| { | |
| "best_metric": 10.339714050292969, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.008005043177201637, | |
| "eval_steps": 25, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.0025215886008184e-05, | |
| "grad_norm": 0.031631357967853546, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 10.3783, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.0025215886008184e-05, | |
| "eval_loss": 10.376290321350098, | |
| "eval_runtime": 0.1629, | |
| "eval_samples_per_second": 306.865, | |
| "eval_steps_per_second": 42.961, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.005043177201637e-05, | |
| "grad_norm": 0.03165977820754051, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 10.3765, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00012007564765802456, | |
| "grad_norm": 0.029739394783973694, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 10.3763, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00016010086354403274, | |
| "grad_norm": 0.03128078579902649, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 10.3774, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00020012607943004093, | |
| "grad_norm": 0.03327089175581932, | |
| "learning_rate": 0.00015, | |
| "loss": 10.3771, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00024015129531604912, | |
| "grad_norm": 0.031221648678183556, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 10.3756, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002801765112020573, | |
| "grad_norm": 0.033140648156404495, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 10.3776, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003202017270880655, | |
| "grad_norm": 0.03264706954360008, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 10.3761, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00036022694297407367, | |
| "grad_norm": 0.03237176313996315, | |
| "learning_rate": 0.00027, | |
| "loss": 10.3775, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00040025215886008186, | |
| "grad_norm": 0.03519490361213684, | |
| "learning_rate": 0.0003, | |
| "loss": 10.377, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00044027737474609005, | |
| "grad_norm": 0.03602423146367073, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 10.3766, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00048030259063209824, | |
| "grad_norm": 0.0372912622988224, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 10.3748, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005203278065181064, | |
| "grad_norm": 0.0409846268594265, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 10.3753, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0005603530224041146, | |
| "grad_norm": 0.038565054535865784, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 10.3746, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0006003782382901228, | |
| "grad_norm": 0.04584704712033272, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 10.3769, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000640403454176131, | |
| "grad_norm": 0.0443044938147068, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 10.3734, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006804286700621392, | |
| "grad_norm": 0.046843986958265305, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 10.3719, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0007204538859481473, | |
| "grad_norm": 0.0493725948035717, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 10.3713, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007604791018341555, | |
| "grad_norm": 0.057320885360240936, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 10.3733, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0008005043177201637, | |
| "grad_norm": 0.056451402604579926, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 10.3725, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008405295336061719, | |
| "grad_norm": 0.06416947394609451, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 10.3709, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0008805547494921801, | |
| "grad_norm": 0.06632953882217407, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 10.3709, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0009205799653781882, | |
| "grad_norm": 0.07961234450340271, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 10.3681, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0009606051812641965, | |
| "grad_norm": 0.07279147952795029, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 10.37, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0010006303971502046, | |
| "grad_norm": 0.08351346105337143, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 10.3697, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010006303971502046, | |
| "eval_loss": 10.366039276123047, | |
| "eval_runtime": 0.1456, | |
| "eval_samples_per_second": 343.361, | |
| "eval_steps_per_second": 48.071, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010406556130362129, | |
| "grad_norm": 0.09310437738895416, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 10.3658, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.001080680828922221, | |
| "grad_norm": 0.09378130733966827, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 10.3663, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0011207060448082291, | |
| "grad_norm": 0.10403110831975937, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 10.3658, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0011607312606942374, | |
| "grad_norm": 0.09855637699365616, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 10.3649, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0012007564765802456, | |
| "grad_norm": 0.09459754824638367, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 10.3645, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0012407816924662537, | |
| "grad_norm": 0.10157828778028488, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 10.3639, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.001280806908352262, | |
| "grad_norm": 0.09586312621831894, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 10.3597, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0013208321242382701, | |
| "grad_norm": 0.09686974436044693, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 10.3595, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0013608573401242784, | |
| "grad_norm": 0.10700739920139313, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 10.3619, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0014008825560102864, | |
| "grad_norm": 0.10100480914115906, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 10.3571, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0014409077718962947, | |
| "grad_norm": 0.08027458190917969, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 10.3593, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.001480932987782303, | |
| "grad_norm": 0.08975960314273834, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 10.3537, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.001520958203668311, | |
| "grad_norm": 0.07283489406108856, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 10.3551, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0015609834195543192, | |
| "grad_norm": 0.07702310383319855, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 10.3544, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0016010086354403274, | |
| "grad_norm": 0.07644236087799072, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 10.3538, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0016410338513263357, | |
| "grad_norm": 0.08016783744096756, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 10.3513, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0016810590672123437, | |
| "grad_norm": 0.0817168653011322, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 10.3543, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.001721084283098352, | |
| "grad_norm": 0.06613239645957947, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 10.3509, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0017611094989843602, | |
| "grad_norm": 0.0739089846611023, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 10.352, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0018011347148703684, | |
| "grad_norm": 0.0704953670501709, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 10.3511, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0018411599307563765, | |
| "grad_norm": 0.06712953001260757, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 10.3521, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0018811851466423847, | |
| "grad_norm": 0.04802524298429489, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 10.3529, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.001921210362528393, | |
| "grad_norm": 0.0486036092042923, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 10.3516, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.001961235578414401, | |
| "grad_norm": 0.04487287998199463, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 10.3525, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0020012607943004092, | |
| "grad_norm": 0.061715804040431976, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 10.3493, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0020012607943004092, | |
| "eval_loss": 10.347302436828613, | |
| "eval_runtime": 0.1452, | |
| "eval_samples_per_second": 344.282, | |
| "eval_steps_per_second": 48.2, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0020412860101864175, | |
| "grad_norm": 0.059315428137779236, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 10.3472, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0020813112260724257, | |
| "grad_norm": 0.054883792996406555, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 10.3476, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.002121336441958434, | |
| "grad_norm": 0.05184870585799217, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 10.346, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.002161361657844442, | |
| "grad_norm": 0.04580259323120117, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 10.3466, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.00220138687373045, | |
| "grad_norm": 0.03658067807555199, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 10.3447, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0022414120896164583, | |
| "grad_norm": 0.03653530403971672, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 10.3457, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0022814373055024665, | |
| "grad_norm": 0.03813878819346428, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 10.3469, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0023214625213884748, | |
| "grad_norm": 0.026853034272789955, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 10.3462, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.002361487737274483, | |
| "grad_norm": 0.03866073861718178, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 10.3471, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0024015129531604913, | |
| "grad_norm": 0.03002983331680298, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 10.3458, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0024415381690464995, | |
| "grad_norm": 0.04265514016151428, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 10.3481, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0024815633849325073, | |
| "grad_norm": 0.035741109400987625, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 10.3474, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0025215886008185156, | |
| "grad_norm": 0.030464909970760345, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 10.3462, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.002561613816704524, | |
| "grad_norm": 0.03574507683515549, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 10.3464, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.002601639032590532, | |
| "grad_norm": 0.03380665183067322, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 10.3463, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0026416642484765403, | |
| "grad_norm": 0.03315335139632225, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 10.3463, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0026816894643625485, | |
| "grad_norm": 0.037679944187402725, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 10.3445, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0027217146802485568, | |
| "grad_norm": 0.029793309047818184, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 10.3457, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0027617398961345646, | |
| "grad_norm": 0.029628276824951172, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 10.3461, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.002801765112020573, | |
| "grad_norm": 0.02894148789346218, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 10.3458, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.002841790327906581, | |
| "grad_norm": 0.025133224204182625, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 10.3462, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0028818155437925893, | |
| "grad_norm": 0.029297346249222755, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 10.3457, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0029218407596785976, | |
| "grad_norm": 0.02636672556400299, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 10.3437, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.002961865975564606, | |
| "grad_norm": 0.027142280712723732, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 10.347, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.003001891191450614, | |
| "grad_norm": 0.032178737223148346, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 10.3449, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.003001891191450614, | |
| "eval_loss": 10.344524383544922, | |
| "eval_runtime": 0.1491, | |
| "eval_samples_per_second": 335.263, | |
| "eval_steps_per_second": 46.937, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.003041916407336622, | |
| "grad_norm": 0.03191864490509033, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 10.3465, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.00308194162322263, | |
| "grad_norm": 0.030026139691472054, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 10.3456, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.0031219668391086384, | |
| "grad_norm": 0.030527856200933456, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 10.3456, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0031619920549946466, | |
| "grad_norm": 0.02526240237057209, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 10.346, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.003202017270880655, | |
| "grad_norm": 0.028264405205845833, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 10.3447, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.003242042486766663, | |
| "grad_norm": 0.03205219283699989, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 10.3443, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.0032820677026526713, | |
| "grad_norm": 0.0387556366622448, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 10.3443, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.003322092918538679, | |
| "grad_norm": 0.02674328349530697, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 10.3467, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.0033621181344246874, | |
| "grad_norm": 0.029292669147253036, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 10.346, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.0034021433503106956, | |
| "grad_norm": 0.02718389220535755, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 10.3449, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.003442168566196704, | |
| "grad_norm": 0.023716706782579422, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 10.3446, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.003482193782082712, | |
| "grad_norm": 0.030224012210965157, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 10.3442, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.0035222189979687204, | |
| "grad_norm": 0.027252135798335075, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 10.3446, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.0035622442138547286, | |
| "grad_norm": 0.031860899180173874, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 10.3461, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.003602269429740737, | |
| "grad_norm": 0.024651000276207924, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 10.3456, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0036422946456267447, | |
| "grad_norm": 0.021395694464445114, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 10.3475, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.003682319861512753, | |
| "grad_norm": 0.02844615839421749, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 10.3456, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.003722345077398761, | |
| "grad_norm": 0.029111430048942566, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 10.3441, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.0037623702932847694, | |
| "grad_norm": 0.04474746063351631, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 10.343, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.0038023955091707777, | |
| "grad_norm": 0.041326723992824554, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 10.3458, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.003842420725056786, | |
| "grad_norm": 0.037037789821624756, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 10.3435, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.003882445940942794, | |
| "grad_norm": 0.049130525439977646, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 10.3454, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.003922471156828802, | |
| "grad_norm": 0.0425594188272953, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 10.3448, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.003962496372714811, | |
| "grad_norm": 0.04153624549508095, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 10.3475, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.0040025215886008185, | |
| "grad_norm": 0.04395274072885513, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 10.3474, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0040025215886008185, | |
| "eval_loss": 10.342674255371094, | |
| "eval_runtime": 0.1446, | |
| "eval_samples_per_second": 345.872, | |
| "eval_steps_per_second": 48.422, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004042546804486826, | |
| "grad_norm": 0.04903431236743927, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 10.3425, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.004082572020372835, | |
| "grad_norm": 0.043851159512996674, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 10.3429, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.004122597236258843, | |
| "grad_norm": 0.0410907119512558, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 10.3425, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.0041626224521448514, | |
| "grad_norm": 0.03217702358961105, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 10.3442, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.004202647668030859, | |
| "grad_norm": 0.03146671503782272, | |
| "learning_rate": 0.00015, | |
| "loss": 10.3423, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.004242672883916868, | |
| "grad_norm": 0.031313665211200714, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 10.3436, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.004282698099802876, | |
| "grad_norm": 0.032109472900629044, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 10.3429, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.004322723315688884, | |
| "grad_norm": 0.030720937997102737, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 10.3438, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.004362748531574892, | |
| "grad_norm": 0.031500861048698425, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 10.3444, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.0044027737474609, | |
| "grad_norm": 0.02337694726884365, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 10.3424, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.004442798963346909, | |
| "grad_norm": 0.02606005035340786, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 10.343, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.0044828241792329165, | |
| "grad_norm": 0.03022804670035839, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 10.3432, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.004522849395118925, | |
| "grad_norm": 0.03159715235233307, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 10.3426, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.004562874611004933, | |
| "grad_norm": 0.02606784552335739, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 10.3428, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.004602899826890942, | |
| "grad_norm": 0.02461070939898491, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 10.3427, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.0046429250427769495, | |
| "grad_norm": 0.023727763444185257, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 10.3416, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.004682950258662957, | |
| "grad_norm": 0.023438477888703346, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 10.3437, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.004722975474548966, | |
| "grad_norm": 0.023708466440439224, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 10.3437, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.004763000690434974, | |
| "grad_norm": 0.021747039631009102, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 10.3433, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.0048030259063209825, | |
| "grad_norm": 0.03227005526423454, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 10.3433, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.00484305112220699, | |
| "grad_norm": 0.03323833644390106, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 10.3408, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.004883076338092999, | |
| "grad_norm": 0.025677289813756943, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 10.3434, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.004923101553979007, | |
| "grad_norm": 0.035302046686410904, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 10.3415, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.004963126769865015, | |
| "grad_norm": 0.024027613922953606, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 10.343, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.005003151985751023, | |
| "grad_norm": 0.027833499014377594, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 10.3424, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.005003151985751023, | |
| "eval_loss": 10.340993881225586, | |
| "eval_runtime": 0.1474, | |
| "eval_samples_per_second": 339.229, | |
| "eval_steps_per_second": 47.492, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.005043177201637031, | |
| "grad_norm": 0.02594025619328022, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 10.3426, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.00508320241752304, | |
| "grad_norm": 0.02147498168051243, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 10.3422, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.005123227633409048, | |
| "grad_norm": 0.023630741983652115, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 10.3435, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.005163252849295056, | |
| "grad_norm": 0.03555876016616821, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 10.3426, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.005203278065181064, | |
| "grad_norm": 0.02538846619427204, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 10.3418, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.005243303281067072, | |
| "grad_norm": 0.026086509227752686, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 10.3428, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.005283328496953081, | |
| "grad_norm": 0.025817938148975372, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 10.3421, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.005323353712839088, | |
| "grad_norm": 0.023846304044127464, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 10.3451, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.005363378928725097, | |
| "grad_norm": 0.02583501860499382, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 10.3442, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.005403404144611105, | |
| "grad_norm": 0.02937057800590992, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 10.3423, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.0054434293604971136, | |
| "grad_norm": 0.03107895329594612, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 10.3446, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.005483454576383121, | |
| "grad_norm": 0.027957648038864136, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 10.3414, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.005523479792269129, | |
| "grad_norm": 0.020909804850816727, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 10.3419, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.005563505008155138, | |
| "grad_norm": 0.034404899924993515, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 10.3424, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.005603530224041146, | |
| "grad_norm": 0.03390046954154968, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 10.343, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.005643555439927154, | |
| "grad_norm": 0.027999985963106155, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 10.3443, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.005683580655813162, | |
| "grad_norm": 0.026290690526366234, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 10.3429, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.005723605871699171, | |
| "grad_norm": 0.04101789742708206, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 10.3398, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.005763631087585179, | |
| "grad_norm": 0.03343582898378372, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 10.3432, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.0058036563034711865, | |
| "grad_norm": 0.044054221361875534, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 10.3427, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.005843681519357195, | |
| "grad_norm": 0.036968328058719635, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 10.3441, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.005883706735243203, | |
| "grad_norm": 0.0363260917365551, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 10.3426, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.005923731951129212, | |
| "grad_norm": 0.04378674924373627, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 10.3449, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.0059637571670152194, | |
| "grad_norm": 0.03407071530818939, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 10.3442, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.006003782382901228, | |
| "grad_norm": 0.05728279426693916, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 10.3453, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.006003782382901228, | |
| "eval_loss": 10.3402681350708, | |
| "eval_runtime": 0.144, | |
| "eval_samples_per_second": 347.135, | |
| "eval_steps_per_second": 48.599, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.006043807598787236, | |
| "grad_norm": 0.03880951926112175, | |
| "learning_rate": 4.659698863221513e-05, | |
| "loss": 10.3405, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.006083832814673244, | |
| "grad_norm": 0.0317707322537899, | |
| "learning_rate": 4.481448235912671e-05, | |
| "loss": 10.3416, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.006123858030559252, | |
| "grad_norm": 0.033779390156269073, | |
| "learning_rate": 4.306073275629044e-05, | |
| "loss": 10.3395, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.00616388324644526, | |
| "grad_norm": 0.027501322329044342, | |
| "learning_rate": 4.133621928133665e-05, | |
| "loss": 10.3412, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.006203908462331269, | |
| "grad_norm": 0.022303588688373566, | |
| "learning_rate": 3.964141339903026e-05, | |
| "loss": 10.3411, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.006243933678217277, | |
| "grad_norm": 0.026241958141326904, | |
| "learning_rate": 3.797677845237696e-05, | |
| "loss": 10.3406, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.006283958894103285, | |
| "grad_norm": 0.02380531281232834, | |
| "learning_rate": 3.634276953594982e-05, | |
| "loss": 10.3418, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.006323984109989293, | |
| "grad_norm": 0.024870751425623894, | |
| "learning_rate": 3.473983337147118e-05, | |
| "loss": 10.341, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.006364009325875301, | |
| "grad_norm": 0.025397121906280518, | |
| "learning_rate": 3.316840818568315e-05, | |
| "loss": 10.3411, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.00640403454176131, | |
| "grad_norm": 0.02394135482609272, | |
| "learning_rate": 3.162892359054098e-05, | |
| "loss": 10.3409, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0064440597576473175, | |
| "grad_norm": 0.02467886172235012, | |
| "learning_rate": 3.0121800465761293e-05, | |
| "loss": 10.3416, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.006484084973533326, | |
| "grad_norm": 0.02491372637450695, | |
| "learning_rate": 2.8647450843757897e-05, | |
| "loss": 10.3397, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.006524110189419334, | |
| "grad_norm": 0.026415346190333366, | |
| "learning_rate": 2.7206277796996144e-05, | |
| "loss": 10.3395, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.006564135405305343, | |
| "grad_norm": 0.027454102411866188, | |
| "learning_rate": 2.5798675327796993e-05, | |
| "loss": 10.3417, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.0066041606211913505, | |
| "grad_norm": 0.02785174734890461, | |
| "learning_rate": 2.4425028260620715e-05, | |
| "loss": 10.3392, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.006644185837077358, | |
| "grad_norm": 0.03313513472676277, | |
| "learning_rate": 2.3085712136859668e-05, | |
| "loss": 10.3402, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.006684211052963367, | |
| "grad_norm": 0.020563622936606407, | |
| "learning_rate": 2.178109311216913e-05, | |
| "loss": 10.3419, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.006724236268849375, | |
| "grad_norm": 0.030172914266586304, | |
| "learning_rate": 2.0511527856363912e-05, | |
| "loss": 10.3421, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.0067642614847353835, | |
| "grad_norm": 0.025563696399331093, | |
| "learning_rate": 1.927736345590839e-05, | |
| "loss": 10.3392, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.006804286700621391, | |
| "grad_norm": 0.01891487091779709, | |
| "learning_rate": 1.8078937319026654e-05, | |
| "loss": 10.3414, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0068443119165074, | |
| "grad_norm": 0.028518687933683395, | |
| "learning_rate": 1.6916577083458228e-05, | |
| "loss": 10.3406, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.006884337132393408, | |
| "grad_norm": 0.020258715376257896, | |
| "learning_rate": 1.579060052688548e-05, | |
| "loss": 10.3395, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.006924362348279416, | |
| "grad_norm": 0.02436778135597706, | |
| "learning_rate": 1.4701315480056164e-05, | |
| "loss": 10.3414, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.006964387564165424, | |
| "grad_norm": 0.018401464447379112, | |
| "learning_rate": 1.3649019742625623e-05, | |
| "loss": 10.3402, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.007004412780051432, | |
| "grad_norm": 0.027630239725112915, | |
| "learning_rate": 1.2634001001741373e-05, | |
| "loss": 10.341, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.007004412780051432, | |
| "eval_loss": 10.339688301086426, | |
| "eval_runtime": 0.15, | |
| "eval_samples_per_second": 333.266, | |
| "eval_steps_per_second": 46.657, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.007044437995937441, | |
| "grad_norm": 0.02613791450858116, | |
| "learning_rate": 1.1656536753392287e-05, | |
| "loss": 10.3422, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.007084463211823449, | |
| "grad_norm": 0.028299255296587944, | |
| "learning_rate": 1.0716894226543953e-05, | |
| "loss": 10.3424, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.007124488427709457, | |
| "grad_norm": 0.027093924582004547, | |
| "learning_rate": 9.815330310080887e-06, | |
| "loss": 10.3432, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.007164513643595465, | |
| "grad_norm": 0.026260150596499443, | |
| "learning_rate": 8.952091482575824e-06, | |
| "loss": 10.3408, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.007204538859481474, | |
| "grad_norm": 0.024819303303956985, | |
| "learning_rate": 8.127413744904804e-06, | |
| "loss": 10.341, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0072445640753674816, | |
| "grad_norm": 0.02742963470518589, | |
| "learning_rate": 7.34152255572697e-06, | |
| "loss": 10.3404, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.007284589291253489, | |
| "grad_norm": 0.024038875475525856, | |
| "learning_rate": 6.594632769846353e-06, | |
| "loss": 10.3424, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.007324614507139498, | |
| "grad_norm": 0.03462977334856987, | |
| "learning_rate": 5.886948579472778e-06, | |
| "loss": 10.3423, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.007364639723025506, | |
| "grad_norm": 0.0273030623793602, | |
| "learning_rate": 5.218663458397715e-06, | |
| "loss": 10.3419, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.0074046649389115145, | |
| "grad_norm": 0.021748429164290428, | |
| "learning_rate": 4.589960109100444e-06, | |
| "loss": 10.3398, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.007444690154797522, | |
| "grad_norm": 0.022143211215734482, | |
| "learning_rate": 4.001010412799138e-06, | |
| "loss": 10.3427, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.007484715370683531, | |
| "grad_norm": 0.028321022167801857, | |
| "learning_rate": 3.451975382460109e-06, | |
| "loss": 10.3435, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.007524740586569539, | |
| "grad_norm": 0.02573862113058567, | |
| "learning_rate": 2.9430051187785962e-06, | |
| "loss": 10.3411, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.007564765802455547, | |
| "grad_norm": 0.027865024283528328, | |
| "learning_rate": 2.4742387691426445e-06, | |
| "loss": 10.3441, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.007604791018341555, | |
| "grad_norm": 0.024411842226982117, | |
| "learning_rate": 2.0458044895916513e-06, | |
| "loss": 10.3414, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.007644816234227563, | |
| "grad_norm": 0.026974577456712723, | |
| "learning_rate": 1.6578194097797258e-06, | |
| "loss": 10.3414, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.007684841450113572, | |
| "grad_norm": 0.02850463055074215, | |
| "learning_rate": 1.3103896009537207e-06, | |
| "loss": 10.343, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.00772486666599958, | |
| "grad_norm": 0.034683018922805786, | |
| "learning_rate": 1.0036100469542786e-06, | |
| "loss": 10.3408, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.007764891881885588, | |
| "grad_norm": 0.03067103587090969, | |
| "learning_rate": 7.375646182482875e-07, | |
| "loss": 10.3422, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.007804917097771596, | |
| "grad_norm": 0.039638079702854156, | |
| "learning_rate": 5.123260489995229e-07, | |
| "loss": 10.3411, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.007844942313657604, | |
| "grad_norm": 0.03353327140212059, | |
| "learning_rate": 3.2795591718381975e-07, | |
| "loss": 10.3424, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.007884967529543612, | |
| "grad_norm": 0.040784239768981934, | |
| "learning_rate": 1.8450462775428942e-07, | |
| "loss": 10.3434, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.007924992745429621, | |
| "grad_norm": 0.03665102273225784, | |
| "learning_rate": 8.201139886109264e-08, | |
| "loss": 10.343, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.007965017961315629, | |
| "grad_norm": 0.04679227992892265, | |
| "learning_rate": 2.0504251129649374e-08, | |
| "loss": 10.3428, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.008005043177201637, | |
| "grad_norm": 0.052072253078222275, | |
| "learning_rate": 0.0, | |
| "loss": 10.3442, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.008005043177201637, | |
| "eval_loss": 10.339714050292969, | |
| "eval_runtime": 0.1466, | |
| "eval_samples_per_second": 340.956, | |
| "eval_steps_per_second": 47.734, | |
| "step": 200 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 22423039524864.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |