| { |
| "best_metric": 0.0748375654220581, |
| "best_model_checkpoint": "saves/psy-course-info-chain/MentaLLaMA-chat-7B/train/fold6/checkpoint-100", |
| "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": 0.9169460535049438, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.6925, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 0.8986674547195435, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.6802, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 0.8439714908599854, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.6236, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 0.7470906376838684, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.6305, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 0.7286505103111267, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.6238, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 1.1989717483520508, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 1.1519, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 0.8558933734893799, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.5489, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 0.9996872544288635, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.5509, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 1.3879613876342773, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 1.0905, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 1.0561827421188354, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.3968, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.30686724185943604, |
| "eval_runtime": 22.1488, |
| "eval_samples_per_second": 2.032, |
| "eval_steps_per_second": 2.032, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 1.2943023443222046, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.8073, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 0.6657110452651978, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.18, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 0.41621145606040955, |
| "learning_rate": 0.0001, |
| "loss": 0.1761, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.4403512477874756, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.1879, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.3638092875480652, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.1802, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 0.4242646396160126, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.1478, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.37074100971221924, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.1135, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.7582241892814636, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.2793, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.38015490770339966, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.1321, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.34248587489128113, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.1613, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.11490465700626373, |
| "eval_runtime": 22.118, |
| "eval_samples_per_second": 2.035, |
| "eval_steps_per_second": 2.035, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.30391812324523926, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.1451, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.29282206296920776, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.1753, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.3033871352672577, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.0988, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.33371463418006897, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.1388, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.5387976765632629, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.1467, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 0.4983171820640564, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.2139, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.23615597188472748, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.1008, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.2767801582813263, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.0987, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.26291826367378235, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.1449, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.25628983974456787, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.1248, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.0980871394276619, |
| "eval_runtime": 22.0418, |
| "eval_samples_per_second": 2.042, |
| "eval_steps_per_second": 2.042, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.32087409496307373, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.1263, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.21643130481243134, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.0754, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.29790735244750977, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.0943, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.3226020634174347, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.0925, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.7879056334495544, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.4045, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.38235238194465637, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.1237, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.20529428124427795, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.0875, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.22516275942325592, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.0718, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.26914745569229126, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.1295, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.23542962968349457, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.0973, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.08462860435247421, |
| "eval_runtime": 22.1165, |
| "eval_samples_per_second": 2.035, |
| "eval_steps_per_second": 2.035, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.1834987998008728, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.0604, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.331197589635849, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.0852, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.33960625529289246, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.1022, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.35516804456710815, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.059, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 2.4785263538360596, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.7148, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.3156376779079437, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.1027, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.2883512079715729, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.0949, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.5673321485519409, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.1484, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.38099104166030884, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.1212, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.2680504620075226, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.119, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.08180101215839386, |
| "eval_runtime": 22.17, |
| "eval_samples_per_second": 2.03, |
| "eval_steps_per_second": 2.03, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.5590800046920776, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.1424, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.20432162284851074, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.0664, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.7314401865005493, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.2772, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.21057157218456268, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.0704, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.29495662450790405, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.0842, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.31583964824676514, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.0987, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.40484264492988586, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.1136, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.25188755989074707, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.0925, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.22642043232917786, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.0567, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.18340834975242615, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.0892, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.07939217984676361, |
| "eval_runtime": 22.1402, |
| "eval_samples_per_second": 2.033, |
| "eval_steps_per_second": 2.033, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.24537509679794312, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0592, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.3490379750728607, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.0541, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.24011555314064026, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.0721, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.28131982684135437, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.0532, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.23307721316814423, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.0897, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.2739829123020172, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.1125, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.2735469341278076, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.0749, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.2104061394929886, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0523, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.2993415594100952, |
| "learning_rate": 5e-05, |
| "loss": 0.0716, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.2382691651582718, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.0624, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.0772421658039093, |
| "eval_runtime": 22.1438, |
| "eval_samples_per_second": 2.032, |
| "eval_steps_per_second": 2.032, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.9657453298568726, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.21, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.3391067385673523, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.0937, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.2690339982509613, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.0572, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.846718966960907, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.3082, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.2872736155986786, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.0474, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.5370579957962036, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.1375, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.6099308729171753, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.1689, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.5868359208106995, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.237, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.1952841579914093, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0548, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.24614837765693665, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.0461, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.07496241480112076, |
| "eval_runtime": 22.124, |
| "eval_samples_per_second": 2.034, |
| "eval_steps_per_second": 2.034, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.31054937839508057, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0621, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.22576239705085754, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.0649, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.2656700015068054, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0753, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.31435734033584595, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0567, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.20330354571342468, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0417, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.26089802384376526, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0516, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.2698304057121277, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.0697, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.29468604922294617, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.1032, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.2897825837135315, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0657, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.31990888714790344, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0736, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.07558552175760269, |
| "eval_runtime": 22.129, |
| "eval_samples_per_second": 2.034, |
| "eval_steps_per_second": 2.034, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.2695581614971161, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.0717, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.30007538199424744, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0644, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.19670215249061584, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0326, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.3278777003288269, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.0558, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.21833066642284393, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0538, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.1789599061012268, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0354, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.4348013401031494, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0899, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.5750954151153564, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.1984, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.3219102919101715, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.066, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.2799324095249176, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.0535, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.0748375654220581, |
| "eval_runtime": 22.1216, |
| "eval_samples_per_second": 2.034, |
| "eval_steps_per_second": 2.034, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.3985480070114136, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.084, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.6111393570899963, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0993, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.29938840866088867, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0556, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.22131609916687012, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.028, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.4337223172187805, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.1353, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.23699785768985748, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0548, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.22737370431423187, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0456, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.2377234846353531, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0547, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.2625718414783478, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0566, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.4952082931995392, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.1773, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.07582581043243408, |
| "eval_runtime": 22.1337, |
| "eval_samples_per_second": 2.033, |
| "eval_steps_per_second": 2.033, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.27143594622612, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.05, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.3428940176963806, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0855, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.31316643953323364, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0743, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.20271068811416626, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0399, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.2756154239177704, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0584, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.34340715408325195, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0673, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.32720911502838135, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0705, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.27625772356987, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0549, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.26519593596458435, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.0417, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.2958471179008484, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0533, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.07575639337301254, |
| "eval_runtime": 22.1456, |
| "eval_samples_per_second": 2.032, |
| "eval_steps_per_second": 2.032, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.3236151337623596, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.0713, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.20681829750537872, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.0417, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.3121144771575928, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0861, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.2348598837852478, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0479, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.4119131565093994, |
| "learning_rate": 0.0, |
| "loss": 0.1822, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.451506611561431e+17, |
| "train_loss": 0.1600769105255604, |
| "train_runtime": 4244.0943, |
| "train_samples_per_second": 0.477, |
| "train_steps_per_second": 0.029 |
| } |
| ], |
| "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": 1.451506611561431e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
