| { | |
| "best_metric": 7.1964921951293945, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.05379597875058839, | |
| "eval_steps": 25, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00026897989375294196, | |
| "grad_norm": 14.062777519226074, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 9.9528, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00026897989375294196, | |
| "eval_loss": 10.383614540100098, | |
| "eval_runtime": 1.103, | |
| "eval_samples_per_second": 45.331, | |
| "eval_steps_per_second": 6.346, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005379597875058839, | |
| "grad_norm": 9.013472557067871, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 10.4374, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008069396812588259, | |
| "grad_norm": 9.113578796386719, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 10.5416, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010759195750117679, | |
| "grad_norm": 9.272452354431152, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 10.5582, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013448994687647099, | |
| "grad_norm": 9.502043724060059, | |
| "learning_rate": 0.00015, | |
| "loss": 10.4131, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016138793625176519, | |
| "grad_norm": 12.628140449523926, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 9.5481, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018828592562705937, | |
| "grad_norm": 10.771757125854492, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 9.7362, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0021518391500235357, | |
| "grad_norm": 8.7677640914917, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 9.394, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0024208190437764775, | |
| "grad_norm": 9.826272010803223, | |
| "learning_rate": 0.00027, | |
| "loss": 8.7301, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0026897989375294197, | |
| "grad_norm": 8.201698303222656, | |
| "learning_rate": 0.0003, | |
| "loss": 8.4353, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0029587788312823615, | |
| "grad_norm": 6.270658493041992, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 7.7853, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0032277587250353038, | |
| "grad_norm": 5.651599884033203, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 7.7574, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0034967386187882456, | |
| "grad_norm": 3.6305131912231445, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 7.9822, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0037657185125411874, | |
| "grad_norm": 3.2104008197784424, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 8.3468, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004034698406294129, | |
| "grad_norm": 2.4810068607330322, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 8.2438, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004303678300047071, | |
| "grad_norm": 2.427516460418701, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 8.4045, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004572658193800014, | |
| "grad_norm": 1.9261265993118286, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 7.9577, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004841638087552955, | |
| "grad_norm": 2.021862268447876, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 8.1164, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005110617981305897, | |
| "grad_norm": 2.315554141998291, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 8.1393, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0053795978750588395, | |
| "grad_norm": 2.343036651611328, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 7.8621, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005648577768811782, | |
| "grad_norm": 1.6685760021209717, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 7.6249, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005917557662564723, | |
| "grad_norm": 1.617172360420227, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 7.8443, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006186537556317665, | |
| "grad_norm": 1.611405611038208, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 7.1947, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0064555174500706075, | |
| "grad_norm": 1.3807909488677979, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 7.7691, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006724497343823549, | |
| "grad_norm": 1.8649704456329346, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 7.6449, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006724497343823549, | |
| "eval_loss": 7.789085865020752, | |
| "eval_runtime": 1.1023, | |
| "eval_samples_per_second": 45.359, | |
| "eval_steps_per_second": 6.35, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006993477237576491, | |
| "grad_norm": 1.826485276222229, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 7.775, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007262457131329433, | |
| "grad_norm": 2.0122640132904053, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 7.4112, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007531437025082375, | |
| "grad_norm": 1.474570870399475, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 7.605, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007800416918835317, | |
| "grad_norm": 1.2456080913543701, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 7.615, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008069396812588258, | |
| "grad_norm": 1.3614413738250732, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 7.1255, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0083383767063412, | |
| "grad_norm": 1.5178754329681396, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 7.3523, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008607356600094143, | |
| "grad_norm": 1.0982545614242554, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 7.2886, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008876336493847085, | |
| "grad_norm": 0.9949588775634766, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 7.705, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009145316387600027, | |
| "grad_norm": 1.0565680265426636, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 7.054, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00941429628135297, | |
| "grad_norm": 1.4660252332687378, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 6.5231, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00968327617510591, | |
| "grad_norm": 1.0093355178833008, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 7.4915, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009952256068858852, | |
| "grad_norm": 1.0597023963928223, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 7.5809, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010221235962611794, | |
| "grad_norm": 1.0300654172897339, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 7.4441, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010490215856364737, | |
| "grad_norm": 1.0486762523651123, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 6.7324, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010759195750117679, | |
| "grad_norm": 0.9966297149658203, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 7.7486, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011028175643870621, | |
| "grad_norm": 0.8546872735023499, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 6.9361, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011297155537623563, | |
| "grad_norm": 0.9719182252883911, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 7.2164, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011566135431376504, | |
| "grad_norm": 1.2323123216629028, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 6.7995, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011835115325129446, | |
| "grad_norm": 1.016748070716858, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 7.3677, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012104095218882388, | |
| "grad_norm": 0.9493099451065063, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 6.8809, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01237307511263533, | |
| "grad_norm": 0.6532073020935059, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 6.9965, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.012642055006388273, | |
| "grad_norm": 1.0315707921981812, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 7.3371, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.012911034900141215, | |
| "grad_norm": 0.867978036403656, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 7.2436, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013180014793894156, | |
| "grad_norm": 0.8053029775619507, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 6.8425, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013448994687647098, | |
| "grad_norm": 1.2040008306503296, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 6.9863, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013448994687647098, | |
| "eval_loss": 7.4686126708984375, | |
| "eval_runtime": 1.1025, | |
| "eval_samples_per_second": 45.352, | |
| "eval_steps_per_second": 6.349, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01371797458140004, | |
| "grad_norm": 2.073488235473633, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 6.6067, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.013986954475152982, | |
| "grad_norm": 1.6959115266799927, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 7.4615, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.014255934368905925, | |
| "grad_norm": 1.1312484741210938, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 7.562, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.014524914262658867, | |
| "grad_norm": 0.8906031847000122, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 7.8548, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.014793894156411809, | |
| "grad_norm": 1.1955941915512085, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 7.5388, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.01506287405016475, | |
| "grad_norm": 1.6056780815124512, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 6.7458, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.015331853943917692, | |
| "grad_norm": 0.9653465151786804, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 7.2338, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.015600833837670634, | |
| "grad_norm": 1.055378794670105, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 7.2497, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.015869813731423574, | |
| "grad_norm": 0.982029378414154, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 6.3055, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.016138793625176517, | |
| "grad_norm": 1.4051647186279297, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 6.7392, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01640777351892946, | |
| "grad_norm": 1.224535346031189, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 6.2815, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0166767534126824, | |
| "grad_norm": 0.9965676069259644, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 6.5987, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.016945733306435343, | |
| "grad_norm": 0.7063784599304199, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 6.5176, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.017214713200188286, | |
| "grad_norm": 1.3905584812164307, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 7.3527, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.017483693093941228, | |
| "grad_norm": 0.6794236898422241, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 7.1635, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.01775267298769417, | |
| "grad_norm": 0.85134357213974, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 6.9162, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.018021652881447112, | |
| "grad_norm": 1.1831365823745728, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 7.4826, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.018290632775200055, | |
| "grad_norm": 0.7540268301963806, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 7.5541, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.018559612668952997, | |
| "grad_norm": 0.8305040597915649, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 7.0236, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.01882859256270594, | |
| "grad_norm": 0.8232185244560242, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 7.256, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01909757245645888, | |
| "grad_norm": 0.8017435669898987, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 7.2468, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.01936655235021182, | |
| "grad_norm": 0.7299101948738098, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 6.8815, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.019635532243964762, | |
| "grad_norm": 0.9603165984153748, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 7.1806, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.019904512137717705, | |
| "grad_norm": 0.7412318587303162, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 6.8687, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.020173492031470647, | |
| "grad_norm": 1.5883235931396484, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 6.6477, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.020173492031470647, | |
| "eval_loss": 7.266612529754639, | |
| "eval_runtime": 1.1026, | |
| "eval_samples_per_second": 45.347, | |
| "eval_steps_per_second": 6.349, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02044247192522359, | |
| "grad_norm": 0.874472975730896, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 6.5988, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.02071145181897653, | |
| "grad_norm": 1.0724687576293945, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 7.0543, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.020980431712729473, | |
| "grad_norm": 0.7699567079544067, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 7.1625, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.021249411606482416, | |
| "grad_norm": 0.622986912727356, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 7.4872, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.021518391500235358, | |
| "grad_norm": 0.9322075843811035, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 7.0894, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0217873713939883, | |
| "grad_norm": 0.6225010752677917, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 6.9691, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.022056351287741242, | |
| "grad_norm": 0.9002844095230103, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 6.5822, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.022325331181494185, | |
| "grad_norm": 0.6348511576652527, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 6.8699, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.022594311075247127, | |
| "grad_norm": 0.5231301188468933, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 6.8725, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.022863290969000066, | |
| "grad_norm": 0.68709397315979, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 6.7312, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.023132270862753008, | |
| "grad_norm": 0.47030457854270935, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 6.7572, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.02340125075650595, | |
| "grad_norm": 0.7477748394012451, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 7.014, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.023670230650258892, | |
| "grad_norm": 0.9135372638702393, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 6.8656, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.023939210544011835, | |
| "grad_norm": 0.7729247212409973, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 6.8811, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.024208190437764777, | |
| "grad_norm": 0.8843768835067749, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 6.8623, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02447717033151772, | |
| "grad_norm": 0.5804451107978821, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 6.8921, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.02474615022527066, | |
| "grad_norm": 0.9439037442207336, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 7.4667, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.025015130119023603, | |
| "grad_norm": 0.6652296185493469, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 7.1213, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.025284110012776546, | |
| "grad_norm": 0.9313641786575317, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 6.9055, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.025553089906529488, | |
| "grad_norm": 0.5718141198158264, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 7.4156, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.02582206980028243, | |
| "grad_norm": 0.90057772397995, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 7.0547, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.026091049694035372, | |
| "grad_norm": 0.8088359236717224, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 6.8638, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.02636002958778831, | |
| "grad_norm": 0.7129319310188293, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 7.0757, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.026629009481541253, | |
| "grad_norm": 0.7212324142456055, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 7.3563, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.026897989375294196, | |
| "grad_norm": 1.3920371532440186, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 7.3419, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.026897989375294196, | |
| "eval_loss": 7.306600570678711, | |
| "eval_runtime": 1.1005, | |
| "eval_samples_per_second": 45.435, | |
| "eval_steps_per_second": 6.361, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.027166969269047138, | |
| "grad_norm": 1.9963257312774658, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 6.673, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.02743594916280008, | |
| "grad_norm": 1.888506293296814, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 7.1533, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.027704929056553022, | |
| "grad_norm": 1.8473235368728638, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 7.442, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.027973908950305965, | |
| "grad_norm": 1.1786754131317139, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 7.4846, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.028242888844058907, | |
| "grad_norm": 1.2605340480804443, | |
| "learning_rate": 0.00015, | |
| "loss": 7.1673, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.02851186873781185, | |
| "grad_norm": 0.6456354856491089, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 7.1138, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.02878084863156479, | |
| "grad_norm": 1.4024274349212646, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 6.8081, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.029049828525317734, | |
| "grad_norm": 1.4252393245697021, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 6.7006, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.029318808419070676, | |
| "grad_norm": 1.7832438945770264, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 6.3993, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.029587788312823618, | |
| "grad_norm": 1.6940126419067383, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 6.4566, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.029856768206576557, | |
| "grad_norm": 1.3766435384750366, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 6.479, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.0301257481003295, | |
| "grad_norm": 1.0472962856292725, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 6.0186, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.03039472799408244, | |
| "grad_norm": 1.0262020826339722, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 7.0508, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.030663707887835383, | |
| "grad_norm": 1.0168136358261108, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 6.2651, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.030932687781588326, | |
| "grad_norm": 1.360337734222412, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 7.0073, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.031201667675341268, | |
| "grad_norm": 1.2837754487991333, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 7.3239, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.031470647569094214, | |
| "grad_norm": 1.3919296264648438, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 6.6288, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.03173962746284715, | |
| "grad_norm": 1.2884666919708252, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 7.1069, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.03200860735660009, | |
| "grad_norm": 1.1876237392425537, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 6.9297, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.03227758725035303, | |
| "grad_norm": 1.10402512550354, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 6.6218, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.032546567144105976, | |
| "grad_norm": 1.4770866632461548, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 7.4542, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.03281554703785892, | |
| "grad_norm": 1.2299976348876953, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 7.1409, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.03308452693161186, | |
| "grad_norm": 0.6715269684791565, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 6.9305, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.0333535068253648, | |
| "grad_norm": 0.812654435634613, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 6.6642, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.033622486719117745, | |
| "grad_norm": 1.3478944301605225, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 7.0165, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.033622486719117745, | |
| "eval_loss": 7.224481105804443, | |
| "eval_runtime": 1.101, | |
| "eval_samples_per_second": 45.415, | |
| "eval_steps_per_second": 6.358, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.03389146661287069, | |
| "grad_norm": 1.1918294429779053, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 6.6002, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.03416044650662363, | |
| "grad_norm": 0.9166633486747742, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 7.461, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.03442942640037657, | |
| "grad_norm": 0.7154397964477539, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 7.38, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.034698406294129513, | |
| "grad_norm": 1.2024431228637695, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 6.5682, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.034967386187882456, | |
| "grad_norm": 1.2459428310394287, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 7.3055, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0352363660816354, | |
| "grad_norm": 0.7260080575942993, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 6.581, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.03550534597538834, | |
| "grad_norm": 0.5916652679443359, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 6.9627, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.03577432586914128, | |
| "grad_norm": 0.7819718718528748, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 6.668, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.036043305762894225, | |
| "grad_norm": 0.8700635433197021, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 7.2856, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.03631228565664717, | |
| "grad_norm": 0.8389477133750916, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 7.0287, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.03658126555040011, | |
| "grad_norm": 0.8980041742324829, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 7.1966, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.03685024544415305, | |
| "grad_norm": 0.7039759159088135, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 6.7216, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.037119225337905994, | |
| "grad_norm": 0.8420053124427795, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 7.2763, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.037388205231658936, | |
| "grad_norm": 0.8006654381752014, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 6.8812, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.03765718512541188, | |
| "grad_norm": 0.5510133504867554, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 7.1272, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03792616501916482, | |
| "grad_norm": 0.6548418998718262, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 6.5317, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.03819514491291776, | |
| "grad_norm": 0.618125319480896, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 7.2238, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.038464124806670705, | |
| "grad_norm": 0.7045526504516602, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 7.0095, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.03873310470042364, | |
| "grad_norm": 0.8406367897987366, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 6.357, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.03900208459417658, | |
| "grad_norm": 0.5313419103622437, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 6.9844, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.039271064487929525, | |
| "grad_norm": 0.7371297478675842, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 7.2803, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.03954004438168247, | |
| "grad_norm": 0.5858275294303894, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 7.0337, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.03980902427543541, | |
| "grad_norm": 0.9702624678611755, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 7.0098, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.04007800416918835, | |
| "grad_norm": 0.7458012104034424, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 7.1638, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.040346984062941293, | |
| "grad_norm": 1.1584868431091309, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 7.3627, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.040346984062941293, | |
| "eval_loss": 7.293600082397461, | |
| "eval_runtime": 1.0743, | |
| "eval_samples_per_second": 46.541, | |
| "eval_steps_per_second": 6.516, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.040615963956694236, | |
| "grad_norm": 1.378065586090088, | |
| "learning_rate": 4.659698863221513e-05, | |
| "loss": 6.2633, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.04088494385044718, | |
| "grad_norm": 1.318018913269043, | |
| "learning_rate": 4.481448235912671e-05, | |
| "loss": 6.6505, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.04115392374420012, | |
| "grad_norm": 1.5204188823699951, | |
| "learning_rate": 4.306073275629044e-05, | |
| "loss": 7.352, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.04142290363795306, | |
| "grad_norm": 1.6174471378326416, | |
| "learning_rate": 4.133621928133665e-05, | |
| "loss": 7.3426, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.041691883531706005, | |
| "grad_norm": 0.9823394417762756, | |
| "learning_rate": 3.964141339903026e-05, | |
| "loss": 7.2325, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.04196086342545895, | |
| "grad_norm": 0.9155641794204712, | |
| "learning_rate": 3.797677845237696e-05, | |
| "loss": 7.0975, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.04222984331921189, | |
| "grad_norm": 0.9602285623550415, | |
| "learning_rate": 3.634276953594982e-05, | |
| "loss": 7.4331, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.04249882321296483, | |
| "grad_norm": 0.4766939878463745, | |
| "learning_rate": 3.473983337147118e-05, | |
| "loss": 6.4512, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.042767803106717774, | |
| "grad_norm": 0.6891216039657593, | |
| "learning_rate": 3.316840818568315e-05, | |
| "loss": 6.2009, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.043036783000470716, | |
| "grad_norm": 0.7973335385322571, | |
| "learning_rate": 3.162892359054098e-05, | |
| "loss": 6.0294, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.04330576289422366, | |
| "grad_norm": 0.7474548816680908, | |
| "learning_rate": 3.0121800465761293e-05, | |
| "loss": 6.385, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.0435747427879766, | |
| "grad_norm": 0.5858322381973267, | |
| "learning_rate": 2.8647450843757897e-05, | |
| "loss": 6.2609, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.04384372268172954, | |
| "grad_norm": 0.7844979763031006, | |
| "learning_rate": 2.7206277796996144e-05, | |
| "loss": 6.3406, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.044112702575482485, | |
| "grad_norm": 1.182106614112854, | |
| "learning_rate": 2.5798675327796993e-05, | |
| "loss": 6.4119, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.04438168246923543, | |
| "grad_norm": 0.9624720215797424, | |
| "learning_rate": 2.4425028260620715e-05, | |
| "loss": 6.6251, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.04465066236298837, | |
| "grad_norm": 0.8138177990913391, | |
| "learning_rate": 2.3085712136859668e-05, | |
| "loss": 7.0401, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.04491964225674131, | |
| "grad_norm": 0.5879483222961426, | |
| "learning_rate": 2.178109311216913e-05, | |
| "loss": 6.9187, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.045188622150494254, | |
| "grad_norm": 1.2505601644515991, | |
| "learning_rate": 2.0511527856363912e-05, | |
| "loss": 7.2914, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.045457602044247196, | |
| "grad_norm": 1.0231761932373047, | |
| "learning_rate": 1.927736345590839e-05, | |
| "loss": 6.8207, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.04572658193800013, | |
| "grad_norm": 0.8401983976364136, | |
| "learning_rate": 1.8078937319026654e-05, | |
| "loss": 7.1883, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.04599556183175307, | |
| "grad_norm": 0.5049845576286316, | |
| "learning_rate": 1.6916577083458228e-05, | |
| "loss": 6.8629, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.046264541725506016, | |
| "grad_norm": 0.7277731895446777, | |
| "learning_rate": 1.579060052688548e-05, | |
| "loss": 7.2852, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.04653352161925896, | |
| "grad_norm": 0.977936863899231, | |
| "learning_rate": 1.4701315480056164e-05, | |
| "loss": 6.9577, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.0468025015130119, | |
| "grad_norm": 0.7111912369728088, | |
| "learning_rate": 1.3649019742625623e-05, | |
| "loss": 7.0556, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.04707148140676484, | |
| "grad_norm": 0.7338117361068726, | |
| "learning_rate": 1.2634001001741373e-05, | |
| "loss": 7.2456, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.04707148140676484, | |
| "eval_loss": 7.184196949005127, | |
| "eval_runtime": 1.074, | |
| "eval_samples_per_second": 46.556, | |
| "eval_steps_per_second": 6.518, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.047340461300517785, | |
| "grad_norm": 0.5232920050621033, | |
| "learning_rate": 1.1656536753392287e-05, | |
| "loss": 6.4342, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.04760944119427073, | |
| "grad_norm": 0.45352447032928467, | |
| "learning_rate": 1.0716894226543953e-05, | |
| "loss": 6.9281, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.04787842108802367, | |
| "grad_norm": 0.611677885055542, | |
| "learning_rate": 9.815330310080887e-06, | |
| "loss": 7.319, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.04814740098177661, | |
| "grad_norm": 0.9648262858390808, | |
| "learning_rate": 8.952091482575824e-06, | |
| "loss": 6.9275, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.048416380875529554, | |
| "grad_norm": 0.7132251262664795, | |
| "learning_rate": 8.127413744904804e-06, | |
| "loss": 6.5056, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.048685360769282496, | |
| "grad_norm": 0.5821110606193542, | |
| "learning_rate": 7.34152255572697e-06, | |
| "loss": 6.84, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.04895434066303544, | |
| "grad_norm": 0.7894052267074585, | |
| "learning_rate": 6.594632769846353e-06, | |
| "loss": 6.9713, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.04922332055678838, | |
| "grad_norm": 0.7041998505592346, | |
| "learning_rate": 5.886948579472778e-06, | |
| "loss": 6.4816, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.04949230045054132, | |
| "grad_norm": 0.5108593702316284, | |
| "learning_rate": 5.218663458397715e-06, | |
| "loss": 7.2662, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.049761280344294265, | |
| "grad_norm": 0.6600824594497681, | |
| "learning_rate": 4.589960109100444e-06, | |
| "loss": 7.2239, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.05003026023804721, | |
| "grad_norm": 0.679880678653717, | |
| "learning_rate": 4.001010412799138e-06, | |
| "loss": 7.0421, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.05029924013180015, | |
| "grad_norm": 0.5693497657775879, | |
| "learning_rate": 3.451975382460109e-06, | |
| "loss": 7.0777, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.05056822002555309, | |
| "grad_norm": 0.6687301397323608, | |
| "learning_rate": 2.9430051187785962e-06, | |
| "loss": 6.6986, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.050837199919306034, | |
| "grad_norm": 0.7745783925056458, | |
| "learning_rate": 2.4742387691426445e-06, | |
| "loss": 7.0626, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.051106179813058976, | |
| "grad_norm": 0.5398703813552856, | |
| "learning_rate": 2.0458044895916513e-06, | |
| "loss": 7.5387, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.05137515970681192, | |
| "grad_norm": 0.5536245703697205, | |
| "learning_rate": 1.6578194097797258e-06, | |
| "loss": 6.8114, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.05164413960056486, | |
| "grad_norm": 0.8733762502670288, | |
| "learning_rate": 1.3103896009537207e-06, | |
| "loss": 7.109, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.0519131194943178, | |
| "grad_norm": 0.9818241000175476, | |
| "learning_rate": 1.0036100469542786e-06, | |
| "loss": 6.679, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.052182099388070745, | |
| "grad_norm": 0.9805580377578735, | |
| "learning_rate": 7.375646182482875e-07, | |
| "loss": 6.5897, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.05245107928182369, | |
| "grad_norm": 1.4828003644943237, | |
| "learning_rate": 5.123260489995229e-07, | |
| "loss": 7.2332, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.05272005917557662, | |
| "grad_norm": 1.0649274587631226, | |
| "learning_rate": 3.2795591718381975e-07, | |
| "loss": 6.9496, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.052989039069329565, | |
| "grad_norm": 1.1552672386169434, | |
| "learning_rate": 1.8450462775428942e-07, | |
| "loss": 6.3958, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.05325801896308251, | |
| "grad_norm": 1.6000089645385742, | |
| "learning_rate": 8.201139886109264e-08, | |
| "loss": 7.0364, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.05352699885683545, | |
| "grad_norm": 0.86728435754776, | |
| "learning_rate": 2.0504251129649374e-08, | |
| "loss": 7.7624, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.05379597875058839, | |
| "grad_norm": 1.0310410261154175, | |
| "learning_rate": 0.0, | |
| "loss": 7.2514, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05379597875058839, | |
| "eval_loss": 7.1964921951293945, | |
| "eval_runtime": 1.1003, | |
| "eval_samples_per_second": 45.441, | |
| "eval_steps_per_second": 6.362, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 174087813267456.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |