| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9998447060285119, | |
| "eval_steps": 500, | |
| "global_step": 503, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.019877628350467434, | |
| "grad_norm": 49.489271990521864, | |
| "learning_rate": 1.730769230769231e-05, | |
| "loss": 18.2674, | |
| "num_tokens": 35435900.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03975525670093487, | |
| "grad_norm": 94.13839060488317, | |
| "learning_rate": 3.653846153846154e-05, | |
| "loss": 6.0352, | |
| "num_tokens": 70986000.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0596328850514023, | |
| "grad_norm": 36.22989263913226, | |
| "learning_rate": 4.999560818649105e-05, | |
| "loss": 2.257, | |
| "num_tokens": 106406261.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07951051340186974, | |
| "grad_norm": 12.381662510455556, | |
| "learning_rate": 4.99175791880267e-05, | |
| "loss": 1.6806, | |
| "num_tokens": 142007549.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09938814175233718, | |
| "grad_norm": 6.078747336589003, | |
| "learning_rate": 4.9742343823849924e-05, | |
| "loss": 1.6283, | |
| "num_tokens": 177749958.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1192657701028046, | |
| "grad_norm": 45.316378371707856, | |
| "learning_rate": 4.947066194375331e-05, | |
| "loss": 1.405, | |
| "num_tokens": 213223619.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13914339845327203, | |
| "grad_norm": 4.457640477421176, | |
| "learning_rate": 4.910371160572305e-05, | |
| "loss": 1.4731, | |
| "num_tokens": 248699816.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.15902102680373947, | |
| "grad_norm": 3.8571852421472106, | |
| "learning_rate": 4.864308396768294e-05, | |
| "loss": 1.1962, | |
| "num_tokens": 284242373.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.17889865515420691, | |
| "grad_norm": 2.922271088762262, | |
| "learning_rate": 4.8090776387967915e-05, | |
| "loss": 1.1482, | |
| "num_tokens": 319801798.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.19877628350467436, | |
| "grad_norm": 3.07929680688637, | |
| "learning_rate": 4.7449183764444924e-05, | |
| "loss": 1.1573, | |
| "num_tokens": 355227417.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2186539118551418, | |
| "grad_norm": 2.986142143054458, | |
| "learning_rate": 4.672108814983597e-05, | |
| "loss": 1.1133, | |
| "num_tokens": 35532164.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2385315402056092, | |
| "grad_norm": 2.347646077232914, | |
| "learning_rate": 4.590964668827306e-05, | |
| "loss": 1.1624, | |
| "num_tokens": 71080907.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.25840916855607665, | |
| "grad_norm": 3.077510825746025, | |
| "learning_rate": 4.501837792539419e-05, | |
| "loss": 1.0658, | |
| "num_tokens": 106602450.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.27828679690654406, | |
| "grad_norm": 1.7347828183409042, | |
| "learning_rate": 4.4051146551342136e-05, | |
| "loss": 1.0483, | |
| "num_tokens": 142169486.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.29816442525701153, | |
| "grad_norm": 2.802057431831608, | |
| "learning_rate": 4.301214664282277e-05, | |
| "loss": 1.0333, | |
| "num_tokens": 177675215.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.31804205360747895, | |
| "grad_norm": 2.268188963759059, | |
| "learning_rate": 4.190588347688833e-05, | |
| "loss": 1.0238, | |
| "num_tokens": 213190309.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3379196819579464, | |
| "grad_norm": 1.6440471046115712, | |
| "learning_rate": 4.073715399530405e-05, | |
| "loss": 0.9957, | |
| "num_tokens": 248802333.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.35779731030841383, | |
| "grad_norm": 1.3717651355528624, | |
| "learning_rate": 3.9511026004207795e-05, | |
| "loss": 0.9574, | |
| "num_tokens": 284367601.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.37767493865888124, | |
| "grad_norm": 1.6711348270758677, | |
| "learning_rate": 3.823281619925673e-05, | |
| "loss": 0.9611, | |
| "num_tokens": 319996464.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3975525670093487, | |
| "grad_norm": 1.8188583401200056, | |
| "learning_rate": 3.69080671115473e-05, | |
| "loss": 0.9318, | |
| "num_tokens": 355585930.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4174301953598161, | |
| "grad_norm": 1.6314158389343252, | |
| "learning_rate": 3.554252307427526e-05, | |
| "loss": 0.9428, | |
| "num_tokens": 391200376.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4373078237102836, | |
| "grad_norm": 1.406291241468206, | |
| "learning_rate": 3.414210531434781e-05, | |
| "loss": 0.934, | |
| "num_tokens": 426715690.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.457185452060751, | |
| "grad_norm": 1.5568298850166404, | |
| "learning_rate": 3.271288627695541e-05, | |
| "loss": 0.8906, | |
| "num_tokens": 462193838.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.4770630804112184, | |
| "grad_norm": 1.6374375121178215, | |
| "learning_rate": 3.126106329443562e-05, | |
| "loss": 0.8869, | |
| "num_tokens": 497775413.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4969407087616859, | |
| "grad_norm": 1.4278396281710222, | |
| "learning_rate": 2.9792931713605558e-05, | |
| "loss": 0.8715, | |
| "num_tokens": 533288808.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5168183371121533, | |
| "grad_norm": 1.3315422073102914, | |
| "learning_rate": 2.831485759808712e-05, | |
| "loss": 0.8535, | |
| "num_tokens": 568733244.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5366959654626208, | |
| "grad_norm": 1.4292589501021156, | |
| "learning_rate": 2.683325012399241e-05, | |
| "loss": 0.8555, | |
| "num_tokens": 604337940.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5565735938130881, | |
| "grad_norm": 1.3191036037659456, | |
| "learning_rate": 2.5354533788666173e-05, | |
| "loss": 0.8258, | |
| "num_tokens": 639897455.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5764512221635556, | |
| "grad_norm": 1.2135834698476922, | |
| "learning_rate": 2.388512055299283e-05, | |
| "loss": 0.8152, | |
| "num_tokens": 675560731.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.5963288505140231, | |
| "grad_norm": 1.1849646162622842, | |
| "learning_rate": 2.2431382038063615e-05, | |
| "loss": 0.8033, | |
| "num_tokens": 710895149.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6162064788644904, | |
| "grad_norm": 1.0526968604787708, | |
| "learning_rate": 2.0999621896763955e-05, | |
| "loss": 0.7823, | |
| "num_tokens": 746372135.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6360841072149579, | |
| "grad_norm": 1.0814389110808431, | |
| "learning_rate": 1.959604848008217e-05, | |
| "loss": 0.7653, | |
| "num_tokens": 781964693.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6559617355654254, | |
| "grad_norm": 1.1579079388621223, | |
| "learning_rate": 1.8226747916663184e-05, | |
| "loss": 0.7535, | |
| "num_tokens": 817483499.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6758393639158928, | |
| "grad_norm": 1.0764253018415963, | |
| "learning_rate": 1.6897657722338715e-05, | |
| "loss": 0.7417, | |
| "num_tokens": 853175363.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6957169922663602, | |
| "grad_norm": 1.0645270530767825, | |
| "learning_rate": 1.561454105406746e-05, | |
| "loss": 0.7284, | |
| "num_tokens": 888676759.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7155946206168277, | |
| "grad_norm": 1.0991349699273438, | |
| "learning_rate": 1.4382961719924382e-05, | |
| "loss": 0.7102, | |
| "num_tokens": 924126537.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7354722489672951, | |
| "grad_norm": 1.096361260557103, | |
| "learning_rate": 1.3208260053500118e-05, | |
| "loss": 0.7016, | |
| "num_tokens": 959627625.0, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.7553498773177625, | |
| "grad_norm": 1.2001309900905168, | |
| "learning_rate": 1.2095529757323018e-05, | |
| "loss": 0.6735, | |
| "num_tokens": 995276803.0, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.77522750566823, | |
| "grad_norm": 1.0243664466225824, | |
| "learning_rate": 1.104959581571463e-05, | |
| "loss": 0.6649, | |
| "num_tokens": 1030735793.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7951051340186974, | |
| "grad_norm": 1.4526878564718964, | |
| "learning_rate": 1.0074993572852243e-05, | |
| "loss": 0.6713, | |
| "num_tokens": 1066374499.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8149827623691648, | |
| "grad_norm": 1.050605567010305, | |
| "learning_rate": 9.175949066759368e-06, | |
| "loss": 0.6419, | |
| "num_tokens": 1101855303.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.8348603907196323, | |
| "grad_norm": 1.125778801254232, | |
| "learning_rate": 8.356360704499399e-06, | |
| "loss": 0.635, | |
| "num_tokens": 1137354673.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.8547380190700997, | |
| "grad_norm": 1.1832572011409386, | |
| "learning_rate": 7.619782358031821e-06, | |
| "loss": 0.6267, | |
| "num_tokens": 1172860263.0, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.8746156474205672, | |
| "grad_norm": 1.1054714685819218, | |
| "learning_rate": 6.969407954030057e-06, | |
| "loss": 0.6116, | |
| "num_tokens": 1208508537.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8944932757710345, | |
| "grad_norm": 1.089754156750933, | |
| "learning_rate": 6.40805762448228e-06, | |
| "loss": 0.6051, | |
| "num_tokens": 1244052723.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.914370904121502, | |
| "grad_norm": 1.0612130068358916, | |
| "learning_rate": 5.938165478128298e-06, | |
| "loss": 0.591, | |
| "num_tokens": 1279456435.0, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9342485324719695, | |
| "grad_norm": 1.1570486650093461, | |
| "learning_rate": 5.5617690457577016e-06, | |
| "loss": 0.5808, | |
| "num_tokens": 1314958319.0, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.9541261608224368, | |
| "grad_norm": 1.4354838420805704, | |
| "learning_rate": 5.280500445136247e-06, | |
| "loss": 0.5754, | |
| "num_tokens": 1350578878.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.9740037891729043, | |
| "grad_norm": 1.3310227594903838, | |
| "learning_rate": 5.095579303870732e-06, | |
| "loss": 0.5693, | |
| "num_tokens": 1386062688.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9938814175233718, | |
| "grad_norm": 1.0908684710720695, | |
| "learning_rate": 5.007807470900112e-06, | |
| "loss": 0.5606, | |
| "num_tokens": 1421565738.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9998447060285119, | |
| "num_tokens": 1432289557.0, | |
| "step": 503, | |
| "total_flos": 1.1360204825667672e+20, | |
| "train_loss": 0.6426609048312512, | |
| "train_runtime": 119967.1502, | |
| "train_samples_per_second": 2.147, | |
| "train_steps_per_second": 0.004 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 503, | |
| "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": 1.1360204825667672e+20, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |