| { | |
| "best_metric": 0.07381793856620789, | |
| "best_model_checkpoint": "saves/psy-course-doc-info/MentaLLaMA-chat-7B/train/fold6/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": 0.32478809356689453, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.4659, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.2620335519313812, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.4204, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.3262457251548767, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.4538, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.4991602897644043, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.6887, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.27236494421958923, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.4345, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 1.3623758554458618, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 1.7838, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.2676299810409546, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.4136, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.27173227071762085, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.397, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 1.354838252067566, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 1.5348, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.32246601581573486, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.369, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.38477885723114014, | |
| "eval_runtime": 31.6562, | |
| "eval_samples_per_second": 1.422, | |
| "eval_steps_per_second": 1.422, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 1.3938984870910645, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 1.8198, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.25469475984573364, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.3431, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.42517632246017456, | |
| "learning_rate": 0.0001, | |
| "loss": 0.435, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.3098965883255005, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.3534, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.2154952436685562, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.287, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.654240071773529, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.552, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.1943136602640152, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.2437, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 1.2268507480621338, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.6708, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.18212898075580597, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.2361, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.20087900757789612, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.2561, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.2379142791032791, | |
| "eval_runtime": 31.6393, | |
| "eval_samples_per_second": 1.422, | |
| "eval_steps_per_second": 1.422, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.20735177397727966, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.2299, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.39741283655166626, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.3477, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.15888196229934692, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.218, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.20267058908939362, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.2177, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.1831192970275879, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.2184, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.2856866121292114, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.3559, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.15155130624771118, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1668, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.18430307507514954, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.2145, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.18313036859035492, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.1855, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.20661067962646484, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.1691, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.16610924899578094, | |
| "eval_runtime": 31.7132, | |
| "eval_samples_per_second": 1.419, | |
| "eval_steps_per_second": 1.419, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.17118042707443237, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.1825, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.12542271614074707, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.1631, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.12957412004470825, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.1366, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.2876640856266022, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.2168, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 2.9788172245025635, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.8475, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.19929751753807068, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.1574, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.15917260944843292, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.1565, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.19141840934753418, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.1723, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.22241544723510742, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.1514, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.1491740643978119, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.1428, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.1387224793434143, | |
| "eval_runtime": 31.6161, | |
| "eval_samples_per_second": 1.423, | |
| "eval_steps_per_second": 1.423, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.13117845356464386, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1346, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.14411711692810059, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.1372, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.2150060087442398, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.1373, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.17487457394599915, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.1397, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 1.5705984830856323, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.8024, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.1369924247264862, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.0997, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.28891894221305847, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.2347, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.31669503450393677, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.2215, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.15486566722393036, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.142, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.1839512288570404, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.1599, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.1205218955874443, | |
| "eval_runtime": 31.4416, | |
| "eval_samples_per_second": 1.431, | |
| "eval_steps_per_second": 1.431, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.3672410249710083, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.1972, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.16895636916160583, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.1055, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.5028992891311646, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.2744, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.2840169072151184, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.1455, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.20649969577789307, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1599, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.15191799402236938, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.1089, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.2591889798641205, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.1875, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.20077136158943176, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.139, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.1763724386692047, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.1119, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.17624808847904205, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0987, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.10505478829145432, | |
| "eval_runtime": 31.5463, | |
| "eval_samples_per_second": 1.426, | |
| "eval_steps_per_second": 1.426, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.17565801739692688, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0982, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.24363920092582703, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1069, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.1984749585390091, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.13, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.1942579448223114, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0907, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.2665734887123108, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.1103, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.18069609999656677, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.1329, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.2113947719335556, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.0964, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.23326236009597778, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.1003, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.21670207381248474, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0932, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.22402864694595337, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.1006, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.09282485395669937, | |
| "eval_runtime": 31.5755, | |
| "eval_samples_per_second": 1.425, | |
| "eval_steps_per_second": 1.425, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.8194271326065063, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.2593, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.1597561538219452, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.0824, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.22981256246566772, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.1548, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.5234227180480957, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.2459, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.26020941138267517, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.1042, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.476631760597229, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1564, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.445199191570282, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.2107, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.4899861514568329, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.2389, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.19874149560928345, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.1021, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.2115294486284256, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0858, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.08395789563655853, | |
| "eval_runtime": 31.6333, | |
| "eval_samples_per_second": 1.423, | |
| "eval_steps_per_second": 1.423, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.22403383255004883, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0773, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.2578152120113373, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0844, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.2265167385339737, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0949, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.2276456654071808, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0909, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.317146897315979, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0849, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.22463715076446533, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0962, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.2270575910806656, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0712, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.20332981646060944, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0816, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.17840082943439484, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0791, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.22554729878902435, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.1106, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.07922010123729706, | |
| "eval_runtime": 31.5642, | |
| "eval_samples_per_second": 1.426, | |
| "eval_steps_per_second": 1.426, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.21418385207653046, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.1064, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.1914474219083786, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0846, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.2209601253271103, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0787, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.25902530550956726, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.1219, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.21699877083301544, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0961, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.19437795877456665, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0709, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.2808574140071869, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1363, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.44856542348861694, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.1931, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.1783359795808792, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0844, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.17846699059009552, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0753, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.07569331675767899, | |
| "eval_runtime": 31.7562, | |
| "eval_samples_per_second": 1.417, | |
| "eval_steps_per_second": 1.417, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.2215527892112732, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0922, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.4758608341217041, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.135, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.23134635388851166, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.1185, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.1720823049545288, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0654, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.39044344425201416, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.1581, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.1952170580625534, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0618, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.21796175837516785, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0873, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.1652745008468628, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0674, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.16285324096679688, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0737, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.3377809524536133, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.1736, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.07391906529664993, | |
| "eval_runtime": 31.6164, | |
| "eval_samples_per_second": 1.423, | |
| "eval_steps_per_second": 1.423, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.18528962135314941, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0824, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.16015830636024475, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0626, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.17608235776424408, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0774, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.20769166946411133, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0911, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.20691965520381927, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0883, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.22542032599449158, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0791, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.18762800097465515, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0799, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.19007661938667297, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0728, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.19705675542354584, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0707, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.24644461274147034, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0906, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.07381793856620789, | |
| "eval_runtime": 31.6513, | |
| "eval_samples_per_second": 1.422, | |
| "eval_steps_per_second": 1.422, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.2570807933807373, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0973, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.18208199739456177, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0813, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.22572754323482513, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.1027, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.20760974287986755, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0778, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.34963181614875793, | |
| "learning_rate": 0.0, | |
| "loss": 0.1786, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.8699637827148186e+17, | |
| "train_loss": 0.22024629747867583, | |
| "train_runtime": 6227.7986, | |
| "train_samples_per_second": 0.325, | |
| "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": 1.8699637827148186e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |