| { | |
| "best_metric": 0.2850205600261688, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.02386029795547072, | |
| "eval_steps": 25, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00023860297955470718, | |
| "grad_norm": 3.9051380157470703, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 3.7044, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023860297955470718, | |
| "eval_loss": 6.847388744354248, | |
| "eval_runtime": 4.8319, | |
| "eval_samples_per_second": 10.348, | |
| "eval_steps_per_second": 10.348, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00047720595910941436, | |
| "grad_norm": 4.679457187652588, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 4.7098, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007158089386641215, | |
| "grad_norm": 9.108196258544922, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 5.1787, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009544119182188287, | |
| "grad_norm": 6.725158214569092, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 5.0075, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001193014897773536, | |
| "grad_norm": 7.477461814880371, | |
| "learning_rate": 0.00015, | |
| "loss": 4.907, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001431617877328243, | |
| "grad_norm": 6.358967304229736, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 3.436, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016702208568829503, | |
| "grad_norm": 5.095180034637451, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.5721, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0019088238364376574, | |
| "grad_norm": 6.78561544418335, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.2853, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002147426815992365, | |
| "grad_norm": 6.9174957275390625, | |
| "learning_rate": 0.00027, | |
| "loss": 1.0685, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002386029795547072, | |
| "grad_norm": 22.914854049682617, | |
| "learning_rate": 0.0003, | |
| "loss": 1.4754, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002624632775101779, | |
| "grad_norm": 24.160343170166016, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 1.4382, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002863235754656486, | |
| "grad_norm": 4.804904937744141, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.5051, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0031018387342111936, | |
| "grad_norm": 4.3781657218933105, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.4762, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0033404417137659005, | |
| "grad_norm": 4.082606315612793, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.3869, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003579044693320608, | |
| "grad_norm": 3.5891997814178467, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.4191, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003817647672875315, | |
| "grad_norm": 3.904242515563965, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.4828, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004056250652430022, | |
| "grad_norm": 4.260214805603027, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.5526, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00429485363198473, | |
| "grad_norm": 3.2408618927001953, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.4121, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004533456611539436, | |
| "grad_norm": 2.9760124683380127, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.3412, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004772059591094144, | |
| "grad_norm": 5.297372817993164, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.4715, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005010662570648851, | |
| "grad_norm": 4.5428338050842285, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.5035, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005249265550203558, | |
| "grad_norm": 2.42583966255188, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.2874, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005487868529758265, | |
| "grad_norm": 1.9801936149597168, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.2981, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005726471509312972, | |
| "grad_norm": 5.431916236877441, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.4561, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00596507448886768, | |
| "grad_norm": 3.5752675533294678, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.372, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00596507448886768, | |
| "eval_loss": 0.5305390357971191, | |
| "eval_runtime": 4.9396, | |
| "eval_samples_per_second": 10.122, | |
| "eval_steps_per_second": 10.122, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006203677468422387, | |
| "grad_norm": 5.811082363128662, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.5621, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0064422804479770945, | |
| "grad_norm": 3.068842887878418, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.3989, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006680883427531801, | |
| "grad_norm": 2.5508522987365723, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.4297, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0069194864070865085, | |
| "grad_norm": 3.687291145324707, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.3715, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007158089386641216, | |
| "grad_norm": 2.5837249755859375, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.3211, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007396692366195923, | |
| "grad_norm": 1.6409099102020264, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.2163, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.00763529534575063, | |
| "grad_norm": 1.997084617614746, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.2928, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.007873898325305337, | |
| "grad_norm": 1.8158376216888428, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.187, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.008112501304860045, | |
| "grad_norm": 2.2966806888580322, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.3337, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.008351104284414752, | |
| "grad_norm": 2.18530011177063, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.2818, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00858970726396946, | |
| "grad_norm": 1.9994254112243652, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.2846, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.008828310243524167, | |
| "grad_norm": 2.239995241165161, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.3391, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009066913223078872, | |
| "grad_norm": 1.9311068058013916, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.2792, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00930551620263358, | |
| "grad_norm": 2.596693992614746, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.265, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.009544119182188287, | |
| "grad_norm": 1.8563891649246216, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.2592, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009782722161742995, | |
| "grad_norm": 3.4870285987854004, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.5375, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.010021325141297702, | |
| "grad_norm": 2.2381041049957275, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.5, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01025992812085241, | |
| "grad_norm": 2.5200259685516357, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.4273, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.010498531100407117, | |
| "grad_norm": 1.4027842283248901, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.3226, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.010737134079961824, | |
| "grad_norm": 2.0196170806884766, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.3148, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01097573705951653, | |
| "grad_norm": 1.3912042379379272, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.3065, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.011214340039071237, | |
| "grad_norm": 1.8494808673858643, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.3245, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.011452943018625945, | |
| "grad_norm": 1.9083304405212402, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.3276, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.011691545998180652, | |
| "grad_norm": 1.7160670757293701, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.3039, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01193014897773536, | |
| "grad_norm": 1.9495787620544434, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.1993, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01193014897773536, | |
| "eval_loss": 0.3537612855434418, | |
| "eval_runtime": 4.9424, | |
| "eval_samples_per_second": 10.117, | |
| "eval_steps_per_second": 10.117, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012168751957290067, | |
| "grad_norm": 1.6003544330596924, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 0.3157, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.012407354936844774, | |
| "grad_norm": 1.2938302755355835, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 0.374, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.012645957916399482, | |
| "grad_norm": 1.600176215171814, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 0.3464, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.012884560895954189, | |
| "grad_norm": 1.3842864036560059, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 0.1721, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.013123163875508895, | |
| "grad_norm": 1.3391578197479248, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 0.2234, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.013361766855063602, | |
| "grad_norm": 1.2759987115859985, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 0.1884, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.01360036983461831, | |
| "grad_norm": 1.2416960000991821, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 0.2361, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.013838972814173017, | |
| "grad_norm": 1.3021742105484009, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 0.1999, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.014077575793727724, | |
| "grad_norm": 3.010028600692749, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 0.2434, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.014316178773282432, | |
| "grad_norm": 1.4798487424850464, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 0.1968, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.014554781752837139, | |
| "grad_norm": 1.279167652130127, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 0.2113, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.014793384732391847, | |
| "grad_norm": 1.1728774309158325, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 0.2935, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.015031987711946552, | |
| "grad_norm": 1.197998285293579, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 0.2799, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.01527059069150126, | |
| "grad_norm": 0.7270916104316711, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 0.1325, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.015509193671055967, | |
| "grad_norm": 1.4482795000076294, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 0.095, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.015747796650610674, | |
| "grad_norm": 1.8109567165374756, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 0.2474, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.01598639963016538, | |
| "grad_norm": 1.784266710281372, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.1641, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.01622500260972009, | |
| "grad_norm": 1.81675386428833, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 0.1561, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.016463605589274795, | |
| "grad_norm": 2.7498233318328857, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 0.3468, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.016702208568829504, | |
| "grad_norm": 2.1186411380767822, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 0.1536, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01694081154838421, | |
| "grad_norm": 2.016608238220215, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 0.2577, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.01717941452793892, | |
| "grad_norm": 2.4243433475494385, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 0.3607, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.017418017507493624, | |
| "grad_norm": 2.7519173622131348, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 0.4148, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.017656620487048334, | |
| "grad_norm": 2.557842493057251, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 0.4217, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.01789522346660304, | |
| "grad_norm": 2.0161449909210205, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 0.4113, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.01789522346660304, | |
| "eval_loss": 0.33875352144241333, | |
| "eval_runtime": 4.9431, | |
| "eval_samples_per_second": 10.115, | |
| "eval_steps_per_second": 10.115, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.018133826446157745, | |
| "grad_norm": 1.2532881498336792, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 0.1656, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.018372429425712454, | |
| "grad_norm": 1.2047579288482666, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 0.2783, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.01861103240526716, | |
| "grad_norm": 1.158872365951538, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 0.1534, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.01884963538482187, | |
| "grad_norm": 1.1011089086532593, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 0.2037, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.019088238364376574, | |
| "grad_norm": 1.56781005859375, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 0.3891, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.019326841343931284, | |
| "grad_norm": 1.317081332206726, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 0.3069, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.01956544432348599, | |
| "grad_norm": 1.2627768516540527, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 0.3146, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.0198040473030407, | |
| "grad_norm": 1.6412408351898193, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 0.2902, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.020042650282595404, | |
| "grad_norm": 1.0755120515823364, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 0.2345, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.02028125326215011, | |
| "grad_norm": 0.9814028143882751, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 0.1788, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.02051985624170482, | |
| "grad_norm": 1.0559604167938232, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.2431, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.020758459221259525, | |
| "grad_norm": 0.9600143432617188, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 0.2243, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.020997062200814234, | |
| "grad_norm": 1.8274849653244019, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 0.3017, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.02123566518036894, | |
| "grad_norm": 1.2286986112594604, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 0.293, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.02147426815992365, | |
| "grad_norm": 0.8336792588233948, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 0.165, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.021712871139478354, | |
| "grad_norm": 2.1570754051208496, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 0.2711, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.02195147411903306, | |
| "grad_norm": 1.6255114078521729, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 0.4418, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.02219007709858777, | |
| "grad_norm": 1.1934351921081543, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 0.3236, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.022428680078142475, | |
| "grad_norm": 1.2108948230743408, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 0.2587, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.022667283057697184, | |
| "grad_norm": 2.282270908355713, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 0.3602, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.02290588603725189, | |
| "grad_norm": 1.5604966878890991, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 0.2781, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.0231444890168066, | |
| "grad_norm": 1.4344300031661987, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 0.3214, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.023383091996361304, | |
| "grad_norm": 1.685638666152954, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 0.3074, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.023621694975916013, | |
| "grad_norm": 1.0541924238204956, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 0.1001, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.02386029795547072, | |
| "grad_norm": 1.225070834159851, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 0.1181, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02386029795547072, | |
| "eval_loss": 0.2850205600261688, | |
| "eval_runtime": 4.9375, | |
| "eval_samples_per_second": 10.127, | |
| "eval_steps_per_second": 10.127, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.576510477565952e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |