| { | |
| "best_metric": 1.1042157411575317, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 1.0023640661938533, | |
| "eval_steps": 50, | |
| "global_step": 212, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004728132387706856, | |
| "grad_norm": 0.9486807584762573, | |
| "learning_rate": 1e-05, | |
| "loss": 1.8408, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004728132387706856, | |
| "eval_loss": 1.963819146156311, | |
| "eval_runtime": 38.0049, | |
| "eval_samples_per_second": 9.394, | |
| "eval_steps_per_second": 2.368, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009456264775413711, | |
| "grad_norm": 0.9640880227088928, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8428, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014184397163120567, | |
| "grad_norm": 0.9609369039535522, | |
| "learning_rate": 3e-05, | |
| "loss": 1.9502, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.018912529550827423, | |
| "grad_norm": 0.9109072685241699, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9277, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02364066193853428, | |
| "grad_norm": 0.9222002625465393, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8179, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.028368794326241134, | |
| "grad_norm": 0.7830185890197754, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7072, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03309692671394799, | |
| "grad_norm": 0.6503215432167053, | |
| "learning_rate": 7e-05, | |
| "loss": 1.6178, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.037825059101654845, | |
| "grad_norm": 0.5257905125617981, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5769, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0425531914893617, | |
| "grad_norm": 0.5728737711906433, | |
| "learning_rate": 9e-05, | |
| "loss": 1.5687, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04728132387706856, | |
| "grad_norm": 0.7015601396560669, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6133, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05200945626477541, | |
| "grad_norm": 0.797338604927063, | |
| "learning_rate": 9.999395316300748e-05, | |
| "loss": 1.5002, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05673758865248227, | |
| "grad_norm": 0.6119827628135681, | |
| "learning_rate": 9.997581411459941e-05, | |
| "loss": 1.5473, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.061465721040189124, | |
| "grad_norm": 0.49313884973526, | |
| "learning_rate": 9.994558724213054e-05, | |
| "loss": 1.4589, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06619385342789598, | |
| "grad_norm": 0.4498696029186249, | |
| "learning_rate": 9.990327985667972e-05, | |
| "loss": 1.4562, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07092198581560284, | |
| "grad_norm": 0.38253799080848694, | |
| "learning_rate": 9.984890219128146e-05, | |
| "loss": 1.3475, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07565011820330969, | |
| "grad_norm": 0.40526261925697327, | |
| "learning_rate": 9.978246739845094e-05, | |
| "loss": 1.3564, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08037825059101655, | |
| "grad_norm": 0.4410207271575928, | |
| "learning_rate": 9.970399154700263e-05, | |
| "loss": 1.3799, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 0.4076521098613739, | |
| "learning_rate": 9.961349361816384e-05, | |
| "loss": 1.4092, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08983451536643026, | |
| "grad_norm": 0.4196551442146301, | |
| "learning_rate": 9.951099550098349e-05, | |
| "loss": 1.3264, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09456264775413711, | |
| "grad_norm": 0.3697325885295868, | |
| "learning_rate": 9.939652198703784e-05, | |
| "loss": 1.3886, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09929078014184398, | |
| "grad_norm": 0.346131294965744, | |
| "learning_rate": 9.927010076443407e-05, | |
| "loss": 1.2821, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10401891252955082, | |
| "grad_norm": 0.3620453476905823, | |
| "learning_rate": 9.913176241111319e-05, | |
| "loss": 1.3636, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10874704491725769, | |
| "grad_norm": 0.37463706731796265, | |
| "learning_rate": 9.898154038745408e-05, | |
| "loss": 1.275, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11347517730496454, | |
| "grad_norm": 0.3912721574306488, | |
| "learning_rate": 9.881947102818036e-05, | |
| "loss": 1.2499, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1182033096926714, | |
| "grad_norm": 0.3786635100841522, | |
| "learning_rate": 9.864559353357187e-05, | |
| "loss": 1.3173, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12293144208037825, | |
| "grad_norm": 0.3728365898132324, | |
| "learning_rate": 9.845994995998332e-05, | |
| "loss": 1.2287, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1276595744680851, | |
| "grad_norm": 0.40303531289100647, | |
| "learning_rate": 9.826258520967178e-05, | |
| "loss": 1.2327, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.13238770685579196, | |
| "grad_norm": 0.3770873546600342, | |
| "learning_rate": 9.805354701993623e-05, | |
| "loss": 1.2309, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13711583924349882, | |
| "grad_norm": 0.41253548860549927, | |
| "learning_rate": 9.783288595157098e-05, | |
| "loss": 1.3503, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.14184397163120568, | |
| "grad_norm": 0.3858996033668518, | |
| "learning_rate": 9.760065537663649e-05, | |
| "loss": 1.2443, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14657210401891252, | |
| "grad_norm": 0.40391531586647034, | |
| "learning_rate": 9.735691146555002e-05, | |
| "loss": 1.1587, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.15130023640661938, | |
| "grad_norm": 0.40914273262023926, | |
| "learning_rate": 9.710171317349945e-05, | |
| "loss": 1.2247, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.15602836879432624, | |
| "grad_norm": 0.41252586245536804, | |
| "learning_rate": 9.683512222618377e-05, | |
| "loss": 1.1826, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1607565011820331, | |
| "grad_norm": 0.42859312891960144, | |
| "learning_rate": 9.655720310488299e-05, | |
| "loss": 1.1764, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.16548463356973994, | |
| "grad_norm": 0.4406868815422058, | |
| "learning_rate": 9.626802303086208e-05, | |
| "loss": 1.1773, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": 0.46166718006134033, | |
| "learning_rate": 9.596765194911181e-05, | |
| "loss": 1.3088, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.17494089834515367, | |
| "grad_norm": 0.4437083303928375, | |
| "learning_rate": 9.565616251143094e-05, | |
| "loss": 1.2081, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.17966903073286053, | |
| "grad_norm": 0.41885045170783997, | |
| "learning_rate": 9.533363005885363e-05, | |
| "loss": 1.2329, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.18439716312056736, | |
| "grad_norm": 0.40488675236701965, | |
| "learning_rate": 9.500013260342651e-05, | |
| "loss": 1.1143, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.18912529550827423, | |
| "grad_norm": 0.4128928780555725, | |
| "learning_rate": 9.465575080933958e-05, | |
| "loss": 1.1915, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1938534278959811, | |
| "grad_norm": 0.4129532277584076, | |
| "learning_rate": 9.430056797341574e-05, | |
| "loss": 1.1523, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.19858156028368795, | |
| "grad_norm": 0.4176290035247803, | |
| "learning_rate": 9.393467000496344e-05, | |
| "loss": 1.1828, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2033096926713948, | |
| "grad_norm": 0.40814054012298584, | |
| "learning_rate": 9.355814540499752e-05, | |
| "loss": 1.1198, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.20803782505910165, | |
| "grad_norm": 0.44160643219947815, | |
| "learning_rate": 9.317108524483318e-05, | |
| "loss": 1.1523, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2127659574468085, | |
| "grad_norm": 0.449492484331131, | |
| "learning_rate": 9.27735831440582e-05, | |
| "loss": 1.1841, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.21749408983451538, | |
| "grad_norm": 0.4739810526371002, | |
| "learning_rate": 9.236573524788887e-05, | |
| "loss": 1.2485, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.4747321605682373, | |
| "learning_rate": 9.194764020391506e-05, | |
| "loss": 1.1819, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.22695035460992907, | |
| "grad_norm": 0.5036101937294006, | |
| "learning_rate": 9.151939913823988e-05, | |
| "loss": 1.2246, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.23167848699763594, | |
| "grad_norm": 0.4752824008464813, | |
| "learning_rate": 9.108111563102004e-05, | |
| "loss": 1.1525, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2364066193853428, | |
| "grad_norm": 0.6015028953552246, | |
| "learning_rate": 9.063289569141251e-05, | |
| "loss": 1.202, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2364066193853428, | |
| "eval_loss": 1.201499104499817, | |
| "eval_runtime": 38.7229, | |
| "eval_samples_per_second": 9.219, | |
| "eval_steps_per_second": 2.324, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24113475177304963, | |
| "grad_norm": 0.5079233646392822, | |
| "learning_rate": 9.017484773193378e-05, | |
| "loss": 1.2754, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.2458628841607565, | |
| "grad_norm": 0.43763864040374756, | |
| "learning_rate": 8.970708254223768e-05, | |
| "loss": 1.266, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.25059101654846333, | |
| "grad_norm": 0.42711228132247925, | |
| "learning_rate": 8.92297132623183e-05, | |
| "loss": 1.3319, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.2553191489361702, | |
| "grad_norm": 0.3751334547996521, | |
| "learning_rate": 8.87428553551445e-05, | |
| "loss": 1.2406, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.26004728132387706, | |
| "grad_norm": 0.36792027950286865, | |
| "learning_rate": 8.824662657873239e-05, | |
| "loss": 1.2687, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2647754137115839, | |
| "grad_norm": 0.36172714829444885, | |
| "learning_rate": 8.774114695766286e-05, | |
| "loss": 1.1624, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.2695035460992908, | |
| "grad_norm": 0.3969741761684418, | |
| "learning_rate": 8.722653875405075e-05, | |
| "loss": 1.1844, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.27423167848699764, | |
| "grad_norm": 0.3591637909412384, | |
| "learning_rate": 8.670292643797302e-05, | |
| "loss": 1.2324, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.2789598108747045, | |
| "grad_norm": 0.3697453439235687, | |
| "learning_rate": 8.617043665736249e-05, | |
| "loss": 1.2002, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.28368794326241137, | |
| "grad_norm": 0.36921319365501404, | |
| "learning_rate": 8.562919820737536e-05, | |
| "loss": 1.2023, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.28841607565011823, | |
| "grad_norm": 0.37672919034957886, | |
| "learning_rate": 8.507934199923884e-05, | |
| "loss": 1.2226, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.29314420803782504, | |
| "grad_norm": 0.38116613030433655, | |
| "learning_rate": 8.452100102858734e-05, | |
| "loss": 1.2582, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2978723404255319, | |
| "grad_norm": 0.3604193329811096, | |
| "learning_rate": 8.39543103432943e-05, | |
| "loss": 1.1556, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.30260047281323876, | |
| "grad_norm": 0.3755967915058136, | |
| "learning_rate": 8.337940701080768e-05, | |
| "loss": 1.1337, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.3073286052009456, | |
| "grad_norm": 0.3861168622970581, | |
| "learning_rate": 8.2796430084997e-05, | |
| "loss": 1.2263, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3120567375886525, | |
| "grad_norm": 0.3755252957344055, | |
| "learning_rate": 8.22055205725199e-05, | |
| "loss": 1.238, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.31678486997635935, | |
| "grad_norm": 0.3644655644893646, | |
| "learning_rate": 8.160682139871633e-05, | |
| "loss": 1.1605, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.3215130023640662, | |
| "grad_norm": 0.3366273045539856, | |
| "learning_rate": 8.100047737303877e-05, | |
| "loss": 1.1462, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.3262411347517731, | |
| "grad_norm": 0.3894293010234833, | |
| "learning_rate": 8.03866351540266e-05, | |
| "loss": 1.2754, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.3309692671394799, | |
| "grad_norm": 0.34858208894729614, | |
| "learning_rate": 7.97654432138333e-05, | |
| "loss": 1.1449, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.33569739952718675, | |
| "grad_norm": 0.3382340669631958, | |
| "learning_rate": 7.913705180231505e-05, | |
| "loss": 1.2337, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 0.33755427598953247, | |
| "learning_rate": 7.850161291068913e-05, | |
| "loss": 1.1643, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.34515366430260047, | |
| "grad_norm": 0.36655935645103455, | |
| "learning_rate": 7.785928023477142e-05, | |
| "loss": 1.1103, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.34988179669030733, | |
| "grad_norm": 0.3621681034564972, | |
| "learning_rate": 7.721020913780137e-05, | |
| "loss": 1.1146, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.3546099290780142, | |
| "grad_norm": 0.3632483184337616, | |
| "learning_rate": 7.655455661286376e-05, | |
| "loss": 1.162, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.35933806146572106, | |
| "grad_norm": 0.39180269837379456, | |
| "learning_rate": 7.589248124491627e-05, | |
| "loss": 1.2159, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3640661938534279, | |
| "grad_norm": 0.3684546649456024, | |
| "learning_rate": 7.5224143172432e-05, | |
| "loss": 1.1239, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.36879432624113473, | |
| "grad_norm": 0.39688640832901, | |
| "learning_rate": 7.454970404866611e-05, | |
| "loss": 1.1401, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.3735224586288416, | |
| "grad_norm": 0.3946040868759155, | |
| "learning_rate": 7.386932700255636e-05, | |
| "loss": 1.1358, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.37825059101654845, | |
| "grad_norm": 0.43118810653686523, | |
| "learning_rate": 7.318317659926637e-05, | |
| "loss": 1.0864, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3829787234042553, | |
| "grad_norm": 0.37678292393684387, | |
| "learning_rate": 7.24914188003818e-05, | |
| "loss": 1.0901, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.3877068557919622, | |
| "grad_norm": 0.41417282819747925, | |
| "learning_rate": 7.179422092376856e-05, | |
| "loss": 1.1902, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.39243498817966904, | |
| "grad_norm": 0.395439475774765, | |
| "learning_rate": 7.109175160310312e-05, | |
| "loss": 1.1476, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.3971631205673759, | |
| "grad_norm": 0.36730679869651794, | |
| "learning_rate": 7.038418074708444e-05, | |
| "loss": 1.1107, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.40189125295508277, | |
| "grad_norm": 0.37374141812324524, | |
| "learning_rate": 6.967167949833763e-05, | |
| "loss": 1.1142, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.4066193853427896, | |
| "grad_norm": 0.3955516815185547, | |
| "learning_rate": 6.895442019201897e-05, | |
| "loss": 1.0354, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.41134751773049644, | |
| "grad_norm": 0.4088446795940399, | |
| "learning_rate": 6.823257631413276e-05, | |
| "loss": 1.1146, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.4160756501182033, | |
| "grad_norm": 0.40435466170310974, | |
| "learning_rate": 6.750632245956953e-05, | |
| "loss": 1.1411, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.42080378250591016, | |
| "grad_norm": 0.38119205832481384, | |
| "learning_rate": 6.677583428987625e-05, | |
| "loss": 1.0443, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 0.39904236793518066, | |
| "learning_rate": 6.604128849076838e-05, | |
| "loss": 1.1301, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4302600472813239, | |
| "grad_norm": 0.39689844846725464, | |
| "learning_rate": 6.530286272939437e-05, | |
| "loss": 1.0686, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.43498817966903075, | |
| "grad_norm": 0.4293765127658844, | |
| "learning_rate": 6.456073561136261e-05, | |
| "loss": 1.0763, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.4397163120567376, | |
| "grad_norm": 0.4394353926181793, | |
| "learning_rate": 6.381508663754153e-05, | |
| "loss": 1.1274, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.4373772442340851, | |
| "learning_rate": 6.306609616064304e-05, | |
| "loss": 1.1152, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.4491725768321513, | |
| "grad_norm": 0.4275088906288147, | |
| "learning_rate": 6.231394534160008e-05, | |
| "loss": 1.0739, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.45390070921985815, | |
| "grad_norm": 0.49015218019485474, | |
| "learning_rate": 6.15588161057485e-05, | |
| "loss": 1.1201, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.458628841607565, | |
| "grad_norm": 0.46768057346343994, | |
| "learning_rate": 6.0800891098824186e-05, | |
| "loss": 1.1138, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.46335697399527187, | |
| "grad_norm": 0.47101691365242004, | |
| "learning_rate": 6.004035364278593e-05, | |
| "loss": 1.1192, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.46808510638297873, | |
| "grad_norm": 0.4808042347431183, | |
| "learning_rate": 5.9277387691474676e-05, | |
| "loss": 1.0965, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.4728132387706856, | |
| "grad_norm": 0.7809662222862244, | |
| "learning_rate": 5.851217778611994e-05, | |
| "loss": 1.2548, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4728132387706856, | |
| "eval_loss": 1.1545641422271729, | |
| "eval_runtime": 38.546, | |
| "eval_samples_per_second": 9.262, | |
| "eval_steps_per_second": 2.335, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.47754137115839246, | |
| "grad_norm": 0.6622450351715088, | |
| "learning_rate": 5.774490901070424e-05, | |
| "loss": 1.2761, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.48226950354609927, | |
| "grad_norm": 0.49634912610054016, | |
| "learning_rate": 5.697576694719616e-05, | |
| "loss": 1.2634, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.48699763593380613, | |
| "grad_norm": 0.41559910774230957, | |
| "learning_rate": 5.620493763066297e-05, | |
| "loss": 1.2799, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.491725768321513, | |
| "grad_norm": 0.38408902287483215, | |
| "learning_rate": 5.543260750427373e-05, | |
| "loss": 1.1719, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.49645390070921985, | |
| "grad_norm": 0.3431536555290222, | |
| "learning_rate": 5.465896337420359e-05, | |
| "loss": 1.1056, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.5011820330969267, | |
| "grad_norm": 0.342176228761673, | |
| "learning_rate": 5.3884192364450325e-05, | |
| "loss": 1.2039, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.5059101654846335, | |
| "grad_norm": 0.37251392006874084, | |
| "learning_rate": 5.3108481871574036e-05, | |
| "loss": 1.223, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": 0.3797588646411896, | |
| "learning_rate": 5.233201951937088e-05, | |
| "loss": 1.1501, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.5153664302600472, | |
| "grad_norm": 0.3910278081893921, | |
| "learning_rate": 5.155499311349185e-05, | |
| "loss": 1.2336, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.5200945626477541, | |
| "grad_norm": 0.3525397479534149, | |
| "learning_rate": 5.077759059601755e-05, | |
| "loss": 1.1213, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.524822695035461, | |
| "grad_norm": 0.3806985020637512, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2013, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.5295508274231678, | |
| "grad_norm": 0.38082411885261536, | |
| "learning_rate": 4.9222409403982453e-05, | |
| "loss": 1.1766, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.5342789598108747, | |
| "grad_norm": 0.35277897119522095, | |
| "learning_rate": 4.844500688650816e-05, | |
| "loss": 1.1419, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.5390070921985816, | |
| "grad_norm": 0.3725706934928894, | |
| "learning_rate": 4.7667980480629124e-05, | |
| "loss": 1.1276, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.5437352245862884, | |
| "grad_norm": 0.3541959226131439, | |
| "learning_rate": 4.6891518128425976e-05, | |
| "loss": 1.0653, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5484633569739953, | |
| "grad_norm": 0.371341347694397, | |
| "learning_rate": 4.611580763554969e-05, | |
| "loss": 1.1224, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.5531914893617021, | |
| "grad_norm": 0.38338702917099, | |
| "learning_rate": 4.534103662579642e-05, | |
| "loss": 1.1465, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.557919621749409, | |
| "grad_norm": 0.3807014226913452, | |
| "learning_rate": 4.456739249572627e-05, | |
| "loss": 1.1659, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.5626477541371159, | |
| "grad_norm": 0.38342806696891785, | |
| "learning_rate": 4.3795062369337034e-05, | |
| "loss": 1.1965, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.5673758865248227, | |
| "grad_norm": 0.39216044545173645, | |
| "learning_rate": 4.3024233052803855e-05, | |
| "loss": 1.2172, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5721040189125296, | |
| "grad_norm": 0.383404016494751, | |
| "learning_rate": 4.2255090989295764e-05, | |
| "loss": 1.1739, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.5768321513002365, | |
| "grad_norm": 0.38151639699935913, | |
| "learning_rate": 4.148782221388007e-05, | |
| "loss": 1.0698, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.5815602836879432, | |
| "grad_norm": 0.35033509135246277, | |
| "learning_rate": 4.0722612308525335e-05, | |
| "loss": 1.121, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.5862884160756501, | |
| "grad_norm": 0.36325815320014954, | |
| "learning_rate": 3.9959646357214084e-05, | |
| "loss": 1.0989, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.5910165484633569, | |
| "grad_norm": 0.38052505254745483, | |
| "learning_rate": 3.919910890117584e-05, | |
| "loss": 1.0776, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5957446808510638, | |
| "grad_norm": 0.3674011826515198, | |
| "learning_rate": 3.844118389425153e-05, | |
| "loss": 1.12, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.6004728132387707, | |
| "grad_norm": 0.3708929717540741, | |
| "learning_rate": 3.7686054658399935e-05, | |
| "loss": 1.1564, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.6052009456264775, | |
| "grad_norm": 0.37105265259742737, | |
| "learning_rate": 3.693390383935698e-05, | |
| "loss": 1.1331, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.6099290780141844, | |
| "grad_norm": 0.38267219066619873, | |
| "learning_rate": 3.618491336245849e-05, | |
| "loss": 1.0379, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.6146572104018913, | |
| "grad_norm": 0.3863324522972107, | |
| "learning_rate": 3.5439264388637405e-05, | |
| "loss": 1.1361, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.6193853427895981, | |
| "grad_norm": 0.3742581307888031, | |
| "learning_rate": 3.469713727060564e-05, | |
| "loss": 1.0579, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.624113475177305, | |
| "grad_norm": 0.3845396041870117, | |
| "learning_rate": 3.395871150923163e-05, | |
| "loss": 1.0839, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.6288416075650118, | |
| "grad_norm": 0.4115036129951477, | |
| "learning_rate": 3.3224165710123756e-05, | |
| "loss": 1.1757, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.6335697399527187, | |
| "grad_norm": 0.39382243156433105, | |
| "learning_rate": 3.249367754043047e-05, | |
| "loss": 1.1352, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.6382978723404256, | |
| "grad_norm": 0.39766818284988403, | |
| "learning_rate": 3.176742368586725e-05, | |
| "loss": 1.1353, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.6430260047281324, | |
| "grad_norm": 0.3955276310443878, | |
| "learning_rate": 3.104557980798104e-05, | |
| "loss": 1.1329, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.6477541371158393, | |
| "grad_norm": 0.4006507396697998, | |
| "learning_rate": 3.032832050166239e-05, | |
| "loss": 1.0925, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.6524822695035462, | |
| "grad_norm": 0.37227386236190796, | |
| "learning_rate": 2.9615819252915565e-05, | |
| "loss": 1.0568, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.6572104018912529, | |
| "grad_norm": 0.4012226462364197, | |
| "learning_rate": 2.890824839689689e-05, | |
| "loss": 1.1103, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.6619385342789598, | |
| "grad_norm": 0.398710697889328, | |
| "learning_rate": 2.8205779076231447e-05, | |
| "loss": 1.086, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.38928738236427307, | |
| "learning_rate": 2.750858119961821e-05, | |
| "loss": 1.1066, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.6713947990543735, | |
| "grad_norm": 0.41606059670448303, | |
| "learning_rate": 2.6816823400733625e-05, | |
| "loss": 1.1212, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.6761229314420804, | |
| "grad_norm": 0.4255363345146179, | |
| "learning_rate": 2.613067299744364e-05, | |
| "loss": 1.0511, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 0.422050416469574, | |
| "learning_rate": 2.5450295951333896e-05, | |
| "loss": 1.1598, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.6855791962174941, | |
| "grad_norm": 0.46749165654182434, | |
| "learning_rate": 2.4775856827568016e-05, | |
| "loss": 1.111, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6903073286052009, | |
| "grad_norm": 0.4487079083919525, | |
| "learning_rate": 2.410751875508373e-05, | |
| "loss": 1.0855, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.6950354609929078, | |
| "grad_norm": 0.45914727449417114, | |
| "learning_rate": 2.3445443387136244e-05, | |
| "loss": 1.0781, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.6997635933806147, | |
| "grad_norm": 0.4794670045375824, | |
| "learning_rate": 2.2789790862198628e-05, | |
| "loss": 1.0906, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.7044917257683215, | |
| "grad_norm": 0.49251869320869446, | |
| "learning_rate": 2.2140719765228584e-05, | |
| "loss": 1.1217, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.7092198581560284, | |
| "grad_norm": 0.6213652491569519, | |
| "learning_rate": 2.1498387089310868e-05, | |
| "loss": 1.1458, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7092198581560284, | |
| "eval_loss": 1.1165207624435425, | |
| "eval_runtime": 38.5292, | |
| "eval_samples_per_second": 9.266, | |
| "eval_steps_per_second": 2.336, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7139479905437353, | |
| "grad_norm": 0.479676216840744, | |
| "learning_rate": 2.0862948197684955e-05, | |
| "loss": 1.2254, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.7186761229314421, | |
| "grad_norm": 0.4174903631210327, | |
| "learning_rate": 2.0234556786166715e-05, | |
| "loss": 1.1599, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.723404255319149, | |
| "grad_norm": 0.4270111918449402, | |
| "learning_rate": 1.961336484597343e-05, | |
| "loss": 1.1773, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.7281323877068558, | |
| "grad_norm": 0.4060277044773102, | |
| "learning_rate": 1.899952262696125e-05, | |
| "loss": 1.2089, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.7328605200945626, | |
| "grad_norm": 0.40245646238327026, | |
| "learning_rate": 1.8393178601283683e-05, | |
| "loss": 1.1942, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.7375886524822695, | |
| "grad_norm": 0.3960253894329071, | |
| "learning_rate": 1.7794479427480117e-05, | |
| "loss": 1.2359, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.7423167848699763, | |
| "grad_norm": 0.36273330450057983, | |
| "learning_rate": 1.7203569915003005e-05, | |
| "loss": 1.1725, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.7470449172576832, | |
| "grad_norm": 0.38699132204055786, | |
| "learning_rate": 1.662059298919232e-05, | |
| "loss": 1.2018, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.75177304964539, | |
| "grad_norm": 0.3809574544429779, | |
| "learning_rate": 1.6045689656705716e-05, | |
| "loss": 1.1198, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.7565011820330969, | |
| "grad_norm": 0.37179070711135864, | |
| "learning_rate": 1.5478998971412668e-05, | |
| "loss": 1.1596, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7612293144208038, | |
| "grad_norm": 0.3978999853134155, | |
| "learning_rate": 1.4920658000761174e-05, | |
| "loss": 1.1881, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.7659574468085106, | |
| "grad_norm": 0.37211042642593384, | |
| "learning_rate": 1.4370801792624656e-05, | |
| "loss": 1.1375, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.7706855791962175, | |
| "grad_norm": 0.36233842372894287, | |
| "learning_rate": 1.3829563342637513e-05, | |
| "loss": 1.0862, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.7754137115839244, | |
| "grad_norm": 0.3661029040813446, | |
| "learning_rate": 1.329707356202699e-05, | |
| "loss": 1.0632, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.7801418439716312, | |
| "grad_norm": 0.3897812068462372, | |
| "learning_rate": 1.2773461245949247e-05, | |
| "loss": 1.1953, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.7848699763593381, | |
| "grad_norm": 0.3424377143383026, | |
| "learning_rate": 1.225885304233716e-05, | |
| "loss": 1.0391, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.789598108747045, | |
| "grad_norm": 0.363320916891098, | |
| "learning_rate": 1.1753373421267621e-05, | |
| "loss": 1.0834, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.7943262411347518, | |
| "grad_norm": 0.36856764554977417, | |
| "learning_rate": 1.125714464485551e-05, | |
| "loss": 1.0455, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.7990543735224587, | |
| "grad_norm": 0.36050939559936523, | |
| "learning_rate": 1.0770286737681701e-05, | |
| "loss": 1.0576, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.8037825059101655, | |
| "grad_norm": 0.3826131224632263, | |
| "learning_rate": 1.0292917457762325e-05, | |
| "loss": 1.1386, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.8085106382978723, | |
| "grad_norm": 0.37651652097702026, | |
| "learning_rate": 9.825152268066213e-06, | |
| "loss": 1.118, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.8132387706855791, | |
| "grad_norm": 0.397661030292511, | |
| "learning_rate": 9.367104308587494e-06, | |
| "loss": 1.1479, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.817966903073286, | |
| "grad_norm": 0.37330368161201477, | |
| "learning_rate": 8.91888436897997e-06, | |
| "loss": 1.047, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.8226950354609929, | |
| "grad_norm": 0.3637228012084961, | |
| "learning_rate": 8.480600861760124e-06, | |
| "loss": 1.0695, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.8274231678486997, | |
| "grad_norm": 0.3934190273284912, | |
| "learning_rate": 8.052359796084951e-06, | |
| "loss": 1.0716, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.8321513002364066, | |
| "grad_norm": 0.36225423216819763, | |
| "learning_rate": 7.63426475211113e-06, | |
| "loss": 1.0293, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.8368794326241135, | |
| "grad_norm": 0.3973957598209381, | |
| "learning_rate": 7.226416855941814e-06, | |
| "loss": 1.072, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.8416075650118203, | |
| "grad_norm": 0.42150604724884033, | |
| "learning_rate": 6.828914755166827e-06, | |
| "loss": 1.0884, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.8463356973995272, | |
| "grad_norm": 0.38192811608314514, | |
| "learning_rate": 6.441854595002477e-06, | |
| "loss": 1.0185, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 0.3970332145690918, | |
| "learning_rate": 6.065329995036573e-06, | |
| "loss": 1.0495, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8557919621749409, | |
| "grad_norm": 0.4090059995651245, | |
| "learning_rate": 5.699432026584267e-06, | |
| "loss": 1.0787, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.8605200945626478, | |
| "grad_norm": 0.3918428421020508, | |
| "learning_rate": 5.344249190660428e-06, | |
| "loss": 1.004, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.8652482269503546, | |
| "grad_norm": 0.3922417163848877, | |
| "learning_rate": 4.999867396573499e-06, | |
| "loss": 1.0025, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.8699763593380615, | |
| "grad_norm": 0.40068820118904114, | |
| "learning_rate": 4.666369941146376e-06, | |
| "loss": 1.0989, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.8747044917257684, | |
| "grad_norm": 0.3978284001350403, | |
| "learning_rate": 4.343837488569058e-06, | |
| "loss": 1.0513, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.8794326241134752, | |
| "grad_norm": 0.4173754155635834, | |
| "learning_rate": 4.032348050888179e-06, | |
| "loss": 1.1416, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.8841607565011821, | |
| "grad_norm": 0.4168488085269928, | |
| "learning_rate": 3.731976969137929e-06, | |
| "loss": 1.0955, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.4095589816570282, | |
| "learning_rate": 3.4427968951170288e-06, | |
| "loss": 1.0602, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.8936170212765957, | |
| "grad_norm": 0.4083250164985657, | |
| "learning_rate": 3.1648777738162494e-06, | |
| "loss": 1.0999, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.8983451536643026, | |
| "grad_norm": 0.4310641586780548, | |
| "learning_rate": 2.8982868265005458e-06, | |
| "loss": 1.1334, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.9030732860520094, | |
| "grad_norm": 0.4352046847343445, | |
| "learning_rate": 2.6430885344499946e-06, | |
| "loss": 1.0898, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.9078014184397163, | |
| "grad_norm": 0.45793259143829346, | |
| "learning_rate": 2.399344623363503e-06, | |
| "loss": 1.053, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.9125295508274232, | |
| "grad_norm": 0.4551216959953308, | |
| "learning_rate": 2.1671140484290142e-06, | |
| "loss": 1.1926, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.91725768321513, | |
| "grad_norm": 0.4517664313316345, | |
| "learning_rate": 1.946452980063773e-06, | |
| "loss": 1.0751, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.9219858156028369, | |
| "grad_norm": 0.48062533140182495, | |
| "learning_rate": 1.7374147903282178e-06, | |
| "loss": 1.17, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.9267139479905437, | |
| "grad_norm": 0.4554964005947113, | |
| "learning_rate": 1.5400500400166939e-06, | |
| "loss": 1.129, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.9314420803782506, | |
| "grad_norm": 0.47884511947631836, | |
| "learning_rate": 1.3544064664281265e-06, | |
| "loss": 1.1257, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.9361702127659575, | |
| "grad_norm": 0.48259878158569336, | |
| "learning_rate": 1.18052897181965e-06, | |
| "loss": 1.1116, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.9408983451536643, | |
| "grad_norm": 0.4733264446258545, | |
| "learning_rate": 1.0184596125459135e-06, | |
| "loss": 1.1168, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.9456264775413712, | |
| "grad_norm": 0.6054824590682983, | |
| "learning_rate": 8.682375888868166e-07, | |
| "loss": 1.2112, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9456264775413712, | |
| "eval_loss": 1.1042157411575317, | |
| "eval_runtime": 38.4897, | |
| "eval_samples_per_second": 9.275, | |
| "eval_steps_per_second": 2.338, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.950354609929078, | |
| "grad_norm": 0.3739728331565857, | |
| "learning_rate": 7.29899235565934e-07, | |
| "loss": 1.1624, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.9550827423167849, | |
| "grad_norm": 0.35657617449760437, | |
| "learning_rate": 6.034780129621664e-07, | |
| "loss": 1.0881, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.9598108747044918, | |
| "grad_norm": 0.37702855467796326, | |
| "learning_rate": 4.890044990165321e-07, | |
| "loss": 1.1991, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.9645390070921985, | |
| "grad_norm": 0.3940827250480652, | |
| "learning_rate": 3.8650638183617694e-07, | |
| "loss": 1.1217, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.9692671394799054, | |
| "grad_norm": 0.3676983118057251, | |
| "learning_rate": 2.9600845299737056e-07, | |
| "loss": 1.0818, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.9739952718676123, | |
| "grad_norm": 0.399383008480072, | |
| "learning_rate": 2.1753260154906973e-07, | |
| "loss": 1.0898, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.9787234042553191, | |
| "grad_norm": 0.3540259599685669, | |
| "learning_rate": 1.5109780871853663e-07, | |
| "loss": 1.0337, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.983451536643026, | |
| "grad_norm": 0.3893062174320221, | |
| "learning_rate": 9.672014332028356e-08, | |
| "loss": 0.9161, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.9881796690307328, | |
| "grad_norm": 0.39612168073654175, | |
| "learning_rate": 5.4412757869459763e-08, | |
| "loss": 1.0683, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.9929078014184397, | |
| "grad_norm": 0.443149209022522, | |
| "learning_rate": 2.4185885400596075e-08, | |
| "loss": 1.0856, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9976359338061466, | |
| "grad_norm": 0.46631062030792236, | |
| "learning_rate": 6.04683699252373e-09, | |
| "loss": 1.101, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.0023640661938533, | |
| "grad_norm": 0.9580826759338379, | |
| "learning_rate": 0.0, | |
| "loss": 1.865, | |
| "step": 212 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 212, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 2.8356191188942848e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |