| { | |
| "best_metric": 1.55006742, | |
| "best_model_checkpoint": "/fs/clip-projects/geoguesser/vlms/qwen/output/qwen2-vl-7b-instruct/v5-20241108-053635/checkpoint-500", | |
| "epoch": 1.9962616822429906, | |
| "eval_steps": 50, | |
| "global_step": 534, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "acc": 0.55171263, | |
| "epoch": 0.003738317757009346, | |
| "grad_norm": 1.868323802947998, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 1.850384, | |
| "memory(GiB)": 31.32, | |
| "step": 1, | |
| "train_speed(iter/s)": 0.082547 | |
| }, | |
| { | |
| "acc": 0.51965243, | |
| "epoch": 0.018691588785046728, | |
| "grad_norm": 1.9730364084243774, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 2.06072664, | |
| "memory(GiB)": 39.03, | |
| "step": 5, | |
| "train_speed(iter/s)": 0.11522 | |
| }, | |
| { | |
| "acc": 0.54611473, | |
| "epoch": 0.037383177570093455, | |
| "grad_norm": 1.2351425886154175, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 1.92748413, | |
| "memory(GiB)": 40.38, | |
| "step": 10, | |
| "train_speed(iter/s)": 0.120543 | |
| }, | |
| { | |
| "acc": 0.53391666, | |
| "epoch": 0.056074766355140186, | |
| "grad_norm": 1.3700778484344482, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 1.8874958, | |
| "memory(GiB)": 41.74, | |
| "step": 15, | |
| "train_speed(iter/s)": 0.122255 | |
| }, | |
| { | |
| "acc": 0.53817282, | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 1.5009832382202148, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 1.8099781, | |
| "memory(GiB)": 41.74, | |
| "step": 20, | |
| "train_speed(iter/s)": 0.123099 | |
| }, | |
| { | |
| "acc": 0.55321841, | |
| "epoch": 0.09345794392523364, | |
| "grad_norm": 1.3406466245651245, | |
| "learning_rate": 9.25925925925926e-05, | |
| "loss": 1.6683075, | |
| "memory(GiB)": 41.74, | |
| "step": 25, | |
| "train_speed(iter/s)": 0.123552 | |
| }, | |
| { | |
| "acc": 0.55131054, | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 1.2054580450057983, | |
| "learning_rate": 9.999136119166803e-05, | |
| "loss": 1.78306332, | |
| "memory(GiB)": 43.11, | |
| "step": 30, | |
| "train_speed(iter/s)": 0.120219 | |
| }, | |
| { | |
| "acc": 0.54619265, | |
| "epoch": 0.1308411214953271, | |
| "grad_norm": 1.3058720827102661, | |
| "learning_rate": 9.99385792841537e-05, | |
| "loss": 1.81088448, | |
| "memory(GiB)": 43.11, | |
| "step": 35, | |
| "train_speed(iter/s)": 0.120961 | |
| }, | |
| { | |
| "acc": 0.56460981, | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 1.2871434688568115, | |
| "learning_rate": 9.983786540671051e-05, | |
| "loss": 1.69376984, | |
| "memory(GiB)": 44.48, | |
| "step": 40, | |
| "train_speed(iter/s)": 0.121524 | |
| }, | |
| { | |
| "acc": 0.57231364, | |
| "epoch": 0.16822429906542055, | |
| "grad_norm": 1.1757748126983643, | |
| "learning_rate": 9.968931622637652e-05, | |
| "loss": 1.6526125, | |
| "memory(GiB)": 44.48, | |
| "step": 45, | |
| "train_speed(iter/s)": 0.121972 | |
| }, | |
| { | |
| "acc": 0.56770124, | |
| "epoch": 0.18691588785046728, | |
| "grad_norm": 1.3221774101257324, | |
| "learning_rate": 9.949307432339625e-05, | |
| "loss": 1.70850391, | |
| "memory(GiB)": 44.48, | |
| "step": 50, | |
| "train_speed(iter/s)": 0.122298 | |
| }, | |
| { | |
| "epoch": 0.18691588785046728, | |
| "eval_acc": 0.5727995201679412, | |
| "eval_loss": 1.6454861164093018, | |
| "eval_runtime": 60.9474, | |
| "eval_samples_per_second": 0.82, | |
| "eval_steps_per_second": 0.82, | |
| "step": 50 | |
| }, | |
| { | |
| "acc": 0.56792145, | |
| "epoch": 0.205607476635514, | |
| "grad_norm": 1.3802762031555176, | |
| "learning_rate": 9.924932805436949e-05, | |
| "loss": 1.61318073, | |
| "memory(GiB)": 44.48, | |
| "step": 55, | |
| "train_speed(iter/s)": 0.10774 | |
| }, | |
| { | |
| "acc": 0.56201911, | |
| "epoch": 0.22429906542056074, | |
| "grad_norm": 1.4624619483947754, | |
| "learning_rate": 9.895831137146318e-05, | |
| "loss": 1.68176594, | |
| "memory(GiB)": 44.48, | |
| "step": 60, | |
| "train_speed(iter/s)": 0.109037 | |
| }, | |
| { | |
| "acc": 0.56515856, | |
| "epoch": 0.24299065420560748, | |
| "grad_norm": 1.3205868005752563, | |
| "learning_rate": 9.862030359785981e-05, | |
| "loss": 1.65190887, | |
| "memory(GiB)": 44.48, | |
| "step": 65, | |
| "train_speed(iter/s)": 0.110146 | |
| }, | |
| { | |
| "acc": 0.55511956, | |
| "epoch": 0.2616822429906542, | |
| "grad_norm": 1.3879112005233765, | |
| "learning_rate": 9.82356291596578e-05, | |
| "loss": 1.6682188, | |
| "memory(GiB)": 44.48, | |
| "step": 70, | |
| "train_speed(iter/s)": 0.111111 | |
| }, | |
| { | |
| "acc": 0.56104274, | |
| "epoch": 0.2803738317757009, | |
| "grad_norm": 1.3009270429611206, | |
| "learning_rate": 9.780465727448149e-05, | |
| "loss": 1.7461134, | |
| "memory(GiB)": 45.86, | |
| "step": 75, | |
| "train_speed(iter/s)": 0.110878 | |
| }, | |
| { | |
| "acc": 0.57672982, | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 1.3524978160858154, | |
| "learning_rate": 9.732780159709912e-05, | |
| "loss": 1.61342182, | |
| "memory(GiB)": 45.86, | |
| "step": 80, | |
| "train_speed(iter/s)": 0.111688 | |
| }, | |
| { | |
| "acc": 0.56858454, | |
| "epoch": 0.3177570093457944, | |
| "grad_norm": 1.368619680404663, | |
| "learning_rate": 9.680551982238942e-05, | |
| "loss": 1.62513695, | |
| "memory(GiB)": 45.86, | |
| "step": 85, | |
| "train_speed(iter/s)": 0.112415 | |
| }, | |
| { | |
| "acc": 0.56374822, | |
| "epoch": 0.3364485981308411, | |
| "grad_norm": 1.397831916809082, | |
| "learning_rate": 9.623831324603754e-05, | |
| "loss": 1.69306774, | |
| "memory(GiB)": 45.86, | |
| "step": 90, | |
| "train_speed(iter/s)": 0.113063 | |
| }, | |
| { | |
| "acc": 0.57811651, | |
| "epoch": 0.35514018691588783, | |
| "grad_norm": 1.271440029144287, | |
| "learning_rate": 9.562672628338233e-05, | |
| "loss": 1.63228798, | |
| "memory(GiB)": 45.86, | |
| "step": 95, | |
| "train_speed(iter/s)": 0.113645 | |
| }, | |
| { | |
| "acc": 0.5570353, | |
| "epoch": 0.37383177570093457, | |
| "grad_norm": 1.2964327335357666, | |
| "learning_rate": 9.497134594687634e-05, | |
| "loss": 1.72664585, | |
| "memory(GiB)": 45.86, | |
| "step": 100, | |
| "train_speed(iter/s)": 0.114174 | |
| }, | |
| { | |
| "epoch": 0.37383177570093457, | |
| "eval_acc": 0.5792472634577898, | |
| "eval_loss": 1.6085342168807983, | |
| "eval_runtime": 62.4797, | |
| "eval_samples_per_second": 0.8, | |
| "eval_steps_per_second": 0.8, | |
| "step": 100 | |
| }, | |
| { | |
| "acc": 0.57630959, | |
| "epoch": 0.3925233644859813, | |
| "grad_norm": 1.244130253791809, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 1.64715214, | |
| "memory(GiB)": 45.86, | |
| "step": 105, | |
| "train_speed(iter/s)": 0.107229 | |
| }, | |
| { | |
| "acc": 0.5584549, | |
| "epoch": 0.411214953271028, | |
| "grad_norm": 1.3243989944458008, | |
| "learning_rate": 9.353176276679396e-05, | |
| "loss": 1.68698692, | |
| "memory(GiB)": 45.86, | |
| "step": 110, | |
| "train_speed(iter/s)": 0.107951 | |
| }, | |
| { | |
| "acc": 0.5546257, | |
| "epoch": 0.42990654205607476, | |
| "grad_norm": 1.437445878982544, | |
| "learning_rate": 9.274894166171888e-05, | |
| "loss": 1.66922894, | |
| "memory(GiB)": 45.86, | |
| "step": 115, | |
| "train_speed(iter/s)": 0.10862 | |
| }, | |
| { | |
| "acc": 0.57244515, | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 1.3543046712875366, | |
| "learning_rate": 9.192508933357753e-05, | |
| "loss": 1.70311775, | |
| "memory(GiB)": 45.86, | |
| "step": 120, | |
| "train_speed(iter/s)": 0.109232 | |
| }, | |
| { | |
| "acc": 0.56850109, | |
| "epoch": 0.4672897196261682, | |
| "grad_norm": 1.287984013557434, | |
| "learning_rate": 9.106099653103728e-05, | |
| "loss": 1.61406059, | |
| "memory(GiB)": 45.86, | |
| "step": 125, | |
| "train_speed(iter/s)": 0.109801 | |
| }, | |
| { | |
| "acc": 0.56755419, | |
| "epoch": 0.48598130841121495, | |
| "grad_norm": 1.4639618396759033, | |
| "learning_rate": 9.015749262631536e-05, | |
| "loss": 1.57637978, | |
| "memory(GiB)": 45.86, | |
| "step": 130, | |
| "train_speed(iter/s)": 0.110329 | |
| }, | |
| { | |
| "acc": 0.58115373, | |
| "epoch": 0.5046728971962616, | |
| "grad_norm": 1.5570566654205322, | |
| "learning_rate": 8.921544481913218e-05, | |
| "loss": 1.62401295, | |
| "memory(GiB)": 45.86, | |
| "step": 135, | |
| "train_speed(iter/s)": 0.110827 | |
| }, | |
| { | |
| "acc": 0.55897279, | |
| "epoch": 0.5233644859813084, | |
| "grad_norm": 1.4730037450790405, | |
| "learning_rate": 8.823575730435693e-05, | |
| "loss": 1.66579857, | |
| "memory(GiB)": 52.51, | |
| "step": 140, | |
| "train_speed(iter/s)": 0.111291 | |
| }, | |
| { | |
| "acc": 0.56799178, | |
| "epoch": 0.5420560747663551, | |
| "grad_norm": 1.350874423980713, | |
| "learning_rate": 8.721937040414481e-05, | |
| "loss": 1.60019073, | |
| "memory(GiB)": 52.51, | |
| "step": 145, | |
| "train_speed(iter/s)": 0.111724 | |
| }, | |
| { | |
| "acc": 0.55238876, | |
| "epoch": 0.5607476635514018, | |
| "grad_norm": 1.5056456327438354, | |
| "learning_rate": 8.616725966539832e-05, | |
| "loss": 1.68097, | |
| "memory(GiB)": 52.51, | |
| "step": 150, | |
| "train_speed(iter/s)": 0.11205 | |
| }, | |
| { | |
| "epoch": 0.5607476635514018, | |
| "eval_acc": 0.5831458989353726, | |
| "eval_loss": 1.588950753211975, | |
| "eval_runtime": 60.5954, | |
| "eval_samples_per_second": 0.825, | |
| "eval_steps_per_second": 0.825, | |
| "step": 150 | |
| }, | |
| { | |
| "acc": 0.56648855, | |
| "epoch": 0.5794392523364486, | |
| "grad_norm": 1.4353731870651245, | |
| "learning_rate": 8.508043492341944e-05, | |
| "loss": 1.61546593, | |
| "memory(GiB)": 52.51, | |
| "step": 155, | |
| "train_speed(iter/s)": 0.107639 | |
| }, | |
| { | |
| "acc": 0.57423716, | |
| "epoch": 0.5981308411214953, | |
| "grad_norm": 1.514600396156311, | |
| "learning_rate": 8.395993933265101e-05, | |
| "loss": 1.65116329, | |
| "memory(GiB)": 52.51, | |
| "step": 160, | |
| "train_speed(iter/s)": 0.108123 | |
| }, | |
| { | |
| "acc": 0.56541142, | |
| "epoch": 0.616822429906542, | |
| "grad_norm": 1.3241384029388428, | |
| "learning_rate": 8.280684836543794e-05, | |
| "loss": 1.65839729, | |
| "memory(GiB)": 52.51, | |
| "step": 165, | |
| "train_speed(iter/s)": 0.108573 | |
| }, | |
| { | |
| "acc": 0.57026463, | |
| "epoch": 0.6355140186915887, | |
| "grad_norm": 1.3388739824295044, | |
| "learning_rate": 8.162226877976887e-05, | |
| "loss": 1.61102333, | |
| "memory(GiB)": 52.51, | |
| "step": 170, | |
| "train_speed(iter/s)": 0.109007 | |
| }, | |
| { | |
| "acc": 0.57890859, | |
| "epoch": 0.6542056074766355, | |
| "grad_norm": 1.37869131565094, | |
| "learning_rate": 8.040733755698955e-05, | |
| "loss": 1.60712547, | |
| "memory(GiB)": 52.51, | |
| "step": 175, | |
| "train_speed(iter/s)": 0.109415 | |
| }, | |
| { | |
| "acc": 0.57019186, | |
| "epoch": 0.6728971962616822, | |
| "grad_norm": 1.4313998222351074, | |
| "learning_rate": 7.916322081050709e-05, | |
| "loss": 1.62115898, | |
| "memory(GiB)": 52.51, | |
| "step": 180, | |
| "train_speed(iter/s)": 0.109805 | |
| }, | |
| { | |
| "acc": 0.57807865, | |
| "epoch": 0.6915887850467289, | |
| "grad_norm": 1.3123388290405273, | |
| "learning_rate": 7.789111266653285e-05, | |
| "loss": 1.63029137, | |
| "memory(GiB)": 52.51, | |
| "step": 185, | |
| "train_speed(iter/s)": 0.110173 | |
| }, | |
| { | |
| "acc": 0.58090611, | |
| "epoch": 0.7102803738317757, | |
| "grad_norm": 1.460463047027588, | |
| "learning_rate": 7.659223411793798e-05, | |
| "loss": 1.57071505, | |
| "memory(GiB)": 52.51, | |
| "step": 190, | |
| "train_speed(iter/s)": 0.110531 | |
| }, | |
| { | |
| "acc": 0.57307801, | |
| "epoch": 0.7289719626168224, | |
| "grad_norm": 1.3995453119277954, | |
| "learning_rate": 7.526783185232207e-05, | |
| "loss": 1.61080112, | |
| "memory(GiB)": 52.51, | |
| "step": 195, | |
| "train_speed(iter/s)": 0.110867 | |
| }, | |
| { | |
| "acc": 0.5799108, | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": 1.4361484050750732, | |
| "learning_rate": 7.391917705541927e-05, | |
| "loss": 1.64733868, | |
| "memory(GiB)": 52.51, | |
| "step": 200, | |
| "train_speed(iter/s)": 0.111188 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "eval_acc": 0.5834457939721097, | |
| "eval_loss": 1.570568561553955, | |
| "eval_runtime": 60.5903, | |
| "eval_samples_per_second": 0.825, | |
| "eval_steps_per_second": 0.825, | |
| "step": 200 | |
| }, | |
| { | |
| "acc": 0.56698923, | |
| "epoch": 0.7663551401869159, | |
| "grad_norm": 1.3287904262542725, | |
| "learning_rate": 7.254756419099074e-05, | |
| "loss": 1.64705162, | |
| "memory(GiB)": 52.51, | |
| "step": 205, | |
| "train_speed(iter/s)": 0.107887 | |
| }, | |
| { | |
| "acc": 0.57151198, | |
| "epoch": 0.7850467289719626, | |
| "grad_norm": 1.38331139087677, | |
| "learning_rate": 7.115430975837457e-05, | |
| "loss": 1.64652443, | |
| "memory(GiB)": 52.51, | |
| "step": 210, | |
| "train_speed(iter/s)": 0.108252 | |
| }, | |
| { | |
| "acc": 0.58841505, | |
| "epoch": 0.8037383177570093, | |
| "grad_norm": 1.5937939882278442, | |
| "learning_rate": 6.974075102888536e-05, | |
| "loss": 1.61707039, | |
| "memory(GiB)": 52.51, | |
| "step": 215, | |
| "train_speed(iter/s)": 0.108603 | |
| }, | |
| { | |
| "acc": 0.55511918, | |
| "epoch": 0.822429906542056, | |
| "grad_norm": 1.6487551927566528, | |
| "learning_rate": 6.830824476227646e-05, | |
| "loss": 1.65553608, | |
| "memory(GiB)": 52.51, | |
| "step": 220, | |
| "train_speed(iter/s)": 0.108935 | |
| }, | |
| { | |
| "acc": 0.58533549, | |
| "epoch": 0.8411214953271028, | |
| "grad_norm": 1.4343266487121582, | |
| "learning_rate": 6.685816590449708e-05, | |
| "loss": 1.58468885, | |
| "memory(GiB)": 52.51, | |
| "step": 225, | |
| "train_speed(iter/s)": 0.109256 | |
| }, | |
| { | |
| "acc": 0.57694592, | |
| "epoch": 0.8598130841121495, | |
| "grad_norm": 1.368004560470581, | |
| "learning_rate": 6.539190626799366e-05, | |
| "loss": 1.60840836, | |
| "memory(GiB)": 52.51, | |
| "step": 230, | |
| "train_speed(iter/s)": 0.109563 | |
| }, | |
| { | |
| "acc": 0.57554379, | |
| "epoch": 0.8785046728971962, | |
| "grad_norm": 1.513482928276062, | |
| "learning_rate": 6.391087319582264e-05, | |
| "loss": 1.59513159, | |
| "memory(GiB)": 52.51, | |
| "step": 235, | |
| "train_speed(iter/s)": 0.109855 | |
| }, | |
| { | |
| "acc": 0.56200686, | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 1.447696566581726, | |
| "learning_rate": 6.241648821085666e-05, | |
| "loss": 1.61208496, | |
| "memory(GiB)": 52.51, | |
| "step": 240, | |
| "train_speed(iter/s)": 0.110135 | |
| }, | |
| { | |
| "acc": 0.57686815, | |
| "epoch": 0.9158878504672897, | |
| "grad_norm": 1.4834848642349243, | |
| "learning_rate": 6.0910185651380626e-05, | |
| "loss": 1.56525345, | |
| "memory(GiB)": 52.51, | |
| "step": 245, | |
| "train_speed(iter/s)": 0.110415 | |
| }, | |
| { | |
| "acc": 0.57838049, | |
| "epoch": 0.9345794392523364, | |
| "grad_norm": 1.4449986219406128, | |
| "learning_rate": 5.939341129438739e-05, | |
| "loss": 1.66088371, | |
| "memory(GiB)": 52.51, | |
| "step": 250, | |
| "train_speed(iter/s)": 0.110677 | |
| }, | |
| { | |
| "epoch": 0.9345794392523364, | |
| "eval_acc": 0.5871944819313241, | |
| "eval_loss": 1.5589616298675537, | |
| "eval_runtime": 60.6063, | |
| "eval_samples_per_second": 0.825, | |
| "eval_steps_per_second": 0.825, | |
| "step": 250 | |
| }, | |
| { | |
| "acc": 0.56091037, | |
| "epoch": 0.9532710280373832, | |
| "grad_norm": 1.4498945474624634, | |
| "learning_rate": 5.786762096789431e-05, | |
| "loss": 1.6876915, | |
| "memory(GiB)": 52.51, | |
| "step": 255, | |
| "train_speed(iter/s)": 0.108045 | |
| }, | |
| { | |
| "acc": 0.57053814, | |
| "epoch": 0.9719626168224299, | |
| "grad_norm": 1.2757234573364258, | |
| "learning_rate": 5.633427915361261e-05, | |
| "loss": 1.65799484, | |
| "memory(GiB)": 52.51, | |
| "step": 260, | |
| "train_speed(iter/s)": 0.108333 | |
| }, | |
| { | |
| "acc": 0.56272326, | |
| "epoch": 0.9906542056074766, | |
| "grad_norm": 1.4214109182357788, | |
| "learning_rate": 5.479485758131089e-05, | |
| "loss": 1.64700985, | |
| "memory(GiB)": 52.51, | |
| "step": 265, | |
| "train_speed(iter/s)": 0.108614 | |
| }, | |
| { | |
| "acc": 0.59196057, | |
| "epoch": 1.0093457943925233, | |
| "grad_norm": 1.255962610244751, | |
| "learning_rate": 5.325083381622165e-05, | |
| "loss": 1.56780367, | |
| "memory(GiB)": 52.51, | |
| "step": 270, | |
| "train_speed(iter/s)": 0.108871 | |
| }, | |
| { | |
| "acc": 0.60109649, | |
| "epoch": 1.02803738317757, | |
| "grad_norm": 1.4240363836288452, | |
| "learning_rate": 5.1703689840846945e-05, | |
| "loss": 1.45532875, | |
| "memory(GiB)": 52.51, | |
| "step": 275, | |
| "train_speed(iter/s)": 0.109138 | |
| }, | |
| { | |
| "acc": 0.59727616, | |
| "epoch": 1.0467289719626167, | |
| "grad_norm": 1.5935661792755127, | |
| "learning_rate": 5.01549106325243e-05, | |
| "loss": 1.51683445, | |
| "memory(GiB)": 52.51, | |
| "step": 280, | |
| "train_speed(iter/s)": 0.109392 | |
| }, | |
| { | |
| "acc": 0.62937155, | |
| "epoch": 1.0654205607476634, | |
| "grad_norm": 1.6722455024719238, | |
| "learning_rate": 4.860598273811792e-05, | |
| "loss": 1.35466251, | |
| "memory(GiB)": 52.51, | |
| "step": 285, | |
| "train_speed(iter/s)": 0.109642 | |
| }, | |
| { | |
| "acc": 0.58850698, | |
| "epoch": 1.0841121495327102, | |
| "grad_norm": 1.524778127670288, | |
| "learning_rate": 4.705839284720376e-05, | |
| "loss": 1.48758812, | |
| "memory(GiB)": 52.51, | |
| "step": 290, | |
| "train_speed(iter/s)": 0.109812 | |
| }, | |
| { | |
| "acc": 0.60075417, | |
| "epoch": 1.102803738317757, | |
| "grad_norm": 1.757370114326477, | |
| "learning_rate": 4.55136263651172e-05, | |
| "loss": 1.50896826, | |
| "memory(GiB)": 52.51, | |
| "step": 295, | |
| "train_speed(iter/s)": 0.110044 | |
| }, | |
| { | |
| "acc": 0.61744561, | |
| "epoch": 1.1214953271028036, | |
| "grad_norm": 2.0011301040649414, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 1.42747393, | |
| "memory(GiB)": 52.51, | |
| "step": 300, | |
| "train_speed(iter/s)": 0.110269 | |
| }, | |
| { | |
| "epoch": 1.1214953271028036, | |
| "eval_acc": 0.5852451641925326, | |
| "eval_loss": 1.5581213235855103, | |
| "eval_runtime": 60.6131, | |
| "eval_samples_per_second": 0.825, | |
| "eval_steps_per_second": 0.825, | |
| "step": 300 | |
| }, | |
| { | |
| "acc": 0.59082665, | |
| "epoch": 1.1401869158878504, | |
| "grad_norm": 1.8005529642105103, | |
| "learning_rate": 4.243849027585096e-05, | |
| "loss": 1.49810066, | |
| "memory(GiB)": 52.51, | |
| "step": 305, | |
| "train_speed(iter/s)": 0.108082 | |
| }, | |
| { | |
| "acc": 0.58803234, | |
| "epoch": 1.158878504672897, | |
| "grad_norm": 1.8836215734481812, | |
| "learning_rate": 4.0911072241036194e-05, | |
| "loss": 1.53769073, | |
| "memory(GiB)": 52.51, | |
| "step": 310, | |
| "train_speed(iter/s)": 0.108325 | |
| }, | |
| { | |
| "acc": 0.61663084, | |
| "epoch": 1.1775700934579438, | |
| "grad_norm": 1.7952263355255127, | |
| "learning_rate": 3.9392377926805226e-05, | |
| "loss": 1.44214535, | |
| "memory(GiB)": 52.51, | |
| "step": 315, | |
| "train_speed(iter/s)": 0.108566 | |
| }, | |
| { | |
| "acc": 0.59271388, | |
| "epoch": 1.1962616822429906, | |
| "grad_norm": 1.8852580785751343, | |
| "learning_rate": 3.788386500398583e-05, | |
| "loss": 1.49927893, | |
| "memory(GiB)": 52.51, | |
| "step": 320, | |
| "train_speed(iter/s)": 0.108797 | |
| }, | |
| { | |
| "acc": 0.60236468, | |
| "epoch": 1.2149532710280373, | |
| "grad_norm": 1.737602949142456, | |
| "learning_rate": 3.6386981371118355e-05, | |
| "loss": 1.42521906, | |
| "memory(GiB)": 52.51, | |
| "step": 325, | |
| "train_speed(iter/s)": 0.109019 | |
| }, | |
| { | |
| "acc": 0.6055068, | |
| "epoch": 1.233644859813084, | |
| "grad_norm": 1.914955496788025, | |
| "learning_rate": 3.49031637647361e-05, | |
| "loss": 1.47248116, | |
| "memory(GiB)": 52.51, | |
| "step": 330, | |
| "train_speed(iter/s)": 0.109238 | |
| }, | |
| { | |
| "acc": 0.61518903, | |
| "epoch": 1.2523364485981308, | |
| "grad_norm": 1.7206995487213135, | |
| "learning_rate": 3.343383638035902e-05, | |
| "loss": 1.38390493, | |
| "memory(GiB)": 52.51, | |
| "step": 335, | |
| "train_speed(iter/s)": 0.109447 | |
| }, | |
| { | |
| "acc": 0.60801978, | |
| "epoch": 1.2710280373831775, | |
| "grad_norm": 1.9262409210205078, | |
| "learning_rate": 3.1980409505524544e-05, | |
| "loss": 1.41381416, | |
| "memory(GiB)": 52.51, | |
| "step": 340, | |
| "train_speed(iter/s)": 0.109652 | |
| }, | |
| { | |
| "acc": 0.60384398, | |
| "epoch": 1.2897196261682242, | |
| "grad_norm": 2.144967794418335, | |
| "learning_rate": 3.054427816616773e-05, | |
| "loss": 1.40025005, | |
| "memory(GiB)": 52.51, | |
| "step": 345, | |
| "train_speed(iter/s)": 0.109855 | |
| }, | |
| { | |
| "acc": 0.60187116, | |
| "epoch": 1.308411214953271, | |
| "grad_norm": 2.0876433849334717, | |
| "learning_rate": 2.91268207876494e-05, | |
| "loss": 1.44376688, | |
| "memory(GiB)": 52.51, | |
| "step": 350, | |
| "train_speed(iter/s)": 0.110051 | |
| }, | |
| { | |
| "epoch": 1.308411214953271, | |
| "eval_acc": 0.5856950067476383, | |
| "eval_loss": 1.5565516948699951, | |
| "eval_runtime": 60.5775, | |
| "eval_samples_per_second": 0.825, | |
| "eval_steps_per_second": 0.825, | |
| "step": 350 | |
| }, | |
| { | |
| "acc": 0.61420636, | |
| "epoch": 1.3271028037383177, | |
| "grad_norm": 1.9940565824508667, | |
| "learning_rate": 2.7729397871718304e-05, | |
| "loss": 1.40987692, | |
| "memory(GiB)": 52.51, | |
| "step": 355, | |
| "train_speed(iter/s)": 0.108178 | |
| }, | |
| { | |
| "acc": 0.59907641, | |
| "epoch": 1.3457943925233644, | |
| "grad_norm": 1.9915255308151245, | |
| "learning_rate": 2.635335069067617e-05, | |
| "loss": 1.44835072, | |
| "memory(GiB)": 52.51, | |
| "step": 360, | |
| "train_speed(iter/s)": 0.108387 | |
| }, | |
| { | |
| "acc": 0.62042379, | |
| "epoch": 1.3644859813084111, | |
| "grad_norm": 2.130258798599243, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.41162367, | |
| "memory(GiB)": 52.51, | |
| "step": 365, | |
| "train_speed(iter/s)": 0.108589 | |
| }, | |
| { | |
| "acc": 0.6139565, | |
| "epoch": 1.3831775700934579, | |
| "grad_norm": 1.8815335035324097, | |
| "learning_rate": 2.367064477065652e-05, | |
| "loss": 1.41061649, | |
| "memory(GiB)": 52.51, | |
| "step": 370, | |
| "train_speed(iter/s)": 0.108788 | |
| }, | |
| { | |
| "acc": 0.60995245, | |
| "epoch": 1.4018691588785046, | |
| "grad_norm": 2.237551689147949, | |
| "learning_rate": 2.2366560942325832e-05, | |
| "loss": 1.41165752, | |
| "memory(GiB)": 52.51, | |
| "step": 375, | |
| "train_speed(iter/s)": 0.108982 | |
| }, | |
| { | |
| "acc": 0.61310611, | |
| "epoch": 1.4205607476635513, | |
| "grad_norm": 2.2738187313079834, | |
| "learning_rate": 2.108900019873103e-05, | |
| "loss": 1.46329918, | |
| "memory(GiB)": 52.51, | |
| "step": 380, | |
| "train_speed(iter/s)": 0.109169 | |
| }, | |
| { | |
| "acc": 0.61972389, | |
| "epoch": 1.439252336448598, | |
| "grad_norm": 2.050431966781616, | |
| "learning_rate": 1.983918876624902e-05, | |
| "loss": 1.39380827, | |
| "memory(GiB)": 52.51, | |
| "step": 385, | |
| "train_speed(iter/s)": 0.109353 | |
| }, | |
| { | |
| "acc": 0.60818005, | |
| "epoch": 1.4579439252336448, | |
| "grad_norm": 2.2794229984283447, | |
| "learning_rate": 1.8618326236955907e-05, | |
| "loss": 1.46415033, | |
| "memory(GiB)": 52.51, | |
| "step": 390, | |
| "train_speed(iter/s)": 0.109532 | |
| }, | |
| { | |
| "acc": 0.59707479, | |
| "epoch": 1.4766355140186915, | |
| "grad_norm": 2.2006595134735107, | |
| "learning_rate": 1.7427584417236194e-05, | |
| "loss": 1.49114666, | |
| "memory(GiB)": 52.51, | |
| "step": 395, | |
| "train_speed(iter/s)": 0.109705 | |
| }, | |
| { | |
| "acc": 0.6111486, | |
| "epoch": 1.4953271028037383, | |
| "grad_norm": 2.0496108531951904, | |
| "learning_rate": 1.626810620306163e-05, | |
| "loss": 1.38812447, | |
| "memory(GiB)": 52.51, | |
| "step": 400, | |
| "train_speed(iter/s)": 0.109877 | |
| }, | |
| { | |
| "epoch": 1.4953271028037383, | |
| "eval_acc": 0.5873444294496926, | |
| "eval_loss": 1.5544381141662598, | |
| "eval_runtime": 60.5613, | |
| "eval_samples_per_second": 0.826, | |
| "eval_steps_per_second": 0.826, | |
| "step": 400 | |
| }, | |
| { | |
| "acc": 0.60279655, | |
| "epoch": 1.514018691588785, | |
| "grad_norm": 1.954108476638794, | |
| "learning_rate": 1.5141004483018323e-05, | |
| "loss": 1.44826994, | |
| "memory(GiB)": 52.51, | |
| "step": 405, | |
| "train_speed(iter/s)": 0.108237 | |
| }, | |
| { | |
| "acc": 0.60491271, | |
| "epoch": 1.5327102803738317, | |
| "grad_norm": 2.4498937129974365, | |
| "learning_rate": 1.4047361070135995e-05, | |
| "loss": 1.4636652, | |
| "memory(GiB)": 52.51, | |
| "step": 410, | |
| "train_speed(iter/s)": 0.108423 | |
| }, | |
| { | |
| "acc": 0.59805059, | |
| "epoch": 1.5514018691588785, | |
| "grad_norm": 1.9891496896743774, | |
| "learning_rate": 1.2988225663543602e-05, | |
| "loss": 1.51361618, | |
| "memory(GiB)": 52.51, | |
| "step": 415, | |
| "train_speed(iter/s)": 0.108601 | |
| }, | |
| { | |
| "acc": 0.60604153, | |
| "epoch": 1.5700934579439252, | |
| "grad_norm": 2.281243324279785, | |
| "learning_rate": 1.1964614840949002e-05, | |
| "loss": 1.43464155, | |
| "memory(GiB)": 52.51, | |
| "step": 420, | |
| "train_speed(iter/s)": 0.108777 | |
| }, | |
| { | |
| "acc": 0.59663863, | |
| "epoch": 1.588785046728972, | |
| "grad_norm": 2.1692161560058594, | |
| "learning_rate": 1.097751108290867e-05, | |
| "loss": 1.47755518, | |
| "memory(GiB)": 52.51, | |
| "step": 425, | |
| "train_speed(iter/s)": 0.108947 | |
| }, | |
| { | |
| "acc": 0.62566915, | |
| "epoch": 1.6074766355140186, | |
| "grad_norm": 2.370448112487793, | |
| "learning_rate": 1.0027861829824952e-05, | |
| "loss": 1.36240664, | |
| "memory(GiB)": 52.51, | |
| "step": 430, | |
| "train_speed(iter/s)": 0.109117 | |
| }, | |
| { | |
| "acc": 0.60366473, | |
| "epoch": 1.6261682242990654, | |
| "grad_norm": 2.143240451812744, | |
| "learning_rate": 9.11657857257509e-06, | |
| "loss": 1.49398394, | |
| "memory(GiB)": 52.51, | |
| "step": 435, | |
| "train_speed(iter/s)": 0.109226 | |
| }, | |
| { | |
| "acc": 0.60729022, | |
| "epoch": 1.644859813084112, | |
| "grad_norm": 2.266324758529663, | |
| "learning_rate": 8.244535977645585e-06, | |
| "loss": 1.4582058, | |
| "memory(GiB)": 52.51, | |
| "step": 440, | |
| "train_speed(iter/s)": 0.109388 | |
| }, | |
| { | |
| "acc": 0.61000395, | |
| "epoch": 1.6635514018691588, | |
| "grad_norm": 2.243384599685669, | |
| "learning_rate": 7.412571047611155e-06, | |
| "loss": 1.39406261, | |
| "memory(GiB)": 52.51, | |
| "step": 445, | |
| "train_speed(iter/s)": 0.109547 | |
| }, | |
| { | |
| "acc": 0.60550241, | |
| "epoch": 1.6822429906542056, | |
| "grad_norm": 2.3402411937713623, | |
| "learning_rate": 6.621482317764105e-06, | |
| "loss": 1.44629755, | |
| "memory(GiB)": 52.51, | |
| "step": 450, | |
| "train_speed(iter/s)": 0.109702 | |
| }, | |
| { | |
| "epoch": 1.6822429906542056, | |
| "eval_acc": 0.5838956365272154, | |
| "eval_loss": 1.5518497228622437, | |
| "eval_runtime": 60.463, | |
| "eval_samples_per_second": 0.827, | |
| "eval_steps_per_second": 0.827, | |
| "step": 450 | |
| }, | |
| { | |
| "acc": 0.62354083, | |
| "epoch": 1.7009345794392523, | |
| "grad_norm": 2.3499748706817627, | |
| "learning_rate": 5.872029089665587e-06, | |
| "loss": 1.36534414, | |
| "memory(GiB)": 52.51, | |
| "step": 455, | |
| "train_speed(iter/s)": 0.108251 | |
| }, | |
| { | |
| "acc": 0.60730128, | |
| "epoch": 1.719626168224299, | |
| "grad_norm": 2.479720115661621, | |
| "learning_rate": 5.164930702353782e-06, | |
| "loss": 1.44677553, | |
| "memory(GiB)": 52.51, | |
| "step": 460, | |
| "train_speed(iter/s)": 0.108417 | |
| }, | |
| { | |
| "acc": 0.59804258, | |
| "epoch": 1.7383177570093458, | |
| "grad_norm": 2.117152214050293, | |
| "learning_rate": 4.500865841909168e-06, | |
| "loss": 1.46659861, | |
| "memory(GiB)": 52.51, | |
| "step": 465, | |
| "train_speed(iter/s)": 0.108577 | |
| }, | |
| { | |
| "acc": 0.60334945, | |
| "epoch": 1.7570093457943925, | |
| "grad_norm": 2.2500483989715576, | |
| "learning_rate": 3.880471890038967e-06, | |
| "loss": 1.4467123, | |
| "memory(GiB)": 52.51, | |
| "step": 470, | |
| "train_speed(iter/s)": 0.108736 | |
| }, | |
| { | |
| "acc": 0.60877209, | |
| "epoch": 1.7757009345794392, | |
| "grad_norm": 2.166339635848999, | |
| "learning_rate": 3.3043443123065286e-06, | |
| "loss": 1.49398079, | |
| "memory(GiB)": 52.51, | |
| "step": 475, | |
| "train_speed(iter/s)": 0.108888 | |
| }, | |
| { | |
| "acc": 0.59179163, | |
| "epoch": 1.794392523364486, | |
| "grad_norm": 2.554819107055664, | |
| "learning_rate": 2.7730360865923956e-06, | |
| "loss": 1.47536173, | |
| "memory(GiB)": 52.51, | |
| "step": 480, | |
| "train_speed(iter/s)": 0.109034 | |
| }, | |
| { | |
| "acc": 0.58686528, | |
| "epoch": 1.8130841121495327, | |
| "grad_norm": 2.176454544067383, | |
| "learning_rate": 2.287057172336021e-06, | |
| "loss": 1.51853113, | |
| "memory(GiB)": 52.51, | |
| "step": 485, | |
| "train_speed(iter/s)": 0.10918 | |
| }, | |
| { | |
| "acc": 0.61157169, | |
| "epoch": 1.8317757009345794, | |
| "grad_norm": 2.2419204711914062, | |
| "learning_rate": 1.8468740210672076e-06, | |
| "loss": 1.45838099, | |
| "memory(GiB)": 52.51, | |
| "step": 490, | |
| "train_speed(iter/s)": 0.109326 | |
| }, | |
| { | |
| "acc": 0.604812, | |
| "epoch": 1.8504672897196262, | |
| "grad_norm": 2.1367015838623047, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 1.42373133, | |
| "memory(GiB)": 52.51, | |
| "step": 495, | |
| "train_speed(iter/s)": 0.10947 | |
| }, | |
| { | |
| "acc": 0.59049854, | |
| "epoch": 1.8691588785046729, | |
| "grad_norm": 2.212156057357788, | |
| "learning_rate": 1.1055406300002347e-06, | |
| "loss": 1.47500782, | |
| "memory(GiB)": 52.51, | |
| "step": 500, | |
| "train_speed(iter/s)": 0.10961 | |
| }, | |
| { | |
| "epoch": 1.8691588785046729, | |
| "eval_acc": 0.5858449542660069, | |
| "eval_loss": 1.55006742477417, | |
| "eval_runtime": 60.5418, | |
| "eval_samples_per_second": 0.826, | |
| "eval_steps_per_second": 0.826, | |
| "step": 500 | |
| }, | |
| { | |
| "acc": 0.61764479, | |
| "epoch": 1.8878504672897196, | |
| "grad_norm": 2.375039577484131, | |
| "learning_rate": 8.0510193567086e-07, | |
| "loss": 1.4303463, | |
| "memory(GiB)": 52.51, | |
| "step": 505, | |
| "train_speed(iter/s)": 0.108303 | |
| }, | |
| { | |
| "acc": 0.60544062, | |
| "epoch": 1.9065420560747663, | |
| "grad_norm": 2.1975295543670654, | |
| "learning_rate": 5.518814123121885e-07, | |
| "loss": 1.48970194, | |
| "memory(GiB)": 52.51, | |
| "step": 510, | |
| "train_speed(iter/s)": 0.108451 | |
| }, | |
| { | |
| "acc": 0.60760684, | |
| "epoch": 1.925233644859813, | |
| "grad_norm": 2.173210859298706, | |
| "learning_rate": 3.4612210565528326e-07, | |
| "loss": 1.43905754, | |
| "memory(GiB)": 52.51, | |
| "step": 515, | |
| "train_speed(iter/s)": 0.108595 | |
| }, | |
| { | |
| "acc": 0.61625342, | |
| "epoch": 1.9439252336448598, | |
| "grad_norm": 2.543931245803833, | |
| "learning_rate": 1.8802150727962876e-07, | |
| "loss": 1.40175552, | |
| "memory(GiB)": 52.51, | |
| "step": 520, | |
| "train_speed(iter/s)": 0.108738 | |
| }, | |
| { | |
| "acc": 0.61394835, | |
| "epoch": 1.9626168224299065, | |
| "grad_norm": 2.0409328937530518, | |
| "learning_rate": 7.773136505700995e-08, | |
| "loss": 1.36281643, | |
| "memory(GiB)": 52.51, | |
| "step": 525, | |
| "train_speed(iter/s)": 0.108834 | |
| }, | |
| { | |
| "acc": 0.60506306, | |
| "epoch": 1.9813084112149533, | |
| "grad_norm": 2.187635898590088, | |
| "learning_rate": 1.5357537501159423e-08, | |
| "loss": 1.45838461, | |
| "memory(GiB)": 52.51, | |
| "step": 530, | |
| "train_speed(iter/s)": 0.10897 | |
| }, | |
| { | |
| "epoch": 1.9962616822429906, | |
| "eval_acc": 0.5853951117109012, | |
| "eval_loss": 1.550318956375122, | |
| "eval_runtime": 60.5393, | |
| "eval_samples_per_second": 0.826, | |
| "eval_steps_per_second": 0.826, | |
| "step": 534 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 534, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.3344607126351155e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |