| { | |
| "best_metric": 10.34074592590332, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.006003782382901228, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.0025215886008184e-05, | |
| "grad_norm": 0.028526226058602333, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 10.3783, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.0025215886008184e-05, | |
| "eval_loss": 10.376290321350098, | |
| "eval_runtime": 0.12, | |
| "eval_samples_per_second": 416.641, | |
| "eval_steps_per_second": 58.33, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.005043177201637e-05, | |
| "grad_norm": 0.029773740097880363, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 10.3765, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00012007564765802456, | |
| "grad_norm": 0.02794136479496956, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 10.3763, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00016010086354403274, | |
| "grad_norm": 0.030925514176487923, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 10.3774, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00020012607943004093, | |
| "grad_norm": 0.03159649670124054, | |
| "learning_rate": 0.00015, | |
| "loss": 10.3771, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00024015129531604912, | |
| "grad_norm": 0.028680993244051933, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 10.3756, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002801765112020573, | |
| "grad_norm": 0.03433338180184364, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 10.3776, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003202017270880655, | |
| "grad_norm": 0.03138856589794159, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 10.3761, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00036022694297407367, | |
| "grad_norm": 0.030663292855024338, | |
| "learning_rate": 0.00027, | |
| "loss": 10.3776, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00040025215886008186, | |
| "grad_norm": 0.034716520458459854, | |
| "learning_rate": 0.0003, | |
| "loss": 10.377, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00044027737474609005, | |
| "grad_norm": 0.03367249295115471, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 10.3767, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00048030259063209824, | |
| "grad_norm": 0.03586790710687637, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 10.3749, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005203278065181064, | |
| "grad_norm": 0.03616034612059593, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 10.3755, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0005603530224041146, | |
| "grad_norm": 0.03707385063171387, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 10.3747, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0006003782382901228, | |
| "grad_norm": 0.040910378098487854, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 10.3772, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000640403454176131, | |
| "grad_norm": 0.037733159959316254, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 10.3738, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006804286700621392, | |
| "grad_norm": 0.04005344212055206, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 10.3723, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0007204538859481473, | |
| "grad_norm": 0.03841446712613106, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 10.3719, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007604791018341555, | |
| "grad_norm": 0.04704993590712547, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 10.3739, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0008005043177201637, | |
| "grad_norm": 0.04559043422341347, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 10.3732, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008405295336061719, | |
| "grad_norm": 0.052254363894462585, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 10.3717, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0008805547494921801, | |
| "grad_norm": 0.05502045899629593, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 10.3717, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0009205799653781882, | |
| "grad_norm": 0.061194684356451035, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 10.3695, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0009606051812641965, | |
| "grad_norm": 0.059378888458013535, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 10.3712, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0010006303971502046, | |
| "grad_norm": 0.06684457510709763, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 10.371, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010006303971502046, | |
| "eval_loss": 10.367866516113281, | |
| "eval_runtime": 0.1084, | |
| "eval_samples_per_second": 461.359, | |
| "eval_steps_per_second": 64.59, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010406556130362129, | |
| "grad_norm": 0.07267913222312927, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 10.3678, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.001080680828922221, | |
| "grad_norm": 0.07705136388540268, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 10.3684, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0011207060448082291, | |
| "grad_norm": 0.08530186861753464, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 10.3682, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0011607312606942374, | |
| "grad_norm": 0.08188481628894806, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 10.3672, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0012007564765802456, | |
| "grad_norm": 0.08364146202802658, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 10.367, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0012407816924662537, | |
| "grad_norm": 0.09279844909906387, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 10.3662, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.001280806908352262, | |
| "grad_norm": 0.08991207182407379, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 10.3624, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0013208321242382701, | |
| "grad_norm": 0.09190763533115387, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 10.3623, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0013608573401242784, | |
| "grad_norm": 0.10333334654569626, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 10.3643, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0014008825560102864, | |
| "grad_norm": 0.10039209574460983, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 10.3599, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0014409077718962947, | |
| "grad_norm": 0.08169548213481903, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 10.3611, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.001480932987782303, | |
| "grad_norm": 0.0989358052611351, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 10.3563, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.001520958203668311, | |
| "grad_norm": 0.07897914946079254, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 10.3573, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0015609834195543192, | |
| "grad_norm": 0.08730727434158325, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 10.3569, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0016010086354403274, | |
| "grad_norm": 0.08495213836431503, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 10.3552, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0016410338513263357, | |
| "grad_norm": 0.08885069191455841, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 10.3535, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0016810590672123437, | |
| "grad_norm": 0.08947066962718964, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 10.3559, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.001721084283098352, | |
| "grad_norm": 0.06976769864559174, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 10.3517, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0017611094989843602, | |
| "grad_norm": 0.0737992525100708, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 10.353, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0018011347148703684, | |
| "grad_norm": 0.06612483412027359, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 10.351, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0018411599307563765, | |
| "grad_norm": 0.06353169679641724, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 10.3521, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0018811851466423847, | |
| "grad_norm": 0.05199315771460533, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 10.353, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.001921210362528393, | |
| "grad_norm": 0.04880088195204735, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 10.3521, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.001961235578414401, | |
| "grad_norm": 0.046220581978559494, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 10.3528, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0020012607943004092, | |
| "grad_norm": 0.05683967471122742, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 10.3495, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0020012607943004092, | |
| "eval_loss": 10.347744941711426, | |
| "eval_runtime": 0.107, | |
| "eval_samples_per_second": 467.451, | |
| "eval_steps_per_second": 65.443, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0020412860101864175, | |
| "grad_norm": 0.0570235475897789, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 10.3473, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0020813112260724257, | |
| "grad_norm": 0.05256696790456772, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 10.3477, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.002121336441958434, | |
| "grad_norm": 0.050024162977933884, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 10.3462, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.002161361657844442, | |
| "grad_norm": 0.044158052653074265, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 10.3468, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.00220138687373045, | |
| "grad_norm": 0.037897855043411255, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 10.345, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0022414120896164583, | |
| "grad_norm": 0.03886739909648895, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 10.3459, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0022814373055024665, | |
| "grad_norm": 0.03855080157518387, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 10.3469, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0023214625213884748, | |
| "grad_norm": 0.03083566203713417, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 10.3466, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.002361487737274483, | |
| "grad_norm": 0.04203694686293602, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 10.3473, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0024015129531604913, | |
| "grad_norm": 0.0328681580722332, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 10.3459, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0024415381690464995, | |
| "grad_norm": 0.041080042719841, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 10.3473, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0024815633849325073, | |
| "grad_norm": 0.03488178178668022, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 10.3477, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0025215886008185156, | |
| "grad_norm": 0.03356154263019562, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 10.3463, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.002561613816704524, | |
| "grad_norm": 0.03565945848822594, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 10.3465, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.002601639032590532, | |
| "grad_norm": 0.03525278717279434, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 10.3463, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0026416642484765403, | |
| "grad_norm": 0.030987795442342758, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 10.3464, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0026816894643625485, | |
| "grad_norm": 0.03691093251109123, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 10.3446, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0027217146802485568, | |
| "grad_norm": 0.02858724258840084, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 10.3457, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0027617398961345646, | |
| "grad_norm": 0.028253184631466866, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 10.3462, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.002801765112020573, | |
| "grad_norm": 0.0265846885740757, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 10.3458, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.002841790327906581, | |
| "grad_norm": 0.024350864812731743, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 10.3461, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0028818155437925893, | |
| "grad_norm": 0.02521437034010887, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 10.3459, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0029218407596785976, | |
| "grad_norm": 0.02496977150440216, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 10.344, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.002961865975564606, | |
| "grad_norm": 0.02404792234301567, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 10.3472, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.003001891191450614, | |
| "grad_norm": 0.03010077029466629, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 10.3448, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.003001891191450614, | |
| "eval_loss": 10.344749450683594, | |
| "eval_runtime": 0.1148, | |
| "eval_samples_per_second": 435.418, | |
| "eval_steps_per_second": 60.959, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.003041916407336622, | |
| "grad_norm": 0.03037099912762642, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 10.3465, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.00308194162322263, | |
| "grad_norm": 0.02771282009780407, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 10.3456, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.0031219668391086384, | |
| "grad_norm": 0.030444588512182236, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 10.3459, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0031619920549946466, | |
| "grad_norm": 0.024369996041059494, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 10.3458, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.003202017270880655, | |
| "grad_norm": 0.027669133618474007, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 10.3449, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.003242042486766663, | |
| "grad_norm": 0.031292203813791275, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 10.3441, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.0032820677026526713, | |
| "grad_norm": 0.034893427044153214, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 10.344, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.003322092918538679, | |
| "grad_norm": 0.028071342036128044, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 10.3466, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.0033621181344246874, | |
| "grad_norm": 0.028758805245161057, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 10.3461, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.0034021433503106956, | |
| "grad_norm": 0.02521163411438465, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 10.3451, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.003442168566196704, | |
| "grad_norm": 0.02419993281364441, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 10.3446, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.003482193782082712, | |
| "grad_norm": 0.030451122671365738, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 10.3444, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.0035222189979687204, | |
| "grad_norm": 0.0291582141071558, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 10.3446, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.0035622442138547286, | |
| "grad_norm": 0.03053348883986473, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 10.3463, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.003602269429740737, | |
| "grad_norm": 0.02546672895550728, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 10.3462, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0036422946456267447, | |
| "grad_norm": 0.01910708285868168, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 10.3479, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.003682319861512753, | |
| "grad_norm": 0.028761953115463257, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 10.3462, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.003722345077398761, | |
| "grad_norm": 0.030038416385650635, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 10.3442, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.0037623702932847694, | |
| "grad_norm": 0.0467698760330677, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 10.3429, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.0038023955091707777, | |
| "grad_norm": 0.040200911462306976, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 10.345, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.003842420725056786, | |
| "grad_norm": 0.035459116101264954, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 10.3434, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.003882445940942794, | |
| "grad_norm": 0.04996730759739876, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 10.3456, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.003922471156828802, | |
| "grad_norm": 0.04418378323316574, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 10.345, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.003962496372714811, | |
| "grad_norm": 0.0408267080783844, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 10.348, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.0040025215886008185, | |
| "grad_norm": 0.04399069771170616, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 10.3486, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0040025215886008185, | |
| "eval_loss": 10.34278678894043, | |
| "eval_runtime": 0.1057, | |
| "eval_samples_per_second": 472.919, | |
| "eval_steps_per_second": 66.209, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004042546804486826, | |
| "grad_norm": 0.052478134632110596, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 10.3423, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.004082572020372835, | |
| "grad_norm": 0.045471854507923126, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 10.3428, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.004122597236258843, | |
| "grad_norm": 0.041743166744709015, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 10.3417, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.0041626224521448514, | |
| "grad_norm": 0.033049073070287704, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 10.3442, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.004202647668030859, | |
| "grad_norm": 0.0301619041711092, | |
| "learning_rate": 0.00015, | |
| "loss": 10.3423, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.004242672883916868, | |
| "grad_norm": 0.03192288801074028, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 10.3433, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.004282698099802876, | |
| "grad_norm": 0.029192527756094933, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 10.343, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.004322723315688884, | |
| "grad_norm": 0.029016323387622833, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 10.3435, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.004362748531574892, | |
| "grad_norm": 0.029492976143956184, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 10.3446, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.0044027737474609, | |
| "grad_norm": 0.02222723700106144, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 10.3425, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.004442798963346909, | |
| "grad_norm": 0.02423178032040596, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 10.343, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.0044828241792329165, | |
| "grad_norm": 0.029552271589636803, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 10.3431, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.004522849395118925, | |
| "grad_norm": 0.027868885546922684, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 10.3425, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.004562874611004933, | |
| "grad_norm": 0.023104622960090637, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 10.3429, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.004602899826890942, | |
| "grad_norm": 0.02286737971007824, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 10.3427, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.0046429250427769495, | |
| "grad_norm": 0.020947955548763275, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 10.3422, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.004682950258662957, | |
| "grad_norm": 0.022833609953522682, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 10.3437, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.004722975474548966, | |
| "grad_norm": 0.022169550880789757, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 10.3439, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.004763000690434974, | |
| "grad_norm": 0.01873929426074028, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 10.3435, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.0048030259063209825, | |
| "grad_norm": 0.03166031464934349, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 10.3433, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.00484305112220699, | |
| "grad_norm": 0.030801922082901, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 10.3406, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.004883076338092999, | |
| "grad_norm": 0.023730628192424774, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 10.3433, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.004923101553979007, | |
| "grad_norm": 0.0322398915886879, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 10.3416, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.004963126769865015, | |
| "grad_norm": 0.02186150848865509, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 10.3429, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.005003151985751023, | |
| "grad_norm": 0.026499362662434578, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 10.3425, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.005003151985751023, | |
| "eval_loss": 10.341180801391602, | |
| "eval_runtime": 0.1146, | |
| "eval_samples_per_second": 436.471, | |
| "eval_steps_per_second": 61.106, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.005043177201637031, | |
| "grad_norm": 0.0234071072191, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 10.3431, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.00508320241752304, | |
| "grad_norm": 0.019846584647893906, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 10.3423, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.005123227633409048, | |
| "grad_norm": 0.019798647612333298, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 10.344, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.005163252849295056, | |
| "grad_norm": 0.034398578107357025, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 10.3428, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.005203278065181064, | |
| "grad_norm": 0.02253597043454647, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 10.342, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.005243303281067072, | |
| "grad_norm": 0.025330521166324615, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 10.3435, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.005283328496953081, | |
| "grad_norm": 0.024900034070014954, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 10.3426, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.005323353712839088, | |
| "grad_norm": 0.023646056652069092, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 10.3449, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.005363378928725097, | |
| "grad_norm": 0.02373456209897995, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 10.3446, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.005403404144611105, | |
| "grad_norm": 0.02603626251220703, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 10.3425, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.0054434293604971136, | |
| "grad_norm": 0.02858271263539791, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 10.3449, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.005483454576383121, | |
| "grad_norm": 0.026183992624282837, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 10.3416, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.005523479792269129, | |
| "grad_norm": 0.02147825062274933, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 10.3423, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.005563505008155138, | |
| "grad_norm": 0.03183015063405037, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 10.3427, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.005603530224041146, | |
| "grad_norm": 0.031085003167390823, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 10.3439, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.005643555439927154, | |
| "grad_norm": 0.028146089985966682, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 10.3442, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.005683580655813162, | |
| "grad_norm": 0.024034341797232628, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 10.3426, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.005723605871699171, | |
| "grad_norm": 0.033353496342897415, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 10.3408, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.005763631087585179, | |
| "grad_norm": 0.03319213166832924, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 10.3431, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.0058036563034711865, | |
| "grad_norm": 0.04052115976810455, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 10.3426, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.005843681519357195, | |
| "grad_norm": 0.03346634283661842, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 10.3442, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.005883706735243203, | |
| "grad_norm": 0.032494258135557175, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 10.343, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.005923731951129212, | |
| "grad_norm": 0.035914331674575806, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 10.3456, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.0059637571670152194, | |
| "grad_norm": 0.03083469532430172, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 10.3451, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.006003782382901228, | |
| "grad_norm": 0.05328581482172012, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 10.3466, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.006003782382901228, | |
| "eval_loss": 10.34074592590332, | |
| "eval_runtime": 0.107, | |
| "eval_samples_per_second": 467.082, | |
| "eval_steps_per_second": 65.391, | |
| "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": 16838118899712.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |