| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 8.957854406130268, | |
| "eval_steps": 17, | |
| "global_step": 585, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01532567049808429, | |
| "grad_norm": 3.475003242492676, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9507, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01532567049808429, | |
| "eval_loss": 1.9943002462387085, | |
| "eval_runtime": 10.4694, | |
| "eval_samples_per_second": 9.552, | |
| "eval_steps_per_second": 4.776, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03065134099616858, | |
| "grad_norm": 3.6678824424743652, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0639, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04597701149425287, | |
| "grad_norm": 3.1201210021972656, | |
| "learning_rate": 6e-05, | |
| "loss": 1.8136, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06130268199233716, | |
| "grad_norm": 3.606743574142456, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9302, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07662835249042145, | |
| "grad_norm": 3.096000909805298, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9869, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09195402298850575, | |
| "grad_norm": 2.841855049133301, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7556, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10727969348659004, | |
| "grad_norm": 2.7530441284179688, | |
| "learning_rate": 0.00014, | |
| "loss": 1.8622, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12260536398467432, | |
| "grad_norm": 2.9382359981536865, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7264, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 2.9906227588653564, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8225, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1532567049808429, | |
| "grad_norm": 2.951603889465332, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8434, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1685823754789272, | |
| "grad_norm": 2.783867120742798, | |
| "learning_rate": 0.00019999916768504724, | |
| "loss": 1.6941, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1839080459770115, | |
| "grad_norm": 2.7186167240142822, | |
| "learning_rate": 0.00019999667075404383, | |
| "loss": 1.8163, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.19923371647509577, | |
| "grad_norm": 2.33475661277771, | |
| "learning_rate": 0.00019999250924855456, | |
| "loss": 1.6088, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.21455938697318008, | |
| "grad_norm": 2.289853811264038, | |
| "learning_rate": 0.00019998668323785296, | |
| "loss": 1.6944, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.22988505747126436, | |
| "grad_norm": 2.4338462352752686, | |
| "learning_rate": 0.00019997919281892067, | |
| "loss": 1.7205, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.24521072796934865, | |
| "grad_norm": 2.6904211044311523, | |
| "learning_rate": 0.00019997003811644533, | |
| "loss": 1.8309, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.26053639846743293, | |
| "grad_norm": 2.0868079662323, | |
| "learning_rate": 0.00019995921928281894, | |
| "loss": 1.714, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.26053639846743293, | |
| "eval_loss": 1.71925687789917, | |
| "eval_runtime": 10.4582, | |
| "eval_samples_per_second": 9.562, | |
| "eval_steps_per_second": 4.781, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 2.312363862991333, | |
| "learning_rate": 0.00019994673649813497, | |
| "loss": 1.7437, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.29118773946360155, | |
| "grad_norm": 2.1838905811309814, | |
| "learning_rate": 0.00019993258997018566, | |
| "loss": 1.6337, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3065134099616858, | |
| "grad_norm": 2.2951676845550537, | |
| "learning_rate": 0.0001999167799344583, | |
| "loss": 1.6456, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3218390804597701, | |
| "grad_norm": 2.147050380706787, | |
| "learning_rate": 0.00019989930665413147, | |
| "loss": 1.5753, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3371647509578544, | |
| "grad_norm": 2.214049816131592, | |
| "learning_rate": 0.00019988017042007065, | |
| "loss": 1.8861, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3524904214559387, | |
| "grad_norm": 2.1761178970336914, | |
| "learning_rate": 0.00019985937155082327, | |
| "loss": 1.5181, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.367816091954023, | |
| "grad_norm": 2.7011399269104004, | |
| "learning_rate": 0.00019983691039261357, | |
| "loss": 1.6559, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3831417624521073, | |
| "grad_norm": 2.0692250728607178, | |
| "learning_rate": 0.0001998127873193367, | |
| "loss": 1.6602, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.39846743295019155, | |
| "grad_norm": 2.190605640411377, | |
| "learning_rate": 0.00019978700273255254, | |
| "loss": 1.6678, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.41379310344827586, | |
| "grad_norm": 2.303030252456665, | |
| "learning_rate": 0.000199759557061479, | |
| "loss": 1.7287, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.42911877394636017, | |
| "grad_norm": 2.3805620670318604, | |
| "learning_rate": 0.000199730450762985, | |
| "loss": 1.6801, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 1.9173905849456787, | |
| "learning_rate": 0.00019969968432158265, | |
| "loss": 1.6536, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.45977011494252873, | |
| "grad_norm": 1.9623961448669434, | |
| "learning_rate": 0.00019966725824941932, | |
| "loss": 1.5311, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.47509578544061304, | |
| "grad_norm": 2.2046408653259277, | |
| "learning_rate": 0.00019963317308626914, | |
| "loss": 1.7119, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4904214559386973, | |
| "grad_norm": 2.034040927886963, | |
| "learning_rate": 0.00019959742939952392, | |
| "loss": 1.6249, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5057471264367817, | |
| "grad_norm": 2.274533271789551, | |
| "learning_rate": 0.00019956002778418372, | |
| "loss": 1.6809, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5210727969348659, | |
| "grad_norm": 1.9758435487747192, | |
| "learning_rate": 0.0001995209688628471, | |
| "loss": 1.5507, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5210727969348659, | |
| "eval_loss": 1.7039636373519897, | |
| "eval_runtime": 10.4847, | |
| "eval_samples_per_second": 9.538, | |
| "eval_steps_per_second": 4.769, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5363984674329502, | |
| "grad_norm": 1.908996820449829, | |
| "learning_rate": 0.00019948025328570042, | |
| "loss": 1.668, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 2.0340089797973633, | |
| "learning_rate": 0.00019943788173050744, | |
| "loss": 1.6788, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5670498084291188, | |
| "grad_norm": 2.1147003173828125, | |
| "learning_rate": 0.0001993938549025977, | |
| "loss": 1.5346, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5823754789272031, | |
| "grad_norm": 2.2234580516815186, | |
| "learning_rate": 0.00019934817353485501, | |
| "loss": 1.6118, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5977011494252874, | |
| "grad_norm": 1.8898108005523682, | |
| "learning_rate": 0.00019930083838770504, | |
| "loss": 1.542, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6130268199233716, | |
| "grad_norm": 1.947200894355774, | |
| "learning_rate": 0.00019925185024910277, | |
| "loss": 1.6701, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6283524904214559, | |
| "grad_norm": 1.9336851835250854, | |
| "learning_rate": 0.00019920120993451948, | |
| "loss": 1.6159, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6436781609195402, | |
| "grad_norm": 2.044646978378296, | |
| "learning_rate": 0.00019914891828692888, | |
| "loss": 1.6761, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6590038314176245, | |
| "grad_norm": 1.9677635431289673, | |
| "learning_rate": 0.00019909497617679348, | |
| "loss": 1.7505, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6743295019157088, | |
| "grad_norm": 1.887392282485962, | |
| "learning_rate": 0.00019903938450204972, | |
| "loss": 1.6804, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 2.1503148078918457, | |
| "learning_rate": 0.0001989821441880933, | |
| "loss": 1.5835, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7049808429118773, | |
| "grad_norm": 1.8051438331604004, | |
| "learning_rate": 0.00019892325618776351, | |
| "loss": 1.721, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7203065134099617, | |
| "grad_norm": 1.8534125089645386, | |
| "learning_rate": 0.0001988627214813277, | |
| "loss": 1.6925, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.735632183908046, | |
| "grad_norm": 1.6843996047973633, | |
| "learning_rate": 0.00019880054107646467, | |
| "loss": 1.7291, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7509578544061303, | |
| "grad_norm": 2.0053601264953613, | |
| "learning_rate": 0.000198736716008248, | |
| "loss": 1.6344, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7662835249042146, | |
| "grad_norm": 1.9978563785552979, | |
| "learning_rate": 0.0001986712473391289, | |
| "loss": 1.5687, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7816091954022989, | |
| "grad_norm": 1.6498862504959106, | |
| "learning_rate": 0.0001986041361589184, | |
| "loss": 1.6354, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.7816091954022989, | |
| "eval_loss": 1.6665664911270142, | |
| "eval_runtime": 10.4646, | |
| "eval_samples_per_second": 9.556, | |
| "eval_steps_per_second": 4.778, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.7969348659003831, | |
| "grad_norm": 2.0754377841949463, | |
| "learning_rate": 0.00019853538358476932, | |
| "loss": 1.7128, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.8122605363984674, | |
| "grad_norm": 1.8503700494766235, | |
| "learning_rate": 0.0001984649907611575, | |
| "loss": 1.6028, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.8275862068965517, | |
| "grad_norm": 1.9877614974975586, | |
| "learning_rate": 0.00019839295885986296, | |
| "loss": 1.7578, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.842911877394636, | |
| "grad_norm": 1.9744536876678467, | |
| "learning_rate": 0.0001983192890799503, | |
| "loss": 1.6639, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.8582375478927203, | |
| "grad_norm": 1.9516663551330566, | |
| "learning_rate": 0.00019824398264774867, | |
| "loss": 1.6724, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.8735632183908046, | |
| "grad_norm": 1.8794466257095337, | |
| "learning_rate": 0.0001981670408168315, | |
| "loss": 1.5008, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 1.7897112369537354, | |
| "learning_rate": 0.0001980884648679955, | |
| "loss": 1.5942, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.9042145593869731, | |
| "grad_norm": 1.776986002922058, | |
| "learning_rate": 0.00019800825610923934, | |
| "loss": 1.5893, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.9195402298850575, | |
| "grad_norm": 1.9505722522735596, | |
| "learning_rate": 0.00019792641587574212, | |
| "loss": 1.6273, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9348659003831418, | |
| "grad_norm": 1.9335532188415527, | |
| "learning_rate": 0.00019784294552984078, | |
| "loss": 1.5953, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.9501915708812261, | |
| "grad_norm": 2.057013750076294, | |
| "learning_rate": 0.0001977578464610077, | |
| "loss": 1.6479, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.9655172413793104, | |
| "grad_norm": 1.838173508644104, | |
| "learning_rate": 0.00019767112008582736, | |
| "loss": 1.6264, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.9808429118773946, | |
| "grad_norm": 1.8121559619903564, | |
| "learning_rate": 0.000197582767847973, | |
| "loss": 1.5673, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.9961685823754789, | |
| "grad_norm": 1.8894027471542358, | |
| "learning_rate": 0.00019749279121818235, | |
| "loss": 1.6727, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.0076628352490422, | |
| "grad_norm": 3.277520179748535, | |
| "learning_rate": 0.00019740119169423337, | |
| "loss": 2.0471, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.0229885057471264, | |
| "grad_norm": 1.553820013999939, | |
| "learning_rate": 0.00019730797080091904, | |
| "loss": 0.9425, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.0383141762452108, | |
| "grad_norm": 1.5284228324890137, | |
| "learning_rate": 0.00019721313009002226, | |
| "loss": 0.9188, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.0383141762452108, | |
| "eval_loss": 1.6558603048324585, | |
| "eval_runtime": 10.461, | |
| "eval_samples_per_second": 9.559, | |
| "eval_steps_per_second": 4.78, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.053639846743295, | |
| "grad_norm": 1.4431841373443604, | |
| "learning_rate": 0.0001971166711402899, | |
| "loss": 0.8091, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.0689655172413792, | |
| "grad_norm": 1.6087971925735474, | |
| "learning_rate": 0.00019701859555740648, | |
| "loss": 0.9413, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0842911877394636, | |
| "grad_norm": 1.6617636680603027, | |
| "learning_rate": 0.0001969189049739674, | |
| "loss": 0.895, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.0996168582375478, | |
| "grad_norm": 1.606227159500122, | |
| "learning_rate": 0.00019681760104945203, | |
| "loss": 0.8442, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.1149425287356323, | |
| "grad_norm": 1.4187818765640259, | |
| "learning_rate": 0.00019671468547019573, | |
| "loss": 0.8078, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.1302681992337165, | |
| "grad_norm": 1.5401397943496704, | |
| "learning_rate": 0.00019661015994936203, | |
| "loss": 0.9093, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.1455938697318007, | |
| "grad_norm": 1.633941888809204, | |
| "learning_rate": 0.000196504026226914, | |
| "loss": 0.8941, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.160919540229885, | |
| "grad_norm": 1.551140308380127, | |
| "learning_rate": 0.00019639628606958533, | |
| "loss": 0.8318, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.1762452107279693, | |
| "grad_norm": 1.920763373374939, | |
| "learning_rate": 0.00019628694127085092, | |
| "loss": 0.8781, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.1915708812260537, | |
| "grad_norm": 1.802857518196106, | |
| "learning_rate": 0.00019617599365089693, | |
| "loss": 0.9417, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.206896551724138, | |
| "grad_norm": 1.5704469680786133, | |
| "learning_rate": 0.0001960634450565907, | |
| "loss": 0.8462, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.2222222222222223, | |
| "grad_norm": 1.67445969581604, | |
| "learning_rate": 0.00019594929736144976, | |
| "loss": 0.9293, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.2375478927203065, | |
| "grad_norm": 1.6255979537963867, | |
| "learning_rate": 0.00019583355246561074, | |
| "loss": 0.8358, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.2528735632183907, | |
| "grad_norm": 1.6431758403778076, | |
| "learning_rate": 0.00019571621229579782, | |
| "loss": 0.9362, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.2681992337164751, | |
| "grad_norm": 1.6321423053741455, | |
| "learning_rate": 0.00019559727880529059, | |
| "loss": 0.9574, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.2835249042145593, | |
| "grad_norm": 1.4820754528045654, | |
| "learning_rate": 0.00019547675397389141, | |
| "loss": 0.7697, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.2988505747126438, | |
| "grad_norm": 1.6704702377319336, | |
| "learning_rate": 0.00019535463980789277, | |
| "loss": 0.8897, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.2988505747126438, | |
| "eval_loss": 1.6953216791152954, | |
| "eval_runtime": 10.5357, | |
| "eval_samples_per_second": 9.492, | |
| "eval_steps_per_second": 4.746, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.314176245210728, | |
| "grad_norm": 1.5606012344360352, | |
| "learning_rate": 0.00019523093834004356, | |
| "loss": 0.8687, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.3295019157088124, | |
| "grad_norm": 1.69247567653656, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.962, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.3448275862068966, | |
| "grad_norm": 1.77336847782135, | |
| "learning_rate": 0.00019497878176186827, | |
| "loss": 0.8073, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.3601532567049808, | |
| "grad_norm": 1.6945431232452393, | |
| "learning_rate": 0.00019485033084901606, | |
| "loss": 0.9388, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.3754789272030652, | |
| "grad_norm": 1.8969769477844238, | |
| "learning_rate": 0.000194720301029191, | |
| "loss": 0.9693, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.3908045977011494, | |
| "grad_norm": 1.6189223527908325, | |
| "learning_rate": 0.0001945886944669084, | |
| "loss": 0.8052, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.4061302681992336, | |
| "grad_norm": 1.652786135673523, | |
| "learning_rate": 0.0001944555133529304, | |
| "loss": 0.9079, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.421455938697318, | |
| "grad_norm": 1.5484676361083984, | |
| "learning_rate": 0.00019432075990422968, | |
| "loss": 0.8395, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.4367816091954024, | |
| "grad_norm": 1.625877022743225, | |
| "learning_rate": 0.00019418443636395248, | |
| "loss": 0.876, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.4521072796934866, | |
| "grad_norm": 1.922146201133728, | |
| "learning_rate": 0.00019404654500138117, | |
| "loss": 0.8344, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.4674329501915708, | |
| "grad_norm": 1.6981974840164185, | |
| "learning_rate": 0.0001939070881118966, | |
| "loss": 0.8232, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.4827586206896552, | |
| "grad_norm": 1.7996752262115479, | |
| "learning_rate": 0.0001937660680169399, | |
| "loss": 0.9207, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.4980842911877394, | |
| "grad_norm": 1.784002423286438, | |
| "learning_rate": 0.00019362348706397373, | |
| "loss": 0.8402, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.5134099616858236, | |
| "grad_norm": 1.436486005783081, | |
| "learning_rate": 0.00019347934762644326, | |
| "loss": 0.7129, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.528735632183908, | |
| "grad_norm": 1.5737037658691406, | |
| "learning_rate": 0.0001933336521037367, | |
| "loss": 0.9158, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.5440613026819925, | |
| "grad_norm": 1.516647219657898, | |
| "learning_rate": 0.00019318640292114524, | |
| "loss": 0.8451, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.5593869731800765, | |
| "grad_norm": 1.6449085474014282, | |
| "learning_rate": 0.00019303760252982287, | |
| "loss": 0.9014, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.5593869731800765, | |
| "eval_loss": 1.7118545770645142, | |
| "eval_runtime": 10.4529, | |
| "eval_samples_per_second": 9.567, | |
| "eval_steps_per_second": 4.783, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.5747126436781609, | |
| "grad_norm": 1.578679084777832, | |
| "learning_rate": 0.00019288725340674536, | |
| "loss": 0.8788, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.5900383141762453, | |
| "grad_norm": 1.635235071182251, | |
| "learning_rate": 0.00019273535805466917, | |
| "loss": 0.8992, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.6053639846743295, | |
| "grad_norm": 1.637152075767517, | |
| "learning_rate": 0.0001925819190020898, | |
| "loss": 0.8922, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.6206896551724137, | |
| "grad_norm": 1.5802862644195557, | |
| "learning_rate": 0.0001924269388031996, | |
| "loss": 0.822, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.6360153256704981, | |
| "grad_norm": 1.5077544450759888, | |
| "learning_rate": 0.00019227042003784527, | |
| "loss": 0.7743, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.6513409961685823, | |
| "grad_norm": 1.7062519788742065, | |
| "learning_rate": 0.000192112365311485, | |
| "loss": 0.8473, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 1.676834225654602, | |
| "learning_rate": 0.0001919527772551451, | |
| "loss": 0.96, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.681992337164751, | |
| "grad_norm": 1.775424838066101, | |
| "learning_rate": 0.00019179165852537596, | |
| "loss": 0.8855, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.6973180076628354, | |
| "grad_norm": 1.5298705101013184, | |
| "learning_rate": 0.0001916290118042082, | |
| "loss": 0.7232, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.7126436781609196, | |
| "grad_norm": 1.5757646560668945, | |
| "learning_rate": 0.0001914648397991078, | |
| "loss": 0.9097, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.7279693486590038, | |
| "grad_norm": 1.5786842107772827, | |
| "learning_rate": 0.00019129914524293102, | |
| "loss": 0.8836, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.7432950191570882, | |
| "grad_norm": 1.8097132444381714, | |
| "learning_rate": 0.00019113193089387903, | |
| "loss": 0.938, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.7586206896551724, | |
| "grad_norm": 1.771764874458313, | |
| "learning_rate": 0.00019096319953545185, | |
| "loss": 0.8042, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.7739463601532566, | |
| "grad_norm": 1.8478142023086548, | |
| "learning_rate": 0.00019079295397640215, | |
| "loss": 0.9323, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.789272030651341, | |
| "grad_norm": 1.5792856216430664, | |
| "learning_rate": 0.00019062119705068843, | |
| "loss": 0.8917, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.8045977011494254, | |
| "grad_norm": 1.6793948411941528, | |
| "learning_rate": 0.00019044793161742782, | |
| "loss": 0.8495, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.8199233716475096, | |
| "grad_norm": 1.6884868144989014, | |
| "learning_rate": 0.00019027316056084858, | |
| "loss": 0.8517, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.8199233716475096, | |
| "eval_loss": 1.7208638191223145, | |
| "eval_runtime": 10.4697, | |
| "eval_samples_per_second": 9.551, | |
| "eval_steps_per_second": 4.776, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.8352490421455938, | |
| "grad_norm": 1.740159511566162, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 0.96, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.8505747126436782, | |
| "grad_norm": 1.6979262828826904, | |
| "learning_rate": 0.0001899191132399138, | |
| "loss": 0.8892, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.8659003831417624, | |
| "grad_norm": 1.7245821952819824, | |
| "learning_rate": 0.00018973984286913584, | |
| "loss": 0.8417, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.8812260536398466, | |
| "grad_norm": 1.8138068914413452, | |
| "learning_rate": 0.0001895590786620963, | |
| "loss": 0.9722, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.896551724137931, | |
| "grad_norm": 1.4977965354919434, | |
| "learning_rate": 0.00018937682362785022, | |
| "loss": 0.8512, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.9118773946360155, | |
| "grad_norm": 1.5849545001983643, | |
| "learning_rate": 0.0001891930808002694, | |
| "loss": 0.7628, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.9272030651340997, | |
| "grad_norm": 1.8099451065063477, | |
| "learning_rate": 0.00018900785323799189, | |
| "loss": 0.9171, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.9425287356321839, | |
| "grad_norm": 1.5819072723388672, | |
| "learning_rate": 0.00018882114402437106, | |
| "loss": 0.7413, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.9578544061302683, | |
| "grad_norm": 1.8191732168197632, | |
| "learning_rate": 0.00018863295626742437, | |
| "loss": 1.0208, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.9731800766283525, | |
| "grad_norm": 1.7665985822677612, | |
| "learning_rate": 0.00018844329309978145, | |
| "loss": 0.8426, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.9885057471264367, | |
| "grad_norm": 1.9029268026351929, | |
| "learning_rate": 0.00018825215767863214, | |
| "loss": 0.983, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.007662835249042, | |
| "grad_norm": 1.5204992294311523, | |
| "learning_rate": 0.0001880595531856738, | |
| "loss": 0.6558, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 2.0229885057471266, | |
| "grad_norm": 1.225983738899231, | |
| "learning_rate": 0.00018786548282705848, | |
| "loss": 0.3984, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.0383141762452106, | |
| "grad_norm": 1.2345383167266846, | |
| "learning_rate": 0.0001876699498333393, | |
| "loss": 0.4303, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 2.053639846743295, | |
| "grad_norm": 1.2123405933380127, | |
| "learning_rate": 0.00018747295745941703, | |
| "loss": 0.4609, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.0689655172413794, | |
| "grad_norm": 1.2038960456848145, | |
| "learning_rate": 0.00018727450898448563, | |
| "loss": 0.3909, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.0842911877394634, | |
| "grad_norm": 1.2191224098205566, | |
| "learning_rate": 0.00018707460771197774, | |
| "loss": 0.4448, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.0842911877394634, | |
| "eval_loss": 1.796938419342041, | |
| "eval_runtime": 10.4571, | |
| "eval_samples_per_second": 9.563, | |
| "eval_steps_per_second": 4.781, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.099616858237548, | |
| "grad_norm": 1.3134615421295166, | |
| "learning_rate": 0.00018687325696950972, | |
| "loss": 0.5176, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 2.1149425287356323, | |
| "grad_norm": 1.39946448802948, | |
| "learning_rate": 0.00018667046010882626, | |
| "loss": 0.4207, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.1302681992337167, | |
| "grad_norm": 1.20857834815979, | |
| "learning_rate": 0.00018646622050574454, | |
| "loss": 0.3165, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 2.1455938697318007, | |
| "grad_norm": 1.4676852226257324, | |
| "learning_rate": 0.00018626054156009806, | |
| "loss": 0.4934, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.160919540229885, | |
| "grad_norm": 1.2490851879119873, | |
| "learning_rate": 0.0001860534266956801, | |
| "loss": 0.4454, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.1762452107279695, | |
| "grad_norm": 1.5670422315597534, | |
| "learning_rate": 0.00018584487936018661, | |
| "loss": 0.4259, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.1915708812260535, | |
| "grad_norm": 1.5839508771896362, | |
| "learning_rate": 0.0001856349030251589, | |
| "loss": 0.4459, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 2.206896551724138, | |
| "grad_norm": 1.4877279996871948, | |
| "learning_rate": 0.00018542350118592584, | |
| "loss": 0.4585, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 1.292151927947998, | |
| "learning_rate": 0.00018521067736154568, | |
| "loss": 0.3635, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.2375478927203067, | |
| "grad_norm": 1.3014862537384033, | |
| "learning_rate": 0.00018499643509474738, | |
| "loss": 0.4268, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.2528735632183907, | |
| "grad_norm": 1.3445168733596802, | |
| "learning_rate": 0.00018478077795187187, | |
| "loss": 0.4178, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.268199233716475, | |
| "grad_norm": 1.2323206663131714, | |
| "learning_rate": 0.0001845637095228124, | |
| "loss": 0.3389, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.2835249042145596, | |
| "grad_norm": 1.321321725845337, | |
| "learning_rate": 0.000184345233420955, | |
| "loss": 0.394, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 2.2988505747126435, | |
| "grad_norm": 1.3308717012405396, | |
| "learning_rate": 0.00018412535328311814, | |
| "loss": 0.3768, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.314176245210728, | |
| "grad_norm": 1.4169113636016846, | |
| "learning_rate": 0.00018390407276949234, | |
| "loss": 0.4106, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 2.3295019157088124, | |
| "grad_norm": 1.4107593297958374, | |
| "learning_rate": 0.00018368139556357928, | |
| "loss": 0.3955, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 2.344827586206897, | |
| "grad_norm": 1.2308950424194336, | |
| "learning_rate": 0.00018345732537213027, | |
| "loss": 0.4053, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.344827586206897, | |
| "eval_loss": 1.8346749544143677, | |
| "eval_runtime": 10.5405, | |
| "eval_samples_per_second": 9.487, | |
| "eval_steps_per_second": 4.744, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.3601532567049808, | |
| "grad_norm": 1.2049033641815186, | |
| "learning_rate": 0.0001832318659250847, | |
| "loss": 0.3675, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 2.375478927203065, | |
| "grad_norm": 1.35014009475708, | |
| "learning_rate": 0.00018300502097550806, | |
| "loss": 0.4565, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.3908045977011496, | |
| "grad_norm": 1.2926514148712158, | |
| "learning_rate": 0.00018277679429952912, | |
| "loss": 0.3887, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.4061302681992336, | |
| "grad_norm": 1.1395353078842163, | |
| "learning_rate": 0.0001825471896962774, | |
| "loss": 0.3469, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 2.421455938697318, | |
| "grad_norm": 1.2925468683242798, | |
| "learning_rate": 0.00018231621098781982, | |
| "loss": 0.3811, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 2.4367816091954024, | |
| "grad_norm": 1.2556133270263672, | |
| "learning_rate": 0.00018208386201909698, | |
| "loss": 0.3961, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 2.4521072796934864, | |
| "grad_norm": 3.042213201522827, | |
| "learning_rate": 0.00018185014665785936, | |
| "loss": 0.4634, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.467432950191571, | |
| "grad_norm": 7.5744099617004395, | |
| "learning_rate": 0.00018161506879460273, | |
| "loss": 0.5113, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 2.4827586206896552, | |
| "grad_norm": 1.288672685623169, | |
| "learning_rate": 0.00018137863234250347, | |
| "loss": 0.3684, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.4980842911877392, | |
| "grad_norm": 1.3630754947662354, | |
| "learning_rate": 0.00018114084123735356, | |
| "loss": 0.4277, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 2.5134099616858236, | |
| "grad_norm": 1.344976544380188, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.3682, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 2.528735632183908, | |
| "grad_norm": 1.5814900398254395, | |
| "learning_rate": 0.000180661210923753, | |
| "loss": 0.4435, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.5440613026819925, | |
| "grad_norm": 1.3256701231002808, | |
| "learning_rate": 0.00018041937969937206, | |
| "loss": 0.3651, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 2.5593869731800765, | |
| "grad_norm": 1.1954660415649414, | |
| "learning_rate": 0.00018017620978994677, | |
| "loss": 0.3662, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 2.574712643678161, | |
| "grad_norm": 1.2444689273834229, | |
| "learning_rate": 0.00017993170524335615, | |
| "loss": 0.4181, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.5900383141762453, | |
| "grad_norm": 1.3350296020507812, | |
| "learning_rate": 0.00017968587012969604, | |
| "loss": 0.4437, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 2.6053639846743293, | |
| "grad_norm": 1.1780810356140137, | |
| "learning_rate": 0.00017943870854121124, | |
| "loss": 0.3723, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.6053639846743293, | |
| "eval_loss": 1.8776559829711914, | |
| "eval_runtime": 10.4883, | |
| "eval_samples_per_second": 9.534, | |
| "eval_steps_per_second": 4.767, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.6206896551724137, | |
| "grad_norm": 1.3304461240768433, | |
| "learning_rate": 0.00017919022459222752, | |
| "loss": 0.4096, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 2.636015325670498, | |
| "grad_norm": 1.429721474647522, | |
| "learning_rate": 0.00017894042241908294, | |
| "loss": 0.4662, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.6513409961685825, | |
| "grad_norm": 1.160591959953308, | |
| "learning_rate": 0.0001786893061800592, | |
| "loss": 0.3493, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 1.2618906497955322, | |
| "learning_rate": 0.00017843688005531226, | |
| "loss": 0.3734, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.681992337164751, | |
| "grad_norm": 1.3741453886032104, | |
| "learning_rate": 0.000178183148246803, | |
| "loss": 0.4422, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.6973180076628354, | |
| "grad_norm": 1.336128830909729, | |
| "learning_rate": 0.0001779281149782269, | |
| "loss": 0.4071, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 2.7126436781609193, | |
| "grad_norm": 1.5618481636047363, | |
| "learning_rate": 0.000177671784494944, | |
| "loss": 0.3985, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 2.7279693486590038, | |
| "grad_norm": 1.4244683980941772, | |
| "learning_rate": 0.00017741416106390826, | |
| "loss": 0.4876, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 2.743295019157088, | |
| "grad_norm": 1.4463664293289185, | |
| "learning_rate": 0.0001771552489735963, | |
| "loss": 0.4698, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 2.7586206896551726, | |
| "grad_norm": 1.3060929775238037, | |
| "learning_rate": 0.0001768950525339362, | |
| "loss": 0.376, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.7739463601532566, | |
| "grad_norm": 1.5133682489395142, | |
| "learning_rate": 0.00017663357607623577, | |
| "loss": 0.4139, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 2.789272030651341, | |
| "grad_norm": 1.4014631509780884, | |
| "learning_rate": 0.00017637082395311024, | |
| "loss": 0.4094, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 2.8045977011494254, | |
| "grad_norm": 1.4687765836715698, | |
| "learning_rate": 0.00017610680053841007, | |
| "loss": 0.4123, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 2.8199233716475094, | |
| "grad_norm": 1.336650013923645, | |
| "learning_rate": 0.000175841510227148, | |
| "loss": 0.3737, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 2.835249042145594, | |
| "grad_norm": 1.5005886554718018, | |
| "learning_rate": 0.00017557495743542585, | |
| "loss": 0.4835, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.8505747126436782, | |
| "grad_norm": 1.3977274894714355, | |
| "learning_rate": 0.00017530714660036112, | |
| "loss": 0.4989, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 2.8659003831417627, | |
| "grad_norm": 1.1647838354110718, | |
| "learning_rate": 0.00017503808218001304, | |
| "loss": 0.339, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 2.8659003831417627, | |
| "eval_loss": 1.875050663948059, | |
| "eval_runtime": 10.5813, | |
| "eval_samples_per_second": 9.451, | |
| "eval_steps_per_second": 4.725, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 2.8812260536398466, | |
| "grad_norm": 1.4600085020065308, | |
| "learning_rate": 0.00017476776865330847, | |
| "loss": 0.4327, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 2.896551724137931, | |
| "grad_norm": 1.3009713888168335, | |
| "learning_rate": 0.00017449621051996713, | |
| "loss": 0.3969, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 2.9118773946360155, | |
| "grad_norm": 1.5662423372268677, | |
| "learning_rate": 0.000174223412300427, | |
| "loss": 0.4866, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.9272030651340994, | |
| "grad_norm": 1.1687737703323364, | |
| "learning_rate": 0.00017394937853576877, | |
| "loss": 0.3411, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 2.942528735632184, | |
| "grad_norm": 1.3152905702590942, | |
| "learning_rate": 0.0001736741137876405, | |
| "loss": 0.4294, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 2.9578544061302683, | |
| "grad_norm": 1.5262017250061035, | |
| "learning_rate": 0.00017339762263818146, | |
| "loss": 0.433, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 2.9731800766283527, | |
| "grad_norm": 1.2779839038848877, | |
| "learning_rate": 0.000173119909689946, | |
| "loss": 0.4334, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 2.9885057471264367, | |
| "grad_norm": 1.2895079851150513, | |
| "learning_rate": 0.00017284097956582692, | |
| "loss": 0.4393, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 3.003831417624521, | |
| "grad_norm": 5.897226810455322, | |
| "learning_rate": 0.0001725608369089785, | |
| "loss": 0.5205, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 3.0191570881226055, | |
| "grad_norm": 1.2967376708984375, | |
| "learning_rate": 0.00017227948638273916, | |
| "loss": 0.202, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 3.0344827586206895, | |
| "grad_norm": 1.050823450088501, | |
| "learning_rate": 0.00017199693267055393, | |
| "loss": 0.2219, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 3.049808429118774, | |
| "grad_norm": 0.8004248738288879, | |
| "learning_rate": 0.00017171318047589637, | |
| "loss": 0.1918, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 3.0651340996168583, | |
| "grad_norm": 0.9603090286254883, | |
| "learning_rate": 0.00017142823452219038, | |
| "loss": 0.1627, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.0804597701149423, | |
| "grad_norm": 1.0117729902267456, | |
| "learning_rate": 0.00017114209955273153, | |
| "loss": 0.1734, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 3.0957854406130267, | |
| "grad_norm": 1.150023102760315, | |
| "learning_rate": 0.00017085478033060806, | |
| "loss": 0.2105, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 3.111111111111111, | |
| "grad_norm": 1.2649832963943481, | |
| "learning_rate": 0.00017056628163862172, | |
| "loss": 0.1996, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 3.1264367816091956, | |
| "grad_norm": 1.1088045835494995, | |
| "learning_rate": 0.00017027660827920798, | |
| "loss": 0.1614, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 3.1264367816091956, | |
| "eval_loss": 2.065758466720581, | |
| "eval_runtime": 10.4748, | |
| "eval_samples_per_second": 9.547, | |
| "eval_steps_per_second": 4.773, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 3.1417624521072796, | |
| "grad_norm": 1.1436564922332764, | |
| "learning_rate": 0.00016998576507435618, | |
| "loss": 0.1886, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 3.157088122605364, | |
| "grad_norm": 1.2624493837356567, | |
| "learning_rate": 0.00016969375686552937, | |
| "loss": 0.1792, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 3.1724137931034484, | |
| "grad_norm": 1.0960315465927124, | |
| "learning_rate": 0.00016940058851358343, | |
| "loss": 0.196, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 3.1877394636015324, | |
| "grad_norm": 1.062483549118042, | |
| "learning_rate": 0.00016910626489868649, | |
| "loss": 0.1577, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 3.203065134099617, | |
| "grad_norm": 1.0054856538772583, | |
| "learning_rate": 0.0001688107909202374, | |
| "loss": 0.1893, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 3.218390804597701, | |
| "grad_norm": 1.111485481262207, | |
| "learning_rate": 0.00016851417149678444, | |
| "loss": 0.1796, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.2337164750957856, | |
| "grad_norm": 1.009745478630066, | |
| "learning_rate": 0.00016821641156594317, | |
| "loss": 0.1523, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 3.2490421455938696, | |
| "grad_norm": 1.213293433189392, | |
| "learning_rate": 0.0001679175160843145, | |
| "loss": 0.1619, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 3.264367816091954, | |
| "grad_norm": 1.5143858194351196, | |
| "learning_rate": 0.00016761749002740193, | |
| "loss": 0.1609, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 3.2796934865900385, | |
| "grad_norm": 1.3771694898605347, | |
| "learning_rate": 0.00016731633838952905, | |
| "loss": 0.1671, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 3.2950191570881224, | |
| "grad_norm": 1.1563445329666138, | |
| "learning_rate": 0.00016701406618375596, | |
| "loss": 0.1885, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 3.310344827586207, | |
| "grad_norm": 1.0585676431655884, | |
| "learning_rate": 0.00016671067844179627, | |
| "loss": 0.1634, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 3.3256704980842913, | |
| "grad_norm": 1.1020563840866089, | |
| "learning_rate": 0.00016640618021393304, | |
| "loss": 0.1838, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 3.3409961685823752, | |
| "grad_norm": 0.9592476487159729, | |
| "learning_rate": 0.00016610057656893482, | |
| "loss": 0.179, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 3.3563218390804597, | |
| "grad_norm": 0.9426510334014893, | |
| "learning_rate": 0.00016579387259397127, | |
| "loss": 0.1581, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 3.371647509578544, | |
| "grad_norm": 1.2259931564331055, | |
| "learning_rate": 0.00016548607339452853, | |
| "loss": 0.2017, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.3869731800766285, | |
| "grad_norm": 1.2636795043945312, | |
| "learning_rate": 0.00016517718409432406, | |
| "loss": 0.1804, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 3.3869731800766285, | |
| "eval_loss": 2.0642523765563965, | |
| "eval_runtime": 10.4896, | |
| "eval_samples_per_second": 9.533, | |
| "eval_steps_per_second": 4.767, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 3.4022988505747125, | |
| "grad_norm": 0.9591987729072571, | |
| "learning_rate": 0.00016486720983522156, | |
| "loss": 0.1653, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 3.417624521072797, | |
| "grad_norm": 0.9433954954147339, | |
| "learning_rate": 0.00016455615577714528, | |
| "loss": 0.1843, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 3.4329501915708813, | |
| "grad_norm": 1.0256028175354004, | |
| "learning_rate": 0.00016424402709799404, | |
| "loss": 0.1596, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 3.4482758620689653, | |
| "grad_norm": 1.0997707843780518, | |
| "learning_rate": 0.00016393082899355516, | |
| "loss": 0.1897, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.4636015325670497, | |
| "grad_norm": 1.6630239486694336, | |
| "learning_rate": 0.00016361656667741802, | |
| "loss": 0.2045, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 3.478927203065134, | |
| "grad_norm": 0.9956857562065125, | |
| "learning_rate": 0.00016330124538088705, | |
| "loss": 0.1653, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 3.4942528735632186, | |
| "grad_norm": 1.3272435665130615, | |
| "learning_rate": 0.0001629848703528949, | |
| "loss": 0.198, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 3.5095785440613025, | |
| "grad_norm": 8.141691207885742, | |
| "learning_rate": 0.0001626674468599149, | |
| "loss": 0.2591, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 3.524904214559387, | |
| "grad_norm": 0.9597133994102478, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 0.1818, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.5402298850574714, | |
| "grad_norm": 0.949269711971283, | |
| "learning_rate": 0.00016202947563206187, | |
| "loss": 0.1675, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 1.0063790082931519, | |
| "learning_rate": 0.00016170893851704876, | |
| "loss": 0.1875, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 3.57088122605364, | |
| "grad_norm": 1.2696994543075562, | |
| "learning_rate": 0.00016138737417659068, | |
| "loss": 0.1746, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 3.586206896551724, | |
| "grad_norm": 1.055250644683838, | |
| "learning_rate": 0.00016106478796354382, | |
| "loss": 0.1919, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 3.6015325670498086, | |
| "grad_norm": 0.9498022794723511, | |
| "learning_rate": 0.00016074118524777477, | |
| "loss": 0.1441, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 3.6168582375478926, | |
| "grad_norm": 1.0420253276824951, | |
| "learning_rate": 0.00016041657141607107, | |
| "loss": 0.1634, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 3.632183908045977, | |
| "grad_norm": 1.2098767757415771, | |
| "learning_rate": 0.0001600909518720517, | |
| "loss": 0.187, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 3.6475095785440614, | |
| "grad_norm": 1.2031207084655762, | |
| "learning_rate": 0.0001597643320360769, | |
| "loss": 0.1881, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 3.6475095785440614, | |
| "eval_loss": 2.092371940612793, | |
| "eval_runtime": 10.4707, | |
| "eval_samples_per_second": 9.551, | |
| "eval_steps_per_second": 4.775, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 3.6628352490421454, | |
| "grad_norm": 1.0068916082382202, | |
| "learning_rate": 0.0001594367173451582, | |
| "loss": 0.1499, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 3.67816091954023, | |
| "grad_norm": 1.188425898551941, | |
| "learning_rate": 0.00015910811325286768, | |
| "loss": 0.1928, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.6934865900383143, | |
| "grad_norm": 1.054997205734253, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 0.1726, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 3.7088122605363987, | |
| "grad_norm": 1.0925296545028687, | |
| "learning_rate": 0.000158447958760718, | |
| "loss": 0.2032, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 3.7241379310344827, | |
| "grad_norm": 1.2014827728271484, | |
| "learning_rate": 0.0001581164193499879, | |
| "loss": 0.1907, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 3.739463601532567, | |
| "grad_norm": 1.1900111436843872, | |
| "learning_rate": 0.0001577839125159613, | |
| "loss": 0.1977, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 3.7547892720306515, | |
| "grad_norm": 1.049250602722168, | |
| "learning_rate": 0.00015745044379364634, | |
| "loss": 0.1734, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 3.7701149425287355, | |
| "grad_norm": 1.1495704650878906, | |
| "learning_rate": 0.00015711601873406313, | |
| "loss": 0.2184, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 3.78544061302682, | |
| "grad_norm": 0.9893819689750671, | |
| "learning_rate": 0.00015678064290415122, | |
| "loss": 0.1594, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 3.8007662835249043, | |
| "grad_norm": 1.0403058528900146, | |
| "learning_rate": 0.00015644432188667695, | |
| "loss": 0.165, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 3.8160919540229887, | |
| "grad_norm": 1.1845136880874634, | |
| "learning_rate": 0.00015610706128014055, | |
| "loss": 0.204, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 3.8314176245210727, | |
| "grad_norm": 1.1242119073867798, | |
| "learning_rate": 0.00015576886669868296, | |
| "loss": 0.1861, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.846743295019157, | |
| "grad_norm": 1.0183254480361938, | |
| "learning_rate": 0.0001554297437719923, | |
| "loss": 0.18, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 3.862068965517241, | |
| "grad_norm": 1.0303974151611328, | |
| "learning_rate": 0.00015508969814521025, | |
| "loss": 0.1951, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 3.8773946360153255, | |
| "grad_norm": 1.1616798639297485, | |
| "learning_rate": 0.000154748735478838, | |
| "loss": 0.2126, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 3.89272030651341, | |
| "grad_norm": 1.1582714319229126, | |
| "learning_rate": 0.00015440686144864207, | |
| "loss": 0.1696, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 3.9080459770114944, | |
| "grad_norm": 1.0691121816635132, | |
| "learning_rate": 0.00015406408174555976, | |
| "loss": 0.1762, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 3.9080459770114944, | |
| "eval_loss": 2.062448501586914, | |
| "eval_runtime": 10.503, | |
| "eval_samples_per_second": 9.521, | |
| "eval_steps_per_second": 4.761, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 3.923371647509579, | |
| "grad_norm": 1.0353065729141235, | |
| "learning_rate": 0.00015372040207560457, | |
| "loss": 0.1894, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 3.9386973180076628, | |
| "grad_norm": 1.1007777452468872, | |
| "learning_rate": 0.00015337582815977104, | |
| "loss": 0.1864, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 3.954022988505747, | |
| "grad_norm": 0.9735039472579956, | |
| "learning_rate": 0.00015303036573393962, | |
| "loss": 0.1716, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 3.969348659003831, | |
| "grad_norm": 1.0294030904769897, | |
| "learning_rate": 0.00015268402054878117, | |
| "loss": 0.1842, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 3.9846743295019156, | |
| "grad_norm": 1.0041604042053223, | |
| "learning_rate": 0.00015233679836966122, | |
| "loss": 0.1904, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 2.519958734512329, | |
| "learning_rate": 0.00015198870497654395, | |
| "loss": 0.4303, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 4.015325670498084, | |
| "grad_norm": 0.9649507999420166, | |
| "learning_rate": 0.0001516397461638962, | |
| "loss": 0.1039, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 4.030651340996169, | |
| "grad_norm": 0.6340312361717224, | |
| "learning_rate": 0.00015128992774059063, | |
| "loss": 0.0831, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 4.045977011494253, | |
| "grad_norm": 2.8160183429718018, | |
| "learning_rate": 0.00015093925552980933, | |
| "loss": 0.0998, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 4.061302681992337, | |
| "grad_norm": 0.9386498332023621, | |
| "learning_rate": 0.00015058773536894685, | |
| "loss": 0.0737, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 4.076628352490421, | |
| "grad_norm": 0.6389781832695007, | |
| "learning_rate": 0.00015023537310951282, | |
| "loss": 0.0714, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 4.091954022988506, | |
| "grad_norm": 0.6236942410469055, | |
| "learning_rate": 0.0001498821746170349, | |
| "loss": 0.0713, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 4.10727969348659, | |
| "grad_norm": 0.7775859236717224, | |
| "learning_rate": 0.00014952814577096071, | |
| "loss": 0.0723, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 4.1226053639846745, | |
| "grad_norm": 0.8838902711868286, | |
| "learning_rate": 0.0001491732924645604, | |
| "loss": 0.0806, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 4.137931034482759, | |
| "grad_norm": 0.8139066696166992, | |
| "learning_rate": 0.00014881762060482814, | |
| "loss": 0.0681, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.153256704980843, | |
| "grad_norm": 0.7435247302055359, | |
| "learning_rate": 0.00014846113611238413, | |
| "loss": 0.0727, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 4.168582375478927, | |
| "grad_norm": 8.997066497802734, | |
| "learning_rate": 0.0001481038449213758, | |
| "loss": 0.195, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 4.168582375478927, | |
| "eval_loss": 2.326845169067383, | |
| "eval_runtime": 10.5534, | |
| "eval_samples_per_second": 9.476, | |
| "eval_steps_per_second": 4.738, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 4.183908045977011, | |
| "grad_norm": 0.7295827269554138, | |
| "learning_rate": 0.0001477457529793792, | |
| "loss": 0.0834, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 4.199233716475096, | |
| "grad_norm": 0.9554088711738586, | |
| "learning_rate": 0.00014738686624729986, | |
| "loss": 0.0966, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 4.21455938697318, | |
| "grad_norm": 0.709963858127594, | |
| "learning_rate": 0.0001470271906992737, | |
| "loss": 0.0573, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.2298850574712645, | |
| "grad_norm": 0.8901592493057251, | |
| "learning_rate": 0.00014666673232256738, | |
| "loss": 0.076, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 4.245210727969349, | |
| "grad_norm": 0.706717848777771, | |
| "learning_rate": 0.00014630549711747888, | |
| "loss": 0.0746, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 4.260536398467433, | |
| "grad_norm": 3.1939444541931152, | |
| "learning_rate": 0.00014594349109723744, | |
| "loss": 0.122, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 4.275862068965517, | |
| "grad_norm": 0.8928236961364746, | |
| "learning_rate": 0.00014558072028790354, | |
| "loss": 0.1025, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 4.291187739463601, | |
| "grad_norm": 0.7875874638557434, | |
| "learning_rate": 0.00014521719072826858, | |
| "loss": 0.0856, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.306513409961686, | |
| "grad_norm": 1.0411407947540283, | |
| "learning_rate": 0.00014485290846975431, | |
| "loss": 0.0819, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 4.32183908045977, | |
| "grad_norm": 0.8319458365440369, | |
| "learning_rate": 0.0001444878795763121, | |
| "loss": 0.0625, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 4.337164750957855, | |
| "grad_norm": 0.7555274963378906, | |
| "learning_rate": 0.00014412211012432212, | |
| "loss": 0.0831, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 4.352490421455939, | |
| "grad_norm": 0.7779274582862854, | |
| "learning_rate": 0.0001437556062024921, | |
| "loss": 0.0991, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 4.3678160919540225, | |
| "grad_norm": 1.9860173463821411, | |
| "learning_rate": 0.00014338837391175582, | |
| "loss": 0.0907, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 4.383141762452107, | |
| "grad_norm": 0.9153367280960083, | |
| "learning_rate": 0.0001430204193651719, | |
| "loss": 0.0957, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 4.398467432950191, | |
| "grad_norm": 1.0085121393203735, | |
| "learning_rate": 0.0001426517486878217, | |
| "loss": 0.1071, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 4.413793103448276, | |
| "grad_norm": 0.7043394446372986, | |
| "learning_rate": 0.00014228236801670763, | |
| "loss": 0.077, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 4.42911877394636, | |
| "grad_norm": 0.7112743854522705, | |
| "learning_rate": 0.00014191228350065078, | |
| "loss": 0.0649, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 4.42911877394636, | |
| "eval_loss": 2.271777868270874, | |
| "eval_runtime": 10.4648, | |
| "eval_samples_per_second": 9.556, | |
| "eval_steps_per_second": 4.778, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 0.7803434729576111, | |
| "learning_rate": 0.00014154150130018866, | |
| "loss": 0.0704, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.459770114942529, | |
| "grad_norm": 0.7092854380607605, | |
| "learning_rate": 0.00014117002758747268, | |
| "loss": 0.0745, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 4.4750957854406135, | |
| "grad_norm": 0.7031986117362976, | |
| "learning_rate": 0.00014079786854616537, | |
| "loss": 0.0649, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 4.490421455938697, | |
| "grad_norm": 0.7902014255523682, | |
| "learning_rate": 0.00014042503037133737, | |
| "loss": 0.0908, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 4.505747126436781, | |
| "grad_norm": 1.1959948539733887, | |
| "learning_rate": 0.00014005151926936452, | |
| "loss": 0.0868, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 4.521072796934866, | |
| "grad_norm": 1.7838146686553955, | |
| "learning_rate": 0.00013967734145782425, | |
| "loss": 0.0785, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 4.53639846743295, | |
| "grad_norm": 1.0136120319366455, | |
| "learning_rate": 0.00013930250316539238, | |
| "loss": 0.1004, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 4.551724137931035, | |
| "grad_norm": 0.9047825932502747, | |
| "learning_rate": 0.00013892701063173918, | |
| "loss": 0.0902, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 4.567049808429119, | |
| "grad_norm": 0.7350003123283386, | |
| "learning_rate": 0.00013855087010742562, | |
| "loss": 0.0728, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 4.582375478927203, | |
| "grad_norm": 1.1646071672439575, | |
| "learning_rate": 0.00013817408785379943, | |
| "loss": 0.092, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 4.597701149425287, | |
| "grad_norm": 0.6288233399391174, | |
| "learning_rate": 0.00013779667014289065, | |
| "loss": 0.0678, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.6130268199233715, | |
| "grad_norm": 0.7127698063850403, | |
| "learning_rate": 0.00013741862325730738, | |
| "loss": 0.0921, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 4.628352490421456, | |
| "grad_norm": 0.8102079629898071, | |
| "learning_rate": 0.00013703995349013113, | |
| "loss": 0.0851, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 4.64367816091954, | |
| "grad_norm": 0.778022050857544, | |
| "learning_rate": 0.00013666066714481206, | |
| "loss": 0.0885, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 4.659003831417625, | |
| "grad_norm": 0.6419159770011902, | |
| "learning_rate": 0.0001362807705350641, | |
| "loss": 0.0736, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 4.674329501915709, | |
| "grad_norm": 0.7336333394050598, | |
| "learning_rate": 0.00013590026998475986, | |
| "loss": 0.0761, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 4.689655172413794, | |
| "grad_norm": 0.6584993600845337, | |
| "learning_rate": 0.00013551917182782529, | |
| "loss": 0.0786, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 4.689655172413794, | |
| "eval_loss": 2.256883144378662, | |
| "eval_runtime": 10.5286, | |
| "eval_samples_per_second": 9.498, | |
| "eval_steps_per_second": 4.749, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 4.704980842911877, | |
| "grad_norm": 0.7220829725265503, | |
| "learning_rate": 0.0001351374824081343, | |
| "loss": 0.0737, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 4.7203065134099615, | |
| "grad_norm": 0.8544161319732666, | |
| "learning_rate": 0.00013475520807940304, | |
| "loss": 0.0839, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 4.735632183908046, | |
| "grad_norm": 0.9264532327651978, | |
| "learning_rate": 0.00013437235520508432, | |
| "loss": 0.0904, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 4.75095785440613, | |
| "grad_norm": 0.6544135212898254, | |
| "learning_rate": 0.00013398893015826167, | |
| "loss": 0.0692, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.766283524904215, | |
| "grad_norm": 0.6521825790405273, | |
| "learning_rate": 0.00013360493932154302, | |
| "loss": 0.0696, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 4.781609195402299, | |
| "grad_norm": 0.7229333519935608, | |
| "learning_rate": 0.00013322038908695466, | |
| "loss": 0.0811, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 4.796934865900383, | |
| "grad_norm": 0.8600510954856873, | |
| "learning_rate": 0.00013283528585583484, | |
| "loss": 0.0623, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 4.812260536398467, | |
| "grad_norm": 0.8433498740196228, | |
| "learning_rate": 0.00013244963603872706, | |
| "loss": 0.0805, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 4.827586206896552, | |
| "grad_norm": 1.2378168106079102, | |
| "learning_rate": 0.00013206344605527355, | |
| "loss": 0.0745, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 4.842911877394636, | |
| "grad_norm": 1.4228192567825317, | |
| "learning_rate": 0.00013167672233410825, | |
| "loss": 0.1218, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 4.85823754789272, | |
| "grad_norm": 0.7594043612480164, | |
| "learning_rate": 0.00013128947131274988, | |
| "loss": 0.0744, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 4.873563218390805, | |
| "grad_norm": 0.8461570739746094, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0907, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 4.888888888888889, | |
| "grad_norm": 0.8196818232536316, | |
| "learning_rate": 0.00013051341316330946, | |
| "loss": 0.0835, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 4.904214559386973, | |
| "grad_norm": 2.694230794906616, | |
| "learning_rate": 0.00013012461895372344, | |
| "loss": 0.0844, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.919540229885057, | |
| "grad_norm": 1.4861178398132324, | |
| "learning_rate": 0.00012973532328072138, | |
| "loss": 0.0782, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 4.934865900383142, | |
| "grad_norm": 0.9646175503730774, | |
| "learning_rate": 0.00012934553262463548, | |
| "loss": 0.069, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 4.950191570881226, | |
| "grad_norm": 0.7597980499267578, | |
| "learning_rate": 0.00012895525347403756, | |
| "loss": 0.0763, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 4.950191570881226, | |
| "eval_loss": 2.252124547958374, | |
| "eval_runtime": 10.469, | |
| "eval_samples_per_second": 9.552, | |
| "eval_steps_per_second": 4.776, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 4.9655172413793105, | |
| "grad_norm": 0.7091509699821472, | |
| "learning_rate": 0.0001285644923256311, | |
| "loss": 0.0734, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 4.980842911877395, | |
| "grad_norm": 0.8412840366363525, | |
| "learning_rate": 0.00012817325568414297, | |
| "loss": 0.0982, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 4.9961685823754785, | |
| "grad_norm": 0.9467046856880188, | |
| "learning_rate": 0.00012778155006221538, | |
| "loss": 0.0725, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 5.011494252873563, | |
| "grad_norm": 1.2083613872528076, | |
| "learning_rate": 0.00012738938198029724, | |
| "loss": 0.0743, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 5.026819923371647, | |
| "grad_norm": 0.8673701882362366, | |
| "learning_rate": 0.0001269967579665357, | |
| "loss": 0.0423, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 5.042145593869732, | |
| "grad_norm": 0.36529555916786194, | |
| "learning_rate": 0.00012660368455666752, | |
| "loss": 0.027, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 5.057471264367816, | |
| "grad_norm": 0.44554996490478516, | |
| "learning_rate": 0.00012621016829391022, | |
| "loss": 0.0296, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.0727969348659006, | |
| "grad_norm": 0.9303228259086609, | |
| "learning_rate": 0.00012581621572885321, | |
| "loss": 0.0569, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 5.088122605363985, | |
| "grad_norm": 0.45792293548583984, | |
| "learning_rate": 0.00012542183341934872, | |
| "loss": 0.036, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 5.103448275862069, | |
| "grad_norm": 0.6033705472946167, | |
| "learning_rate": 0.0001250270279304026, | |
| "loss": 0.0409, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 5.118773946360153, | |
| "grad_norm": 0.5663286447525024, | |
| "learning_rate": 0.000124631805834065, | |
| "loss": 0.0258, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 5.134099616858237, | |
| "grad_norm": 0.6377267837524414, | |
| "learning_rate": 0.00012423617370932127, | |
| "loss": 0.039, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 5.149425287356322, | |
| "grad_norm": 0.4742782711982727, | |
| "learning_rate": 0.00012384013814198196, | |
| "loss": 0.0335, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 5.164750957854406, | |
| "grad_norm": 0.5032561421394348, | |
| "learning_rate": 0.00012344370572457366, | |
| "loss": 0.0269, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 5.180076628352491, | |
| "grad_norm": 0.4018470048904419, | |
| "learning_rate": 0.0001230468830562289, | |
| "loss": 0.0271, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 5.195402298850575, | |
| "grad_norm": 0.5031781196594238, | |
| "learning_rate": 0.00012264967674257646, | |
| "loss": 0.0252, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 5.210727969348659, | |
| "grad_norm": 0.6742706894874573, | |
| "learning_rate": 0.00012225209339563145, | |
| "loss": 0.0509, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.210727969348659, | |
| "eval_loss": 2.4545507431030273, | |
| "eval_runtime": 10.7404, | |
| "eval_samples_per_second": 9.311, | |
| "eval_steps_per_second": 4.655, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.226053639846743, | |
| "grad_norm": 0.6078564524650574, | |
| "learning_rate": 0.00012185413963368519, | |
| "loss": 0.0453, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 5.241379310344827, | |
| "grad_norm": 0.5548681616783142, | |
| "learning_rate": 0.00012145582208119497, | |
| "loss": 0.031, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 5.256704980842912, | |
| "grad_norm": 0.5871354937553406, | |
| "learning_rate": 0.00012105714736867391, | |
| "loss": 0.0391, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 5.272030651340996, | |
| "grad_norm": 0.5070196986198425, | |
| "learning_rate": 0.0001206581221325805, | |
| "loss": 0.0282, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 5.287356321839081, | |
| "grad_norm": 0.6400995850563049, | |
| "learning_rate": 0.0001202587530152081, | |
| "loss": 0.0326, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 5.302681992337165, | |
| "grad_norm": 0.5636530518531799, | |
| "learning_rate": 0.00011985904666457455, | |
| "loss": 0.0341, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 5.3180076628352495, | |
| "grad_norm": 0.27172422409057617, | |
| "learning_rate": 0.00011945900973431128, | |
| "loss": 0.0226, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 0.41421565413475037, | |
| "learning_rate": 0.00011905864888355263, | |
| "loss": 0.0322, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 5.3486590038314175, | |
| "grad_norm": 0.444100022315979, | |
| "learning_rate": 0.00011865797077682508, | |
| "loss": 0.0262, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 5.363984674329502, | |
| "grad_norm": 0.5755631923675537, | |
| "learning_rate": 0.00011825698208393619, | |
| "loss": 0.0314, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.379310344827586, | |
| "grad_norm": 0.5454833507537842, | |
| "learning_rate": 0.00011785568947986367, | |
| "loss": 0.0336, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 5.394636015325671, | |
| "grad_norm": 1.3440561294555664, | |
| "learning_rate": 0.00011745409964464424, | |
| "loss": 0.0345, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 5.409961685823755, | |
| "grad_norm": 0.4198431670665741, | |
| "learning_rate": 0.0001170522192632624, | |
| "loss": 0.0276, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 5.425287356321839, | |
| "grad_norm": 0.4718680679798126, | |
| "learning_rate": 0.00011665005502553911, | |
| "loss": 0.0288, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 5.440613026819923, | |
| "grad_norm": 0.9051384329795837, | |
| "learning_rate": 0.00011624761362602061, | |
| "loss": 0.0444, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 5.4559386973180075, | |
| "grad_norm": 0.5586571097373962, | |
| "learning_rate": 0.00011584490176386671, | |
| "loss": 0.027, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 5.471264367816092, | |
| "grad_norm": 0.5432120561599731, | |
| "learning_rate": 0.00011544192614273956, | |
| "loss": 0.0374, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 5.471264367816092, | |
| "eval_loss": 2.4692599773406982, | |
| "eval_runtime": 10.4877, | |
| "eval_samples_per_second": 9.535, | |
| "eval_steps_per_second": 4.768, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 5.486590038314176, | |
| "grad_norm": 0.884427547454834, | |
| "learning_rate": 0.00011503869347069185, | |
| "loss": 0.0558, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 5.501915708812261, | |
| "grad_norm": 0.43964701890945435, | |
| "learning_rate": 0.00011463521046005523, | |
| "loss": 0.0278, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 5.517241379310345, | |
| "grad_norm": 0.44980964064598083, | |
| "learning_rate": 0.00011423148382732853, | |
| "loss": 0.0275, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.53256704980843, | |
| "grad_norm": 0.40179964900016785, | |
| "learning_rate": 0.00011382752029306604, | |
| "loss": 0.0304, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 5.547892720306513, | |
| "grad_norm": 0.6193554401397705, | |
| "learning_rate": 0.00011342332658176555, | |
| "loss": 0.0305, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 5.563218390804598, | |
| "grad_norm": 0.4448515474796295, | |
| "learning_rate": 0.00011301890942175648, | |
| "loss": 0.0303, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 5.578544061302682, | |
| "grad_norm": 0.40030574798583984, | |
| "learning_rate": 0.0001126142755450878, | |
| "loss": 0.0263, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 5.593869731800766, | |
| "grad_norm": 0.5186451077461243, | |
| "learning_rate": 0.000112209431687416, | |
| "loss": 0.0278, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 5.609195402298851, | |
| "grad_norm": 0.5285075902938843, | |
| "learning_rate": 0.00011180438458789304, | |
| "loss": 0.0348, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 5.624521072796935, | |
| "grad_norm": 0.4877240061759949, | |
| "learning_rate": 0.00011139914098905406, | |
| "loss": 0.0386, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 5.639846743295019, | |
| "grad_norm": 0.5512449145317078, | |
| "learning_rate": 0.00011099370763670523, | |
| "loss": 0.0297, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 5.655172413793103, | |
| "grad_norm": 0.5295383334159851, | |
| "learning_rate": 0.00011058809127981134, | |
| "loss": 0.0344, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 5.670498084291188, | |
| "grad_norm": 0.5817351341247559, | |
| "learning_rate": 0.00011018229867038356, | |
| "loss": 0.0363, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.685823754789272, | |
| "grad_norm": 0.3530018627643585, | |
| "learning_rate": 0.00010977633656336706, | |
| "loss": 0.0212, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 5.7011494252873565, | |
| "grad_norm": 2.2889881134033203, | |
| "learning_rate": 0.00010937021171652841, | |
| "loss": 0.0352, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 5.716475095785441, | |
| "grad_norm": 0.846163809299469, | |
| "learning_rate": 0.00010896393089034336, | |
| "loss": 0.0477, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 5.731800766283525, | |
| "grad_norm": 0.31894299387931824, | |
| "learning_rate": 0.00010855750084788398, | |
| "loss": 0.0216, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 5.731800766283525, | |
| "eval_loss": 2.4762635231018066, | |
| "eval_runtime": 10.4616, | |
| "eval_samples_per_second": 9.559, | |
| "eval_steps_per_second": 4.779, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 5.747126436781609, | |
| "grad_norm": 0.6521170139312744, | |
| "learning_rate": 0.00010815092835470633, | |
| "loss": 0.0268, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 5.762452107279693, | |
| "grad_norm": 0.2925560772418976, | |
| "learning_rate": 0.00010774422017873771, | |
| "loss": 0.0223, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 5.777777777777778, | |
| "grad_norm": 0.7669603824615479, | |
| "learning_rate": 0.00010733738309016401, | |
| "loss": 0.027, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 5.793103448275862, | |
| "grad_norm": 0.30490854382514954, | |
| "learning_rate": 0.00010693042386131713, | |
| "loss": 0.02, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 5.8084291187739465, | |
| "grad_norm": 0.456485390663147, | |
| "learning_rate": 0.00010652334926656209, | |
| "loss": 0.0278, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 5.823754789272031, | |
| "grad_norm": 0.5804373621940613, | |
| "learning_rate": 0.00010611616608218429, | |
| "loss": 0.0347, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.8390804597701145, | |
| "grad_norm": 1.551376461982727, | |
| "learning_rate": 0.00010570888108627681, | |
| "loss": 0.0274, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 5.854406130268199, | |
| "grad_norm": 0.7403205037117004, | |
| "learning_rate": 0.00010530150105862748, | |
| "loss": 0.0285, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 5.869731800766283, | |
| "grad_norm": 0.7229623794555664, | |
| "learning_rate": 0.00010489403278060613, | |
| "loss": 0.0391, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 5.885057471264368, | |
| "grad_norm": 0.3897419571876526, | |
| "learning_rate": 0.00010448648303505151, | |
| "loss": 0.0231, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 5.900383141762452, | |
| "grad_norm": 0.5959421396255493, | |
| "learning_rate": 0.00010407885860615859, | |
| "loss": 0.0309, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 5.915708812260537, | |
| "grad_norm": 0.7538139224052429, | |
| "learning_rate": 0.00010367116627936548, | |
| "loss": 0.0306, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 5.931034482758621, | |
| "grad_norm": 0.46324053406715393, | |
| "learning_rate": 0.00010326341284124061, | |
| "loss": 0.0293, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 5.946360153256705, | |
| "grad_norm": 1.4018464088439941, | |
| "learning_rate": 0.00010285560507936961, | |
| "loss": 0.0393, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 5.961685823754789, | |
| "grad_norm": 0.5677470564842224, | |
| "learning_rate": 0.00010244774978224254, | |
| "loss": 0.0361, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 5.977011494252873, | |
| "grad_norm": 0.35945063829421997, | |
| "learning_rate": 0.00010203985373914056, | |
| "loss": 0.0206, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.992337164750958, | |
| "grad_norm": 0.35713624954223633, | |
| "learning_rate": 0.0001016319237400232, | |
| "loss": 0.0272, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 5.992337164750958, | |
| "eval_loss": 2.511009454727173, | |
| "eval_runtime": 10.521, | |
| "eval_samples_per_second": 9.505, | |
| "eval_steps_per_second": 4.752, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 6.003831417624521, | |
| "grad_norm": 0.6757388114929199, | |
| "learning_rate": 0.00010122396657541522, | |
| "loss": 0.035, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 6.019157088122605, | |
| "grad_norm": 0.3791247010231018, | |
| "learning_rate": 0.0001008159890362936, | |
| "loss": 0.0174, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 6.0344827586206895, | |
| "grad_norm": 0.19176137447357178, | |
| "learning_rate": 0.00010040799791397444, | |
| "loss": 0.0146, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 6.049808429118774, | |
| "grad_norm": 0.16038718819618225, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0118, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 6.065134099616858, | |
| "grad_norm": 0.14217466115951538, | |
| "learning_rate": 9.95920020860256e-05, | |
| "loss": 0.009, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 6.080459770114943, | |
| "grad_norm": 0.19670097529888153, | |
| "learning_rate": 9.918401096370644e-05, | |
| "loss": 0.0134, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 6.095785440613027, | |
| "grad_norm": 0.7063495516777039, | |
| "learning_rate": 9.877603342458483e-05, | |
| "loss": 0.0186, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 6.111111111111111, | |
| "grad_norm": 0.27073654532432556, | |
| "learning_rate": 9.836807625997683e-05, | |
| "loss": 0.0123, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 6.126436781609195, | |
| "grad_norm": 0.34357860684394836, | |
| "learning_rate": 9.79601462608595e-05, | |
| "loss": 0.0224, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.14176245210728, | |
| "grad_norm": 1.0311784744262695, | |
| "learning_rate": 9.755225021775749e-05, | |
| "loss": 0.0122, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 6.157088122605364, | |
| "grad_norm": 0.12156683206558228, | |
| "learning_rate": 9.71443949206304e-05, | |
| "loss": 0.011, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 6.172413793103448, | |
| "grad_norm": 0.15306659042835236, | |
| "learning_rate": 9.67365871587594e-05, | |
| "loss": 0.0101, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 6.187739463601533, | |
| "grad_norm": 0.40619829297065735, | |
| "learning_rate": 9.632883372063457e-05, | |
| "loss": 0.0124, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 6.203065134099617, | |
| "grad_norm": 0.2220255583524704, | |
| "learning_rate": 9.592114139384145e-05, | |
| "loss": 0.0115, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 6.218390804597701, | |
| "grad_norm": 0.36143144965171814, | |
| "learning_rate": 9.551351696494854e-05, | |
| "loss": 0.0143, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 6.233716475095785, | |
| "grad_norm": 0.19601793587207794, | |
| "learning_rate": 9.51059672193939e-05, | |
| "loss": 0.0121, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 6.24904214559387, | |
| "grad_norm": 0.17943957448005676, | |
| "learning_rate": 9.469849894137253e-05, | |
| "loss": 0.0117, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 6.24904214559387, | |
| "eval_loss": 2.7329955101013184, | |
| "eval_runtime": 10.5244, | |
| "eval_samples_per_second": 9.502, | |
| "eval_steps_per_second": 4.751, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 6.264367816091954, | |
| "grad_norm": 0.19360607862472534, | |
| "learning_rate": 9.42911189137232e-05, | |
| "loss": 0.0095, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 6.2796934865900385, | |
| "grad_norm": 0.24287296831607819, | |
| "learning_rate": 9.388383391781575e-05, | |
| "loss": 0.0116, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.295019157088123, | |
| "grad_norm": 0.554787814617157, | |
| "learning_rate": 9.347665073343794e-05, | |
| "loss": 0.0138, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 6.310344827586207, | |
| "grad_norm": 0.23142507672309875, | |
| "learning_rate": 9.306957613868292e-05, | |
| "loss": 0.0131, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 6.325670498084291, | |
| "grad_norm": 0.2346455603837967, | |
| "learning_rate": 9.266261690983602e-05, | |
| "loss": 0.011, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 6.340996168582375, | |
| "grad_norm": 0.8730548620223999, | |
| "learning_rate": 9.225577982126234e-05, | |
| "loss": 0.0151, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 6.35632183908046, | |
| "grad_norm": 0.3552612364292145, | |
| "learning_rate": 9.184907164529368e-05, | |
| "loss": 0.0232, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 6.371647509578544, | |
| "grad_norm": 0.22842758893966675, | |
| "learning_rate": 9.144249915211605e-05, | |
| "loss": 0.0153, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 6.3869731800766285, | |
| "grad_norm": 0.20680157840251923, | |
| "learning_rate": 9.103606910965666e-05, | |
| "loss": 0.0128, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 6.402298850574713, | |
| "grad_norm": 0.4528963565826416, | |
| "learning_rate": 9.062978828347161e-05, | |
| "loss": 0.0222, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 6.417624521072797, | |
| "grad_norm": 0.298604816198349, | |
| "learning_rate": 9.022366343663298e-05, | |
| "loss": 0.0168, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 6.432950191570881, | |
| "grad_norm": 0.11246322840452194, | |
| "learning_rate": 8.981770132961649e-05, | |
| "loss": 0.0089, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.448275862068965, | |
| "grad_norm": 0.2391061782836914, | |
| "learning_rate": 8.94119087201887e-05, | |
| "loss": 0.0105, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 6.46360153256705, | |
| "grad_norm": 0.10826307535171509, | |
| "learning_rate": 8.900629236329482e-05, | |
| "loss": 0.0089, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 6.478927203065134, | |
| "grad_norm": 0.18837091326713562, | |
| "learning_rate": 8.860085901094595e-05, | |
| "loss": 0.0117, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 6.494252873563219, | |
| "grad_norm": 0.24223893880844116, | |
| "learning_rate": 8.819561541210698e-05, | |
| "loss": 0.0109, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 6.509578544061303, | |
| "grad_norm": 0.38215088844299316, | |
| "learning_rate": 8.779056831258402e-05, | |
| "loss": 0.0115, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 6.509578544061303, | |
| "eval_loss": 2.640347480773926, | |
| "eval_runtime": 10.5535, | |
| "eval_samples_per_second": 9.475, | |
| "eval_steps_per_second": 4.738, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 6.5249042145593865, | |
| "grad_norm": 0.4854836165904999, | |
| "learning_rate": 8.738572445491226e-05, | |
| "loss": 0.0168, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 6.540229885057471, | |
| "grad_norm": 0.20515725016593933, | |
| "learning_rate": 8.698109057824354e-05, | |
| "loss": 0.0128, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 6.555555555555555, | |
| "grad_norm": 0.21756961941719055, | |
| "learning_rate": 8.657667341823448e-05, | |
| "loss": 0.0114, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 6.57088122605364, | |
| "grad_norm": 0.18275758624076843, | |
| "learning_rate": 8.617247970693398e-05, | |
| "loss": 0.0105, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 6.586206896551724, | |
| "grad_norm": 0.175423264503479, | |
| "learning_rate": 8.57685161726715e-05, | |
| "loss": 0.0102, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.601532567049809, | |
| "grad_norm": 0.3893040418624878, | |
| "learning_rate": 8.53647895399448e-05, | |
| "loss": 0.0151, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 6.616858237547893, | |
| "grad_norm": 0.3841419816017151, | |
| "learning_rate": 8.496130652930818e-05, | |
| "loss": 0.0135, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 6.6321839080459775, | |
| "grad_norm": 0.1184447631239891, | |
| "learning_rate": 8.455807385726046e-05, | |
| "loss": 0.0096, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 6.647509578544061, | |
| "grad_norm": 0.11839904636144638, | |
| "learning_rate": 8.415509823613331e-05, | |
| "loss": 0.0087, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 6.662835249042145, | |
| "grad_norm": 0.27116042375564575, | |
| "learning_rate": 8.375238637397942e-05, | |
| "loss": 0.0134, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 6.67816091954023, | |
| "grad_norm": 0.1837141215801239, | |
| "learning_rate": 8.334994497446091e-05, | |
| "loss": 0.0102, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 6.693486590038314, | |
| "grad_norm": 0.14119590818881989, | |
| "learning_rate": 8.294778073673762e-05, | |
| "loss": 0.0103, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 6.708812260536399, | |
| "grad_norm": 0.38409751653671265, | |
| "learning_rate": 8.254590035535579e-05, | |
| "loss": 0.0146, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 6.724137931034483, | |
| "grad_norm": 0.1519305408000946, | |
| "learning_rate": 8.214431052013634e-05, | |
| "loss": 0.0097, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 6.739463601532567, | |
| "grad_norm": 0.2955567240715027, | |
| "learning_rate": 8.174301791606385e-05, | |
| "loss": 0.0114, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.754789272030651, | |
| "grad_norm": 0.2837064862251282, | |
| "learning_rate": 8.134202922317495e-05, | |
| "loss": 0.0134, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 6.7701149425287355, | |
| "grad_norm": 0.13082526624202728, | |
| "learning_rate": 8.094135111644742e-05, | |
| "loss": 0.0092, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 6.7701149425287355, | |
| "eval_loss": 2.7746777534484863, | |
| "eval_runtime": 10.5408, | |
| "eval_samples_per_second": 9.487, | |
| "eval_steps_per_second": 4.743, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 6.78544061302682, | |
| "grad_norm": 0.5769606232643127, | |
| "learning_rate": 8.054099026568874e-05, | |
| "loss": 0.0147, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 6.800766283524904, | |
| "grad_norm": 0.1398877650499344, | |
| "learning_rate": 8.014095333542548e-05, | |
| "loss": 0.0098, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 6.816091954022989, | |
| "grad_norm": 0.16053611040115356, | |
| "learning_rate": 7.974124698479192e-05, | |
| "loss": 0.0074, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 6.831417624521073, | |
| "grad_norm": 0.27454668283462524, | |
| "learning_rate": 7.934187786741956e-05, | |
| "loss": 0.0103, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 6.846743295019158, | |
| "grad_norm": 0.36763104796409607, | |
| "learning_rate": 7.894285263132612e-05, | |
| "loss": 0.0153, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 6.862068965517241, | |
| "grad_norm": 0.21019311249256134, | |
| "learning_rate": 7.854417791880507e-05, | |
| "loss": 0.013, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 6.8773946360153255, | |
| "grad_norm": 0.2829742133617401, | |
| "learning_rate": 7.814586036631483e-05, | |
| "loss": 0.0118, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 6.89272030651341, | |
| "grad_norm": 0.30828389525413513, | |
| "learning_rate": 7.774790660436858e-05, | |
| "loss": 0.011, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.908045977011494, | |
| "grad_norm": 0.6878758072853088, | |
| "learning_rate": 7.735032325742355e-05, | |
| "loss": 0.0293, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 6.923371647509579, | |
| "grad_norm": 0.15684568881988525, | |
| "learning_rate": 7.695311694377115e-05, | |
| "loss": 0.01, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 6.938697318007663, | |
| "grad_norm": 0.32623958587646484, | |
| "learning_rate": 7.655629427542635e-05, | |
| "loss": 0.0117, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 6.954022988505747, | |
| "grad_norm": 0.10675598680973053, | |
| "learning_rate": 7.615986185801807e-05, | |
| "loss": 0.0077, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 6.969348659003831, | |
| "grad_norm": 0.3139125406742096, | |
| "learning_rate": 7.576382629067877e-05, | |
| "loss": 0.0134, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 6.984674329501916, | |
| "grad_norm": 0.37668049335479736, | |
| "learning_rate": 7.536819416593504e-05, | |
| "loss": 0.011, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.15798693895339966, | |
| "learning_rate": 7.497297206959746e-05, | |
| "loss": 0.0093, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 7.011494252873563, | |
| "grad_norm": 0.3846645653247833, | |
| "learning_rate": 7.457816658065134e-05, | |
| "loss": 0.0108, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 7.026819923371647, | |
| "grad_norm": 0.05968603119254112, | |
| "learning_rate": 7.41837842711468e-05, | |
| "loss": 0.0064, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 7.026819923371647, | |
| "eval_loss": 2.7342193126678467, | |
| "eval_runtime": 10.5281, | |
| "eval_samples_per_second": 9.498, | |
| "eval_steps_per_second": 4.749, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 7.042145593869732, | |
| "grad_norm": 0.05475788936018944, | |
| "learning_rate": 7.378983170608982e-05, | |
| "loss": 0.0054, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 7.057471264367816, | |
| "grad_norm": 0.055521685630083084, | |
| "learning_rate": 7.339631544333249e-05, | |
| "loss": 0.0057, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 7.0727969348659006, | |
| "grad_norm": 0.06325386464595795, | |
| "learning_rate": 7.300324203346431e-05, | |
| "loss": 0.0061, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 7.088122605363985, | |
| "grad_norm": 0.5059542655944824, | |
| "learning_rate": 7.261061801970277e-05, | |
| "loss": 0.0079, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 7.103448275862069, | |
| "grad_norm": 0.06388293951749802, | |
| "learning_rate": 7.221844993778464e-05, | |
| "loss": 0.0056, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 7.118773946360153, | |
| "grad_norm": 0.07516956329345703, | |
| "learning_rate": 7.182674431585704e-05, | |
| "loss": 0.006, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 7.134099616858237, | |
| "grad_norm": 0.14318601787090302, | |
| "learning_rate": 7.143550767436894e-05, | |
| "loss": 0.0067, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 7.149425287356322, | |
| "grad_norm": 0.1426093429327011, | |
| "learning_rate": 7.104474652596245e-05, | |
| "loss": 0.0079, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 7.164750957854406, | |
| "grad_norm": 0.05885975807905197, | |
| "learning_rate": 7.065446737536456e-05, | |
| "loss": 0.0055, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 7.180076628352491, | |
| "grad_norm": 0.06351395696401596, | |
| "learning_rate": 7.026467671927863e-05, | |
| "loss": 0.0059, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 7.195402298850575, | |
| "grad_norm": 0.0676102414727211, | |
| "learning_rate": 6.98753810462766e-05, | |
| "loss": 0.0062, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.210727969348659, | |
| "grad_norm": 0.07731365412473679, | |
| "learning_rate": 6.948658683669056e-05, | |
| "loss": 0.0058, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 7.226053639846743, | |
| "grad_norm": 0.06487540900707245, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0061, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 7.241379310344827, | |
| "grad_norm": 0.09343966096639633, | |
| "learning_rate": 6.871052868725012e-05, | |
| "loss": 0.0062, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 7.256704980842912, | |
| "grad_norm": 0.1045990064740181, | |
| "learning_rate": 6.832327766589177e-05, | |
| "loss": 0.0063, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 7.272030651340996, | |
| "grad_norm": 0.05801545828580856, | |
| "learning_rate": 6.793655394472644e-05, | |
| "loss": 0.0057, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 7.287356321839081, | |
| "grad_norm": 0.06868793070316315, | |
| "learning_rate": 6.755036396127296e-05, | |
| "loss": 0.0059, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 7.287356321839081, | |
| "eval_loss": 2.8930225372314453, | |
| "eval_runtime": 10.5758, | |
| "eval_samples_per_second": 9.456, | |
| "eval_steps_per_second": 4.728, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 7.302681992337165, | |
| "grad_norm": 0.08218348026275635, | |
| "learning_rate": 6.716471414416519e-05, | |
| "loss": 0.0075, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 7.3180076628352495, | |
| "grad_norm": 0.08141635358333588, | |
| "learning_rate": 6.677961091304535e-05, | |
| "loss": 0.0061, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 7.333333333333333, | |
| "grad_norm": 0.05970093235373497, | |
| "learning_rate": 6.639506067845697e-05, | |
| "loss": 0.006, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 7.3486590038314175, | |
| "grad_norm": 0.07674306631088257, | |
| "learning_rate": 6.601106984173835e-05, | |
| "loss": 0.0058, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.363984674329502, | |
| "grad_norm": 0.07168275862932205, | |
| "learning_rate": 6.562764479491565e-05, | |
| "loss": 0.0054, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 7.379310344827586, | |
| "grad_norm": 0.06897211819887161, | |
| "learning_rate": 6.524479192059698e-05, | |
| "loss": 0.0059, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 7.394636015325671, | |
| "grad_norm": 0.5173123478889465, | |
| "learning_rate": 6.486251759186572e-05, | |
| "loss": 0.008, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 7.409961685823755, | |
| "grad_norm": 0.05815713480114937, | |
| "learning_rate": 6.448082817217471e-05, | |
| "loss": 0.0052, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 7.425287356321839, | |
| "grad_norm": 0.08304629474878311, | |
| "learning_rate": 6.409973001524012e-05, | |
| "loss": 0.0058, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 7.440613026819923, | |
| "grad_norm": 0.10966533422470093, | |
| "learning_rate": 6.371922946493591e-05, | |
| "loss": 0.0058, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 7.4559386973180075, | |
| "grad_norm": 0.06352514773607254, | |
| "learning_rate": 6.333933285518796e-05, | |
| "loss": 0.0054, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 7.471264367816092, | |
| "grad_norm": 0.16141043603420258, | |
| "learning_rate": 6.29600465098689e-05, | |
| "loss": 0.0106, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 7.486590038314176, | |
| "grad_norm": 0.06440207362174988, | |
| "learning_rate": 6.258137674269261e-05, | |
| "loss": 0.006, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 7.501915708812261, | |
| "grad_norm": 0.08629340678453445, | |
| "learning_rate": 6.220332985710936e-05, | |
| "loss": 0.0073, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 7.517241379310345, | |
| "grad_norm": 0.06371556222438812, | |
| "learning_rate": 6.182591214620057e-05, | |
| "loss": 0.006, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 7.53256704980843, | |
| "grad_norm": 0.08433310687541962, | |
| "learning_rate": 6.144912989257441e-05, | |
| "loss": 0.006, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 7.547892720306513, | |
| "grad_norm": 0.08213558048009872, | |
| "learning_rate": 6.107298936826086e-05, | |
| "loss": 0.0065, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 7.547892720306513, | |
| "eval_loss": 2.91325306892395, | |
| "eval_runtime": 10.6133, | |
| "eval_samples_per_second": 9.422, | |
| "eval_steps_per_second": 4.711, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 7.563218390804598, | |
| "grad_norm": 0.059887565672397614, | |
| "learning_rate": 6.069749683460765e-05, | |
| "loss": 0.0055, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 7.578544061302682, | |
| "grad_norm": 0.06606566160917282, | |
| "learning_rate": 6.0322658542175736e-05, | |
| "loss": 0.0045, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 7.593869731800766, | |
| "grad_norm": 0.076997309923172, | |
| "learning_rate": 5.994848073063551e-05, | |
| "loss": 0.0059, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 7.609195402298851, | |
| "grad_norm": 0.0730021744966507, | |
| "learning_rate": 5.957496962866262e-05, | |
| "loss": 0.0053, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 7.624521072796935, | |
| "grad_norm": 0.05936294421553612, | |
| "learning_rate": 5.920213145383466e-05, | |
| "loss": 0.0054, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 7.639846743295019, | |
| "grad_norm": 0.14003659784793854, | |
| "learning_rate": 5.8829972412527327e-05, | |
| "loss": 0.0073, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 7.655172413793103, | |
| "grad_norm": 0.05907728150486946, | |
| "learning_rate": 5.845849869981137e-05, | |
| "loss": 0.0042, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.670498084291188, | |
| "grad_norm": 0.057687729597091675, | |
| "learning_rate": 5.808771649934923e-05, | |
| "loss": 0.0052, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 7.685823754789272, | |
| "grad_norm": 0.09928648918867111, | |
| "learning_rate": 5.7717631983292375e-05, | |
| "loss": 0.0055, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 7.7011494252873565, | |
| "grad_norm": 0.07954944670200348, | |
| "learning_rate": 5.73482513121783e-05, | |
| "loss": 0.0057, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 7.716475095785441, | |
| "grad_norm": 0.06073677912354469, | |
| "learning_rate": 5.6979580634828125e-05, | |
| "loss": 0.0059, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 7.731800766283525, | |
| "grad_norm": 0.06618310511112213, | |
| "learning_rate": 5.6611626088244194e-05, | |
| "loss": 0.0056, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 7.747126436781609, | |
| "grad_norm": 0.06377172470092773, | |
| "learning_rate": 5.624439379750794e-05, | |
| "loss": 0.0053, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 7.762452107279693, | |
| "grad_norm": 0.06222354248166084, | |
| "learning_rate": 5.5877889875677845e-05, | |
| "loss": 0.0054, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 7.777777777777778, | |
| "grad_norm": 0.06755752861499786, | |
| "learning_rate": 5.551212042368792e-05, | |
| "loss": 0.0069, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 7.793103448275862, | |
| "grad_norm": 0.23886863887310028, | |
| "learning_rate": 5.514709153024571e-05, | |
| "loss": 0.007, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 7.8084291187739465, | |
| "grad_norm": 0.06176340579986572, | |
| "learning_rate": 5.478280927173145e-05, | |
| "loss": 0.0059, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.8084291187739465, | |
| "eval_loss": 2.921626091003418, | |
| "eval_runtime": 10.5435, | |
| "eval_samples_per_second": 9.485, | |
| "eval_steps_per_second": 4.742, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.823754789272031, | |
| "grad_norm": 0.056606221944093704, | |
| "learning_rate": 5.4419279712096437e-05, | |
| "loss": 0.0049, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 7.8390804597701145, | |
| "grad_norm": 0.06514956057071686, | |
| "learning_rate": 5.405650890276255e-05, | |
| "loss": 0.0061, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 7.854406130268199, | |
| "grad_norm": 0.05932604894042015, | |
| "learning_rate": 5.3694502882521125e-05, | |
| "loss": 0.0058, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 7.869731800766283, | |
| "grad_norm": 0.06986385583877563, | |
| "learning_rate": 5.333326767743263e-05, | |
| "loss": 0.0048, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 7.885057471264368, | |
| "grad_norm": 0.07194341719150543, | |
| "learning_rate": 5.297280930072632e-05, | |
| "loss": 0.0065, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 7.900383141762452, | |
| "grad_norm": 0.12007016688585281, | |
| "learning_rate": 5.261313375270014e-05, | |
| "loss": 0.0068, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 7.915708812260537, | |
| "grad_norm": 0.05479056015610695, | |
| "learning_rate": 5.2254247020620814e-05, | |
| "loss": 0.0052, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 7.931034482758621, | |
| "grad_norm": 0.18069668114185333, | |
| "learning_rate": 5.189615507862422e-05, | |
| "loss": 0.0077, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 7.946360153256705, | |
| "grad_norm": 0.08876926451921463, | |
| "learning_rate": 5.153886388761586e-05, | |
| "loss": 0.0063, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 7.961685823754789, | |
| "grad_norm": 0.05993456766009331, | |
| "learning_rate": 5.11823793951719e-05, | |
| "loss": 0.0048, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.977011494252873, | |
| "grad_norm": 0.05695677176117897, | |
| "learning_rate": 5.082670753543961e-05, | |
| "loss": 0.0049, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 7.992337164750958, | |
| "grad_norm": 0.0639839619398117, | |
| "learning_rate": 5.047185422903928e-05, | |
| "loss": 0.0054, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 8.007662835249041, | |
| "grad_norm": 0.1566697508096695, | |
| "learning_rate": 5.011782538296512e-05, | |
| "loss": 0.0103, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 8.022988505747126, | |
| "grad_norm": 0.0462418757379055, | |
| "learning_rate": 4.976462689048717e-05, | |
| "loss": 0.0043, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 8.03831417624521, | |
| "grad_norm": 0.046641357243061066, | |
| "learning_rate": 4.9412264631053216e-05, | |
| "loss": 0.0048, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 8.053639846743295, | |
| "grad_norm": 0.04404853284358978, | |
| "learning_rate": 4.9060744470190676e-05, | |
| "loss": 0.0044, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 8.068965517241379, | |
| "grad_norm": 0.053229521960020065, | |
| "learning_rate": 4.87100722594094e-05, | |
| "loss": 0.0058, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 8.068965517241379, | |
| "eval_loss": 2.9435019493103027, | |
| "eval_runtime": 10.5293, | |
| "eval_samples_per_second": 9.497, | |
| "eval_steps_per_second": 4.749, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 8.084291187739463, | |
| "grad_norm": 0.039271771907806396, | |
| "learning_rate": 4.836025383610382e-05, | |
| "loss": 0.0035, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 8.099616858237548, | |
| "grad_norm": 0.0491085946559906, | |
| "learning_rate": 4.801129502345605e-05, | |
| "loss": 0.0048, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 8.114942528735632, | |
| "grad_norm": 0.03886023536324501, | |
| "learning_rate": 4.7663201630338816e-05, | |
| "loss": 0.004, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 8.130268199233717, | |
| "grad_norm": 0.04504215344786644, | |
| "learning_rate": 4.7315979451218864e-05, | |
| "loss": 0.0047, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 8.145593869731801, | |
| "grad_norm": 0.05867081508040428, | |
| "learning_rate": 4.696963426606041e-05, | |
| "loss": 0.0058, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 8.160919540229886, | |
| "grad_norm": 0.0445120669901371, | |
| "learning_rate": 4.6624171840229e-05, | |
| "loss": 0.0043, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 8.17624521072797, | |
| "grad_norm": 0.05101229250431061, | |
| "learning_rate": 4.6279597924395436e-05, | |
| "loss": 0.0044, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 8.191570881226054, | |
| "grad_norm": 0.04617276415228844, | |
| "learning_rate": 4.593591825444028e-05, | |
| "loss": 0.0045, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 8.206896551724139, | |
| "grad_norm": 0.048301588743925095, | |
| "learning_rate": 4.559313855135795e-05, | |
| "loss": 0.0046, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 8.222222222222221, | |
| "grad_norm": 0.05069313570857048, | |
| "learning_rate": 4.5251264521162005e-05, | |
| "loss": 0.005, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 8.237547892720306, | |
| "grad_norm": 0.04811912775039673, | |
| "learning_rate": 4.491030185478976e-05, | |
| "loss": 0.0045, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 8.25287356321839, | |
| "grad_norm": 0.04650574177503586, | |
| "learning_rate": 4.457025622800771e-05, | |
| "loss": 0.0049, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 8.268199233716475, | |
| "grad_norm": 0.038902636617422104, | |
| "learning_rate": 4.423113330131707e-05, | |
| "loss": 0.0037, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 8.28352490421456, | |
| "grad_norm": 0.0576075054705143, | |
| "learning_rate": 4.389293871985949e-05, | |
| "loss": 0.0066, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 8.298850574712644, | |
| "grad_norm": 0.051424864679574966, | |
| "learning_rate": 4.355567811332311e-05, | |
| "loss": 0.0053, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 8.314176245210728, | |
| "grad_norm": 0.040568236261606216, | |
| "learning_rate": 4.3219357095848836e-05, | |
| "loss": 0.0038, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 8.329501915708812, | |
| "grad_norm": 0.051232922822237015, | |
| "learning_rate": 4.2883981265936876e-05, | |
| "loss": 0.0046, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 8.329501915708812, | |
| "eval_loss": 3.006831169128418, | |
| "eval_runtime": 10.5212, | |
| "eval_samples_per_second": 9.505, | |
| "eval_steps_per_second": 4.752, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 8.344827586206897, | |
| "grad_norm": 0.04653798043727875, | |
| "learning_rate": 4.25495562063537e-05, | |
| "loss": 0.0048, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 8.360153256704981, | |
| "grad_norm": 0.04423636198043823, | |
| "learning_rate": 4.2216087484038714e-05, | |
| "loss": 0.0038, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 8.375478927203066, | |
| "grad_norm": 0.04573935642838478, | |
| "learning_rate": 4.188358065001215e-05, | |
| "loss": 0.0045, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 8.39080459770115, | |
| "grad_norm": 0.044406238943338394, | |
| "learning_rate": 4.155204123928205e-05, | |
| "loss": 0.0041, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 8.406130268199234, | |
| "grad_norm": 0.044500816613435745, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0044, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 8.421455938697317, | |
| "grad_norm": 0.039383914321660995, | |
| "learning_rate": 4.089188674713236e-05, | |
| "loss": 0.0038, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 8.436781609195402, | |
| "grad_norm": 0.04521704837679863, | |
| "learning_rate": 4.056328265484184e-05, | |
| "loss": 0.0046, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 8.452107279693486, | |
| "grad_norm": 0.047671083360910416, | |
| "learning_rate": 4.023566796392313e-05, | |
| "loss": 0.0042, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 8.46743295019157, | |
| "grad_norm": 0.04466583952307701, | |
| "learning_rate": 3.990904812794834e-05, | |
| "loss": 0.0043, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 8.482758620689655, | |
| "grad_norm": 0.05882612615823746, | |
| "learning_rate": 3.958342858392893e-05, | |
| "loss": 0.0059, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 8.49808429118774, | |
| "grad_norm": 0.048001233488321304, | |
| "learning_rate": 3.9258814752225284e-05, | |
| "loss": 0.0042, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 8.513409961685824, | |
| "grad_norm": 0.06287714838981628, | |
| "learning_rate": 3.893521203645618e-05, | |
| "loss": 0.0053, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 8.528735632183908, | |
| "grad_norm": 0.047715529799461365, | |
| "learning_rate": 3.8612625823409366e-05, | |
| "loss": 0.0041, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 8.544061302681992, | |
| "grad_norm": 0.05052071437239647, | |
| "learning_rate": 3.829106148295126e-05, | |
| "loss": 0.0046, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 8.559386973180077, | |
| "grad_norm": 0.24502001702785492, | |
| "learning_rate": 3.797052436793814e-05, | |
| "loss": 0.0066, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 8.574712643678161, | |
| "grad_norm": 0.046199604868888855, | |
| "learning_rate": 3.7651019814126654e-05, | |
| "loss": 0.0045, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.590038314176246, | |
| "grad_norm": 0.049519941210746765, | |
| "learning_rate": 3.7332553140085155e-05, | |
| "loss": 0.0051, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 8.590038314176246, | |
| "eval_loss": 3.0260815620422363, | |
| "eval_runtime": 10.5212, | |
| "eval_samples_per_second": 9.505, | |
| "eval_steps_per_second": 4.752, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 8.60536398467433, | |
| "grad_norm": 0.053081195801496506, | |
| "learning_rate": 3.701512964710513e-05, | |
| "loss": 0.0046, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 8.620689655172415, | |
| "grad_norm": 0.041760966181755066, | |
| "learning_rate": 3.669875461911297e-05, | |
| "loss": 0.0036, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 8.636015325670499, | |
| "grad_norm": 0.05594363436102867, | |
| "learning_rate": 3.638343332258203e-05, | |
| "loss": 0.0052, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 8.651340996168582, | |
| "grad_norm": 0.04741170257329941, | |
| "learning_rate": 3.606917100644488e-05, | |
| "loss": 0.0039, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 8.666666666666666, | |
| "grad_norm": 0.1333678662776947, | |
| "learning_rate": 3.5755972902005987e-05, | |
| "loss": 0.0048, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 8.68199233716475, | |
| "grad_norm": 0.060406796634197235, | |
| "learning_rate": 3.544384422285477e-05, | |
| "loss": 0.0056, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 8.697318007662835, | |
| "grad_norm": 0.04437935724854469, | |
| "learning_rate": 3.513279016477844e-05, | |
| "loss": 0.004, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 8.71264367816092, | |
| "grad_norm": 0.04306851327419281, | |
| "learning_rate": 3.4822815905675954e-05, | |
| "loss": 0.0043, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 8.727969348659004, | |
| "grad_norm": 0.049886684864759445, | |
| "learning_rate": 3.45139266054715e-05, | |
| "loss": 0.0054, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 8.743295019157088, | |
| "grad_norm": 0.039504941552877426, | |
| "learning_rate": 3.4206127406028745e-05, | |
| "loss": 0.0036, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 8.758620689655173, | |
| "grad_norm": 0.05250853672623634, | |
| "learning_rate": 3.389942343106522e-05, | |
| "loss": 0.0055, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 8.773946360153257, | |
| "grad_norm": 0.06467723846435547, | |
| "learning_rate": 3.359381978606701e-05, | |
| "loss": 0.0046, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 8.789272030651341, | |
| "grad_norm": 0.04862450435757637, | |
| "learning_rate": 3.328932155820377e-05, | |
| "loss": 0.0045, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 8.804597701149426, | |
| "grad_norm": 0.04701303318142891, | |
| "learning_rate": 3.298593381624406e-05, | |
| "loss": 0.0045, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 8.81992337164751, | |
| "grad_norm": 0.04837154597043991, | |
| "learning_rate": 3.2683661610470963e-05, | |
| "loss": 0.0039, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 8.835249042145595, | |
| "grad_norm": 0.04792990908026695, | |
| "learning_rate": 3.238250997259808e-05, | |
| "loss": 0.0041, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 8.850574712643677, | |
| "grad_norm": 0.04371470585465431, | |
| "learning_rate": 3.208248391568553e-05, | |
| "loss": 0.0044, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 8.850574712643677, | |
| "eval_loss": 3.0277657508850098, | |
| "eval_runtime": 10.5822, | |
| "eval_samples_per_second": 9.45, | |
| "eval_steps_per_second": 4.725, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 8.865900383141762, | |
| "grad_norm": 0.048086583614349365, | |
| "learning_rate": 3.178358843405684e-05, | |
| "loss": 0.0043, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 8.881226053639846, | |
| "grad_norm": 0.0496319979429245, | |
| "learning_rate": 3.1485828503215585e-05, | |
| "loss": 0.0047, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.89655172413793, | |
| "grad_norm": 0.05418609455227852, | |
| "learning_rate": 3.1189209079762607e-05, | |
| "loss": 0.0045, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 8.911877394636015, | |
| "grad_norm": 0.046972278505563736, | |
| "learning_rate": 3.089373510131354e-05, | |
| "loss": 0.0046, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 8.9272030651341, | |
| "grad_norm": 0.043504588305950165, | |
| "learning_rate": 3.0599411486416585e-05, | |
| "loss": 0.0039, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 8.942528735632184, | |
| "grad_norm": 0.05620258301496506, | |
| "learning_rate": 3.030624313447067e-05, | |
| "loss": 0.0048, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 8.957854406130268, | |
| "grad_norm": 0.05009399726986885, | |
| "learning_rate": 3.0014234925643837e-05, | |
| "loss": 0.0049, | |
| "step": 585 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 780, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 65, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.74949251811115e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |