16": {"acc": 0.926, "reasoning_bytes": 122.016, "flops_per_problem": 7066798129.152}, "parity.sumd.rev16": {"acc": 0.508, "reasoning_bytes": 116.696, "flops_per_problem": 6743524442.112}, "parity.sumd.rev20": {"acc": 0.48, "reasoning_bytes": 137.168, "flops_per_problem": 7824283140.096}, "parity.sumd.rev24": {"acc": 0.514, "reasoning_bytes": 154.64, "flops_per_problem": 8772552622.08}, "parity.rev.sumd16": {"acc": 0.502, "reasoning_bytes": 116.588, "flops_per_problem": 6738754830.336}, "parity.rev.sumd20": {"acc": 0.48, "reasoning_bytes": 136.952, "flops_per_problem": 7814743916.544}, "parity.rev.sumd24": {"acc": 0.522, "reasoning_bytes": 154.292, "flops_per_problem": 8757183873.024}, "count.inc.sumd16": {"acc": 0.842, "reasoning_bytes": 108.58, "flops_per_problem": 6429260021.76}, "count.inc.sumd18": {"acc": 0.734, "reasoning_bytes": 117.382, "flops_per_problem": 6906309525.504}, "count.inc.sumd20": {"acc": 0.622, "reasoning_bytes": 126.04, "flops_per_problem": 7376999546.88}, "inc.sumd.rev6": {"acc": 0.578, "reasoning_bytes": 125.806, "flops_per_problem": 6615274881.024}, "inc.sumd.rev7": {"acc": 0.104, "reasoning_bytes": 138.596, "flops_per_problem": 7224460296.192}, "inc.sumd.rev8": {"acc": 0.032, "reasoning_bytes": 145.296, "flops_per_problem": 7564780929.024}, "count.count.cmp16": {"acc": 0.994, "reasoning_bytes": 110.57, "flops_per_problem": 6737959895.04}, "count.count.cmp18": {"acc": 0.992, "reasoning_bytes": 119.954, "flops_per_problem": 7240712306.688}, "count.count.cmp20": {"acc": 0.976, "reasoning_bytes": 128.852, "flops_per_problem": 7722001465.344}, "parity.rev.find16": {"acc": 0.878, "reasoning_bytes": 118.66, "flops_per_problem": 6918586859.52}, "parity.rev.find20": {"acc": 0.88, "reasoning_bytes": 139.108, "flops_per_problem": 7998285643.776}, "parity.rev.find24": {"acc": 0.868, "reasoning_bytes": 156.916, "flops_per_problem": 8961393917.952}, "count.sumd.cmp16": {"acc": 0.972, "reasoning_bytes": 109.15, "flops_per_problem": 6542759116.8}, "count.sumd.cmp18": {"acc": 0.956, "reasoning_bytes": 118.106, "flops_per_problem": 7026609733.632}, "count.sumd.cmp20": {"acc": 0.908, "reasoning_bytes": 126.796, "flops_per_problem": 7498712973.312}, "sumd.count.count6": {"acc": 1.0, "reasoning_bytes": 83.392, "flops_per_problem": 5051902132.224}, "sumd.count.count7": {"acc": 0.998, "reasoning_bytes": 90.89, "flops_per_problem": 5428083179.52}, "sumd.count.count8": {"acc": 0.996, "reasoning_bytes": 94.15, "flops_per_problem": 5616129540.096}, "runmax.rev.inc12": {"acc": 0.99, "reasoning_bytes": 95.676, "flops_per_problem": 5625227132.928}, "runmax.rev.inc14": {"acc": 0.974, "reasoning_bytes": 105.028, "flops_per_problem": 6129481089.024}, "runmax.rev.inc16": {"acc": 0.956, "reasoning_bytes": 112.94, "flops_per_problem": 6568903655.424}, "parity.sumd.find16": {"acc": 0.872, "reasoning_bytes": 121.324, "flops_per_problem": 7080400355.328}, "parity.sumd.find20": {"acc": 0.88, "reasoning_bytes": 141.376, "flops_per_problem": 8142610563.072}, "parity.sumd.find24": {"acc": 0.874, "reasoning_bytes": 158.728, "flops_per_problem": 9085580476.416}, "runmax.runmax.cmp12": {"acc": 0.994, "reasoning_bytes": 99.872, "flops_per_problem": 6000524918.784}, "runmax.runmax.cmp14": {"acc": 0.99, "reasoning_bytes": 110.072, "flops_per_problem": 6539314397.184}, "runmax.runmax.cmp16": {"acc": 0.994, "reasoning_bytes": 121.544, "flops_per_problem": 7134279303.168}, "count.runmax.count16": {"acc": 1.0, "reasoning_bytes": 110.586, "flops_per_problem": 6782829576.192}, "count.runmax.count18": {"acc": 1.0, "reasoning_bytes": 119.906, "flops_per_problem": 7282755551.232}, "count.runmax.count20": {"acc": 1.0, "reasoning_bytes": 129.192, "flops_per_problem": 7781179981.824}, "inc.inc.sumd6": {"acc": 0.112, "reasoning_bytes": 168.348, "flops_per_problem": 8493971963.904}, "inc.inc.sumd7": {"acc": 0.054, "reasoning_bytes": 186.578, "flops_per_problem": 9343757795.328}, "inc.inc.sumd8": {"acc": 0.016, "reasoning_bytes": 187.994, "flops_per_problem": 9450367451.136}, "add.sumd.find6": {"acc": 0.728, "reasoning_bytes": 145.874, "flops_per_problem": 7900243623.936}, "add.sumd.find7": {"acc": 0.658, "reasoning_bytes": 160.098, "flops_per_problem": 8617893543.936}, "add.sumd.find8": {"acc": 0.616, "reasoning_bytes": 175.824, "flops_per_problem": 9399668244.48}, "sumd.rev.rev6": {"acc": 0.88, "reasoning_bytes": 80.548, "flops_per_problem": 4616895873.024}, "sumd.rev.rev7": {"acc": 0.624, "reasoning_bytes": 88.288, "flops_per_problem": 5005354254.336}, "sumd.rev.rev8": {"acc": 0.214, "reasoning_bytes": 93.72, "flops_per_problem": 5287732936.704}, "runmax.inc.runmax12": {"acc": 0.988, "reasoning_bytes": 106.484, "flops_per_problem": 6204205006.848}, "runmax.inc.runmax14": {"acc": 0.972, "reasoning_bytes": 116.184, "flops_per_problem": 6720912949.248}, "runmax.inc.runmax16": {"acc": 0.978, "reasoning_bytes": 127.722, "flops_per_problem": 7318792617.984}, "parity.inc.find16": {"acc": 0.872, "reasoning_bytes": 122.324, "flops_per_problem": 7080400355.328}, "parity.inc.find20": {"acc": 0.888, "reasoning_bytes": 141.116, "flops_per_problem": 8086965092.352}, "parity.inc.find24": {"acc": 0.87, "reasoning_bytes": 158.216, "flops_per_problem": 9018805911.552}, "inc.runmax.sumd6": {"acc": 0.978, "reasoning_bytes": 118.008, "flops_per_problem": 6359835672.576}, "inc.runmax.sumd7": {"acc": 0.862, "reasoning_bytes": 130.536, "flops_per_problem": 6957273710.592}, "inc.runmax.sumd8": {"acc": 0.824, "reasoning_bytes": 139.864, "flops_per_problem": 7413389918.208}, "sumd.rev.cmp6": {"acc": 0.762, "reasoning_bytes": 80.486, "flops_per_problem": 4703632146.432}, "sumd.rev.cmp7": {"acc": 0.722, "reasoning_bytes": 88.014, "flops_per_problem": 5082021347.328}, "sumd.rev.cmp8": {"acc": 0.594, "reasoning_bytes": 91.648, "flops_per_problem": 5290912677.888}, "runmax.runmax.count12": {"acc": 1.0, "reasoning_bytes": 99.84, "flops_per_problem": 6087437844.48}, "runmax.runmax.count14": {"acc": 1.0, "reasoning_bytes": 111.02, "flops_per_problem": 6669507133.44}, "runmax.runmax.count16": {"acc": 1.0, "reasoning_bytes": 122.376, "flops_per_problem": 7259349123.072}, "count.count.count16": {"acc": 1.0, "reasoning_bytes": 110.004, "flops_per_problem": 6801289740.288}, "count.count.count18": {"acc": 1.0, "reasoning_bytes": 119.402, "flops_per_problem": 7304660434.944}, "count.count.count20": {"acc": 1.0, "reasoning_bytes": 128.706, "flops_per_problem": 7803879800.832}, "add.sumd.rev6": {"acc": 0.192, "reasoning_bytes": 138.808, "flops_per_problem": 7498624647.168}, "add.sumd.rev7": {"acc": 0.04, "reasoning_bytes": 154.972, "flops_per_problem": 8301067665.408}, "add.sumd.rev8": {"acc": 0.042, "reasoning_bytes": 171.176, "flops_per_problem": 9105807163.392}, "add.rev.rev6": {"acc": 0.01, "reasoning_bytes": 179.482, "flops_per_problem": 9429787459.584}, "add.rev.rev7": {"acc": 0.0, "reasoning_bytes": 204.74, "flops_per_problem": 10650896400.384}, "add.rev.rev8": {"acc": 0.0, "reasoning_bytes": 226.68, "flops_per_problem": 11736866340.864}, "inc.runmax.cmp6": {"acc": 0.644, "reasoning_bytes": 79.562, "flops_per_problem": 4706105278.464}, "inc.runmax.cmp7": {"acc": 0.594, "reasoning_bytes": 86.672, "flops_per_problem": 5064356118.528}, "inc.runmax.cmp8": {"acc": 0.664, "reasoning_bytes": 92.344, "flops_per_problem": 5359100461.056}, "count.rev.cmp16": {"acc": 0.978, "reasoning_bytes": 106.43, "flops_per_problem": 6378472488.96}, "count.rev.cmp18": {"acc": 0.958, "reasoning_bytes": 115.604, "flops_per_problem": 6872038981.632}, "count.rev.cmp20": {"acc": 0.918, "reasoning_bytes": 124.324, "flops_per_problem": 7345555439.616}} +{"step": 3000, "train_loss": 1.2323530912399292} +{"step": 3020, "train_loss": 1.29121994972229} +{"step": 3040, "train_loss": 1.1986018419265747} +{"step": 3060, "train_loss": 1.3078384399414062} +{"step": 3080, "train_loss": 1.253762125968933} +{"step": 3100, "train_loss": 1.2456445693969727} +{"step": 3120, "train_loss": 1.1817682981491089} +{"step": 3140, "train_loss": 1.2226450443267822} +{"step": 3160, "train_loss": 1.278710961341858} +{"step": 3180, "train_loss": 1.191028356552124} +{"step": 3200, "train_loss": 1.146209955215454} +{"step": 3220, "train_loss": 1.2393648624420166} +{"step": 3240, "train_loss": 1.2349612712860107} +{"step": 3260, "train_loss": 1.25003981590271} +{"step": 3280, "train_loss": 1.256955623626709} +{"step": 3300, "train_loss": 1.2974863052368164} +{"step": 3320, "train_loss": 1.175562858581543} +{"step": 3340, "train_loss": 1.159119725227356} +{"step": 3360, "train_loss": 1.1650028228759766} +{"step": 3380, "train_loss": 1.2881767749786377} +{"step": 3400, "train_loss": 1.1922781467437744} +{"step": 3420, "train_loss": 1.208404302597046} +{"step": 3440, "train_loss": 1.1628620624542236} +{"step": 3460, "train_loss": 1.1987029314041138} +{"step": 3480, "train_loss": 1.198535680770874} +{"step": 3500, "train_loss": 1.2179851531982422} +{"step": 3520, "train_loss": 1.1708338260650635} +{"step": 3540, "train_loss": 1.270632266998291} +{"step": 3560, "train_loss": 1.3314766883850098} +{"step": 3580, "train_loss": 1.2674834728240967} +{"step": 3600, "train_loss": 1.1655383110046387} +{"step": 3620, "train_loss": 1.1182334423065186} +{"step": 3640, "train_loss": 1.2430644035339355} +{"step": 3660, "train_loss": 1.172795057296753} +{"step": 3680, "train_loss": 1.1615214347839355} +{"step": 3700, "train_loss": 1.1792652606964111} +{"step": 3720, "train_loss": 1.2603237628936768} +{"step": 3740, "train_loss": 1.2499940395355225} +{"step": 3760, "train_loss": 1.257246732711792} +{"step": 3780, "train_loss": 1.1748329401016235} +{"step": 3800, "train_loss": 1.229633092880249} +{"step": 3820, "train_loss": 1.1785176992416382} +{"step": 3840, "train_loss": 1.2166818380355835} +{"step": 3860, "train_loss": 1.2451071739196777} +{"step": 3880, "train_loss": 1.198850154876709} +{"step": 3900, "train_loss": 1.2092037200927734} +{"step": 3920, "train_loss": 1.2165414094924927} +{"step": 3940, "train_loss": 1.1474672555923462} +{"step": 3960, "train_loss": 1.036288857460022} +{"step": 3980, "train_loss": 1.1538127660751343} +{"step": 4000, "tokens": 131072000, "val_loss": 2.1026387572288514, "val_bpb": 0.7579671119745622, "lr": 0.0004789669757536829, "elapsed": 678.4883332252502, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.08, "reasoning_bytes": 79.218, "flops_per_problem": 4943790931.968}, "add9": {"acc": 0.002, "reasoning_bytes": 89.282, "flops_per_problem": 5545556951.04}, "add10": {"acc": 0.0, "reasoning_bytes": 98.136, "flops_per_problem": 6083993124.864}, "reach14": {"acc": 0.514, "reasoning_bytes": 8.92, "flops_per_problem": 4677752586.24}, "reach16": {"acc": 0.494, "reasoning_bytes": 10.152, "flops_per_problem": 5261853376.512}, "reach18": {"acc": 0.524, "reasoning_bytes": 10.54, "flops_per_problem": 5809210490.88}, "parity24": {"acc": 0.414, "reasoning_bytes": 148.26, "flops_per_problem": 8108163366.912}, "parity28": {"acc": 0.304, "reasoning_bytes": 172.156, "flops_per_problem": 9377233403.904}, "parity32": {"acc": 0.266, "reasoning_bytes": 196.02, "flops_per_problem": 10617862422.528}, "cmp8": {"acc": 0.974, "reasoning_bytes": 5.816, "flops_per_problem": 1360929226.752}, "cmp9": {"acc": 0.984, "reasoning_bytes": 5.672, "flops_per_problem": 1442895888.384}, "cmp10": {"acc": 0.978, "reasoning_bytes": 5.784, "flops_per_problem": 1536256622.592}, "runmax12": {"acc": 0.992, "reasoning_bytes": 69.824, "flops_per_problem": 4099392995.328}, "runmax14": {"acc": 0.99, "reasoning_bytes": 77.572, "flops_per_problem": 4529894621.184}, "runmax16": {"acc": 0.98, "reasoning_bytes": 88.424, "flops_per_problem": 5097478422.528}, "count16": {"acc": 0.806, "reasoning_bytes": 75.25, "flops_per_problem": 4559837184.0}, "count18": {"acc": 0.698, "reasoning_bytes": 84.046, "flops_per_problem": 5036621709.312}, "count20": {"acc": 0.582, "reasoning_bytes": 92.9, "flops_per_problem": 5515967692.8}, "brackets16": {"acc": 0.608, "reasoning_bytes": 42.654, "flops_per_problem": 3164460761.088}, "brackets18": {"acc": 0.564, "reasoning_bytes": 35.184, "flops_per_problem": 2922888757.248}, "brackets20": {"acc": 0.486, "reasoning_bytes": 31.92, "flops_per_problem": 2867066634.24}, "sumd8": {"acc": 0.766, "reasoning_bytes": 58.664, "flops_per_problem": 3385187794.944}, "sumd9": {"acc": 0.424, "reasoning_bytes": 66.81, "flops_per_problem": 3789368229.888}, "sumd10": {"acc": 0.132, "reasoning_bytes": 74.422, "flops_per_problem": 4169788932.096}, "inc8": {"acc": 0.446, "reasoning_bytes": 63.0, "flops_per_problem": 3803677065.216}, "inc9": {"acc": 0.02, "reasoning_bytes": 70.878, "flops_per_problem": 4248664178.688}, "inc10": {"acc": 0.002, "reasoning_bytes": 76.026, "flops_per_problem": 4555862507.52}, "add.cmp6": {"acc": 0.964, "reasoning_bytes": 92.604, "flops_per_problem": 5531248115.712}, "add.cmp7": {"acc": 0.904, "reasoning_bytes": 105.768, "flops_per_problem": 6245541642.24}, "add.cmp8": {"acc": 0.788, "reasoning_bytes": 119.186, "flops_per_problem": 6987657904.128}, "add.runmax6": {"acc": 0.96, "reasoning_bytes": 120.9, "flops_per_problem": 6575793094.656}, "add.runmax7": {"acc": 0.782, "reasoning_bytes": 139.476, "flops_per_problem": 7483697528.832}, "add.runmax8": {"acc": 0.61, "reasoning_bytes": 158.62, "flops_per_problem": 8418099806.208}, "add.count6": {"acc": 0.694, "reasoning_bytes": 115.974, "flops_per_problem": 6402497200.128}, "add.count7": {"acc": 0.47, "reasoning_bytes": 133.664, "flops_per_problem": 7271979761.664}, "add.count8": {"acc": 0.378, "reasoning_bytes": 149.762, "flops_per_problem": 8071684669.44}, "add.find6": {"acc": 0.712, "reasoning_bytes": 108.466, "flops_per_problem": 6026404478.976}, "add.find7": {"acc": 0.48, "reasoning_bytes": 125.742, "flops_per_problem": 6876720267.264}, "add.find8": {"acc": 0.296, "reasoning_bytes": 144.616, "flops_per_problem": 7816068808.704}, "add.rev6": {"acc": 0.524, "reasoning_bytes": 122.716, "flops_per_problem": 6766224261.12}, "add.rev7": {"acc": 0.062, "reasoning_bytes": 141.164, "flops_per_problem": 7694355382.272}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 160.108, "flops_per_problem": 8640328384.512}, "add.sumd6": {"acc": 0.684, "reasoning_bytes": 127.21, "flops_per_problem": 6809769050.112}, "add.sumd7": {"acc": 0.178, "reasoning_bytes": 147.392, "flops_per_problem": 7790454226.944}, "add.sumd8": {"acc": 0.052, "reasoning_bytes": 166.36, "flops_per_problem": 8716377194.496}, "add.inc6": {"acc": 0.058, "reasoning_bytes": 127.368, "flops_per_problem": 6974055677.952}, "add.inc7": {"acc": 0.0, "reasoning_bytes": 144.69, "flops_per_problem": 7867209646.08}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 161.154, "flops_per_problem": 8710459342.848}, "runmax.cmp12": {"acc": 0.998, "reasoning_bytes": 86.88, "flops_per_problem": 5117616783.36}, "runmax.cmp14": {"acc": 0.998, "reasoning_bytes": 93.696, "flops_per_problem": 5506958426.112}, "runmax.cmp16": {"acc": 0.99, "reasoning_bytes": 104.508, "flops_per_problem": 6072775704.576}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 87.976, "flops_per_problem": 5210182582.272}, "runmax.runmax14": {"acc": 0.994, "reasoning_bytes": 96.964, "flops_per_problem": 5695446417.408}, "runmax.runmax16": {"acc": 0.98, "reasoning_bytes": 106.188, "flops_per_problem": 6191132737.536}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 87.964, "flops_per_problem": 5253815697.408}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 97.036, "flops_per_problem": 5742789230.592}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 106.076, "flops_per_problem": 6230349545.472}, "runmax.find12": {"acc": 0.998, "reasoning_bytes": 87.736, "flops_per_problem": 5199583444.992}, "runmax.find14": {"acc": 0.998, "reasoning_bytes": 95.164, "flops_per_problem": 5615952887.808}, "runmax.find16": {"acc": 0.994, "reasoning_bytes": 105.676, "flops_per_problem": 6168521244.672}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 82.904, "flops_per_problem": 4853698265.088}, "runmax.rev14": {"acc": 0.996, "reasoning_bytes": 90.392, "flops_per_problem": 5272717492.224}, "runmax.rev16": {"acc": 0.982, "reasoning_bytes": 100.84, "flops_per_problem": 5822459412.48}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 85.868, "flops_per_problem": 5028760682.496}, "runmax.sumd14": {"acc": 0.996, "reasoning_bytes": 93.86, "flops_per_problem": 5470038097.92}, "runmax.sumd16": {"acc": 0.98, "reasoning_bytes": 104.004, "flops_per_problem": 6006354444.288}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 86.712, "flops_per_problem": 5053050372.096}, "runmax.inc14": {"acc": 0.994, "reasoning_bytes": 94.204, "flops_per_problem": 5475425992.704}, "runmax.inc16": {"acc": 0.98, "reasoning_bytes": 104.792, "flops_per_problem": 6033735548.928}, "count.cmp16": {"acc": 0.958, "reasoning_bytes": 90.76, "flops_per_problem": 5509784862.72}, "count.cmp18": {"acc": 0.93, "reasoning_bytes": 99.79, "flops_per_problem": 5996991873.024}, "count.cmp20": {"acc": 0.884, "reasoning_bytes": 107.646, "flops_per_problem": 6432351436.8}, "count.runmax16": {"acc": 0.814, "reasoning_bytes": 92.41, "flops_per_problem": 5626817003.52}, "count.runmax18": {"acc": 0.748, "reasoning_bytes": 101.508, "flops_per_problem": 6116938776.576}, "count.runmax20": {"acc": 0.664, "reasoning_bytes": 110.414, "flops_per_problem": 6598581239.808}, "count.count16": {"acc": 1.0, "reasoning_bytes": 92.38, "flops_per_problem": 5669655183.36}, "count.count18": {"acc": 1.0, "reasoning_bytes": 101.36, "flops_per_problem": 6154565713.92}, "count.count20": {"acc": 0.998, "reasoning_bytes": 109.936, "flops_per_problem": 6621634363.392}, "count.find16": {"acc": 0.936, "reasoning_bytes": 91.87, "flops_per_problem": 5602968944.64}, "count.find18": {"acc": 0.91, "reasoning_bytes": 100.99, "flops_per_problem": 6094062305.28}, "count.find20": {"acc": 0.852, "reasoning_bytes": 109.03, "flops_per_problem": 6537459548.16}, "count.rev16": {"acc": 0.822, "reasoning_bytes": 87.526, "flops_per_problem": 5278635343.872}, "count.rev18": {"acc": 0.738, "reasoning_bytes": 96.238, "flops_per_problem": 5751710171.136}, "count.rev20": {"acc": 0.582, "reasoning_bytes": 104.934, "flops_per_problem": 6224078389.248}, "count.sumd16": {"acc": 0.792, "reasoning_bytes": 90.312, "flops_per_problem": 5445836734.464}, "count.sumd18": {"acc": 0.706, "reasoning_bytes": 99.034, "flops_per_problem": 5919353192.448}, "count.sumd20": {"acc": 0.544, "reasoning_bytes": 107.684, "flops_per_problem": 6389689909.248}, "count.inc16": {"acc": 0.81, "reasoning_bytes": 91.226, "flops_per_problem": 5442038710.272}, "count.inc18": {"acc": 0.738, "reasoning_bytes": 100.138, "flops_per_problem": 5923946151.936}, "count.inc20": {"acc": 0.576, "reasoning_bytes": 108.558, "flops_per_problem": 6384831971.328}, "parity.cmp16": {"acc": 0.974, "reasoning_bytes": 111.132, "flops_per_problem": 6365311893.504}, "parity.cmp20": {"acc": 0.94, "reasoning_bytes": 134.928, "flops_per_problem": 7592868642.816}, "parity.cmp24": {"acc": 0.938, "reasoning_bytes": 157.182, "flops_per_problem": 8752237608.96}, "parity.runmax16": {"acc": 0.838, "reasoning_bytes": 114.22, "flops_per_problem": 6545850531.84}, "parity.runmax20": {"acc": 0.462, "reasoning_bytes": 136.396, "flops_per_problem": 7701863104.512}, "parity.runmax24": {"acc": 0.506, "reasoning_bytes": 160.912, "flops_per_problem": 8961217265.664}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 116.152, "flops_per_problem": 6675336658.944}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 138.112, "flops_per_problem": 7821810008.064}, "parity.count24": {"acc": 0.992, "reasoning_bytes": 160.928, "flops_per_problem": 9005733642.24}, "parity.find16": {"acc": 0.944, "reasoning_bytes": 112.852, "flops_per_problem": 6485435449.344}, "parity.find20": {"acc": 0.854, "reasoning_bytes": 136.156, "flops_per_problem": 7691263967.232}, "parity.find24": {"acc": 0.862, "reasoning_bytes": 160.18, "flops_per_problem": 8928889896.96}, "parity.rev16": {"acc": 0.778, "reasoning_bytes": 108.404, "flops_per_problem": 6156508889.088}, "parity.rev20": {"acc": 0.468, "reasoning_bytes": 131.132, "flops_per_problem": 7336899477.504}, "parity.rev24": {"acc": 0.516, "reasoning_bytes": 155.228, "flops_per_problem": 8577705148.416}, "parity.sumd16": {"acc": 0.826, "reasoning_bytes": 111.428, "flops_per_problem": 6334221090.816}, "parity.sumd20": {"acc": 0.452, "reasoning_bytes": 134.372, "flops_per_problem": 7524150902.784}, "parity.sumd24": {"acc": 0.428, "reasoning_bytes": 159.56, "flops_per_problem": 8813182648.32}, "parity.inc16": {"acc": 0.794, "reasoning_bytes": 113.916, "flops_per_problem": 6399935741.952}, "parity.inc20": {"acc": 0.446, "reasoning_bytes": 135.984, "flops_per_problem": 7551178702.848}, "parity.inc24": {"acc": 0.484, "reasoning_bytes": 161.24, "flops_per_problem": 8843743494.144}, "sumd.cmp6": {"acc": 0.954, "reasoning_bytes": 62.068, "flops_per_problem": 3712524484.608}, "sumd.cmp7": {"acc": 0.944, "reasoning_bytes": 70.224, "flops_per_problem": 4117058224.128}, "sumd.cmp8": {"acc": 0.93, "reasoning_bytes": 77.494, "flops_per_problem": 4482198503.424}, "sumd.runmax6": {"acc": 0.97, "reasoning_bytes": 67.544, "flops_per_problem": 3954538119.168}, "sumd.runmax7": {"acc": 0.916, "reasoning_bytes": 75.446, "flops_per_problem": 4347677786.112}, "sumd.runmax8": {"acc": 0.784, "reasoning_bytes": 83.502, "flops_per_problem": 4747618566.144}, "sumd.count6": {"acc": 0.996, "reasoning_bytes": 66.438, "flops_per_problem": 3949856833.536}, "sumd.count7": {"acc": 0.978, "reasoning_bytes": 74.454, "flops_per_problem": 4348031090.688}, "sumd.count8": {"acc": 0.898, "reasoning_bytes": 82.524, "flops_per_problem": 4749385089.024}, "sumd.find6": {"acc": 1.0, "reasoning_bytes": 66.254, "flops_per_problem": 3897567756.288}, "sumd.find7": {"acc": 0.984, "reasoning_bytes": 74.39, "flops_per_problem": 4301041582.08}, "sumd.find8": {"acc": 0.924, "reasoning_bytes": 82.3, "flops_per_problem": 4694622879.744}, "sumd.rev6": {"acc": 0.988, "reasoning_bytes": 61.57, "flops_per_problem": 3602381783.04}, "sumd.rev7": {"acc": 0.936, "reasoning_bytes": 69.448, "flops_per_problem": 3994284883.968}, "sumd.rev8": {"acc": 0.788, "reasoning_bytes": 77.556, "flops_per_problem": 4396610469.888}, "sumd.sumd6": {"acc": 0.984, "reasoning_bytes": 65.8, "flops_per_problem": 3798200844.288}, "sumd.sumd7": {"acc": 0.914, "reasoning_bytes": 73.716, "flops_per_problem": 4193636990.976}, "sumd.sumd8": {"acc": 0.73, "reasoning_bytes": 81.682, "flops_per_problem": 4590044725.248}, "sumd.inc6": {"acc": 0.854, "reasoning_bytes": 68.59, "flops_per_problem": 3916027920.384}, "sumd.inc7": {"acc": 0.624, "reasoning_bytes": 76.49, "flops_per_problem": 4311640719.36}, "sumd.inc8": {"acc": 0.358, "reasoning_bytes": 84.378, "flops_per_problem": 4706988539.904}, "inc.cmp6": {"acc": 0.932, "reasoning_bytes": 79.398, "flops_per_problem": 4611331325.952}, "inc.cmp7": {"acc": 0.78, "reasoning_bytes": 90.662, "flops_per_problem": 5196315377.664}, "inc.cmp8": {"acc": 0.848, "reasoning_bytes": 93.964, "flops_per_problem": 5430467985.408}, "inc.runmax6": {"acc": 0.936, "reasoning_bytes": 104.372, "flops_per_problem": 5534957813.76}, "inc.runmax7": {"acc": 0.888, "reasoning_bytes": 120.314, "flops_per_problem": 6283610210.304}, "inc.runmax8": {"acc": 0.868, "reasoning_bytes": 127.81, "flops_per_problem": 6665179152.384}, "inc.count6": {"acc": 0.73, "reasoning_bytes": 99.242, "flops_per_problem": 5354419175.424}, "inc.count7": {"acc": 0.554, "reasoning_bytes": 113.924, "flops_per_problem": 6046984470.528}, "inc.count8": {"acc": 0.562, "reasoning_bytes": 117.352, "flops_per_problem": 6242538553.344}, "inc.find6": {"acc": 0.78, "reasoning_bytes": 92.52, "flops_per_problem": 5012773650.432}, "inc.find7": {"acc": 0.612, "reasoning_bytes": 105.118, "flops_per_problem": 5613833060.352}, "inc.find8": {"acc": 0.578, "reasoning_bytes": 112.618, "flops_per_problem": 5989219172.352}, "inc.rev6": {"acc": 0.818, "reasoning_bytes": 103.92, "flops_per_problem": 5603057270.784}, "inc.rev7": {"acc": 0.144, "reasoning_bytes": 121.74, "flops_per_problem": 6465650393.088}, "inc.rev8": {"acc": 0.0, "reasoning_bytes": 127.87, "flops_per_problem": 6782741250.048}, "inc.sumd6": {"acc": 0.718, "reasoning_bytes": 110.508, "flops_per_problem": 5773085097.984}, "inc.sumd7": {"acc": 0.404, "reasoning_bytes": 127.968, "flops_per_problem": 6594076606.464}, "inc.sumd8": {"acc": 0.08, "reasoning_bytes": 135.9, "flops_per_problem": 6975203917.824}, "inc.inc6": {"acc": 0.612, "reasoning_bytes": 113.08, "flops_per_problem": 6018101821.44}, "inc.inc7": {"acc": 0.076, "reasoning_bytes": 128.924, "flops_per_problem": 6806942613.504}, "inc.inc8": {"acc": 0.002, "reasoning_bytes": 132.606, "flops_per_problem": 7028906213.376}, "count.inc.cmp16": {"acc": 0.026, "reasoning_bytes": 94.44, "flops_per_problem": 5946734297.088}, "count.inc.cmp18": {"acc": 0.032, "reasoning_bytes": 106.788, "flops_per_problem": 6549471903.744}, "count.inc.cmp20": {"acc": 0.07, "reasoning_bytes": 118.262, "flops_per_problem": 7112109441.024}, "inc.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 158.876, "flops_per_problem": 8239239364.608}, "inc.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 182.51, "flops_per_problem": 9348527407.104}, "inc.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 190.358, "flops_per_problem": 9749528100.864}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 132.468, "flops_per_problem": 7705042845.696}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 155.712, "flops_per_problem": 8908221579.264}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 177.228, "flops_per_problem": 10035086524.416}, "add.count.find6": {"acc": 0.0, "reasoning_bytes": 135.514, "flops_per_problem": 7593751904.256}, "add.count.find7": {"acc": 0.0, "reasoning_bytes": 152.272, "flops_per_problem": 8445304258.56}, "add.count.find8": {"acc": 0.002, "reasoning_bytes": 144.872, "flops_per_problem": 8200552513.536}, "runmax.inc.find12": {"acc": 0.876, "reasoning_bytes": 106.624, "flops_per_problem": 6210387836.928}, "runmax.inc.find14": {"acc": 0.88, "reasoning_bytes": 113.492, "flops_per_problem": 6602025959.424}, "runmax.inc.find16": {"acc": 0.8, "reasoning_bytes": 123.636, "flops_per_problem": 7138342305.792}, "parity.sumd.rev16": {"acc": 0.878, "reasoning_bytes": 123.044, "flops_per_problem": 7023871623.168}, "parity.sumd.rev20": {"acc": 0.444, "reasoning_bytes": 146.06, "flops_per_problem": 8216981176.32}, "parity.sumd.rev24": {"acc": 0.494, "reasoning_bytes": 169.912, "flops_per_problem": 9447011057.664}, "parity.rev.sumd16": {"acc": 0.886, "reasoning_bytes": 122.816, "flops_per_problem": 7013802442.752}, "parity.rev.sumd20": {"acc": 0.44, "reasoning_bytes": 146.036, "flops_per_problem": 8215921262.592}, "parity.rev.sumd24": {"acc": 0.51, "reasoning_bytes": 169.488, "flops_per_problem": 9428285915.136}, "count.inc.sumd16": {"acc": 0.79, "reasoning_bytes": 106.36, "flops_per_problem": 6331218001.92}, "count.inc.sumd18": {"acc": 0.678, "reasoning_bytes": 115.15, "flops_per_problem": 6807737548.8}, "count.inc.sumd20": {"acc": 0.532, "reasoning_bytes": 123.404, "flops_per_problem": 7260585689.088}, "inc.sumd.rev6": {"acc": 0.792, "reasoning_bytes": 129.24, "flops_per_problem": 6766665891.84}, "inc.sumd.rev7": {"acc": 0.324, "reasoning_bytes": 146.54, "flops_per_problem": 7579531395.072}, "inc.sumd.rev8": {"acc": 0.072, "reasoning_bytes": 154.15, "flops_per_problem": 7965604970.496}, "count.count.cmp16": {"acc": 0.998, "reasoning_bytes": 108.05, "flops_per_problem": 6626668953.6}, "count.count.cmp18": {"acc": 1.0, "reasoning_bytes": 117.17, "flops_per_problem": 7117762314.24}, "count.count.cmp20": {"acc": 0.998, "reasoning_bytes": 125.886, "flops_per_problem": 7591013793.792}, "parity.rev.find16": {"acc": 0.962, "reasoning_bytes": 125.044, "flops_per_problem": 7200523911.168}, "parity.rev.find20": {"acc": 0.852, "reasoning_bytes": 148.0, "flops_per_problem": 8390983680.0}, "parity.rev.find24": {"acc": 0.884, "reasoning_bytes": 171.604, "flops_per_problem": 9610061119.488}, "count.sumd.cmp16": {"acc": 0.956, "reasoning_bytes": 106.02, "flops_per_problem": 6404528701.44}, "count.sumd.cmp18": {"acc": 0.914, "reasoning_bytes": 115.0, "flops_per_problem": 6889439232.0}, "count.sumd.cmp20": {"acc": 0.85, "reasoning_bytes": 123.196, "flops_per_problem": 7339725914.112}, "sumd.count.count6": {"acc": 1.0, "reasoning_bytes": 83.446, "flops_per_problem": 5054286938.112}, "sumd.count.count7": {"acc": 1.0, "reasoning_bytes": 91.532, "flops_per_problem": 5455552610.304}, "sumd.count.count8": {"acc": 0.998, "reasoning_bytes": 99.046, "flops_per_problem": 5832616919.04}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 98.856, "flops_per_problem": 5766019006.464}, "runmax.rev.inc14": {"acc": 0.998, "reasoning_bytes": 107.26, "flops_per_problem": 6228936327.168}, "runmax.rev.inc16": {"acc": 0.98, "reasoning_bytes": 117.012, "flops_per_problem": 6749883924.48}, "parity.sumd.find16": {"acc": 0.96, "reasoning_bytes": 128.344, "flops_per_problem": 7390425120.768}, "parity.sumd.find20": {"acc": 0.848, "reasoning_bytes": 151.12, "flops_per_problem": 8572935536.64}, "parity.sumd.find24": {"acc": 0.878, "reasoning_bytes": 174.922, "flops_per_problem": 9800757264.384}, "runmax.runmax.cmp12": {"acc": 0.962, "reasoning_bytes": 104.056, "flops_per_problem": 6185303212.032}, "runmax.runmax.cmp14": {"acc": 0.94, "reasoning_bytes": 113.16, "flops_per_problem": 6675689963.52}, "runmax.runmax.cmp16": {"acc": 0.924, "reasoning_bytes": 122.32, "flops_per_problem": 7168549847.04}, "count.runmax.count16": {"acc": 1.0, "reasoning_bytes": 109.05, "flops_per_problem": 6714995097.6}, "count.runmax.count18": {"acc": 1.0, "reasoning_bytes": 118.286, "flops_per_problem": 7211211374.592}, "count.runmax.count20": {"acc": 1.0, "reasoning_bytes": 127.402, "flops_per_problem": 7702128082.944}, "inc.inc.sumd6": {"acc": 0.222, "reasoning_bytes": 178.52, "flops_per_problem": 8938782425.088}, "inc.inc.sumd7": {"acc": 0.084, "reasoning_bytes": 204.138, "flops_per_problem": 10119261339.648}, "inc.inc.sumd8": {"acc": 0.044, "reasoning_bytes": 208.162, "flops_per_problem": 10347849400.32}, "add.sumd.find6": {"acc": 0.834, "reasoning_bytes": 151.328, "flops_per_problem": 8139960778.752}, "add.sumd.find7": {"acc": 0.658, "reasoning_bytes": 171.232, "flops_per_problem": 9108015316.992}, "add.sumd.find8": {"acc": 0.624, "reasoning_bytes": 189.116, "flops_per_problem": 9987743711.232}, "sumd.rev.rev6": {"acc": 0.986, "reasoning_bytes": 80.548, "flops_per_problem": 4617072525.312}, "sumd.rev.rev7": {"acc": 0.918, "reasoning_bytes": 88.368, "flops_per_problem": 5006414168.064}, "sumd.rev.rev8": {"acc": 0.702, "reasoning_bytes": 96.022, "flops_per_problem": 5388778045.44}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.624, "flops_per_problem": 6342877052.928}, "runmax.inc.runmax14": {"acc": 0.992, "reasoning_bytes": 120.388, "flops_per_problem": 6906574503.936}, "runmax.inc.runmax16": {"acc": 0.98, "reasoning_bytes": 129.14, "flops_per_problem": 7381415854.08}, "parity.inc.find16": {"acc": 0.964, "reasoning_bytes": 129.692, "flops_per_problem": 7405793869.824}, "parity.inc.find20": {"acc": 0.876, "reasoning_bytes": 152.036, "flops_per_problem": 8569225838.592}, "parity.inc.find24": {"acc": 0.878, "reasoning_bytes": 175.482, "flops_per_problem": 9781325512.704}, "inc.runmax.sumd6": {"acc": 0.89, "reasoning_bytes": 119.838, "flops_per_problem": 6436591091.712}, "inc.runmax.sumd7": {"acc": 0.882, "reasoning_bytes": 135.362, "flops_per_problem": 7169256456.192}, "inc.runmax.sumd8": {"acc": 0.872, "reasoning_bytes": 146.072, "flops_per_problem": 7687554269.184}, "sumd.rev.cmp6": {"acc": 0.004, "reasoning_bytes": 80.452, "flops_per_problem": 4745057107.968}, "sumd.rev.cmp7": {"acc": 0.0, "reasoning_bytes": 88.438, "flops_per_problem": 5142348103.68}, "sumd.rev.cmp8": {"acc": 0.002, "reasoning_bytes": 95.456, "flops_per_problem": 5496977571.84}, "runmax.runmax.count12": {"acc": 1.0, "reasoning_bytes": 104.988, "flops_per_problem": 6314789339.136}, "runmax.runmax.count14": {"acc": 1.0, "reasoning_bytes": 115.476, "flops_per_problem": 6866297782.272}, "runmax.runmax.count16": {"acc": 1.0, "reasoning_bytes": 123.852, "flops_per_problem": 7324533817.344}, "count.count.count16": {"acc": 1.0, "reasoning_bytes": 109.14, "flops_per_problem": 6763132846.08}, "count.count.count18": {"acc": 1.0, "reasoning_bytes": 118.37, "flops_per_problem": 7259084144.64}, "count.count.count20": {"acc": 1.0, "reasoning_bytes": 127.334, "flops_per_problem": 7743288066.048}, "add.sumd.rev6": {"acc": 0.55, "reasoning_bytes": 147.148, "flops_per_problem": 7889114529.792}, "add.sumd.rev7": {"acc": 0.048, "reasoning_bytes": 168.52, "flops_per_problem": 8941343883.264}, "add.sumd.rev8": {"acc": 0.012, "reasoning_bytes": 189.506, "flops_per_problem": 9971933331.456}, "add.rev.rev6": {"acc": 0.036, "reasoning_bytes": 181.916, "flops_per_problem": 9544081489.92}, "add.rev.rev7": {"acc": 0.0, "reasoning_bytes": 204.064, "flops_per_problem": 10628814864.384}, "add.rev.rev8": {"acc": 0.0, "reasoning_bytes": 230.544, "flops_per_problem": 11918288240.64}, "inc.runmax.cmp6": {"acc": 0.628, "reasoning_bytes": 83.94, "flops_per_problem": 4902719275.008}, "inc.runmax.cmp7": {"acc": 0.58, "reasoning_bytes": 93.59, "flops_per_problem": 5369964576.768}, "inc.runmax.cmp8": {"acc": 0.826, "reasoning_bytes": 92.546, "flops_per_problem": 5366961487.872}, "count.rev.cmp16": {"acc": 0.968, "reasoning_bytes": 103.64, "flops_per_problem": 6255257518.08}, "count.rev.cmp18": {"acc": 0.94, "reasoning_bytes": 112.32, "flops_per_problem": 6727007453.184}, "count.rev.cmp20": {"acc": 0.874, "reasoning_bytes": 120.746, "flops_per_problem": 7187539968.0}} +{"step": 4000, "train_loss": 1.1752794981002808} +{"step": 4020, "train_loss": 1.1982898712158203} +{"step": 4040, "train_loss": 1.2356390953063965} +{"step": 4060, "train_loss": 1.1657443046569824} +{"step": 4080, "train_loss": 1.144209861755371} +{"step": 4100, "train_loss": 1.156805157661438} +{"step": 4120, "train_loss": 1.1713519096374512} +{"step": 4140, "train_loss": 1.1432324647903442} +{"step": 4160, "train_loss": 1.163553237915039} +{"step": 4180, "train_loss": 1.1742980480194092} +{"step": 4200, "train_loss": 1.1555166244506836} +{"step": 4220, "train_loss": 1.1760451793670654} +{"step": 4240, "train_loss": 1.1396708488464355} +{"step": 4260, "train_loss": 1.2358717918395996} +{"step": 4280, "train_loss": 1.1195262670516968} +{"step": 4300, "train_loss": 1.1883363723754883} +{"step": 4320, "train_loss": 1.145790934562683} +{"step": 4340, "train_loss": 1.1135096549987793} +{"step": 4360, "train_loss": 1.0702797174453735} +{"step": 4380, "train_loss": 1.1253153085708618} +{"step": 4400, "train_loss": 1.1625243425369263} +{"step": 4420, "train_loss": 1.144294023513794} +{"step": 4440, "train_loss": 1.1617358922958374} +{"step": 4460, "train_loss": 1.1337494850158691} +{"step": 4480, "train_loss": 1.2522834539413452} +{"step": 4500, "train_loss": 1.2220451831817627} +{"step": 4520, "train_loss": 1.113988995552063} +{"step": 4540, "train_loss": 1.115396499633789} +{"step": 4560, "train_loss": 1.2406384944915771} +{"step": 4580, "train_loss": 1.1491285562515259} +{"step": 4600, "train_loss": 1.2403538227081299} +{"step": 4620, "train_loss": 1.1144871711730957} +{"step": 4640, "train_loss": 1.1094343662261963} +{"step": 4660, "train_loss": 1.2199907302856445} +{"step": 4680, "train_loss": 1.1719413995742798} +{"step": 4700, "train_loss": 1.2035624980926514} +{"step": 4720, "train_loss": 1.1257727146148682} +{"step": 4740, "train_loss": 1.098212718963623} +{"step": 4760, "train_loss": 1.1854896545410156} +{"step": 4780, "train_loss": 1.1666841506958008} +{"step": 4800, "train_loss": 1.1591508388519287} +{"step": 4820, "train_loss": 1.133932113647461} +{"step": 4840, "train_loss": 1.1171729564666748} +{"step": 4860, "train_loss": 1.1655306816101074} +{"step": 4880, "train_loss": 1.0795272588729858} +{"step": 4900, "train_loss": 1.0294101238250732} +{"step": 4920, "train_loss": 1.0845496654510498} +{"step": 4940, "train_loss": 1.124068260192871} +{"step": 4960, "train_loss": 1.1831035614013672} +{"step": 4980, "train_loss": 1.0967165231704712} +{"step": 5000, "tokens": 163840000, "val_loss": 2.007053869962692, "val_bpb": 0.7235103130116107, "lr": 0.00041540119322753773, "elapsed": 846.4490120410919, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.318, "reasoning_bytes": 79.0, "flops_per_problem": 4915084935.168}, "add9": {"acc": 0.0, "reasoning_bytes": 89.0, "flops_per_problem": 5472864534.528}, "add10": {"acc": 0.0, "reasoning_bytes": 99.048, "flops_per_problem": 6047337775.104}, "reach14": {"acc": 0.528, "reasoning_bytes": 11.32, "flops_per_problem": 4813509869.568}, "reach16": {"acc": 0.486, "reasoning_bytes": 13.112, "flops_per_problem": 5448221540.352}, "reach18": {"acc": 0.452, "reasoning_bytes": 13.472, "flops_per_problem": 6055640432.64}, "parity24": {"acc": 0.458, "reasoning_bytes": 145.128, "flops_per_problem": 7959510466.56}, "parity28": {"acc": 0.49, "reasoning_bytes": 166.188, "flops_per_problem": 9063852244.992}, "parity32": {"acc": 0.478, "reasoning_bytes": 186.528, "flops_per_problem": 10136926568.448}, "cmp8": {"acc": 0.984, "reasoning_bytes": 5.836, "flops_per_problem": 1362077466.624}, "cmp9": {"acc": 0.972, "reasoning_bytes": 5.66, "flops_per_problem": 1442365931.52}, "cmp10": {"acc": 0.986, "reasoning_bytes": 5.844, "flops_per_problem": 1538729754.624}, "runmax12": {"acc": 0.998, "reasoning_bytes": 71.516, "flops_per_problem": 4174116913.152}, "runmax14": {"acc": 0.998, "reasoning_bytes": 82.964, "flops_per_problem": 4768021905.408}, "runmax16": {"acc": 0.998, "reasoning_bytes": 92.384, "flops_per_problem": 5272364187.648}, "count16": {"acc": 0.91, "reasoning_bytes": 79.3, "flops_per_problem": 4738697625.6}, "count18": {"acc": 0.824, "reasoning_bytes": 88.96, "flops_per_problem": 5253639045.12}, "count20": {"acc": 0.696, "reasoning_bytes": 98.318, "flops_per_problem": 5755331543.04}, "brackets16": {"acc": 0.874, "reasoning_bytes": 52.604, "flops_per_problem": 3603883327.488}, "brackets18": {"acc": 0.81, "reasoning_bytes": 53.034, "flops_per_problem": 3711729549.312}, "brackets20": {"acc": 0.736, "reasoning_bytes": 53.156, "flops_per_problem": 3805090283.52}, "sumd8": {"acc": 0.868, "reasoning_bytes": 58.574, "flops_per_problem": 3381478096.896}, "sumd9": {"acc": 0.482, "reasoning_bytes": 66.56, "flops_per_problem": 3780093984.768}, "sumd10": {"acc": 0.14, "reasoning_bytes": 74.238, "flops_per_problem": 4168817344.512}, "inc8": {"acc": 0.74, "reasoning_bytes": 63.0, "flops_per_problem": 3788926599.168}, "inc9": {"acc": 0.104, "reasoning_bytes": 71.0, "flops_per_problem": 4215276896.256}, "inc10": {"acc": 0.0, "reasoning_bytes": 78.984, "flops_per_problem": 4642422128.64}, "add.cmp6": {"acc": 0.984, "reasoning_bytes": 92.418, "flops_per_problem": 5523033784.32}, "add.cmp7": {"acc": 0.944, "reasoning_bytes": 104.77, "flops_per_problem": 6198287155.2}, "add.cmp8": {"acc": 0.828, "reasoning_bytes": 119.79, "flops_per_problem": 6995607257.088}, "add.runmax6": {"acc": 0.996, "reasoning_bytes": 120.906, "flops_per_problem": 6576146399.232}, "add.runmax7": {"acc": 0.88, "reasoning_bytes": 138.796, "flops_per_problem": 7454549901.312}, "add.runmax8": {"acc": 0.59, "reasoning_bytes": 156.112, "flops_per_problem": 8307515473.92}, "add.count6": {"acc": 0.634, "reasoning_bytes": 116.974, "flops_per_problem": 6446660272.128}, "add.count7": {"acc": 0.556, "reasoning_bytes": 133.328, "flops_per_problem": 7257229295.616}, "add.count8": {"acc": 0.388, "reasoning_bytes": 148.292, "flops_per_problem": 8006411649.024}, "add.find6": {"acc": 0.852, "reasoning_bytes": 108.016, "flops_per_problem": 6006884401.152}, "add.find7": {"acc": 0.69, "reasoning_bytes": 122.238, "flops_per_problem": 6723297755.136}, "add.find8": {"acc": 0.348, "reasoning_bytes": 138.868, "flops_per_problem": 7546055786.496}, "add.rev6": {"acc": 0.556, "reasoning_bytes": 123.754, "flops_per_problem": 6805706047.488}, "add.rev7": {"acc": 0.124, "reasoning_bytes": 144.114, "flops_per_problem": 7810062630.912}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 161.75, "flops_per_problem": 8684403130.368}, "add.sumd6": {"acc": 0.91, "reasoning_bytes": 126.532, "flops_per_problem": 6780268118.016}, "add.sumd7": {"acc": 0.48, "reasoning_bytes": 145.59, "flops_per_problem": 7710342414.336}, "add.sumd8": {"acc": 0.044, "reasoning_bytes": 161.98, "flops_per_problem": 8522412982.272}, "add.inc6": {"acc": 0.718, "reasoning_bytes": 130.886, "flops_per_problem": 7122885230.592}, "add.inc7": {"acc": 0.082, "reasoning_bytes": 149.2, "flops_per_problem": 8034234384.384}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 164.098, "flops_per_problem": 8801611923.456}, "runmax.cmp12": {"acc": 0.996, "reasoning_bytes": 87.216, "flops_per_problem": 5132455575.552}, "runmax.cmp14": {"acc": 0.992, "reasoning_bytes": 97.2, "flops_per_problem": 5661705830.4}, "runmax.cmp16": {"acc": 0.984, "reasoning_bytes": 104.996, "flops_per_problem": 6094327283.712}, "runmax.runmax12": {"acc": 0.998, "reasoning_bytes": 89.116, "flops_per_problem": 5260528484.352}, "runmax.runmax14": {"acc": 0.986, "reasoning_bytes": 100.12, "flops_per_problem": 5834825072.64}, "runmax.runmax16": {"acc": 0.974, "reasoning_bytes": 109.192, "flops_per_problem": 6323798605.824}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.888, "flops_per_problem": 5294622375.936}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 100.06, "flops_per_problem": 5876338360.32}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 108.196, "flops_per_problem": 6323975258.112}, "runmax.find12": {"acc": 0.962, "reasoning_bytes": 88.912, "flops_per_problem": 5251519217.664}, "runmax.find14": {"acc": 0.922, "reasoning_bytes": 99.52, "flops_per_problem": 5808327229.44}, "runmax.find16": {"acc": 0.882, "reasoning_bytes": 107.164, "flops_per_problem": 6234235895.808}, "runmax.rev12": {"acc": 0.998, "reasoning_bytes": 83.6, "flops_per_problem": 4884435763.2}, "runmax.rev14": {"acc": 0.986, "reasoning_bytes": 94.58, "flops_per_problem": 5457672437.76}, "runmax.rev16": {"acc": 0.962, "reasoning_bytes": 101.876, "flops_per_problem": 5868212355.072}, "runmax.sumd12": {"acc": 0.996, "reasoning_bytes": 87.152, "flops_per_problem": 5085466066.944}, "runmax.sumd14": {"acc": 0.992, "reasoning_bytes": 97.988, "flops_per_problem": 5652343259.136}, "runmax.sumd16": {"acc": 0.978, "reasoning_bytes": 106.58, "flops_per_problem": 6120118517.76}, "runmax.inc12": {"acc": 0.996, "reasoning_bytes": 87.528, "flops_per_problem": 5089087438.848}, "runmax.inc14": {"acc": 0.99, "reasoning_bytes": 98.448, "flops_per_problem": 5662589091.84}, "runmax.inc16": {"acc": 0.964, "reasoning_bytes": 105.84, "flops_per_problem": 6078958534.656}, "count.cmp16": {"acc": 0.99, "reasoning_bytes": 95.09, "flops_per_problem": 5701982552.064}, "count.cmp18": {"acc": 0.97, "reasoning_bytes": 104.504, "flops_per_problem": 6206148182.016}, "count.cmp20": {"acc": 0.942, "reasoning_bytes": 112.854, "flops_per_problem": 6662352715.776}, "count.runmax16": {"acc": 0.972, "reasoning_bytes": 96.554, "flops_per_problem": 5809828773.888}, "count.runmax18": {"acc": 0.946, "reasoning_bytes": 106.484, "flops_per_problem": 6336694222.848}, "count.runmax20": {"acc": 0.814, "reasoning_bytes": 115.86, "flops_per_problem": 6839093329.92}, "count.count16": {"acc": 1.0, "reasoning_bytes": 96.8, "flops_per_problem": 5864855961.6}, "count.count18": {"acc": 1.0, "reasoning_bytes": 106.65, "flops_per_problem": 6388188364.8}, "count.count20": {"acc": 0.998, "reasoning_bytes": 116.09, "flops_per_problem": 6893413908.48}, "count.find16": {"acc": 0.984, "reasoning_bytes": 96.686, "flops_per_problem": 5815569973.248}, "count.find18": {"acc": 0.962, "reasoning_bytes": 106.44, "flops_per_problem": 6334751047.68}, "count.find20": {"acc": 0.912, "reasoning_bytes": 115.56, "flops_per_problem": 6825844408.32}, "count.rev16": {"acc": 0.956, "reasoning_bytes": 91.27, "flops_per_problem": 5443981885.44}, "count.rev18": {"acc": 0.888, "reasoning_bytes": 101.03, "flops_per_problem": 5963339612.16}, "count.rev20": {"acc": 0.74, "reasoning_bytes": 109.08, "flops_per_problem": 6407178485.76}, "count.sumd16": {"acc": 0.952, "reasoning_bytes": 94.49, "flops_per_problem": 5630350049.28}, "count.sumd18": {"acc": 0.918, "reasoning_bytes": 104.41, "flops_per_problem": 6156773867.52}, "count.sumd20": {"acc": 0.79, "reasoning_bytes": 113.446, "flops_per_problem": 6644157530.112}, "count.inc16": {"acc": 0.964, "reasoning_bytes": 95.22, "flops_per_problem": 5618426019.84}, "count.inc18": {"acc": 0.912, "reasoning_bytes": 104.972, "flops_per_problem": 6137430441.984}, "count.inc20": {"acc": 0.774, "reasoning_bytes": 113.152, "flops_per_problem": 6587187167.232}, "parity.cmp16": {"acc": 0.958, "reasoning_bytes": 111.452, "flops_per_problem": 6381387251.712}, "parity.cmp20": {"acc": 0.958, "reasoning_bytes": 129.618, "flops_per_problem": 7358362730.496}, "parity.cmp24": {"acc": 0.95, "reasoning_bytes": 148.39, "flops_per_problem": 8364044206.08}, "parity.runmax16": {"acc": 0.774, "reasoning_bytes": 112.92, "flops_per_problem": 6499037675.52}, "parity.runmax20": {"acc": 0.486, "reasoning_bytes": 134.278, "flops_per_problem": 7611505459.2}, "parity.runmax24": {"acc": 0.534, "reasoning_bytes": 159.026, "flops_per_problem": 8883225280.512}, "parity.count16": {"acc": 0.978, "reasoning_bytes": 113.33, "flops_per_problem": 6562367520.768}, "parity.count20": {"acc": 0.998, "reasoning_bytes": 134.49, "flops_per_problem": 7662911275.008}, "parity.count24": {"acc": 0.998, "reasoning_bytes": 156.726, "flops_per_problem": 8821573632.0}, "parity.find16": {"acc": 0.9, "reasoning_bytes": 112.89, "flops_per_problem": 6513611489.28}, "parity.find20": {"acc": 0.876, "reasoning_bytes": 133.432, "flops_per_problem": 7570963759.104}, "parity.find24": {"acc": 0.88, "reasoning_bytes": 155.896, "flops_per_problem": 8741815123.968}, "parity.rev16": {"acc": 0.588, "reasoning_bytes": 108.896, "flops_per_problem": 6187511365.632}, "parity.rev20": {"acc": 0.526, "reasoning_bytes": 129.632, "flops_per_problem": 7272509718.528}, "parity.rev24": {"acc": 0.494, "reasoning_bytes": 152.396, "flops_per_problem": 8453253611.52}, "parity.sumd16": {"acc": 0.738, "reasoning_bytes": 110.804, "flops_per_problem": 6315495948.288}, "parity.sumd20": {"acc": 0.504, "reasoning_bytes": 131.336, "flops_per_problem": 7391838339.072}, "parity.sumd24": {"acc": 0.538, "reasoning_bytes": 156.392, "flops_per_problem": 8675040559.104}, "parity.inc16": {"acc": 0.672, "reasoning_bytes": 111.8, "flops_per_problem": 6305780072.448}, "parity.inc20": {"acc": 0.558, "reasoning_bytes": 132.74, "flops_per_problem": 7407737044.992}, "parity.inc24": {"acc": 0.528, "reasoning_bytes": 155.664, "flops_per_problem": 8597048573.952}, "sumd.cmp6": {"acc": 0.98, "reasoning_bytes": 62.09, "flops_per_problem": 3713496072.192}, "sumd.cmp7": {"acc": 0.95, "reasoning_bytes": 70.146, "flops_per_problem": 4113613504.512}, "sumd.cmp8": {"acc": 0.938, "reasoning_bytes": 77.124, "flops_per_problem": 4465858166.784}, "sumd.runmax6": {"acc": 0.99, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.95, "reasoning_bytes": 75.472, "flops_per_problem": 4348826025.984}, "sumd.runmax8": {"acc": 0.782, "reasoning_bytes": 83.252, "flops_per_problem": 4736577798.144}, "sumd.count6": {"acc": 0.992, "reasoning_bytes": 66.428, "flops_per_problem": 3949415202.816}, "sumd.count7": {"acc": 0.986, "reasoning_bytes": 74.46, "flops_per_problem": 4348296069.12}, "sumd.count8": {"acc": 0.852, "reasoning_bytes": 81.418, "flops_per_problem": 4699745796.096}, "sumd.find6": {"acc": 0.996, "reasoning_bytes": 66.198, "flops_per_problem": 3895094624.256}, "sumd.find7": {"acc": 0.978, "reasoning_bytes": 74.444, "flops_per_problem": 4303426387.968}, "sumd.find8": {"acc": 0.866, "reasoning_bytes": 80.352, "flops_per_problem": 4608504889.344}, "sumd.rev6": {"acc": 0.994, "reasoning_bytes": 61.544, "flops_per_problem": 3601145217.024}, "sumd.rev7": {"acc": 0.95, "reasoning_bytes": 69.48, "flops_per_problem": 3995874754.56}, "sumd.rev8": {"acc": 0.73, "reasoning_bytes": 77.122, "flops_per_problem": 4377443696.64}, "sumd.sumd6": {"acc": 0.982, "reasoning_bytes": 65.742, "flops_per_problem": 3795462733.824}, "sumd.sumd7": {"acc": 0.854, "reasoning_bytes": 73.704, "flops_per_problem": 4192488751.104}, "sumd.sumd8": {"acc": 0.516, "reasoning_bytes": 81.346, "flops_per_problem": 4571761213.44}, "sumd.inc6": {"acc": 0.954, "reasoning_bytes": 68.562, "flops_per_problem": 3910993330.176}, "sumd.inc7": {"acc": 0.872, "reasoning_bytes": 76.42, "flops_per_problem": 4302278148.096}, "sumd.inc8": {"acc": 0.506, "reasoning_bytes": 83.766, "flops_per_problem": 4671658082.304}, "inc.cmp6": {"acc": 0.986, "reasoning_bytes": 78.582, "flops_per_problem": 4574499323.904}, "inc.cmp7": {"acc": 0.966, "reasoning_bytes": 89.444, "flops_per_problem": 5142524755.968}, "inc.cmp8": {"acc": 0.742, "reasoning_bytes": 99.94, "flops_per_problem": 5694386503.68}, "inc.runmax6": {"acc": 1.0, "reasoning_bytes": 104.002, "flops_per_problem": 5520472326.144}, "inc.runmax7": {"acc": 0.986, "reasoning_bytes": 119.764, "flops_per_problem": 6260733739.008}, "inc.runmax8": {"acc": 0.856, "reasoning_bytes": 134.71, "flops_per_problem": 6964958085.12}, "inc.count6": {"acc": 0.822, "reasoning_bytes": 99.086, "flops_per_problem": 5347529736.192}, "inc.count7": {"acc": 0.67, "reasoning_bytes": 113.82, "flops_per_problem": 6042391511.04}, "inc.count8": {"acc": 0.55, "reasoning_bytes": 125.912, "flops_per_problem": 6620574449.664}, "inc.find6": {"acc": 0.9, "reasoning_bytes": 91.9, "flops_per_problem": 4986010828.8}, "inc.find7": {"acc": 0.852, "reasoning_bytes": 102.992, "flops_per_problem": 5520030695.424}, "inc.find8": {"acc": 0.402, "reasoning_bytes": 116.508, "flops_per_problem": 6161101848.576}, "inc.rev6": {"acc": 0.934, "reasoning_bytes": 104.07, "flops_per_problem": 5609240100.864}, "inc.rev7": {"acc": 0.554, "reasoning_bytes": 123.478, "flops_per_problem": 6543554052.096}, "inc.rev8": {"acc": 0.0, "reasoning_bytes": 137.046, "flops_per_problem": 7194782711.808}, "inc.sumd6": {"acc": 0.972, "reasoning_bytes": 109.534, "flops_per_problem": 5720531042.304}, "inc.sumd7": {"acc": 0.698, "reasoning_bytes": 126.564, "flops_per_problem": 6516791230.464}, "inc.sumd8": {"acc": 0.058, "reasoning_bytes": 139.398, "flops_per_problem": 7127743168.512}, "inc.inc6": {"acc": 0.876, "reasoning_bytes": 112.938, "flops_per_problem": 5998670069.76}, "inc.inc7": {"acc": 0.56, "reasoning_bytes": 130.152, "flops_per_problem": 6836090241.024}, "inc.inc8": {"acc": 0.0, "reasoning_bytes": 143.264, "flops_per_problem": 7467445518.336}, "count.inc.cmp16": {"acc": 0.192, "reasoning_bytes": 108.96, "flops_per_problem": 6596903043.072}, "count.inc.cmp18": {"acc": 0.212, "reasoning_bytes": 118.45, "flops_per_problem": 7097535627.264}, "count.inc.cmp20": {"acc": 0.242, "reasoning_bytes": 126.878, "flops_per_problem": 7536339910.656}, "inc.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 163.254, "flops_per_problem": 8428522291.2}, "inc.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 192.012, "flops_per_problem": 9755004321.792}, "inc.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 206.738, "flops_per_problem": 10469386174.464}, "parity.runmax.count16": {"acc": 0.984, "reasoning_bytes": 130.444, "flops_per_problem": 7624136097.792}, "parity.runmax.count20": {"acc": 0.99, "reasoning_bytes": 152.974, "flops_per_problem": 8792602656.768}, "parity.runmax.count24": {"acc": 0.998, "reasoning_bytes": 175.494, "flops_per_problem": 9959567671.296}, "add.count.find6": {"acc": 0.0, "reasoning_bytes": 137.488, "flops_per_problem": 7669535735.808}, "add.count.find7": {"acc": 0.0, "reasoning_bytes": 153.974, "flops_per_problem": 8479574802.432}, "add.count.find8": {"acc": 0.0, "reasoning_bytes": 168.468, "flops_per_problem": 9207382228.992}, "runmax.inc.find12": {"acc": 0.872, "reasoning_bytes": 106.654, "flops_per_problem": 6211712729.088}, "runmax.inc.find14": {"acc": 0.888, "reasoning_bytes": 117.38, "flops_per_problem": 6773731983.36}, "runmax.inc.find16": {"acc": 0.826, "reasoning_bytes": 125.384, "flops_per_problem": 7215539355.648}, "parity.sumd.rev16": {"acc": 0.82, "reasoning_bytes": 122.78, "flops_per_problem": 7015303987.2}, "parity.sumd.rev20": {"acc": 0.496, "reasoning_bytes": 144.264, "flops_per_problem": 8143228846.08}, "parity.sumd.rev24": {"acc": 0.516, "reasoning_bytes": 167.47, "flops_per_problem": 9340401401.856}, "parity.rev.sumd16": {"acc": 0.826, "reasoning_bytes": 122.744, "flops_per_problem": 7014155747.328}, "parity.rev.sumd20": {"acc": 0.504, "reasoning_bytes": 143.714, "flops_per_problem": 8121323962.368}, "parity.rev.sumd24": {"acc": 0.508, "reasoning_bytes": 167.716, "flops_per_problem": 9352678735.872}, "count.inc.sumd16": {"acc": 0.958, "reasoning_bytes": 110.424, "flops_per_problem": 6510608400.384}, "count.inc.sumd18": {"acc": 0.938, "reasoning_bytes": 120.314, "flops_per_problem": 7035795652.608}, "count.inc.sumd20": {"acc": 0.81, "reasoning_bytes": 128.534, "flops_per_problem": 7487937183.744}, "inc.sumd.rev6": {"acc": 0.964, "reasoning_bytes": 128.532, "flops_per_problem": 6736281698.304}, "inc.sumd.rev7": {"acc": 0.638, "reasoning_bytes": 145.264, "flops_per_problem": 7519027986.432}, "inc.sumd.rev8": {"acc": 0.076, "reasoning_bytes": 156.834, "flops_per_problem": 8072302952.448}, "count.count.cmp16": {"acc": 1.0, "reasoning_bytes": 112.544, "flops_per_problem": 6825137799.168}, "count.count.cmp18": {"acc": 1.0, "reasoning_bytes": 122.38, "flops_per_problem": 7347851919.36}, "count.count.cmp20": {"acc": 0.998, "reasoning_bytes": 132.058, "flops_per_problem": 7863588274.176}, "parity.rev.find16": {"acc": 0.924, "reasoning_bytes": 125.03, "flops_per_problem": 7217924161.536}, "parity.rev.find20": {"acc": 0.876, "reasoning_bytes": 146.11, "flops_per_problem": 8310695215.104}, "parity.rev.find24": {"acc": 0.886, "reasoning_bytes": 168.52, "flops_per_problem": 9473862205.44}, "count.sumd.cmp16": {"acc": 0.996, "reasoning_bytes": 110.32, "flops_per_problem": 6594429911.04}, "count.sumd.cmp18": {"acc": 0.988, "reasoning_bytes": 120.14, "flops_per_problem": 7116437422.08}, "count.sumd.cmp20": {"acc": 0.966, "reasoning_bytes": 129.216, "flops_per_problem": 7605587607.552}, "sumd.count.count6": {"acc": 1.0, "reasoning_bytes": 83.476, "flops_per_problem": 5055611830.272}, "sumd.count.count7": {"acc": 0.998, "reasoning_bytes": 91.49, "flops_per_problem": 5453697761.28}, "sumd.count.count8": {"acc": 0.998, "reasoning_bytes": 96.506, "flops_per_problem": 5719382802.432}, "runmax.rev.inc12": {"acc": 0.998, "reasoning_bytes": 99.816, "flops_per_problem": 5808415555.584}, "runmax.rev.inc14": {"acc": 0.99, "reasoning_bytes": 110.976, "flops_per_problem": 6392604672.0}, "runmax.rev.inc16": {"acc": 0.968, "reasoning_bytes": 119.352, "flops_per_problem": 6852518903.808}, "parity.sumd.find16": {"acc": 0.956, "reasoning_bytes": 127.608, "flops_per_problem": 7362160754.688}, "parity.sumd.find20": {"acc": 0.906, "reasoning_bytes": 147.964, "flops_per_problem": 8433556881.408}, "parity.sumd.find24": {"acc": 0.864, "reasoning_bytes": 171.534, "flops_per_problem": 9652192690.176}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.78, "flops_per_problem": 6217277276.16}, "runmax.runmax.cmp14": {"acc": 0.98, "reasoning_bytes": 116.12, "flops_per_problem": 6806412656.64}, "runmax.runmax.cmp16": {"acc": 0.992, "reasoning_bytes": 125.552, "flops_per_problem": 7311284895.744}, "count.runmax.count16": {"acc": 1.0, "reasoning_bytes": 113.708, "flops_per_problem": 6920706686.976}, "count.runmax.count18": {"acc": 1.0, "reasoning_bytes": 123.918, "flops_per_problem": 7459937796.096}, "count.runmax.count20": {"acc": 1.0, "reasoning_bytes": 133.682, "flops_per_problem": 7979472175.104}, "inc.inc.sumd6": {"acc": 0.744, "reasoning_bytes": 175.218, "flops_per_problem": 8797548920.832}, "inc.inc.sumd7": {"acc": 0.226, "reasoning_bytes": 198.94, "flops_per_problem": 9889701691.392}, "inc.inc.sumd8": {"acc": 0.034, "reasoning_bytes": 212.326, "flops_per_problem": 10523265122.304}, "add.sumd.find6": {"acc": 0.948, "reasoning_bytes": 150.438, "flops_per_problem": 8101185601.536}, "add.sumd.find7": {"acc": 0.744, "reasoning_bytes": 168.95, "flops_per_problem": 9007146860.544}, "add.sumd.find8": {"acc": 0.638, "reasoning_bytes": 184.972, "flops_per_problem": 9805085245.44}, "sumd.rev.rev6": {"acc": 0.99, "reasoning_bytes": 80.53, "flops_per_problem": 4616277590.016}, "sumd.rev.rev7": {"acc": 0.918, "reasoning_bytes": 88.47, "flops_per_problem": 5011183779.84}, "sumd.rev.rev8": {"acc": 0.464, "reasoning_bytes": 94.222, "flops_per_problem": 5309284515.84}, "runmax.inc.runmax12": {"acc": 0.988, "reasoning_bytes": 111.052, "flops_per_problem": 6405941919.744}, "runmax.inc.runmax14": {"acc": 0.984, "reasoning_bytes": 122.448, "flops_per_problem": 6997550432.256}, "runmax.inc.runmax16": {"acc": 0.988, "reasoning_bytes": 133.484, "flops_per_problem": 7573260238.848}, "parity.inc.find16": {"acc": 0.942, "reasoning_bytes": 128.508, "flops_per_problem": 7355624620.032}, "parity.inc.find20": {"acc": 0.896, "reasoning_bytes": 148.456, "flops_per_problem": 8412181954.56}, "parity.inc.find24": {"acc": 0.84, "reasoning_bytes": 170.488, "flops_per_problem": 9560775131.136}, "inc.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 119.104, "flops_per_problem": 6408238399.488}, "inc.runmax.sumd7": {"acc": 0.984, "reasoning_bytes": 135.216, "flops_per_problem": 7163956887.552}, "inc.runmax.sumd8": {"acc": 0.832, "reasoning_bytes": 149.036, "flops_per_problem": 7818983571.456}, "sumd.rev.cmp6": {"acc": 0.49, "reasoning_bytes": 81.154, "flops_per_problem": 4748766806.016}, "sumd.rev.cmp7": {"acc": 0.374, "reasoning_bytes": 89.134, "flops_per_problem": 5149060890.624}, "sumd.rev.cmp8": {"acc": 0.2, "reasoning_bytes": 93.668, "flops_per_problem": 5396815724.544}, "runmax.runmax.count12": {"acc": 1.0, "reasoning_bytes": 106.236, "flops_per_problem": 6369904852.992}, "runmax.runmax.count14": {"acc": 1.0, "reasoning_bytes": 117.672, "flops_per_problem": 6963279888.384}, "runmax.runmax.count16": {"acc": 1.0, "reasoning_bytes": 128.652, "flops_per_problem": 7536516562.944}, "count.count.count16": {"acc": 1.0, "reasoning_bytes": 113.764, "flops_per_problem": 6967342891.008}, "count.count.count18": {"acc": 1.0, "reasoning_bytes": 123.93, "flops_per_problem": 7504630824.96}, "count.count.count20": {"acc": 1.0, "reasoning_bytes": 133.594, "flops_per_problem": 8019748896.768}, "add.sumd.rev6": {"acc": 0.876, "reasoning_bytes": 145.266, "flops_per_problem": 7784271396.864}, "add.sumd.rev7": {"acc": 0.326, "reasoning_bytes": 163.852, "flops_per_problem": 8693412397.056}, "add.sumd.rev8": {"acc": 0.046, "reasoning_bytes": 180.232, "flops_per_problem": 9505129660.416}, "add.rev.rev6": {"acc": 0.136, "reasoning_bytes": 187.488, "flops_per_problem": 9772051267.584}, "add.rev.rev7": {"acc": 0.006, "reasoning_bytes": 212.72, "flops_per_problem": 10991923642.368}, "add.rev.rev8": {"acc": 0.0, "reasoning_bytes": 235.65, "flops_per_problem": 12107217862.656}, "inc.runmax.cmp6": {"acc": 0.502, "reasoning_bytes": 73.678, "flops_per_problem": 4446249762.816}, "inc.runmax.cmp7": {"acc": 0.416, "reasoning_bytes": 87.414, "flops_per_problem": 5097036791.808}, "inc.runmax.cmp8": {"acc": 0.41, "reasoning_bytes": 98.86, "flops_per_problem": 5646690385.92}, "count.rev.cmp16": {"acc": 0.994, "reasoning_bytes": 107.166, "flops_per_problem": 6410976509.952}, "count.rev.cmp18": {"acc": 0.982, "reasoning_bytes": 116.814, "flops_per_problem": 6925476298.752}, "count.rev.cmp20": {"acc": 0.966, "reasoning_bytes": 125.15, "flops_per_problem": 7382034137.088}} +{"step": 5000, "train_loss": 1.1209816932678223} +{"step": 5020, "train_loss": 1.1183891296386719} +{"step": 5040, "train_loss": 1.2000720500946045} +{"step": 5060, "train_loss": 1.183145523071289} +{"step": 5080, "train_loss": 1.208932638168335} +{"step": 5100, "train_loss": 1.152288794517517} +{"step": 5120, "train_loss": 1.1297481060028076} +{"step": 5140, "train_loss": 1.1510387659072876} +{"step": 5160, "train_loss": 1.1142547130584717} +{"step": 5180, "train_loss": 1.0655457973480225} +{"step": 5200, "train_loss": 1.1382343769073486} +{"step": 5220, "train_loss": 1.186635136604309} +{"step": 5240, "train_loss": 1.107522964477539} +{"step": 5260, "train_loss": 1.1890474557876587} +{"step": 5280, "train_loss": 1.0807600021362305} +{"step": 5300, "train_loss": 1.0976910591125488} +{"step": 5320, "train_loss": 1.1743018627166748} +{"step": 5340, "train_loss": 1.1209094524383545} +{"step": 5360, "train_loss": 1.073083519935608} +{"step": 5380, "train_loss": 1.1191222667694092} +{"step": 5400, "train_loss": 1.1455457210540771} +{"step": 5420, "train_loss": 1.0551390647888184} +{"step": 5440, "train_loss": 1.0424275398254395} +{"step": 5460, "train_loss": 1.101179838180542} +{"step": 5480, "train_loss": 1.0988895893096924} +{"step": 5500, "train_loss": 1.1894197463989258} +{"step": 5520, "train_loss": 1.1732901334762573} +{"step": 5540, "train_loss": 1.1323645114898682} +{"step": 5560, "train_loss": 1.118690013885498} +{"step": 5580, "train_loss": 1.1533215045928955} +{"step": 5600, "train_loss": 1.125967025756836} +{"step": 5620, "train_loss": 1.1555407047271729} +{"step": 5640, "train_loss": 1.0780482292175293} +{"step": 5660, "train_loss": 1.1432580947875977} +{"step": 5680, "train_loss": 1.151470422744751} +{"step": 5700, "train_loss": 1.1566601991653442} +{"step": 5720, "train_loss": 1.1866099834442139} +{"step": 5740, "train_loss": 1.1210697889328003} +{"step": 5760, "train_loss": 1.088152527809143} +{"step": 5780, "train_loss": 1.1010313034057617} +{"step": 5800, "train_loss": 1.142982006072998} +{"step": 5820, "train_loss": 1.1978521347045898} +{"step": 5840, "train_loss": 1.0988116264343262} +{"step": 5860, "train_loss": 1.2037134170532227} +{"step": 5880, "train_loss": 1.0711817741394043} +{"step": 5900, "train_loss": 1.1404101848602295} +{"step": 5920, "train_loss": 1.1520941257476807} +{"step": 5940, "train_loss": 1.1799944639205933} +{"step": 5960, "train_loss": 1.1750507354736328} +{"step": 5980, "train_loss": 1.0959464311599731} +{"step": 6000, "tokens": 196608000, "val_loss": 1.963578176498413, "val_bpb": 0.7078380318349614, "lr": 0.0003459796115961056, "elapsed": 1016.1707441806793, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.144, "reasoning_bytes": 79.0, "flops_per_problem": 4925242441.728}, "add9": {"acc": 0.0, "reasoning_bytes": 88.9, "flops_per_problem": 5493356199.936}, "add10": {"acc": 0.0, "reasoning_bytes": 96.32, "flops_per_problem": 5944702795.776}, "reach14": {"acc": 0.538, "reasoning_bytes": 6.78, "flops_per_problem": 4583243612.16}, "reach16": {"acc": 0.55, "reasoning_bytes": 7.982, "flops_per_problem": 5166284488.704}, "reach18": {"acc": 0.56, "reasoning_bytes": 8.316, "flops_per_problem": 5710903492.608}, "parity24": {"acc": 0.554, "reasoning_bytes": 136.904, "flops_per_problem": 7591808729.088}, "parity28": {"acc": 0.462, "reasoning_bytes": 160.052, "flops_per_problem": 8790747807.744}, "parity32": {"acc": 0.496, "reasoning_bytes": 183.416, "flops_per_problem": 9999226109.952}, "cmp8": {"acc": 0.966, "reasoning_bytes": 5.776, "flops_per_problem": 1359162703.872}, "cmp9": {"acc": 0.962, "reasoning_bytes": 5.612, "flops_per_problem": 1440246104.064}, "cmp10": {"acc": 0.964, "reasoning_bytes": 5.748, "flops_per_problem": 1534578425.856}, "runmax12": {"acc": 1.0, "reasoning_bytes": 69.836, "flops_per_problem": 4099922952.192}, "runmax14": {"acc": 0.998, "reasoning_bytes": 77.312, "flops_per_problem": 4518412222.464}, "runmax16": {"acc": 0.994, "reasoning_bytes": 87.236, "flops_per_problem": 5045012692.992}, "count16": {"acc": 0.93, "reasoning_bytes": 77.61, "flops_per_problem": 4664062033.92}, "count18": {"acc": 0.866, "reasoning_bytes": 85.26, "flops_per_problem": 5090235678.72}, "count20": {"acc": 0.758, "reasoning_bytes": 94.19, "flops_per_problem": 5572938055.68}, "brackets16": {"acc": 0.72, "reasoning_bytes": 52.908, "flops_per_problem": 3617308901.376}, "brackets18": {"acc": 0.552, "reasoning_bytes": 55.102, "flops_per_problem": 3802528825.344}, "brackets20": {"acc": 0.492, "reasoning_bytes": 59.822, "flops_per_problem": 4099304669.184}, "sumd8": {"acc": 0.908, "reasoning_bytes": 58.528, "flops_per_problem": 3379534921.728}, "sumd9": {"acc": 0.622, "reasoning_bytes": 65.724, "flops_per_problem": 3741495459.84}, "sumd10": {"acc": 0.248, "reasoning_bytes": 70.808, "flops_per_problem": 4009565306.88}, "inc8": {"acc": 0.914, "reasoning_bytes": 63.0, "flops_per_problem": 3798024192.0}, "inc9": {"acc": 0.29, "reasoning_bytes": 70.994, "flops_per_problem": 4239831564.288}, "inc10": {"acc": 0.0, "reasoning_bytes": 78.832, "flops_per_problem": 4673777909.76}, "add.cmp6": {"acc": 0.99, "reasoning_bytes": 92.45, "flops_per_problem": 5524447002.624}, "add.cmp7": {"acc": 0.902, "reasoning_bytes": 104.914, "flops_per_problem": 6204646637.568}, "add.cmp8": {"acc": 0.77, "reasoning_bytes": 116.874, "flops_per_problem": 6866827739.136}, "add.runmax6": {"acc": 0.998, "reasoning_bytes": 120.844, "flops_per_problem": 6573408288.768}, "add.runmax7": {"acc": 0.89, "reasoning_bytes": 138.766, "flops_per_problem": 7453225009.152}, "add.runmax8": {"acc": 0.538, "reasoning_bytes": 155.952, "flops_per_problem": 8300537708.544}, "add.count6": {"acc": 0.858, "reasoning_bytes": 115.638, "flops_per_problem": 6387658407.936}, "add.count7": {"acc": 0.692, "reasoning_bytes": 131.478, "flops_per_problem": 7175527612.416}, "add.count8": {"acc": 0.438, "reasoning_bytes": 146.242, "flops_per_problem": 7915877351.424}, "add.find6": {"acc": 0.914, "reasoning_bytes": 107.904, "flops_per_problem": 6001938137.088}, "add.find7": {"acc": 0.66, "reasoning_bytes": 123.198, "flops_per_problem": 6765694304.256}, "add.find8": {"acc": 0.278, "reasoning_bytes": 142.004, "flops_per_problem": 7684727832.576}, "add.rev6": {"acc": 0.736, "reasoning_bytes": 123.206, "flops_per_problem": 6786892578.816}, "add.rev7": {"acc": 0.204, "reasoning_bytes": 145.312, "flops_per_problem": 7887259680.768}, "add.rev8": {"acc": 0.002, "reasoning_bytes": 164.316, "flops_per_problem": 8835175858.176}, "add.sumd6": {"acc": 0.91, "reasoning_bytes": 126.49, "flops_per_problem": 6778148290.56}, "add.sumd7": {"acc": 0.466, "reasoning_bytes": 146.034, "flops_per_problem": 7729774166.016}, "add.sumd8": {"acc": 0.04, "reasoning_bytes": 162.302, "flops_per_problem": 8537163448.32}, "add.inc6": {"acc": 0.936, "reasoning_bytes": 131.06, "flops_per_problem": 7140638785.536}, "add.inc7": {"acc": 0.328, "reasoning_bytes": 150.34, "flops_per_problem": 8122207223.808}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 163.738, "flops_per_problem": 8824046764.032}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 86.688, "flops_per_problem": 5109137473.536}, "runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 94.392, "flops_per_problem": 5537695924.224}, "runmax.cmp16": {"acc": 1.0, "reasoning_bytes": 104.182, "flops_per_problem": 6058378543.104}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 87.724, "flops_per_problem": 5199053488.128}, "runmax.runmax14": {"acc": 1.0, "reasoning_bytes": 96.208, "flops_per_problem": 5662059134.976}, "runmax.runmax16": {"acc": 0.992, "reasoning_bytes": 105.7, "flops_per_problem": 6169581158.4}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 87.844, "flops_per_problem": 5248516128.768}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 96.7, "flops_per_problem": 5727950438.4}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 105.94, "flops_per_problem": 6224343367.68}, "runmax.find12": {"acc": 0.998, "reasoning_bytes": 87.712, "flops_per_problem": 5198523531.264}, "runmax.find14": {"acc": 0.998, "reasoning_bytes": 95.32, "flops_per_problem": 5622842327.04}, "runmax.find16": {"acc": 0.992, "reasoning_bytes": 104.812, "flops_per_problem": 6130364350.464}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 82.664, "flops_per_problem": 4843099127.808}, "runmax.rev14": {"acc": 0.998, "reasoning_bytes": 90.152, "flops_per_problem": 5262118354.944}, "runmax.rev16": {"acc": 0.994, "reasoning_bytes": 99.788, "flops_per_problem": 5775999860.736}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 85.604, "flops_per_problem": 5017101631.488}, "runmax.sumd14": {"acc": 0.998, "reasoning_bytes": 93.2, "flops_per_problem": 5440890470.4}, "runmax.sumd16": {"acc": 0.996, "reasoning_bytes": 103.004, "flops_per_problem": 5962191372.288}, "runmax.inc12": {"acc": 0.968, "reasoning_bytes": 86.58, "flops_per_problem": 5045807628.288}, "runmax.inc14": {"acc": 0.918, "reasoning_bytes": 93.708, "flops_per_problem": 5450253041.664}, "runmax.inc16": {"acc": 0.692, "reasoning_bytes": 103.152, "flops_per_problem": 5948147515.392}, "count.cmp16": {"acc": 0.954, "reasoning_bytes": 93.83, "flops_per_problem": 5645365493.76}, "count.cmp18": {"acc": 0.932, "reasoning_bytes": 100.77, "flops_per_problem": 6040271683.584}, "count.cmp20": {"acc": 0.914, "reasoning_bytes": 109.866, "flops_per_problem": 6530393456.64}, "count.runmax16": {"acc": 0.962, "reasoning_bytes": 95.02, "flops_per_problem": 5742082621.44}, "count.runmax18": {"acc": 0.864, "reasoning_bytes": 102.33, "flops_per_problem": 6153240821.76}, "count.runmax20": {"acc": 0.77, "reasoning_bytes": 110.93, "flops_per_problem": 6621369384.96}, "count.count16": {"acc": 1.0, "reasoning_bytes": 94.71, "flops_per_problem": 5772555141.12}, "count.count18": {"acc": 0.994, "reasoning_bytes": 101.928, "flops_per_problem": 6179650338.816}, "count.count20": {"acc": 0.986, "reasoning_bytes": 110.88, "flops_per_problem": 6663500955.648}, "count.find16": {"acc": 0.968, "reasoning_bytes": 94.87, "flops_per_problem": 5735458160.64}, "count.find18": {"acc": 0.93, "reasoning_bytes": 101.76, "flops_per_problem": 6128067870.72}, "count.find20": {"acc": 0.908, "reasoning_bytes": 110.824, "flops_per_problem": 6616688099.328}, "count.rev16": {"acc": 0.912, "reasoning_bytes": 89.01, "flops_per_problem": 5344173342.72}, "count.rev18": {"acc": 0.812, "reasoning_bytes": 96.21, "flops_per_problem": 5750473605.12}, "count.rev20": {"acc": 0.73, "reasoning_bytes": 105.174, "flops_per_problem": 6234677526.528}, "count.sumd16": {"acc": 0.93, "reasoning_bytes": 92.46, "flops_per_problem": 5540699013.12}, "count.sumd18": {"acc": 0.818, "reasoning_bytes": 99.41, "flops_per_problem": 5935958507.52}, "count.sumd20": {"acc": 0.74, "reasoning_bytes": 108.4, "flops_per_problem": 6421310668.8}, "count.inc16": {"acc": 0.896, "reasoning_bytes": 92.63, "flops_per_problem": 5504043663.36}, "count.inc18": {"acc": 0.79, "reasoning_bytes": 100.12, "flops_per_problem": 5923151216.64}, "count.inc20": {"acc": 0.728, "reasoning_bytes": 108.896, "flops_per_problem": 6399052480.512}, "parity.cmp16": {"acc": 0.968, "reasoning_bytes": 107.448, "flops_per_problem": 6202615136.256}, "parity.cmp20": {"acc": 0.946, "reasoning_bytes": 126.636, "flops_per_problem": 7226668449.792}, "parity.cmp24": {"acc": 0.934, "reasoning_bytes": 145.56, "flops_per_problem": 8239062712.32}, "parity.runmax16": {"acc": 0.752, "reasoning_bytes": 109.804, "flops_per_problem": 6350826405.888}, "parity.runmax20": {"acc": 0.542, "reasoning_bytes": 128.704, "flops_per_problem": 7362160754.688}, "parity.runmax24": {"acc": 0.468, "reasoning_bytes": 147.952, "flops_per_problem": 8388863852.544}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 110.068, "flops_per_problem": 6406648528.896}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 129.328, "flops_per_problem": 7433881583.616}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 148.562, "flops_per_problem": 8459966398.464}, "parity.find16": {"acc": 0.922, "reasoning_bytes": 109.18, "flops_per_problem": 6323268648.96}, "parity.find20": {"acc": 0.87, "reasoning_bytes": 128.788, "flops_per_problem": 7365870452.736}, "parity.find24": {"acc": 0.868, "reasoning_bytes": 148.108, "flops_per_problem": 8395753291.776}, "parity.rev16": {"acc": 0.698, "reasoning_bytes": 104.084, "flops_per_problem": 5965724418.048}, "parity.rev20": {"acc": 0.476, "reasoning_bytes": 123.2, "flops_per_problem": 6986597990.4}, "parity.rev24": {"acc": 0.448, "reasoning_bytes": 142.424, "flops_per_problem": 8012241174.528}, "parity.sumd16": {"acc": 0.75, "reasoning_bytes": 107.696, "flops_per_problem": 6169404506.112}, "parity.sumd20": {"acc": 0.48, "reasoning_bytes": 126.728, "flops_per_problem": 7186568380.416}, "parity.sumd24": {"acc": 0.484, "reasoning_bytes": 146.786, "flops_per_problem": 8249661849.6}, "parity.inc16": {"acc": 0.712, "reasoning_bytes": 107.928, "flops_per_problem": 6135487266.816}, "parity.inc20": {"acc": 0.488, "reasoning_bytes": 126.612, "flops_per_problem": 7137282392.064}, "parity.inc24": {"acc": 0.47, "reasoning_bytes": 145.716, "flops_per_problem": 8157626007.552}, "sumd.cmp6": {"acc": 0.988, "reasoning_bytes": 62.012, "flops_per_problem": 3710051352.576}, "sumd.cmp7": {"acc": 0.98, "reasoning_bytes": 69.764, "flops_per_problem": 4096743211.008}, "sumd.cmp8": {"acc": 0.966, "reasoning_bytes": 75.91, "flops_per_problem": 4412244197.376}, "sumd.runmax6": {"acc": 0.998, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.984, "reasoning_bytes": 75.478, "flops_per_problem": 4349091004.416}, "sumd.runmax8": {"acc": 0.766, "reasoning_bytes": 82.124, "flops_per_problem": 4686761852.928}, "sumd.count6": {"acc": 0.998, "reasoning_bytes": 66.426, "flops_per_problem": 3949326876.672}, "sumd.count7": {"acc": 0.994, "reasoning_bytes": 74.454, "flops_per_problem": 4348031090.688}, "sumd.count8": {"acc": 0.86, "reasoning_bytes": 80.472, "flops_per_problem": 4657967529.984}, "sumd.find6": {"acc": 0.994, "reasoning_bytes": 66.276, "flops_per_problem": 3898539343.872}, "sumd.find7": {"acc": 0.962, "reasoning_bytes": 74.62, "flops_per_problem": 4311199088.64}, "sumd.find8": {"acc": 0.844, "reasoning_bytes": 81.146, "flops_per_problem": 4643570368.512}, "sumd.rev6": {"acc": 0.996, "reasoning_bytes": 61.566, "flops_per_problem": 3602205130.752}, "sumd.rev7": {"acc": 0.976, "reasoning_bytes": 69.468, "flops_per_problem": 3994991493.12}, "sumd.rev8": {"acc": 0.71, "reasoning_bytes": 75.564, "flops_per_problem": 4308284325.888}, "sumd.sumd6": {"acc": 0.978, "reasoning_bytes": 65.744, "flops_per_problem": 3796434321.408}, "sumd.sumd7": {"acc": 0.92, "reasoning_bytes": 73.734, "flops_per_problem": 4194961883.136}, "sumd.sumd8": {"acc": 0.508, "reasoning_bytes": 80.108, "flops_per_problem": 4518853853.184}, "sumd.inc6": {"acc": 0.992, "reasoning_bytes": 68.538, "flops_per_problem": 3910021742.592}, "sumd.inc7": {"acc": 0.882, "reasoning_bytes": 76.482, "flops_per_problem": 4305281236.992}, "sumd.inc8": {"acc": 0.522, "reasoning_bytes": 82.95, "flops_per_problem": 4635179384.832}, "inc.cmp6": {"acc": 0.98, "reasoning_bytes": 78.538, "flops_per_problem": 4572556148.736}, "inc.cmp7": {"acc": 0.966, "reasoning_bytes": 89.242, "flops_per_problem": 5133603815.424}, "inc.cmp8": {"acc": 0.912, "reasoning_bytes": 99.024, "flops_per_problem": 5653933129.728}, "inc.runmax6": {"acc": 1.0, "reasoning_bytes": 104.002, "flops_per_problem": 5520472326.144}, "inc.runmax7": {"acc": 1.0, "reasoning_bytes": 119.976, "flops_per_problem": 6270096310.272}, "inc.runmax8": {"acc": 0.854, "reasoning_bytes": 133.888, "flops_per_problem": 6928656039.936}, "inc.count6": {"acc": 0.938, "reasoning_bytes": 99.0, "flops_per_problem": 5343731712.0}, "inc.count7": {"acc": 0.856, "reasoning_bytes": 113.974, "flops_per_problem": 6049192624.128}, "inc.count8": {"acc": 0.64, "reasoning_bytes": 122.274, "flops_per_problem": 6459909193.728}, "inc.find6": {"acc": 0.918, "reasoning_bytes": 92.3, "flops_per_problem": 5003676057.6}, "inc.find7": {"acc": 0.81, "reasoning_bytes": 104.722, "flops_per_problem": 5596432809.984}, "inc.find8": {"acc": 0.356, "reasoning_bytes": 116.912, "flops_per_problem": 6179562012.672}, "inc.rev6": {"acc": 0.954, "reasoning_bytes": 103.938, "flops_per_problem": 5604735467.52}, "inc.rev7": {"acc": 0.668, "reasoning_bytes": 123.656, "flops_per_problem": 6558569496.576}, "inc.rev8": {"acc": 0.032, "reasoning_bytes": 136.59, "flops_per_problem": 7191691296.768}, "inc.sumd6": {"acc": 0.972, "reasoning_bytes": 109.568, "flops_per_problem": 5722120912.896}, "inc.sumd7": {"acc": 0.824, "reasoning_bytes": 127.506, "flops_per_problem": 6558304518.144}, "inc.sumd8": {"acc": 0.138, "reasoning_bytes": 141.366, "flops_per_problem": 7215451029.504}, "inc.inc6": {"acc": 0.976, "reasoning_bytes": 113.0, "flops_per_problem": 6005912813.568}, "inc.inc7": {"acc": 0.896, "reasoning_bytes": 131.0, "flops_per_problem": 6888732622.848}, "inc.inc8": {"acc": 0.09, "reasoning_bytes": 146.424, "flops_per_problem": 7648955744.256}, "count.inc.cmp16": {"acc": 0.188, "reasoning_bytes": 109.44, "flops_per_problem": 6514759729.152}, "count.inc.cmp18": {"acc": 0.204, "reasoning_bytes": 116.05, "flops_per_problem": 6897388584.96}, "count.inc.cmp20": {"acc": 0.154, "reasoning_bytes": 125.134, "flops_per_problem": 7391220056.064}, "inc.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 161.59, "flops_per_problem": 8366429011.968}, "inc.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 193.384, "flops_per_problem": 9832643002.368}, "inc.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 213.138, "flops_per_problem": 10768546824.192}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 127.344, "flops_per_problem": 7478751264.768}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 146.828, "flops_per_problem": 8515876847.616}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 165.324, "flops_per_problem": 9509369315.328}, "add.count.find6": {"acc": 0.002, "reasoning_bytes": 136.328, "flops_per_problem": 7610975502.336}, "add.count.find7": {"acc": 0.02, "reasoning_bytes": 151.644, "flops_per_problem": 8380296216.576}, "add.count.find8": {"acc": 0.024, "reasoning_bytes": 160.148, "flops_per_problem": 8858582286.336}, "runmax.inc.find12": {"acc": 0.76, "reasoning_bytes": 106.762, "flops_per_problem": 6216482340.864}, "runmax.inc.find14": {"acc": 0.736, "reasoning_bytes": 112.22, "flops_per_problem": 6545850531.84}, "runmax.inc.find16": {"acc": 0.69, "reasoning_bytes": 121.21, "flops_per_problem": 7031202693.12}, "parity.sumd.rev16": {"acc": 0.756, "reasoning_bytes": 119.828, "flops_per_problem": 6881843183.616}, "parity.sumd.rev20": {"acc": 0.538, "reasoning_bytes": 138.74, "flops_per_problem": 7893707489.28}, "parity.sumd.rev24": {"acc": 0.484, "reasoning_bytes": 157.792, "flops_per_problem": 8911754625.024}, "parity.rev.sumd16": {"acc": 0.764, "reasoning_bytes": 119.876, "flops_per_problem": 6883963011.072}, "parity.rev.sumd20": {"acc": 0.542, "reasoning_bytes": 138.764, "flops_per_problem": 7894767403.008}, "parity.rev.sumd24": {"acc": 0.49, "reasoning_bytes": 157.964, "flops_per_problem": 8919350673.408}, "count.inc.sumd16": {"acc": 0.922, "reasoning_bytes": 108.47, "flops_per_problem": 6424402083.84}, "count.inc.sumd18": {"acc": 0.81, "reasoning_bytes": 115.61, "flops_per_problem": 6828052561.92}, "count.inc.sumd20": {"acc": 0.762, "reasoning_bytes": 124.242, "flops_per_problem": 7297682669.568}, "inc.sumd.rev6": {"acc": 0.984, "reasoning_bytes": 128.566, "flops_per_problem": 6737783242.752}, "inc.sumd.rev7": {"acc": 0.796, "reasoning_bytes": 146.432, "flops_per_problem": 7571052085.248}, "inc.sumd.rev8": {"acc": 0.092, "reasoning_bytes": 155.644, "flops_per_problem": 8022751985.664}, "count.count.cmp16": {"acc": 0.998, "reasoning_bytes": 111.22, "flops_per_problem": 6766665891.84}, "count.count.cmp18": {"acc": 0.996, "reasoning_bytes": 119.138, "flops_per_problem": 7204675239.936}, "count.count.cmp20": {"acc": 0.99, "reasoning_bytes": 127.224, "flops_per_problem": 7650103984.128}, "parity.rev.find16": {"acc": 0.92, "reasoning_bytes": 121.492, "flops_per_problem": 7043656679.424}, "parity.rev.find20": {"acc": 0.882, "reasoning_bytes": 140.704, "flops_per_problem": 8068769906.688}, "parity.rev.find24": {"acc": 0.868, "reasoning_bytes": 159.568, "flops_per_problem": 9078514384.896}, "count.sumd.cmp16": {"acc": 0.964, "reasoning_bytes": 109.26, "flops_per_problem": 6547617054.72}, "count.sumd.cmp18": {"acc": 0.932, "reasoning_bytes": 116.852, "flops_per_problem": 6971229241.344}, "count.sumd.cmp20": {"acc": 0.926, "reasoning_bytes": 125.098, "flops_per_problem": 7423724077.056}, "sumd.count.count6": {"acc": 1.0, "reasoning_bytes": 83.436, "flops_per_problem": 5053845307.392}, "sumd.count.count7": {"acc": 1.0, "reasoning_bytes": 91.384, "flops_per_problem": 5449016475.648}, "sumd.count.count8": {"acc": 1.0, "reasoning_bytes": 95.964, "flops_per_problem": 5694651482.112}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 98.424, "flops_per_problem": 5746940559.36}, "runmax.rev.inc14": {"acc": 0.998, "reasoning_bytes": 106.884, "flops_per_problem": 6212154359.808}, "runmax.rev.inc16": {"acc": 0.996, "reasoning_bytes": 116.316, "flops_per_problem": 6719588057.088}, "parity.sumd.find16": {"acc": 0.926, "reasoning_bytes": 124.816, "flops_per_problem": 7234617802.752}, "parity.sumd.find20": {"acc": 0.868, "reasoning_bytes": 143.908, "flops_per_problem": 8254431461.376}, "parity.sumd.find24": {"acc": 0.864, "reasoning_bytes": 162.736, "flops_per_problem": 9262586068.992}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 103.652, "flops_per_problem": 6167461330.944}, "runmax.runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 113.228, "flops_per_problem": 6678693052.416}, "runmax.runmax.cmp16": {"acc": 1.0, "reasoning_bytes": 122.168, "flops_per_problem": 7161837060.096}, "count.runmax.count16": {"acc": 1.0, "reasoning_bytes": 112.23, "flops_per_problem": 6855433666.56}, "count.runmax.count18": {"acc": 0.996, "reasoning_bytes": 120.6, "flops_per_problem": 7313758027.776}, "count.runmax.count20": {"acc": 0.988, "reasoning_bytes": 128.34, "flops_per_problem": 7744083001.344}, "inc.inc.sumd6": {"acc": 0.786, "reasoning_bytes": 175.526, "flops_per_problem": 8811769430.016}, "inc.inc.sumd7": {"acc": 0.24, "reasoning_bytes": 202.49, "flops_per_problem": 10047982141.44}, "inc.inc.sumd8": {"acc": 0.046, "reasoning_bytes": 220.016, "flops_per_problem": 10871181803.52}, "add.sumd.find6": {"acc": 0.954, "reasoning_bytes": 151.07, "flops_per_problem": 8129096663.04}, "add.sumd.find7": {"acc": 0.668, "reasoning_bytes": 170.94, "flops_per_problem": 9095119699.968}, "add.sumd.find8": {"acc": 0.606, "reasoning_bytes": 185.646, "flops_per_problem": 9832996306.944}, "sumd.rev.rev6": {"acc": 0.99, "reasoning_bytes": 80.53, "flops_per_problem": 4616277590.016}, "sumd.rev.rev7": {"acc": 0.968, "reasoning_bytes": 88.45, "flops_per_problem": 5010300518.4}, "sumd.rev.rev8": {"acc": 0.376, "reasoning_bytes": 91.522, "flops_per_problem": 5189779243.008}, "runmax.inc.runmax12": {"acc": 0.992, "reasoning_bytes": 109.152, "flops_per_problem": 6322032082.944}, "runmax.inc.runmax14": {"acc": 0.936, "reasoning_bytes": 118.624, "flops_per_problem": 6828670844.928}, "runmax.inc.runmax16": {"acc": 0.632, "reasoning_bytes": 124.244, "flops_per_problem": 7165193453.568}, "parity.inc.find16": {"acc": 0.908, "reasoning_bytes": 124.772, "flops_per_problem": 7188511555.584}, "parity.inc.find20": {"acc": 0.868, "reasoning_bytes": 143.48, "flops_per_problem": 8191366594.56}, "parity.inc.find24": {"acc": 0.834, "reasoning_bytes": 161.78, "flops_per_problem": 9176203100.16}, "inc.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 118.988, "flops_per_problem": 6403115483.136}, "inc.runmax.sumd7": {"acc": 0.99, "reasoning_bytes": 134.976, "flops_per_problem": 7153357750.272}, "inc.runmax.sumd8": {"acc": 0.808, "reasoning_bytes": 148.806, "flops_per_problem": 7808296108.032}, "sumd.rev.cmp6": {"acc": 0.692, "reasoning_bytes": 80.694, "flops_per_problem": 4720679092.224}, "sumd.rev.cmp7": {"acc": 0.538, "reasoning_bytes": 88.512, "flops_per_problem": 5118411718.656}, "sumd.rev.cmp8": {"acc": 0.272, "reasoning_bytes": 92.13, "flops_per_problem": 5330129485.824}, "runmax.runmax.count12": {"acc": 1.0, "reasoning_bytes": 104.688, "flops_per_problem": 6301540417.536}, "runmax.runmax.count14": {"acc": 1.0, "reasoning_bytes": 114.924, "flops_per_problem": 6841919766.528}, "runmax.runmax.count16": {"acc": 1.0, "reasoning_bytes": 123.48, "flops_per_problem": 7308105154.56}, "count.count.count16": {"acc": 1.0, "reasoning_bytes": 111.832, "flops_per_problem": 6882019835.904}, "count.count.count18": {"acc": 1.0, "reasoning_bytes": 119.77, "flops_per_problem": 7320912445.44}, "count.count.count20": {"acc": 1.0, "reasoning_bytes": 128.146, "flops_per_problem": 7779148480.512}, "add.sumd.rev6": {"acc": 0.898, "reasoning_bytes": 145.47, "flops_per_problem": 7793280663.552}, "add.sumd.rev7": {"acc": 0.37, "reasoning_bytes": 165.238, "flops_per_problem": 8754710740.992}, "add.sumd.rev8": {"acc": 0.04, "reasoning_bytes": 180.706, "flops_per_problem": 9532687417.344}, "add.rev.rev6": {"acc": 0.302, "reasoning_bytes": 187.352, "flops_per_problem": 9786006798.336}, "add.rev.rev7": {"acc": 0.018, "reasoning_bytes": 222.2, "flops_per_problem": 11445831696.384}, "add.rev.rev8": {"acc": 0.0, "reasoning_bytes": 250.234, "flops_per_problem": 12794306936.832}, "inc.runmax.cmp6": {"acc": 0.74, "reasoning_bytes": 102.644, "flops_per_problem": 5725742284.8}, "inc.runmax.cmp7": {"acc": 0.686, "reasoning_bytes": 110.282, "flops_per_problem": 6107752857.6}, "inc.runmax.cmp8": {"acc": 0.884, "reasoning_bytes": 120.416, "flops_per_problem": 6598934544.384}, "count.rev.cmp16": {"acc": 0.972, "reasoning_bytes": 106.3, "flops_per_problem": 6372731289.6}, "count.rev.cmp18": {"acc": 0.94, "reasoning_bytes": 113.8, "flops_per_problem": 6792368799.744}, "count.rev.cmp20": {"acc": 0.942, "reasoning_bytes": 122.096, "flops_per_problem": 7247160115.2}} +{"step": 6000, "train_loss": 1.220137119293213} +{"step": 6020, "train_loss": 1.0809545516967773} +{"step": 6040, "train_loss": 1.0851932764053345} +{"step": 6060, "train_loss": 1.1161894798278809} +{"step": 6080, "train_loss": 1.2139973640441895} +{"step": 6100, "train_loss": 1.117247223854065} +{"step": 6120, "train_loss": 1.1704670190811157} +{"step": 6140, "train_loss": 1.1652551889419556} +{"step": 6160, "train_loss": 1.081221103668213} +{"step": 6180, "train_loss": 1.1779253482818604} +{"step": 6200, "train_loss": 1.1340922117233276} +{"step": 6220, "train_loss": 1.1010162830352783} +{"step": 6240, "train_loss": 1.164703130722046} +{"step": 6260, "train_loss": 1.1533045768737793} +{"step": 6280, "train_loss": 1.1890254020690918} +{"step": 6300, "train_loss": 1.0984026193618774} +{"step": 6320, "train_loss": 1.104203462600708} +{"step": 6340, "train_loss": 1.1137394905090332} +{"step": 6360, "train_loss": 1.1275827884674072} +{"step": 6380, "train_loss": 1.135697364807129} +{"step": 6400, "train_loss": 1.0653808116912842} +{"step": 6420, "train_loss": 1.0675396919250488} +{"step": 6440, "train_loss": 1.054363489151001} +{"step": 6460, "train_loss": 1.1391334533691406} +{"step": 6480, "train_loss": 1.0925800800323486} +{"step": 6500, "train_loss": 1.0725936889648438} +{"step": 6520, "train_loss": 1.1369799375534058} +{"step": 6540, "train_loss": 1.0933191776275635} +{"step": 6560, "train_loss": 1.1773759126663208} +{"step": 6580, "train_loss": 1.0843555927276611} +{"step": 6600, "train_loss": 1.156895399093628} +{"step": 6620, "train_loss": 1.0374200344085693} +{"step": 6640, "train_loss": 1.097592830657959} +{"step": 6660, "train_loss": 1.0759344100952148} +{"step": 6680, "train_loss": 1.0135608911514282} +{"step": 6700, "train_loss": 1.0832115411758423} +{"step": 6720, "train_loss": 1.092009425163269} +{"step": 6740, "train_loss": 1.0806764364242554} +{"step": 6760, "train_loss": 1.0409282445907593} +{"step": 6780, "train_loss": 1.1194829940795898} +{"step": 6800, "train_loss": 1.0171453952789307} +{"step": 6820, "train_loss": 1.0559492111206055} +{"step": 6840, "train_loss": 1.0004923343658447} +{"step": 6860, "train_loss": 1.065239667892456} +{"step": 6880, "train_loss": 1.1826179027557373} +{"step": 6900, "train_loss": 1.0481255054473877} +{"step": 6920, "train_loss": 0.9944841861724854} +{"step": 6940, "train_loss": 1.1822148561477661} +{"step": 6960, "train_loss": 1.0673598051071167} +{"step": 6980, "train_loss": 1.0495506525039673} +{"step": 7000, "tokens": 229376000, "val_loss": 1.8941286027431488, "val_bpb": 0.6828025887917071, "lr": 0.00027546233806915164, "elapsed": 1181.515653848648, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.794, "reasoning_bytes": 79.0, "flops_per_problem": 4932396859.392}, "add9": {"acc": 0.014, "reasoning_bytes": 88.98, "flops_per_problem": 5520295673.856}, "add10": {"acc": 0.0, "reasoning_bytes": 98.216, "flops_per_problem": 6075248836.608}, "reach14": {"acc": 0.522, "reasoning_bytes": 8.078, "flops_per_problem": 4640567279.616}, "reach16": {"acc": 0.526, "reasoning_bytes": 8.248, "flops_per_problem": 5178031865.856}, "reach18": {"acc": 0.538, "reasoning_bytes": 9.174, "flops_per_problem": 5748707082.24}, "parity24": {"acc": 0.452, "reasoning_bytes": 140.504, "flops_per_problem": 7750795788.288}, "parity28": {"acc": 0.488, "reasoning_bytes": 162.956, "flops_per_problem": 8918997368.832}, "parity32": {"acc": 0.458, "reasoning_bytes": 186.836, "flops_per_problem": 10146377465.856}, "cmp8": {"acc": 0.976, "reasoning_bytes": 5.792, "flops_per_problem": 1359869313.024}, "cmp9": {"acc": 0.978, "reasoning_bytes": 5.708, "flops_per_problem": 1444485758.976}, "cmp10": {"acc": 0.958, "reasoning_bytes": 5.78, "flops_per_problem": 1535991644.16}, "runmax12": {"acc": 0.998, "reasoning_bytes": 71.0, "flops_per_problem": 4151328768.0}, "runmax14": {"acc": 0.994, "reasoning_bytes": 83.012, "flops_per_problem": 4770141732.864}, "runmax16": {"acc": 0.96, "reasoning_bytes": 94.884, "flops_per_problem": 5382683541.504}, "count16": {"acc": 0.912, "reasoning_bytes": 78.2, "flops_per_problem": 4690118246.4}, "count18": {"acc": 0.792, "reasoning_bytes": 86.788, "flops_per_problem": 5157716852.736}, "count20": {"acc": 0.686, "reasoning_bytes": 95.842, "flops_per_problem": 5647926951.936}, "brackets16": {"acc": 0.96, "reasoning_bytes": 53.76, "flops_per_problem": 3654935838.72}, "brackets18": {"acc": 0.902, "reasoning_bytes": 56.888, "flops_per_problem": 3881404071.936}, "brackets20": {"acc": 0.862, "reasoning_bytes": 63.22, "flops_per_problem": 4249370787.84}, "sumd8": {"acc": 0.902, "reasoning_bytes": 58.558, "flops_per_problem": 3380859813.888}, "sumd9": {"acc": 0.684, "reasoning_bytes": 66.226, "flops_per_problem": 3763753648.128}, "sumd10": {"acc": 0.378, "reasoning_bytes": 73.558, "flops_per_problem": 4131808690.176}, "inc8": {"acc": 0.96, "reasoning_bytes": 63.0, "flops_per_problem": 3798024192.0}, "inc9": {"acc": 0.354, "reasoning_bytes": 70.984, "flops_per_problem": 4240273195.008}, "inc10": {"acc": 0.0, "reasoning_bytes": 78.168, "flops_per_problem": 4651254743.04}, "add.cmp6": {"acc": 0.98, "reasoning_bytes": 92.866, "flops_per_problem": 5543083819.008}, "add.cmp7": {"acc": 0.942, "reasoning_bytes": 106.334, "flops_per_problem": 6267269873.664}, "add.cmp8": {"acc": 0.872, "reasoning_bytes": 120.98, "flops_per_problem": 7048514617.344}, "add.runmax6": {"acc": 0.994, "reasoning_bytes": 120.894, "flops_per_problem": 6575439790.08}, "add.runmax7": {"acc": 0.97, "reasoning_bytes": 139.31, "flops_per_problem": 7476984741.888}, "add.runmax8": {"acc": 0.446, "reasoning_bytes": 158.68, "flops_per_problem": 8419954655.232}, "add.count6": {"acc": 0.844, "reasoning_bytes": 115.47, "flops_per_problem": 6380239011.84}, "add.count7": {"acc": 0.766, "reasoning_bytes": 132.072, "flops_per_problem": 7201760477.184}, "add.count8": {"acc": 0.512, "reasoning_bytes": 148.504, "flops_per_problem": 8015597568.0}, "add.find6": {"acc": 0.816, "reasoning_bytes": 108.974, "flops_per_problem": 6049192624.128}, "add.find7": {"acc": 0.65, "reasoning_bytes": 124.326, "flops_per_problem": 6815510249.472}, "add.find8": {"acc": 0.334, "reasoning_bytes": 142.402, "flops_per_problem": 7703364648.96}, "add.rev6": {"acc": 0.584, "reasoning_bytes": 122.988, "flops_per_problem": 6768785719.296}, "add.rev7": {"acc": 0.068, "reasoning_bytes": 140.892, "flops_per_problem": 7661586382.848}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 158.148, "flops_per_problem": 8525504397.312}, "add.sumd6": {"acc": 0.928, "reasoning_bytes": 126.63, "flops_per_problem": 6784507772.928}, "add.sumd7": {"acc": 0.688, "reasoning_bytes": 146.644, "flops_per_problem": 7756448661.504}, "add.sumd8": {"acc": 0.046, "reasoning_bytes": 166.384, "flops_per_problem": 8717260455.936}, "add.inc6": {"acc": 0.812, "reasoning_bytes": 131.036, "flops_per_problem": 7143641874.432}, "add.inc7": {"acc": 0.24, "reasoning_bytes": 148.624, "flops_per_problem": 8058082443.264}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 163.612, "flops_per_problem": 8853547696.128}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.012, "flops_per_problem": 5123446308.864}, "runmax.cmp14": {"acc": 0.998, "reasoning_bytes": 98.964, "flops_per_problem": 5739609489.408}, "runmax.cmp16": {"acc": 0.992, "reasoning_bytes": 107.412, "flops_per_problem": 6201025265.664}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.runmax14": {"acc": 0.992, "reasoning_bytes": 100.0, "flops_per_problem": 5829525504.0}, "runmax.runmax16": {"acc": 0.968, "reasoning_bytes": 110.332, "flops_per_problem": 6374144507.904}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5255405568.0}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 100.024, "flops_per_problem": 5874748489.728}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 110.62, "flops_per_problem": 6431026544.64}, "runmax.find12": {"acc": 0.998, "reasoning_bytes": 88.012, "flops_per_problem": 5211772452.864}, "runmax.find14": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5829525504.0}, "runmax.find16": {"acc": 0.986, "reasoning_bytes": 109.66, "flops_per_problem": 6344466923.52}, "runmax.rev12": {"acc": 0.998, "reasoning_bytes": 83.0, "flops_per_problem": 4857937920.0}, "runmax.rev14": {"acc": 0.988, "reasoning_bytes": 95.0, "flops_per_problem": 5476220928.0}, "runmax.rev16": {"acc": 0.96, "reasoning_bytes": 105.836, "flops_per_problem": 6043098120.192}, "runmax.sumd12": {"acc": 0.998, "reasoning_bytes": 86.0, "flops_per_problem": 5034590208.0}, "runmax.sumd14": {"acc": 0.992, "reasoning_bytes": 98.0, "flops_per_problem": 5652873216.0}, "runmax.sumd16": {"acc": 0.962, "reasoning_bytes": 108.704, "flops_per_problem": 6213920882.688}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 87.06, "flops_per_problem": 5068419121.152}, "runmax.inc14": {"acc": 0.988, "reasoning_bytes": 99.072, "flops_per_problem": 5690235174.912}, "runmax.inc16": {"acc": 0.878, "reasoning_bytes": 110.688, "flops_per_problem": 6289263083.52}, "count.cmp16": {"acc": 0.98, "reasoning_bytes": 93.75, "flops_per_problem": 5641832448.0}, "count.cmp18": {"acc": 0.944, "reasoning_bytes": 101.548, "flops_per_problem": 6074630553.6}, "count.cmp20": {"acc": 0.918, "reasoning_bytes": 109.946, "flops_per_problem": 6533926502.4}, "count.runmax16": {"acc": 0.926, "reasoning_bytes": 94.96, "flops_per_problem": 5739432837.12}, "count.runmax18": {"acc": 0.788, "reasoning_bytes": 103.084, "flops_per_problem": 6186539778.048}, "count.runmax20": {"acc": 0.696, "reasoning_bytes": 111.588, "flops_per_problem": 6650428686.336}, "count.count16": {"acc": 1.0, "reasoning_bytes": 94.78, "flops_per_problem": 5775646556.16}, "count.count18": {"acc": 0.998, "reasoning_bytes": 102.87, "flops_per_problem": 6221251952.64}, "count.count20": {"acc": 0.992, "reasoning_bytes": 111.442, "flops_per_problem": 6688143949.824}, "count.find16": {"acc": 0.974, "reasoning_bytes": 94.36, "flops_per_problem": 5712934993.92}, "count.find18": {"acc": 0.918, "reasoning_bytes": 102.52, "flops_per_problem": 6163221676.032}, "count.find20": {"acc": 0.828, "reasoning_bytes": 111.568, "flops_per_problem": 6654138384.384}, "count.rev16": {"acc": 0.926, "reasoning_bytes": 89.85, "flops_per_problem": 5381270323.2}, "count.rev18": {"acc": 0.79, "reasoning_bytes": 97.7, "flops_per_problem": 5816276582.4}, "count.rev20": {"acc": 0.684, "reasoning_bytes": 106.458, "flops_per_problem": 6291382910.976}, "count.sumd16": {"acc": 0.934, "reasoning_bytes": 93.26, "flops_per_problem": 5576029470.72}, "count.sumd18": {"acc": 0.782, "reasoning_bytes": 101.42, "flops_per_problem": 6024726282.24}, "count.sumd20": {"acc": 0.708, "reasoning_bytes": 109.832, "flops_per_problem": 6484552187.904}, "count.inc16": {"acc": 0.91, "reasoning_bytes": 93.89, "flops_per_problem": 5559689134.08}, "count.inc18": {"acc": 0.786, "reasoning_bytes": 101.934, "flops_per_problem": 6003351355.392}, "count.inc20": {"acc": 0.7, "reasoning_bytes": 110.378, "flops_per_problem": 6464502153.216}, "parity.cmp16": {"acc": 0.994, "reasoning_bytes": 110.964, "flops_per_problem": 6357892497.408}, "parity.cmp20": {"acc": 0.916, "reasoning_bytes": 129.756, "flops_per_problem": 7364457234.432}, "parity.cmp24": {"acc": 0.934, "reasoning_bytes": 150.318, "flops_per_problem": 8449190608.896}, "parity.runmax16": {"acc": 0.992, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.runmax20": {"acc": 0.38, "reasoning_bytes": 131.356, "flops_per_problem": 7479281221.632}, "parity.runmax24": {"acc": 0.312, "reasoning_bytes": 154.012, "flops_per_problem": 8656492068.864}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6491971584.0}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 131.872, "flops_per_problem": 7546232438.784}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 154.072, "flops_per_problem": 8703304925.184}, "parity.find16": {"acc": 0.996, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.find20": {"acc": 0.832, "reasoning_bytes": 131.848, "flops_per_problem": 7501009453.056}, "parity.find24": {"acc": 0.828, "reasoning_bytes": 154.072, "flops_per_problem": 8659141853.184}, "parity.rev16": {"acc": 0.988, "reasoning_bytes": 107.0, "flops_per_problem": 6094503936.0}, "parity.rev20": {"acc": 0.3, "reasoning_bytes": 125.864, "flops_per_problem": 7104248414.208}, "parity.rev24": {"acc": 0.352, "reasoning_bytes": 148.808, "flops_per_problem": 8294178226.176}, "parity.sumd16": {"acc": 0.978, "reasoning_bytes": 110.0, "flops_per_problem": 6271156224.0}, "parity.sumd20": {"acc": 0.398, "reasoning_bytes": 130.496, "flops_per_problem": 7352974835.712}, "parity.sumd24": {"acc": 0.378, "reasoning_bytes": 152.84, "flops_per_problem": 8516406804.48}, "parity.inc16": {"acc": 0.972, "reasoning_bytes": 111.0, "flops_per_problem": 6271156224.0}, "parity.inc20": {"acc": 0.424, "reasoning_bytes": 131.892, "flops_per_problem": 7370463412.224}, "parity.inc24": {"acc": 0.378, "reasoning_bytes": 155.324, "flops_per_problem": 8581944803.328}, "sumd.cmp6": {"acc": 0.994, "reasoning_bytes": 62.064, "flops_per_problem": 3712347832.32}, "sumd.cmp7": {"acc": 0.986, "reasoning_bytes": 69.572, "flops_per_problem": 4088263901.184}, "sumd.cmp8": {"acc": 0.938, "reasoning_bytes": 71.78, "flops_per_problem": 4229850710.016}, "sumd.runmax6": {"acc": 0.996, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.952, "reasoning_bytes": 75.388, "flops_per_problem": 4345116327.936}, "sumd.runmax8": {"acc": 0.688, "reasoning_bytes": 81.446, "flops_per_problem": 4656819290.112}, "sumd.count6": {"acc": 0.988, "reasoning_bytes": 66.412, "flops_per_problem": 3948708593.664}, "sumd.count7": {"acc": 0.95, "reasoning_bytes": 74.292, "flops_per_problem": 4340876673.024}, "sumd.count8": {"acc": 0.844, "reasoning_bytes": 79.034, "flops_per_problem": 4594461032.448}, "sumd.find6": {"acc": 1.0, "reasoning_bytes": 66.224, "flops_per_problem": 3896242864.128}, "sumd.find7": {"acc": 0.976, "reasoning_bytes": 74.182, "flops_per_problem": 4291855663.104}, "sumd.find8": {"acc": 0.822, "reasoning_bytes": 78.408, "flops_per_problem": 4522651877.376}, "sumd.rev6": {"acc": 0.984, "reasoning_bytes": 61.544, "flops_per_problem": 3601145217.024}, "sumd.rev7": {"acc": 0.956, "reasoning_bytes": 69.422, "flops_per_problem": 3993224970.24}, "sumd.rev8": {"acc": 0.634, "reasoning_bytes": 74.954, "flops_per_problem": 4281698156.544}, "sumd.sumd6": {"acc": 0.97, "reasoning_bytes": 65.73, "flops_per_problem": 3794932776.96}, "sumd.sumd7": {"acc": 0.77, "reasoning_bytes": 73.444, "flops_per_problem": 4181536309.248}, "sumd.sumd8": {"acc": 0.276, "reasoning_bytes": 78.03, "flops_per_problem": 4423373291.52}, "sumd.inc6": {"acc": 0.932, "reasoning_bytes": 68.526, "flops_per_problem": 3909403459.584}, "sumd.inc7": {"acc": 0.744, "reasoning_bytes": 76.312, "flops_per_problem": 4297773514.752}, "sumd.inc8": {"acc": 0.388, "reasoning_bytes": 83.426, "flops_per_problem": 4655052767.232}, "inc.cmp6": {"acc": 0.984, "reasoning_bytes": 78.656, "flops_per_problem": 4577767391.232}, "inc.cmp7": {"acc": 0.954, "reasoning_bytes": 89.91, "flops_per_problem": 5163369725.952}, "inc.cmp8": {"acc": 0.686, "reasoning_bytes": 100.922, "flops_per_problem": 5737754640.384}, "inc.runmax6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5520384000.0}, "inc.runmax7": {"acc": 0.998, "reasoning_bytes": 119.696, "flops_per_problem": 6257730650.112}, "inc.runmax8": {"acc": 0.908, "reasoning_bytes": 120.742, "flops_per_problem": 6348088295.424}, "inc.count6": {"acc": 0.914, "reasoning_bytes": 99.0, "flops_per_problem": 5343731712.0}, "inc.count7": {"acc": 0.752, "reasoning_bytes": 112.35, "flops_per_problem": 5977471795.2}, "inc.count8": {"acc": 0.69, "reasoning_bytes": 114.124, "flops_per_problem": 6099980156.928}, "inc.find6": {"acc": 0.866, "reasoning_bytes": 92.9, "flops_per_problem": 5030173900.8}, "inc.find7": {"acc": 0.624, "reasoning_bytes": 106.164, "flops_per_problem": 5660115959.808}, "inc.find8": {"acc": 0.642, "reasoning_bytes": 108.086, "flops_per_problem": 5789160456.192}, "inc.rev6": {"acc": 0.738, "reasoning_bytes": 103.876, "flops_per_problem": 5595196243.968}, "inc.rev7": {"acc": 0.072, "reasoning_bytes": 119.02, "flops_per_problem": 6321502126.08}, "inc.rev8": {"acc": 0.0, "reasoning_bytes": 117.638, "flops_per_problem": 6304366854.144}, "inc.sumd6": {"acc": 0.956, "reasoning_bytes": 109.558, "flops_per_problem": 5721590956.032}, "inc.sumd7": {"acc": 0.744, "reasoning_bytes": 127.488, "flops_per_problem": 6557509582.848}, "inc.sumd8": {"acc": 0.09, "reasoning_bytes": 132.602, "flops_per_problem": 6827610931.2}, "inc.inc6": {"acc": 0.924, "reasoning_bytes": 113.0, "flops_per_problem": 6006266118.144}, "inc.inc7": {"acc": 0.582, "reasoning_bytes": 130.9, "flops_per_problem": 6894650474.496}, "inc.inc8": {"acc": 0.002, "reasoning_bytes": 132.122, "flops_per_problem": 7004086566.912}, "count.inc.cmp16": {"acc": 0.0, "reasoning_bytes": 107.97, "flops_per_problem": 6446483619.84}, "count.inc.cmp18": {"acc": 0.002, "reasoning_bytes": 115.838, "flops_per_problem": 6882461466.624}, "count.inc.cmp20": {"acc": 0.0, "reasoning_bytes": 123.492, "flops_per_problem": 7309253394.432}, "inc.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 150.296, "flops_per_problem": 7842743304.192}, "inc.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 172.588, "flops_per_problem": 8894266048.512}, "inc.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 172.802, "flops_per_problem": 8946201821.184}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 128.964, "flops_per_problem": 7550295441.408}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 148.536, "flops_per_problem": 8591307374.592}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 169.91, "flops_per_problem": 9711901163.52}, "add.count.find6": {"acc": 0.002, "reasoning_bytes": 132.142, "flops_per_problem": 7425667252.224}, "add.count.find7": {"acc": 0.0, "reasoning_bytes": 149.282, "flops_per_problem": 8270771798.016}, "add.count.find8": {"acc": 0.012, "reasoning_bytes": 159.92, "flops_per_problem": 8840563752.96}, "runmax.inc.find12": {"acc": 0.878, "reasoning_bytes": 105.428, "flops_per_problem": 6157568802.816}, "runmax.inc.find14": {"acc": 0.892, "reasoning_bytes": 117.54, "flops_per_problem": 6780798074.88}, "runmax.inc.find16": {"acc": 0.804, "reasoning_bytes": 126.952, "flops_per_problem": 7284787052.544}, "parity.sumd.rev16": {"acc": 0.978, "reasoning_bytes": 121.976, "flops_per_problem": 6976705462.272}, "parity.sumd.rev20": {"acc": 0.276, "reasoning_bytes": 140.84, "flops_per_problem": 7986449940.48}, "parity.sumd.rev24": {"acc": 0.372, "reasoning_bytes": 162.156, "flops_per_problem": 9104482271.232}, "parity.rev.sumd16": {"acc": 0.986, "reasoning_bytes": 121.976, "flops_per_problem": 6976705462.272}, "parity.rev.sumd20": {"acc": 0.304, "reasoning_bytes": 140.972, "flops_per_problem": 7992279465.984}, "parity.rev.sumd24": {"acc": 0.362, "reasoning_bytes": 162.752, "flops_per_problem": 9130803462.144}, "count.inc.sumd16": {"acc": 0.908, "reasoning_bytes": 108.45, "flops_per_problem": 6423518822.4}, "count.inc.sumd18": {"acc": 0.786, "reasoning_bytes": 116.132, "flops_per_problem": 6851105685.504}, "count.inc.sumd20": {"acc": 0.674, "reasoning_bytes": 123.56, "flops_per_problem": 7267475128.32}, "inc.sumd.rev6": {"acc": 0.954, "reasoning_bytes": 128.544, "flops_per_problem": 6736723329.024}, "inc.sumd.rev7": {"acc": 0.57, "reasoning_bytes": 143.682, "flops_per_problem": 7449338658.816}, "inc.sumd.rev8": {"acc": 0.084, "reasoning_bytes": 146.504, "flops_per_problem": 7618129920.0}, "count.count.cmp16": {"acc": 1.0, "reasoning_bytes": 110.31, "flops_per_problem": 6726477496.32}, "count.count.cmp18": {"acc": 0.996, "reasoning_bytes": 118.812, "flops_per_problem": 7190278078.464}, "count.count.cmp20": {"acc": 0.972, "reasoning_bytes": 126.552, "flops_per_problem": 7620426399.744}, "parity.rev.find16": {"acc": 1.0, "reasoning_bytes": 123.988, "flops_per_problem": 7153887707.136}, "parity.rev.find20": {"acc": 0.818, "reasoning_bytes": 142.972, "flops_per_problem": 8168931753.984}, "parity.rev.find24": {"acc": 0.838, "reasoning_bytes": 163.796, "flops_per_problem": 9265235853.312}, "count.sumd.cmp16": {"acc": 0.988, "reasoning_bytes": 108.51, "flops_per_problem": 6514494750.72}, "count.sumd.cmp18": {"acc": 0.944, "reasoning_bytes": 116.224, "flops_per_problem": 6943494832.128}, "count.sumd.cmp20": {"acc": 0.932, "reasoning_bytes": 123.952, "flops_per_problem": 7373113196.544}, "sumd.count.count6": {"acc": 1.0, "reasoning_bytes": 83.336, "flops_per_problem": 5049429000.192}, "sumd.count.count7": {"acc": 1.0, "reasoning_bytes": 89.716, "flops_per_problem": 5375352471.552}, "sumd.count.count8": {"acc": 1.0, "reasoning_bytes": 93.042, "flops_per_problem": 5566401921.024}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 99.012, "flops_per_problem": 5772908445.696}, "runmax.rev.inc14": {"acc": 0.994, "reasoning_bytes": 111.036, "flops_per_problem": 6395431108.608}, "runmax.rev.inc16": {"acc": 0.966, "reasoning_bytes": 122.028, "flops_per_problem": 6970699284.48}, "parity.sumd.find16": {"acc": 0.994, "reasoning_bytes": 126.94, "flops_per_problem": 7328420167.68}, "parity.sumd.find20": {"acc": 0.818, "reasoning_bytes": 146.32, "flops_per_problem": 8360952791.04}, "parity.sumd.find24": {"acc": 0.862, "reasoning_bytes": 167.336, "flops_per_problem": 9465736200.192}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.012, "flops_per_problem": 6183360036.864}, "runmax.runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 115.988, "flops_per_problem": 6800583131.136}, "runmax.runmax.cmp16": {"acc": 0.998, "reasoning_bytes": 126.308, "flops_per_problem": 7344672178.176}, "count.runmax.count16": {"acc": 1.0, "reasoning_bytes": 110.88, "flops_per_problem": 6795813519.36}, "count.runmax.count18": {"acc": 1.0, "reasoning_bytes": 119.65, "flops_per_problem": 7271449804.8}, "count.runmax.count20": {"acc": 1.0, "reasoning_bytes": 128.248, "flops_per_problem": 7739490041.856}, "inc.inc.sumd6": {"acc": 0.522, "reasoning_bytes": 175.672, "flops_per_problem": 8817245650.944}, "inc.inc.sumd7": {"acc": 0.128, "reasoning_bytes": 203.2, "flops_per_problem": 10075363246.08}, "inc.inc.sumd8": {"acc": 0.04, "reasoning_bytes": 203.302, "flops_per_problem": 10125532495.872}, "add.sumd.find6": {"acc": 0.978, "reasoning_bytes": 150.594, "flops_per_problem": 8108075040.768}, "add.sumd.find7": {"acc": 0.82, "reasoning_bytes": 170.672, "flops_per_problem": 9083107344.384}, "add.sumd.find8": {"acc": 0.652, "reasoning_bytes": 189.638, "flops_per_problem": 10009206964.224}, "sumd.rev.rev6": {"acc": 0.982, "reasoning_bytes": 80.398, "flops_per_problem": 4610271412.224}, "sumd.rev.rev7": {"acc": 0.722, "reasoning_bytes": 86.21, "flops_per_problem": 4911198584.832}, "sumd.rev.rev8": {"acc": 0.176, "reasoning_bytes": 89.576, "flops_per_problem": 5104014557.184}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.66, "flops_per_problem": 6344466923.52}, "runmax.inc.runmax14": {"acc": 0.994, "reasoning_bytes": 122.296, "flops_per_problem": 6990837645.312}, "runmax.inc.runmax16": {"acc": 0.976, "reasoning_bytes": 132.532, "flops_per_problem": 7531216994.304}, "parity.inc.find16": {"acc": 0.998, "reasoning_bytes": 128.0, "flops_per_problem": 7331069952.0}, "parity.inc.find20": {"acc": 0.852, "reasoning_bytes": 146.912, "flops_per_problem": 8342934257.664}, "parity.inc.find24": {"acc": 0.83, "reasoning_bytes": 169.12, "flops_per_problem": 9500360048.64}, "inc.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 119.0, "flops_per_problem": 6403645440.0}, "inc.runmax.sumd7": {"acc": 0.998, "reasoning_bytes": 134.696, "flops_per_problem": 7140992090.112}, "inc.runmax.sumd8": {"acc": 0.886, "reasoning_bytes": 135.632, "flops_per_problem": 7226491797.504}, "sumd.rev.cmp6": {"acc": 0.53, "reasoning_bytes": 81.118, "flops_per_problem": 4748943458.304}, "sumd.rev.cmp7": {"acc": 0.302, "reasoning_bytes": 85.238, "flops_per_problem": 4982831087.616}, "sumd.rev.cmp8": {"acc": 0.146, "reasoning_bytes": 88.898, "flops_per_problem": 5194018897.92}, "runmax.runmax.count12": {"acc": 1.0, "reasoning_bytes": 105.012, "flops_per_problem": 6315849252.864}, "runmax.runmax.count14": {"acc": 1.0, "reasoning_bytes": 117.036, "flops_per_problem": 6935192174.592}, "runmax.runmax.count16": {"acc": 1.0, "reasoning_bytes": 128.388, "flops_per_problem": 7524857511.936}, "count.count.count16": {"acc": 1.0, "reasoning_bytes": 111.11, "flops_per_problem": 6850134097.92}, "count.count.count18": {"acc": 1.0, "reasoning_bytes": 120.13, "flops_per_problem": 7336811151.36}, "count.count.count20": {"acc": 0.996, "reasoning_bytes": 128.452, "flops_per_problem": 7792662380.544}, "add.sumd.rev6": {"acc": 0.918, "reasoning_bytes": 145.508, "flops_per_problem": 7794782208.0}, "add.sumd.rev7": {"acc": 0.596, "reasoning_bytes": 165.65, "flops_per_problem": 8772640948.224}, "add.sumd.rev8": {"acc": 0.034, "reasoning_bytes": 185.602, "flops_per_problem": 9742108704.768}, "add.rev.rev6": {"acc": 0.31, "reasoning_bytes": 184.52, "flops_per_problem": 9659877064.704}, "add.rev.rev7": {"acc": 0.016, "reasoning_bytes": 205.722, "flops_per_problem": 10695236124.672}, "add.rev.rev8": {"acc": 0.0, "reasoning_bytes": 232.27, "flops_per_problem": 11973138776.064}, "inc.runmax.cmp6": {"acc": 0.562, "reasoning_bytes": 104.73, "flops_per_problem": 5817601474.56}, "inc.runmax.cmp7": {"acc": 0.31, "reasoning_bytes": 121.008, "flops_per_problem": 6580651032.576}, "inc.runmax.cmp8": {"acc": 0.644, "reasoning_bytes": 127.734, "flops_per_problem": 6921854926.848}, "count.rev.cmp16": {"acc": 0.986, "reasoning_bytes": 105.334, "flops_per_problem": 6330069762.048}, "count.rev.cmp18": {"acc": 0.946, "reasoning_bytes": 113.298, "flops_per_problem": 6770198937.6}, "count.rev.cmp20": {"acc": 0.934, "reasoning_bytes": 121.4, "flops_per_problem": 7216422617.088}} +{"step": 7000, "train_loss": 1.147524118423462} +{"step": 7020, "train_loss": 1.0656445026397705} +{"step": 7040, "train_loss": 1.072460651397705} +{"step": 7060, "train_loss": 1.1427241563796997} +{"step": 7080, "train_loss": 1.1158863306045532} +{"step": 7100, "train_loss": 1.000738501548767} +{"step": 7120, "train_loss": 1.1529297828674316} +{"step": 7140, "train_loss": 1.0322222709655762} +{"step": 7160, "train_loss": 1.0651233196258545} +{"step": 7180, "train_loss": 1.1316102743148804} +{"step": 7200, "train_loss": 1.1442246437072754} +{"step": 7220, "train_loss": 1.0018882751464844} +{"step": 7240, "train_loss": 1.0772818326950073} +{"step": 7260, "train_loss": 1.0546643733978271} +{"step": 7280, "train_loss": 1.0899301767349243} +{"step": 7300, "train_loss": 1.008373498916626} +{"step": 7320, "train_loss": 1.147033929824829} +{"step": 7340, "train_loss": 1.0857317447662354} +{"step": 7360, "train_loss": 1.0631178617477417} +{"step": 7380, "train_loss": 1.1346921920776367} +{"step": 7400, "train_loss": 1.0703548192977905} +{"step": 7420, "train_loss": 1.0609440803527832} +{"step": 7440, "train_loss": 1.0710490942001343} +{"step": 7460, "train_loss": 1.1043835878372192} +{"step": 7480, "train_loss": 1.1187763214111328} +{"step": 7500, "train_loss": 1.0514012575149536} +{"step": 7520, "train_loss": 1.0875076055526733} +{"step": 7540, "train_loss": 1.0845738649368286} +{"step": 7560, "train_loss": 1.1652507781982422} +{"step": 7580, "train_loss": 1.0698219537734985} +{"step": 7600, "train_loss": 1.0668933391571045} +{"step": 7620, "train_loss": 1.1016545295715332} +{"step": 7640, "train_loss": 1.0571264028549194} +{"step": 7660, "train_loss": 1.0631569623947144} +{"step": 7680, "train_loss": 1.059651255607605} +{"step": 7700, "train_loss": 1.1253612041473389} +{"step": 7720, "train_loss": 1.072218894958496} +{"step": 7740, "train_loss": 1.0504556894302368} +{"step": 7760, "train_loss": 1.0766918659210205} +{"step": 7780, "train_loss": 1.065688133239746} +{"step": 7800, "train_loss": 1.1053658723831177} +{"step": 7820, "train_loss": 1.0426825284957886} +{"step": 7840, "train_loss": 1.061887264251709} +{"step": 7860, "train_loss": 1.0633180141448975} +{"step": 7880, "train_loss": 1.1237766742706299} +{"step": 7900, "train_loss": 1.0736147165298462} +{"step": 7920, "train_loss": 1.0708861351013184} +{"step": 7940, "train_loss": 0.9933505654335022} +{"step": 7960, "train_loss": 1.0408480167388916} +{"step": 7980, "train_loss": 1.0103909969329834} +{"step": 8000, "tokens": 262144000, "val_loss": 1.860171616077423, "val_bpb": 0.6705616467725938, "lr": 0.00020868460938776225, "elapsed": 1352.9818439483643, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.864, "reasoning_bytes": 78.992, "flops_per_problem": 4926214029.312}, "add9": {"acc": 0.472, "reasoning_bytes": 88.928, "flops_per_problem": 5499627356.16}, "add10": {"acc": 0.0, "reasoning_bytes": 98.868, "flops_per_problem": 6075248836.608}, "reach14": {"acc": 0.564, "reasoning_bytes": 7.866, "flops_per_problem": 4631204708.352}, "reach16": {"acc": 0.508, "reasoning_bytes": 8.832, "flops_per_problem": 5204883013.632}, "reach18": {"acc": 0.51, "reasoning_bytes": 9.536, "flops_per_problem": 5781034450.944}, "parity24": {"acc": 0.512, "reasoning_bytes": 147.136, "flops_per_problem": 8043950260.224}, "parity28": {"acc": 0.52, "reasoning_bytes": 172.652, "flops_per_problem": 9351177191.424}, "parity32": {"acc": 0.342, "reasoning_bytes": 196.316, "flops_per_problem": 10610178048.0}, "cmp8": {"acc": 0.984, "reasoning_bytes": 5.756, "flops_per_problem": 1358279442.432}, "cmp9": {"acc": 0.976, "reasoning_bytes": 5.676, "flops_per_problem": 1443072540.672}, "cmp10": {"acc": 0.96, "reasoning_bytes": 5.824, "flops_per_problem": 1537846493.184}, "runmax12": {"acc": 1.0, "reasoning_bytes": 71.012, "flops_per_problem": 4151858724.864}, "runmax14": {"acc": 0.998, "reasoning_bytes": 83.0, "flops_per_problem": 4769611776.0}, "runmax16": {"acc": 0.992, "reasoning_bytes": 94.892, "flops_per_problem": 5383125172.224}, "count16": {"acc": 0.97, "reasoning_bytes": 78.98, "flops_per_problem": 4724565442.56}, "count18": {"acc": 0.926, "reasoning_bytes": 88.74, "flops_per_problem": 5243923169.28}, "count20": {"acc": 0.77, "reasoning_bytes": 97.78, "flops_per_problem": 5731483484.16}, "brackets16": {"acc": 0.886, "reasoning_bytes": 50.672, "flops_per_problem": 3518560272.384}, "brackets18": {"acc": 0.702, "reasoning_bytes": 47.492, "flops_per_problem": 3466447847.424}, "brackets20": {"acc": 0.614, "reasoning_bytes": 50.406, "flops_per_problem": 3683465183.232}, "sumd8": {"acc": 0.882, "reasoning_bytes": 59.398, "flops_per_problem": 3414600400.896}, "sumd9": {"acc": 0.646, "reasoning_bytes": 68.002, "flops_per_problem": 3836181086.208}, "sumd10": {"acc": 0.348, "reasoning_bytes": 77.48, "flops_per_problem": 4297066905.6}, "inc8": {"acc": 0.96, "reasoning_bytes": 63.0, "flops_per_problem": 3797140930.56}, "inc9": {"acc": 0.77, "reasoning_bytes": 71.0, "flops_per_problem": 4236033540.096}, "inc10": {"acc": 0.016, "reasoning_bytes": 79.024, "flops_per_problem": 4676427694.08}, "add.cmp6": {"acc": 0.996, "reasoning_bytes": 92.296, "flops_per_problem": 5517645889.536}, "add.cmp7": {"acc": 0.968, "reasoning_bytes": 105.104, "flops_per_problem": 6213037621.248}, "add.cmp8": {"acc": 0.872, "reasoning_bytes": 118.286, "flops_per_problem": 6934573891.584}, "add.runmax6": {"acc": 1.0, "reasoning_bytes": 120.676, "flops_per_problem": 6565988892.672}, "add.runmax7": {"acc": 0.972, "reasoning_bytes": 138.69, "flops_per_problem": 7449868615.68}, "add.runmax8": {"acc": 0.502, "reasoning_bytes": 156.43, "flops_per_problem": 8321647656.96}, "add.count6": {"acc": 0.93, "reasoning_bytes": 115.518, "flops_per_problem": 6382358839.296}, "add.count7": {"acc": 0.774, "reasoning_bytes": 132.106, "flops_per_problem": 7206353436.672}, "add.count8": {"acc": 0.282, "reasoning_bytes": 149.552, "flops_per_problem": 8084668612.608}, "add.find6": {"acc": 0.898, "reasoning_bytes": 107.992, "flops_per_problem": 6005824487.424}, "add.find7": {"acc": 0.732, "reasoning_bytes": 123.302, "flops_per_problem": 6770287263.744}, "add.find8": {"acc": 0.356, "reasoning_bytes": 142.958, "flops_per_problem": 7740019998.72}, "add.rev6": {"acc": 0.878, "reasoning_bytes": 122.204, "flops_per_problem": 6745644269.568}, "add.rev7": {"acc": 0.298, "reasoning_bytes": 138.45, "flops_per_problem": 7572288651.264}, "add.rev8": {"acc": 0.002, "reasoning_bytes": 158.912, "flops_per_problem": 8583887978.496}, "add.sumd6": {"acc": 0.932, "reasoning_bytes": 126.32, "flops_per_problem": 6770905546.752}, "add.sumd7": {"acc": 0.77, "reasoning_bytes": 146.184, "flops_per_problem": 7736575279.104}, "add.sumd8": {"acc": 0.07, "reasoning_bytes": 165.128, "flops_per_problem": 8661879963.648}, "add.inc6": {"acc": 0.462, "reasoning_bytes": 130.724, "flops_per_problem": 7145320071.168}, "add.inc7": {"acc": 0.098, "reasoning_bytes": 147.014, "flops_per_problem": 7998373969.92}, "add.inc8": {"acc": 0.0, "reasoning_bytes": 161.584, "flops_per_problem": 8763101724.672}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5122916352.0}, "runmax.cmp14": {"acc": 0.998, "reasoning_bytes": 98.316, "flops_per_problem": 5710991818.752}, "runmax.cmp16": {"acc": 0.998, "reasoning_bytes": 105.456, "flops_per_problem": 6114642296.832}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.runmax14": {"acc": 1.0, "reasoning_bytes": 99.844, "flops_per_problem": 5822636064.768}, "runmax.runmax16": {"acc": 0.984, "reasoning_bytes": 106.504, "flops_per_problem": 6207384748.032}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5255405568.0}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 100.0, "flops_per_problem": 5873688576.0}, "runmax.count16": {"acc": 0.996, "reasoning_bytes": 108.228, "flops_per_problem": 6325565128.704}, "runmax.find12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.find14": {"acc": 1.0, "reasoning_bytes": 99.688, "flops_per_problem": 5815746625.536}, "runmax.find16": {"acc": 0.996, "reasoning_bytes": 106.56, "flops_per_problem": 6207738052.608}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 83.0, "flops_per_problem": 4857937920.0}, "runmax.rev14": {"acc": 1.0, "reasoning_bytes": 94.916, "flops_per_problem": 5472511229.952}, "runmax.rev16": {"acc": 0.994, "reasoning_bytes": 102.956, "flops_per_problem": 5915908472.832}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 86.0, "flops_per_problem": 5034590208.0}, "runmax.sumd14": {"acc": 0.998, "reasoning_bytes": 97.904, "flops_per_problem": 5648633561.088}, "runmax.sumd16": {"acc": 0.994, "reasoning_bytes": 106.124, "flops_per_problem": 6099980156.928}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5065769336.832}, "runmax.inc14": {"acc": 0.982, "reasoning_bytes": 98.832, "flops_per_problem": 5685023932.416}, "runmax.inc16": {"acc": 0.586, "reasoning_bytes": 107.19, "flops_per_problem": 6340757225.472}, "count.cmp16": {"acc": 0.996, "reasoning_bytes": 94.96, "flops_per_problem": 5695269765.12}, "count.cmp18": {"acc": 0.982, "reasoning_bytes": 103.992, "flops_per_problem": 6182565101.568}, "count.cmp20": {"acc": 0.942, "reasoning_bytes": 110.878, "flops_per_problem": 6575086485.504}, "count.runmax16": {"acc": 0.982, "reasoning_bytes": 95.87, "flops_per_problem": 5779621232.64}, "count.runmax18": {"acc": 0.912, "reasoning_bytes": 104.78, "flops_per_problem": 6261440348.16}, "count.runmax20": {"acc": 0.78, "reasoning_bytes": 111.66, "flops_per_problem": 6653608427.52}, "count.count16": {"acc": 1.0, "reasoning_bytes": 95.89, "flops_per_problem": 5824667566.08}, "count.count18": {"acc": 1.0, "reasoning_bytes": 105.65, "flops_per_problem": 6344025292.8}, "count.count20": {"acc": 0.998, "reasoning_bytes": 112.86, "flops_per_problem": 6750767185.92}, "count.find16": {"acc": 0.994, "reasoning_bytes": 96.0, "flops_per_problem": 5785362432.0}, "count.find18": {"acc": 0.972, "reasoning_bytes": 105.57, "flops_per_problem": 6296329175.04}, "count.find20": {"acc": 0.946, "reasoning_bytes": 112.28, "flops_per_problem": 6680989532.16}, "count.rev16": {"acc": 0.974, "reasoning_bytes": 90.82, "flops_per_problem": 5424108503.04}, "count.rev18": {"acc": 0.888, "reasoning_bytes": 99.27, "flops_per_problem": 5885612605.44}, "count.rev20": {"acc": 0.75, "reasoning_bytes": 106.25, "flops_per_problem": 6282196992.0}, "count.sumd16": {"acc": 0.982, "reasoning_bytes": 93.94, "flops_per_problem": 5606060359.68}, "count.sumd18": {"acc": 0.906, "reasoning_bytes": 102.89, "flops_per_problem": 6090264281.088}, "count.sumd20": {"acc": 0.75, "reasoning_bytes": 109.582, "flops_per_problem": 6474571333.632}, "count.inc16": {"acc": 0.982, "reasoning_bytes": 94.85, "flops_per_problem": 5602085683.2}, "count.inc18": {"acc": 0.91, "reasoning_bytes": 103.7, "flops_per_problem": 6081255014.4}, "count.inc20": {"acc": 0.756, "reasoning_bytes": 110.53, "flops_per_problem": 6471214940.16}, "parity.cmp16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6359482368.0}, "parity.cmp20": {"acc": 0.95, "reasoning_bytes": 132.096, "flops_per_problem": 7467798822.912}, "parity.cmp24": {"acc": 0.92, "reasoning_bytes": 152.856, "flops_per_problem": 8561276485.632}, "parity.runmax16": {"acc": 0.998, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.runmax20": {"acc": 0.66, "reasoning_bytes": 134.812, "flops_per_problem": 7631908798.464}, "parity.runmax24": {"acc": 0.324, "reasoning_bytes": 155.248, "flops_per_problem": 8711077625.856}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6491971584.0}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 135.316, "flops_per_problem": 7698330058.752}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 155.464, "flops_per_problem": 8764779921.408}, "parity.find16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.find20": {"acc": 0.91, "reasoning_bytes": 134.548, "flops_per_problem": 7620249747.456}, "parity.find24": {"acc": 0.828, "reasoning_bytes": 155.356, "flops_per_problem": 8715847237.632}, "parity.rev16": {"acc": 0.988, "reasoning_bytes": 107.0, "flops_per_problem": 6094503936.0}, "parity.rev20": {"acc": 0.668, "reasoning_bytes": 129.848, "flops_per_problem": 7280194093.056}, "parity.rev24": {"acc": 0.384, "reasoning_bytes": 150.092, "flops_per_problem": 8350883610.624}, "parity.sumd16": {"acc": 0.998, "reasoning_bytes": 110.0, "flops_per_problem": 6271156224.0}, "parity.sumd20": {"acc": 0.674, "reasoning_bytes": 133.22, "flops_per_problem": 7473275043.84}, "parity.sumd24": {"acc": 0.354, "reasoning_bytes": 154.736, "flops_per_problem": 8600139988.992}, "parity.inc16": {"acc": 0.994, "reasoning_bytes": 111.0, "flops_per_problem": 6271156224.0}, "parity.inc20": {"acc": 0.688, "reasoning_bytes": 134.1, "flops_per_problem": 7467975475.2}, "parity.inc24": {"acc": 0.342, "reasoning_bytes": 154.908, "flops_per_problem": 8563572965.376}, "sumd.cmp6": {"acc": 0.984, "reasoning_bytes": 62.09, "flops_per_problem": 3713496072.192}, "sumd.cmp7": {"acc": 0.976, "reasoning_bytes": 70.1, "flops_per_problem": 4111582003.2}, "sumd.cmp8": {"acc": 0.982, "reasoning_bytes": 77.632, "flops_per_problem": 4488293007.36}, "sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.992, "reasoning_bytes": 75.48, "flops_per_problem": 4349179330.56}, "sumd.runmax8": {"acc": 0.894, "reasoning_bytes": 83.502, "flops_per_problem": 4747618566.144}, "sumd.count6": {"acc": 0.974, "reasoning_bytes": 66.428, "flops_per_problem": 3949415202.816}, "sumd.count7": {"acc": 0.962, "reasoning_bytes": 74.434, "flops_per_problem": 4347147829.248}, "sumd.count8": {"acc": 0.912, "reasoning_bytes": 82.36, "flops_per_problem": 4741347409.92}, "sumd.find6": {"acc": 0.996, "reasoning_bytes": 66.244, "flops_per_problem": 3897037799.424}, "sumd.find7": {"acc": 0.99, "reasoning_bytes": 74.408, "flops_per_problem": 4301836517.376}, "sumd.find8": {"acc": 0.962, "reasoning_bytes": 82.278, "flops_per_problem": 4693562966.016}, "sumd.rev6": {"acc": 1.0, "reasoning_bytes": 61.544, "flops_per_problem": 3601145217.024}, "sumd.rev7": {"acc": 0.992, "reasoning_bytes": 69.48, "flops_per_problem": 3995874754.56}, "sumd.rev8": {"acc": 0.932, "reasoning_bytes": 77.536, "flops_per_problem": 4395727208.448}, "sumd.sumd6": {"acc": 0.998, "reasoning_bytes": 65.776, "flops_per_problem": 3797052604.416}, "sumd.sumd7": {"acc": 0.976, "reasoning_bytes": 73.766, "flops_per_problem": 4196551753.728}, "sumd.sumd8": {"acc": 0.792, "reasoning_bytes": 81.676, "flops_per_problem": 4588896485.376}, "sumd.inc6": {"acc": 0.988, "reasoning_bytes": 68.586, "flops_per_problem": 3911876591.616}, "sumd.inc7": {"acc": 0.868, "reasoning_bytes": 76.456, "flops_per_problem": 4305457889.28}, "sumd.inc8": {"acc": 0.442, "reasoning_bytes": 84.518, "flops_per_problem": 4707253518.336}, "inc.cmp6": {"acc": 0.99, "reasoning_bytes": 78.61, "flops_per_problem": 4575735889.92}, "inc.cmp7": {"acc": 0.966, "reasoning_bytes": 89.746, "flops_per_problem": 5155862003.712}, "inc.cmp8": {"acc": 0.778, "reasoning_bytes": 100.19, "flops_per_problem": 5705427271.68}, "inc.runmax6": {"acc": 0.998, "reasoning_bytes": 103.984, "flops_per_problem": 5519677390.848}, "inc.runmax7": {"acc": 0.988, "reasoning_bytes": 119.572, "flops_per_problem": 6252254429.184}, "inc.runmax8": {"acc": 0.874, "reasoning_bytes": 124.976, "flops_per_problem": 6535074742.272}, "inc.count6": {"acc": 0.916, "reasoning_bytes": 98.902, "flops_per_problem": 5339403730.944}, "inc.count7": {"acc": 0.838, "reasoning_bytes": 113.014, "flops_per_problem": 6007679336.448}, "inc.count8": {"acc": 0.698, "reasoning_bytes": 113.788, "flops_per_problem": 6085141364.736}, "inc.find6": {"acc": 0.956, "reasoning_bytes": 91.968, "flops_per_problem": 4989013917.696}, "inc.find7": {"acc": 0.84, "reasoning_bytes": 102.75, "flops_per_problem": 5509343232.0}, "inc.find8": {"acc": 0.686, "reasoning_bytes": 107.51, "flops_per_problem": 5764429135.872}, "inc.rev6": {"acc": 0.986, "reasoning_bytes": 103.85, "flops_per_problem": 5601467400.192}, "inc.rev7": {"acc": 0.762, "reasoning_bytes": 121.812, "flops_per_problem": 6475366268.928}, "inc.rev8": {"acc": 0.0, "reasoning_bytes": 131.756, "flops_per_problem": 6967254564.864}, "inc.sumd6": {"acc": 0.966, "reasoning_bytes": 109.604, "flops_per_problem": 5723357478.912}, "inc.sumd7": {"acc": 0.75, "reasoning_bytes": 127.236, "flops_per_problem": 6545673879.552}, "inc.sumd8": {"acc": 0.168, "reasoning_bytes": 142.166, "flops_per_problem": 7250958139.392}, "inc.inc6": {"acc": 0.91, "reasoning_bytes": 112.94, "flops_per_problem": 6006796075.008}, "inc.inc7": {"acc": 0.452, "reasoning_bytes": 130.348, "flops_per_problem": 6878221811.712}, "inc.inc8": {"acc": 0.01, "reasoning_bytes": 143.51, "flops_per_problem": 7543759306.752}, "count.inc.cmp16": {"acc": 0.612, "reasoning_bytes": 111.096, "flops_per_problem": 6584537382.912}, "count.inc.cmp18": {"acc": 0.622, "reasoning_bytes": 120.174, "flops_per_problem": 7074305851.392}, "count.inc.cmp20": {"acc": 0.592, "reasoning_bytes": 126.986, "flops_per_problem": 7464442429.44}, "inc.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 160.99, "flops_per_problem": 8350971936.768}, "inc.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 185.336, "flops_per_problem": 9488965976.064}, "inc.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 191.292, "flops_per_problem": 9815949361.152}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7551885312.0}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 150.336, "flops_per_problem": 8670800904.192}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 170.784, "flops_per_problem": 9750499688.448}, "add.count.find6": {"acc": 0.0, "reasoning_bytes": 136.328, "flops_per_problem": 7642684588.032}, "add.count.find7": {"acc": 0.002, "reasoning_bytes": 152.496, "flops_per_problem": 8477543301.12}, "add.count.find8": {"acc": 0.002, "reasoning_bytes": 140.992, "flops_per_problem": 8093412900.864}, "runmax.inc.find12": {"acc": 0.878, "reasoning_bytes": 105.428, "flops_per_problem": 6157568802.816}, "runmax.inc.find14": {"acc": 0.898, "reasoning_bytes": 116.428, "flops_per_problem": 6731688738.816}, "runmax.inc.find16": {"acc": 0.838, "reasoning_bytes": 123.776, "flops_per_problem": 7144525135.872}, "parity.sumd.rev16": {"acc": 0.996, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.sumd.rev20": {"acc": 0.504, "reasoning_bytes": 142.94, "flops_per_problem": 8079192391.68}, "parity.sumd.rev24": {"acc": 0.318, "reasoning_bytes": 163.868, "flops_per_problem": 9180089450.496}, "parity.rev.sumd16": {"acc": 0.998, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.rev.sumd20": {"acc": 0.548, "reasoning_bytes": 143.24, "flops_per_problem": 8092441313.28}, "parity.rev.sumd24": {"acc": 0.328, "reasoning_bytes": 164.096, "flops_per_problem": 9190158630.912}, "count.inc.sumd16": {"acc": 0.97, "reasoning_bytes": 109.78, "flops_per_problem": 6482255708.16}, "count.inc.sumd18": {"acc": 0.862, "reasoning_bytes": 117.34, "flops_per_problem": 6904454676.48}, "count.inc.sumd20": {"acc": 0.748, "reasoning_bytes": 124.66, "flops_per_problem": 7316054507.52}, "inc.sumd.rev6": {"acc": 0.962, "reasoning_bytes": 128.496, "flops_per_problem": 6734515175.424}, "inc.sumd.rev7": {"acc": 0.716, "reasoning_bytes": 145.814, "flops_per_problem": 7543494328.32}, "inc.sumd.rev8": {"acc": 0.122, "reasoning_bytes": 147.54, "flops_per_problem": 7663971188.736}, "count.count.cmp16": {"acc": 1.0, "reasoning_bytes": 111.9, "flops_per_problem": 6796696780.8}, "count.count.cmp18": {"acc": 0.998, "reasoning_bytes": 121.42, "flops_per_problem": 7305455370.24}, "count.count.cmp20": {"acc": 0.994, "reasoning_bytes": 128.97, "flops_per_problem": 7727212707.84}, "parity.rev.find16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7154417664.0}, "parity.rev.find20": {"acc": 0.87, "reasoning_bytes": 144.88, "flops_per_problem": 8253194895.36}, "parity.rev.find24": {"acc": 0.836, "reasoning_bytes": 165.652, "flops_per_problem": 9347202514.944}, "count.sumd.cmp16": {"acc": 0.998, "reasoning_bytes": 109.86, "flops_per_problem": 6574114897.92}, "count.sumd.cmp18": {"acc": 0.976, "reasoning_bytes": 118.19, "flops_per_problem": 7030319431.68}, "count.sumd.cmp20": {"acc": 0.942, "reasoning_bytes": 125.08, "flops_per_problem": 7422929141.76}, "sumd.count.count6": {"acc": 1.0, "reasoning_bytes": 83.476, "flops_per_problem": 5055611830.272}, "sumd.count.count7": {"acc": 1.0, "reasoning_bytes": 91.512, "flops_per_problem": 5454669348.864}, "sumd.count.count8": {"acc": 0.998, "reasoning_bytes": 97.774, "flops_per_problem": 5775381577.728}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 99.0, "flops_per_problem": 5772378488.832}, "runmax.rev.inc14": {"acc": 1.0, "reasoning_bytes": 110.808, "flops_per_problem": 6385538580.48}, "runmax.rev.inc16": {"acc": 0.994, "reasoning_bytes": 118.488, "flops_per_problem": 6815510249.472}, "parity.sumd.find16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.sumd.find20": {"acc": 0.856, "reasoning_bytes": 147.34, "flops_per_problem": 8405999124.48}, "parity.sumd.find24": {"acc": 0.82, "reasoning_bytes": 168.76, "flops_per_problem": 9528624414.72}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 115.652, "flops_per_problem": 6785744338.944}, "runmax.runmax.cmp16": {"acc": 1.0, "reasoning_bytes": 122.216, "flops_per_problem": 7163956887.552}, "count.runmax.count16": {"acc": 1.0, "reasoning_bytes": 112.71, "flops_per_problem": 6876631941.12}, "count.runmax.count18": {"acc": 1.0, "reasoning_bytes": 121.68, "flops_per_problem": 7361100840.96}, "count.runmax.count20": {"acc": 1.0, "reasoning_bytes": 128.96, "flops_per_problem": 7770934149.12}, "inc.inc.sumd6": {"acc": 0.686, "reasoning_bytes": 175.906, "flops_per_problem": 8827933114.368}, "inc.inc.sumd7": {"acc": 0.16, "reasoning_bytes": 203.586, "flops_per_problem": 10089407102.976}, "inc.inc.sumd8": {"acc": 0.034, "reasoning_bytes": 205.234, "flops_per_problem": 10214476922.88}, "add.sumd.find6": {"acc": 0.966, "reasoning_bytes": 150.524, "flops_per_problem": 8104983625.728}, "add.sumd.find7": {"acc": 0.882, "reasoning_bytes": 169.584, "flops_per_problem": 9034969595.904}, "add.sumd.find8": {"acc": 0.68, "reasoning_bytes": 188.174, "flops_per_problem": 9944375574.528}, "sumd.rev.rev6": {"acc": 0.998, "reasoning_bytes": 80.5, "flops_per_problem": 4614864371.712}, "sumd.rev.rev7": {"acc": 0.99, "reasoning_bytes": 88.48, "flops_per_problem": 5011625410.56}, "sumd.rev.rev8": {"acc": 0.802, "reasoning_bytes": 95.738, "flops_per_problem": 5376235732.992}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.648, "flops_per_problem": 6343936966.656}, "runmax.inc.runmax14": {"acc": 1.0, "reasoning_bytes": 122.04, "flops_per_problem": 6979531898.88}, "runmax.inc.runmax16": {"acc": 0.964, "reasoning_bytes": 129.116, "flops_per_problem": 7380355940.352}, "parity.inc.find16": {"acc": 1.0, "reasoning_bytes": 128.0, "flops_per_problem": 7331069952.0}, "parity.inc.find20": {"acc": 0.886, "reasoning_bytes": 147.956, "flops_per_problem": 8389040504.832}, "parity.inc.find24": {"acc": 0.818, "reasoning_bytes": 168.644, "flops_per_problem": 9479338426.368}, "inc.runmax.sumd6": {"acc": 0.998, "reasoning_bytes": 118.984, "flops_per_problem": 6402938830.848}, "inc.runmax.sumd7": {"acc": 0.99, "reasoning_bytes": 134.574, "flops_per_problem": 7135604195.328}, "inc.runmax.sumd8": {"acc": 0.848, "reasoning_bytes": 136.654, "flops_per_problem": 7271626457.088}, "sumd.rev.cmp6": {"acc": 0.834, "reasoning_bytes": 80.896, "flops_per_problem": 4722798919.68}, "sumd.rev.cmp7": {"acc": 0.762, "reasoning_bytes": 88.82, "flops_per_problem": 5120001589.248}, "sumd.rev.cmp8": {"acc": 0.518, "reasoning_bytes": 94.24, "flops_per_problem": 5412537778.176}, "runmax.runmax.count12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6315319296.0}, "runmax.runmax.count14": {"acc": 1.0, "reasoning_bytes": 116.964, "flops_per_problem": 6932012433.408}, "runmax.runmax.count16": {"acc": 1.0, "reasoning_bytes": 124.716, "flops_per_problem": 7362690711.552}, "count.count.count16": {"acc": 1.0, "reasoning_bytes": 112.74, "flops_per_problem": 6922119905.28}, "count.count.count18": {"acc": 1.0, "reasoning_bytes": 122.45, "flops_per_problem": 7439269478.4}, "count.count.count20": {"acc": 1.0, "reasoning_bytes": 130.31, "flops_per_problem": 7874717368.32}, "add.sumd.rev6": {"acc": 0.892, "reasoning_bytes": 145.264, "flops_per_problem": 7784183070.72}, "add.sumd.rev7": {"acc": 0.678, "reasoning_bytes": 164.952, "flops_per_problem": 8742080102.4}, "add.sumd.rev8": {"acc": 0.05, "reasoning_bytes": 184.006, "flops_per_problem": 9677630619.648}, "add.rev.rev6": {"acc": 0.408, "reasoning_bytes": 184.816, "flops_per_problem": 9690526236.672}, "add.rev.rev7": {"acc": 0.092, "reasoning_bytes": 205.23, "flops_per_problem": 10705305305.088}, "add.rev.rev8": {"acc": 0.0, "reasoning_bytes": 234.96, "flops_per_problem": 12131419226.112}, "inc.runmax.cmp6": {"acc": 0.952, "reasoning_bytes": 104.006, "flops_per_problem": 5785627410.432}, "inc.runmax.cmp7": {"acc": 0.898, "reasoning_bytes": 120.104, "flops_per_problem": 6540727615.488}, "inc.runmax.cmp8": {"acc": 0.908, "reasoning_bytes": 129.72, "flops_per_problem": 7009562787.84}, "count.rev.cmp16": {"acc": 0.998, "reasoning_bytes": 106.78, "flops_per_problem": 6393929564.16}, "count.rev.cmp18": {"acc": 0.978, "reasoning_bytes": 115.18, "flops_per_problem": 6853313839.104}, "count.rev.cmp20": {"acc": 0.944, "reasoning_bytes": 122.13, "flops_per_problem": 7248661659.648}} +{"step": 8000, "train_loss": 1.0603001117706299} +{"step": 8020, "train_loss": 1.006181001663208} +{"step": 8040, "train_loss": 1.0435529947280884} +{"step": 8060, "train_loss": 1.0600950717926025} +{"step": 8080, "train_loss": 1.0645180940628052} +{"step": 8100, "train_loss": 1.025374174118042} +{"step": 8120, "train_loss": 1.0805761814117432} +{"step": 8140, "train_loss": 1.0898888111114502} +{"step": 8160, "train_loss": 1.0994092226028442} +{"step": 8180, "train_loss": 1.0409610271453857} +{"step": 8200, "train_loss": 1.07025146484375} +{"step": 8220, "train_loss": 1.0316426753997803} +{"step": 8240, "train_loss": 1.0576026439666748} +{"step": 8260, "train_loss": 1.0571227073669434} +{"step": 8280, "train_loss": 1.079402208328247} +{"step": 8300, "train_loss": 1.0616545677185059} +{"step": 8320, "train_loss": 1.0032542943954468} +{"step": 8340, "train_loss": 1.128025770187378} +{"step": 8360, "train_loss": 1.0240869522094727} +{"step": 8380, "train_loss": 1.0697588920593262} +{"step": 8400, "train_loss": 1.0791466236114502} +{"step": 8420, "train_loss": 1.0738234519958496} +{"step": 8440, "train_loss": 1.029140591621399} +{"step": 8460, "train_loss": 1.088396430015564} +{"step": 8480, "train_loss": 1.0696260929107666} +{"step": 8500, "train_loss": 1.0366837978363037} +{"step": 8520, "train_loss": 1.1038243770599365} +{"step": 8540, "train_loss": 1.042742133140564} +{"step": 8560, "train_loss": 1.0020071268081665} +{"step": 8580, "train_loss": 1.0890167951583862} +{"step": 8600, "train_loss": 1.0561392307281494} +{"step": 8620, "train_loss": 1.0207359790802002} +{"step": 8640, "train_loss": 1.028841257095337} +{"step": 8660, "train_loss": 1.0438334941864014} +{"step": 8680, "train_loss": 1.150923490524292} +{"step": 8700, "train_loss": 1.0882103443145752} +{"step": 8720, "train_loss": 1.1508557796478271} +{"step": 8740, "train_loss": 1.16715669631958} +{"step": 8760, "train_loss": 1.0641475915908813} +{"step": 8780, "train_loss": 1.1187613010406494} +{"step": 8800, "train_loss": 1.0989320278167725} +{"step": 8820, "train_loss": 1.1005961894989014} +{"step": 8840, "train_loss": 1.0763187408447266} +{"step": 8860, "train_loss": 0.9895661473274231} +{"step": 8880, "train_loss": 1.0847498178482056} +{"step": 8900, "train_loss": 1.0311729907989502} +{"step": 8920, "train_loss": 1.019247055053711} +{"step": 8940, "train_loss": 1.0507588386535645} +{"step": 8960, "train_loss": 1.1174674034118652} +{"step": 8980, "train_loss": 1.0348984003067017} +{"step": 9000, "tokens": 294912000, "val_loss": 1.8400626480579376, "val_bpb": 0.6633126904970011, "lr": 0.00015022524874031755, "elapsed": 1516.1385769844055, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.78, "reasoning_bytes": 79.0, "flops_per_problem": 4927980552.192}, "add9": {"acc": 0.15, "reasoning_bytes": 89.0, "flops_per_problem": 5500157313.024}, "add10": {"acc": 0.0, "reasoning_bytes": 99.0, "flops_per_problem": 6069595963.392}, "reach14": {"acc": 0.522, "reasoning_bytes": 8.96, "flops_per_problem": 4681197305.856}, "reach16": {"acc": 0.49, "reasoning_bytes": 8.96, "flops_per_problem": 5209299320.832}, "reach18": {"acc": 0.534, "reasoning_bytes": 9.91, "flops_per_problem": 5781034450.944}, "parity24": {"acc": 0.644, "reasoning_bytes": 142.436, "flops_per_problem": 7836118843.392}, "parity28": {"acc": 0.498, "reasoning_bytes": 163.936, "flops_per_problem": 8962277179.392}, "parity32": {"acc": 0.502, "reasoning_bytes": 188.928, "flops_per_problem": 10242387984.384}, "cmp8": {"acc": 0.992, "reasoning_bytes": 5.84, "flops_per_problem": 1361989140.48}, "cmp9": {"acc": 0.99, "reasoning_bytes": 5.72, "flops_per_problem": 1445015715.84}, "cmp10": {"acc": 0.998, "reasoning_bytes": 5.768, "flops_per_problem": 1535461687.296}, "runmax12": {"acc": 1.0, "reasoning_bytes": 71.0, "flops_per_problem": 4151328768.0}, "runmax14": {"acc": 1.0, "reasoning_bytes": 82.832, "flops_per_problem": 4762192379.904}, "runmax16": {"acc": 0.998, "reasoning_bytes": 91.28, "flops_per_problem": 5223608156.16}, "count16": {"acc": 0.912, "reasoning_bytes": 77.56, "flops_per_problem": 4661853880.32}, "count18": {"acc": 0.824, "reasoning_bytes": 85.2, "flops_per_problem": 5087585894.4}, "count20": {"acc": 0.774, "reasoning_bytes": 94.3, "flops_per_problem": 5577795993.6}, "brackets16": {"acc": 0.928, "reasoning_bytes": 53.282, "flops_per_problem": 3633825890.304}, "brackets18": {"acc": 0.808, "reasoning_bytes": 55.82, "flops_per_problem": 3834237911.04}, "brackets20": {"acc": 0.718, "reasoning_bytes": 63.238, "flops_per_problem": 4250165723.136}, "sumd8": {"acc": 0.96, "reasoning_bytes": 58.278, "flops_per_problem": 3368582479.872}, "sumd9": {"acc": 0.568, "reasoning_bytes": 63.566, "flops_per_problem": 3646368202.752}, "sumd10": {"acc": 0.256, "reasoning_bytes": 69.456, "flops_per_problem": 3950563442.688}, "inc8": {"acc": 0.766, "reasoning_bytes": 63.0, "flops_per_problem": 3798024192.0}, "inc9": {"acc": 0.11, "reasoning_bytes": 71.0, "flops_per_problem": 4239566585.856}, "inc10": {"acc": 0.0, "reasoning_bytes": 78.888, "flops_per_problem": 4672188039.168}, "add.cmp6": {"acc": 0.992, "reasoning_bytes": 92.624, "flops_per_problem": 5532131377.152}, "add.cmp7": {"acc": 0.92, "reasoning_bytes": 105.49, "flops_per_problem": 6230084567.04}, "add.cmp8": {"acc": 0.83, "reasoning_bytes": 118.114, "flops_per_problem": 6924328058.88}, "add.runmax6": {"acc": 1.0, "reasoning_bytes": 120.832, "flops_per_problem": 6572878331.904}, "add.runmax7": {"acc": 0.956, "reasoning_bytes": 138.848, "flops_per_problem": 7456846381.056}, "add.runmax8": {"acc": 0.638, "reasoning_bytes": 156.866, "flops_per_problem": 8340902756.352}, "add.count6": {"acc": 0.996, "reasoning_bytes": 115.648, "flops_per_problem": 6388100038.656}, "add.count7": {"acc": 0.84, "reasoning_bytes": 132.114, "flops_per_problem": 7203615326.208}, "add.count8": {"acc": 0.366, "reasoning_bytes": 148.346, "flops_per_problem": 8008796454.912}, "add.find6": {"acc": 0.918, "reasoning_bytes": 107.84, "flops_per_problem": 5999111700.48}, "add.find7": {"acc": 0.82, "reasoning_bytes": 121.464, "flops_per_problem": 6689115537.408}, "add.find8": {"acc": 0.428, "reasoning_bytes": 139.958, "flops_per_problem": 7594900144.128}, "add.rev6": {"acc": 1.0, "reasoning_bytes": 123.248, "flops_per_problem": 6794576953.344}, "add.rev7": {"acc": 0.836, "reasoning_bytes": 145.462, "flops_per_problem": 7906161475.584}, "add.rev8": {"acc": 0.0, "reasoning_bytes": 157.754, "flops_per_problem": 8540254863.36}, "add.sumd6": {"acc": 1.0, "reasoning_bytes": 126.476, "flops_per_problem": 6777794985.984}, "add.sumd7": {"acc": 0.86, "reasoning_bytes": 146.328, "flops_per_problem": 7742934761.472}, "add.sumd8": {"acc": 0.098, "reasoning_bytes": 165.782, "flops_per_problem": 8690232655.872}, "add.inc6": {"acc": 0.994, "reasoning_bytes": 131.04, "flops_per_problem": 7138695610.368}, "add.inc7": {"acc": 0.892, "reasoning_bytes": 151.01, "flops_per_problem": 8152679743.488}, "add.inc8": {"acc": 0.008, "reasoning_bytes": 160.832, "flops_per_problem": 8681223389.184}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5122916352.0}, "runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 98.784, "flops_per_problem": 5731660136.448}, "runmax.cmp16": {"acc": 0.992, "reasoning_bytes": 105.468, "flops_per_problem": 6115172253.696}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.runmax14": {"acc": 1.0, "reasoning_bytes": 99.664, "flops_per_problem": 5814686711.808}, "runmax.runmax16": {"acc": 0.972, "reasoning_bytes": 106.12, "flops_per_problem": 6188129648.64}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5255405568.0}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 99.928, "flops_per_problem": 5870508834.816}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 106.828, "flops_per_problem": 6263560175.616}, "runmax.find12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.find14": {"acc": 1.0, "reasoning_bytes": 99.112, "flops_per_problem": 5790308696.064}, "runmax.find16": {"acc": 0.998, "reasoning_bytes": 106.252, "flops_per_problem": 6193959174.144}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 83.0, "flops_per_problem": 4857937920.0}, "runmax.rev14": {"acc": 1.0, "reasoning_bytes": 94.7, "flops_per_problem": 5462972006.4}, "runmax.rev16": {"acc": 0.974, "reasoning_bytes": 101.408, "flops_per_problem": 5847544037.376}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 86.0, "flops_per_problem": 5034590208.0}, "runmax.sumd14": {"acc": 1.0, "reasoning_bytes": 97.688, "flops_per_problem": 5639094337.536}, "runmax.sumd16": {"acc": 0.984, "reasoning_bytes": 104.624, "flops_per_problem": 6033735548.928}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5065769336.832}, "runmax.inc14": {"acc": 0.998, "reasoning_bytes": 97.92, "flops_per_problem": 5639624294.4}, "runmax.inc16": {"acc": 0.982, "reasoning_bytes": 105.344, "flops_per_problem": 6057848586.24}, "count.cmp16": {"acc": 0.98, "reasoning_bytes": 93.47, "flops_per_problem": 5629466787.84}, "count.cmp18": {"acc": 0.946, "reasoning_bytes": 100.73, "flops_per_problem": 6038505160.704}, "count.cmp20": {"acc": 0.944, "reasoning_bytes": 110.044, "flops_per_problem": 6538254483.456}, "count.runmax16": {"acc": 0.952, "reasoning_bytes": 94.944, "flops_per_problem": 5738726227.968}, "count.runmax18": {"acc": 0.838, "reasoning_bytes": 102.384, "flops_per_problem": 6155625627.648}, "count.runmax20": {"acc": 0.786, "reasoning_bytes": 111.148, "flops_per_problem": 6630996934.656}, "count.count16": {"acc": 1.0, "reasoning_bytes": 95.59, "flops_per_problem": 5811418644.48}, "count.count18": {"acc": 1.0, "reasoning_bytes": 102.97, "flops_per_problem": 6225668259.84}, "count.count20": {"acc": 0.998, "reasoning_bytes": 111.21, "flops_per_problem": 6677898117.12}, "count.find16": {"acc": 0.984, "reasoning_bytes": 95.22, "flops_per_problem": 5750915235.84}, "count.find18": {"acc": 0.934, "reasoning_bytes": 102.5, "flops_per_problem": 6160748544.0}, "count.find20": {"acc": 0.932, "reasoning_bytes": 111.08, "flops_per_problem": 6627993845.76}, "count.rev16": {"acc": 0.954, "reasoning_bytes": 90.14, "flops_per_problem": 5394077614.08}, "count.rev18": {"acc": 0.826, "reasoning_bytes": 97.154, "flops_per_problem": 5792163545.088}, "count.rev20": {"acc": 0.766, "reasoning_bytes": 106.094, "flops_per_problem": 6275307552.768}, "count.sumd16": {"acc": 0.966, "reasoning_bytes": 93.27, "flops_per_problem": 5576471101.44}, "count.sumd18": {"acc": 0.838, "reasoning_bytes": 100.52, "flops_per_problem": 5984979517.44}, "count.sumd20": {"acc": 0.778, "reasoning_bytes": 109.206, "flops_per_problem": 6456906104.832}, "count.inc16": {"acc": 0.952, "reasoning_bytes": 94.01, "flops_per_problem": 5564988702.72}, "count.inc18": {"acc": 0.826, "reasoning_bytes": 101.14, "flops_per_problem": 5968197550.08}, "count.inc20": {"acc": 0.788, "reasoning_bytes": 109.912, "flops_per_problem": 6443922161.664}, "parity.cmp16": {"acc": 1.0, "reasoning_bytes": 110.904, "flops_per_problem": 6355242713.088}, "parity.cmp20": {"acc": 0.934, "reasoning_bytes": 129.0, "flops_per_problem": 7331069952.0}, "parity.cmp24": {"acc": 0.914, "reasoning_bytes": 148.108, "flops_per_problem": 8351590219.776}, "parity.runmax16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.runmax20": {"acc": 0.56, "reasoning_bytes": 130.948, "flops_per_problem": 7461262688.256}, "parity.runmax24": {"acc": 0.502, "reasoning_bytes": 153.988, "flops_per_problem": 8655432155.136}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6491971584.0}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 131.212, "flops_per_problem": 7517084811.264}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 153.988, "flops_per_problem": 8699595227.136}, "parity.find16": {"acc": 1.0, "reasoning_bytes": 111.988, "flops_per_problem": 6447278555.136}, "parity.find20": {"acc": 0.852, "reasoning_bytes": 130.264, "flops_per_problem": 7431055147.008}, "parity.find24": {"acc": 0.83, "reasoning_bytes": 153.988, "flops_per_problem": 8655432155.136}, "parity.rev16": {"acc": 1.0, "reasoning_bytes": 107.0, "flops_per_problem": 6094503936.0}, "parity.rev20": {"acc": 0.492, "reasoning_bytes": 125.768, "flops_per_problem": 7100008759.296}, "parity.rev24": {"acc": 0.434, "reasoning_bytes": 148.976, "flops_per_problem": 8301597622.272}, "parity.sumd16": {"acc": 1.0, "reasoning_bytes": 110.0, "flops_per_problem": 6271156224.0}, "parity.sumd20": {"acc": 0.618, "reasoning_bytes": 130.136, "flops_per_problem": 7337076129.792}, "parity.sumd24": {"acc": 0.484, "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": 0.54, "reasoning_bytes": 130.08, "flops_per_problem": 7290439925.76}, "parity.inc24": {"acc": 0.43, "reasoning_bytes": 152.992, "flops_per_problem": 8478956519.424}, "sumd.cmp6": {"acc": 1.0, "reasoning_bytes": 62.088, "flops_per_problem": 3713407746.048}, "sumd.cmp7": {"acc": 0.99, "reasoning_bytes": 69.524, "flops_per_problem": 4086144073.728}, "sumd.cmp8": {"acc": 0.932, "reasoning_bytes": 70.85, "flops_per_problem": 4188779053.056}, "sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.974, "reasoning_bytes": 75.276, "flops_per_problem": 4340170063.872}, "sumd.runmax8": {"acc": 0.52, "reasoning_bytes": 79.01, "flops_per_problem": 4549238046.72}, "sumd.count6": {"acc": 0.998, "reasoning_bytes": 66.428, "flops_per_problem": 3949415202.816}, "sumd.count7": {"acc": 0.976, "reasoning_bytes": 74.122, "flops_per_problem": 4333368950.784}, "sumd.count8": {"acc": 0.568, "reasoning_bytes": 76.322, "flops_per_problem": 4474690781.184}, "sumd.find6": {"acc": 1.0, "reasoning_bytes": 66.24, "flops_per_problem": 3896949473.28}, "sumd.find7": {"acc": 0.982, "reasoning_bytes": 73.99, "flops_per_problem": 4283376353.28}, "sumd.find8": {"acc": 0.742, "reasoning_bytes": 75.786, "flops_per_problem": 4406856302.592}, "sumd.rev6": {"acc": 1.0, "reasoning_bytes": 61.544, "flops_per_problem": 3601145217.024}, "sumd.rev7": {"acc": 0.964, "reasoning_bytes": 69.184, "flops_per_problem": 3982625832.96}, "sumd.rev8": {"acc": 0.302, "reasoning_bytes": 71.38, "flops_per_problem": 4123859337.216}, "sumd.sumd6": {"acc": 0.998, "reasoning_bytes": 65.75, "flops_per_problem": 3795904364.544}, "sumd.sumd7": {"acc": 0.97, "reasoning_bytes": 73.624, "flops_per_problem": 4189927292.928}, "sumd.sumd8": {"acc": 0.442, "reasoning_bytes": 76.738, "flops_per_problem": 4374175629.312}, "sumd.inc6": {"acc": 1.0, "reasoning_bytes": 68.538, "flops_per_problem": 3910021742.592}, "sumd.inc7": {"acc": 0.904, "reasoning_bytes": 75.754, "flops_per_problem": 4272865542.144}, "sumd.inc8": {"acc": 0.348, "reasoning_bytes": 78.998, "flops_per_problem": 4460381945.856}, "inc.cmp6": {"acc": 0.992, "reasoning_bytes": 78.636, "flops_per_problem": 4576884129.792}, "inc.cmp7": {"acc": 0.882, "reasoning_bytes": 89.918, "flops_per_problem": 5163723030.528}, "inc.cmp8": {"acc": 0.736, "reasoning_bytes": 101.104, "flops_per_problem": 5746057297.92}, "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": 0.896, "reasoning_bytes": 126.268, "flops_per_problem": 6592133431.296}, "inc.count6": {"acc": 0.972, "reasoning_bytes": 99.0, "flops_per_problem": 5343731712.0}, "inc.count7": {"acc": 0.818, "reasoning_bytes": 114.0, "flops_per_problem": 6050340864.0}, "inc.count8": {"acc": 0.772, "reasoning_bytes": 115.562, "flops_per_problem": 6163486654.464}, "inc.find6": {"acc": 0.952, "reasoning_bytes": 91.868, "flops_per_problem": 4984597610.496}, "inc.find7": {"acc": 0.732, "reasoning_bytes": 103.258, "flops_per_problem": 5531778072.576}, "inc.find8": {"acc": 0.638, "reasoning_bytes": 110.502, "flops_per_problem": 5895858438.144}, "inc.rev6": {"acc": 0.996, "reasoning_bytes": 104.0, "flops_per_problem": 5608710144.0}, "inc.rev7": {"acc": 0.688, "reasoning_bytes": 123.76, "flops_per_problem": 6568638676.992}, "inc.rev8": {"acc": 0.0, "reasoning_bytes": 127.104, "flops_per_problem": 6757656625.152}, "inc.sumd6": {"acc": 0.998, "reasoning_bytes": 109.558, "flops_per_problem": 5721590956.032}, "inc.sumd7": {"acc": 0.912, "reasoning_bytes": 127.5, "flops_per_problem": 6558216192.0}, "inc.sumd8": {"acc": 0.124, "reasoning_bytes": 141.252, "flops_per_problem": 7209621504.0}, "inc.inc6": {"acc": 0.994, "reasoning_bytes": 113.0, "flops_per_problem": 6006177792.0}, "inc.inc7": {"acc": 0.884, "reasoning_bytes": 131.0, "flops_per_problem": 6889439232.0}, "inc.inc8": {"acc": 0.01, "reasoning_bytes": 133.006, "flops_per_problem": 7025549819.904}, "count.inc.cmp16": {"acc": 0.168, "reasoning_bytes": 107.408, "flops_per_problem": 6425638649.856}, "count.inc.cmp18": {"acc": 0.094, "reasoning_bytes": 115.68, "flops_per_problem": 6882638118.912}, "count.inc.cmp20": {"acc": 0.064, "reasoning_bytes": 125.018, "flops_per_problem": 7383094050.816}, "inc.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 160.75, "flops_per_problem": 8335073230.848}, "inc.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 189.326, "flops_per_problem": 9678602207.232}, "inc.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 188.75, "flops_per_problem": 9688759713.792}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 128.784, "flops_per_problem": 7542346088.448}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 147.276, "flops_per_problem": 8535661903.872}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 170.676, "flops_per_problem": 9745730076.672}, "add.count.find6": {"acc": 0.002, "reasoning_bytes": 135.93, "flops_per_problem": 7592868642.816}, "add.count.find7": {"acc": 0.002, "reasoning_bytes": 151.758, "flops_per_problem": 8383740936.192}, "add.count.find8": {"acc": 0.002, "reasoning_bytes": 154.71, "flops_per_problem": 8670535925.76}, "runmax.inc.find12": {"acc": 0.866, "reasoning_bytes": 105.404, "flops_per_problem": 6156508889.088}, "runmax.inc.find14": {"acc": 0.848, "reasoning_bytes": 114.98, "flops_per_problem": 6667740610.56}, "runmax.inc.find16": {"acc": 0.784, "reasoning_bytes": 123.694, "flops_per_problem": 7140903763.968}, "parity.sumd.rev16": {"acc": 0.998, "reasoning_bytes": 121.988, "flops_per_problem": 6977235419.136}, "parity.sumd.rev20": {"acc": 0.464, "reasoning_bytes": 140.0, "flops_per_problem": 7949352960.0}, "parity.sumd.rev24": {"acc": 0.414, "reasoning_bytes": 162.212, "flops_per_problem": 9106955403.264}, "parity.rev.sumd16": {"acc": 0.998, "reasoning_bytes": 121.988, "flops_per_problem": 6977235419.136}, "parity.rev.sumd20": {"acc": 0.472, "reasoning_bytes": 140.0, "flops_per_problem": 7949352960.0}, "parity.rev.sumd24": {"acc": 0.454, "reasoning_bytes": 162.992, "flops_per_problem": 9141402599.424}, "count.inc.sumd16": {"acc": 0.944, "reasoning_bytes": 108.75, "flops_per_problem": 6436767744.0}, "count.inc.sumd18": {"acc": 0.826, "reasoning_bytes": 116.03, "flops_per_problem": 6846601052.16}, "count.inc.sumd20": {"acc": 0.792, "reasoning_bytes": 125.05, "flops_per_problem": 7333278105.6}, "inc.sumd.rev6": {"acc": 0.996, "reasoning_bytes": 128.544, "flops_per_problem": 6736723329.024}, "inc.sumd.rev7": {"acc": 0.754, "reasoning_bytes": 146.476, "flops_per_problem": 7572906934.272}, "inc.sumd.rev8": {"acc": 0.146, "reasoning_bytes": 147.768, "flops_per_problem": 7675276935.168}, "count.count.cmp16": {"acc": 0.998, "reasoning_bytes": 110.376, "flops_per_problem": 6729392259.072}, "count.count.cmp18": {"acc": 0.986, "reasoning_bytes": 117.952, "flops_per_problem": 7152297836.544}, "count.count.cmp20": {"acc": 0.92, "reasoning_bytes": 124.914, "flops_per_problem": 7548087287.808}, "parity.rev.find16": {"acc": 1.0, "reasoning_bytes": 123.976, "flops_per_problem": 7153357750.272}, "parity.rev.find20": {"acc": 0.844, "reasoning_bytes": 142.0, "flops_per_problem": 8126005248.0}, "parity.rev.find24": {"acc": 0.842, "reasoning_bytes": 162.64, "flops_per_problem": 9214183342.08}, "count.sumd.cmp16": {"acc": 0.982, "reasoning_bytes": 108.3, "flops_per_problem": 6505220505.6}, "count.sumd.cmp18": {"acc": 0.95, "reasoning_bytes": 115.78, "flops_per_problem": 6923886428.16}, "count.sumd.cmp20": {"acc": 0.95, "reasoning_bytes": 125.01, "flops_per_problem": 7419837726.72}, "sumd.count.count6": {"acc": 0.994, "reasoning_bytes": 83.476, "flops_per_problem": 5055611830.272}, "sumd.count.count7": {"acc": 0.994, "reasoning_bytes": 90.692, "flops_per_problem": 5418455629.824}, "sumd.count.count8": {"acc": 0.99, "reasoning_bytes": 92.244, "flops_per_problem": 5530983137.28}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 99.0, "flops_per_problem": 5772378488.832}, "runmax.rev.inc14": {"acc": 0.996, "reasoning_bytes": 109.692, "flops_per_problem": 6336164265.984}, "runmax.rev.inc16": {"acc": 0.972, "reasoning_bytes": 117.084, "flops_per_problem": 6752622034.944}, "parity.sumd.find16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.sumd.find20": {"acc": 0.844, "reasoning_bytes": 145.0, "flops_per_problem": 8302657536.0}, "parity.sumd.find24": {"acc": 0.84, "reasoning_bytes": 166.552, "flops_per_problem": 9431112351.744}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 115.956, "flops_per_problem": 6799169912.832}, "runmax.runmax.cmp16": {"acc": 0.994, "reasoning_bytes": 122.352, "flops_per_problem": 7169963065.344}, "count.runmax.count16": {"acc": 1.0, "reasoning_bytes": 111.048, "flops_per_problem": 6803232915.456}, "count.runmax.count18": {"acc": 1.0, "reasoning_bytes": 119.45, "flops_per_problem": 7262617190.4}, "count.runmax.count20": {"acc": 0.998, "reasoning_bytes": 128.198, "flops_per_problem": 7737281888.256}, "inc.inc.sumd6": {"acc": 0.96, "reasoning_bytes": 175.586, "flops_per_problem": 8814242562.048}, "inc.inc.sumd7": {"acc": 0.618, "reasoning_bytes": 203.36, "flops_per_problem": 10084990795.776}, "inc.inc.sumd8": {"acc": 0.126, "reasoning_bytes": 203.618, "flops_per_problem": 10140636266.496}, "add.sumd.find6": {"acc": 0.998, "reasoning_bytes": 150.526, "flops_per_problem": 8105071951.872}, "add.sumd.find7": {"acc": 0.878, "reasoning_bytes": 170.07, "flops_per_problem": 9056521175.04}, "add.sumd.find8": {"acc": 0.678, "reasoning_bytes": 188.424, "flops_per_problem": 9955504668.672}, "sumd.rev.rev6": {"acc": 1.0, "reasoning_bytes": 80.53, "flops_per_problem": 4616277590.016}, "sumd.rev.rev7": {"acc": 0.768, "reasoning_bytes": 86.472, "flops_per_problem": 4922857635.84}, "sumd.rev.rev8": {"acc": 0.134, "reasoning_bytes": 88.766, "flops_per_problem": 5068330795.008}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.648, "flops_per_problem": 6343936966.656}, "runmax.inc.runmax14": {"acc": 0.996, "reasoning_bytes": 121.148, "flops_per_problem": 6940138438.656}, "runmax.inc.runmax16": {"acc": 0.964, "reasoning_bytes": 128.548, "flops_per_problem": 7355271315.456}, "parity.inc.find16": {"acc": 1.0, "reasoning_bytes": 127.976, "flops_per_problem": 7330010038.272}, "parity.inc.find20": {"acc": 0.87, "reasoning_bytes": 146.0, "flops_per_problem": 8302657536.0}, "parity.inc.find24": {"acc": 0.832, "reasoning_bytes": 166.076, "flops_per_problem": 9365927657.472}, "inc.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 119.0, "flops_per_problem": 6403645440.0}, "inc.runmax.sumd7": {"acc": 0.988, "reasoning_bytes": 135.0, "flops_per_problem": 7154417664.0}, "inc.runmax.sumd8": {"acc": 0.866, "reasoning_bytes": 141.924, "flops_per_problem": 7504365846.528}, "sumd.rev.cmp6": {"acc": 0.902, "reasoning_bytes": 80.484, "flops_per_problem": 4703013863.424}, "sumd.rev.cmp7": {"acc": 0.742, "reasoning_bytes": 86.132, "flops_per_problem": 4999083098.112}, "sumd.rev.cmp8": {"acc": 0.544, "reasoning_bytes": 88.5, "flops_per_problem": 5148089303.04}, "runmax.runmax.count12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6315319296.0}, "runmax.runmax.count14": {"acc": 1.0, "reasoning_bytes": 116.904, "flops_per_problem": 6929362649.088}, "runmax.runmax.count16": {"acc": 1.0, "reasoning_bytes": 123.888, "flops_per_problem": 7326123687.936}, "count.count.count16": {"acc": 1.0, "reasoning_bytes": 111.71, "flops_per_problem": 6876631941.12}, "count.count.count18": {"acc": 1.0, "reasoning_bytes": 120.11, "flops_per_problem": 7335927889.92}, "count.count.count20": {"acc": 1.0, "reasoning_bytes": 128.428, "flops_per_problem": 7791602466.816}, "add.sumd.rev6": {"acc": 1.0, "reasoning_bytes": 145.448, "flops_per_problem": 7792309075.968}, "add.sumd.rev7": {"acc": 0.77, "reasoning_bytes": 165.324, "flops_per_problem": 8758508765.184}, "add.sumd.rev8": {"acc": 0.046, "reasoning_bytes": 184.05, "flops_per_problem": 9680103751.68}, "add.rev.rev6": {"acc": 0.988, "reasoning_bytes": 187.494, "flops_per_problem": 9808529965.056}, "add.rev.rev7": {"acc": 0.41, "reasoning_bytes": 221.81, "flops_per_problem": 11453427744.768}, "add.rev.rev8": {"acc": 0.0, "reasoning_bytes": 234.906, "flops_per_problem": 12122763264.0}, "inc.runmax.cmp6": {"acc": 0.886, "reasoning_bytes": 102.642, "flops_per_problem": 5725388980.224}, "inc.runmax.cmp7": {"acc": 0.88, "reasoning_bytes": 120.018, "flops_per_problem": 6536929591.296}, "inc.runmax.cmp8": {"acc": 0.776, "reasoning_bytes": 133.466, "flops_per_problem": 7174997655.552}, "count.rev.cmp16": {"acc": 0.984, "reasoning_bytes": 105.08, "flops_per_problem": 6318852341.76}, "count.rev.cmp18": {"acc": 0.948, "reasoning_bytes": 112.71, "flops_per_problem": 6744231051.264}, "count.rev.cmp20": {"acc": 0.952, "reasoning_bytes": 122.012, "flops_per_problem": 7243450417.152}} +{"step": 9000, "train_loss": 1.0526610612869263} +{"step": 9020, "train_loss": 1.0581419467926025} +{"step": 9040, "train_loss": 1.0952056646347046} +{"step": 9060, "train_loss": 1.0983779430389404} +{"step": 9080, "train_loss": 0.9828253984451294} +{"step": 9100, "train_loss": 1.1079715490341187} +{"step": 9120, "train_loss": 1.0877714157104492} +{"step": 9140, "train_loss": 1.0339078903198242} +{"step": 9160, "train_loss": 1.0503472089767456} +{"step": 9180, "train_loss": 1.029619812965393} +{"step": 9200, "train_loss": 1.07280695438385} +{"step": 9220, "train_loss": 1.0267503261566162} +{"step": 9240, "train_loss": 0.9200059175491333} +{"step": 9260, "train_loss": 1.0273854732513428} +{"step": 9280, "train_loss": 1.0482195615768433} +{"step": 9300, "train_loss": 1.0191051959991455} +{"step": 9320, "train_loss": 1.106501579284668} +{"step": 9340, "train_loss": 1.0809998512268066} +{"step": 9360, "train_loss": 1.0285935401916504} +{"step": 9380, "train_loss": 1.0210648775100708} +{"step": 9400, "train_loss": 1.016094446182251} +{"step": 9420, "train_loss": 1.033265471458435} +{"step": 9440, "train_loss": 0.9635905027389526} +{"step": 9460, "train_loss": 1.0983526706695557} +{"step": 9480, "train_loss": 1.0657424926757812} +{"step": 9500, "train_loss": 1.0460963249206543} +{"step": 9520, "train_loss": 1.0080366134643555} +{"step": 9540, "train_loss": 1.1815643310546875} +{"step": 9560, "train_loss": 1.076094388961792} +{"step": 9580, "train_loss": 1.0984891653060913} +{"step": 9600, "train_loss": 1.0665655136108398} +{"step": 9620, "train_loss": 1.1259853839874268} +{"step": 9640, "train_loss": 1.0223462581634521} +{"step": 9660, "train_loss": 1.0043373107910156} +{"step": 9680, "train_loss": 1.0475332736968994} +{"step": 9700, "train_loss": 1.120333194732666} +{"step": 9720, "train_loss": 1.0465078353881836} +{"step": 9740, "train_loss": 1.0570554733276367} +{"step": 9760, "train_loss": 1.0346319675445557} +{"step": 9780, "train_loss": 1.0612151622772217} +{"step": 9800, "train_loss": 1.0530049800872803} +{"step": 9820, "train_loss": 1.0247273445129395} +{"step": 9840, "train_loss": 1.0707474946975708} +{"step": 9860, "train_loss": 1.031537413597107} +{"step": 9880, "train_loss": 1.028235673904419} +{"step": 9900, "train_loss": 0.9634641408920288} +{"step": 9920, "train_loss": 1.1229617595672607} +{"step": 9940, "train_loss": 1.0479646921157837} +{"step": 9960, "train_loss": 1.0250329971313477} +{"step": 9980, "train_loss": 1.0016076564788818} +{"step": 10000, "tokens": 327680000, "val_loss": 1.8266797006130218, "val_bpb": 0.6584883553658923, "lr": 0.00010409270447323454, "elapsed": 1682.5761473178864, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.972, "reasoning_bytes": 79.0, "flops_per_problem": 4928775487.488}, "add9": {"acc": 0.44, "reasoning_bytes": 88.9, "flops_per_problem": 5498479116.288}, "add10": {"acc": 0.0, "reasoning_bytes": 95.092, "flops_per_problem": 5890205564.928}, "reach14": {"acc": 0.588, "reasoning_bytes": 6.636, "flops_per_problem": 4576884129.792}, "reach16": {"acc": 0.58, "reasoning_bytes": 7.03, "flops_per_problem": 5124241244.16}, "reach18": {"acc": 0.578, "reasoning_bytes": 7.672, "flops_per_problem": 5682020843.52}, "parity24": {"acc": 0.482, "reasoning_bytes": 138.968, "flops_per_problem": 7682961309.696}, "parity28": {"acc": 0.46, "reasoning_bytes": 161.696, "flops_per_problem": 8863351898.112}, "parity32": {"acc": 0.49, "reasoning_bytes": 183.028, "flops_per_problem": 9982090838.016}, "cmp8": {"acc": 0.988, "reasoning_bytes": 5.8, "flops_per_problem": 1360222617.6}, "cmp9": {"acc": 0.988, "reasoning_bytes": 5.696, "flops_per_problem": 1443955802.112}, "cmp10": {"acc": 0.986, "reasoning_bytes": 5.768, "flops_per_problem": 1535461687.296}, "runmax12": {"acc": 1.0, "reasoning_bytes": 71.0, "flops_per_problem": 4151328768.0}, "runmax14": {"acc": 1.0, "reasoning_bytes": 82.916, "flops_per_problem": 4765902077.952}, "runmax16": {"acc": 0.994, "reasoning_bytes": 90.446, "flops_per_problem": 5186864480.256}, "count16": {"acc": 0.984, "reasoning_bytes": 79.01, "flops_per_problem": 4725890334.72}, "count18": {"acc": 0.948, "reasoning_bytes": 89.0, "flops_per_problem": 5255405568.0}, "count20": {"acc": 0.818, "reasoning_bytes": 98.51, "flops_per_problem": 5763722526.72}, "brackets16": {"acc": 0.98, "reasoning_bytes": 53.34, "flops_per_problem": 3636387348.48}, "brackets18": {"acc": 0.844, "reasoning_bytes": 56.202, "flops_per_problem": 3851196530.688}, "brackets20": {"acc": 0.744, "reasoning_bytes": 62.754, "flops_per_problem": 4228790796.288}, "sumd8": {"acc": 0.96, "reasoning_bytes": 58.566, "flops_per_problem": 3381301444.608}, "sumd9": {"acc": 0.794, "reasoning_bytes": 66.246, "flops_per_problem": 3764725235.712}, "sumd10": {"acc": 0.366, "reasoning_bytes": 72.372, "flops_per_problem": 4079431286.784}, "inc8": {"acc": 0.996, "reasoning_bytes": 63.0, "flops_per_problem": 3798024192.0}, "inc9": {"acc": 0.808, "reasoning_bytes": 70.968, "flops_per_problem": 4238065041.408}, "inc10": {"acc": 0.006, "reasoning_bytes": 75.068, "flops_per_problem": 4483170091.008}, "add.cmp6": {"acc": 0.998, "reasoning_bytes": 92.624, "flops_per_problem": 5532131377.152}, "add.cmp7": {"acc": 0.968, "reasoning_bytes": 105.4, "flops_per_problem": 6226109890.56}, "add.cmp8": {"acc": 0.872, "reasoning_bytes": 117.982, "flops_per_problem": 6916025401.344}, "add.runmax6": {"acc": 1.0, "reasoning_bytes": 120.832, "flops_per_problem": 6572878331.904}, "add.runmax7": {"acc": 0.976, "reasoning_bytes": 138.848, "flops_per_problem": 7456846381.056}, "add.runmax8": {"acc": 0.556, "reasoning_bytes": 156.762, "flops_per_problem": 8336309796.864}, "add.count6": {"acc": 0.984, "reasoning_bytes": 115.648, "flops_per_problem": 6388100038.656}, "add.count7": {"acc": 0.918, "reasoning_bytes": 132.098, "flops_per_problem": 7202908717.056}, "add.count8": {"acc": 0.39, "reasoning_bytes": 148.25, "flops_per_problem": 8005440061.44}, "add.find6": {"acc": 0.934, "reasoning_bytes": 107.828, "flops_per_problem": 5998581743.616}, "add.find7": {"acc": 0.856, "reasoning_bytes": 121.86, "flops_per_problem": 6706604113.92}, "add.find8": {"acc": 0.388, "reasoning_bytes": 139.152, "flops_per_problem": 7558598098.944}, "add.rev6": {"acc": 0.994, "reasoning_bytes": 123.25, "flops_per_problem": 6794841931.776}, "add.rev7": {"acc": 0.9, "reasoning_bytes": 145.604, "flops_per_problem": 7913757523.968}, "add.rev8": {"acc": 0.032, "reasoning_bytes": 160.392, "flops_per_problem": 8667621163.008}, "add.sumd6": {"acc": 0.994, "reasoning_bytes": 126.474, "flops_per_problem": 6777706659.84}, "add.sumd7": {"acc": 0.916, "reasoning_bytes": 146.332, "flops_per_problem": 7743111413.76}, "add.sumd8": {"acc": 0.114, "reasoning_bytes": 165.242, "flops_per_problem": 8666561249.28}, "add.inc6": {"acc": 0.992, "reasoning_bytes": 131.04, "flops_per_problem": 7138695610.368}, "add.inc7": {"acc": 0.91, "reasoning_bytes": 151.026, "flops_per_problem": 8153827983.36}, "add.inc8": {"acc": 0.03, "reasoning_bytes": 164.404, "flops_per_problem": 8854607609.856}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5122916352.0}, "runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 98.076, "flops_per_problem": 5700392681.472}, "runmax.cmp16": {"acc": 0.992, "reasoning_bytes": 104.994, "flops_per_problem": 6094238957.568}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.runmax14": {"acc": 0.998, "reasoning_bytes": 99.652, "flops_per_problem": 5814156754.944}, "runmax.runmax16": {"acc": 0.974, "reasoning_bytes": 106.008, "flops_per_problem": 6183183384.576}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5255405568.0}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 99.544, "flops_per_problem": 5853550215.168}, "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": 98.69, "flops_per_problem": 5771671879.68}, "runmax.find16": {"acc": 0.99, "reasoning_bytes": 105.996, "flops_per_problem": 6182653427.712}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 83.0, "flops_per_problem": 4857937920.0}, "runmax.rev14": {"acc": 0.994, "reasoning_bytes": 94.604, "flops_per_problem": 5458732351.488}, "runmax.rev16": {"acc": 0.972, "reasoning_bytes": 101.074, "flops_per_problem": 5832881897.472}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 86.0, "flops_per_problem": 5034590208.0}, "runmax.sumd14": {"acc": 0.998, "reasoning_bytes": 97.58, "flops_per_problem": 5634324725.76}, "runmax.sumd16": {"acc": 0.978, "reasoning_bytes": 104.104, "flops_per_problem": 6010770751.488}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5065769336.832}, "runmax.inc14": {"acc": 0.994, "reasoning_bytes": 98.146, "flops_per_problem": 5649516822.528}, "runmax.inc16": {"acc": 0.978, "reasoning_bytes": 105.094, "flops_per_problem": 6046631165.952}, "count.cmp16": {"acc": 1.0, "reasoning_bytes": 95.01, "flops_per_problem": 5697477918.72}, "count.cmp18": {"acc": 0.992, "reasoning_bytes": 104.96, "flops_per_problem": 6225314955.264}, "count.cmp20": {"acc": 0.962, "reasoning_bytes": 112.72, "flops_per_problem": 6656434864.128}, "count.runmax16": {"acc": 0.996, "reasoning_bytes": 96.01, "flops_per_problem": 5785804062.72}, "count.runmax18": {"acc": 0.98, "reasoning_bytes": 105.98, "flops_per_problem": 6314436034.56}, "count.runmax20": {"acc": 0.86, "reasoning_bytes": 114.14, "flops_per_problem": 6763132846.08}, "count.count16": {"acc": 1.0, "reasoning_bytes": 96.0, "flops_per_problem": 5829525504.0}, "count.count18": {"acc": 1.0, "reasoning_bytes": 105.98, "flops_per_problem": 6358599106.56}, "count.count20": {"acc": 0.998, "reasoning_bytes": 115.03, "flops_per_problem": 6846601052.16}, "count.find16": {"acc": 0.992, "reasoning_bytes": 96.04, "flops_per_problem": 5787128954.88}, "count.find18": {"acc": 0.976, "reasoning_bytes": 106.01, "flops_per_problem": 6315760926.72}, "count.find20": {"acc": 0.956, "reasoning_bytes": 114.58, "flops_per_problem": 6782564597.76}, "count.rev16": {"acc": 0.996, "reasoning_bytes": 91.0, "flops_per_problem": 5432057856.0}, "count.rev18": {"acc": 0.976, "reasoning_bytes": 100.97, "flops_per_problem": 5960689827.84}, "count.rev20": {"acc": 0.808, "reasoning_bytes": 107.93, "flops_per_problem": 6356390952.96}, "count.sumd16": {"acc": 0.994, "reasoning_bytes": 94.01, "flops_per_problem": 5609151774.72}, "count.sumd18": {"acc": 0.96, "reasoning_bytes": 103.99, "flops_per_problem": 6138225377.28}, "count.sumd20": {"acc": 0.83, "reasoning_bytes": 111.58, "flops_per_problem": 6561749237.76}, "count.inc16": {"acc": 0.994, "reasoning_bytes": 95.01, "flops_per_problem": 5609151774.72}, "count.inc18": {"acc": 0.976, "reasoning_bytes": 104.95, "flops_per_problem": 6136458854.4}, "count.inc20": {"acc": 0.82, "reasoning_bytes": 112.37, "flops_per_problem": 6552474992.64}, "parity.cmp16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6359482368.0}, "parity.cmp20": {"acc": 0.942, "reasoning_bytes": 129.072, "flops_per_problem": 7334249693.184}, "parity.cmp24": {"acc": 0.934, "reasoning_bytes": 147.564, "flops_per_problem": 8327565508.608}, "parity.runmax16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.runmax20": {"acc": 0.572, "reasoning_bytes": 131.368, "flops_per_problem": 7479811178.496}, "parity.runmax24": {"acc": 0.514, "reasoning_bytes": 151.648, "flops_per_problem": 8552090566.656}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6491971584.0}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 131.452, "flops_per_problem": 7527683948.544}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 151.756, "flops_per_problem": 8601023250.432}, "parity.find16": {"acc": 0.998, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.find20": {"acc": 0.886, "reasoning_bytes": 131.248, "flops_per_problem": 7474511609.856}, "parity.find24": {"acc": 0.888, "reasoning_bytes": 151.396, "flops_per_problem": 8540961472.512}, "parity.rev16": {"acc": 0.99, "reasoning_bytes": 107.0, "flops_per_problem": 6094503936.0}, "parity.rev20": {"acc": 0.53, "reasoning_bytes": 126.104, "flops_per_problem": 7114847551.488}, "parity.rev24": {"acc": 0.5, "reasoning_bytes": 146.612, "flops_per_problem": 8197196120.064}, "parity.sumd16": {"acc": 1.0, "reasoning_bytes": 110.0, "flops_per_problem": 6271156224.0}, "parity.sumd20": {"acc": 0.554, "reasoning_bytes": 129.152, "flops_per_problem": 7293619666.944}, "parity.sumd24": {"acc": 0.518, "reasoning_bytes": 149.984, "flops_per_problem": 8390277070.848}, "parity.inc16": {"acc": 0.992, "reasoning_bytes": 111.0, "flops_per_problem": 6271156224.0}, "parity.inc20": {"acc": 0.562, "reasoning_bytes": 130.116, "flops_per_problem": 7292029796.352}, "parity.inc24": {"acc": 0.55, "reasoning_bytes": 150.684, "flops_per_problem": 8377028149.248}, "sumd.cmp6": {"acc": 0.998, "reasoning_bytes": 62.088, "flops_per_problem": 3713407746.048}, "sumd.cmp7": {"acc": 0.984, "reasoning_bytes": 69.972, "flops_per_problem": 4105929129.984}, "sumd.cmp8": {"acc": 0.956, "reasoning_bytes": 72.488, "flops_per_problem": 4261118164.992}, "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": 0.824, "reasoning_bytes": 82.306, "flops_per_problem": 4694799532.032}, "sumd.count6": {"acc": 1.0, "reasoning_bytes": 66.428, "flops_per_problem": 3949415202.816}, "sumd.count7": {"acc": 1.0, "reasoning_bytes": 74.458, "flops_per_problem": 4348207742.976}, "sumd.count8": {"acc": 0.748, "reasoning_bytes": 79.142, "flops_per_problem": 4598082404.352}, "sumd.find6": {"acc": 1.0, "reasoning_bytes": 66.24, "flops_per_problem": 3896949473.28}, "sumd.find7": {"acc": 1.0, "reasoning_bytes": 74.428, "flops_per_problem": 4302719778.816}, "sumd.find8": {"acc": 0.884, "reasoning_bytes": 80.048, "flops_per_problem": 4595079315.456}, "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": 0.668, "reasoning_bytes": 74.724, "flops_per_problem": 4271540649.984}, "sumd.sumd6": {"acc": 1.0, "reasoning_bytes": 65.744, "flops_per_problem": 3795639386.112}, "sumd.sumd7": {"acc": 0.99, "reasoning_bytes": 73.742, "flops_per_problem": 4195668492.288}, "sumd.sumd8": {"acc": 0.81, "reasoning_bytes": 80.822, "flops_per_problem": 4554007658.496}, "sumd.inc6": {"acc": 0.998, "reasoning_bytes": 68.538, "flops_per_problem": 3910021742.592}, "sumd.inc7": {"acc": 0.98, "reasoning_bytes": 76.48, "flops_per_problem": 4305016258.56}, "sumd.inc8": {"acc": 0.684, "reasoning_bytes": 82.612, "flops_per_problem": 4620340592.64}, "inc.cmp6": {"acc": 0.99, "reasoning_bytes": 78.634, "flops_per_problem": 4576795803.648}, "inc.cmp7": {"acc": 0.986, "reasoning_bytes": 89.81, "flops_per_problem": 5158688440.32}, "inc.cmp8": {"acc": 0.87, "reasoning_bytes": 100.792, "flops_per_problem": 5732013441.024}, "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": 0.88, "reasoning_bytes": 123.06, "flops_per_problem": 6450458296.32}, "inc.count6": {"acc": 0.986, "reasoning_bytes": 98.998, "flops_per_problem": 5343643385.856}, "inc.count7": {"acc": 0.946, "reasoning_bytes": 113.07, "flops_per_problem": 6009269207.04}, "inc.count8": {"acc": 0.768, "reasoning_bytes": 114.028, "flops_per_problem": 6095740502.016}, "inc.find6": {"acc": 0.958, "reasoning_bytes": 92.072, "flops_per_problem": 4993606877.184}, "inc.find7": {"acc": 0.882, "reasoning_bytes": 103.064, "flops_per_problem": 5523210436.608}, "inc.find8": {"acc": 0.728, "reasoning_bytes": 106.26, "flops_per_problem": 5708695339.008}, "inc.rev6": {"acc": 0.998, "reasoning_bytes": 104.002, "flops_per_problem": 5608886796.288}, "inc.rev7": {"acc": 0.962, "reasoning_bytes": 124.02, "flops_per_problem": 6581534294.016}, "inc.rev8": {"acc": 0.012, "reasoning_bytes": 127.634, "flops_per_problem": 6788835753.984}, "inc.sumd6": {"acc": 0.996, "reasoning_bytes": 109.558, "flops_per_problem": 5721590956.032}, "inc.sumd7": {"acc": 0.968, "reasoning_bytes": 127.482, "flops_per_problem": 6557332930.56}, "inc.sumd8": {"acc": 0.168, "reasoning_bytes": 135.348, "flops_per_problem": 6948971053.056}, "inc.inc6": {"acc": 1.0, "reasoning_bytes": 113.0, "flops_per_problem": 6006177792.0}, "inc.inc7": {"acc": 0.998, "reasoning_bytes": 131.0, "flops_per_problem": 6889439232.0}, "inc.inc8": {"acc": 0.102, "reasoning_bytes": 136.69, "flops_per_problem": 7196814213.12}, "count.inc.cmp16": {"acc": 0.654, "reasoning_bytes": 110.12, "flops_per_problem": 6541610876.928}, "count.inc.cmp18": {"acc": 0.68, "reasoning_bytes": 118.016, "flops_per_problem": 6979620225.024}, "count.inc.cmp20": {"acc": 0.646, "reasoning_bytes": 124.346, "flops_per_problem": 7347145310.208}, "inc.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 160.99, "flops_per_problem": 8346820608.0}, "inc.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 192.902, "flops_per_problem": 9845096988.672}, "inc.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 193.134, "flops_per_problem": 9896591130.624}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 128.988, "flops_per_problem": 7551355355.136}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 147.888, "flops_per_problem": 8562689703.936}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 167.112, "flops_per_problem": 9588332888.064}, "add.count.find6": {"acc": 0.006, "reasoning_bytes": 137.104, "flops_per_problem": 7644186132.48}, "add.count.find7": {"acc": 0.006, "reasoning_bytes": 146.944, "flops_per_problem": 8195076292.608}, "add.count.find8": {"acc": 0.008, "reasoning_bytes": 141.922, "flops_per_problem": 8192161529.856}, "runmax.inc.find12": {"acc": 0.864, "reasoning_bytes": 105.428, "flops_per_problem": 6157568802.816}, "runmax.inc.find14": {"acc": 0.882, "reasoning_bytes": 115.4, "flops_per_problem": 6686289100.8}, "runmax.inc.find16": {"acc": 0.814, "reasoning_bytes": 123.48, "flops_per_problem": 7131541192.704}, "parity.sumd.rev16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.sumd.rev20": {"acc": 0.486, "reasoning_bytes": 140.204, "flops_per_problem": 7958362226.688}, "parity.sumd.rev24": {"acc": 0.492, "reasoning_bytes": 159.164, "flops_per_problem": 8972346359.808}, "parity.rev.sumd16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.rev.sumd20": {"acc": 0.512, "reasoning_bytes": 140.336, "flops_per_problem": 7964191752.192}, "parity.rev.sumd24": {"acc": 0.492, "reasoning_bytes": 159.692, "flops_per_problem": 8995664461.824}, "count.inc.sumd16": {"acc": 0.992, "reasoning_bytes": 110.0, "flops_per_problem": 6491971584.0}, "count.inc.sumd18": {"acc": 0.988, "reasoning_bytes": 119.87, "flops_per_problem": 7016187248.64}, "count.inc.sumd20": {"acc": 0.8, "reasoning_bytes": 125.77, "flops_per_problem": 7365075517.44}, "inc.sumd.rev6": {"acc": 0.998, "reasoning_bytes": 128.544, "flops_per_problem": 6736723329.024}, "inc.sumd.rev7": {"acc": 0.942, "reasoning_bytes": 146.456, "flops_per_problem": 7571935346.688}, "inc.sumd.rev8": {"acc": 0.076, "reasoning_bytes": 147.008, "flops_per_problem": 7640388108.288}, "count.count.cmp16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6801113088.0}, "count.count.cmp18": {"acc": 0.998, "reasoning_bytes": 122.0, "flops_per_problem": 7331069952.0}, "count.count.cmp20": {"acc": 0.998, "reasoning_bytes": 131.138, "flops_per_problem": 7822958247.936}, "parity.rev.find16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7154417664.0}, "parity.rev.find20": {"acc": 0.868, "reasoning_bytes": 142.588, "flops_per_problem": 8151973134.336}, "parity.rev.find24": {"acc": 0.894, "reasoning_bytes": 161.68, "flops_per_problem": 9171786792.96}, "count.sumd.cmp16": {"acc": 1.0, "reasoning_bytes": 110.02, "flops_per_problem": 6581180989.44}, "count.sumd.cmp18": {"acc": 0.994, "reasoning_bytes": 119.96, "flops_per_problem": 7108488069.12}, "count.sumd.cmp20": {"acc": 0.948, "reasoning_bytes": 126.4, "flops_per_problem": 7481224396.8}, "sumd.count.count6": {"acc": 1.0, "reasoning_bytes": 83.476, "flops_per_problem": 5055611830.272}, "sumd.count.count7": {"acc": 1.0, "reasoning_bytes": 91.424, "flops_per_problem": 5450782998.528}, "sumd.count.count8": {"acc": 0.996, "reasoning_bytes": 93.604, "flops_per_problem": 5591486545.92}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 99.0, "flops_per_problem": 5772378488.832}, "runmax.rev.inc14": {"acc": 0.996, "reasoning_bytes": 110.578, "flops_per_problem": 6375292747.776}, "runmax.rev.inc16": {"acc": 0.976, "reasoning_bytes": 117.068, "flops_per_problem": 6752003751.936}, "parity.sumd.find16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.sumd.find20": {"acc": 0.862, "reasoning_bytes": 145.312, "flops_per_problem": 8316436414.464}, "parity.sumd.find24": {"acc": 0.782, "reasoning_bytes": 163.96, "flops_per_problem": 9316641669.12}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 116.0, "flops_per_problem": 6801113088.0}, "runmax.runmax.cmp16": {"acc": 0.994, "reasoning_bytes": 122.082, "flops_per_problem": 7158039035.904}, "count.runmax.count16": {"acc": 1.0, "reasoning_bytes": 113.0, "flops_per_problem": 6889439232.0}, "count.runmax.count18": {"acc": 1.0, "reasoning_bytes": 122.98, "flops_per_problem": 7418512834.56}, "count.runmax.count20": {"acc": 1.0, "reasoning_bytes": 132.16, "flops_per_problem": 7912255979.52}, "inc.inc.sumd6": {"acc": 0.976, "reasoning_bytes": 175.56, "flops_per_problem": 8813182648.32}, "inc.inc.sumd7": {"acc": 0.792, "reasoning_bytes": 203.458, "flops_per_problem": 10089407102.976}, "inc.inc.sumd8": {"acc": 0.062, "reasoning_bytes": 204.224, "flops_per_problem": 10167310761.984}, "add.sumd.find6": {"acc": 1.0, "reasoning_bytes": 150.512, "flops_per_problem": 8104453668.864}, "add.sumd.find7": {"acc": 0.872, "reasoning_bytes": 170.144, "flops_per_problem": 9059789242.368}, "add.sumd.find8": {"acc": 0.708, "reasoning_bytes": 187.022, "flops_per_problem": 9893499715.584}, "sumd.rev.rev6": {"acc": 0.998, "reasoning_bytes": 80.53, "flops_per_problem": 4616277590.016}, "sumd.rev.rev7": {"acc": 0.974, "reasoning_bytes": 88.382, "flops_per_problem": 5007297429.504}, "sumd.rev.rev8": {"acc": 0.334, "reasoning_bytes": 90.728, "flops_per_problem": 5154978742.272}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.648, "flops_per_problem": 6343936966.656}, "runmax.inc.runmax14": {"acc": 0.998, "reasoning_bytes": 121.868, "flops_per_problem": 6971935850.496}, "runmax.inc.runmax16": {"acc": 0.958, "reasoning_bytes": 128.58, "flops_per_problem": 7356684533.76}, "parity.inc.find16": {"acc": 1.0, "reasoning_bytes": 128.0, "flops_per_problem": 7331069952.0}, "parity.inc.find20": {"acc": 0.876, "reasoning_bytes": 146.168, "flops_per_problem": 8310076932.096}, "parity.inc.find24": {"acc": 0.852, "reasoning_bytes": 164.72, "flops_per_problem": 9306042531.84}, "inc.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 119.0, "flops_per_problem": 6403645440.0}, "inc.runmax.sumd7": {"acc": 0.986, "reasoning_bytes": 135.0, "flops_per_problem": 7154417664.0}, "inc.runmax.sumd8": {"acc": 0.862, "reasoning_bytes": 137.95, "flops_per_problem": 7328420167.68}, "sumd.rev.cmp6": {"acc": 0.924, "reasoning_bytes": 80.904, "flops_per_problem": 4721385701.376}, "sumd.rev.cmp7": {"acc": 0.862, "reasoning_bytes": 88.068, "flops_per_problem": 5083346239.488}, "sumd.rev.cmp8": {"acc": 0.6, "reasoning_bytes": 89.59, "flops_per_problem": 5196315377.664}, "runmax.runmax.count12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6315319296.0}, "runmax.runmax.count14": {"acc": 1.0, "reasoning_bytes": 116.88, "flops_per_problem": 6928302735.36}, "runmax.runmax.count16": {"acc": 1.0, "reasoning_bytes": 123.096, "flops_per_problem": 7291146534.912}, "count.count.count16": {"acc": 1.0, "reasoning_bytes": 113.0, "flops_per_problem": 6933602304.0}, "count.count.count18": {"acc": 1.0, "reasoning_bytes": 123.0, "flops_per_problem": 7463559168.0}, "count.count.count20": {"acc": 1.0, "reasoning_bytes": 132.51, "flops_per_problem": 7971876126.72}, "add.sumd.rev6": {"acc": 0.994, "reasoning_bytes": 145.446, "flops_per_problem": 7792220749.824}, "add.sumd.rev7": {"acc": 0.79, "reasoning_bytes": 165.326, "flops_per_problem": 8758597091.328}, "add.sumd.rev8": {"acc": 0.076, "reasoning_bytes": 182.832, "flops_per_problem": 9619953647.616}, "add.rev.rev6": {"acc": 0.956, "reasoning_bytes": 187.562, "flops_per_problem": 9812239663.104}, "add.rev.rev7": {"acc": 0.422, "reasoning_bytes": 221.712, "flops_per_problem": 11452279504.896}, "add.rev.rev8": {"acc": 0.0, "reasoning_bytes": 239.474, "flops_per_problem": 12334922661.888}, "inc.runmax.cmp6": {"acc": 0.916, "reasoning_bytes": 104.664, "flops_per_problem": 5814686711.808}, "inc.runmax.cmp7": {"acc": 0.81, "reasoning_bytes": 124.014, "flops_per_problem": 6713228574.72}, "inc.runmax.cmp8": {"acc": 0.836, "reasoning_bytes": 140.826, "flops_per_problem": 7499861213.184}, "count.rev.cmp16": {"acc": 1.0, "reasoning_bytes": 107.01, "flops_per_problem": 6404087070.72}, "count.rev.cmp18": {"acc": 0.994, "reasoning_bytes": 116.97, "flops_per_problem": 6932365737.984}, "count.rev.cmp20": {"acc": 0.962, "reasoning_bytes": 123.83, "flops_per_problem": 7323738882.048}} +{"step": 10000, "train_loss": 1.092826008796692} +{"step": 10020, "train_loss": 1.0430498123168945} +{"step": 10040, "train_loss": 1.1265480518341064} +{"step": 10060, "train_loss": 1.0502796173095703} +{"step": 10080, "train_loss": 1.0275814533233643} +{"step": 10100, "train_loss": 1.0317835807800293} +{"step": 10120, "train_loss": 1.013547658920288} +{"step": 10140, "train_loss": 1.0820053815841675} +{"step": 10160, "train_loss": 1.0582630634307861} +{"step": 10180, "train_loss": 1.0994529724121094} +{"step": 10200, "train_loss": 1.007978916168213} +{"step": 10220, "train_loss": 1.1242527961730957} +{"step": 10240, "train_loss": 1.0036728382110596} +{"step": 10260, "train_loss": 1.042311191558838} +{"step": 10280, "train_loss": 1.0574405193328857} +{"step": 10300, "train_loss": 1.027543544769287} +{"step": 10320, "train_loss": 1.0301207304000854} +{"step": 10340, "train_loss": 0.9874641299247742} +{"step": 10360, "train_loss": 1.028611421585083} +{"step": 10380, "train_loss": 1.0809485912322998} +{"step": 10400, "train_loss": 1.070051670074463} +{"step": 10420, "train_loss": 1.0373525619506836} +{"step": 10440, "train_loss": 1.1139464378356934} +{"step": 10460, "train_loss": 0.9628478288650513} +{"step": 10480, "train_loss": 0.9855203628540039} +{"step": 10500, "train_loss": 1.0888885259628296} +{"step": 10520, "train_loss": 1.1099416017532349} +{"step": 10540, "train_loss": 0.9451761245727539} +{"step": 10560, "train_loss": 1.047563076019287} +{"step": 10580, "train_loss": 0.9753097891807556} +{"step": 10600, "train_loss": 1.0047955513000488} +{"step": 10620, "train_loss": 1.0374810695648193} +{"step": 10640, "train_loss": 1.0503259897232056} +{"step": 10660, "train_loss": 1.0125176906585693} +{"step": 10680, "train_loss": 0.9804841876029968} +{"step": 10700, "train_loss": 0.9927552342414856} +{"step": 10720, "train_loss": 1.1132985353469849} +{"step": 10740, "train_loss": 1.0472079515457153} +{"step": 10760, "train_loss": 0.9800451993942261} +{"step": 10780, "train_loss": 1.076259732246399} +{"step": 10800, "train_loss": 0.9806531667709351} +{"step": 10820, "train_loss": 1.1178804636001587} +{"step": 10840, "train_loss": 1.0241293907165527} +{"step": 10860, "train_loss": 0.9640951156616211} +{"step": 10880, "train_loss": 1.0405635833740234} +{"step": 10900, "train_loss": 1.0179100036621094} +{"step": 10920, "train_loss": 1.0190984010696411} +{"step": 10940, "train_loss": 1.0493723154067993} +{"step": 10960, "train_loss": 1.051018238067627} +{"step": 10980, "train_loss": 1.0097569227218628} +{"step": 11000, "tokens": 360448000, "val_loss": 1.8058815836906432, "val_bpb": 0.6509909721068959, "lr": 7.345019833124972e-05, "elapsed": 1844.1601090431213, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.978, "reasoning_bytes": 79.0, "flops_per_problem": 4928775487.488}, "add9": {"acc": 0.47, "reasoning_bytes": 88.996, "flops_per_problem": 5503248728.064}, "add10": {"acc": 0.0, "reasoning_bytes": 98.32, "flops_per_problem": 6049722580.992}, "reach14": {"acc": 0.6, "reasoning_bytes": 8.544, "flops_per_problem": 4661147271.168}, "reach16": {"acc": 0.58, "reasoning_bytes": 9.15, "flops_per_problem": 5217690304.512}, "reach18": {"acc": 0.468, "reasoning_bytes": 9.858, "flops_per_problem": 5778914623.488}, "parity24": {"acc": 0.814, "reasoning_bytes": 143.0, "flops_per_problem": 7861026816.0}, "parity28": {"acc": 0.596, "reasoning_bytes": 167.588, "flops_per_problem": 9123560718.336}, "parity32": {"acc": 0.522, "reasoning_bytes": 192.428, "flops_per_problem": 10397223714.816}, "cmp8": {"acc": 0.99, "reasoning_bytes": 5.828, "flops_per_problem": 1361459183.616}, "cmp9": {"acc": 0.988, "reasoning_bytes": 5.708, "flops_per_problem": 1444485758.976}, "cmp10": {"acc": 0.984, "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": 1.0, "reasoning_bytes": 94.976, "flops_per_problem": 5386834870.272}, "count16": {"acc": 1.0, "reasoning_bytes": 79.0, "flops_per_problem": 4725448704.0}, "count18": {"acc": 0.992, "reasoning_bytes": 88.9, "flops_per_problem": 5250989260.8}, "count20": {"acc": 0.862, "reasoning_bytes": 95.64, "flops_per_problem": 5636974510.08}, "brackets16": {"acc": 0.982, "reasoning_bytes": 53.546, "flops_per_problem": 3645484941.312}, "brackets18": {"acc": 0.964, "reasoning_bytes": 56.692, "flops_per_problem": 3873101414.4}, "brackets20": {"acc": 0.904, "reasoning_bytes": 62.522, "flops_per_problem": 4218544963.584}, "sumd8": {"acc": 0.978, "reasoning_bytes": 58.566, "flops_per_problem": 3381301444.608}, "sumd9": {"acc": 0.88, "reasoning_bytes": 66.346, "flops_per_problem": 3768788238.336}, "sumd10": {"acc": 0.492, "reasoning_bytes": 72.906, "flops_per_problem": 4102042779.648}, "inc8": {"acc": 0.994, "reasoning_bytes": 63.0, "flops_per_problem": 3798024192.0}, "inc9": {"acc": 0.854, "reasoning_bytes": 71.0, "flops_per_problem": 4239654912.0}, "inc10": {"acc": 0.016, "reasoning_bytes": 79.0, "flops_per_problem": 4681285632.0}, "add.cmp6": {"acc": 0.996, "reasoning_bytes": 92.62, "flops_per_problem": 5531954724.864}, "add.cmp7": {"acc": 0.968, "reasoning_bytes": 105.498, "flops_per_problem": 6230437871.616}, "add.cmp8": {"acc": 0.866, "reasoning_bytes": 118.406, "flops_per_problem": 6934485565.44}, "add.runmax6": {"acc": 1.0, "reasoning_bytes": 120.832, "flops_per_problem": 6572878331.904}, "add.runmax7": {"acc": 0.998, "reasoning_bytes": 138.848, "flops_per_problem": 7456846381.056}, "add.runmax8": {"acc": 0.578, "reasoning_bytes": 156.766, "flops_per_problem": 8336486449.152}, "add.count6": {"acc": 0.994, "reasoning_bytes": 115.648, "flops_per_problem": 6388100038.656}, "add.count7": {"acc": 0.954, "reasoning_bytes": 132.098, "flops_per_problem": 7202908717.056}, "add.count8": {"acc": 0.384, "reasoning_bytes": 147.998, "flops_per_problem": 7993604358.144}, "add.find6": {"acc": 0.946, "reasoning_bytes": 107.816, "flops_per_problem": 5998051786.752}, "add.find7": {"acc": 0.842, "reasoning_bytes": 122.012, "flops_per_problem": 6713316900.864}, "add.find8": {"acc": 0.364, "reasoning_bytes": 141.512, "flops_per_problem": 7664677797.888}, "add.rev6": {"acc": 1.0, "reasoning_bytes": 123.248, "flops_per_problem": 6794576953.344}, "add.rev7": {"acc": 0.958, "reasoning_bytes": 145.878, "flops_per_problem": 7926299836.416}, "add.rev8": {"acc": 0.058, "reasoning_bytes": 160.814, "flops_per_problem": 8684756434.944}, "add.sumd6": {"acc": 0.998, "reasoning_bytes": 126.476, "flops_per_problem": 6777794985.984}, "add.sumd7": {"acc": 0.964, "reasoning_bytes": 146.338, "flops_per_problem": 7743376392.192}, "add.sumd8": {"acc": 0.218, "reasoning_bytes": 165.81, "flops_per_problem": 8691645874.176}, "add.inc6": {"acc": 0.994, "reasoning_bytes": 131.04, "flops_per_problem": 7138695610.368}, "add.inc7": {"acc": 0.928, "reasoning_bytes": 150.958, "flops_per_problem": 8150471589.888}, "add.inc8": {"acc": 0.044, "reasoning_bytes": 163.59, "flops_per_problem": 8820778696.704}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5122916352.0}, "runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 98.892, "flops_per_problem": 5736429748.224}, "runmax.cmp16": {"acc": 0.992, "reasoning_bytes": 105.144, "flops_per_problem": 6100863418.368}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.runmax14": {"acc": 1.0, "reasoning_bytes": 99.964, "flops_per_problem": 5827935633.408}, "runmax.runmax16": {"acc": 0.97, "reasoning_bytes": 106.418, "flops_per_problem": 6201378570.24}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5255405568.0}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 99.916, "flops_per_problem": 5869978877.952}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 106.576, "flops_per_problem": 6252431081.472}, "runmax.find12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.find14": {"acc": 1.0, "reasoning_bytes": 99.748, "flops_per_problem": 5818396409.856}, "runmax.find16": {"acc": 0.986, "reasoning_bytes": 106.064, "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": 94.976, "flops_per_problem": 5475161014.272}, "runmax.rev16": {"acc": 0.968, "reasoning_bytes": 102.896, "flops_per_problem": 5913523666.944}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 86.0, "flops_per_problem": 5034590208.0}, "runmax.sumd14": {"acc": 1.0, "reasoning_bytes": 97.94, "flops_per_problem": 5650223431.68}, "runmax.sumd16": {"acc": 0.976, "reasoning_bytes": 105.06, "flops_per_problem": 6053167300.608}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5065769336.832}, "runmax.inc14": {"acc": 1.0, "reasoning_bytes": 98.952, "flops_per_problem": 5685288910.848}, "runmax.inc16": {"acc": 0.976, "reasoning_bytes": 106.116, "flops_per_problem": 6092030803.968}, "count.cmp16": {"acc": 0.996, "reasoning_bytes": 95.0, "flops_per_problem": 5697036288.0}, "count.cmp18": {"acc": 0.98, "reasoning_bytes": 103.95, "flops_per_problem": 6180710252.544}, "count.cmp20": {"acc": 0.942, "reasoning_bytes": 110.03, "flops_per_problem": 6537636200.448}, "count.runmax16": {"acc": 1.0, "reasoning_bytes": 96.0, "flops_per_problem": 5785362432.0}, "count.runmax18": {"acc": 0.956, "reasoning_bytes": 104.91, "flops_per_problem": 6267181547.52}, "count.runmax20": {"acc": 0.806, "reasoning_bytes": 111.08, "flops_per_problem": 6627993845.76}, "count.count16": {"acc": 1.0, "reasoning_bytes": 96.0, "flops_per_problem": 5829525504.0}, "count.count18": {"acc": 1.0, "reasoning_bytes": 105.68, "flops_per_problem": 6345350184.96}, "count.count20": {"acc": 0.998, "reasoning_bytes": 111.25, "flops_per_problem": 6679664640.0}, "count.find16": {"acc": 1.0, "reasoning_bytes": 96.0, "flops_per_problem": 5785362432.0}, "count.find18": {"acc": 0.982, "reasoning_bytes": 105.15, "flops_per_problem": 6277780684.8}, "count.find20": {"acc": 0.952, "reasoning_bytes": 111.06, "flops_per_problem": 6627110584.32}, "count.rev16": {"acc": 0.998, "reasoning_bytes": 90.99, "flops_per_problem": 5431616225.28}, "count.rev18": {"acc": 0.928, "reasoning_bytes": 99.15, "flops_per_problem": 5880313036.8}, "count.rev20": {"acc": 0.798, "reasoning_bytes": 106.04, "flops_per_problem": 6272922746.88}, "count.sumd16": {"acc": 1.0, "reasoning_bytes": 94.0, "flops_per_problem": 5608710144.0}, "count.sumd18": {"acc": 0.95, "reasoning_bytes": 102.73, "flops_per_problem": 6082579906.56}, "count.sumd20": {"acc": 0.798, "reasoning_bytes": 109.06, "flops_per_problem": 6450458296.32}, "count.inc16": {"acc": 0.998, "reasoning_bytes": 95.0, "flops_per_problem": 5608710144.0}, "count.inc18": {"acc": 0.954, "reasoning_bytes": 103.83, "flops_per_problem": 6086996213.76}, "count.inc20": {"acc": 0.804, "reasoning_bytes": 110.06, "flops_per_problem": 6450458296.32}, "parity.cmp16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6359482368.0}, "parity.cmp20": {"acc": 0.952, "reasoning_bytes": 130.344, "flops_per_problem": 7390425120.768}, "parity.cmp24": {"acc": 0.932, "reasoning_bytes": 153.168, "flops_per_problem": 8575055364.096}, "parity.runmax16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.runmax20": {"acc": 0.908, "reasoning_bytes": 135.1, "flops_per_problem": 7644627763.2}, "parity.runmax24": {"acc": 0.556, "reasoning_bytes": 154.0, "flops_per_problem": 8655962112.0}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6491971584.0}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 135.076, "flops_per_problem": 7687730921.472}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 154.0, "flops_per_problem": 8700125184.0}, "parity.find16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.find20": {"acc": 0.94, "reasoning_bytes": 133.828, "flops_per_problem": 7588452335.616}, "parity.find24": {"acc": 0.832, "reasoning_bytes": 153.976, "flops_per_problem": 8654902198.272}, "parity.rev16": {"acc": 1.0, "reasoning_bytes": 107.0, "flops_per_problem": 6094503936.0}, "parity.rev20": {"acc": 0.922, "reasoning_bytes": 130.412, "flops_per_problem": 7305102065.664}, "parity.rev24": {"acc": 0.474, "reasoning_bytes": 149.036, "flops_per_problem": 8304247406.592}, "parity.sumd16": {"acc": 1.0, "reasoning_bytes": 110.0, "flops_per_problem": 6271156224.0}, "parity.sumd20": {"acc": 0.864, "reasoning_bytes": 132.68, "flops_per_problem": 7449426984.96}, "parity.sumd24": {"acc": 0.504, "reasoning_bytes": 152.012, "flops_per_problem": 8479839780.864}, "parity.inc16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6271156224.0}, "parity.inc20": {"acc": 0.926, "reasoning_bytes": 134.46, "flops_per_problem": 7483874181.12}, "parity.inc24": {"acc": 0.52, "reasoning_bytes": 153.072, "flops_per_problem": 8482489565.184}, "sumd.cmp6": {"acc": 1.0, "reasoning_bytes": 62.088, "flops_per_problem": 3713407746.048}, "sumd.cmp7": {"acc": 0.992, "reasoning_bytes": 70.072, "flops_per_problem": 4110345437.184}, "sumd.cmp8": {"acc": 0.958, "reasoning_bytes": 73.046, "flops_per_problem": 4285761159.168}, "sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.996, "reasoning_bytes": 75.48, "flops_per_problem": 4349179330.56}, "sumd.runmax8": {"acc": 0.886, "reasoning_bytes": 82.866, "flops_per_problem": 4719530852.352}, "sumd.count6": {"acc": 0.998, "reasoning_bytes": 66.428, "flops_per_problem": 3949415202.816}, "sumd.count7": {"acc": 0.998, "reasoning_bytes": 74.458, "flops_per_problem": 4348207742.976}, "sumd.count8": {"acc": 0.8, "reasoning_bytes": 79.952, "flops_per_problem": 4635002732.544}, "sumd.find6": {"acc": 1.0, "reasoning_bytes": 66.24, "flops_per_problem": 3896949473.28}, "sumd.find7": {"acc": 0.994, "reasoning_bytes": 74.44, "flops_per_problem": 4303249735.68}, "sumd.find8": {"acc": 0.912, "reasoning_bytes": 80.24, "flops_per_problem": 4603558625.28}, "sumd.rev6": {"acc": 1.0, "reasoning_bytes": 61.544, "flops_per_problem": 3601145217.024}, "sumd.rev7": {"acc": 0.992, "reasoning_bytes": 69.48, "flops_per_problem": 3995874754.56}, "sumd.rev8": {"acc": 0.806, "reasoning_bytes": 76.02, "flops_per_problem": 4328775991.296}, "sumd.sumd6": {"acc": 1.0, "reasoning_bytes": 65.744, "flops_per_problem": 3795639386.112}, "sumd.sumd7": {"acc": 0.996, "reasoning_bytes": 73.738, "flops_per_problem": 4195315187.712}, "sumd.sumd8": {"acc": 0.834, "reasoning_bytes": 81.148, "flops_per_problem": 4567963189.248}, "sumd.inc6": {"acc": 1.0, "reasoning_bytes": 68.538, "flops_per_problem": 3910021742.592}, "sumd.inc7": {"acc": 0.98, "reasoning_bytes": 76.48, "flops_per_problem": 4305016258.56}, "sumd.inc8": {"acc": 0.756, "reasoning_bytes": 83.366, "flops_per_problem": 4653551222.784}, "inc.cmp6": {"acc": 0.994, "reasoning_bytes": 78.624, "flops_per_problem": 4576354172.928}, "inc.cmp7": {"acc": 0.986, "reasoning_bytes": 89.804, "flops_per_problem": 5158423461.888}, "inc.cmp8": {"acc": 0.85, "reasoning_bytes": 100.528, "flops_per_problem": 5720354390.016}, "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": 0.892, "reasoning_bytes": 135.552, "flops_per_problem": 7002143391.744}, "inc.count6": {"acc": 0.986, "reasoning_bytes": 98.998, "flops_per_problem": 5343643385.856}, "inc.count7": {"acc": 0.958, "reasoning_bytes": 113.998, "flops_per_problem": 6050252537.856}, "inc.count8": {"acc": 0.71, "reasoning_bytes": 118.684, "flops_per_problem": 6301363765.248}, "inc.find6": {"acc": 0.97, "reasoning_bytes": 91.88, "flops_per_problem": 4985127567.36}, "inc.find7": {"acc": 0.876, "reasoning_bytes": 102.89, "flops_per_problem": 5515526062.08}, "inc.find8": {"acc": 0.41, "reasoning_bytes": 117.706, "flops_per_problem": 6214009208.832}, "inc.rev6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5608710144.0}, "inc.rev7": {"acc": 0.986, "reasoning_bytes": 123.996, "flops_per_problem": 6580121075.712}, "inc.rev8": {"acc": 0.006, "reasoning_bytes": 134.346, "flops_per_problem": 7085699923.968}, "inc.sumd6": {"acc": 0.996, "reasoning_bytes": 109.558, "flops_per_problem": 5721590956.032}, "inc.sumd7": {"acc": 0.962, "reasoning_bytes": 127.484, "flops_per_problem": 6557421256.704}, "inc.sumd8": {"acc": 0.158, "reasoning_bytes": 142.378, "flops_per_problem": 7259260796.928}, "inc.inc6": {"acc": 1.0, "reasoning_bytes": 113.0, "flops_per_problem": 6006177792.0}, "inc.inc7": {"acc": 0.982, "reasoning_bytes": 131.0, "flops_per_problem": 6889439232.0}, "inc.inc8": {"acc": 0.108, "reasoning_bytes": 142.164, "flops_per_problem": 7438474543.104}, "count.inc.cmp16": {"acc": 0.542, "reasoning_bytes": 111.744, "flops_per_problem": 6613155053.568}, "count.inc.cmp18": {"acc": 0.6, "reasoning_bytes": 119.362, "flops_per_problem": 7038533763.072}, "count.inc.cmp20": {"acc": 0.66, "reasoning_bytes": 126.208, "flops_per_problem": 7429023645.696}, "inc.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 161.0, "flops_per_problem": 8346820608.0}, "inc.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 192.392, "flops_per_problem": 9820542320.64}, "inc.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 202.274, "flops_per_problem": 10302449762.304}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7551885312.0}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 148.944, "flops_per_problem": 8609325907.968}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 170.928, "flops_per_problem": 9756859170.816}, "add.count.find6": {"acc": 0.0, "reasoning_bytes": 136.94, "flops_per_problem": 7637031714.816}, "add.count.find7": {"acc": 0.0, "reasoning_bytes": 151.43, "flops_per_problem": 8377911410.688}, "add.count.find8": {"acc": 0.0, "reasoning_bytes": 149.266, "flops_per_problem": 8499183206.4}, "runmax.inc.find12": {"acc": 0.876, "reasoning_bytes": 105.382, "flops_per_problem": 6155537301.504}, "runmax.inc.find14": {"acc": 0.896, "reasoning_bytes": 116.106, "flops_per_problem": 6717468229.632}, "runmax.inc.find16": {"acc": 0.824, "reasoning_bytes": 123.37, "flops_per_problem": 7126594928.64}, "parity.sumd.rev16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.sumd.rev20": {"acc": 0.57, "reasoning_bytes": 140.816, "flops_per_problem": 7985390026.752}, "parity.sumd.rev24": {"acc": 0.488, "reasoning_bytes": 162.976, "flops_per_problem": 9140695990.272}, "parity.rev.sumd16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.rev.sumd20": {"acc": 0.604, "reasoning_bytes": 141.188, "flops_per_problem": 8001818689.536}, "parity.rev.sumd24": {"acc": 0.506, "reasoning_bytes": 163.652, "flops_per_problem": 9170550226.944}, "count.inc.sumd16": {"acc": 0.998, "reasoning_bytes": 110.0, "flops_per_problem": 6491971584.0}, "count.inc.sumd18": {"acc": 0.918, "reasoning_bytes": 117.79, "flops_per_problem": 6924328058.88}, "count.inc.sumd20": {"acc": 0.802, "reasoning_bytes": 124.95, "flops_per_problem": 7328861798.4}, "inc.sumd.rev6": {"acc": 0.996, "reasoning_bytes": 128.544, "flops_per_problem": 6736723329.024}, "inc.sumd.rev7": {"acc": 0.95, "reasoning_bytes": 146.466, "flops_per_problem": 7572376977.408}, "inc.sumd.rev8": {"acc": 0.084, "reasoning_bytes": 159.942, "flops_per_problem": 8211769933.824}, "count.count.cmp16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6801113088.0}, "count.count.cmp18": {"acc": 1.0, "reasoning_bytes": 121.69, "flops_per_problem": 7317379399.68}, "count.count.cmp20": {"acc": 1.0, "reasoning_bytes": 127.34, "flops_per_problem": 7655226900.48}, "parity.rev.find16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7154417664.0}, "parity.rev.find20": {"acc": 0.914, "reasoning_bytes": 143.464, "flops_per_problem": 8190659985.408}, "parity.rev.find24": {"acc": 0.86, "reasoning_bytes": 165.736, "flops_per_problem": 9350912212.992}, "count.sumd.cmp16": {"acc": 1.0, "reasoning_bytes": 110.0, "flops_per_problem": 6580297728.0}, "count.sumd.cmp18": {"acc": 0.976, "reasoning_bytes": 118.78, "flops_per_problem": 7056375644.16}, "count.sumd.cmp20": {"acc": 0.95, "reasoning_bytes": 125.05, "flops_per_problem": 7421604249.6}, "sumd.count.count6": {"acc": 1.0, "reasoning_bytes": 83.468, "flops_per_problem": 5055258525.696}, "sumd.count.count7": {"acc": 1.0, "reasoning_bytes": 91.496, "flops_per_problem": 5453962739.712}, "sumd.count.count8": {"acc": 0.996, "reasoning_bytes": 94.62, "flops_per_problem": 5636091248.64}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 99.0, "flops_per_problem": 5772378488.832}, "runmax.rev.inc14": {"acc": 1.0, "reasoning_bytes": 110.928, "flops_per_problem": 6390838149.12}, "runmax.rev.inc16": {"acc": 0.972, "reasoning_bytes": 117.484, "flops_per_problem": 6770198937.6}, "parity.sumd.find16": {"acc": 1.0, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.sumd.find20": {"acc": 0.878, "reasoning_bytes": 145.288, "flops_per_problem": 8315376500.736}, "parity.sumd.find24": {"acc": 0.858, "reasoning_bytes": 167.252, "flops_per_problem": 9462026502.144}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 116.0, "flops_per_problem": 6801113088.0}, "runmax.runmax.cmp16": {"acc": 0.994, "reasoning_bytes": 122.476, "flops_per_problem": 7175439286.272}, "count.runmax.count16": {"acc": 1.0, "reasoning_bytes": 113.0, "flops_per_problem": 6889439232.0}, "count.runmax.count18": {"acc": 1.0, "reasoning_bytes": 122.44, "flops_per_problem": 7394664775.68}, "count.runmax.count20": {"acc": 1.0, "reasoning_bytes": 128.2, "flops_per_problem": 7737370214.4}, "inc.inc.sumd6": {"acc": 0.972, "reasoning_bytes": 175.56, "flops_per_problem": 8813182648.32}, "inc.inc.sumd7": {"acc": 0.776, "reasoning_bytes": 203.326, "flops_per_problem": 10083400925.184}, "inc.inc.sumd8": {"acc": 0.04, "reasoning_bytes": 218.392, "flops_per_problem": 10795839602.688}, "add.sumd.find6": {"acc": 1.0, "reasoning_bytes": 150.512, "flops_per_problem": 8104453668.864}, "add.sumd.find7": {"acc": 0.906, "reasoning_bytes": 170.034, "flops_per_problem": 9054931304.448}, "add.sumd.find8": {"acc": 0.676, "reasoning_bytes": 187.914, "flops_per_problem": 9932893175.808}, "sumd.rev.rev6": {"acc": 1.0, "reasoning_bytes": 80.53, "flops_per_problem": 4616277590.016}, "sumd.rev.rev7": {"acc": 0.986, "reasoning_bytes": 88.48, "flops_per_problem": 5011625410.56}, "sumd.rev.rev8": {"acc": 0.488, "reasoning_bytes": 92.126, "flops_per_problem": 5216718716.928}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.648, "flops_per_problem": 6343936966.656}, "runmax.inc.runmax14": {"acc": 1.0, "reasoning_bytes": 122.188, "flops_per_problem": 6986068033.536}, "runmax.inc.runmax16": {"acc": 0.974, "reasoning_bytes": 128.504, "flops_per_problem": 7353328140.288}, "parity.inc.find16": {"acc": 1.0, "reasoning_bytes": 128.0, "flops_per_problem": 7331069952.0}, "parity.inc.find20": {"acc": 0.91, "reasoning_bytes": 146.42, "flops_per_problem": 8321206026.24}, "parity.inc.find24": {"acc": 0.844, "reasoning_bytes": 169.292, "flops_per_problem": 9507956097.024}, "inc.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 119.0, "flops_per_problem": 6403645440.0}, "inc.runmax.sumd7": {"acc": 1.0, "reasoning_bytes": 134.996, "flops_per_problem": 7154241011.712}, "inc.runmax.sumd8": {"acc": 0.852, "reasoning_bytes": 149.856, "flops_per_problem": 7854667333.632}, "sumd.rev.cmp6": {"acc": 0.94, "reasoning_bytes": 81.098, "flops_per_problem": 4729600032.768}, "sumd.rev.cmp7": {"acc": 0.892, "reasoning_bytes": 89.054, "flops_per_problem": 5126184419.328}, "sumd.rev.cmp8": {"acc": 0.602, "reasoning_bytes": 90.778, "flops_per_problem": 5247809519.616}, "runmax.runmax.count12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6315319296.0}, "runmax.runmax.count14": {"acc": 1.0, "reasoning_bytes": 116.904, "flops_per_problem": 6929362649.088}, "runmax.runmax.count16": {"acc": 1.0, "reasoning_bytes": 123.72, "flops_per_problem": 7318704291.84}, "count.count.count16": {"acc": 1.0, "reasoning_bytes": 113.0, "flops_per_problem": 6933602304.0}, "count.count.count18": {"acc": 1.0, "reasoning_bytes": 122.78, "flops_per_problem": 7453843292.16}, "count.count.count20": {"acc": 0.998, "reasoning_bytes": 128.628, "flops_per_problem": 7800523407.36}, "add.sumd.rev6": {"acc": 0.996, "reasoning_bytes": 145.448, "flops_per_problem": 7792309075.968}, "add.sumd.rev7": {"acc": 0.928, "reasoning_bytes": 165.308, "flops_per_problem": 8757802156.032}, "add.sumd.rev8": {"acc": 0.06, "reasoning_bytes": 183.986, "flops_per_problem": 9671006158.848}, "add.rev.rev6": {"acc": 0.998, "reasoning_bytes": 187.496, "flops_per_problem": 9808618291.2}, "add.rev.rev7": {"acc": 0.54, "reasoning_bytes": 222.536, "flops_per_problem": 11484341895.168}, "add.rev.rev8": {"acc": 0.0, "reasoning_bytes": 238.402, "flops_per_problem": 12280337104.896}, "inc.runmax.cmp6": {"acc": 0.932, "reasoning_bytes": 104.036, "flops_per_problem": 5786952302.592}, "inc.runmax.cmp7": {"acc": 0.66, "reasoning_bytes": 120.614, "flops_per_problem": 6563250782.208}, "inc.runmax.cmp8": {"acc": 0.548, "reasoning_bytes": 137.004, "flops_per_problem": 7331246604.288}, "count.rev.cmp16": {"acc": 0.998, "reasoning_bytes": 107.0, "flops_per_problem": 6403645440.0}, "count.rev.cmp18": {"acc": 0.98, "reasoning_bytes": 115.59, "flops_per_problem": 6871420698.624}, "count.rev.cmp20": {"acc": 0.952, "reasoning_bytes": 122.03, "flops_per_problem": 7244245352.448}} +{"step": 11000, "train_loss": 1.0686603784561157} +{"step": 11020, "train_loss": 1.0327025651931763} +{"step": 11040, "train_loss": 1.1236143112182617} +{"step": 11060, "train_loss": 1.1080090999603271} +{"step": 11080, "train_loss": 1.0630263090133667} +{"step": 11100, "train_loss": 1.0686579942703247} +{"step": 11120, "train_loss": 1.0800548791885376} +{"step": 11140, "train_loss": 1.0462645292282104} +{"step": 11160, "train_loss": 1.0784778594970703} +{"step": 11180, "train_loss": 1.0194615125656128} +{"step": 11200, "train_loss": 1.0851942300796509} +{"step": 11220, "train_loss": 0.9742832183837891} +{"step": 11240, "train_loss": 1.0247802734375} +{"step": 11260, "train_loss": 1.0359441041946411} +{"step": 11280, "train_loss": 1.105023741722107} +{"step": 11300, "train_loss": 1.027880072593689} +{"step": 11320, "train_loss": 1.0517120361328125} +{"step": 11340, "train_loss": 1.0487339496612549} +{"step": 11360, "train_loss": 0.9963016510009766} +{"step": 11380, "train_loss": 0.9395204186439514} +{"step": 11400, "train_loss": 1.1037189960479736} +{"step": 11420, "train_loss": 1.0700068473815918} +{"step": 11440, "train_loss": 1.0549354553222656} +{"step": 11460, "train_loss": 1.052868366241455} +{"step": 11480, "train_loss": 1.0329058170318604} +{"step": 11500, "train_loss": 0.9869112968444824} +{"step": 11520, "train_loss": 1.038278341293335} +{"step": 11540, "train_loss": 1.0377647876739502} +{"step": 11560, "train_loss": 0.9898301959037781} +{"step": 11580, "train_loss": 1.0574612617492676} +{"step": 11600, "train_loss": 1.025036334991455} +{"step": 11620, "train_loss": 1.0244226455688477} +{"step": 11640, "train_loss": 1.0924222469329834} +{"step": 11660, "train_loss": 0.9797552824020386} +{"step": 11680, "train_loss": 1.0384376049041748} +{"step": 11700, "train_loss": 1.0030521154403687} +{"step": 11720, "train_loss": 1.075222134590149} +{"step": 11740, "train_loss": 1.0595295429229736} +{"step": 11760, "train_loss": 1.0754649639129639} +{"step": 11780, "train_loss": 1.1061865091323853} +{"step": 11800, "train_loss": 1.001539945602417} +{"step": 11820, "train_loss": 1.0700492858886719} +{"step": 11840, "train_loss": 0.9434441328048706} +{"step": 11860, "train_loss": 1.0784876346588135} +{"step": 11880, "train_loss": 1.0249285697937012} +{"step": 11900, "train_loss": 1.0783345699310303} +{"step": 11920, "train_loss": 1.0058486461639404} +{"step": 11940, "train_loss": 1.005518913269043} +{"step": 11960, "train_loss": 1.0302447080612183} +{"step": 11980, "train_loss": 1.0365796089172363} +{"step": 12000, "tokens": 393216000, "val_loss": 1.7899871528148652, "val_bpb": 0.6452612880011628, "lr": 6.039882929516903e-05, "elapsed": 2011.0153152942657, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.99, "reasoning_bytes": 78.992, "flops_per_problem": 4928333856.768}, "add9": {"acc": 0.664, "reasoning_bytes": 88.956, "flops_per_problem": 5501393879.04}, "add10": {"acc": 0.0, "reasoning_bytes": 97.048, "flops_per_problem": 5990809042.944}, "reach14": {"acc": 0.582, "reasoning_bytes": 7.768, "flops_per_problem": 4628554924.032}, "reach16": {"acc": 0.54, "reasoning_bytes": 7.706, "flops_per_problem": 5153212219.392}, "reach18": {"acc": 0.564, "reasoning_bytes": 7.886, "flops_per_problem": 5691295088.64}, "parity24": {"acc": 0.73, "reasoning_bytes": 141.8, "flops_per_problem": 7808031129.6}, "parity28": {"acc": 0.548, "reasoning_bytes": 163.268, "flops_per_problem": 8932776247.296}, "parity32": {"acc": 0.522, "reasoning_bytes": 185.852, "flops_per_problem": 10106807353.344}, "cmp8": {"acc": 0.99, "reasoning_bytes": 5.812, "flops_per_problem": 1360752574.464}, "cmp9": {"acc": 0.992, "reasoning_bytes": 5.684, "flops_per_problem": 1443425845.248}, "cmp10": {"acc": 0.99, "reasoning_bytes": 5.744, "flops_per_problem": 1534401773.568}, "runmax12": {"acc": 1.0, "reasoning_bytes": 70.976, "flops_per_problem": 4150268854.272}, "runmax14": {"acc": 1.0, "reasoning_bytes": 82.616, "flops_per_problem": 4752653156.352}, "runmax16": {"acc": 0.994, "reasoning_bytes": 92.22, "flops_per_problem": 5265386422.272}, "count16": {"acc": 0.992, "reasoning_bytes": 78.96, "flops_per_problem": 4723682181.12}, "count18": {"acc": 0.94, "reasoning_bytes": 87.53, "flops_per_problem": 5190485852.16}, "count20": {"acc": 0.826, "reasoning_bytes": 94.55, "flops_per_problem": 5588836761.6}, "brackets16": {"acc": 0.862, "reasoning_bytes": 51.156, "flops_per_problem": 3539935199.232}, "brackets18": {"acc": 0.864, "reasoning_bytes": 51.678, "flops_per_problem": 3651579445.248}, "brackets20": {"acc": 0.784, "reasoning_bytes": 56.304, "flops_per_problem": 3943938981.888}, "sumd8": {"acc": 0.956, "reasoning_bytes": 58.554, "flops_per_problem": 3380771487.744}, "sumd9": {"acc": 0.768, "reasoning_bytes": 65.816, "flops_per_problem": 3745735114.752}, "sumd10": {"acc": 0.324, "reasoning_bytes": 70.434, "flops_per_problem": 3993754927.104}, "inc8": {"acc": 0.998, "reasoning_bytes": 63.0, "flops_per_problem": 3798024192.0}, "inc9": {"acc": 0.844, "reasoning_bytes": 71.0, "flops_per_problem": 4239743238.144}, "inc10": {"acc": 0.004, "reasoning_bytes": 78.168, "flops_per_problem": 4640125648.896}, "add.cmp6": {"acc": 0.994, "reasoning_bytes": 92.632, "flops_per_problem": 5532484681.728}, "add.cmp7": {"acc": 0.97, "reasoning_bytes": 105.414, "flops_per_problem": 6226728173.568}, "add.cmp8": {"acc": 0.922, "reasoning_bytes": 118.082, "flops_per_problem": 6920176730.112}, "add.runmax6": {"acc": 0.998, "reasoning_bytes": 120.832, "flops_per_problem": 6572878331.904}, "add.runmax7": {"acc": 0.992, "reasoning_bytes": 138.826, "flops_per_problem": 7455874793.472}, "add.runmax8": {"acc": 0.686, "reasoning_bytes": 156.068, "flops_per_problem": 8305660624.896}, "add.count6": {"acc": 0.994, "reasoning_bytes": 115.65, "flops_per_problem": 6388188364.8}, "add.count7": {"acc": 0.874, "reasoning_bytes": 131.366, "flops_per_problem": 7170581348.352}, "add.count8": {"acc": 0.44, "reasoning_bytes": 146.208, "flops_per_problem": 7914375806.976}, "add.find6": {"acc": 0.954, "reasoning_bytes": 107.816, "flops_per_problem": 5998051786.752}, "add.find7": {"acc": 0.862, "reasoning_bytes": 121.868, "flops_per_problem": 6706957418.496}, "add.find8": {"acc": 0.416, "reasoning_bytes": 139.76, "flops_per_problem": 7586685812.736}, "add.rev6": {"acc": 1.0, "reasoning_bytes": 123.248, "flops_per_problem": 6794576953.344}, "add.rev7": {"acc": 0.756, "reasoning_bytes": 144.688, "flops_per_problem": 7869594451.968}, "add.rev8": {"acc": 0.018, "reasoning_bytes": 158.816, "flops_per_problem": 8591749005.312}, "add.sumd6": {"acc": 0.998, "reasoning_bytes": 126.476, "flops_per_problem": 6777794985.984}, "add.sumd7": {"acc": 0.926, "reasoning_bytes": 146.292, "flops_per_problem": 7741344890.88}, "add.sumd8": {"acc": 0.188, "reasoning_bytes": 164.06, "flops_per_problem": 8614448824.32}, "add.inc6": {"acc": 0.998, "reasoning_bytes": 131.04, "flops_per_problem": 7138695610.368}, "add.inc7": {"acc": 0.814, "reasoning_bytes": 150.484, "flops_per_problem": 8129096663.04}, "add.inc8": {"acc": 0.05, "reasoning_bytes": 163.406, "flops_per_problem": 8816362389.504}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5122916352.0}, "runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 97.02, "flops_per_problem": 5653756477.44}, "runmax.cmp16": {"acc": 1.0, "reasoning_bytes": 105.022, "flops_per_problem": 6095475523.584}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 87.976, "flops_per_problem": 5210182582.272}, "runmax.runmax14": {"acc": 1.0, "reasoning_bytes": 98.272, "flops_per_problem": 5753211715.584}, "runmax.runmax16": {"acc": 0.98, "reasoning_bytes": 105.91, "flops_per_problem": 6179120381.952}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5255405568.0}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 98.86, "flops_per_problem": 5823342673.92}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 106.108, "flops_per_problem": 6231762763.776}, "runmax.find12": {"acc": 1.0, "reasoning_bytes": 87.964, "flops_per_problem": 5209652625.408}, "runmax.find14": {"acc": 1.0, "reasoning_bytes": 96.712, "flops_per_problem": 5684317323.264}, "runmax.find16": {"acc": 0.992, "reasoning_bytes": 105.862, "flops_per_problem": 6177000554.496}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 82.952, "flops_per_problem": 4855818092.544}, "runmax.rev14": {"acc": 0.998, "reasoning_bytes": 93.212, "flops_per_problem": 5397257355.264}, "runmax.rev16": {"acc": 0.982, "reasoning_bytes": 101.044, "flops_per_problem": 5831557005.312}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 85.976, "flops_per_problem": 5033530294.272}, "runmax.sumd14": {"acc": 0.998, "reasoning_bytes": 95.78, "flops_per_problem": 5554831196.16}, "runmax.sumd16": {"acc": 0.982, "reasoning_bytes": 104.05, "flops_per_problem": 6008474271.744}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 86.94, "flops_per_problem": 5063119552.512}, "runmax.inc14": {"acc": 0.998, "reasoning_bytes": 97.356, "flops_per_problem": 5614892974.08}, "runmax.inc16": {"acc": 0.992, "reasoning_bytes": 105.12, "flops_per_problem": 6048397688.832}, "count.cmp16": {"acc": 1.0, "reasoning_bytes": 94.98, "flops_per_problem": 5696153026.56}, "count.cmp18": {"acc": 0.986, "reasoning_bytes": 103.312, "flops_per_problem": 6152534212.608}, "count.cmp20": {"acc": 0.95, "reasoning_bytes": 110.01, "flops_per_problem": 6536752939.008}, "count.runmax16": {"acc": 0.992, "reasoning_bytes": 95.94, "flops_per_problem": 5782712647.68}, "count.runmax18": {"acc": 0.906, "reasoning_bytes": 103.59, "flops_per_problem": 6208886292.48}, "count.runmax20": {"acc": 0.792, "reasoning_bytes": 111.01, "flops_per_problem": 6624902430.72}, "count.count16": {"acc": 1.0, "reasoning_bytes": 95.99, "flops_per_problem": 5829083873.28}, "count.count18": {"acc": 1.0, "reasoning_bytes": 104.85, "flops_per_problem": 6308694835.2}, "count.count20": {"acc": 0.996, "reasoning_bytes": 111.108, "flops_per_problem": 6673393483.776}, "count.find16": {"acc": 1.0, "reasoning_bytes": 95.99, "flops_per_problem": 5784920801.28}, "count.find18": {"acc": 0.976, "reasoning_bytes": 104.24, "flops_per_problem": 6237592289.28}, "count.find20": {"acc": 0.914, "reasoning_bytes": 111.02, "flops_per_problem": 6625344061.44}, "count.rev16": {"acc": 0.988, "reasoning_bytes": 90.92, "flops_per_problem": 5428524810.24}, "count.rev18": {"acc": 0.872, "reasoning_bytes": 98.02, "flops_per_problem": 5830408765.44}, "count.rev20": {"acc": 0.794, "reasoning_bytes": 105.9, "flops_per_problem": 6266739916.8}, "count.sumd16": {"acc": 0.986, "reasoning_bytes": 93.96, "flops_per_problem": 5606943621.12}, "count.sumd18": {"acc": 0.898, "reasoning_bytes": 101.51, "flops_per_problem": 6028700958.72}, "count.sumd20": {"acc": 0.794, "reasoning_bytes": 108.99, "flops_per_problem": 6447366881.28}, "count.inc16": {"acc": 0.994, "reasoning_bytes": 94.98, "flops_per_problem": 5607826882.56}, "count.inc18": {"acc": 0.902, "reasoning_bytes": 102.562, "flops_per_problem": 6030997438.464}, "count.inc20": {"acc": 0.772, "reasoning_bytes": 110.01, "flops_per_problem": 6448250142.72}, "parity.cmp16": {"acc": 1.0, "reasoning_bytes": 110.952, "flops_per_problem": 6357362540.544}, "parity.cmp20": {"acc": 0.962, "reasoning_bytes": 130.752, "flops_per_problem": 7408443654.144}, "parity.cmp24": {"acc": 0.948, "reasoning_bytes": 149.52, "flops_per_problem": 8413948477.44}, "parity.runmax16": {"acc": 0.99, "reasoning_bytes": 111.952, "flops_per_problem": 6445688684.544}, "parity.runmax20": {"acc": 0.696, "reasoning_bytes": 132.52, "flops_per_problem": 7530687037.44}, "parity.runmax24": {"acc": 0.618, "reasoning_bytes": 152.74, "flops_per_problem": 8600316641.28}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 111.952, "flops_per_problem": 6489851756.544}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 133.216, "flops_per_problem": 7605587607.552}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 153.208, "flops_per_problem": 8665148030.976}, "parity.find16": {"acc": 0.996, "reasoning_bytes": 111.952, "flops_per_problem": 6445688684.544}, "parity.find20": {"acc": 0.92, "reasoning_bytes": 133.0, "flops_per_problem": 7551885312.0}, "parity.find24": {"acc": 0.838, "reasoning_bytes": 153.04, "flops_per_problem": 8613565562.88}, "parity.rev16": {"acc": 0.996, "reasoning_bytes": 106.964, "flops_per_problem": 6092914065.408}, "parity.rev20": {"acc": 0.728, "reasoning_bytes": 128.456, "flops_per_problem": 7218719096.832}, "parity.rev24": {"acc": 0.532, "reasoning_bytes": 148.4, "flops_per_problem": 8276159692.8}, "parity.sumd16": {"acc": 1.0, "reasoning_bytes": 109.964, "flops_per_problem": 6269566353.408}, "parity.sumd20": {"acc": 0.728, "reasoning_bytes": 131.252, "flops_per_problem": 7386362118.144}, "parity.sumd24": {"acc": 0.522, "reasoning_bytes": 151.524, "flops_per_problem": 8458288201.728}, "parity.inc16": {"acc": 0.998, "reasoning_bytes": 110.988, "flops_per_problem": 6270626267.136}, "parity.inc20": {"acc": 0.75, "reasoning_bytes": 132.6, "flops_per_problem": 7401730867.2}, "parity.inc24": {"acc": 0.566, "reasoning_bytes": 152.652, "flops_per_problem": 8463941074.944}, "sumd.cmp6": {"acc": 1.0, "reasoning_bytes": 62.088, "flops_per_problem": 3713407746.048}, "sumd.cmp7": {"acc": 0.994, "reasoning_bytes": 69.96, "flops_per_problem": 4105399173.12}, "sumd.cmp8": {"acc": 0.95, "reasoning_bytes": 72.67, "flops_per_problem": 4269155844.096}, "sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.992, "reasoning_bytes": 75.48, "flops_per_problem": 4349179330.56}, "sumd.runmax8": {"acc": 0.802, "reasoning_bytes": 82.212, "flops_per_problem": 4690648203.264}, "sumd.count6": {"acc": 1.0, "reasoning_bytes": 66.428, "flops_per_problem": 3949415202.816}, "sumd.count7": {"acc": 0.998, "reasoning_bytes": 74.458, "flops_per_problem": 4348207742.976}, "sumd.count8": {"acc": 0.83, "reasoning_bytes": 80.114, "flops_per_problem": 4642157150.208}, "sumd.find6": {"acc": 1.0, "reasoning_bytes": 66.24, "flops_per_problem": 3896949473.28}, "sumd.find7": {"acc": 0.992, "reasoning_bytes": 74.464, "flops_per_problem": 4304309649.408}, "sumd.find8": {"acc": 0.89, "reasoning_bytes": 79.954, "flops_per_problem": 4590927986.688}, "sumd.rev6": {"acc": 1.0, "reasoning_bytes": 61.544, "flops_per_problem": 3601145217.024}, "sumd.rev7": {"acc": 0.99, "reasoning_bytes": 69.48, "flops_per_problem": 3995874754.56}, "sumd.rev8": {"acc": 0.688, "reasoning_bytes": 75.0, "flops_per_problem": 4283729657.856}, "sumd.sumd6": {"acc": 1.0, "reasoning_bytes": 65.744, "flops_per_problem": 3795639386.112}, "sumd.sumd7": {"acc": 0.99, "reasoning_bytes": 73.738, "flops_per_problem": 4195315187.712}, "sumd.sumd8": {"acc": 0.792, "reasoning_bytes": 80.57, "flops_per_problem": 4542701912.064}, "sumd.inc6": {"acc": 1.0, "reasoning_bytes": 68.538, "flops_per_problem": 3910021742.592}, "sumd.inc7": {"acc": 0.976, "reasoning_bytes": 76.48, "flops_per_problem": 4305016258.56}, "sumd.inc8": {"acc": 0.668, "reasoning_bytes": 82.6, "flops_per_problem": 4619987288.064}, "inc.cmp6": {"acc": 0.994, "reasoning_bytes": 78.622, "flops_per_problem": 4576265846.784}, "inc.cmp7": {"acc": 0.984, "reasoning_bytes": 89.756, "flops_per_problem": 5156303634.432}, "inc.cmp8": {"acc": 0.89, "reasoning_bytes": 99.752, "flops_per_problem": 5686083846.144}, "inc.runmax6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5520384000.0}, "inc.runmax7": {"acc": 1.0, "reasoning_bytes": 119.992, "flops_per_problem": 6270802919.424}, "inc.runmax8": {"acc": 0.844, "reasoning_bytes": 125.71, "flops_per_problem": 6567490437.12}, "inc.count6": {"acc": 0.994, "reasoning_bytes": 98.998, "flops_per_problem": 5343643385.856}, "inc.count7": {"acc": 0.9, "reasoning_bytes": 113.882, "flops_per_problem": 6045129621.504}, "inc.count8": {"acc": 0.794, "reasoning_bytes": 114.566, "flops_per_problem": 6119500234.752}, "inc.find6": {"acc": 0.998, "reasoning_bytes": 91.88, "flops_per_problem": 4985127567.36}, "inc.find7": {"acc": 0.912, "reasoning_bytes": 102.518, "flops_per_problem": 5499097399.296}, "inc.find8": {"acc": 0.622, "reasoning_bytes": 110.572, "flops_per_problem": 5898949853.184}, "inc.rev6": {"acc": 0.998, "reasoning_bytes": 104.0, "flops_per_problem": 5608798470.144}, "inc.rev7": {"acc": 0.97, "reasoning_bytes": 123.996, "flops_per_problem": 6580121075.712}, "inc.rev8": {"acc": 0.0, "reasoning_bytes": 130.506, "flops_per_problem": 6913728921.6}, "inc.sumd6": {"acc": 0.998, "reasoning_bytes": 109.558, "flops_per_problem": 5721590956.032}, "inc.sumd7": {"acc": 0.968, "reasoning_bytes": 127.404, "flops_per_problem": 6553888210.944}, "inc.sumd8": {"acc": 0.098, "reasoning_bytes": 140.772, "flops_per_problem": 7188334903.296}, "inc.inc6": {"acc": 1.0, "reasoning_bytes": 113.0, "flops_per_problem": 6006177792.0}, "inc.inc7": {"acc": 0.988, "reasoning_bytes": 131.018, "flops_per_problem": 6889880862.72}, "inc.inc8": {"acc": 0.016, "reasoning_bytes": 139.258, "flops_per_problem": 7310136655.872}, "count.inc.cmp16": {"acc": 0.562, "reasoning_bytes": 102.698, "flops_per_problem": 6213655904.256}, "count.inc.cmp18": {"acc": 0.544, "reasoning_bytes": 109.662, "flops_per_problem": 6610505269.248}, "count.inc.cmp20": {"acc": 0.53, "reasoning_bytes": 117.354, "flops_per_problem": 7038003806.208}, "inc.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 160.994, "flops_per_problem": 8347173912.576}, "inc.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 191.478, "flops_per_problem": 9776732553.216}, "inc.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 198.702, "flops_per_problem": 10150352142.336}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 128.952, "flops_per_problem": 7549765484.544}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 148.284, "flops_per_problem": 8580178280.448}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 167.088, "flops_per_problem": 9587272974.336}, "add.count.find6": {"acc": 0.012, "reasoning_bytes": 135.074, "flops_per_problem": 7555153379.328}, "add.count.find7": {"acc": 0.004, "reasoning_bytes": 150.884, "flops_per_problem": 8351590219.776}, "add.count.find8": {"acc": 0.004, "reasoning_bytes": 155.25, "flops_per_problem": 8725298135.04}, "runmax.inc.find12": {"acc": 0.872, "reasoning_bytes": 105.368, "flops_per_problem": 6154919018.496}, "runmax.inc.find14": {"acc": 0.896, "reasoning_bytes": 113.384, "flops_per_problem": 6597256347.648}, "runmax.inc.find16": {"acc": 0.798, "reasoning_bytes": 122.936, "flops_per_problem": 7107693133.824}, "parity.sumd.rev16": {"acc": 0.998, "reasoning_bytes": 121.916, "flops_per_problem": 6974055677.952}, "parity.sumd.rev20": {"acc": 0.548, "reasoning_bytes": 141.26, "flops_per_problem": 8004998430.72}, "parity.sumd.rev24": {"acc": 0.458, "reasoning_bytes": 159.12, "flops_per_problem": 8970403184.64}, "parity.rev.sumd16": {"acc": 0.998, "reasoning_bytes": 121.904, "flops_per_problem": 6973525721.088}, "parity.rev.sumd20": {"acc": 0.578, "reasoning_bytes": 141.488, "flops_per_problem": 8015067611.136}, "parity.rev.sumd24": {"acc": 0.48, "reasoning_bytes": 161.24, "flops_per_problem": 9064028897.28}, "count.inc.sumd16": {"acc": 0.994, "reasoning_bytes": 109.92, "flops_per_problem": 6488438538.24}, "count.inc.sumd18": {"acc": 0.842, "reasoning_bytes": 116.19, "flops_per_problem": 6853667143.68}, "count.inc.sumd20": {"acc": 0.776, "reasoning_bytes": 124.396, "flops_per_problem": 7304395456.512}, "inc.sumd.rev6": {"acc": 0.998, "reasoning_bytes": 128.544, "flops_per_problem": 6736723329.024}, "inc.sumd.rev7": {"acc": 0.942, "reasoning_bytes": 146.418, "flops_per_problem": 7570257149.952}, "inc.sumd.rev8": {"acc": 0.134, "reasoning_bytes": 150.406, "flops_per_problem": 7790630879.232}, "count.count.cmp16": {"acc": 1.0, "reasoning_bytes": 111.98, "flops_per_problem": 6800229826.56}, "count.count.cmp18": {"acc": 0.998, "reasoning_bytes": 121.03, "flops_per_problem": 7288231772.16}, "count.count.cmp20": {"acc": 0.994, "reasoning_bytes": 127.08, "flops_per_problem": 7643832827.904}, "parity.rev.find16": {"acc": 0.998, "reasoning_bytes": 123.904, "flops_per_problem": 7150178009.088}, "parity.rev.find20": {"acc": 0.904, "reasoning_bytes": 143.644, "flops_per_problem": 8198609338.368}, "parity.rev.find24": {"acc": 0.854, "reasoning_bytes": 162.94, "flops_per_problem": 9227432263.68}, "count.sumd.cmp16": {"acc": 0.998, "reasoning_bytes": 109.96, "flops_per_problem": 6578531205.12}, "count.sumd.cmp18": {"acc": 0.976, "reasoning_bytes": 117.55, "flops_per_problem": 7002055065.6}, "count.sumd.cmp20": {"acc": 0.96, "reasoning_bytes": 124.896, "flops_per_problem": 7414803136.512}, "sumd.count.count6": {"acc": 1.0, "reasoning_bytes": 83.476, "flops_per_problem": 5055611830.272}, "sumd.count.count7": {"acc": 1.0, "reasoning_bytes": 91.366, "flops_per_problem": 5448221540.352}, "sumd.count.count8": {"acc": 1.0, "reasoning_bytes": 94.294, "flops_per_problem": 5621694087.168}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 98.988, "flops_per_problem": 5771848531.968}, "runmax.rev.inc14": {"acc": 1.0, "reasoning_bytes": 108.18, "flops_per_problem": 6269478027.264}, "runmax.rev.inc16": {"acc": 0.988, "reasoning_bytes": 116.988, "flops_per_problem": 6749088989.184}, "parity.sumd.find16": {"acc": 0.998, "reasoning_bytes": 126.952, "flops_per_problem": 7328950124.544}, "parity.sumd.find20": {"acc": 0.896, "reasoning_bytes": 146.212, "flops_per_problem": 8356183179.264}, "parity.sumd.find24": {"acc": 0.852, "reasoning_bytes": 163.276, "flops_per_problem": 9286434127.872}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 115.508, "flops_per_problem": 6779384856.576}, "runmax.runmax.cmp16": {"acc": 1.0, "reasoning_bytes": 122.06, "flops_per_problem": 7157067448.32}, "count.runmax.count16": {"acc": 1.0, "reasoning_bytes": 112.99, "flops_per_problem": 6888997601.28}, "count.runmax.count18": {"acc": 1.0, "reasoning_bytes": 121.36, "flops_per_problem": 7346968657.92}, "count.runmax.count20": {"acc": 1.0, "reasoning_bytes": 128.088, "flops_per_problem": 7732423950.336}, "inc.inc.sumd6": {"acc": 0.976, "reasoning_bytes": 175.56, "flops_per_problem": 8813182648.32}, "inc.inc.sumd7": {"acc": 0.696, "reasoning_bytes": 202.932, "flops_per_problem": 10066265653.248}, "inc.inc.sumd8": {"acc": 0.108, "reasoning_bytes": 210.22, "flops_per_problem": 10432907476.992}, "add.sumd.find6": {"acc": 0.998, "reasoning_bytes": 150.5, "flops_per_problem": 8103923712.0}, "add.sumd.find7": {"acc": 0.906, "reasoning_bytes": 169.66, "flops_per_problem": 9038414315.52}, "add.sumd.find8": {"acc": 0.704, "reasoning_bytes": 186.042, "flops_per_problem": 9850573209.6}, "sumd.rev.rev6": {"acc": 1.0, "reasoning_bytes": 80.53, "flops_per_problem": 4616277590.016}, "sumd.rev.rev7": {"acc": 0.962, "reasoning_bytes": 88.246, "flops_per_problem": 5001202925.568}, "sumd.rev.rev8": {"acc": 0.298, "reasoning_bytes": 90.228, "flops_per_problem": 5132897206.272}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.636, "flops_per_problem": 6343407009.792}, "runmax.inc.runmax14": {"acc": 1.0, "reasoning_bytes": 119.928, "flops_per_problem": 6886259490.816}, "runmax.inc.runmax16": {"acc": 0.984, "reasoning_bytes": 128.64, "flops_per_problem": 7359334318.08}, "parity.inc.find16": {"acc": 1.0, "reasoning_bytes": 127.928, "flops_per_problem": 7327890210.816}, "parity.inc.find20": {"acc": 0.902, "reasoning_bytes": 146.888, "flops_per_problem": 8341874343.936}, "parity.inc.find24": {"acc": 0.846, "reasoning_bytes": 165.812, "flops_per_problem": 9354268606.464}, "inc.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 119.0, "flops_per_problem": 6403645440.0}, "inc.runmax.sumd7": {"acc": 0.99, "reasoning_bytes": 134.894, "flops_per_problem": 7149736378.368}, "inc.runmax.sumd8": {"acc": 0.834, "reasoning_bytes": 139.956, "flops_per_problem": 7417452920.832}, "sumd.rev.cmp6": {"acc": 0.936, "reasoning_bytes": 80.742, "flops_per_problem": 4714319609.856}, "sumd.rev.cmp7": {"acc": 0.81, "reasoning_bytes": 87.746, "flops_per_problem": 5071775514.624}, "sumd.rev.cmp8": {"acc": 0.556, "reasoning_bytes": 89.432, "flops_per_problem": 5191015809.024}, "runmax.runmax.count12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6315319296.0}, "runmax.runmax.count14": {"acc": 1.0, "reasoning_bytes": 116.448, "flops_per_problem": 6909224288.256}, "runmax.runmax.count16": {"acc": 1.0, "reasoning_bytes": 123.108, "flops_per_problem": 7291676491.776}, "count.count.count16": {"acc": 1.0, "reasoning_bytes": 112.97, "flops_per_problem": 6932277411.84}, "count.count.count18": {"acc": 1.0, "reasoning_bytes": 121.95, "flops_per_problem": 7417187942.4}, "count.count.count20": {"acc": 0.998, "reasoning_bytes": 128.256, "flops_per_problem": 7784094744.576}, "add.sumd.rev6": {"acc": 0.994, "reasoning_bytes": 145.444, "flops_per_problem": 7792132423.68}, "add.sumd.rev7": {"acc": 0.862, "reasoning_bytes": 165.24, "flops_per_problem": 8754799067.136}, "add.sumd.rev8": {"acc": 0.056, "reasoning_bytes": 182.044, "flops_per_problem": 9586213060.608}, "add.rev.rev6": {"acc": 0.958, "reasoning_bytes": 187.57, "flops_per_problem": 9812681293.824}, "add.rev.rev7": {"acc": 0.384, "reasoning_bytes": 216.904, "flops_per_problem": 11231994101.76}, "add.rev.rev8": {"acc": 0.0, "reasoning_bytes": 234.936, "flops_per_problem": 12130094333.952}, "inc.runmax.cmp6": {"acc": 0.918, "reasoning_bytes": 104.026, "flops_per_problem": 5786510671.872}, "inc.runmax.cmp7": {"acc": 0.578, "reasoning_bytes": 120.398, "flops_per_problem": 6553711558.656}, "inc.runmax.cmp8": {"acc": 0.4, "reasoning_bytes": 134.67, "flops_per_problem": 7228169994.24}, "count.rev.cmp16": {"acc": 1.0, "reasoning_bytes": 106.96, "flops_per_problem": 6401878917.12}, "count.rev.cmp18": {"acc": 0.97, "reasoning_bytes": 114.57, "flops_per_problem": 6826374365.184}, "count.rev.cmp20": {"acc": 0.96, "reasoning_bytes": 121.92, "flops_per_problem": 7239387414.528}} +{"step": 12000, "train_loss": 1.056150197982788} +{"step": 12020, "train_loss": 0.9815082550048828} +{"step": 12040, "train_loss": 1.040501594543457} +{"step": 12060, "train_loss": 1.0305171012878418} +{"step": 12080, "train_loss": 0.9824275970458984} +{"step": 12100, "train_loss": 1.0790424346923828} +{"step": 12120, "train_loss": 0.9886043071746826} +{"step": 12140, "train_loss": 1.0565736293792725} +{"step": 12160, "train_loss": 1.0080997943878174} +{"step": 12180, "train_loss": 1.1031665802001953} +{"step": 12200, "train_loss": 1.0230519771575928} +{"step": 12207, "tokens": 399998976, "val_loss": 1.8013041317462921, "val_bpb": 0.6493408750474111, "lr": 5.9999999999999995e-05, "elapsed": 2138.6409792900085, "peak_mem_gb": 3.51196672, "add8": {"acc": 0.994, "reasoning_bytes": 79.0, "flops_per_problem": 4928775487.488}, "add9": {"acc": 0.72, "reasoning_bytes": 89.0, "flops_per_problem": 5503690358.784}, "add10": {"acc": 0.0, "reasoning_bytes": 98.988, "flops_per_problem": 6083816472.576}, "reach14": {"acc": 0.632, "reasoning_bytes": 7.302, "flops_per_problem": 4608063258.624}, "reach16": {"acc": 0.572, "reasoning_bytes": 7.366, "flops_per_problem": 5138815057.92}, "reach18": {"acc": 0.534, "reasoning_bytes": 7.886, "flops_per_problem": 5692001697.792}, "parity24": {"acc": 0.834, "reasoning_bytes": 143.012, "flops_per_problem": 7861556772.864}, "parity28": {"acc": 0.524, "reasoning_bytes": 167.948, "flops_per_problem": 9139459424.256}, "parity32": {"acc": 0.474, "reasoning_bytes": 192.884, "flops_per_problem": 10417362075.648}, "cmp8": {"acc": 0.994, "reasoning_bytes": 5.812, "flops_per_problem": 1360752574.464}, "cmp9": {"acc": 0.998, "reasoning_bytes": 5.708, "flops_per_problem": 1444485758.976}, "cmp10": {"acc": 0.99, "reasoning_bytes": 5.768, "flops_per_problem": 1535461687.296}, "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": 0.992, "reasoning_bytes": 94.828, "flops_per_problem": 5380387061.76}, "count16": {"acc": 1.0, "reasoning_bytes": 79.0, "flops_per_problem": 4725448704.0}, "count18": {"acc": 0.99, "reasoning_bytes": 88.97, "flops_per_problem": 5254080675.84}, "count20": {"acc": 0.922, "reasoning_bytes": 98.244, "flops_per_problem": 5751975149.568}, "brackets16": {"acc": 0.994, "reasoning_bytes": 53.466, "flops_per_problem": 3642216873.984}, "brackets18": {"acc": 0.996, "reasoning_bytes": 56.782, "flops_per_problem": 3876722786.304}, "brackets20": {"acc": 0.944, "reasoning_bytes": 63.012, "flops_per_problem": 4240184868.864}, "sumd8": {"acc": 0.972, "reasoning_bytes": 58.554, "flops_per_problem": 3380771487.744}, "sumd9": {"acc": 0.856, "reasoning_bytes": 66.43, "flops_per_problem": 3772762914.816}, "sumd10": {"acc": 0.622, "reasoning_bytes": 74.112, "flops_per_problem": 4155833401.344}, "inc8": {"acc": 0.996, "reasoning_bytes": 63.0, "flops_per_problem": 3798024192.0}, "inc9": {"acc": 0.83, "reasoning_bytes": 71.0, "flops_per_problem": 4239654912.0}, "inc10": {"acc": 0.006, "reasoning_bytes": 78.99, "flops_per_problem": 4680225718.272}, "add.cmp6": {"acc": 0.998, "reasoning_bytes": 92.622, "flops_per_problem": 5532043051.008}, "add.cmp7": {"acc": 0.98, "reasoning_bytes": 105.504, "flops_per_problem": 6230702850.048}, "add.cmp8": {"acc": 0.904, "reasoning_bytes": 118.252, "flops_per_problem": 6927684452.352}, "add.runmax6": {"acc": 1.0, "reasoning_bytes": 120.832, "flops_per_problem": 6572878331.904}, "add.runmax7": {"acc": 0.994, "reasoning_bytes": 138.848, "flops_per_problem": 7456846381.056}, "add.runmax8": {"acc": 0.67, "reasoning_bytes": 156.422, "flops_per_problem": 8321294352.384}, "add.count6": {"acc": 0.99, "reasoning_bytes": 115.648, "flops_per_problem": 6388100038.656}, "add.count7": {"acc": 0.914, "reasoning_bytes": 131.998, "flops_per_problem": 7198492409.856}, "add.count8": {"acc": 0.446, "reasoning_bytes": 147.674, "flops_per_problem": 7979118870.528}, "add.find6": {"acc": 0.952, "reasoning_bytes": 107.708, "flops_per_problem": 5993282174.976}, "add.find7": {"acc": 0.874, "reasoning_bytes": 121.364, "flops_per_problem": 6684699230.208}, "add.find8": {"acc": 0.478, "reasoning_bytes": 139.192, "flops_per_problem": 7560452947.968}, "add.rev6": {"acc": 1.0, "reasoning_bytes": 123.248, "flops_per_problem": 6794576953.344}, "add.rev7": {"acc": 0.904, "reasoning_bytes": 145.854, "flops_per_problem": 7925063270.4}, "add.rev8": {"acc": 0.064, "reasoning_bytes": 162.718, "flops_per_problem": 8770432794.624}, "add.sumd6": {"acc": 0.998, "reasoning_bytes": 126.476, "flops_per_problem": 6777794985.984}, "add.sumd7": {"acc": 0.96, "reasoning_bytes": 146.35, "flops_per_problem": 7743906349.056}, "add.sumd8": {"acc": 0.216, "reasoning_bytes": 165.196, "flops_per_problem": 8664618074.112}, "add.inc6": {"acc": 0.996, "reasoning_bytes": 131.04, "flops_per_problem": 7138695610.368}, "add.inc7": {"acc": 0.948, "reasoning_bytes": 151.02, "flops_per_problem": 8153563004.928}, "add.inc8": {"acc": 0.132, "reasoning_bytes": 165.492, "flops_per_problem": 8906366730.24}, "runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5122916352.0}, "runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 98.82, "flops_per_problem": 5733250007.04}, "runmax.cmp16": {"acc": 0.994, "reasoning_bytes": 105.216, "flops_per_problem": 6104043159.552}, "runmax.runmax12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.runmax14": {"acc": 1.0, "reasoning_bytes": 99.964, "flops_per_problem": 5827935633.408}, "runmax.runmax16": {"acc": 0.968, "reasoning_bytes": 106.56, "flops_per_problem": 6207738052.608}, "runmax.count12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5255405568.0}, "runmax.count14": {"acc": 1.0, "reasoning_bytes": 99.976, "flops_per_problem": 5872628662.272}, "runmax.count16": {"acc": 1.0, "reasoning_bytes": 107.452, "flops_per_problem": 6291117932.544}, "runmax.find12": {"acc": 1.0, "reasoning_bytes": 88.0, "flops_per_problem": 5211242496.0}, "runmax.find14": {"acc": 1.0, "reasoning_bytes": 99.856, "flops_per_problem": 5823166021.632}, "runmax.find16": {"acc": 0.992, "reasoning_bytes": 106.574, "flops_per_problem": 6208268009.472}, "runmax.rev12": {"acc": 1.0, "reasoning_bytes": 83.0, "flops_per_problem": 4857937920.0}, "runmax.rev14": {"acc": 1.0, "reasoning_bytes": 94.964, "flops_per_problem": 5474631057.408}, "runmax.rev16": {"acc": 0.974, "reasoning_bytes": 102.72, "flops_per_problem": 5905927618.56}, "runmax.sumd12": {"acc": 1.0, "reasoning_bytes": 86.0, "flops_per_problem": 5034590208.0}, "runmax.sumd14": {"acc": 1.0, "reasoning_bytes": 97.976, "flops_per_problem": 5651813302.272}, "runmax.sumd16": {"acc": 0.976, "reasoning_bytes": 105.918, "flops_per_problem": 6091324194.816}, "runmax.inc12": {"acc": 1.0, "reasoning_bytes": 87.0, "flops_per_problem": 5065769336.832}, "runmax.inc14": {"acc": 1.0, "reasoning_bytes": 98.964, "flops_per_problem": 5685818867.712}, "runmax.inc16": {"acc": 0.976, "reasoning_bytes": 106.872, "flops_per_problem": 6125771390.976}, "count.cmp16": {"acc": 1.0, "reasoning_bytes": 95.0, "flops_per_problem": 5697036288.0}, "count.cmp18": {"acc": 0.99, "reasoning_bytes": 104.97, "flops_per_problem": 6225756585.984}, "count.cmp20": {"acc": 0.958, "reasoning_bytes": 111.27, "flops_per_problem": 6592398409.728}, "count.runmax16": {"acc": 1.0, "reasoning_bytes": 96.0, "flops_per_problem": 5785362432.0}, "count.runmax18": {"acc": 0.994, "reasoning_bytes": 105.96, "flops_per_problem": 6313552773.12}, "count.runmax20": {"acc": 0.862, "reasoning_bytes": 112.33, "flops_per_problem": 6683197685.76}, "count.count16": {"acc": 1.0, "reasoning_bytes": 96.0, "flops_per_problem": 5829525504.0}, "count.count18": {"acc": 1.0, "reasoning_bytes": 105.98, "flops_per_problem": 6358599106.56}, "count.count20": {"acc": 0.998, "reasoning_bytes": 112.99, "flops_per_problem": 6756508385.28}, "count.find16": {"acc": 0.996, "reasoning_bytes": 96.0, "flops_per_problem": 5785362432.0}, "count.find18": {"acc": 0.986, "reasoning_bytes": 105.99, "flops_per_problem": 6314877665.28}, "count.find20": {"acc": 0.934, "reasoning_bytes": 112.5, "flops_per_problem": 6690705408.0}, "count.rev16": {"acc": 0.998, "reasoning_bytes": 91.0, "flops_per_problem": 5432057856.0}, "count.rev18": {"acc": 0.99, "reasoning_bytes": 100.93, "flops_per_problem": 5958923304.96}, "count.rev20": {"acc": 0.844, "reasoning_bytes": 107.16, "flops_per_problem": 6322385387.52}, "count.sumd16": {"acc": 0.998, "reasoning_bytes": 94.0, "flops_per_problem": 5608710144.0}, "count.sumd18": {"acc": 0.99, "reasoning_bytes": 103.95, "flops_per_problem": 6136458854.4}, "count.sumd20": {"acc": 0.848, "reasoning_bytes": 110.39, "flops_per_problem": 6509195182.08}, "count.inc16": {"acc": 0.998, "reasoning_bytes": 95.0, "flops_per_problem": 5608710144.0}, "count.inc18": {"acc": 0.992, "reasoning_bytes": 104.956, "flops_per_problem": 6136723832.832}, "count.inc20": {"acc": 0.858, "reasoning_bytes": 111.468, "flops_per_problem": 6512639901.696}, "parity.cmp16": {"acc": 1.0, "reasoning_bytes": 111.0, "flops_per_problem": 6359482368.0}, "parity.cmp20": {"acc": 0.984, "reasoning_bytes": 132.348, "flops_per_problem": 7478927917.056}, "parity.cmp24": {"acc": 0.952, "reasoning_bytes": 152.808, "flops_per_problem": 8559156658.176}, "parity.runmax16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.runmax20": {"acc": 0.932, "reasoning_bytes": 135.184, "flops_per_problem": 7648337461.248}, "parity.runmax24": {"acc": 0.688, "reasoning_bytes": 154.096, "flops_per_problem": 8660201766.912}, "parity.count16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6491971584.0}, "parity.count20": {"acc": 1.0, "reasoning_bytes": 135.472, "flops_per_problem": 7705219497.984}, "parity.count24": {"acc": 1.0, "reasoning_bytes": 154.372, "flops_per_problem": 8716553846.784}, "parity.find16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6447808512.0}, "parity.find20": {"acc": 0.99, "reasoning_bytes": 135.436, "flops_per_problem": 7659466555.392}, "parity.find24": {"acc": 0.892, "reasoning_bytes": 154.192, "flops_per_problem": 8664441421.824}, "parity.rev16": {"acc": 1.0, "reasoning_bytes": 107.0, "flops_per_problem": 6094503936.0}, "parity.rev20": {"acc": 0.964, "reasoning_bytes": 130.904, "flops_per_problem": 7326830297.088}, "parity.rev24": {"acc": 0.66, "reasoning_bytes": 149.588, "flops_per_problem": 8328625422.336}, "parity.sumd16": {"acc": 1.0, "reasoning_bytes": 110.0, "flops_per_problem": 6271156224.0}, "parity.sumd20": {"acc": 0.956, "reasoning_bytes": 133.796, "flops_per_problem": 7498712973.312}, "parity.sumd24": {"acc": 0.666, "reasoning_bytes": 152.984, "flops_per_problem": 8522766286.848}, "parity.inc16": {"acc": 0.998, "reasoning_bytes": 111.0, "flops_per_problem": 6271156224.0}, "parity.inc20": {"acc": 0.964, "reasoning_bytes": 134.94, "flops_per_problem": 7505072455.68}, "parity.inc24": {"acc": 0.68, "reasoning_bytes": 154.092, "flops_per_problem": 8527535898.624}, "sumd.cmp6": {"acc": 0.992, "reasoning_bytes": 62.04, "flops_per_problem": 3711287918.592}, "sumd.cmp7": {"acc": 0.984, "reasoning_bytes": 69.816, "flops_per_problem": 4099039690.752}, "sumd.cmp8": {"acc": 0.942, "reasoning_bytes": 71.876, "flops_per_problem": 4234090364.928}, "sumd.runmax6": {"acc": 1.0, "reasoning_bytes": 67.542, "flops_per_problem": 3954449793.024}, "sumd.runmax7": {"acc": 0.996, "reasoning_bytes": 75.48, "flops_per_problem": 4349179330.56}, "sumd.runmax8": {"acc": 0.914, "reasoning_bytes": 83.186, "flops_per_problem": 4733663035.392}, "sumd.count6": {"acc": 1.0, "reasoning_bytes": 66.428, "flops_per_problem": 3949415202.816}, "sumd.count7": {"acc": 0.998, "reasoning_bytes": 74.458, "flops_per_problem": 4348207742.976}, "sumd.count8": {"acc": 0.888, "reasoning_bytes": 80.8, "flops_per_problem": 4672453017.6}, "sumd.find6": {"acc": 1.0, "reasoning_bytes": 66.24, "flops_per_problem": 3896949473.28}, "sumd.find7": {"acc": 0.996, "reasoning_bytes": 74.452, "flops_per_problem": 4303779692.544}, "sumd.find8": {"acc": 0.932, "reasoning_bytes": 81.366, "flops_per_problem": 4653286244.352}, "sumd.rev6": {"acc": 0.998, "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": 0.812, "reasoning_bytes": 76.18, "flops_per_problem": 4335842082.816}, "sumd.sumd6": {"acc": 1.0, "reasoning_bytes": 65.744, "flops_per_problem": 3795639386.112}, "sumd.sumd7": {"acc": 0.992, "reasoning_bytes": 73.738, "flops_per_problem": 4195315187.712}, "sumd.sumd8": {"acc": 0.904, "reasoning_bytes": 81.612, "flops_per_problem": 4588631506.944}, "sumd.inc6": {"acc": 1.0, "reasoning_bytes": 68.538, "flops_per_problem": 3910021742.592}, "sumd.inc7": {"acc": 0.97, "reasoning_bytes": 76.48, "flops_per_problem": 4305016258.56}, "sumd.inc8": {"acc": 0.734, "reasoning_bytes": 83.81, "flops_per_problem": 4672806322.176}, "inc.cmp6": {"acc": 0.994, "reasoning_bytes": 78.624, "flops_per_problem": 4576354172.928}, "inc.cmp7": {"acc": 0.978, "reasoning_bytes": 89.774, "flops_per_problem": 5157098569.728}, "inc.cmp8": {"acc": 0.872, "reasoning_bytes": 99.856, "flops_per_problem": 5690676805.632}, "inc.runmax6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5520384000.0}, "inc.runmax7": {"acc": 1.0, "reasoning_bytes": 119.998, "flops_per_problem": 6271067897.856}, "inc.runmax8": {"acc": 0.836, "reasoning_bytes": 134.594, "flops_per_problem": 6959835168.768}, "inc.count6": {"acc": 0.992, "reasoning_bytes": 99.0, "flops_per_problem": 5343731712.0}, "inc.count7": {"acc": 0.944, "reasoning_bytes": 113.99, "flops_per_problem": 6049899233.28}, "inc.count8": {"acc": 0.774, "reasoning_bytes": 115.892, "flops_per_problem": 6178060468.224}, "inc.find6": {"acc": 0.998, "reasoning_bytes": 91.88, "flops_per_problem": 4985127567.36}, "inc.find7": {"acc": 0.902, "reasoning_bytes": 102.618, "flops_per_problem": 5503513706.496}, "inc.find8": {"acc": 0.474, "reasoning_bytes": 116.936, "flops_per_problem": 6180003643.392}, "inc.rev6": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 5608710144.0}, "inc.rev7": {"acc": 0.982, "reasoning_bytes": 124.0, "flops_per_problem": 6580297728.0}, "inc.rev8": {"acc": 0.008, "reasoning_bytes": 137.538, "flops_per_problem": 7231349735.424}, "inc.sumd6": {"acc": 0.998, "reasoning_bytes": 109.558, "flops_per_problem": 5721590956.032}, "inc.sumd7": {"acc": 0.972, "reasoning_bytes": 127.46, "flops_per_problem": 6556361342.976}, "inc.sumd8": {"acc": 0.106, "reasoning_bytes": 141.792, "flops_per_problem": 7233469562.88}, "inc.inc6": {"acc": 1.0, "reasoning_bytes": 113.0, "flops_per_problem": 6006177792.0}, "inc.inc7": {"acc": 0.996, "reasoning_bytes": 131.0, "flops_per_problem": 6889439232.0}, "inc.inc8": {"acc": 0.112, "reasoning_bytes": 146.95, "flops_per_problem": 7676601827.328}, "count.inc.cmp16": {"acc": 0.236, "reasoning_bytes": 109.636, "flops_per_problem": 6527302041.6}, "count.inc.cmp18": {"acc": 0.326, "reasoning_bytes": 117.412, "flops_per_problem": 6959128559.616}, "count.inc.cmp20": {"acc": 0.314, "reasoning_bytes": 123.658, "flops_per_problem": 7321442402.304}, "inc.rev.sumd6": {"acc": 0.0, "reasoning_bytes": 160.972, "flops_per_problem": 8345495715.84}, "inc.rev.sumd7": {"acc": 0.0, "reasoning_bytes": 192.924, "flops_per_problem": 9844743684.096}, "inc.rev.sumd8": {"acc": 0.0, "reasoning_bytes": 204.29, "flops_per_problem": 10396428779.52}, "parity.runmax.count16": {"acc": 1.0, "reasoning_bytes": 129.0, "flops_per_problem": 7551885312.0}, "parity.runmax.count20": {"acc": 1.0, "reasoning_bytes": 150.756, "flops_per_problem": 8689349394.432}, "parity.runmax.count24": {"acc": 1.0, "reasoning_bytes": 170.892, "flops_per_problem": 9755269300.224}, "add.count.find6": {"acc": 0.018, "reasoning_bytes": 130.844, "flops_per_problem": 7370021781.504}, "add.count.find7": {"acc": 0.018, "reasoning_bytes": 142.958, "flops_per_problem": 8028846489.6}, "add.count.find8": {"acc": 0.002, "reasoning_bytes": 143.242, "flops_per_problem": 8252223307.776}, "runmax.inc.find12": {"acc": 0.878, "reasoning_bytes": 105.428, "flops_per_problem": 6157568802.816}, "runmax.inc.find14": {"acc": 0.898, "reasoning_bytes": 116.96, "flops_per_problem": 6755183493.12}, "runmax.inc.find16": {"acc": 0.834, "reasoning_bytes": 123.712, "flops_per_problem": 7141698699.264}, "parity.sumd.rev16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.sumd.rev20": {"acc": 0.792, "reasoning_bytes": 143.612, "flops_per_problem": 8108869976.064}, "parity.sumd.rev24": {"acc": 0.654, "reasoning_bytes": 163.948, "flops_per_problem": 9183622496.256}, "parity.rev.sumd16": {"acc": 1.0, "reasoning_bytes": 122.0, "flops_per_problem": 6977765376.0}, "parity.rev.sumd20": {"acc": 0.816, "reasoning_bytes": 143.888, "flops_per_problem": 8121058983.936}, "parity.rev.sumd24": {"acc": 0.654, "reasoning_bytes": 163.988, "flops_per_problem": 9185389019.136}, "count.inc.sumd16": {"acc": 0.998, "reasoning_bytes": 110.0, "flops_per_problem": 6491971584.0}, "count.inc.sumd18": {"acc": 0.986, "reasoning_bytes": 119.59, "flops_per_problem": 7003821588.48}, "count.inc.sumd20": {"acc": 0.814, "reasoning_bytes": 125.196, "flops_per_problem": 7339725914.112}, "inc.sumd.rev6": {"acc": 1.0, "reasoning_bytes": 128.542, "flops_per_problem": 6736635002.88}, "inc.sumd.rev7": {"acc": 0.952, "reasoning_bytes": 146.44, "flops_per_problem": 7571228737.536}, "inc.sumd.rev8": {"acc": 0.132, "reasoning_bytes": 155.288, "flops_per_problem": 8008354824.192}, "count.count.cmp16": {"acc": 1.0, "reasoning_bytes": 112.0, "flops_per_problem": 6801113088.0}, "count.count.cmp18": {"acc": 0.998, "reasoning_bytes": 122.0, "flops_per_problem": 7331069952.0}, "count.count.cmp20": {"acc": 1.0, "reasoning_bytes": 128.96, "flops_per_problem": 7726771077.12}, "parity.rev.find16": {"acc": 1.0, "reasoning_bytes": 124.0, "flops_per_problem": 7154417664.0}, "parity.rev.find20": {"acc": 0.956, "reasoning_bytes": 146.056, "flops_per_problem": 8305130668.032}, "parity.rev.find24": {"acc": 0.9, "reasoning_bytes": 165.964, "flops_per_problem": 9360981393.408}, "count.sumd.cmp16": {"acc": 1.0, "reasoning_bytes": 110.0, "flops_per_problem": 6580297728.0}, "count.sumd.cmp18": {"acc": 0.992, "reasoning_bytes": 119.88, "flops_per_problem": 7104955023.36}, "count.sumd.cmp20": {"acc": 0.958, "reasoning_bytes": 125.43, "flops_per_problem": 7438386216.96}, "sumd.count.count6": {"acc": 1.0, "reasoning_bytes": 83.476, "flops_per_problem": 5055611830.272}, "sumd.count.count7": {"acc": 1.0, "reasoning_bytes": 91.416, "flops_per_problem": 5450429693.952}, "sumd.count.count8": {"acc": 0.998, "reasoning_bytes": 94.894, "flops_per_problem": 5648103604.224}, "runmax.rev.inc12": {"acc": 1.0, "reasoning_bytes": 99.0, "flops_per_problem": 5772378488.832}, "runmax.rev.inc14": {"acc": 1.0, "reasoning_bytes": 110.964, "flops_per_problem": 6392428019.712}, "runmax.rev.inc16": {"acc": 0.976, "reasoning_bytes": 118.56, "flops_per_problem": 6817895055.36}, "parity.sumd.find16": {"acc": 0.998, "reasoning_bytes": 127.0, "flops_per_problem": 7331069952.0}, "parity.sumd.find20": {"acc": 0.942, "reasoning_bytes": 148.264, "flops_per_problem": 8446805803.008}, "parity.sumd.find24": {"acc": 0.908, "reasoning_bytes": 168.652, "flops_per_problem": 9523854802.944}, "runmax.runmax.cmp12": {"acc": 1.0, "reasoning_bytes": 104.0, "flops_per_problem": 6182830080.0}, "runmax.runmax.cmp14": {"acc": 1.0, "reasoning_bytes": 116.0, "flops_per_problem": 6801113088.0}, "runmax.runmax.cmp16": {"acc": 1.0, "reasoning_bytes": 123.172, "flops_per_problem": 7206176784.384}, "count.runmax.count16": {"acc": 1.0, "reasoning_bytes": 113.0, "flops_per_problem": 6889439232.0}, "count.runmax.count18": {"acc": 1.0, "reasoning_bytes": 122.92, "flops_per_problem": 7415863050.24}, "count.runmax.count20": {"acc": 1.0, "reasoning_bytes": 129.54, "flops_per_problem": 7796548730.88}, "inc.inc.sumd6": {"acc": 0.988, "reasoning_bytes": 175.564, "flops_per_problem": 8813359300.608}, "inc.inc.sumd7": {"acc": 0.77, "reasoning_bytes": 203.484, "flops_per_problem": 10090555342.848}, "inc.inc.sumd8": {"acc": 0.078, "reasoning_bytes": 220.618, "flops_per_problem": 10891761795.072}, "add.sumd.find6": {"acc": 1.0, "reasoning_bytes": 150.512, "flops_per_problem": 8104453668.864}, "add.sumd.find7": {"acc": 0.93, "reasoning_bytes": 170.04, "flops_per_problem": 9055196282.88}, "add.sumd.find8": {"acc": 0.734, "reasoning_bytes": 188.184, "flops_per_problem": 9944817205.248}, "sumd.rev.rev6": {"acc": 1.0, "reasoning_bytes": 80.53, "flops_per_problem": 4616277590.016}, "sumd.rev.rev7": {"acc": 0.986, "reasoning_bytes": 88.4, "flops_per_problem": 5008092364.8}, "sumd.rev.rev8": {"acc": 0.426, "reasoning_bytes": 91.59, "flops_per_problem": 5193047310.336}, "runmax.inc.runmax12": {"acc": 1.0, "reasoning_bytes": 109.648, "flops_per_problem": 6343936966.656}, "runmax.inc.runmax14": {"acc": 1.0, "reasoning_bytes": 122.196, "flops_per_problem": 6986421338.112}, "runmax.inc.runmax16": {"acc": 0.976, "reasoning_bytes": 128.528, "flops_per_problem": 7354388054.016}, "parity.inc.find16": {"acc": 1.0, "reasoning_bytes": 128.0, "flops_per_problem": 7331069952.0}, "parity.inc.find20": {"acc": 0.956, "reasoning_bytes": 149.288, "flops_per_problem": 8447865716.736}, "parity.inc.find24": {"acc": 0.898, "reasoning_bytes": 169.772, "flops_per_problem": 9529154371.584}, "inc.runmax.sumd6": {"acc": 1.0, "reasoning_bytes": 119.0, "flops_per_problem": 6403645440.0}, "inc.runmax.sumd7": {"acc": 0.996, "reasoning_bytes": 134.984, "flops_per_problem": 7153711054.848}, "inc.runmax.sumd8": {"acc": 0.842, "reasoning_bytes": 146.522, "flops_per_problem": 7707427651.584}, "sumd.rev.cmp6": {"acc": 0.836, "reasoning_bytes": 73.996, "flops_per_problem": 4416130547.712}, "sumd.rev.cmp7": {"acc": 0.766, "reasoning_bytes": 73.812, "flops_per_problem": 4452520919.04}, "sumd.rev.cmp8": {"acc": 0.67, "reasoning_bytes": 72.484, "flops_per_problem": 4437947105.28}, "runmax.runmax.count12": {"acc": 1.0, "reasoning_bytes": 105.0, "flops_per_problem": 6315319296.0}, "runmax.runmax.count14": {"acc": 1.0, "reasoning_bytes": 117.0, "flops_per_problem": 6933602304.0}, "runmax.runmax.count16": {"acc": 1.0, "reasoning_bytes": 125.328, "flops_per_problem": 7389718511.616}, "count.count.count16": {"acc": 1.0, "reasoning_bytes": 113.0, "flops_per_problem": 6933602304.0}, "count.count.count18": {"acc": 1.0, "reasoning_bytes": 122.96, "flops_per_problem": 7461792645.12}, "count.count.count20": {"acc": 1.0, "reasoning_bytes": 130.438, "flops_per_problem": 7880370241.536}, "add.sumd.rev6": {"acc": 1.0, "reasoning_bytes": 145.448, "flops_per_problem": 7792309075.968}, "add.sumd.rev7": {"acc": 0.928, "reasoning_bytes": 165.356, "flops_per_problem": 8759921983.488}, "add.sumd.rev8": {"acc": 0.044, "reasoning_bytes": 184.698, "flops_per_problem": 9704040136.704}, "add.rev.rev6": {"acc": 1.0, "reasoning_bytes": 187.496, "flops_per_problem": 9808618291.2}, "add.rev.rev7": {"acc": 0.514, "reasoning_bytes": 222.35, "flops_per_problem": 11469326450.688}, "add.rev.rev8": {"acc": 0.0, "reasoning_bytes": 242.41, "flops_per_problem": 12454251282.432}, "inc.runmax.cmp6": {"acc": 0.52, "reasoning_bytes": 103.238, "flops_per_problem": 5751710171.136}, "inc.runmax.cmp7": {"acc": 0.048, "reasoning_bytes": 117.248, "flops_per_problem": 6414597881.856}, "inc.runmax.cmp8": {"acc": 0.106, "reasoning_bytes": 126.908, "flops_per_problem": 6885376229.376}, "count.rev.cmp16": {"acc": 1.0, "reasoning_bytes": 107.0, "flops_per_problem": 6403645440.0}, "count.rev.cmp18": {"acc": 0.994, "reasoning_bytes": 116.93, "flops_per_problem": 6930599215.104}, "count.rev.cmp20": {"acc": 0.962, "reasoning_bytes": 122.7, "flops_per_problem": 7273834610.688}} diff --git a/5m-s0-bpe4096-step-bytes3-v8-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-v8-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..25bbafdf18d999d2d8c93eff2dc4ba6b98e14f90 --- /dev/null +++ b/5m-s0-bpe4096-step-bytes3-v8-nocount.inc.cmp-noinc.rev.sumd-noadd.count.find-norunmax.inc.find-nosumd.rev.cmp-noinc.runmax.cmp-none-docmask/summary.json @@ -0,0 +1,1225 @@ +{ + "params": 5787648, + "tokens": 399998976, + "train_flops": 17665183577014272, + "wall_s": 2260.1129274368286, + "peak_mem_gb": 3.51196672, + "final_val_loss": 1.8013041317462921, + "final_val_bpb": 0.6493408750474111, + "bytes_seen": 1600839241.8284984, + "add8": { + "acc": 0.994, + "reasoning_bytes": 79.0, + "flops_per_problem": 4928775487.488 + }, + "add9": { + "acc": 0.72, + "reasoning_bytes": 89.0, + "flops_per_problem": 5503690358.784 + }, + "add10": { + "acc": 0.0, + "reasoning_bytes": 98.988, + "flops_per_problem": 6083816472.576 + }, + "reach14": { + "acc": 0.632, + "reasoning_bytes": 7.302, + "flops_per_problem": 4608063258.624 + }, + "reach16": { + "acc": 0.572, + "reasoning_bytes": 7.366, + "flops_per_problem": 5138815057.92 + }, + "reach18": { + "acc": 0.534, + "reasoning_bytes": 7.886, + "flops_per_problem": 5692001697.792 + }, + "parity24": { + "acc": 0.834, + "reasoning_bytes": 143.012, + "flops_per_problem": 7861556772.864 + }, + "parity28": { + "acc": 0.524, + "reasoning_bytes": 167.948, + "flops_per_problem": 9139459424.256 + }, + "parity32": { + "acc": 0.474, + "reasoning_bytes": 192.884, + "flops_per_problem": 10417362075.648 + }, + "cmp8": { + "acc": 0.994, + "reasoning_bytes": 5.812, + "flops_per_problem": 1360752574.464 + }, + "cmp9": { + "acc": 0.998, + "reasoning_bytes": 5.708, + "flops_per_problem": 1444485758.976 + }, + "cmp10": { + "acc": 0.99, + "reasoning_bytes": 5.768, + "flops_per_problem": 1535461687.296 + }, + "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": 0.992, + "reasoning_bytes": 94.828, + "flops_per_problem": 5380387061.76 + }, + "count16": { + "acc": 1.0, + "reasoning_bytes": 79.0, + "flops_per_problem": 4725448704.0 + }, + "count18": { + "acc": 0.99, + "reasoning_bytes": 88.97, + "flops_per_problem": 5254080675.84 + }, + "count20": { + "acc": 0.922, + "reasoning_bytes": 98.244, + "flops_per_problem": 5751975149.568 + }, + "brackets16": { + "acc": 0.994, + "reasoning_bytes": 53.466, + "flops_per_problem": 3642216873.984 + }, + "brackets18": { + "acc": 0.996, + "reasoning_bytes": 56.782, + "flops_per_problem": 3876722786.304 + }, + "brackets20": { + "acc": 0.944, + "reasoning_bytes": 63.012, + "flops_per_problem": 4240184868.864 + }, + "sumd8": { + "acc": 0.972, + "reasoning_bytes": 58.554, + "flops_per_problem": 3380771487.744 + }, + "sumd9": { + "acc": 0.856, + "reasoning_bytes": 66.43, + "flops_per_problem": 3772762914.816 + }, + "sumd10": { + "acc": 0.622, + "reasoning_bytes": 74.112, + "flops_per_problem": 4155833401.344 + }, + "inc8": { + "acc": 0.996, + "reasoning_bytes": 63.0, + "flops_per_problem": 3798024192.0 + }, + "inc9": { + "acc": 0.83, + "reasoning_bytes": 71.0, + "flops_per_problem": 4239654912.0 + }, + "inc10": { + "acc": 0.006, + "reasoning_bytes": 78.99, + "flops_per_problem": 4680225718.272 + }, + "add.cmp6": { + "acc": 0.998, + "reasoning_bytes": 92.622, + "flops_per_problem": 5532043051.008 + }, + "add.cmp7": { + "acc": 0.98, + "reasoning_bytes": 105.504, + "flops_per_problem": 6230702850.048 + }, + "add.cmp8": { + "acc": 0.904, + "reasoning_bytes": 118.252, + "flops_per_problem": 6927684452.352 + }, + "add.runmax6": { + "acc": 1.0, + "reasoning_bytes": 120.832, + "flops_per_problem": 6572878331.904 + }, + "add.runmax7": { + "acc": 0.994, + "reasoning_bytes": 138.848, + "flops_per_problem": 7456846381.056 + }, + "add.runmax8": { + "acc": 0.67, + "reasoning_bytes": 156.422, + "flops_per_problem": 8321294352.384 + }, + "add.count6": { + "acc": 0.99, + "reasoning_bytes": 115.648, + "flops_per_problem": 6388100038.656 + }, + "add.count7": { + "acc": 0.914, + "reasoning_bytes": 131.998, + "flops_per_problem": 7198492409.856 + }, + "add.count8": { + "acc": 0.446, + "reasoning_bytes": 147.674, + "flops_per_problem": 7979118870.528 + }, + "add.find6": { + "acc": 0.952, + "reasoning_bytes": 107.708, + "flops_per_problem": 5993282174.976 + }, + "add.find7": { + "acc": 0.874, + "reasoning_bytes": 121.364, + "flops_per_problem": 6684699230.208 + }, + "add.find8": { + "acc": 0.478, + "reasoning_bytes": 139.192, + "flops_per_problem": 7560452947.968 + }, + "add.rev6": { + "acc": 1.0, + "reasoning_bytes": 123.248, + "flops_per_problem": 6794576953.344 + }, + "add.rev7": { + "acc": 0.904, + "reasoning_bytes": 145.854, + "flops_per_problem": 7925063270.4 + }, + "add.rev8": { + "acc": 0.064, + "reasoning_bytes": 162.718, + "flops_per_problem": 8770432794.624 + }, + "add.sumd6": { + "acc": 0.998, + "reasoning_bytes": 126.476, + "flops_per_problem": 6777794985.984 + }, + "add.sumd7": { + "acc": 0.96, + "reasoning_bytes": 146.35, + "flops_per_problem": 7743906349.056 + }, + "add.sumd8": { + "acc": 0.216, + "reasoning_bytes": 165.196, + "flops_per_problem": 8664618074.112 + }, + "add.inc6": { + "acc": 0.996, + "reasoning_bytes": 131.04, + "flops_per_problem": 7138695610.368 + }, + "add.inc7": { + "acc": 0.948, + "reasoning_bytes": 151.02, + "flops_per_problem": 8153563004.928 + }, + "add.inc8": { + "acc": 0.132, + "reasoning_bytes": 165.492, + "flops_per_problem": 8906366730.24 + }, + "runmax.cmp12": { + "acc": 1.0, + "reasoning_bytes": 87.0, + "flops_per_problem": 5122916352.0 + }, + "runmax.cmp14": { + "acc": 1.0, + "reasoning_bytes": 98.82, + "flops_per_problem": 5733250007.04 + }, + "runmax.cmp16": { + "acc": 0.994, + "reasoning_bytes": 105.216, + "flops_per_problem": 6104043159.552 + }, + "runmax.runmax12": { + "acc": 1.0, + "reasoning_bytes": 88.0, + "flops_per_problem": 5211242496.0 + }, + "runmax.runmax14": { + "acc": 1.0, + "reasoning_bytes": 99.964, + "flops_per_problem": 5827935633.408 + }, + "runmax.runmax16": { + "acc": 0.968, + "reasoning_bytes": 106.56, + "flops_per_problem": 6207738052.608 + }, + "runmax.count12": { + "acc": 1.0, + "reasoning_bytes": 88.0, + "flops_per_problem": 5255405568.0 + }, + "runmax.count14": { + "acc": 1.0, + "reasoning_bytes": 99.976, + "flops_per_problem": 5872628662.272 + }, + "runmax.count16": { + "acc": 1.0, + "reasoning_bytes": 107.452, + "flops_per_problem": 6291117932.544 + }, + "runmax.find12": { + "acc": 1.0, + "reasoning_bytes": 88.0, + "flops_per_problem": 5211242496.0 + }, + "runmax.find14": { + "acc": 1.0, + "reasoning_bytes": 99.856, + "flops_per_problem": 5823166021.632 + }, + "runmax.find16": { + "acc": 0.992, + "reasoning_bytes": 106.574, + "flops_per_problem": 6208268009.472 + }, + "runmax.rev12": { + "acc": 1.0, + "reasoning_bytes": 83.0, + "flops_per_problem": 4857937920.0 + }, + "runmax.rev14": { + "acc": 1.0, + "reasoning_bytes": 94.964, + "flops_per_problem": 5474631057.408 + }, + "runmax.rev16": { + "acc": 0.974, + "reasoning_bytes": 102.72, + "flops_per_problem": 5905927618.56 + }, + "runmax.sumd12": { + "acc": 1.0, + "reasoning_bytes": 86.0, + "flops_per_problem": 5034590208.0 + }, + "runmax.sumd14": { + "acc": 1.0, + "reasoning_bytes": 97.976, + "flops_per_problem": 5651813302.272 + }, + "runmax.sumd16": { + "acc": 0.976, + "reasoning_bytes": 105.918, + "flops_per_problem": 6091324194.816 + }, + "runmax.inc12": { + "acc": 1.0, + "reasoning_bytes": 87.0, + "flops_per_problem": 5065769336.832 + }, + "runmax.inc14": { + "acc": 1.0, + "reasoning_bytes": 98.964, + "flops_per_problem": 5685818867.712 + }, + "runmax.inc16": { + "acc": 0.976, + "reasoning_bytes": 106.872, + "flops_per_problem": 6125771390.976 + }, + "count.cmp16": { + "acc": 1.0, + "reasoning_bytes": 95.0, + "flops_per_problem": 5697036288.0 + }, + "count.cmp18": { + "acc": 0.99, + "reasoning_bytes": 104.97, + "flops_per_problem": 6225756585.984 + }, + "count.cmp20": { + "acc": 0.958, + "reasoning_bytes": 111.27, + "flops_per_problem": 6592398409.728 + }, + "count.runmax16": { + "acc": 1.0, + "reasoning_bytes": 96.0, + "flops_per_problem": 5785362432.0 + }, + "count.runmax18": { + "acc": 0.994, + "reasoning_bytes": 105.96, + "flops_per_problem": 6313552773.12 + }, + "count.runmax20": { + "acc": 0.862, + "reasoning_bytes": 112.33, + "flops_per_problem": 6683197685.76 + }, + "count.count16": { + "acc": 1.0, + "reasoning_bytes": 96.0, + "flops_per_problem": 5829525504.0 + }, + "count.count18": { + "acc": 1.0, + "reasoning_bytes": 105.98, + "flops_per_problem": 6358599106.56 + }, + "count.count20": { + "acc": 0.998, + "reasoning_bytes": 112.99, + "flops_per_problem": 6756508385.28 + }, + "count.find16": { + "acc": 0.996, + "reasoning_bytes": 96.0, + "flops_per_problem": 5785362432.0 + }, + "count.find18": { + "acc": 0.986, + "reasoning_bytes": 105.99, + "flops_per_problem": 6314877665.28 + }, + "count.find20": { + "acc": 0.934, + "reasoning_bytes": 112.5, + "flops_per_problem": 6690705408.0 + }, + "count.rev16": { + "acc": 0.998, + "reasoning_bytes": 91.0, + "flops_per_problem": 5432057856.0 + }, + "count.rev18": { + "acc": 0.99, + "reasoning_bytes": 100.93, + "flops_per_problem": 5958923304.96 + }, + "count.rev20": { + "acc": 0.844, + "reasoning_bytes": 107.16, + "flops_per_problem": 6322385387.52 + }, + "count.sumd16": { + "acc": 0.998, + "reasoning_bytes": 94.0, + "flops_per_problem": 5608710144.0 + }, + "count.sumd18": { + "acc": 0.99, + "reasoning_bytes": 103.95, + "flops_per_problem": 6136458854.4 + }, + "count.sumd20": { + "acc": 0.848, + "reasoning_bytes": 110.39, + "flops_per_problem": 6509195182.08 + }, + "count.inc16": { + "acc": 0.998, + "reasoning_bytes": 95.0, + "flops_per_problem": 5608710144.0 + }, + "count.inc18": { + "acc": 0.992, + "reasoning_bytes": 104.956, + "flops_per_problem": 6136723832.832 + }, + "count.inc20": { + "acc": 0.858, + "reasoning_bytes": 111.468, + "flops_per_problem": 6512639901.696 + }, + "parity.cmp16": { + "acc": 1.0, + "reasoning_bytes": 111.0, + "flops_per_problem": 6359482368.0 + }, + "parity.cmp20": { + "acc": 0.984, + "reasoning_bytes": 132.348, + "flops_per_problem": 7478927917.056 + }, + "parity.cmp24": { + "acc": 0.952, + "reasoning_bytes": 152.808, + "flops_per_problem": 8559156658.176 + }, + "parity.runmax16": { + "acc": 1.0, + "reasoning_bytes": 112.0, + "flops_per_problem": 6447808512.0 + }, + "parity.runmax20": { + "acc": 0.932, + "reasoning_bytes": 135.184, + "flops_per_problem": 7648337461.248 + }, + "parity.runmax24": { + "acc": 0.688, + "reasoning_bytes": 154.096, + "flops_per_problem": 8660201766.912 + }, + "parity.count16": { + "acc": 1.0, + "reasoning_bytes": 112.0, + "flops_per_problem": 6491971584.0 + }, + "parity.count20": { + "acc": 1.0, + "reasoning_bytes": 135.472, + "flops_per_problem": 7705219497.984 + }, + "parity.count24": { + "acc": 1.0, + "reasoning_bytes": 154.372, + "flops_per_problem": 8716553846.784 + }, + "parity.find16": { + "acc": 1.0, + "reasoning_bytes": 112.0, + "flops_per_problem": 6447808512.0 + }, + "parity.find20": { + "acc": 0.99, + "reasoning_bytes": 135.436, + "flops_per_problem": 7659466555.392 + }, + "parity.find24": { + "acc": 0.892, + "reasoning_bytes": 154.192, + "flops_per_problem": 8664441421.824 + }, + "parity.rev16": { + "acc": 1.0, + "reasoning_bytes": 107.0, + "flops_per_problem": 6094503936.0 + }, + "parity.rev20": { + "acc": 0.964, + "reasoning_bytes": 130.904, + "flops_per_problem": 7326830297.088 + }, + "parity.rev24": { + "acc": 0.66, + "reasoning_bytes": 149.588, + "flops_per_problem": 8328625422.336 + }, + "parity.sumd16": { + "acc": 1.0, + "reasoning_bytes": 110.0, + "flops_per_problem": 6271156224.0 + }, + "parity.sumd20": { + "acc": 0.956, + "reasoning_bytes": 133.796, + "flops_per_problem": 7498712973.312 + }, + "parity.sumd24": { + "acc": 0.666, + "reasoning_bytes": 152.984, + "flops_per_problem": 8522766286.848 + }, + "parity.inc16": { + "acc": 0.998, + "reasoning_bytes": 111.0, + "flops_per_problem": 6271156224.0 + }, + "parity.inc20": { + "acc": 0.964, + "reasoning_bytes": 134.94, + "flops_per_problem": 7505072455.68 + }, + "parity.inc24": { + "acc": 0.68, + "reasoning_bytes": 154.092, + "flops_per_problem": 8527535898.624 + }, + "sumd.cmp6": { + "acc": 0.992, + "reasoning_bytes": 62.04, + "flops_per_problem": 3711287918.592 + }, + "sumd.cmp7": { + "acc": 0.984, + "reasoning_bytes": 69.816, + "flops_per_problem": 4099039690.752 + }, + "sumd.cmp8": { + "acc": 0.942, + "reasoning_bytes": 71.876, + "flops_per_problem": 4234090364.928 + }, + "sumd.runmax6": { + "acc": 1.0, + "reasoning_bytes": 67.542, + "flops_per_problem": 3954449793.024 + }, + "sumd.runmax7": { + "acc": 0.996, + "reasoning_bytes": 75.48, + "flops_per_problem": 4349179330.56 + }, + "sumd.runmax8": { + "acc": 0.914, + "reasoning_bytes": 83.186, + "flops_per_problem": 4733663035.392 + }, + "sumd.count6": { + "acc": 1.0, + "reasoning_bytes": 66.428, + "flops_per_problem": 3949415202.816 + }, + "sumd.count7": { + "acc": 0.998, + "reasoning_bytes": 74.458, + "flops_per_problem": 4348207742.976 + }, + "sumd.count8": { + "acc": 0.888, + "reasoning_bytes": 80.8, + "flops_per_problem": 4672453017.6 + }, + "sumd.find6": { + "acc": 1.0, + "reasoning_bytes": 66.24, + "flops_per_problem": 3896949473.28 + }, + "sumd.find7": { + "acc": 0.996, + "reasoning_bytes": 74.452, + "flops_per_problem": 4303779692.544 + }, + "sumd.find8": { + "acc": 0.932, + "reasoning_bytes": 81.366, + "flops_per_problem": 4653286244.352 + }, + "sumd.rev6": { + "acc": 0.998, + "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": 0.812, + "reasoning_bytes": 76.18, + "flops_per_problem": 4335842082.816 + }, + "sumd.sumd6": { + "acc": 1.0, + "reasoning_bytes": 65.744, + "flops_per_problem": 3795639386.112 + }, + "sumd.sumd7": { + "acc": 0.992, + "reasoning_bytes": 73.738, + "flops_per_problem": 4195315187.712 + }, + "sumd.sumd8": { + "acc": 0.904, + "reasoning_bytes": 81.612, + "flops_per_problem": 4588631506.944 + }, + "sumd.inc6": { + "acc": 1.0, + "reasoning_bytes": 68.538, + "flops_per_problem": 3910021742.592 + }, + "sumd.inc7": { + "acc": 0.97, + "reasoning_bytes": 76.48, + "flops_per_problem": 4305016258.56 + }, + "sumd.inc8": { + "acc": 0.734, + "reasoning_bytes": 83.81, + "flops_per_problem": 4672806322.176 + }, + "inc.cmp6": { + "acc": 0.994, + "reasoning_bytes": 78.624, + "flops_per_problem": 4576354172.928 + }, + "inc.cmp7": { + "acc": 0.978, + "reasoning_bytes": 89.774, + "flops_per_problem": 5157098569.728 + }, + "inc.cmp8": { + "acc": 0.872, + "reasoning_bytes": 99.856, + "flops_per_problem": 5690676805.632 + }, + "inc.runmax6": { + "acc": 1.0, + "reasoning_bytes": 104.0, + "flops_per_problem": 5520384000.0 + }, + "inc.runmax7": { + "acc": 1.0, + "reasoning_bytes": 119.998, + "flops_per_problem": 6271067897.856 + }, + "inc.runmax8": { + "acc": 0.836, + "reasoning_bytes": 134.594, + "flops_per_problem": 6959835168.768 + }, + "inc.count6": { + "acc": 0.992, + "reasoning_bytes": 99.0, + "flops_per_problem": 5343731712.0 + }, + "inc.count7": { + "acc": 0.944, + "reasoning_bytes": 113.99, + "flops_per_problem": 6049899233.28 + }, + "inc.count8": { + "acc": 0.774, + "reasoning_bytes": 115.892, + "flops_per_problem": 6178060468.224 + }, + "inc.find6": { + "acc": 0.998, + "reasoning_bytes": 91.88, + "flops_per_problem": 4985127567.36 + }, + "inc.find7": { + "acc": 0.902, + "reasoning_bytes": 102.618, + "flops_per_problem": 5503513706.496 + }, + "inc.find8": { + "acc": 0.474, + "reasoning_bytes": 116.936, + "flops_per_problem": 6180003643.392 + }, + "inc.rev6": { + "acc": 1.0, + "reasoning_bytes": 104.0, + "flops_per_problem": 5608710144.0 + }, + "inc.rev7": { + "acc": 0.982, + "reasoning_bytes": 124.0, + "flops_per_problem": 6580297728.0 + }, + "inc.rev8": { + "acc": 0.008, + "reasoning_bytes": 137.538, + "flops_per_problem": 7231349735.424 + }, + "inc.sumd6": { + "acc": 0.998, + "reasoning_bytes": 109.558, + "flops_per_problem": 5721590956.032 + }, + "inc.sumd7": { + "acc": 0.972, + "reasoning_bytes": 127.46, + "flops_per_problem": 6556361342.976 + }, + "inc.sumd8": { + "acc": 0.106, + "reasoning_bytes": 141.792, + "flops_per_problem": 7233469562.88 + }, + "inc.inc6": { + "acc": 1.0, + "reasoning_bytes": 113.0, + "flops_per_problem": 6006177792.0 + }, + "inc.inc7": { + "acc": 0.996, + "reasoning_bytes": 131.0, + "flops_per_problem": 6889439232.0 + }, + "inc.inc8": { + "acc": 0.112, + "reasoning_bytes": 146.95, + "flops_per_problem": 7676601827.328 + }, + "count.inc.cmp16": { + "acc": 0.236, + "reasoning_bytes": 109.636, + "flops_per_problem": 6527302041.6 + }, + "count.inc.cmp18": { + "acc": 0.326, + "reasoning_bytes": 117.412, + "flops_per_problem": 6959128559.616 + }, + "count.inc.cmp20": { + "acc": 0.314, + "reasoning_bytes": 123.658, + "flops_per_problem": 7321442402.304 + }, + "inc.rev.sumd6": { + "acc": 0.0, + "reasoning_bytes": 160.972, + "flops_per_problem": 8345495715.84 + }, + "inc.rev.sumd7": { + "acc": 0.0, + "reasoning_bytes": 192.924, + "flops_per_problem": 9844743684.096 + }, + "inc.rev.sumd8": { + "acc": 0.0, + "reasoning_bytes": 204.29, + "flops_per_problem": 10396428779.52 + }, + "parity.runmax.count16": { + "acc": 1.0, + "reasoning_bytes": 129.0, + "flops_per_problem": 7551885312.0 + }, + "parity.runmax.count20": { + "acc": 1.0, + "reasoning_bytes": 150.756, + "flops_per_problem": 8689349394.432 + }, + "parity.runmax.count24": { + "acc": 1.0, + "reasoning_bytes": 170.892, + "flops_per_problem": 9755269300.224 + }, + "add.count.find6": { + "acc": 0.018, + "reasoning_bytes": 130.844, + "flops_per_problem": 7370021781.504 + }, + "add.count.find7": { + "acc": 0.018, + "reasoning_bytes": 142.958, + "flops_per_problem": 8028846489.6 + }, + "add.count.find8": { + "acc": 0.002, + "reasoning_bytes": 143.242, + "flops_per_problem": 8252223307.776 + }, + "runmax.inc.find12": { + "acc": 0.878, + "reasoning_bytes": 105.428, + "flops_per_problem": 6157568802.816 + }, + "runmax.inc.find14": { + "acc": 0.898, + "reasoning_bytes": 116.96, + "flops_per_problem": 6755183493.12 + }, + "runmax.inc.find16": { + "acc": 0.834, + "reasoning_bytes": 123.712, + "flops_per_problem": 7141698699.264 + }, + "parity.sumd.rev16": { + "acc": 1.0, + "reasoning_bytes": 122.0, + "flops_per_problem": 6977765376.0 + }, + "parity.sumd.rev20": { + "acc": 0.792, + "reasoning_bytes": 143.612, + "flops_per_problem": 8108869976.064 + }, + "parity.sumd.rev24": { + "acc": 0.654, + "reasoning_bytes": 163.948, + "flops_per_problem": 9183622496.256 + }, + "parity.rev.sumd16": { + "acc": 1.0, + "reasoning_bytes": 122.0, + "flops_per_problem": 6977765376.0 + }, + "parity.rev.sumd20": { + "acc": 0.816, + "reasoning_bytes": 143.888, + "flops_per_problem": 8121058983.936 + }, + "parity.rev.sumd24": { + "acc": 0.654, + "reasoning_bytes": 163.988, + "flops_per_problem": 9185389019.136 + }, + "count.inc.sumd16": { + "acc": 0.998, + "reasoning_bytes": 110.0, + "flops_per_problem": 6491971584.0 + }, + "count.inc.sumd18": { + "acc": 0.986, + "reasoning_bytes": 119.59, + "flops_per_problem": 7003821588.48 + }, + "count.inc.sumd20": { + "acc": 0.814, + "reasoning_bytes": 125.196, + "flops_per_problem": 7339725914.112 + }, + "inc.sumd.rev6": { + "acc": 1.0, + "reasoning_bytes": 128.542, + "flops_per_problem": 6736635002.88 + }, + "inc.sumd.rev7": { + "acc": 0.952, + "reasoning_bytes": 146.44, + "flops_per_problem": 7571228737.536 + }, + "inc.sumd.rev8": { + "acc": 0.132, + "reasoning_bytes": 155.288, + "flops_per_problem": 8008354824.192 + }, + "count.count.cmp16": { + "acc": 1.0, + "reasoning_bytes": 112.0, + "flops_per_problem": 6801113088.0 + }, + "count.count.cmp18": { + "acc": 0.998, + "reasoning_bytes": 122.0, + "flops_per_problem": 7331069952.0 + }, + "count.count.cmp20": { + "acc": 1.0, + "reasoning_bytes": 128.96, + "flops_per_problem": 7726771077.12 + }, + "parity.rev.find16": { + "acc": 1.0, + "reasoning_bytes": 124.0, + "flops_per_problem": 7154417664.0 + }, + "parity.rev.find20": { + "acc": 0.956, + "reasoning_bytes": 146.056, + "flops_per_problem": 8305130668.032 + }, + "parity.rev.find24": { + "acc": 0.9, + "reasoning_bytes": 165.964, + "flops_per_problem": 9360981393.408 + }, + "count.sumd.cmp16": { + "acc": 1.0, + "reasoning_bytes": 110.0, + "flops_per_problem": 6580297728.0 + }, + "count.sumd.cmp18": { + "acc": 0.992, + "reasoning_bytes": 119.88, + "flops_per_problem": 7104955023.36 + }, + "count.sumd.cmp20": { + "acc": 0.958, + "reasoning_bytes": 125.43, + "flops_per_problem": 7438386216.96 + }, + "sumd.count.count6": { + "acc": 1.0, + "reasoning_bytes": 83.476, + "flops_per_problem": 5055611830.272 + }, + "sumd.count.count7": { + "acc": 1.0, + "reasoning_bytes": 91.416, + "flops_per_problem": 5450429693.952 + }, + "sumd.count.count8": { + "acc": 0.998, + "reasoning_bytes": 94.894, + "flops_per_problem": 5648103604.224 + }, + "runmax.rev.inc12": { + "acc": 1.0, + "reasoning_bytes": 99.0, + "flops_per_problem": 5772378488.832 + }, + "runmax.rev.inc14": { + "acc": 1.0, + "reasoning_bytes": 110.964, + "flops_per_problem": 6392428019.712 + }, + "runmax.rev.inc16": { + "acc": 0.976, + "reasoning_bytes": 118.56, + "flops_per_problem": 6817895055.36 + }, + "parity.sumd.find16": { + "acc": 0.998, + "reasoning_bytes": 127.0, + "flops_per_problem": 7331069952.0 + }, + "parity.sumd.find20": { + "acc": 0.942, + "reasoning_bytes": 148.264, + "flops_per_problem": 8446805803.008 + }, + "parity.sumd.find24": { + "acc": 0.908, + "reasoning_bytes": 168.652, + "flops_per_problem": 9523854802.944 + }, + "runmax.runmax.cmp12": { + "acc": 1.0, + "reasoning_bytes": 104.0, + "flops_per_problem": 6182830080.0 + }, + "runmax.runmax.cmp14": { + "acc": 1.0, + "reasoning_bytes": 116.0, + "flops_per_problem": 6801113088.0 + }, + "runmax.runmax.cmp16": { + "acc": 1.0, + "reasoning_bytes": 123.172, + "flops_per_problem": 7206176784.384 + }, + "count.runmax.count16": { + "acc": 1.0, + "reasoning_bytes": 113.0, + "flops_per_problem": 6889439232.0 + }, + "count.runmax.count18": { + "acc": 1.0, + "reasoning_bytes": 122.92, + "flops_per_problem": 7415863050.24 + }, + "count.runmax.count20": { + "acc": 1.0, + "reasoning_bytes": 129.54, + "flops_per_problem": 7796548730.88 + }, + "inc.inc.sumd6": { + "acc": 0.988, + "reasoning_bytes": 175.564, + "flops_per_problem": 8813359300.608 + }, + "inc.inc.sumd7": { + "acc": 0.77, + "reasoning_bytes": 203.484, + "flops_per_problem": 10090555342.848 + }, + "inc.inc.sumd8": { + "acc": 0.078, + "reasoning_bytes": 220.618, + "flops_per_problem": 10891761795.072 + }, + "add.sumd.find6": { + "acc": 1.0, + "reasoning_bytes": 150.512, + "flops_per_problem": 8104453668.864 + }, + "add.sumd.find7": { + "acc": 0.93, + "reasoning_bytes": 170.04, + "flops_per_problem": 9055196282.88 + }, + "add.sumd.find8": { + "acc": 0.734, + "reasoning_bytes": 188.184, + "flops_per_problem": 9944817205.248 + }, + "sumd.rev.rev6": { + "acc": 1.0, + "reasoning_bytes": 80.53, + "flops_per_problem": 4616277590.016 + }, + "sumd.rev.rev7": { + "acc": 0.986, + "reasoning_bytes": 88.4, + "flops_per_problem": 5008092364.8 + }, + "sumd.rev.rev8": { + "acc": 0.426, + "reasoning_bytes": 91.59, + "flops_per_problem": 5193047310.336 + }, + "runmax.inc.runmax12": { + "acc": 1.0, + "reasoning_bytes": 109.648, + "flops_per_problem": 6343936966.656 + }, + "runmax.inc.runmax14": { + "acc": 1.0, + "reasoning_bytes": 122.196, + "flops_per_problem": 6986421338.112 + }, + "runmax.inc.runmax16": { + "acc": 0.976, + "reasoning_bytes": 128.528, + "flops_per_problem": 7354388054.016 + }, + "parity.inc.find16": { + "acc": 1.0, + "reasoning_bytes": 128.0, + "flops_per_problem": 7331069952.0 + }, + "parity.inc.find20": { + "acc": 0.956, + "reasoning_bytes": 149.288, + "flops_per_problem": 8447865716.736 + }, + "parity.inc.find24": { + "acc": 0.898, + "reasoning_bytes": 169.772, + "flops_per_problem": 9529154371.584 + }, + "inc.runmax.sumd6": { + "acc": 1.0, + "reasoning_bytes": 119.0, + "flops_per_problem": 6403645440.0 + }, + "inc.runmax.sumd7": { + "acc": 0.996, + "reasoning_bytes": 134.984, + "flops_per_problem": 7153711054.848 + }, + "inc.runmax.sumd8": { + "acc": 0.842, + "reasoning_bytes": 146.522, + "flops_per_problem": 7707427651.584 + }, + "sumd.rev.cmp6": { + "acc": 0.836, + "reasoning_bytes": 73.996, + "flops_per_problem": 4416130547.712 + }, + "sumd.rev.cmp7": { + "acc": 0.766, + "reasoning_bytes": 73.812, + "flops_per_problem": 4452520919.04 + }, + "sumd.rev.cmp8": { + "acc": 0.67, + "reasoning_bytes": 72.484, + "flops_per_problem": 4437947105.28 + }, + "runmax.runmax.count12": { + "acc": 1.0, + "reasoning_bytes": 105.0, + "flops_per_problem": 6315319296.0 + }, + "runmax.runmax.count14": { + "acc": 1.0, + "reasoning_bytes": 117.0, + "flops_per_problem": 6933602304.0 + }, + "runmax.runmax.count16": { + "acc": 1.0, + "reasoning_bytes": 125.328, + "flops_per_problem": 7389718511.616 + }, + "count.count.count16": { + "acc": 1.0, + "reasoning_bytes": 113.0, + "flops_per_problem": 6933602304.0 + }, + "count.count.count18": { + "acc": 1.0, + "reasoning_bytes": 122.96, + "flops_per_problem": 7461792645.12 + }, + "count.count.count20": { + "acc": 1.0, + "reasoning_bytes": 130.438, + "flops_per_problem": 7880370241.536 + }, + "add.sumd.rev6": { + "acc": 1.0, + "reasoning_bytes": 145.448, + "flops_per_problem": 7792309075.968 + }, + "add.sumd.rev7": { + "acc": 0.928, + "reasoning_bytes": 165.356, + "flops_per_problem": 8759921983.488 + }, + "add.sumd.rev8": { + "acc": 0.044, + "reasoning_bytes": 184.698, + "flops_per_problem": 9704040136.704 + }, + "add.rev.rev6": { + "acc": 1.0, + "reasoning_bytes": 187.496, + "flops_per_problem": 9808618291.2 + }, + "add.rev.rev7": { + "acc": 0.514, + "reasoning_bytes": 222.35, + "flops_per_problem": 11469326450.688 + }, + "add.rev.rev8": { + "acc": 0.0, + "reasoning_bytes": 242.41, + "flops_per_problem": 12454251282.432 + }, + "inc.runmax.cmp6": { + "acc": 0.52, + "reasoning_bytes": 103.238, + "flops_per_problem": 5751710171.136 + }, + "inc.runmax.cmp7": { + "acc": 0.048, + "reasoning_bytes": 117.248, + "flops_per_problem": 6414597881.856 + }, + "inc.runmax.cmp8": { + "acc": 0.106, + "reasoning_bytes": 126.908, + "flops_per_problem": 6885376229.376 + }, + "count.rev.cmp16": { + "acc": 1.0, + "reasoning_bytes": 107.0, + "flops_per_problem": 6403645440.0 + }, + "count.rev.cmp18": { + "acc": 0.994, + "reasoning_bytes": 116.93, + "flops_per_problem": 6930599215.104 + }, + "count.rev.cmp20": { + "acc": 0.962, + "reasoning_bytes": 122.7, + "flops_per_problem": 7273834610.688 + } +} \ No newline at end of file