| { | |
| "best_metric": 0.2768600583076477, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.5080440304826418, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003386960203217612, | |
| "grad_norm": 13.740797996520996, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 3.1754, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003386960203217612, | |
| "eval_loss": 4.746492385864258, | |
| "eval_runtime": 6.8487, | |
| "eval_samples_per_second": 7.301, | |
| "eval_steps_per_second": 1.022, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006773920406435224, | |
| "grad_norm": 15.781672477722168, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 3.1112, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010160880609652836, | |
| "grad_norm": 13.645687103271484, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 3.0881, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013547840812870448, | |
| "grad_norm": 9.539155960083008, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.7159, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01693480101608806, | |
| "grad_norm": 4.083582878112793, | |
| "learning_rate": 0.00015, | |
| "loss": 0.4898, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02032176121930567, | |
| "grad_norm": 2.5189051628112793, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.2539, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023708721422523286, | |
| "grad_norm": 6.38540506362915, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.3516, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.027095681625740897, | |
| "grad_norm": 13.505107879638672, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.5986, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03048264182895851, | |
| "grad_norm": 3.495882987976074, | |
| "learning_rate": 0.00027, | |
| "loss": 0.2681, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03386960203217612, | |
| "grad_norm": 4.064078330993652, | |
| "learning_rate": 0.0003, | |
| "loss": 0.1063, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03725656223539373, | |
| "grad_norm": 5.738462924957275, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.0551, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04064352243861134, | |
| "grad_norm": 11.198445320129395, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.5952, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04403048264182896, | |
| "grad_norm": 10.263776779174805, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.4714, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04741744284504657, | |
| "grad_norm": 13.766398429870605, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.615, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05080440304826418, | |
| "grad_norm": 6.041114330291748, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.6127, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05419136325148179, | |
| "grad_norm": 3.049060583114624, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.5814, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.057578323454699404, | |
| "grad_norm": 2.864790678024292, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.4473, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06096528365791702, | |
| "grad_norm": 6.220133304595947, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.4051, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06435224386113463, | |
| "grad_norm": 2.263486862182617, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.2403, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06773920406435224, | |
| "grad_norm": 4.127490520477295, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.2728, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07112616426756986, | |
| "grad_norm": 3.9908688068389893, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.2682, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07451312447078746, | |
| "grad_norm": 9.111742973327637, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.2637, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07790008467400508, | |
| "grad_norm": 3.493535280227661, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.2798, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08128704487722269, | |
| "grad_norm": 2.2693541049957275, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.2922, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0846740050804403, | |
| "grad_norm": 3.484853744506836, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.2737, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0846740050804403, | |
| "eval_loss": 1.9888197183609009, | |
| "eval_runtime": 6.9843, | |
| "eval_samples_per_second": 7.159, | |
| "eval_steps_per_second": 1.002, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08806096528365792, | |
| "grad_norm": 2.42002534866333, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.1555, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09144792548687553, | |
| "grad_norm": 4.468302249908447, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.2272, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09483488569009314, | |
| "grad_norm": 4.684446334838867, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.5432, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09822184589331075, | |
| "grad_norm": 11.514558792114258, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.4408, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10160880609652836, | |
| "grad_norm": 4.456749439239502, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.3308, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10499576629974598, | |
| "grad_norm": 6.331120491027832, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.7949, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10838272650296359, | |
| "grad_norm": 29.455829620361328, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 4.6651, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1117696867061812, | |
| "grad_norm": 11.79928970336914, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 1.6663, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11515664690939881, | |
| "grad_norm": 6.791766166687012, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.6458, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11854360711261643, | |
| "grad_norm": 9.273675918579102, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.6169, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12193056731583404, | |
| "grad_norm": 1.2118967771530151, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.315, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12531752751905165, | |
| "grad_norm": 3.5652599334716797, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.3108, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12870448772226925, | |
| "grad_norm": 1.0388684272766113, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.3072, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.13209144792548688, | |
| "grad_norm": 1.3198330402374268, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.2595, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1354784081287045, | |
| "grad_norm": 9.642812728881836, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.4847, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1388653683319221, | |
| "grad_norm": 8.038244247436523, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.4086, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.14225232853513972, | |
| "grad_norm": 2.3692054748535156, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.3204, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14563928873835733, | |
| "grad_norm": 0.9498773217201233, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.2721, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.14902624894157493, | |
| "grad_norm": 0.9654709100723267, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.1986, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.15241320914479256, | |
| "grad_norm": 3.0386719703674316, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.2193, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15580016934801016, | |
| "grad_norm": 4.969003200531006, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.296, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15918712955122777, | |
| "grad_norm": 5.841146945953369, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.5754, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.16257408975444537, | |
| "grad_norm": 4.163698196411133, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.3311, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.165961049957663, | |
| "grad_norm": 0.9581086039543152, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.1751, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1693480101608806, | |
| "grad_norm": 0.8359802961349487, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.1348, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1693480101608806, | |
| "eval_loss": 4.9084954261779785, | |
| "eval_runtime": 6.9763, | |
| "eval_samples_per_second": 7.167, | |
| "eval_steps_per_second": 1.003, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1727349703640982, | |
| "grad_norm": 32.02179718017578, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 7.2472, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.17612193056731584, | |
| "grad_norm": 22.66502571105957, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 4.8676, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.17950889077053345, | |
| "grad_norm": 14.20208740234375, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 2.6102, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.18289585097375105, | |
| "grad_norm": 5.688993453979492, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 1.1202, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.18628281117696868, | |
| "grad_norm": 3.7992303371429443, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 0.7116, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1896697713801863, | |
| "grad_norm": 3.9511473178863525, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 0.5208, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1930567315834039, | |
| "grad_norm": 7.438797473907471, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 0.5567, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.1964436917866215, | |
| "grad_norm": 5.829729080200195, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 0.293, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.19983065198983913, | |
| "grad_norm": 9.083565711975098, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 0.1996, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.20321761219305673, | |
| "grad_norm": 5.10175895690918, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 0.3137, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.20660457239627433, | |
| "grad_norm": 15.429557800292969, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 0.3407, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.20999153259949196, | |
| "grad_norm": 18.3114070892334, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 0.4097, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.21337849280270957, | |
| "grad_norm": 3.552994966506958, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 0.4042, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.21676545300592717, | |
| "grad_norm": 4.608700275421143, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 0.4649, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.2201524132091448, | |
| "grad_norm": 2.5039749145507812, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 0.3056, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2235393734123624, | |
| "grad_norm": 3.510558843612671, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 0.3055, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.22692633361558, | |
| "grad_norm": 16.571596145629883, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.1449, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.23031329381879762, | |
| "grad_norm": 7.662303447723389, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 0.2374, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.23370025402201525, | |
| "grad_norm": 15.79422664642334, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 0.4983, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.23708721422523285, | |
| "grad_norm": 14.23752498626709, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 0.1434, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.24047417442845045, | |
| "grad_norm": 18.481346130371094, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 0.4387, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.2438611346316681, | |
| "grad_norm": 21.514892578125, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 0.4085, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.2472480948348857, | |
| "grad_norm": 4.610980033874512, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 0.3288, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.2506350550381033, | |
| "grad_norm": 3.399989604949951, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 0.2039, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.2540220152413209, | |
| "grad_norm": 4.643821716308594, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 0.3874, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2540220152413209, | |
| "eval_loss": 2.8409361839294434, | |
| "eval_runtime": 6.9844, | |
| "eval_samples_per_second": 7.159, | |
| "eval_steps_per_second": 1.002, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2574089754445385, | |
| "grad_norm": 2.7294604778289795, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 0.2599, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.26079593564775616, | |
| "grad_norm": 3.761537790298462, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 0.2562, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.26418289585097376, | |
| "grad_norm": 1.4261208772659302, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 0.1571, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.26756985605419137, | |
| "grad_norm": 6.343429088592529, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 0.3837, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.270956816257409, | |
| "grad_norm": 3.1032464504241943, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 0.2757, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2743437764606266, | |
| "grad_norm": 8.276625633239746, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 0.9201, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.2777307366638442, | |
| "grad_norm": 21.709529876708984, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 2.7845, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.28111769686706184, | |
| "grad_norm": 12.479153633117676, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 1.088, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.28450465707027944, | |
| "grad_norm": 16.008235931396484, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 2.6327, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.28789161727349705, | |
| "grad_norm": 24.19379425048828, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 3.6331, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.29127857747671465, | |
| "grad_norm": 15.384114265441895, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 1.6797, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.29466553767993225, | |
| "grad_norm": 6.6495513916015625, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 0.8018, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.29805249788314986, | |
| "grad_norm": 3.5732247829437256, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 0.3255, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.30143945808636746, | |
| "grad_norm": 2.2254087924957275, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 0.3037, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.3048264182895851, | |
| "grad_norm": 1.5037360191345215, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 0.2061, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3082133784928027, | |
| "grad_norm": 3.9089977741241455, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 0.3156, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.31160033869602033, | |
| "grad_norm": 3.679975748062134, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 0.1626, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.31498729889923793, | |
| "grad_norm": 13.911907196044922, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 0.6001, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.31837425910245554, | |
| "grad_norm": 8.585356712341309, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 0.3546, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.32176121930567314, | |
| "grad_norm": 3.8996129035949707, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 0.2943, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.32514817950889074, | |
| "grad_norm": 1.8221895694732666, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 0.2067, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.3285351397121084, | |
| "grad_norm": 1.2952618598937988, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 0.2006, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.331922099915326, | |
| "grad_norm": 5.522075176239014, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 0.4567, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.3353090601185436, | |
| "grad_norm": 2.7754757404327393, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 0.3529, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.3386960203217612, | |
| "grad_norm": 1.3497525453567505, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 0.2046, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3386960203217612, | |
| "eval_loss": 3.0519299507141113, | |
| "eval_runtime": 6.9889, | |
| "eval_samples_per_second": 7.154, | |
| "eval_steps_per_second": 1.002, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3420829805249788, | |
| "grad_norm": 38.04734802246094, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 3.9559, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.3454699407281964, | |
| "grad_norm": 26.404071807861328, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 2.5687, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.3488569009314141, | |
| "grad_norm": 15.545836448669434, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 1.778, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.3522438611346317, | |
| "grad_norm": 4.218338966369629, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 0.9969, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.3556308213378493, | |
| "grad_norm": 3.6731631755828857, | |
| "learning_rate": 0.00015, | |
| "loss": 0.8109, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.3590177815410669, | |
| "grad_norm": 3.383131265640259, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 0.6936, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.3624047417442845, | |
| "grad_norm": 3.4778740406036377, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 0.3881, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.3657917019475021, | |
| "grad_norm": 2.038445472717285, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 0.3805, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.3691786621507197, | |
| "grad_norm": 7.391066074371338, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 0.3025, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.37256562235393736, | |
| "grad_norm": 9.895805358886719, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 0.4677, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.37595258255715497, | |
| "grad_norm": 7.2605881690979, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 0.2445, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.3793395427603726, | |
| "grad_norm": 11.445152282714844, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 0.3512, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.3827265029635902, | |
| "grad_norm": 6.710597515106201, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 0.4151, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.3861134631668078, | |
| "grad_norm": 2.882502794265747, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 0.0975, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.3895004233700254, | |
| "grad_norm": 11.19640064239502, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 0.1504, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.392887383573243, | |
| "grad_norm": 2.5462589263916016, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 0.166, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.39627434377646065, | |
| "grad_norm": 6.280060768127441, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 0.3321, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.39966130397967825, | |
| "grad_norm": 3.742800235748291, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 0.2449, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.40304826418289585, | |
| "grad_norm": 4.07996129989624, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 0.1723, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.40643522438611346, | |
| "grad_norm": 2.472219705581665, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 0.1045, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.40982218458933106, | |
| "grad_norm": 5.641716003417969, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 0.3207, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.41320914479254867, | |
| "grad_norm": 7.763329029083252, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 0.2601, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.4165961049957663, | |
| "grad_norm": 5.5211501121521, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 0.3374, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.41998306519898393, | |
| "grad_norm": 5.142914772033691, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 0.3671, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.42337002540220153, | |
| "grad_norm": 3.195248603820801, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 0.1383, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.42337002540220153, | |
| "eval_loss": 0.8896229267120361, | |
| "eval_runtime": 6.9917, | |
| "eval_samples_per_second": 7.151, | |
| "eval_steps_per_second": 1.001, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.42675698560541914, | |
| "grad_norm": 1.123442530632019, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 0.1009, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.43014394580863674, | |
| "grad_norm": 4.091561794281006, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 0.1741, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.43353090601185434, | |
| "grad_norm": 3.3476603031158447, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 0.3535, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.43691786621507195, | |
| "grad_norm": 4.132399559020996, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 0.3354, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.4403048264182896, | |
| "grad_norm": 3.9859485626220703, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 0.2174, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4436917866215072, | |
| "grad_norm": 3.752464771270752, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 0.3398, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.4470787468247248, | |
| "grad_norm": 5.6418585777282715, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 0.5945, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.4504657070279424, | |
| "grad_norm": 5.202731609344482, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 0.5471, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.45385266723116, | |
| "grad_norm": 4.451300621032715, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 0.5935, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.4572396274343776, | |
| "grad_norm": 11.032302856445312, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 0.9239, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.46062658763759523, | |
| "grad_norm": 6.030894756317139, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 0.5839, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.4640135478408129, | |
| "grad_norm": 4.059135913848877, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 0.5012, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.4674005080440305, | |
| "grad_norm": 3.3977863788604736, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 0.3867, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.4707874682472481, | |
| "grad_norm": 2.3960726261138916, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 0.3875, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.4741744284504657, | |
| "grad_norm": 1.9398398399353027, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 0.2928, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4775613886536833, | |
| "grad_norm": 2.1065077781677246, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 0.2398, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.4809483488569009, | |
| "grad_norm": 2.4689295291900635, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 0.2825, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.48433530906011857, | |
| "grad_norm": 2.2755885124206543, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.2738, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.4877222692633362, | |
| "grad_norm": 3.0065155029296875, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 0.369, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.4911092294665538, | |
| "grad_norm": 1.313037633895874, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 0.266, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.4944961896697714, | |
| "grad_norm": 0.7761518359184265, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 0.2709, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.497883149872989, | |
| "grad_norm": 0.8235387206077576, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 0.2851, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.5012701100762066, | |
| "grad_norm": 1.2671778202056885, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 0.2433, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.5046570702794242, | |
| "grad_norm": 1.3252907991409302, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 0.2527, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.5080440304826418, | |
| "grad_norm": 1.3691195249557495, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 0.246, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5080440304826418, | |
| "eval_loss": 0.2768600583076477, | |
| "eval_runtime": 6.982, | |
| "eval_samples_per_second": 7.161, | |
| "eval_steps_per_second": 1.003, | |
| "step": 150 | |
| } | |
| ], | |
| "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": 2.625264977707008e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |