| { | |
| "best_metric": 1.53044581, | |
| "best_model_checkpoint": "/fs/clip-projects/geoguesser/vlms/cpm/output/minicpm-v-v2_6-chat/v3-20241108-065955/checkpoint-534", | |
| "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": 0.55045807, | |
| "epoch": 0.003738317757009346, | |
| "grad_norm": 1.613571286201477, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 1.95084548, | |
| "memory(GiB)": 18.97, | |
| "step": 1, | |
| "train_speed(iter/s)": 0.133639 | |
| }, | |
| { | |
| "acc": 0.50916213, | |
| "epoch": 0.018691588785046728, | |
| "grad_norm": 1.757776141166687, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 2.09828925, | |
| "memory(GiB)": 19.98, | |
| "step": 5, | |
| "train_speed(iter/s)": 0.287053 | |
| }, | |
| { | |
| "acc": 0.54273653, | |
| "epoch": 0.037383177570093455, | |
| "grad_norm": 1.2750011682510376, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 1.98593979, | |
| "memory(GiB)": 19.98, | |
| "step": 10, | |
| "train_speed(iter/s)": 0.333912 | |
| }, | |
| { | |
| "acc": 0.53456535, | |
| "epoch": 0.056074766355140186, | |
| "grad_norm": 1.1665784120559692, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 1.90109081, | |
| "memory(GiB)": 21.0, | |
| "step": 15, | |
| "train_speed(iter/s)": 0.352318 | |
| }, | |
| { | |
| "acc": 0.54925652, | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 1.3744975328445435, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 1.76896648, | |
| "memory(GiB)": 21.0, | |
| "step": 20, | |
| "train_speed(iter/s)": 0.362181 | |
| }, | |
| { | |
| "acc": 0.5564671, | |
| "epoch": 0.09345794392523364, | |
| "grad_norm": 1.2068527936935425, | |
| "learning_rate": 9.25925925925926e-05, | |
| "loss": 1.65932693, | |
| "memory(GiB)": 21.0, | |
| "step": 25, | |
| "train_speed(iter/s)": 0.368232 | |
| }, | |
| { | |
| "acc": 0.55754151, | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 0.974327802658081, | |
| "learning_rate": 9.999136119166803e-05, | |
| "loss": 1.7156683, | |
| "memory(GiB)": 22.04, | |
| "step": 30, | |
| "train_speed(iter/s)": 0.3718 | |
| }, | |
| { | |
| "acc": 0.554459, | |
| "epoch": 0.1308411214953271, | |
| "grad_norm": 1.1023714542388916, | |
| "learning_rate": 9.99385792841537e-05, | |
| "loss": 1.76657219, | |
| "memory(GiB)": 22.04, | |
| "step": 35, | |
| "train_speed(iter/s)": 0.37456 | |
| }, | |
| { | |
| "acc": 0.55972748, | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 1.0901970863342285, | |
| "learning_rate": 9.983786540671051e-05, | |
| "loss": 1.64107857, | |
| "memory(GiB)": 23.08, | |
| "step": 40, | |
| "train_speed(iter/s)": 0.376463 | |
| }, | |
| { | |
| "acc": 0.5773067, | |
| "epoch": 0.16822429906542055, | |
| "grad_norm": 1.043094277381897, | |
| "learning_rate": 9.968931622637652e-05, | |
| "loss": 1.62755222, | |
| "memory(GiB)": 23.08, | |
| "step": 45, | |
| "train_speed(iter/s)": 0.378202 | |
| }, | |
| { | |
| "acc": 0.5643084, | |
| "epoch": 0.18691588785046728, | |
| "grad_norm": 1.1167865991592407, | |
| "learning_rate": 9.949307432339625e-05, | |
| "loss": 1.67872505, | |
| "memory(GiB)": 23.08, | |
| "step": 50, | |
| "train_speed(iter/s)": 0.379293 | |
| }, | |
| { | |
| "epoch": 0.18691588785046728, | |
| "eval_acc": 0.5715999400209927, | |
| "eval_loss": 1.6141570806503296, | |
| "eval_runtime": 19.3426, | |
| "eval_samples_per_second": 2.585, | |
| "eval_steps_per_second": 2.585, | |
| "step": 50 | |
| }, | |
| { | |
| "acc": 0.57612801, | |
| "epoch": 0.205607476635514, | |
| "grad_norm": 1.0558923482894897, | |
| "learning_rate": 9.924932805436949e-05, | |
| "loss": 1.57275066, | |
| "memory(GiB)": 23.08, | |
| "step": 55, | |
| "train_speed(iter/s)": 0.333772 | |
| }, | |
| { | |
| "acc": 0.56456318, | |
| "epoch": 0.22429906542056074, | |
| "grad_norm": 1.2267849445343018, | |
| "learning_rate": 9.895831137146318e-05, | |
| "loss": 1.62593994, | |
| "memory(GiB)": 23.08, | |
| "step": 60, | |
| "train_speed(iter/s)": 0.337909 | |
| }, | |
| { | |
| "acc": 0.57293587, | |
| "epoch": 0.24299065420560748, | |
| "grad_norm": 1.203539252281189, | |
| "learning_rate": 9.862030359785981e-05, | |
| "loss": 1.62202415, | |
| "memory(GiB)": 23.08, | |
| "step": 65, | |
| "train_speed(iter/s)": 0.341402 | |
| }, | |
| { | |
| "acc": 0.56972237, | |
| "epoch": 0.2616822429906542, | |
| "grad_norm": 1.1968094110488892, | |
| "learning_rate": 9.82356291596578e-05, | |
| "loss": 1.62049065, | |
| "memory(GiB)": 23.08, | |
| "step": 70, | |
| "train_speed(iter/s)": 0.344462 | |
| }, | |
| { | |
| "acc": 0.56793709, | |
| "epoch": 0.2803738317757009, | |
| "grad_norm": 1.1416860818862915, | |
| "learning_rate": 9.780465727448149e-05, | |
| "loss": 1.68797512, | |
| "memory(GiB)": 24.13, | |
| "step": 75, | |
| "train_speed(iter/s)": 0.346849 | |
| }, | |
| { | |
| "acc": 0.58297682, | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 1.1054881811141968, | |
| "learning_rate": 9.732780159709912e-05, | |
| "loss": 1.57775593, | |
| "memory(GiB)": 24.13, | |
| "step": 80, | |
| "train_speed(iter/s)": 0.349274 | |
| }, | |
| { | |
| "acc": 0.57728238, | |
| "epoch": 0.3177570093457944, | |
| "grad_norm": 1.1610243320465088, | |
| "learning_rate": 9.680551982238942e-05, | |
| "loss": 1.59094667, | |
| "memory(GiB)": 24.13, | |
| "step": 85, | |
| "train_speed(iter/s)": 0.351479 | |
| }, | |
| { | |
| "acc": 0.5719296, | |
| "epoch": 0.3364485981308411, | |
| "grad_norm": 1.1896332502365112, | |
| "learning_rate": 9.623831324603754e-05, | |
| "loss": 1.65499535, | |
| "memory(GiB)": 24.13, | |
| "step": 90, | |
| "train_speed(iter/s)": 0.353415 | |
| }, | |
| { | |
| "acc": 0.58935571, | |
| "epoch": 0.35514018691588783, | |
| "grad_norm": 1.0724711418151855, | |
| "learning_rate": 9.562672628338233e-05, | |
| "loss": 1.58491564, | |
| "memory(GiB)": 24.13, | |
| "step": 95, | |
| "train_speed(iter/s)": 0.355195 | |
| }, | |
| { | |
| "acc": 0.56192031, | |
| "epoch": 0.37383177570093457, | |
| "grad_norm": 1.0967603921890259, | |
| "learning_rate": 9.497134594687634e-05, | |
| "loss": 1.68490829, | |
| "memory(GiB)": 24.13, | |
| "step": 100, | |
| "train_speed(iter/s)": 0.356737 | |
| }, | |
| { | |
| "epoch": 0.37383177570093457, | |
| "eval_acc": 0.5846453741190584, | |
| "eval_loss": 1.5773682594299316, | |
| "eval_runtime": 19.3689, | |
| "eval_samples_per_second": 2.581, | |
| "eval_steps_per_second": 2.581, | |
| "step": 100 | |
| }, | |
| { | |
| "acc": 0.58094668, | |
| "epoch": 0.3925233644859813, | |
| "grad_norm": 1.0203641653060913, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 1.63088989, | |
| "memory(GiB)": 24.13, | |
| "step": 105, | |
| "train_speed(iter/s)": 0.334857 | |
| }, | |
| { | |
| "acc": 0.56821561, | |
| "epoch": 0.411214953271028, | |
| "grad_norm": 1.0685813426971436, | |
| "learning_rate": 9.353176276679396e-05, | |
| "loss": 1.67582684, | |
| "memory(GiB)": 24.13, | |
| "step": 110, | |
| "train_speed(iter/s)": 0.33707 | |
| }, | |
| { | |
| "acc": 0.56454325, | |
| "epoch": 0.42990654205607476, | |
| "grad_norm": 1.1684739589691162, | |
| "learning_rate": 9.274894166171888e-05, | |
| "loss": 1.63463154, | |
| "memory(GiB)": 24.13, | |
| "step": 115, | |
| "train_speed(iter/s)": 0.33915 | |
| }, | |
| { | |
| "acc": 0.57855415, | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 1.077269434928894, | |
| "learning_rate": 9.192508933357753e-05, | |
| "loss": 1.67274055, | |
| "memory(GiB)": 24.13, | |
| "step": 120, | |
| "train_speed(iter/s)": 0.341042 | |
| }, | |
| { | |
| "acc": 0.57130666, | |
| "epoch": 0.4672897196261682, | |
| "grad_norm": 1.066927194595337, | |
| "learning_rate": 9.106099653103728e-05, | |
| "loss": 1.57755241, | |
| "memory(GiB)": 24.13, | |
| "step": 125, | |
| "train_speed(iter/s)": 0.34276 | |
| }, | |
| { | |
| "acc": 0.57805595, | |
| "epoch": 0.48598130841121495, | |
| "grad_norm": 1.214378833770752, | |
| "learning_rate": 9.015749262631536e-05, | |
| "loss": 1.5515789, | |
| "memory(GiB)": 24.13, | |
| "step": 130, | |
| "train_speed(iter/s)": 0.344333 | |
| }, | |
| { | |
| "acc": 0.58489175, | |
| "epoch": 0.5046728971962616, | |
| "grad_norm": 1.2008962631225586, | |
| "learning_rate": 8.921544481913218e-05, | |
| "loss": 1.60749855, | |
| "memory(GiB)": 24.13, | |
| "step": 135, | |
| "train_speed(iter/s)": 0.345892 | |
| }, | |
| { | |
| "acc": 0.55853381, | |
| "epoch": 0.5233644859813084, | |
| "grad_norm": 1.1639275550842285, | |
| "learning_rate": 8.823575730435693e-05, | |
| "loss": 1.63589153, | |
| "memory(GiB)": 25.22, | |
| "step": 140, | |
| "train_speed(iter/s)": 0.3473 | |
| }, | |
| { | |
| "acc": 0.57799473, | |
| "epoch": 0.5420560747663551, | |
| "grad_norm": 1.0502570867538452, | |
| "learning_rate": 8.721937040414481e-05, | |
| "loss": 1.55451593, | |
| "memory(GiB)": 25.22, | |
| "step": 145, | |
| "train_speed(iter/s)": 0.348596 | |
| }, | |
| { | |
| "acc": 0.56694794, | |
| "epoch": 0.5607476635514018, | |
| "grad_norm": 1.2373900413513184, | |
| "learning_rate": 8.616725966539832e-05, | |
| "loss": 1.64150391, | |
| "memory(GiB)": 25.22, | |
| "step": 150, | |
| "train_speed(iter/s)": 0.349855 | |
| }, | |
| { | |
| "epoch": 0.5607476635514018, | |
| "eval_acc": 0.5879442195231669, | |
| "eval_loss": 1.5577113628387451, | |
| "eval_runtime": 19.4081, | |
| "eval_samples_per_second": 2.576, | |
| "eval_steps_per_second": 2.576, | |
| "step": 150 | |
| }, | |
| { | |
| "acc": 0.57931132, | |
| "epoch": 0.5794392523364486, | |
| "grad_norm": 1.148728847503662, | |
| "learning_rate": 8.508043492341944e-05, | |
| "loss": 1.59622688, | |
| "memory(GiB)": 25.22, | |
| "step": 155, | |
| "train_speed(iter/s)": 0.335587 | |
| }, | |
| { | |
| "acc": 0.57598162, | |
| "epoch": 0.5981308411214953, | |
| "grad_norm": 1.1714155673980713, | |
| "learning_rate": 8.395993933265101e-05, | |
| "loss": 1.63730679, | |
| "memory(GiB)": 25.22, | |
| "step": 160, | |
| "train_speed(iter/s)": 0.337039 | |
| }, | |
| { | |
| "acc": 0.56635065, | |
| "epoch": 0.616822429906542, | |
| "grad_norm": 1.000349521636963, | |
| "learning_rate": 8.280684836543794e-05, | |
| "loss": 1.61145477, | |
| "memory(GiB)": 25.22, | |
| "step": 165, | |
| "train_speed(iter/s)": 0.338357 | |
| }, | |
| { | |
| "acc": 0.57298255, | |
| "epoch": 0.6355140186915887, | |
| "grad_norm": 1.1170839071273804, | |
| "learning_rate": 8.162226877976887e-05, | |
| "loss": 1.59238987, | |
| "memory(GiB)": 25.22, | |
| "step": 170, | |
| "train_speed(iter/s)": 0.339705 | |
| }, | |
| { | |
| "acc": 0.58343244, | |
| "epoch": 0.6542056074766355, | |
| "grad_norm": 1.0932862758636475, | |
| "learning_rate": 8.040733755698955e-05, | |
| "loss": 1.58805714, | |
| "memory(GiB)": 25.22, | |
| "step": 175, | |
| "train_speed(iter/s)": 0.340942 | |
| }, | |
| { | |
| "acc": 0.5746861, | |
| "epoch": 0.6728971962616822, | |
| "grad_norm": 1.147817850112915, | |
| "learning_rate": 7.916322081050709e-05, | |
| "loss": 1.58162947, | |
| "memory(GiB)": 25.22, | |
| "step": 180, | |
| "train_speed(iter/s)": 0.342139 | |
| }, | |
| { | |
| "acc": 0.57306166, | |
| "epoch": 0.6915887850467289, | |
| "grad_norm": 1.076221227645874, | |
| "learning_rate": 7.789111266653285e-05, | |
| "loss": 1.58194542, | |
| "memory(GiB)": 25.22, | |
| "step": 185, | |
| "train_speed(iter/s)": 0.343249 | |
| }, | |
| { | |
| "acc": 0.58896809, | |
| "epoch": 0.7102803738317757, | |
| "grad_norm": 1.1743425130844116, | |
| "learning_rate": 7.659223411793798e-05, | |
| "loss": 1.53554783, | |
| "memory(GiB)": 25.22, | |
| "step": 190, | |
| "train_speed(iter/s)": 0.344334 | |
| }, | |
| { | |
| "acc": 0.57240195, | |
| "epoch": 0.7289719626168224, | |
| "grad_norm": 1.0945876836776733, | |
| "learning_rate": 7.526783185232207e-05, | |
| "loss": 1.59289436, | |
| "memory(GiB)": 25.22, | |
| "step": 195, | |
| "train_speed(iter/s)": 0.345336 | |
| }, | |
| { | |
| "acc": 0.5794302, | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": 1.1055279970169067, | |
| "learning_rate": 7.391917705541927e-05, | |
| "loss": 1.621562, | |
| "memory(GiB)": 25.22, | |
| "step": 200, | |
| "train_speed(iter/s)": 0.346324 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "eval_acc": 0.5871944819313241, | |
| "eval_loss": 1.5511505603790283, | |
| "eval_runtime": 19.403, | |
| "eval_samples_per_second": 2.577, | |
| "eval_steps_per_second": 2.577, | |
| "step": 200 | |
| }, | |
| { | |
| "acc": 0.56806307, | |
| "epoch": 0.7663551401869159, | |
| "grad_norm": 1.017061471939087, | |
| "learning_rate": 7.254756419099074e-05, | |
| "loss": 1.6349041, | |
| "memory(GiB)": 25.22, | |
| "step": 205, | |
| "train_speed(iter/s)": 0.335703 | |
| }, | |
| { | |
| "acc": 0.56848702, | |
| "epoch": 0.7850467289719626, | |
| "grad_norm": 1.1138246059417725, | |
| "learning_rate": 7.115430975837457e-05, | |
| "loss": 1.60775127, | |
| "memory(GiB)": 25.22, | |
| "step": 210, | |
| "train_speed(iter/s)": 0.336869 | |
| }, | |
| { | |
| "acc": 0.58039517, | |
| "epoch": 0.8037383177570093, | |
| "grad_norm": 1.2759917974472046, | |
| "learning_rate": 6.974075102888536e-05, | |
| "loss": 1.59430618, | |
| "memory(GiB)": 25.22, | |
| "step": 215, | |
| "train_speed(iter/s)": 0.337979 | |
| }, | |
| { | |
| "acc": 0.56688986, | |
| "epoch": 0.822429906542056, | |
| "grad_norm": 1.259171724319458, | |
| "learning_rate": 6.830824476227646e-05, | |
| "loss": 1.61376076, | |
| "memory(GiB)": 25.22, | |
| "step": 220, | |
| "train_speed(iter/s)": 0.339033 | |
| }, | |
| { | |
| "acc": 0.58966751, | |
| "epoch": 0.8411214953271028, | |
| "grad_norm": 1.1861165761947632, | |
| "learning_rate": 6.685816590449708e-05, | |
| "loss": 1.56043501, | |
| "memory(GiB)": 25.22, | |
| "step": 225, | |
| "train_speed(iter/s)": 0.340035 | |
| }, | |
| { | |
| "acc": 0.58497729, | |
| "epoch": 0.8598130841121495, | |
| "grad_norm": 1.1015815734863281, | |
| "learning_rate": 6.539190626799366e-05, | |
| "loss": 1.57877932, | |
| "memory(GiB)": 25.22, | |
| "step": 230, | |
| "train_speed(iter/s)": 0.341016 | |
| }, | |
| { | |
| "acc": 0.58781128, | |
| "epoch": 0.8785046728971962, | |
| "grad_norm": 1.2020829916000366, | |
| "learning_rate": 6.391087319582264e-05, | |
| "loss": 1.57381382, | |
| "memory(GiB)": 25.22, | |
| "step": 235, | |
| "train_speed(iter/s)": 0.341901 | |
| }, | |
| { | |
| "acc": 0.57930512, | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 1.1107765436172485, | |
| "learning_rate": 6.241648821085666e-05, | |
| "loss": 1.56744556, | |
| "memory(GiB)": 25.22, | |
| "step": 240, | |
| "train_speed(iter/s)": 0.338406 | |
| }, | |
| { | |
| "acc": 0.57636843, | |
| "epoch": 0.9158878504672897, | |
| "grad_norm": 1.1953294277191162, | |
| "learning_rate": 6.0910185651380626e-05, | |
| "loss": 1.53063288, | |
| "memory(GiB)": 25.22, | |
| "step": 245, | |
| "train_speed(iter/s)": 0.339394 | |
| }, | |
| { | |
| "acc": 0.57735896, | |
| "epoch": 0.9345794392523364, | |
| "grad_norm": 1.1470882892608643, | |
| "learning_rate": 5.939341129438739e-05, | |
| "loss": 1.64163361, | |
| "memory(GiB)": 25.22, | |
| "step": 250, | |
| "train_speed(iter/s)": 0.340265 | |
| }, | |
| { | |
| "epoch": 0.9345794392523364, | |
| "eval_acc": 0.5865946918578497, | |
| "eval_loss": 1.539453148841858, | |
| "eval_runtime": 19.2796, | |
| "eval_samples_per_second": 2.593, | |
| "eval_steps_per_second": 2.593, | |
| "step": 250 | |
| }, | |
| { | |
| "acc": 0.55690722, | |
| "epoch": 0.9532710280373832, | |
| "grad_norm": 1.225205421447754, | |
| "learning_rate": 5.786762096789431e-05, | |
| "loss": 1.68273106, | |
| "memory(GiB)": 25.22, | |
| "step": 255, | |
| "train_speed(iter/s)": 0.332148 | |
| }, | |
| { | |
| "acc": 0.56964278, | |
| "epoch": 0.9719626168224299, | |
| "grad_norm": 1.0283957719802856, | |
| "learning_rate": 5.633427915361261e-05, | |
| "loss": 1.64168797, | |
| "memory(GiB)": 25.22, | |
| "step": 260, | |
| "train_speed(iter/s)": 0.333054 | |
| }, | |
| { | |
| "acc": 0.55817146, | |
| "epoch": 0.9906542056074766, | |
| "grad_norm": 1.0989590883255005, | |
| "learning_rate": 5.479485758131089e-05, | |
| "loss": 1.61564522, | |
| "memory(GiB)": 25.22, | |
| "step": 265, | |
| "train_speed(iter/s)": 0.333997 | |
| }, | |
| { | |
| "acc": 0.59431157, | |
| "epoch": 1.0093457943925233, | |
| "grad_norm": 1.0156042575836182, | |
| "learning_rate": 5.325083381622165e-05, | |
| "loss": 1.54522419, | |
| "memory(GiB)": 25.22, | |
| "step": 270, | |
| "train_speed(iter/s)": 0.334781 | |
| }, | |
| { | |
| "acc": 0.59816217, | |
| "epoch": 1.02803738317757, | |
| "grad_norm": 1.1333341598510742, | |
| "learning_rate": 5.1703689840846945e-05, | |
| "loss": 1.43400564, | |
| "memory(GiB)": 25.22, | |
| "step": 275, | |
| "train_speed(iter/s)": 0.335687 | |
| }, | |
| { | |
| "acc": 0.5830586, | |
| "epoch": 1.0467289719626167, | |
| "grad_norm": 1.289959192276001, | |
| "learning_rate": 5.01549106325243e-05, | |
| "loss": 1.52126703, | |
| "memory(GiB)": 25.22, | |
| "step": 280, | |
| "train_speed(iter/s)": 0.336526 | |
| }, | |
| { | |
| "acc": 0.62401681, | |
| "epoch": 1.0654205607476634, | |
| "grad_norm": 1.3222240209579468, | |
| "learning_rate": 4.860598273811792e-05, | |
| "loss": 1.36042976, | |
| "memory(GiB)": 25.22, | |
| "step": 285, | |
| "train_speed(iter/s)": 0.337368 | |
| }, | |
| { | |
| "acc": 0.57799129, | |
| "epoch": 1.0841121495327102, | |
| "grad_norm": 1.261518120765686, | |
| "learning_rate": 4.705839284720376e-05, | |
| "loss": 1.48789501, | |
| "memory(GiB)": 25.22, | |
| "step": 290, | |
| "train_speed(iter/s)": 0.338162 | |
| }, | |
| { | |
| "acc": 0.60333071, | |
| "epoch": 1.102803738317757, | |
| "grad_norm": 1.351491928100586, | |
| "learning_rate": 4.55136263651172e-05, | |
| "loss": 1.49587126, | |
| "memory(GiB)": 25.22, | |
| "step": 295, | |
| "train_speed(iter/s)": 0.338912 | |
| }, | |
| { | |
| "acc": 0.61315393, | |
| "epoch": 1.1214953271028036, | |
| "grad_norm": 1.6314853429794312, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 1.43088112, | |
| "memory(GiB)": 25.22, | |
| "step": 300, | |
| "train_speed(iter/s)": 0.339653 | |
| }, | |
| { | |
| "epoch": 1.1214953271028036, | |
| "eval_acc": 0.5912430649272754, | |
| "eval_loss": 1.5384690761566162, | |
| "eval_runtime": 19.3435, | |
| "eval_samples_per_second": 2.585, | |
| "eval_steps_per_second": 2.585, | |
| "step": 300 | |
| }, | |
| { | |
| "acc": 0.60021753, | |
| "epoch": 1.1401869158878504, | |
| "grad_norm": 1.4269309043884277, | |
| "learning_rate": 4.243849027585096e-05, | |
| "loss": 1.47466078, | |
| "memory(GiB)": 25.22, | |
| "step": 305, | |
| "train_speed(iter/s)": 0.332888 | |
| }, | |
| { | |
| "acc": 0.58526664, | |
| "epoch": 1.158878504672897, | |
| "grad_norm": 1.4827656745910645, | |
| "learning_rate": 4.0911072241036194e-05, | |
| "loss": 1.53870859, | |
| "memory(GiB)": 25.22, | |
| "step": 310, | |
| "train_speed(iter/s)": 0.333651 | |
| }, | |
| { | |
| "acc": 0.6124382, | |
| "epoch": 1.1775700934579438, | |
| "grad_norm": 1.428358793258667, | |
| "learning_rate": 3.9392377926805226e-05, | |
| "loss": 1.44478369, | |
| "memory(GiB)": 25.22, | |
| "step": 315, | |
| "train_speed(iter/s)": 0.334437 | |
| }, | |
| { | |
| "acc": 0.58961325, | |
| "epoch": 1.1962616822429906, | |
| "grad_norm": 1.4965459108352661, | |
| "learning_rate": 3.788386500398583e-05, | |
| "loss": 1.49487057, | |
| "memory(GiB)": 25.22, | |
| "step": 320, | |
| "train_speed(iter/s)": 0.335206 | |
| }, | |
| { | |
| "acc": 0.58942304, | |
| "epoch": 1.2149532710280373, | |
| "grad_norm": 1.3801062107086182, | |
| "learning_rate": 3.6386981371118355e-05, | |
| "loss": 1.44996719, | |
| "memory(GiB)": 25.22, | |
| "step": 325, | |
| "train_speed(iter/s)": 0.335913 | |
| }, | |
| { | |
| "acc": 0.5930171, | |
| "epoch": 1.233644859813084, | |
| "grad_norm": 1.550034523010254, | |
| "learning_rate": 3.49031637647361e-05, | |
| "loss": 1.4618269, | |
| "memory(GiB)": 25.22, | |
| "step": 330, | |
| "train_speed(iter/s)": 0.336661 | |
| }, | |
| { | |
| "acc": 0.61733942, | |
| "epoch": 1.2523364485981308, | |
| "grad_norm": 1.467942237854004, | |
| "learning_rate": 3.343383638035902e-05, | |
| "loss": 1.37453032, | |
| "memory(GiB)": 25.22, | |
| "step": 335, | |
| "train_speed(iter/s)": 0.337353 | |
| }, | |
| { | |
| "acc": 0.60188942, | |
| "epoch": 1.2710280373831775, | |
| "grad_norm": 1.571946620941162, | |
| "learning_rate": 3.1980409505524544e-05, | |
| "loss": 1.42003136, | |
| "memory(GiB)": 25.22, | |
| "step": 340, | |
| "train_speed(iter/s)": 0.33804 | |
| }, | |
| { | |
| "acc": 0.60350924, | |
| "epoch": 1.2897196261682242, | |
| "grad_norm": 1.773979663848877, | |
| "learning_rate": 3.054427816616773e-05, | |
| "loss": 1.40252638, | |
| "memory(GiB)": 25.22, | |
| "step": 345, | |
| "train_speed(iter/s)": 0.338706 | |
| }, | |
| { | |
| "acc": 0.59472365, | |
| "epoch": 1.308411214953271, | |
| "grad_norm": 1.5724050998687744, | |
| "learning_rate": 2.91268207876494e-05, | |
| "loss": 1.46759853, | |
| "memory(GiB)": 25.22, | |
| "step": 350, | |
| "train_speed(iter/s)": 0.339365 | |
| }, | |
| { | |
| "epoch": 1.308411214953271, | |
| "eval_acc": 0.5880941670415355, | |
| "eval_loss": 1.5372613668441772, | |
| "eval_runtime": 19.309, | |
| "eval_samples_per_second": 2.589, | |
| "eval_steps_per_second": 2.589, | |
| "step": 350 | |
| }, | |
| { | |
| "acc": 0.60742517, | |
| "epoch": 1.3271028037383177, | |
| "grad_norm": 1.6696964502334595, | |
| "learning_rate": 2.7729397871718304e-05, | |
| "loss": 1.41251793, | |
| "memory(GiB)": 25.22, | |
| "step": 355, | |
| "train_speed(iter/s)": 0.333524 | |
| }, | |
| { | |
| "acc": 0.59874382, | |
| "epoch": 1.3457943925233644, | |
| "grad_norm": 1.631954550743103, | |
| "learning_rate": 2.635335069067617e-05, | |
| "loss": 1.43565807, | |
| "memory(GiB)": 25.22, | |
| "step": 360, | |
| "train_speed(iter/s)": 0.33422 | |
| }, | |
| { | |
| "acc": 0.62206426, | |
| "epoch": 1.3644859813084111, | |
| "grad_norm": 1.6964654922485352, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.40124302, | |
| "memory(GiB)": 25.22, | |
| "step": 365, | |
| "train_speed(iter/s)": 0.334875 | |
| }, | |
| { | |
| "acc": 0.60629749, | |
| "epoch": 1.3831775700934579, | |
| "grad_norm": 1.4727040529251099, | |
| "learning_rate": 2.367064477065652e-05, | |
| "loss": 1.4464427, | |
| "memory(GiB)": 25.22, | |
| "step": 370, | |
| "train_speed(iter/s)": 0.335544 | |
| }, | |
| { | |
| "acc": 0.60391579, | |
| "epoch": 1.4018691588785046, | |
| "grad_norm": 1.7280242443084717, | |
| "learning_rate": 2.2366560942325832e-05, | |
| "loss": 1.41403561, | |
| "memory(GiB)": 25.22, | |
| "step": 375, | |
| "train_speed(iter/s)": 0.336204 | |
| }, | |
| { | |
| "acc": 0.60924401, | |
| "epoch": 1.4205607476635513, | |
| "grad_norm": 1.7434614896774292, | |
| "learning_rate": 2.108900019873103e-05, | |
| "loss": 1.44466, | |
| "memory(GiB)": 25.22, | |
| "step": 380, | |
| "train_speed(iter/s)": 0.336821 | |
| }, | |
| { | |
| "acc": 0.62293906, | |
| "epoch": 1.439252336448598, | |
| "grad_norm": 1.5931147336959839, | |
| "learning_rate": 1.983918876624902e-05, | |
| "loss": 1.36733408, | |
| "memory(GiB)": 25.22, | |
| "step": 385, | |
| "train_speed(iter/s)": 0.337406 | |
| }, | |
| { | |
| "acc": 0.60391083, | |
| "epoch": 1.4579439252336448, | |
| "grad_norm": 1.8774250745773315, | |
| "learning_rate": 1.8618326236955907e-05, | |
| "loss": 1.47434216, | |
| "memory(GiB)": 25.22, | |
| "step": 390, | |
| "train_speed(iter/s)": 0.337991 | |
| }, | |
| { | |
| "acc": 0.59494829, | |
| "epoch": 1.4766355140186915, | |
| "grad_norm": 1.6903536319732666, | |
| "learning_rate": 1.7427584417236194e-05, | |
| "loss": 1.4961113, | |
| "memory(GiB)": 25.22, | |
| "step": 395, | |
| "train_speed(iter/s)": 0.338556 | |
| }, | |
| { | |
| "acc": 0.61160607, | |
| "epoch": 1.4953271028037383, | |
| "grad_norm": 1.6840981245040894, | |
| "learning_rate": 1.626810620306163e-05, | |
| "loss": 1.3965476, | |
| "memory(GiB)": 25.22, | |
| "step": 400, | |
| "train_speed(iter/s)": 0.339121 | |
| }, | |
| { | |
| "epoch": 1.4953271028037383, | |
| "eval_acc": 0.5915429599640126, | |
| "eval_loss": 1.5317269563674927, | |
| "eval_runtime": 19.3286, | |
| "eval_samples_per_second": 2.587, | |
| "eval_steps_per_second": 2.587, | |
| "step": 400 | |
| }, | |
| { | |
| "acc": 0.59379582, | |
| "epoch": 1.514018691588785, | |
| "grad_norm": 1.6205955743789673, | |
| "learning_rate": 1.5141004483018323e-05, | |
| "loss": 1.44787579, | |
| "memory(GiB)": 25.22, | |
| "step": 405, | |
| "train_speed(iter/s)": 0.333982 | |
| }, | |
| { | |
| "acc": 0.61180854, | |
| "epoch": 1.5327102803738317, | |
| "grad_norm": 1.9331731796264648, | |
| "learning_rate": 1.4047361070135995e-05, | |
| "loss": 1.46465635, | |
| "memory(GiB)": 25.22, | |
| "step": 410, | |
| "train_speed(iter/s)": 0.334588 | |
| }, | |
| { | |
| "acc": 0.59493322, | |
| "epoch": 1.5514018691588785, | |
| "grad_norm": 1.579399824142456, | |
| "learning_rate": 1.2988225663543602e-05, | |
| "loss": 1.51334658, | |
| "memory(GiB)": 25.22, | |
| "step": 415, | |
| "train_speed(iter/s)": 0.335141 | |
| }, | |
| { | |
| "acc": 0.60085406, | |
| "epoch": 1.5700934579439252, | |
| "grad_norm": 1.7813141345977783, | |
| "learning_rate": 1.1964614840949002e-05, | |
| "loss": 1.44739676, | |
| "memory(GiB)": 25.22, | |
| "step": 420, | |
| "train_speed(iter/s)": 0.335707 | |
| }, | |
| { | |
| "acc": 0.59427462, | |
| "epoch": 1.588785046728972, | |
| "grad_norm": 1.6966168880462646, | |
| "learning_rate": 1.097751108290867e-05, | |
| "loss": 1.47780085, | |
| "memory(GiB)": 25.22, | |
| "step": 425, | |
| "train_speed(iter/s)": 0.336254 | |
| }, | |
| { | |
| "acc": 0.623209, | |
| "epoch": 1.6074766355140186, | |
| "grad_norm": 1.801193118095398, | |
| "learning_rate": 1.0027861829824952e-05, | |
| "loss": 1.37850494, | |
| "memory(GiB)": 25.22, | |
| "step": 430, | |
| "train_speed(iter/s)": 0.336818 | |
| }, | |
| { | |
| "acc": 0.60559597, | |
| "epoch": 1.6261682242990654, | |
| "grad_norm": 1.694907307624817, | |
| "learning_rate": 9.11657857257509e-06, | |
| "loss": 1.47119045, | |
| "memory(GiB)": 25.22, | |
| "step": 435, | |
| "train_speed(iter/s)": 0.337357 | |
| }, | |
| { | |
| "acc": 0.60444808, | |
| "epoch": 1.644859813084112, | |
| "grad_norm": 1.8144758939743042, | |
| "learning_rate": 8.244535977645585e-06, | |
| "loss": 1.46991854, | |
| "memory(GiB)": 25.22, | |
| "step": 440, | |
| "train_speed(iter/s)": 0.337883 | |
| }, | |
| { | |
| "acc": 0.61087198, | |
| "epoch": 1.6635514018691588, | |
| "grad_norm": 1.8258271217346191, | |
| "learning_rate": 7.412571047611155e-06, | |
| "loss": 1.39234638, | |
| "memory(GiB)": 25.22, | |
| "step": 445, | |
| "train_speed(iter/s)": 0.3384 | |
| }, | |
| { | |
| "acc": 0.60143399, | |
| "epoch": 1.6822429906542056, | |
| "grad_norm": 1.8941428661346436, | |
| "learning_rate": 6.621482317764105e-06, | |
| "loss": 1.43530188, | |
| "memory(GiB)": 25.22, | |
| "step": 450, | |
| "train_speed(iter/s)": 0.338913 | |
| }, | |
| { | |
| "epoch": 1.6822429906542056, | |
| "eval_acc": 0.5921427500374868, | |
| "eval_loss": 1.532676100730896, | |
| "eval_runtime": 19.3483, | |
| "eval_samples_per_second": 2.584, | |
| "eval_steps_per_second": 2.584, | |
| "step": 450 | |
| }, | |
| { | |
| "acc": 0.61480565, | |
| "epoch": 1.7009345794392523, | |
| "grad_norm": 1.939122200012207, | |
| "learning_rate": 5.872029089665587e-06, | |
| "loss": 1.39058199, | |
| "memory(GiB)": 25.22, | |
| "step": 455, | |
| "train_speed(iter/s)": 0.33434 | |
| }, | |
| { | |
| "acc": 0.60005183, | |
| "epoch": 1.719626168224299, | |
| "grad_norm": 1.91712486743927, | |
| "learning_rate": 5.164930702353782e-06, | |
| "loss": 1.45630856, | |
| "memory(GiB)": 25.22, | |
| "step": 460, | |
| "train_speed(iter/s)": 0.334872 | |
| }, | |
| { | |
| "acc": 0.59249868, | |
| "epoch": 1.7383177570093458, | |
| "grad_norm": 1.6661227941513062, | |
| "learning_rate": 4.500865841909168e-06, | |
| "loss": 1.46352968, | |
| "memory(GiB)": 25.22, | |
| "step": 465, | |
| "train_speed(iter/s)": 0.335375 | |
| }, | |
| { | |
| "acc": 0.6019537, | |
| "epoch": 1.7570093457943925, | |
| "grad_norm": 1.7562310695648193, | |
| "learning_rate": 3.880471890038967e-06, | |
| "loss": 1.4511817, | |
| "memory(GiB)": 25.22, | |
| "step": 470, | |
| "train_speed(iter/s)": 0.335886 | |
| }, | |
| { | |
| "acc": 0.60008221, | |
| "epoch": 1.7757009345794392, | |
| "grad_norm": 1.6243735551834106, | |
| "learning_rate": 3.3043443123065286e-06, | |
| "loss": 1.49449492, | |
| "memory(GiB)": 25.22, | |
| "step": 475, | |
| "train_speed(iter/s)": 0.336362 | |
| }, | |
| { | |
| "acc": 0.59502878, | |
| "epoch": 1.794392523364486, | |
| "grad_norm": 2.1284008026123047, | |
| "learning_rate": 2.7730360865923956e-06, | |
| "loss": 1.46432257, | |
| "memory(GiB)": 25.22, | |
| "step": 480, | |
| "train_speed(iter/s)": 0.336856 | |
| }, | |
| { | |
| "acc": 0.58453884, | |
| "epoch": 1.8130841121495327, | |
| "grad_norm": 1.7423293590545654, | |
| "learning_rate": 2.287057172336021e-06, | |
| "loss": 1.53189554, | |
| "memory(GiB)": 25.22, | |
| "step": 485, | |
| "train_speed(iter/s)": 0.337332 | |
| }, | |
| { | |
| "acc": 0.59840698, | |
| "epoch": 1.8317757009345794, | |
| "grad_norm": 1.787650227546692, | |
| "learning_rate": 1.8468740210672076e-06, | |
| "loss": 1.44042816, | |
| "memory(GiB)": 25.22, | |
| "step": 490, | |
| "train_speed(iter/s)": 0.337808 | |
| }, | |
| { | |
| "acc": 0.60692272, | |
| "epoch": 1.8504672897196262, | |
| "grad_norm": 1.7444405555725098, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 1.42584867, | |
| "memory(GiB)": 25.22, | |
| "step": 495, | |
| "train_speed(iter/s)": 0.338284 | |
| }, | |
| { | |
| "acc": 0.58918037, | |
| "epoch": 1.8691588785046729, | |
| "grad_norm": 1.7888891696929932, | |
| "learning_rate": 1.1055406300002347e-06, | |
| "loss": 1.48684044, | |
| "memory(GiB)": 25.22, | |
| "step": 500, | |
| "train_speed(iter/s)": 0.338742 | |
| }, | |
| { | |
| "epoch": 1.8691588785046729, | |
| "eval_acc": 0.5931923826660669, | |
| "eval_loss": 1.5313353538513184, | |
| "eval_runtime": 19.3381, | |
| "eval_samples_per_second": 2.586, | |
| "eval_steps_per_second": 2.586, | |
| "step": 500 | |
| }, | |
| { | |
| "acc": 0.61618199, | |
| "epoch": 1.8878504672897196, | |
| "grad_norm": 1.9864728450775146, | |
| "learning_rate": 8.0510193567086e-07, | |
| "loss": 1.43374748, | |
| "memory(GiB)": 25.22, | |
| "step": 505, | |
| "train_speed(iter/s)": 0.334578 | |
| }, | |
| { | |
| "acc": 0.60259299, | |
| "epoch": 1.9065420560747663, | |
| "grad_norm": 1.688388705253601, | |
| "learning_rate": 5.518814123121885e-07, | |
| "loss": 1.49144144, | |
| "memory(GiB)": 25.22, | |
| "step": 510, | |
| "train_speed(iter/s)": 0.335056 | |
| }, | |
| { | |
| "acc": 0.61285515, | |
| "epoch": 1.925233644859813, | |
| "grad_norm": 1.6542000770568848, | |
| "learning_rate": 3.4612210565528326e-07, | |
| "loss": 1.44376268, | |
| "memory(GiB)": 25.22, | |
| "step": 515, | |
| "train_speed(iter/s)": 0.335522 | |
| }, | |
| { | |
| "acc": 0.61628981, | |
| "epoch": 1.9439252336448598, | |
| "grad_norm": 2.033604145050049, | |
| "learning_rate": 1.8802150727962876e-07, | |
| "loss": 1.39236612, | |
| "memory(GiB)": 25.22, | |
| "step": 520, | |
| "train_speed(iter/s)": 0.335983 | |
| }, | |
| { | |
| "acc": 0.62410831, | |
| "epoch": 1.9626168224299065, | |
| "grad_norm": 1.6692521572113037, | |
| "learning_rate": 7.773136505700995e-08, | |
| "loss": 1.36968622, | |
| "memory(GiB)": 25.22, | |
| "step": 525, | |
| "train_speed(iter/s)": 0.336429 | |
| }, | |
| { | |
| "acc": 0.60063834, | |
| "epoch": 1.9813084112149533, | |
| "grad_norm": 1.7963093519210815, | |
| "learning_rate": 1.5357537501159423e-08, | |
| "loss": 1.46681242, | |
| "memory(GiB)": 25.22, | |
| "step": 530, | |
| "train_speed(iter/s)": 0.336698 | |
| }, | |
| { | |
| "epoch": 1.9962616822429906, | |
| "eval_acc": 0.5915429599640126, | |
| "eval_loss": 1.5304458141326904, | |
| "eval_runtime": 20.9568, | |
| "eval_samples_per_second": 2.386, | |
| "eval_steps_per_second": 2.386, | |
| "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": 8.23057811304193e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |