| { | |
| "best_metric": 1.556872844696045, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.023405500292568753, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000156036668617125, | |
| "grad_norm": 0.6086230874061584, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.8397, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000156036668617125, | |
| "eval_loss": 2.050737142562866, | |
| "eval_runtime": 4.681, | |
| "eval_samples_per_second": 10.682, | |
| "eval_steps_per_second": 1.495, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00031207333723425, | |
| "grad_norm": 0.8839565515518188, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.9253, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004681100058513751, | |
| "grad_norm": 0.5914949178695679, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 1.7086, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006241466744685, | |
| "grad_norm": 0.6697356104850769, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.676, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007801833430856252, | |
| "grad_norm": 0.7815700173377991, | |
| "learning_rate": 0.00015, | |
| "loss": 1.7765, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009362200117027502, | |
| "grad_norm": 0.8394500613212585, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.7859, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001092256680319875, | |
| "grad_norm": 0.6029866337776184, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 1.6454, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001248293348937, | |
| "grad_norm": 0.5297218561172485, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.7182, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014043300175541251, | |
| "grad_norm": 0.8180967569351196, | |
| "learning_rate": 0.00027, | |
| "loss": 1.8304, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015603666861712503, | |
| "grad_norm": 0.9878036379814148, | |
| "learning_rate": 0.0003, | |
| "loss": 1.7367, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017164033547883754, | |
| "grad_norm": 0.5219380855560303, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 1.878, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0018724400234055004, | |
| "grad_norm": 0.5020744800567627, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 1.8158, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0020284766920226254, | |
| "grad_norm": 0.5324579477310181, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 1.562, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00218451336063975, | |
| "grad_norm": 0.849560558795929, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 1.6667, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0023405500292568754, | |
| "grad_norm": 0.5848795771598816, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 1.6083, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002496586697874, | |
| "grad_norm": 0.6541223526000977, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 1.6179, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0026526233664911254, | |
| "grad_norm": 0.6580960154533386, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 1.4159, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0028086600351082502, | |
| "grad_norm": 0.5440740585327148, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 1.5937, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0029646967037253755, | |
| "grad_norm": 0.6181334257125854, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 1.5747, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0031207333723425007, | |
| "grad_norm": 0.7562193870544434, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 1.4357, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0032767700409596255, | |
| "grad_norm": 0.9943856000900269, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 1.5356, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0034328067095767507, | |
| "grad_norm": 0.7195516228675842, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 1.3726, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0035888433781938755, | |
| "grad_norm": 0.9126946330070496, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 1.3734, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0037448800468110007, | |
| "grad_norm": 0.6467637419700623, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 1.3602, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0039009167154281255, | |
| "grad_norm": 0.5799360275268555, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 1.2958, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0039009167154281255, | |
| "eval_loss": 1.5699554681777954, | |
| "eval_runtime": 4.237, | |
| "eval_samples_per_second": 11.801, | |
| "eval_steps_per_second": 1.652, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004056953384045251, | |
| "grad_norm": 0.6595892310142517, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 1.3138, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004212990052662376, | |
| "grad_norm": 0.6430525779724121, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 1.3484, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0043690267212795, | |
| "grad_norm": 0.6260256171226501, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 1.4841, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004525063389896626, | |
| "grad_norm": 0.644149899482727, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 1.3044, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.004681100058513751, | |
| "grad_norm": 0.5812307596206665, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 1.2462, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004837136727130876, | |
| "grad_norm": 0.5822577476501465, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 1.333, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.004993173395748, | |
| "grad_norm": 0.7623059749603271, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 1.269, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005149210064365126, | |
| "grad_norm": 0.6771302223205566, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 1.4905, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005305246732982251, | |
| "grad_norm": 0.7112970948219299, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 1.3871, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.005461283401599376, | |
| "grad_norm": 0.7185697555541992, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 1.2095, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0056173200702165004, | |
| "grad_norm": 0.8005110025405884, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 1.3555, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005773356738833626, | |
| "grad_norm": 0.8502066135406494, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 1.3121, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.005929393407450751, | |
| "grad_norm": 0.8016048073768616, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 1.058, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006085430076067876, | |
| "grad_norm": 0.8298421502113342, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 1.1519, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006241466744685001, | |
| "grad_norm": 0.9262282848358154, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 1.2059, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006397503413302126, | |
| "grad_norm": 0.9439979195594788, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 1.0447, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.006553540081919251, | |
| "grad_norm": 1.0094624757766724, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.9239, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006709576750536376, | |
| "grad_norm": 0.9697788953781128, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.8678, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.006865613419153501, | |
| "grad_norm": 1.063493251800537, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.7462, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007021650087770626, | |
| "grad_norm": 0.9183794856071472, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.9486, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007177686756387751, | |
| "grad_norm": 1.2309966087341309, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.9477, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.007333723425004876, | |
| "grad_norm": 1.1949628591537476, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.9138, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0074897600936220015, | |
| "grad_norm": 1.3658891916275024, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.8504, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.007645796762239126, | |
| "grad_norm": 1.4715008735656738, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.7391, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.007801833430856251, | |
| "grad_norm": 2.4105653762817383, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.5911, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007801833430856251, | |
| "eval_loss": 1.770018458366394, | |
| "eval_runtime": 4.2306, | |
| "eval_samples_per_second": 11.819, | |
| "eval_steps_per_second": 1.655, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007957870099473376, | |
| "grad_norm": 1.0819034576416016, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 1.9653, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.008113906768090502, | |
| "grad_norm": 0.7710573673248291, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 1.8359, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.008269943436707627, | |
| "grad_norm": 0.48816221952438354, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 1.8161, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.008425980105324752, | |
| "grad_norm": 0.396649569272995, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 1.6526, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.008582016773941877, | |
| "grad_norm": 0.4052954912185669, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 1.6535, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.008738053442559, | |
| "grad_norm": 0.3467097282409668, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 1.6361, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.008894090111176126, | |
| "grad_norm": 0.43388938903808594, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 1.587, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.009050126779793251, | |
| "grad_norm": 0.40722790360450745, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 1.768, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.009206163448410376, | |
| "grad_norm": 0.4063577950000763, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 1.7566, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.009362200117027502, | |
| "grad_norm": 0.43215540051460266, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 1.5319, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.009518236785644627, | |
| "grad_norm": 0.43602800369262695, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 1.6151, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.009674273454261752, | |
| "grad_norm": 0.5021372437477112, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 1.5425, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.009830310122878877, | |
| "grad_norm": 0.5338031649589539, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 1.359, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.009986346791496, | |
| "grad_norm": 0.48262616991996765, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 1.5978, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.010142383460113126, | |
| "grad_norm": 0.46118801832199097, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 1.6026, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.010298420128730251, | |
| "grad_norm": 0.5712929964065552, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 1.4651, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.010454456797347376, | |
| "grad_norm": 0.5087805986404419, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 1.4682, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.010610493465964502, | |
| "grad_norm": 0.4359475374221802, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 1.4087, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.010766530134581627, | |
| "grad_norm": 0.5143886804580688, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 1.4626, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.010922566803198752, | |
| "grad_norm": 0.5556894540786743, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 1.3555, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.011078603471815877, | |
| "grad_norm": 0.5038280487060547, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 1.3505, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.011234640140433001, | |
| "grad_norm": 0.5278029441833496, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 1.3662, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.011390676809050126, | |
| "grad_norm": 0.4867488145828247, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 1.372, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.011546713477667251, | |
| "grad_norm": 0.5492080450057983, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 1.5234, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.011702750146284377, | |
| "grad_norm": 0.5313156247138977, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 1.4519, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.011702750146284377, | |
| "eval_loss": 1.5630431175231934, | |
| "eval_runtime": 4.2373, | |
| "eval_samples_per_second": 11.8, | |
| "eval_steps_per_second": 1.652, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.011858786814901502, | |
| "grad_norm": 0.5244495272636414, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 1.1777, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.012014823483518627, | |
| "grad_norm": 0.5840427279472351, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 1.3972, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.012170860152135752, | |
| "grad_norm": 0.6866291761398315, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 1.2804, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.012326896820752878, | |
| "grad_norm": 0.6470672488212585, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 1.1939, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.012482933489370003, | |
| "grad_norm": 0.605287492275238, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 1.2211, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.012638970157987126, | |
| "grad_norm": 0.6617386341094971, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 1.3554, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.012795006826604251, | |
| "grad_norm": 0.7803332805633545, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 1.4042, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.012951043495221377, | |
| "grad_norm": 0.7971398830413818, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 1.3547, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.013107080163838502, | |
| "grad_norm": 0.7347298264503479, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 1.2184, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.013263116832455627, | |
| "grad_norm": 0.7346494793891907, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 1.3167, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.013419153501072752, | |
| "grad_norm": 0.7652532458305359, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 1.2579, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.013575190169689878, | |
| "grad_norm": 0.7349557876586914, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 1.32, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.013731226838307003, | |
| "grad_norm": 0.7894690036773682, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 1.3112, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.013887263506924126, | |
| "grad_norm": 0.7287887334823608, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 0.9867, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.014043300175541252, | |
| "grad_norm": 0.8633901476860046, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 0.9666, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.014199336844158377, | |
| "grad_norm": 0.9012820720672607, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 1.3182, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.014355373512775502, | |
| "grad_norm": 0.8617823719978333, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 0.9379, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.014511410181392627, | |
| "grad_norm": 0.9759750962257385, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 0.7805, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.014667446850009752, | |
| "grad_norm": 0.9067065119743347, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 0.8336, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.014823483518626878, | |
| "grad_norm": 0.9368504881858826, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 0.6109, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.014979520187244003, | |
| "grad_norm": 1.0724397897720337, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 0.6566, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.015135556855861128, | |
| "grad_norm": 1.2549207210540771, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 0.6063, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.015291593524478252, | |
| "grad_norm": 1.4020940065383911, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 0.694, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.015447630193095377, | |
| "grad_norm": 1.450042724609375, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 0.7677, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.015603666861712502, | |
| "grad_norm": 1.282713532447815, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 0.3616, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.015603666861712502, | |
| "eval_loss": 1.7407159805297852, | |
| "eval_runtime": 4.2307, | |
| "eval_samples_per_second": 11.818, | |
| "eval_steps_per_second": 1.655, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.015759703530329627, | |
| "grad_norm": 1.586954951286316, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 1.7972, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.015915740198946753, | |
| "grad_norm": 1.2741862535476685, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 1.9201, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.016071776867563878, | |
| "grad_norm": 0.6053886413574219, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 1.7792, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.016227813536181003, | |
| "grad_norm": 0.41298413276672363, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 1.6967, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.016383850204798128, | |
| "grad_norm": 0.40215033292770386, | |
| "learning_rate": 0.00015, | |
| "loss": 1.5317, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.016539886873415253, | |
| "grad_norm": 0.37002134323120117, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 1.3801, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.01669592354203238, | |
| "grad_norm": 0.3345126509666443, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 1.6087, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.016851960210649504, | |
| "grad_norm": 0.3286733031272888, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 1.6558, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.01700799687926663, | |
| "grad_norm": 0.33727169036865234, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 1.5913, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.017164033547883754, | |
| "grad_norm": 0.36604514718055725, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 1.7023, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.017320070216500876, | |
| "grad_norm": 0.37442222237586975, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 1.5861, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.017476106885118, | |
| "grad_norm": 0.3668552339076996, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 1.5585, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.017632143553735127, | |
| "grad_norm": 0.4178268313407898, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 1.5074, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.017788180222352252, | |
| "grad_norm": 0.4216821491718292, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 1.5226, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.017944216890969377, | |
| "grad_norm": 0.4330349564552307, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 1.5936, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.018100253559586502, | |
| "grad_norm": 0.40683087706565857, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 1.4997, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.018256290228203628, | |
| "grad_norm": 0.4639085531234741, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 1.621, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.018412326896820753, | |
| "grad_norm": 0.4048534333705902, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 1.4418, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.018568363565437878, | |
| "grad_norm": 0.5087499022483826, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 1.4201, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.018724400234055003, | |
| "grad_norm": 0.4334667921066284, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 1.4683, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.01888043690267213, | |
| "grad_norm": 0.5327019691467285, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 1.4945, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.019036473571289254, | |
| "grad_norm": 0.47470083832740784, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 1.3291, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.01919251023990638, | |
| "grad_norm": 0.6149418354034424, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 1.2161, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.019348546908523504, | |
| "grad_norm": 0.5498756766319275, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 1.3206, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.01950458357714063, | |
| "grad_norm": 0.47626209259033203, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 1.3595, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.01950458357714063, | |
| "eval_loss": 1.5063681602478027, | |
| "eval_runtime": 4.2353, | |
| "eval_samples_per_second": 11.806, | |
| "eval_steps_per_second": 1.653, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.019660620245757755, | |
| "grad_norm": 0.7411504983901978, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 1.2422, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.019816656914374876, | |
| "grad_norm": 0.553561806678772, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 1.3354, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.019972693582992, | |
| "grad_norm": 0.5869704484939575, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 1.3886, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.020128730251609127, | |
| "grad_norm": 0.5671099424362183, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 1.202, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.020284766920226252, | |
| "grad_norm": 0.5848771929740906, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 1.3358, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.020440803588843377, | |
| "grad_norm": 0.5958598852157593, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 1.2995, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.020596840257460503, | |
| "grad_norm": 0.5293942093849182, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 1.2137, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.020752876926077628, | |
| "grad_norm": 0.6163585186004639, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 1.3201, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.020908913594694753, | |
| "grad_norm": 0.6630733013153076, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 1.3034, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.021064950263311878, | |
| "grad_norm": 0.6297780871391296, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 1.3303, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.021220986931929003, | |
| "grad_norm": 0.729103147983551, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 1.2309, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.02137702360054613, | |
| "grad_norm": 0.7240315675735474, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 1.3329, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.021533060269163254, | |
| "grad_norm": 0.6736621260643005, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 1.2543, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.02168909693778038, | |
| "grad_norm": 0.7319989204406738, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 1.0579, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.021845133606397504, | |
| "grad_norm": 0.7406724691390991, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 1.0662, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.02200117027501463, | |
| "grad_norm": 0.7126467227935791, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 0.9226, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.022157206943631755, | |
| "grad_norm": 0.7633868455886841, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 0.9552, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.02231324361224888, | |
| "grad_norm": 0.7974080443382263, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.9406, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.022469280280866002, | |
| "grad_norm": 0.9059422612190247, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 0.7214, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.022625316949483127, | |
| "grad_norm": 0.7691546082496643, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 0.7137, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.022781353618100252, | |
| "grad_norm": 0.9734190106391907, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 0.616, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.022937390286717377, | |
| "grad_norm": 0.9143376350402832, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 0.7956, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.023093426955334503, | |
| "grad_norm": 1.1513112783432007, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 0.5356, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.023249463623951628, | |
| "grad_norm": 1.3281687498092651, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 0.7548, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.023405500292568753, | |
| "grad_norm": 1.3413094282150269, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 0.4853, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.023405500292568753, | |
| "eval_loss": 1.556872844696045, | |
| "eval_runtime": 4.2279, | |
| "eval_samples_per_second": 11.826, | |
| "eval_steps_per_second": 1.656, | |
| "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": 2.364765716348928e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |