| { | |
| "best_metric": 0.0826086550951004, | |
| "best_model_checkpoint": "saves/psy-course-doc-info/MentaLLaMA-chat-7B/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": 0.23379452526569366, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.3653, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.38269081711769104, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.5701, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.29890552163124084, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.4908, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.2320939600467682, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.3899, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.2590828239917755, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.4074, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.2968398928642273, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.4472, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.23495590686798096, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.3579, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.3406902551651001, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.4591, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.3091307580471039, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.4087, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.3242417573928833, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.3964, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.3730747103691101, | |
| "eval_runtime": 30.7503, | |
| "eval_samples_per_second": 1.463, | |
| "eval_steps_per_second": 1.463, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.296606183052063, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.3558, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 1.9387372732162476, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 1.8454, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.2125854343175888, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3125, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.23318788409233093, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.3063, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 1.4085311889648438, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 1.4939, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 1.1487336158752441, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.8605, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.1767246127128601, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.2455, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.19973139464855194, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.2446, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.1879604160785675, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.2369, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.23784227669239044, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.2367, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.24137747287750244, | |
| "eval_runtime": 31.0207, | |
| "eval_samples_per_second": 1.451, | |
| "eval_steps_per_second": 1.451, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.18966764211654663, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.2287, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.1852101981639862, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.2013, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.17951731383800507, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.2083, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.5945624113082886, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.3977, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.1589384227991104, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.2016, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.25356489419937134, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.3186, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.14721356332302094, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1797, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.14408989250659943, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.1618, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.2013700306415558, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.2138, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.14896339178085327, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.1494, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.1709626317024231, | |
| "eval_runtime": 30.881, | |
| "eval_samples_per_second": 1.457, | |
| "eval_steps_per_second": 1.457, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.13771717250347137, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.151, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 2.0878639221191406, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.7078, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.3051440417766571, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.2622, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.1416388750076294, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1344, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.178971529006958, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.1736, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.6260426044464111, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.3256, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.1311056762933731, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.1138, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.25532424449920654, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.2152, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.18685665726661682, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.1737, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.1918065845966339, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.1387, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.14503218233585358, | |
| "eval_runtime": 31.1011, | |
| "eval_samples_per_second": 1.447, | |
| "eval_steps_per_second": 1.447, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.19696283340454102, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1488, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.17390817403793335, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.1335, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.1966904252767563, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.1396, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 1.2149896621704102, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.4098, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.28715962171554565, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.2135, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.14478421211242676, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.124, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.1873386651277542, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.1306, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.2636202871799469, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1008, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.18967285752296448, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.149, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.17793232202529907, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.1217, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.12450981140136719, | |
| "eval_runtime": 31.0739, | |
| "eval_samples_per_second": 1.448, | |
| "eval_steps_per_second": 1.448, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.349618524312973, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.1869, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.2017081379890442, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.1067, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.16659758985042572, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0949, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.21230676770210266, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.1186, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.24930888414382935, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0981, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.21169251203536987, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.1113, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.21746277809143066, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.129, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.1997109353542328, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.0935, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.1949642300605774, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0938, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.3156469166278839, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.1619, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.10886365920305252, | |
| "eval_runtime": 31.0811, | |
| "eval_samples_per_second": 1.448, | |
| "eval_steps_per_second": 1.448, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.2106146514415741, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.1045, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.23380246758460999, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1149, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.1971890777349472, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.0959, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.20937186479568481, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0878, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 4.234495162963867, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.728, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.21267755329608917, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0707, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.2758687436580658, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.1203, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.26877880096435547, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.1023, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.22849218547344208, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0808, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.30066975951194763, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0898, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.09731356054544449, | |
| "eval_runtime": 30.7677, | |
| "eval_samples_per_second": 1.463, | |
| "eval_steps_per_second": 1.463, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.15799197554588318, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0739, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.22999851405620575, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.1672, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.19496366381645203, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0892, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.22875598073005676, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0876, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.1938869208097458, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.098, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.32159966230392456, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1989, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.20841865241527557, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.1076, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.21569669246673584, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0903, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.1733500212430954, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0814, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.18550099432468414, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0722, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.08973520994186401, | |
| "eval_runtime": 30.9684, | |
| "eval_samples_per_second": 1.453, | |
| "eval_steps_per_second": 1.453, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.17454929649829865, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0739, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.22093729674816132, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0941, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.1803879290819168, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0747, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.20230059325695038, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0688, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.21432296931743622, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0749, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.22255626320838928, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.1196, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.6395688056945801, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.2457, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.22127795219421387, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.1024, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.23985256254673004, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0859, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.1938234567642212, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0731, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.08613130450248718, | |
| "eval_runtime": 30.8113, | |
| "eval_samples_per_second": 1.461, | |
| "eval_steps_per_second": 1.461, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.1874358355998993, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.081, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.16792158782482147, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0734, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.2021740823984146, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.072, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.48607754707336426, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.2722, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.21351835131645203, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0828, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.20002371072769165, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.081, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.18304619193077087, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0711, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.2650962173938751, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0743, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.24449852108955383, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0778, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.19059909880161285, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0815, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.08394669741392136, | |
| "eval_runtime": 31.0345, | |
| "eval_samples_per_second": 1.45, | |
| "eval_steps_per_second": 1.45, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.2761356830596924, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.1078, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.33258873224258423, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.1696, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.1938905119895935, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0606, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.19631120562553406, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0695, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.192363440990448, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0716, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.1669272929430008, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0687, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.2094244509935379, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0756, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.18058207631111145, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0638, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.3677760660648346, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.2091, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.17185920476913452, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0645, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.08281425386667252, | |
| "eval_runtime": 31.0534, | |
| "eval_samples_per_second": 1.449, | |
| "eval_steps_per_second": 1.449, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.17028263211250305, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0619, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.22767986357212067, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0836, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.24015401303768158, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0692, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.18320655822753906, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0666, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.2382071614265442, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0802, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.21920350193977356, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0979, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.2299313247203827, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0936, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.17599497735500336, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0592, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.17056764662265778, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0704, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.4011198878288269, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.2197, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.0826086550951004, | |
| "eval_runtime": 30.911, | |
| "eval_samples_per_second": 1.456, | |
| "eval_steps_per_second": 1.456, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.164878249168396, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0578, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.1911156326532364, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0817, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.22381922602653503, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.1128, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.16524603962898254, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0628, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.1745150089263916, | |
| "learning_rate": 0.0, | |
| "loss": 0.0646, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.8335272410375782e+17, | |
| "train_loss": 0.19870565083622932, | |
| "train_runtime": 5829.1193, | |
| "train_samples_per_second": 0.347, | |
| "train_steps_per_second": 0.021 | |
| } | |
| ], | |
| "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": 1.8335272410375782e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |