|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 25, |
|
"global_step": 241, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 2e-05, |
|
"loss": 4.2853, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"eval_loss": 4.086624622344971, |
|
"eval_runtime": 32.056, |
|
"eval_samples_per_second": 42.083, |
|
"eval_steps_per_second": 42.083, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4e-05, |
|
"loss": 4.1922, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 6e-05, |
|
"loss": 4.1936, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 8e-05, |
|
"loss": 4.1179, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.0001, |
|
"loss": 3.8564, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00012, |
|
"loss": 3.5264, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00014, |
|
"loss": 3.3411, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00016, |
|
"loss": 3.2172, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00018, |
|
"loss": 3.1712, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0002, |
|
"loss": 2.9996, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00019999075218579183, |
|
"loss": 2.8862, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00019996301045360873, |
|
"loss": 2.7707, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0001999167799344583, |
|
"loss": 2.7771, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00019985206917896563, |
|
"loss": 2.6648, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00019976889015579165, |
|
"loss": 2.5946, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00019966725824941932, |
|
"loss": 2.4833, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00019954719225730847, |
|
"loss": 2.4827, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00019940871438641882, |
|
"loss": 2.4079, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00019925185024910277, |
|
"loss": 2.4623, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00019907662885836836, |
|
"loss": 2.4305, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.00019888308262251285, |
|
"loss": 2.3536, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0001986712473391289, |
|
"loss": 2.3493, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00019844116218848334, |
|
"loss": 2.296, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00019819286972627066, |
|
"loss": 2.1051, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00019792641587574212, |
|
"loss": 2.188, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"eval_loss": 1.9750964641571045, |
|
"eval_runtime": 32.726, |
|
"eval_samples_per_second": 41.221, |
|
"eval_steps_per_second": 41.221, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00019764184991921178, |
|
"loss": 2.1358, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0001973392244889415, |
|
"loss": 2.034, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00019701859555740648, |
|
"loss": 2.0622, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00019668002242694238, |
|
"loss": 2.0607, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00019632356771877735, |
|
"loss": 1.9011, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.00019594929736144976, |
|
"loss": 1.8635, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0001955572805786141, |
|
"loss": 1.8738, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00019514758987623784, |
|
"loss": 1.7801, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.000194720301029191, |
|
"loss": 1.7083, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00019427549306723097, |
|
"loss": 1.7086, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0001938132482603856, |
|
"loss": 1.6391, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0001933336521037367, |
|
"loss": 1.6092, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.00019283679330160726, |
|
"loss": 1.5884, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.00019232276375115515, |
|
"loss": 1.4404, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.00019179165852537596, |
|
"loss": 1.5762, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.00019124357585551872, |
|
"loss": 1.4584, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.00019067861711291744, |
|
"loss": 1.4526, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.0001900968867902419, |
|
"loss": 1.4832, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.000189498492482171, |
|
"loss": 1.4897, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00018888354486549237, |
|
"loss": 1.4288, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00018825215767863214, |
|
"loss": 1.4583, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.0001876044477006183, |
|
"loss": 1.3071, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00018694053472948156, |
|
"loss": 1.3369, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00018626054156009806, |
|
"loss": 1.3406, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00018556459396147775, |
|
"loss": 1.2702, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"eval_loss": 1.2179754972457886, |
|
"eval_runtime": 32.7495, |
|
"eval_samples_per_second": 41.191, |
|
"eval_steps_per_second": 41.191, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00018485282065350235, |
|
"loss": 1.2637, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00018412535328311814, |
|
"loss": 1.2336, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.0001833823263999867, |
|
"loss": 1.262, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.0001826238774315995, |
|
"loss": 1.2782, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00018185014665785936, |
|
"loss": 1.2531, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00018106127718513516, |
|
"loss": 1.2322, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00018025741491979326, |
|
"loss": 1.1701, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00017943870854121124, |
|
"loss": 1.2151, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00017860530947427875, |
|
"loss": 1.1879, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00017775737186139038, |
|
"loss": 1.2357, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.0001768950525339362, |
|
"loss": 1.1604, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.00017601851098329483, |
|
"loss": 1.1958, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.00017512790933133437, |
|
"loss": 1.0923, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.000174223412300427, |
|
"loss": 1.1973, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00017330518718298264, |
|
"loss": 1.1571, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00017237340381050703, |
|
"loss": 1.1335, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00017142823452219038, |
|
"loss": 1.0601, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00017046985413303215, |
|
"loss": 1.135, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.00016949843990150796, |
|
"loss": 1.1512, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.00016851417149678444, |
|
"loss": 1.1113, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.00016751723096548835, |
|
"loss": 1.113, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.00016650780269803587, |
|
"loss": 1.0758, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.00016548607339452853, |
|
"loss": 1.1117, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.00016445223203022166, |
|
"loss": 1.0408, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.00016340646982057247, |
|
"loss": 1.0671, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"eval_loss": 1.0150682926177979, |
|
"eval_runtime": 32.7268, |
|
"eval_samples_per_second": 41.22, |
|
"eval_steps_per_second": 41.22, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.00016234898018587337, |
|
"loss": 1.0944, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0001612799587154777, |
|
"loss": 1.0673, |
|
"step": 77 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.00016019960313162434, |
|
"loss": 1.0592, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.00015910811325286768, |
|
"loss": 1.0601, |
|
"step": 79 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.00015800569095711982, |
|
"loss": 1.1125, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00015689254014431225, |
|
"loss": 1.0926, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00015576886669868296, |
|
"loss": 1.0727, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00015463487845069707, |
|
"loss": 1.0461, |
|
"step": 83 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.00015349078513860726, |
|
"loss": 4.5701, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.00015233679836966122, |
|
"loss": 1.0468, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.0001511731315809637, |
|
"loss": 1.0684, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.00015000000000000001, |
|
"loss": 1.0938, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.00014881762060482814, |
|
"loss": 1.0245, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.0001476262120839475, |
|
"loss": 1.0563, |
|
"step": 89 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.00014642599479585105, |
|
"loss": 1.0125, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 0.00014521719072826858, |
|
"loss": 1.0123, |
|
"step": 91 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 0.0001440000234571087, |
|
"loss": 0.9582, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0001427747181051071, |
|
"loss": 1.0677, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.00014154150130018866, |
|
"loss": 1.0533, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.00014030060113355116, |
|
"loss": 1.0029, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.00013905224711747844, |
|
"loss": 1.0508, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.00013779667014289065, |
|
"loss": 1.0256, |
|
"step": 97 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.00013653410243663952, |
|
"loss": 0.9858, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.00013526477751855644, |
|
"loss": 0.9672, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.00013398893015826167, |
|
"loss": 0.9542, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"eval_loss": 0.9208987355232239, |
|
"eval_runtime": 32.7377, |
|
"eval_samples_per_second": 41.206, |
|
"eval_steps_per_second": 41.206, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.00013270679633174218, |
|
"loss": 1.009, |
|
"step": 101 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.00013141861317770626, |
|
"loss": 1.0237, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.00013012461895372344, |
|
"loss": 0.9836, |
|
"step": 103 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.0001288250529921571, |
|
"loss": 0.9401, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.00012752015565589852, |
|
"loss": 0.9535, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.00012621016829391022, |
|
"loss": 0.9697, |
|
"step": 106 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.00012489533319658702, |
|
"loss": 0.9458, |
|
"step": 107 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.00012357589355094275, |
|
"loss": 0.9681, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.00012225209339563145, |
|
"loss": 0.9961, |
|
"step": 109 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.00012092417757581085, |
|
"loss": 0.9671, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.00011959239169785667, |
|
"loss": 0.9608, |
|
"step": 111 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.00011825698208393619, |
|
"loss": 0.9483, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.00011691819572644939, |
|
"loss": 0.987, |
|
"step": 113 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.0001155762802423463, |
|
"loss": 0.9121, |
|
"step": 114 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.00011423148382732853, |
|
"loss": 0.9534, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.0001128840552099439, |
|
"loss": 0.9927, |
|
"step": 116 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 0.00011153424360558267, |
|
"loss": 0.9515, |
|
"step": 117 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 0.00011018229867038356, |
|
"loss": 0.926, |
|
"step": 118 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 0.00010882847045505808, |
|
"loss": 0.9243, |
|
"step": 119 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.00010747300935864243, |
|
"loss": 0.9605, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.00010611616608218429, |
|
"loss": 0.9483, |
|
"step": 121 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.00010475819158237425, |
|
"loss": 0.9092, |
|
"step": 122 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.00010339933702512979, |
|
"loss": 0.9367, |
|
"step": 123 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.00010203985373914056, |
|
"loss": 0.9375, |
|
"step": 124 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 0.00010067999316938347, |
|
"loss": 0.9318, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"eval_loss": 0.867986261844635, |
|
"eval_runtime": 32.7483, |
|
"eval_samples_per_second": 41.193, |
|
"eval_steps_per_second": 41.193, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 9.932000683061653e-05, |
|
"loss": 0.9292, |
|
"step": 126 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 9.79601462608595e-05, |
|
"loss": 0.8995, |
|
"step": 127 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 9.660066297487022e-05, |
|
"loss": 0.9279, |
|
"step": 128 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 9.524180841762577e-05, |
|
"loss": 0.9002, |
|
"step": 129 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 9.388383391781575e-05, |
|
"loss": 0.9175, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 9.252699064135758e-05, |
|
"loss": 0.8565, |
|
"step": 131 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 9.117152954494194e-05, |
|
"loss": 0.9448, |
|
"step": 132 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 8.981770132961649e-05, |
|
"loss": 0.8993, |
|
"step": 133 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 8.846575639441732e-05, |
|
"loss": 0.917, |
|
"step": 134 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 8.711594479005614e-05, |
|
"loss": 0.882, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 8.57685161726715e-05, |
|
"loss": 0.9425, |
|
"step": 136 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 8.442371975765368e-05, |
|
"loss": 0.9444, |
|
"step": 137 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 8.308180427355062e-05, |
|
"loss": 0.8971, |
|
"step": 138 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 8.174301791606385e-05, |
|
"loss": 0.8634, |
|
"step": 139 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 8.040760830214333e-05, |
|
"loss": 0.9023, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 7.907582242418916e-05, |
|
"loss": 0.8944, |
|
"step": 141 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 7.774790660436858e-05, |
|
"loss": 0.9128, |
|
"step": 142 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 7.642410644905726e-05, |
|
"loss": 0.952, |
|
"step": 143 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 7.510466680341301e-05, |
|
"loss": 0.8837, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 7.378983170608982e-05, |
|
"loss": 0.8667, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 7.24798443441015e-05, |
|
"loss": 0.9039, |
|
"step": 146 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 7.117494700784292e-05, |
|
"loss": 0.9015, |
|
"step": 147 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 6.98753810462766e-05, |
|
"loss": 0.8869, |
|
"step": 148 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 6.858138682229376e-05, |
|
"loss": 0.8992, |
|
"step": 149 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 6.729320366825784e-05, |
|
"loss": 0.858, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"eval_loss": 0.8283783793449402, |
|
"eval_runtime": 32.7267, |
|
"eval_samples_per_second": 41.22, |
|
"eval_steps_per_second": 41.22, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 6.601106984173835e-05, |
|
"loss": 0.9077, |
|
"step": 151 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 6.47352224814436e-05, |
|
"loss": 0.8779, |
|
"step": 152 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 6.34658975633605e-05, |
|
"loss": 0.8306, |
|
"step": 153 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 6.220332985710936e-05, |
|
"loss": 0.862, |
|
"step": 154 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 6.094775288252157e-05, |
|
"loss": 0.8632, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 5.969939886644884e-05, |
|
"loss": 0.8395, |
|
"step": 156 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 5.845849869981137e-05, |
|
"loss": 0.8724, |
|
"step": 157 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 5.7225281894892935e-05, |
|
"loss": 0.8882, |
|
"step": 158 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 5.599997654289129e-05, |
|
"loss": 0.9296, |
|
"step": 159 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 5.478280927173145e-05, |
|
"loss": 0.8743, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 5.357400520414898e-05, |
|
"loss": 0.8932, |
|
"step": 161 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 5.2373787916052486e-05, |
|
"loss": 0.8769, |
|
"step": 162 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 5.11823793951719e-05, |
|
"loss": 0.89, |
|
"step": 163 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 5.000000000000002e-05, |
|
"loss": 0.886, |
|
"step": 164 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 4.882686841903628e-05, |
|
"loss": 0.8907, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 4.7663201630338816e-05, |
|
"loss": 0.868, |
|
"step": 166 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 4.650921486139278e-05, |
|
"loss": 0.8267, |
|
"step": 167 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 4.5365121549302914e-05, |
|
"loss": 0.8562, |
|
"step": 168 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 4.423113330131707e-05, |
|
"loss": 0.89, |
|
"step": 169 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 4.310745985568778e-05, |
|
"loss": 0.8262, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 4.19943090428802e-05, |
|
"loss": 0.822, |
|
"step": 171 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 4.089188674713236e-05, |
|
"loss": 0.8698, |
|
"step": 172 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 3.980039686837568e-05, |
|
"loss": 0.8847, |
|
"step": 173 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 3.872004128452231e-05, |
|
"loss": 0.8404, |
|
"step": 174 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 3.7651019814126654e-05, |
|
"loss": 0.8247, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"eval_loss": 0.807971715927124, |
|
"eval_runtime": 32.7317, |
|
"eval_samples_per_second": 41.214, |
|
"eval_steps_per_second": 41.214, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 3.6593530179427535e-05, |
|
"loss": 0.878, |
|
"step": 176 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 3.554776796977836e-05, |
|
"loss": 0.8518, |
|
"step": 177 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 3.45139266054715e-05, |
|
"loss": 0.8973, |
|
"step": 178 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 3.3492197301964145e-05, |
|
"loss": 0.8436, |
|
"step": 179 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 3.248276903451171e-05, |
|
"loss": 0.8855, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 3.1485828503215585e-05, |
|
"loss": 0.8617, |
|
"step": 181 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 3.0501560098492056e-05, |
|
"loss": 0.8574, |
|
"step": 182 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 2.9530145866967895e-05, |
|
"loss": 0.8424, |
|
"step": 183 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 2.8571765477809643e-05, |
|
"loss": 0.8656, |
|
"step": 184 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 2.7626596189492983e-05, |
|
"loss": 0.8577, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 2.669481281701739e-05, |
|
"loss": 0.864, |
|
"step": 186 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 2.5776587699573006e-05, |
|
"loss": 0.8752, |
|
"step": 187 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 2.487209066866565e-05, |
|
"loss": 0.8628, |
|
"step": 188 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 2.3981489016705205e-05, |
|
"loss": 0.8443, |
|
"step": 189 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 2.3104947466063787e-05, |
|
"loss": 0.8765, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 2.2242628138609623e-05, |
|
"loss": 0.8312, |
|
"step": 191 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 2.139469052572127e-05, |
|
"loss": 0.8494, |
|
"step": 192 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 2.0561291458788733e-05, |
|
"loss": 0.8081, |
|
"step": 193 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1.9742585080206755e-05, |
|
"loss": 0.8787, |
|
"step": 194 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 1.893872281486486e-05, |
|
"loss": 0.8343, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 1.8149853342140645e-05, |
|
"loss": 0.8693, |
|
"step": 196 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 1.7376122568400532e-05, |
|
"loss": 0.8446, |
|
"step": 197 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 1.6617673600013296e-05, |
|
"loss": 0.8589, |
|
"step": 198 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 1.587464671688187e-05, |
|
"loss": 0.8535, |
|
"step": 199 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 1.5147179346497664e-05, |
|
"loss": 0.8576, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"eval_loss": 0.7966279983520508, |
|
"eval_runtime": 32.7581, |
|
"eval_samples_per_second": 41.181, |
|
"eval_steps_per_second": 41.181, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 1.443540603852227e-05, |
|
"loss": 0.8526, |
|
"step": 201 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.373945843990192e-05, |
|
"loss": 0.7966, |
|
"step": 202 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.3059465270518468e-05, |
|
"loss": 0.8883, |
|
"step": 203 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 1.2395552299381741e-05, |
|
"loss": 0.8413, |
|
"step": 204 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 1.1747842321367886e-05, |
|
"loss": 0.8513, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 1.1116455134507664e-05, |
|
"loss": 0.8598, |
|
"step": 206 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 1.0501507517829012e-05, |
|
"loss": 0.8406, |
|
"step": 207 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 9.903113209758096e-06, |
|
"loss": 0.8189, |
|
"step": 208 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 9.321382887082563e-06, |
|
"loss": 0.8506, |
|
"step": 209 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 8.756424144481312e-06, |
|
"loss": 0.8356, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 8.208341474624071e-06, |
|
"loss": 0.8296, |
|
"step": 211 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 7.677236248844855e-06, |
|
"loss": 0.8456, |
|
"step": 212 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 7.163206698392744e-06, |
|
"loss": 0.835, |
|
"step": 213 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 6.666347896263325e-06, |
|
"loss": 0.815, |
|
"step": 214 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 6.186751739614405e-06, |
|
"loss": 0.8354, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 5.724506932769014e-06, |
|
"loss": 0.8782, |
|
"step": 216 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 5.27969897080901e-06, |
|
"loss": 0.8403, |
|
"step": 217 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 4.8524101237621635e-06, |
|
"loss": 0.8407, |
|
"step": 218 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 4.442719421385922e-06, |
|
"loss": 0.8439, |
|
"step": 219 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 4.050702638550275e-06, |
|
"loss": 0.9107, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 3.6764322812226415e-06, |
|
"loss": 0.8253, |
|
"step": 221 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 3.319977573057642e-06, |
|
"loss": 0.8103, |
|
"step": 222 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 2.9814044425935606e-06, |
|
"loss": 0.8744, |
|
"step": 223 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 2.6607755110584887e-06, |
|
"loss": 0.8626, |
|
"step": 224 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 2.3581500807882462e-06, |
|
"loss": 0.9026, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"eval_loss": 0.793445348739624, |
|
"eval_runtime": 32.7223, |
|
"eval_samples_per_second": 41.226, |
|
"eval_steps_per_second": 41.226, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 2.073584124257899e-06, |
|
"loss": 0.8356, |
|
"step": 226 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 1.8071302737293295e-06, |
|
"loss": 0.8072, |
|
"step": 227 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 1.5588378115166669e-06, |
|
"loss": 0.8643, |
|
"step": 228 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 1.3287526608711131e-06, |
|
"loss": 0.8778, |
|
"step": 229 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 1.1169173774871478e-06, |
|
"loss": 0.8558, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 9.233711416316571e-07, |
|
"loss": 0.8623, |
|
"step": 231 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 7.481497508972312e-07, |
|
"loss": 0.8407, |
|
"step": 232 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 5.912856135812051e-07, |
|
"loss": 0.8425, |
|
"step": 233 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 4.5280774269154115e-07, |
|
"loss": 0.8596, |
|
"step": 234 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 3.3274175058067846e-07, |
|
"loss": 0.8498, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 2.311098442083659e-07, |
|
"loss": 0.8642, |
|
"step": 236 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 1.4793082103435885e-07, |
|
"loss": 0.8156, |
|
"step": 237 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 8.322006554171146e-08, |
|
"loss": 0.8533, |
|
"step": 238 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 3.6989546391297256e-08, |
|
"loss": 0.8269, |
|
"step": 239 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 9.24781420816867e-09, |
|
"loss": 0.8119, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.0, |
|
"loss": 0.8459, |
|
"step": 241 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 241, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 500, |
|
"total_flos": 1.845262501848023e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|