| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06521827742224759, | |
| "eval_steps": 100, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016304569355561895, | |
| "eval_loss": 0.8931331634521484, | |
| "eval_runtime": 103.0135, | |
| "eval_samples_per_second": 25.074, | |
| "eval_steps_per_second": 12.542, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008152284677780948, | |
| "grad_norm": 0.12432650476694107, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8325, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016304569355561896, | |
| "grad_norm": 0.07345214486122131, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7545, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0024456854033342843, | |
| "grad_norm": 0.10935397446155548, | |
| "learning_rate": 9.995944990857849e-05, | |
| "loss": 0.749, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003260913871112379, | |
| "grad_norm": 0.08493407070636749, | |
| "learning_rate": 9.983786540671051e-05, | |
| "loss": 0.8535, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004076142338890474, | |
| "grad_norm": 0.12133610993623734, | |
| "learning_rate": 9.96354437049027e-05, | |
| "loss": 0.7942, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004891370806668569, | |
| "grad_norm": 0.1005958840250969, | |
| "learning_rate": 9.935251313189564e-05, | |
| "loss": 0.7716, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005706599274446664, | |
| "grad_norm": 0.15381614863872528, | |
| "learning_rate": 9.898953260211338e-05, | |
| "loss": 0.7529, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006521827742224758, | |
| "grad_norm": 0.13883520662784576, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 0.784, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0073370562100028534, | |
| "grad_norm": 0.13536342978477478, | |
| "learning_rate": 9.802590558156862e-05, | |
| "loss": 0.7463, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008152284677780949, | |
| "grad_norm": 0.11243531107902527, | |
| "learning_rate": 9.742682209735727e-05, | |
| "loss": 0.7407, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008967513145559042, | |
| "grad_norm": 0.11041439324617386, | |
| "learning_rate": 9.675081213427076e-05, | |
| "loss": 0.7344, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.009782741613337137, | |
| "grad_norm": 0.14278548955917358, | |
| "learning_rate": 9.599897218294122e-05, | |
| "loss": 0.7297, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.010597970081115233, | |
| "grad_norm": 0.35408827662467957, | |
| "learning_rate": 9.517252173051911e-05, | |
| "loss": 0.7141, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.011413198548893328, | |
| "grad_norm": 0.14454330503940582, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 0.7633, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.012228427016671423, | |
| "grad_norm": 0.1598002314567566, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7148, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.013043655484449516, | |
| "grad_norm": 0.25007447600364685, | |
| "learning_rate": 9.225950427718975e-05, | |
| "loss": 0.7256, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.013858883952227612, | |
| "grad_norm": 0.17986750602722168, | |
| "learning_rate": 9.114919329468282e-05, | |
| "loss": 0.7391, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.014674112420005707, | |
| "grad_norm": 0.17775388062000275, | |
| "learning_rate": 8.997213817017507e-05, | |
| "loss": 0.6845, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.015489340887783802, | |
| "grad_norm": 0.23661121726036072, | |
| "learning_rate": 8.873024809138272e-05, | |
| "loss": 0.7645, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.016304569355561897, | |
| "grad_norm": 0.18184030055999756, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 0.8042, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.016304569355561897, | |
| "eval_loss": 0.7536669373512268, | |
| "eval_runtime": 102.391, | |
| "eval_samples_per_second": 25.227, | |
| "eval_steps_per_second": 12.618, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.017119797823339993, | |
| "grad_norm": 0.23096653819084167, | |
| "learning_rate": 8.606012236719073e-05, | |
| "loss": 0.6521, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.017935026291118084, | |
| "grad_norm": 0.21091365814208984, | |
| "learning_rate": 8.463621767547998e-05, | |
| "loss": 0.6747, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.01875025475889618, | |
| "grad_norm": 0.16294293105602264, | |
| "learning_rate": 8.315613291203976e-05, | |
| "loss": 0.6636, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.019565483226674275, | |
| "grad_norm": 0.17157024145126343, | |
| "learning_rate": 8.162226877976887e-05, | |
| "loss": 0.7743, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02038071169445237, | |
| "grad_norm": 0.1470104157924652, | |
| "learning_rate": 8.003711321189895e-05, | |
| "loss": 0.7405, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.021195940162230465, | |
| "grad_norm": 0.13396376371383667, | |
| "learning_rate": 7.840323733655778e-05, | |
| "loss": 0.6663, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.02201116863000856, | |
| "grad_norm": 0.18456505239009857, | |
| "learning_rate": 7.672329130639005e-05, | |
| "loss": 0.755, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.022826397097786656, | |
| "grad_norm": 0.1341053545475006, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6231, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.02364162556556475, | |
| "grad_norm": 0.15663418173789978, | |
| "learning_rate": 7.323615860218843e-05, | |
| "loss": 0.7846, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.024456854033342846, | |
| "grad_norm": 0.16723978519439697, | |
| "learning_rate": 7.143462807015271e-05, | |
| "loss": 0.6989, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.025272082501120938, | |
| "grad_norm": 0.19980840384960175, | |
| "learning_rate": 6.959833049300377e-05, | |
| "loss": 0.7202, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.026087310968899033, | |
| "grad_norm": 0.16260208189487457, | |
| "learning_rate": 6.773024435212678e-05, | |
| "loss": 0.7097, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.026902539436677128, | |
| "grad_norm": 0.2040923684835434, | |
| "learning_rate": 6.583339969007363e-05, | |
| "loss": 0.6251, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.027717767904455223, | |
| "grad_norm": 0.140736386179924, | |
| "learning_rate": 6.391087319582264e-05, | |
| "loss": 0.7478, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.02853299637223332, | |
| "grad_norm": 0.23201903700828552, | |
| "learning_rate": 6.19657832143779e-05, | |
| "loss": 0.6886, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.029348224840011414, | |
| "grad_norm": 0.20656245946884155, | |
| "learning_rate": 6.0001284688802226e-05, | |
| "loss": 0.6724, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03016345330778951, | |
| "grad_norm": 0.1894981861114502, | |
| "learning_rate": 5.8020564042888015e-05, | |
| "loss": 0.7793, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.030978681775567604, | |
| "grad_norm": 0.1519327610731125, | |
| "learning_rate": 5.602683401276615e-05, | |
| "loss": 0.6349, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.0317939102433457, | |
| "grad_norm": 0.16416174173355103, | |
| "learning_rate": 5.402332843583631e-05, | |
| "loss": 0.7005, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.032609138711123795, | |
| "grad_norm": 0.13308531045913696, | |
| "learning_rate": 5.201329700547076e-05, | |
| "loss": 0.6768, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.032609138711123795, | |
| "eval_loss": 0.7349870204925537, | |
| "eval_runtime": 102.1982, | |
| "eval_samples_per_second": 25.274, | |
| "eval_steps_per_second": 12.642, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03342436717890189, | |
| "grad_norm": 0.18553270399570465, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6936, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.034239595646679985, | |
| "grad_norm": 0.1617966592311859, | |
| "learning_rate": 4.798670299452926e-05, | |
| "loss": 0.7387, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.03505482411445808, | |
| "grad_norm": 0.23151330649852753, | |
| "learning_rate": 4.597667156416371e-05, | |
| "loss": 0.6698, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.03587005258223617, | |
| "grad_norm": 0.172349214553833, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 0.6974, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.036685281050014264, | |
| "grad_norm": 0.15773482620716095, | |
| "learning_rate": 4.197943595711198e-05, | |
| "loss": 0.7278, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.03750050951779236, | |
| "grad_norm": 0.1810629963874817, | |
| "learning_rate": 3.9998715311197785e-05, | |
| "loss": 0.6484, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.038315737985570454, | |
| "grad_norm": 0.18713156878948212, | |
| "learning_rate": 3.803421678562213e-05, | |
| "loss": 0.684, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.03913096645334855, | |
| "grad_norm": 0.25403130054473877, | |
| "learning_rate": 3.608912680417737e-05, | |
| "loss": 0.7086, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.039946194921126645, | |
| "grad_norm": 0.15474697947502136, | |
| "learning_rate": 3.4166600309926387e-05, | |
| "loss": 0.6171, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.04076142338890474, | |
| "grad_norm": 0.17823943495750427, | |
| "learning_rate": 3.226975564787322e-05, | |
| "loss": 0.6566, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.041576651856682835, | |
| "grad_norm": 0.34823134541511536, | |
| "learning_rate": 3.0401669506996256e-05, | |
| "loss": 0.6684, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.04239188032446093, | |
| "grad_norm": 0.15805622935295105, | |
| "learning_rate": 2.8565371929847284e-05, | |
| "loss": 0.6549, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.043207108792239025, | |
| "grad_norm": 0.13102880120277405, | |
| "learning_rate": 2.6763841397811573e-05, | |
| "loss": 0.6221, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.04402233726001712, | |
| "grad_norm": 0.15072394907474518, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.699, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.044837565727795216, | |
| "grad_norm": 0.18680483102798462, | |
| "learning_rate": 2.3276708693609943e-05, | |
| "loss": 0.7056, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.04565279419557331, | |
| "grad_norm": 0.19171744585037231, | |
| "learning_rate": 2.1596762663442218e-05, | |
| "loss": 0.6821, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.046468022663351406, | |
| "grad_norm": 0.2306189388036728, | |
| "learning_rate": 1.996288678810105e-05, | |
| "loss": 0.725, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.0472832511311295, | |
| "grad_norm": 0.2382626235485077, | |
| "learning_rate": 1.837773122023114e-05, | |
| "loss": 0.7041, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.0480984795989076, | |
| "grad_norm": 0.2878624498844147, | |
| "learning_rate": 1.684386708796025e-05, | |
| "loss": 0.7284, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.04891370806668569, | |
| "grad_norm": 0.2006363421678543, | |
| "learning_rate": 1.536378232452003e-05, | |
| "loss": 0.7574, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.04891370806668569, | |
| "eval_loss": 0.7295248508453369, | |
| "eval_runtime": 102.1368, | |
| "eval_samples_per_second": 25.29, | |
| "eval_steps_per_second": 12.65, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.04972893653446378, | |
| "grad_norm": 0.19537951052188873, | |
| "learning_rate": 1.3939877632809278e-05, | |
| "loss": 0.7115, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.050544165002241875, | |
| "grad_norm": 0.19865351915359497, | |
| "learning_rate": 1.257446259144494e-05, | |
| "loss": 0.7565, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.05135939347001997, | |
| "grad_norm": 0.15447907149791718, | |
| "learning_rate": 1.1269751908617277e-05, | |
| "loss": 0.6733, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.052174621937798066, | |
| "grad_norm": 0.2033657431602478, | |
| "learning_rate": 1.0027861829824952e-05, | |
| "loss": 0.7061, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.05298985040557616, | |
| "grad_norm": 0.16816996037960052, | |
| "learning_rate": 8.850806705317183e-06, | |
| "loss": 0.6847, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.053805078873354256, | |
| "grad_norm": 0.2432698756456375, | |
| "learning_rate": 7.740495722810271e-06, | |
| "loss": 0.7002, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.05462030734113235, | |
| "grad_norm": 0.24160774052143097, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.6765, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.05543553580891045, | |
| "grad_norm": 0.200673907995224, | |
| "learning_rate": 5.727198717339511e-06, | |
| "loss": 0.7059, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.05625076427668854, | |
| "grad_norm": 0.19187721610069275, | |
| "learning_rate": 4.827478269480895e-06, | |
| "loss": 0.6578, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.05706599274446664, | |
| "grad_norm": 0.23926900327205658, | |
| "learning_rate": 4.001027817058789e-06, | |
| "loss": 0.7351, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.05788122121224473, | |
| "grad_norm": 0.23108696937561035, | |
| "learning_rate": 3.249187865729264e-06, | |
| "loss": 0.6804, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.05869644968002283, | |
| "grad_norm": 0.20840156078338623, | |
| "learning_rate": 2.573177902642726e-06, | |
| "loss": 0.7588, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.05951167814780092, | |
| "grad_norm": 0.1447313278913498, | |
| "learning_rate": 1.974094418431388e-06, | |
| "loss": 0.6967, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.06032690661557902, | |
| "grad_norm": 0.22718173265457153, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 0.703, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.06114213508335711, | |
| "grad_norm": 0.19592629373073578, | |
| "learning_rate": 1.0104673978866164e-06, | |
| "loss": 0.73, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.06195736355113521, | |
| "grad_norm": 0.174259752035141, | |
| "learning_rate": 6.474868681043578e-07, | |
| "loss": 0.7086, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.0627725920189133, | |
| "grad_norm": 0.17397546768188477, | |
| "learning_rate": 3.6455629509730136e-07, | |
| "loss": 0.7023, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.0635878204866914, | |
| "grad_norm": 0.19760173559188843, | |
| "learning_rate": 1.6213459328950352e-07, | |
| "loss": 0.7668, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.0644030489544695, | |
| "grad_norm": 0.24907608330249786, | |
| "learning_rate": 4.055009142152067e-08, | |
| "loss": 0.7054, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.06521827742224759, | |
| "grad_norm": 0.35565948486328125, | |
| "learning_rate": 0.0, | |
| "loss": 0.701, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06521827742224759, | |
| "eval_loss": 0.7286320924758911, | |
| "eval_runtime": 101.9776, | |
| "eval_samples_per_second": 25.329, | |
| "eval_steps_per_second": 12.669, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.729929899553587e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |