| { | |
| "best_metric": 0.015150871127843857, | |
| "best_model_checkpoint": "saves/psy-course-doc/Ministral-8B-Instruct-2410/train/fold4/checkpoint-90", | |
| "epoch": 4.938271604938271, | |
| "eval_steps": 10, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03950617283950617, | |
| "grad_norm": 0.259811669588089, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.1451, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.21856799721717834, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.1334, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.2536189556121826, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.1497, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.2746030390262604, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.1521, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.24607554078102112, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.1371, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.2447366714477539, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.1411, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.3005838096141815, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.1363, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.22351126372814178, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.0971, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.19229702651500702, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.087, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.2087402492761612, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.0866, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.06995195150375366, | |
| "eval_runtime": 34.7293, | |
| "eval_samples_per_second": 1.296, | |
| "eval_steps_per_second": 1.296, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.2082526534795761, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.0744, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.18972650170326233, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.0677, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.15210555493831635, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0534, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.18539117276668549, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.0487, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.17620058357715607, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.0454, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.15738727152347565, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.0351, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.11879970133304596, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.0329, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.0888441726565361, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.0275, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.10117721557617188, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.0273, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.09964396804571152, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.0303, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.027827324345707893, | |
| "eval_runtime": 34.0069, | |
| "eval_samples_per_second": 1.323, | |
| "eval_steps_per_second": 1.323, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.09134901314973831, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.0256, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.1198984906077385, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.0303, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.08325838297605515, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.0208, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.09585024416446686, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.0285, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.08273596316576004, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.0204, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.11438865959644318, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.021, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.09493660926818848, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.025, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.07655069231987, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.0171, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.1291963756084442, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.0208, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.09888683259487152, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.0158, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.019997378811240196, | |
| "eval_runtime": 33.868, | |
| "eval_samples_per_second": 1.329, | |
| "eval_steps_per_second": 1.329, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.08587799221277237, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.0202, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.11007233709096909, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.0207, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.1075129508972168, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.0183, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.08770933747291565, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0184, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.09319794178009033, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.0157, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.09335294365882874, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.0161, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.09088359028100967, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.0214, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.10883085429668427, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.0194, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.0793033093214035, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.0154, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.06822165846824646, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.017, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.017982618883252144, | |
| "eval_runtime": 33.882, | |
| "eval_samples_per_second": 1.328, | |
| "eval_steps_per_second": 1.328, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.10045751929283142, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0185, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.08925819396972656, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.0166, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.07123195379972458, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.0176, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.07266723364591599, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.015, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.08309267461299896, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.0165, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.061351366341114044, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.0167, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.06396614760160446, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.0139, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.07251725345849991, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0154, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.05715200677514076, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.0141, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.07328388839960098, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.0132, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.01624014787375927, | |
| "eval_runtime": 33.8652, | |
| "eval_samples_per_second": 1.329, | |
| "eval_steps_per_second": 1.329, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.047515422105789185, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.0114, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.06575234979391098, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.0125, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.05306783691048622, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0122, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.06478891521692276, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.0145, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.0635116770863533, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0129, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.07700419425964355, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.0129, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.054616447538137436, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.012, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.052965547889471054, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.0116, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.06303577870130539, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0122, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.07790898531675339, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.01, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.015550716780126095, | |
| "eval_runtime": 33.8678, | |
| "eval_samples_per_second": 1.329, | |
| "eval_steps_per_second": 1.329, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.06859813630580902, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0108, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.059151791036129, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0094, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.07225264608860016, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.0113, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.062095895409584045, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.012, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.10294982045888901, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0134, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.09647207707166672, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0107, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.05926242098212242, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.0131, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.0715462863445282, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0123, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.07793395966291428, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0119, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.08099521696567535, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0147, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.015393273904919624, | |
| "eval_runtime": 33.8821, | |
| "eval_samples_per_second": 1.328, | |
| "eval_steps_per_second": 1.328, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.09489183872938156, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0115, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.07101252675056458, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.0121, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.08010490983724594, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0153, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.06497953087091446, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0114, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.06178692355751991, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0125, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.05926448106765747, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.014, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.05290903523564339, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0084, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.057583536952733994, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0122, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.051079414784908295, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.011, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.06656457483768463, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0114, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.015239902772009373, | |
| "eval_runtime": 33.9129, | |
| "eval_samples_per_second": 1.327, | |
| "eval_steps_per_second": 1.327, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.052675649523735046, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0101, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.062444377690553665, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0089, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.04709114134311676, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0082, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.050120994448661804, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0091, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.059984926134347916, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0107, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.05490294471383095, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0097, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.05020734667778015, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0115, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.07408353686332703, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0115, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.0462699793279171, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.008, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.07202935218811035, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0105, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.015150871127843857, | |
| "eval_runtime": 33.9319, | |
| "eval_samples_per_second": 1.326, | |
| "eval_steps_per_second": 1.326, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.06206715106964111, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.0099, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.05500008910894394, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.009, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.043605607002973557, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0094, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.05252497270703316, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0091, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.05935841053724289, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0097, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.06067981570959091, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0088, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.06056810915470123, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0118, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.06950204819440842, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0098, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.06430943310260773, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0098, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.06338050961494446, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0116, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.015350483357906342, | |
| "eval_runtime": 33.9756, | |
| "eval_samples_per_second": 1.324, | |
| "eval_steps_per_second": 1.324, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.05366296321153641, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0088, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.04958593472838402, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.0092, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.055580854415893555, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0091, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.06366383284330368, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.008, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.04874936118721962, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0091, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.056903958320617676, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.008, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.04988300800323486, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0088, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.0554828941822052, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0096, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.04456499591469765, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0069, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.055592332035303116, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0103, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.015325266867876053, | |
| "eval_runtime": 33.9529, | |
| "eval_samples_per_second": 1.325, | |
| "eval_steps_per_second": 1.325, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.04917145520448685, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0077, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.059481002390384674, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0105, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.051867205649614334, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0081, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.057682864367961884, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0077, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.05795108526945114, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0104, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.05662466213107109, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0111, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.062402110546827316, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.009, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.057597823441028595, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0084, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.058831024914979935, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0104, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.05306454747915268, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0075, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.015353033319115639, | |
| "eval_runtime": 33.9912, | |
| "eval_samples_per_second": 1.324, | |
| "eval_steps_per_second": 1.324, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.04983245208859444, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0089, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.0667429119348526, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0084, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.061287686228752136, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.0088, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.04979460686445236, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0081, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.05955219268798828, | |
| "learning_rate": 0.0, | |
| "loss": 0.0102, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.9835335038939955e+17, | |
| "train_loss": 0.024442945823073388, | |
| "train_runtime": 6275.5304, | |
| "train_samples_per_second": 0.323, | |
| "train_steps_per_second": 0.02 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9835335038939955e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |