| { | |
| "best_metric": 0.052800051867961884, | |
| "best_model_checkpoint": "saves/psy-course-doc-info/Llama-3.1-8B-Instruct/train/fold6/checkpoint-110", | |
| "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": 0.5146947503089905, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.4084, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.4019896984100342, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.3408, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.5166494846343994, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.3892, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.3998715579509735, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.3429, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.45492351055145264, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.3341, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.4303339123725891, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.342, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.4862079918384552, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.3587, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.3997127413749695, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.2992, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.3324596881866455, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.2757, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.4178152084350586, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.265, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.27192339301109314, | |
| "eval_runtime": 25.982, | |
| "eval_samples_per_second": 1.732, | |
| "eval_steps_per_second": 1.732, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.48562926054000854, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.2865, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.4852800965309143, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.2422, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.48137393593788147, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2421, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.3652872145175934, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.2099, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.34822386503219604, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.209, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.3031443655490875, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.1967, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.31227704882621765, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.1765, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.3406769633293152, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.1795, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.32388052344322205, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.1576, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.2666756212711334, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.1689, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.14510378241539001, | |
| "eval_runtime": 25.986, | |
| "eval_samples_per_second": 1.732, | |
| "eval_steps_per_second": 1.732, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.25905218720436096, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.1437, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.3037348687648773, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.1623, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.34230226278305054, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.1272, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.418644517660141, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.1437, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.28610771894454956, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.138, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.5024089813232422, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.2049, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.2994146943092346, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0987, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.3435674011707306, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.1196, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.30092939734458923, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.1156, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.2616022825241089, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.1027, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.10370857268571854, | |
| "eval_runtime": 25.9985, | |
| "eval_samples_per_second": 1.731, | |
| "eval_steps_per_second": 1.731, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.23512841761112213, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.1173, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.2797624468803406, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.1047, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.21222670376300812, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.0901, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.22136375308036804, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0961, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.2523188292980194, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.0986, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.24723868072032928, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.0951, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.22367025911808014, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.0835, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.3691348433494568, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.0958, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.2751408517360687, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.0917, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.23567897081375122, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.0848, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.08050418645143509, | |
| "eval_runtime": 25.9982, | |
| "eval_samples_per_second": 1.731, | |
| "eval_steps_per_second": 1.731, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.31919142603874207, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0818, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.2822875678539276, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.0775, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.3018384277820587, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.0828, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.2712375521659851, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.073, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.35071420669555664, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.087, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.2117828130722046, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.0595, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.3012438118457794, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.1004, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.21643108129501343, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0645, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.23656418919563293, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.0908, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.21919803321361542, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.0671, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.06918726116418839, | |
| "eval_runtime": 26.0005, | |
| "eval_samples_per_second": 1.731, | |
| "eval_steps_per_second": 1.731, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.49693554639816284, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.1146, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.19470937550067902, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.055, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.19454921782016754, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0624, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.25666776299476624, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.0711, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.2294730246067047, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0646, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.20461145043373108, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.0524, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.2858906686306, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.0686, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.32071003317832947, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.0805, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.22127433121204376, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0651, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.2365463823080063, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0635, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.061441570520401, | |
| "eval_runtime": 26.0166, | |
| "eval_samples_per_second": 1.73, | |
| "eval_steps_per_second": 1.73, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.24754828214645386, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0556, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.21690750122070312, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0598, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.2789786458015442, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.074, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.187678262591362, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.051, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.17922283709049225, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0612, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.20609335601329803, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0623, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.24197928607463837, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.0547, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.20105622708797455, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0555, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.2905729115009308, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0608, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.22538885474205017, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0637, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.06007562205195427, | |
| "eval_runtime": 26.0197, | |
| "eval_samples_per_second": 1.729, | |
| "eval_steps_per_second": 1.729, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.22092154622077942, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0546, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.16019904613494873, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.0456, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.20831051468849182, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0608, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.17661935091018677, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0505, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.238091841340065, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0558, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.41548091173171997, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0997, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.1865716576576233, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0498, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.17337585985660553, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.046, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.20592160522937775, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0528, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.22112375497817993, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0525, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.05618962645530701, | |
| "eval_runtime": 26.0008, | |
| "eval_samples_per_second": 1.731, | |
| "eval_steps_per_second": 1.731, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.21675719320774078, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0392, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.17582350969314575, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0474, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.1740693897008896, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0513, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.22133827209472656, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0502, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.1794731616973877, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0438, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.1969956010580063, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0575, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.20567215979099274, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0472, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.19513347744941711, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0479, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.19764341413974762, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0491, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.19821615517139435, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0567, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.0555027574300766, | |
| "eval_runtime": 25.9911, | |
| "eval_samples_per_second": 1.731, | |
| "eval_steps_per_second": 1.731, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.20487791299819946, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.0562, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.18421317636966705, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0505, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.20219753682613373, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.045, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.2213960587978363, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0475, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.21140997111797333, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0499, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.18448854982852936, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0401, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.1983409821987152, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0449, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.21478283405303955, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0633, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.18524666130542755, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0488, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.16829054057598114, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0437, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.05377759039402008, | |
| "eval_runtime": 25.9991, | |
| "eval_samples_per_second": 1.731, | |
| "eval_steps_per_second": 1.731, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.27219635248184204, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0592, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.4242662489414215, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.0903, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.1797526776790619, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0446, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.18448083102703094, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0383, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.13986733555793762, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0454, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.153441920876503, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0346, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.19964894652366638, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0465, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.17707543075084686, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0424, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.16833744943141937, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0461, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.19674107432365417, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0503, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.052800051867961884, | |
| "eval_runtime": 26.0016, | |
| "eval_samples_per_second": 1.731, | |
| "eval_steps_per_second": 1.731, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.15886488556861877, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0423, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.1287938952445984, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0352, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.18720778822898865, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0484, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.18879911303520203, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0459, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.22935695946216583, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.049, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.1820475161075592, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0509, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.19951429963111877, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0439, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.19163917005062103, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0506, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.18294872343540192, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0428, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.21816276013851166, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0521, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.0528191402554512, | |
| "eval_runtime": 26.0107, | |
| "eval_samples_per_second": 1.73, | |
| "eval_steps_per_second": 1.73, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.1912989616394043, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0453, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.1969219148159027, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0485, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.2046165019273758, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.0533, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.20170378684997559, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0466, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.15134376287460327, | |
| "learning_rate": 0.0, | |
| "loss": 0.0407, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.69590230591275e+17, | |
| "train_loss": 0.10049069952964783, | |
| "train_runtime": 4885.3949, | |
| "train_samples_per_second": 0.415, | |
| "train_steps_per_second": 0.026 | |
| } | |
| ], | |
| "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": 1.69590230591275e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |