| { | |
| "best_metric": 0.20841871201992035, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.074719800747198, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00049813200498132, | |
| "grad_norm": 5.953134059906006, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 4.8123, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00049813200498132, | |
| "eval_loss": 5.567110538482666, | |
| "eval_runtime": 4.675, | |
| "eval_samples_per_second": 10.695, | |
| "eval_steps_per_second": 1.497, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00099626400996264, | |
| "grad_norm": 6.526628494262695, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 4.6673, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014943960149439602, | |
| "grad_norm": 6.885717391967773, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 4.9635, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00199252801992528, | |
| "grad_norm": 6.974002361297607, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 4.7067, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0024906600249066002, | |
| "grad_norm": 6.78061580657959, | |
| "learning_rate": 0.00015, | |
| "loss": 3.2747, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029887920298879204, | |
| "grad_norm": 6.11532735824585, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.2891, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034869240348692405, | |
| "grad_norm": 7.936379909515381, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 1.9396, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00398505603985056, | |
| "grad_norm": 4.918308258056641, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.0278, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00448318804483188, | |
| "grad_norm": 2.4183318614959717, | |
| "learning_rate": 0.00027, | |
| "loss": 0.6151, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0049813200498132005, | |
| "grad_norm": 3.024343252182007, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5268, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005479452054794521, | |
| "grad_norm": 5.444397926330566, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.6453, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005977584059775841, | |
| "grad_norm": 1.5527619123458862, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.4021, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006475716064757161, | |
| "grad_norm": 2.6941704750061035, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.5887, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006973848069738481, | |
| "grad_norm": 2.389618158340454, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.5361, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007471980074719801, | |
| "grad_norm": 3.0418622493743896, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.6187, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00797011207970112, | |
| "grad_norm": 2.0878942012786865, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.5258, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008468244084682441, | |
| "grad_norm": 1.712019681930542, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.5596, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00896637608966376, | |
| "grad_norm": 1.5270085334777832, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.5545, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009464508094645082, | |
| "grad_norm": 1.2116973400115967, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.5171, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009962640099626401, | |
| "grad_norm": 1.9724152088165283, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.5578, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01046077210460772, | |
| "grad_norm": 1.3572190999984741, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.4079, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010958904109589041, | |
| "grad_norm": 1.0932906866073608, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.3469, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01145703611457036, | |
| "grad_norm": 2.3079965114593506, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.4726, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011955168119551681, | |
| "grad_norm": 1.4202669858932495, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.432, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012453300124533, | |
| "grad_norm": 1.4758336544036865, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.4866, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012453300124533, | |
| "eval_loss": 0.4223214089870453, | |
| "eval_runtime": 4.2101, | |
| "eval_samples_per_second": 11.876, | |
| "eval_steps_per_second": 1.663, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012951432129514322, | |
| "grad_norm": 1.7702012062072754, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.404, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.013449564134495641, | |
| "grad_norm": 1.6178979873657227, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.4401, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013947696139476962, | |
| "grad_norm": 1.7393587827682495, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.3987, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014445828144458281, | |
| "grad_norm": 1.4745129346847534, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.3417, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014943960149439602, | |
| "grad_norm": 2.148548126220703, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.389, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015442092154420922, | |
| "grad_norm": 1.60543692111969, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.3174, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01594022415940224, | |
| "grad_norm": 1.9873653650283813, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.3543, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01643835616438356, | |
| "grad_norm": 2.2028841972351074, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.3658, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.016936488169364883, | |
| "grad_norm": 2.061235189437866, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.3557, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.017434620174346202, | |
| "grad_norm": 1.9047632217407227, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.3839, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01793275217932752, | |
| "grad_norm": 1.9746155738830566, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.337, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01843088418430884, | |
| "grad_norm": 1.2726603746414185, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.2521, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.018929016189290163, | |
| "grad_norm": 1.6630284786224365, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.3524, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.019427148194271483, | |
| "grad_norm": 2.152161121368408, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.3155, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.019925280199252802, | |
| "grad_norm": 1.6489615440368652, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.2775, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02042341220423412, | |
| "grad_norm": 1.6735095977783203, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.2775, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02092154420921544, | |
| "grad_norm": 1.5859333276748657, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.3597, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.021419676214196763, | |
| "grad_norm": 1.8575478792190552, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.3549, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.021917808219178082, | |
| "grad_norm": 1.4628279209136963, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.2813, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0224159402241594, | |
| "grad_norm": 1.3827449083328247, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.2231, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02291407222914072, | |
| "grad_norm": 1.371862769126892, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.2659, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.023412204234122044, | |
| "grad_norm": 1.628051519393921, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.3401, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.023910336239103363, | |
| "grad_norm": 1.2595473527908325, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.2926, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.024408468244084682, | |
| "grad_norm": 1.9967325925827026, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.3504, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.024906600249066, | |
| "grad_norm": 1.8664722442626953, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.278, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024906600249066, | |
| "eval_loss": 0.2656872272491455, | |
| "eval_runtime": 4.2304, | |
| "eval_samples_per_second": 11.819, | |
| "eval_steps_per_second": 1.655, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.025404732254047324, | |
| "grad_norm": 1.4346284866333008, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 0.2574, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.025902864259028643, | |
| "grad_norm": 1.349393367767334, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 0.2641, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.026400996264009963, | |
| "grad_norm": 2.0565531253814697, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 0.3113, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.026899128268991282, | |
| "grad_norm": 1.7186627388000488, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 0.2532, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0273972602739726, | |
| "grad_norm": 1.5477849245071411, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 0.3041, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.027895392278953924, | |
| "grad_norm": 1.3647983074188232, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 0.2715, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.028393524283935243, | |
| "grad_norm": 1.3015156984329224, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 0.2774, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.028891656288916562, | |
| "grad_norm": 1.343042254447937, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 0.1843, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.029389788293897882, | |
| "grad_norm": 1.6829490661621094, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 0.3086, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.029887920298879204, | |
| "grad_norm": 1.5559968948364258, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 0.245, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.030386052303860524, | |
| "grad_norm": 1.6984091997146606, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 0.2805, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.030884184308841843, | |
| "grad_norm": 1.6316205263137817, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 0.2328, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.03138231631382316, | |
| "grad_norm": 1.7361657619476318, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 0.358, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.03188044831880448, | |
| "grad_norm": 1.2437626123428345, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 0.1992, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0323785803237858, | |
| "grad_norm": 1.4107438325881958, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 0.261, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.03287671232876712, | |
| "grad_norm": 1.0943936109542847, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 0.1947, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.033374844333748446, | |
| "grad_norm": 1.371076226234436, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.1723, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.033872976338729766, | |
| "grad_norm": 1.8774269819259644, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 0.3099, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.034371108343711085, | |
| "grad_norm": 1.5689069032669067, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 0.2458, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.034869240348692404, | |
| "grad_norm": 1.4060947895050049, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 0.2045, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03536737235367372, | |
| "grad_norm": 1.5080294609069824, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 0.2674, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.03586550435865504, | |
| "grad_norm": 2.0735766887664795, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 0.268, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.03636363636363636, | |
| "grad_norm": 1.7785519361495972, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 0.4725, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.03686176836861768, | |
| "grad_norm": 1.6680009365081787, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 0.1942, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.037359900373599, | |
| "grad_norm": 1.2794748544692993, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 0.1952, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.037359900373599, | |
| "eval_loss": 0.24085499346256256, | |
| "eval_runtime": 4.2231, | |
| "eval_samples_per_second": 11.84, | |
| "eval_steps_per_second": 1.658, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.03785803237858033, | |
| "grad_norm": 2.097665309906006, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 0.2742, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.038356164383561646, | |
| "grad_norm": 2.0213897228240967, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 0.3291, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.038854296388542965, | |
| "grad_norm": 1.8470332622528076, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 0.3145, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.039352428393524284, | |
| "grad_norm": 1.370811104774475, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 0.2163, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.039850560398505604, | |
| "grad_norm": 1.4120204448699951, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 0.2512, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04034869240348692, | |
| "grad_norm": 1.5628596544265747, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 0.2742, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.04084682440846824, | |
| "grad_norm": 1.351811408996582, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 0.2858, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.04134495641344956, | |
| "grad_norm": 1.495460033416748, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 0.2085, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.04184308841843088, | |
| "grad_norm": 1.1618963479995728, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 0.256, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.04234122042341221, | |
| "grad_norm": 1.481665015220642, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 0.267, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.042839352428393526, | |
| "grad_norm": 0.9506065249443054, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.1691, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.043337484433374845, | |
| "grad_norm": 1.7585303783416748, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 0.2362, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.043835616438356165, | |
| "grad_norm": 1.6562221050262451, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 0.2178, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.044333748443337484, | |
| "grad_norm": 1.6594310998916626, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 0.2027, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.0448318804483188, | |
| "grad_norm": 2.217742443084717, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 0.2966, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04533001245330012, | |
| "grad_norm": 1.4910566806793213, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 0.179, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.04582814445828144, | |
| "grad_norm": 2.0381054878234863, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 0.3568, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.04632627646326277, | |
| "grad_norm": 1.7185461521148682, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 0.2823, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.04682440846824409, | |
| "grad_norm": 1.6253682374954224, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 0.2248, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.047322540473225407, | |
| "grad_norm": 1.2121644020080566, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 0.1926, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.047820672478206726, | |
| "grad_norm": 1.1331689357757568, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 0.1632, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.048318804483188045, | |
| "grad_norm": 1.6569329500198364, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 0.2536, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.048816936488169364, | |
| "grad_norm": 1.3067047595977783, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 0.1937, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.049315068493150684, | |
| "grad_norm": 2.5061912536621094, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 0.3301, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.049813200498132, | |
| "grad_norm": 1.3976527452468872, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 0.2458, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.049813200498132, | |
| "eval_loss": 0.23561157286167145, | |
| "eval_runtime": 4.2306, | |
| "eval_samples_per_second": 11.819, | |
| "eval_steps_per_second": 1.655, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05031133250311332, | |
| "grad_norm": 1.5023231506347656, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 0.3569, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.05080946450809465, | |
| "grad_norm": 1.3988009691238403, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 0.3297, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.05130759651307597, | |
| "grad_norm": 0.9321001768112183, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 0.1681, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.05180572851805729, | |
| "grad_norm": 0.9476335048675537, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 0.231, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.052303860523038606, | |
| "grad_norm": 1.978179931640625, | |
| "learning_rate": 0.00015, | |
| "loss": 0.2637, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.052801992528019925, | |
| "grad_norm": 1.2657047510147095, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 0.2849, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.053300124533001245, | |
| "grad_norm": 1.3403172492980957, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 0.1678, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.053798256537982564, | |
| "grad_norm": 1.4121437072753906, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 0.2355, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.05429638854296388, | |
| "grad_norm": 1.2850801944732666, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 0.2286, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.0547945205479452, | |
| "grad_norm": 1.5912704467773438, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 0.1789, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.05529265255292653, | |
| "grad_norm": 1.3650376796722412, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 0.2312, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.05579078455790785, | |
| "grad_norm": 1.250728964805603, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 0.2088, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.05628891656288917, | |
| "grad_norm": 1.529443383216858, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 0.2381, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.056787048567870486, | |
| "grad_norm": 3.1690664291381836, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 0.2461, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.057285180572851806, | |
| "grad_norm": 2.206183671951294, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 0.3148, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.057783312577833125, | |
| "grad_norm": 1.5377274751663208, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 0.2579, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.058281444582814444, | |
| "grad_norm": 1.16757333278656, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 0.1926, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.058779576587795763, | |
| "grad_norm": 1.0124973058700562, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 0.1666, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.05927770859277708, | |
| "grad_norm": 1.0924897193908691, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 0.2009, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.05977584059775841, | |
| "grad_norm": 1.521816611289978, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 0.2777, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06027397260273973, | |
| "grad_norm": 0.987753689289093, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 0.2156, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.06077210460772105, | |
| "grad_norm": 1.1866604089736938, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 0.1879, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.06127023661270237, | |
| "grad_norm": 0.9479057788848877, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 0.1357, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.061768368617683686, | |
| "grad_norm": 1.3598674535751343, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 0.1816, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.062266500622665005, | |
| "grad_norm": 1.0631945133209229, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 0.1546, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.062266500622665005, | |
| "eval_loss": 0.20524150133132935, | |
| "eval_runtime": 4.2258, | |
| "eval_samples_per_second": 11.832, | |
| "eval_steps_per_second": 1.656, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.06276463262764632, | |
| "grad_norm": 1.541964054107666, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 0.3075, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.06326276463262764, | |
| "grad_norm": 1.6632496118545532, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 0.2464, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.06376089663760896, | |
| "grad_norm": 1.1813774108886719, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 0.2453, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.06425902864259028, | |
| "grad_norm": 1.1383943557739258, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 0.2151, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.0647571606475716, | |
| "grad_norm": 1.3484247922897339, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 0.1931, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.06525529265255292, | |
| "grad_norm": 1.8112094402313232, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 0.3539, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.06575342465753424, | |
| "grad_norm": 1.0824347734451294, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 0.2023, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.06625155666251557, | |
| "grad_norm": 2.051572799682617, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 0.3869, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.06674968866749689, | |
| "grad_norm": 1.9844508171081543, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 0.2098, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.06724782067247821, | |
| "grad_norm": 1.694000244140625, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 0.2233, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.06774595267745953, | |
| "grad_norm": 1.8740932941436768, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 0.3123, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.06824408468244085, | |
| "grad_norm": 1.0883699655532837, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 0.1602, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.06874221668742217, | |
| "grad_norm": 1.4678159952163696, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 0.3026, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.06924034869240349, | |
| "grad_norm": 1.4052225351333618, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 0.2146, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.06973848069738481, | |
| "grad_norm": 1.304583191871643, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 0.1773, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.07023661270236613, | |
| "grad_norm": 1.4806348085403442, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 0.2221, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.07073474470734745, | |
| "grad_norm": 1.6636650562286377, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 0.1933, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.07123287671232877, | |
| "grad_norm": 1.2898904085159302, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.1931, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.07173100871731009, | |
| "grad_norm": 1.110796332359314, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 0.1722, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.0722291407222914, | |
| "grad_norm": 1.4751225709915161, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 0.2576, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.07272727272727272, | |
| "grad_norm": 1.2125765085220337, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 0.1481, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.07322540473225404, | |
| "grad_norm": 1.3493611812591553, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 0.1998, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.07372353673723536, | |
| "grad_norm": 1.5324091911315918, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 0.2094, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.07422166874221668, | |
| "grad_norm": 1.8139060735702515, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 0.2159, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.074719800747198, | |
| "grad_norm": 1.0446826219558716, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 0.1404, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.074719800747198, | |
| "eval_loss": 0.20841871201992035, | |
| "eval_runtime": 4.2113, | |
| "eval_samples_per_second": 11.873, | |
| "eval_steps_per_second": 1.662, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.364765716348928e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |