| { | |
| "best_metric": 0.06684371829032898, | |
| "best_model_checkpoint": "saves/psy-course-info-chain/Llama-3.1-8B-Instruct/train/fold1/checkpoint-120", | |
| "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": 1.7534302473068237, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.5276, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 1.6594399213790894, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.5322, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 1.7843174934387207, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.5109, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 1.7626229524612427, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.5394, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 1.815011739730835, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.519, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 1.5044406652450562, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.483, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 1.7126368284225464, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.424, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 1.967699646949768, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.3509, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 1.2087763547897339, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.193, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.7323130369186401, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.175, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.15156826376914978, | |
| "eval_runtime": 21.0352, | |
| "eval_samples_per_second": 2.139, | |
| "eval_steps_per_second": 2.139, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.5891270637512207, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.1207, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.6813968420028687, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.1954, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.946879506111145, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2548, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.8726567029953003, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.1641, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.6376297473907471, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.1747, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.5921506881713867, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.1838, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.6308391094207764, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.1716, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.4433191418647766, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.1243, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.5776513814926147, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.1369, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.3834328055381775, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.099, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.12395185977220535, | |
| "eval_runtime": 20.9205, | |
| "eval_samples_per_second": 2.151, | |
| "eval_steps_per_second": 2.151, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.42168161273002625, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.1307, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.3687320947647095, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.0919, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.3716530203819275, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.0851, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.5560383796691895, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.1307, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.4219168424606323, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.148, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.6669564247131348, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.1859, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.4102296531200409, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1018, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.5062835812568665, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.129, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.45242568850517273, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.1037, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.4103507697582245, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.0955, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.09509595483541489, | |
| "eval_runtime": 20.9712, | |
| "eval_samples_per_second": 2.146, | |
| "eval_steps_per_second": 2.146, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.4553764760494232, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.0872, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.4687905013561249, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.1058, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.48785629868507385, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.1469, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.3559998571872711, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1027, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.30200159549713135, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.0761, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.39950889348983765, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.1153, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.33219078183174133, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.0844, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.42346814274787903, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.102, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.4340456426143646, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.1239, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.3331095576286316, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.0741, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.0872035026550293, | |
| "eval_runtime": 20.931, | |
| "eval_samples_per_second": 2.15, | |
| "eval_steps_per_second": 2.15, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.4618953764438629, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1074, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.29720261693000793, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.0626, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.49544522166252136, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.105, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.4234393835067749, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.0895, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.5573832392692566, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.1134, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.4032742977142334, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.0992, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.29090389609336853, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.0357, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.40429532527923584, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0739, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.49074608087539673, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.1451, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.3378618359565735, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.0671, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.07864316552877426, | |
| "eval_runtime": 20.956, | |
| "eval_samples_per_second": 2.147, | |
| "eval_steps_per_second": 2.147, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.7849867939949036, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.1505, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.29336991906166077, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.0623, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.3683113157749176, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0722, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.44332262873649597, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.1282, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.3715544044971466, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0848, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.4191085696220398, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.0554, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.3467198610305786, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.0548, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.24871347844600677, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.0416, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.44350406527519226, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0542, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.27462178468704224, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0422, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.07898063957691193, | |
| "eval_runtime": 20.9796, | |
| "eval_samples_per_second": 2.145, | |
| "eval_steps_per_second": 2.145, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.3473226726055145, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0541, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.45636582374572754, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0886, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.47652554512023926, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.0751, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.3730301856994629, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0651, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.4122215807437897, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0681, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.506348729133606, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.044, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.47149717807769775, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.0497, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.4436272382736206, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0678, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.5666233897209167, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0608, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.5969477891921997, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0758, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.07115509361028671, | |
| "eval_runtime": 20.9773, | |
| "eval_samples_per_second": 2.145, | |
| "eval_steps_per_second": 2.145, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.5112955570220947, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0819, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.6357370615005493, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.1089, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.6567676663398743, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.1079, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.3676830232143402, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0751, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.4251662492752075, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0773, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.8321242928504944, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1391, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.32981082797050476, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0483, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.41706305742263794, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0563, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.4880906641483307, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0564, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.4189813733100891, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0359, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.07390694320201874, | |
| "eval_runtime": 21.022, | |
| "eval_samples_per_second": 2.141, | |
| "eval_steps_per_second": 2.141, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.32041606307029724, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0444, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.6350606679916382, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0665, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.38409528136253357, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0521, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.4244583249092102, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0896, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.3476863503456116, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0526, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.37426993250846863, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0486, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.5348115563392639, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.065, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.38502976298332214, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0453, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.34430432319641113, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0582, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.40302205085754395, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0385, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.07315154373645782, | |
| "eval_runtime": 21.0309, | |
| "eval_samples_per_second": 2.14, | |
| "eval_steps_per_second": 2.14, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.6493139266967773, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.1011, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.6032883524894714, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0751, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.4316764771938324, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0458, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.3671962022781372, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0589, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.3559502065181732, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0429, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.3240104615688324, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0474, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.31719568371772766, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0477, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.40934890508651733, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0504, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.45837289094924927, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0657, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.41513946652412415, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0507, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.0681799054145813, | |
| "eval_runtime": 21.0348, | |
| "eval_samples_per_second": 2.139, | |
| "eval_steps_per_second": 2.139, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.562179684638977, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0934, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 1.0771077871322632, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.1265, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.38524681329727173, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.043, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.49528777599334717, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0521, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.40660879015922546, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0451, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.3841019868850708, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0434, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.2953658103942871, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0347, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.36496424674987793, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0546, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.5377872586250305, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0643, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.26345789432525635, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0352, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.0669243261218071, | |
| "eval_runtime": 21.0024, | |
| "eval_samples_per_second": 2.143, | |
| "eval_steps_per_second": 2.143, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.3408642113208771, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.045, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.34921032190322876, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0592, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.2842159867286682, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0307, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.38709065318107605, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0423, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.2887662649154663, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.03, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.3436429500579834, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0361, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.38178807497024536, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0458, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.33953651785850525, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0538, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.4527745246887207, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0635, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.41231685876846313, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0603, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.06684371829032898, | |
| "eval_runtime": 21.0307, | |
| "eval_samples_per_second": 2.14, | |
| "eval_steps_per_second": 2.14, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.30335646867752075, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0231, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.36105185747146606, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0625, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.319932758808136, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.0508, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.31719672679901123, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0383, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.33628955483436584, | |
| "learning_rate": 0.0, | |
| "loss": 0.0472, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.3285867935773491e+17, | |
| "train_loss": 0.1088795803785324, | |
| "train_runtime": 3712.9103, | |
| "train_samples_per_second": 0.545, | |
| "train_steps_per_second": 0.034 | |
| } | |
| ], | |
| "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": 1.3285867935773491e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |