| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.11471836641046232, |
| "eval_steps": 10, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.001147183664104623, |
| "eval_loss": 1.873344898223877, |
| "eval_runtime": 12.7647, |
| "eval_samples_per_second": 515.797, |
| "eval_steps_per_second": 8.069, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.002294367328209246, |
| "eval_loss": 1.8726389408111572, |
| "eval_runtime": 12.8667, |
| "eval_samples_per_second": 511.709, |
| "eval_steps_per_second": 8.005, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0034415509923138693, |
| "eval_loss": 1.8714078664779663, |
| "eval_runtime": 12.9103, |
| "eval_samples_per_second": 509.979, |
| "eval_steps_per_second": 7.978, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.004588734656418492, |
| "eval_loss": 1.8696790933609009, |
| "eval_runtime": 12.947, |
| "eval_samples_per_second": 508.534, |
| "eval_steps_per_second": 7.955, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0057359183205231154, |
| "eval_loss": 1.8675329685211182, |
| "eval_runtime": 12.9458, |
| "eval_samples_per_second": 508.582, |
| "eval_steps_per_second": 7.956, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.006883101984627739, |
| "eval_loss": 1.8649154901504517, |
| "eval_runtime": 13.0432, |
| "eval_samples_per_second": 504.785, |
| "eval_steps_per_second": 7.897, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.008030285648732363, |
| "eval_loss": 1.8619294166564941, |
| "eval_runtime": 13.0638, |
| "eval_samples_per_second": 503.988, |
| "eval_steps_per_second": 7.884, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.009177469312836984, |
| "eval_loss": 1.8583979606628418, |
| "eval_runtime": 13.0482, |
| "eval_samples_per_second": 504.592, |
| "eval_steps_per_second": 7.894, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.010324652976941608, |
| "eval_loss": 1.85438871383667, |
| "eval_runtime": 13.0615, |
| "eval_samples_per_second": 504.075, |
| "eval_steps_per_second": 7.886, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.011471836641046231, |
| "grad_norm": 9.938580513000488, |
| "learning_rate": 3.8226299694189603e-07, |
| "loss": 3.1046, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.011471836641046231, |
| "eval_loss": 1.849947214126587, |
| "eval_runtime": 13.0663, |
| "eval_samples_per_second": 503.89, |
| "eval_steps_per_second": 7.883, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.012619020305150854, |
| "eval_loss": 1.8451412916183472, |
| "eval_runtime": 12.9771, |
| "eval_samples_per_second": 507.357, |
| "eval_steps_per_second": 7.937, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.013766203969255477, |
| "eval_loss": 1.8399487733840942, |
| "eval_runtime": 13.0209, |
| "eval_samples_per_second": 505.648, |
| "eval_steps_per_second": 7.91, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.0149133876333601, |
| "eval_loss": 1.8342881202697754, |
| "eval_runtime": 13.0369, |
| "eval_samples_per_second": 505.028, |
| "eval_steps_per_second": 7.901, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.016060571297464726, |
| "eval_loss": 1.8283486366271973, |
| "eval_runtime": 13.0149, |
| "eval_samples_per_second": 505.88, |
| "eval_steps_per_second": 7.914, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.017207754961569347, |
| "eval_loss": 1.822334885597229, |
| "eval_runtime": 13.0213, |
| "eval_samples_per_second": 505.632, |
| "eval_steps_per_second": 7.91, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.01835493862567397, |
| "eval_loss": 1.8158738613128662, |
| "eval_runtime": 13.0599, |
| "eval_samples_per_second": 504.14, |
| "eval_steps_per_second": 7.887, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.019502122289778594, |
| "eval_loss": 1.8090614080429077, |
| "eval_runtime": 13.034, |
| "eval_samples_per_second": 505.14, |
| "eval_steps_per_second": 7.902, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.020649305953883215, |
| "eval_loss": 1.8015782833099365, |
| "eval_runtime": 13.0665, |
| "eval_samples_per_second": 503.885, |
| "eval_steps_per_second": 7.883, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.02179648961798784, |
| "eval_loss": 1.793796420097351, |
| "eval_runtime": 13.0555, |
| "eval_samples_per_second": 504.31, |
| "eval_steps_per_second": 7.889, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.022943673282092462, |
| "grad_norm": 4.906337738037109, |
| "learning_rate": 7.645259938837921e-07, |
| "loss": 3.0303, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.022943673282092462, |
| "eval_loss": 1.785815715789795, |
| "eval_runtime": 12.9925, |
| "eval_samples_per_second": 506.754, |
| "eval_steps_per_second": 7.928, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.024090856946197087, |
| "eval_loss": 1.7775053977966309, |
| "eval_runtime": 13.0639, |
| "eval_samples_per_second": 503.986, |
| "eval_steps_per_second": 7.884, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.025238040610301708, |
| "eval_loss": 1.7692992687225342, |
| "eval_runtime": 13.0129, |
| "eval_samples_per_second": 505.96, |
| "eval_steps_per_second": 7.915, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.026385224274406333, |
| "eval_loss": 1.760453224182129, |
| "eval_runtime": 13.0078, |
| "eval_samples_per_second": 506.158, |
| "eval_steps_per_second": 7.918, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.027532407938510955, |
| "eval_loss": 1.751396656036377, |
| "eval_runtime": 12.9957, |
| "eval_samples_per_second": 506.628, |
| "eval_steps_per_second": 7.926, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.02867959160261558, |
| "eval_loss": 1.7417218685150146, |
| "eval_runtime": 12.9774, |
| "eval_samples_per_second": 507.344, |
| "eval_steps_per_second": 7.937, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.0298267752667202, |
| "eval_loss": 1.7319914102554321, |
| "eval_runtime": 13.0219, |
| "eval_samples_per_second": 505.611, |
| "eval_steps_per_second": 7.91, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.030973958930824826, |
| "eval_loss": 1.7227253913879395, |
| "eval_runtime": 13.0026, |
| "eval_samples_per_second": 506.361, |
| "eval_steps_per_second": 7.922, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.03212114259492945, |
| "eval_loss": 1.7133797407150269, |
| "eval_runtime": 12.9757, |
| "eval_samples_per_second": 507.409, |
| "eval_steps_per_second": 7.938, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.03326832625903407, |
| "eval_loss": 1.704041600227356, |
| "eval_runtime": 12.9845, |
| "eval_samples_per_second": 507.065, |
| "eval_steps_per_second": 7.933, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.034415509923138694, |
| "grad_norm": 4.665822505950928, |
| "learning_rate": 1.1467889908256882e-06, |
| "loss": 2.9459, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.034415509923138694, |
| "eval_loss": 1.6940686702728271, |
| "eval_runtime": 13.0019, |
| "eval_samples_per_second": 506.387, |
| "eval_steps_per_second": 7.922, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.035562693587243316, |
| "eval_loss": 1.683342695236206, |
| "eval_runtime": 13.0065, |
| "eval_samples_per_second": 506.209, |
| "eval_steps_per_second": 7.919, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.03670987725134794, |
| "eval_loss": 1.6724653244018555, |
| "eval_runtime": 13.0129, |
| "eval_samples_per_second": 505.96, |
| "eval_steps_per_second": 7.915, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.037857060915452566, |
| "eval_loss": 1.6614341735839844, |
| "eval_runtime": 12.9921, |
| "eval_samples_per_second": 506.769, |
| "eval_steps_per_second": 7.928, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.03900424457955719, |
| "eval_loss": 1.6510112285614014, |
| "eval_runtime": 13.0242, |
| "eval_samples_per_second": 505.52, |
| "eval_steps_per_second": 7.908, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.04015142824366181, |
| "eval_loss": 1.6401513814926147, |
| "eval_runtime": 12.9214, |
| "eval_samples_per_second": 509.542, |
| "eval_steps_per_second": 7.971, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.04129861190776643, |
| "eval_loss": 1.6295816898345947, |
| "eval_runtime": 12.9563, |
| "eval_samples_per_second": 508.171, |
| "eval_steps_per_second": 7.95, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.04244579557187106, |
| "eval_loss": 1.6187150478363037, |
| "eval_runtime": 12.9758, |
| "eval_samples_per_second": 507.405, |
| "eval_steps_per_second": 7.938, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.04359297923597568, |
| "eval_loss": 1.607272982597351, |
| "eval_runtime": 12.9876, |
| "eval_samples_per_second": 506.947, |
| "eval_steps_per_second": 7.931, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.0447401629000803, |
| "eval_loss": 1.5961676836013794, |
| "eval_runtime": 12.9782, |
| "eval_samples_per_second": 507.313, |
| "eval_steps_per_second": 7.936, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.045887346564184923, |
| "grad_norm": 4.870114326477051, |
| "learning_rate": 1.5290519877675841e-06, |
| "loss": 2.7813, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.045887346564184923, |
| "eval_loss": 1.5848218202590942, |
| "eval_runtime": 12.9783, |
| "eval_samples_per_second": 507.309, |
| "eval_steps_per_second": 7.936, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.04703453022828955, |
| "eval_loss": 1.5734797716140747, |
| "eval_runtime": 12.9739, |
| "eval_samples_per_second": 507.482, |
| "eval_steps_per_second": 7.939, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.04818171389239417, |
| "eval_loss": 1.562021255493164, |
| "eval_runtime": 12.9388, |
| "eval_samples_per_second": 508.855, |
| "eval_steps_per_second": 7.961, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.049328897556498795, |
| "eval_loss": 1.5495364665985107, |
| "eval_runtime": 12.9412, |
| "eval_samples_per_second": 508.764, |
| "eval_steps_per_second": 7.959, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.050476081220603417, |
| "eval_loss": 1.5375314950942993, |
| "eval_runtime": 12.9686, |
| "eval_samples_per_second": 507.687, |
| "eval_steps_per_second": 7.942, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.051623264884708045, |
| "eval_loss": 1.525598168373108, |
| "eval_runtime": 12.9695, |
| "eval_samples_per_second": 507.651, |
| "eval_steps_per_second": 7.942, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.052770448548812667, |
| "eval_loss": 1.5132672786712646, |
| "eval_runtime": 12.8961, |
| "eval_samples_per_second": 510.543, |
| "eval_steps_per_second": 7.987, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.05391763221291729, |
| "eval_loss": 1.5012215375900269, |
| "eval_runtime": 12.9428, |
| "eval_samples_per_second": 508.7, |
| "eval_steps_per_second": 7.958, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.05506481587702191, |
| "eval_loss": 1.4892219305038452, |
| "eval_runtime": 12.9208, |
| "eval_samples_per_second": 509.567, |
| "eval_steps_per_second": 7.972, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.05621199954112653, |
| "eval_loss": 1.4768636226654053, |
| "eval_runtime": 12.9423, |
| "eval_samples_per_second": 508.721, |
| "eval_steps_per_second": 7.958, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.05735918320523116, |
| "grad_norm": 4.155641555786133, |
| "learning_rate": 1.9113149847094803e-06, |
| "loss": 2.6308, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.05735918320523116, |
| "eval_loss": 1.4640088081359863, |
| "eval_runtime": 12.8729, |
| "eval_samples_per_second": 511.462, |
| "eval_steps_per_second": 8.001, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.05850636686933578, |
| "eval_loss": 1.4513096809387207, |
| "eval_runtime": 12.9653, |
| "eval_samples_per_second": 507.817, |
| "eval_steps_per_second": 7.944, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.0596535505334404, |
| "eval_loss": 1.439149260520935, |
| "eval_runtime": 12.9443, |
| "eval_samples_per_second": 508.639, |
| "eval_steps_per_second": 7.957, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.060800734197545024, |
| "eval_loss": 1.426237940788269, |
| "eval_runtime": 12.9496, |
| "eval_samples_per_second": 508.433, |
| "eval_steps_per_second": 7.954, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.06194791786164965, |
| "eval_loss": 1.4129557609558105, |
| "eval_runtime": 12.9822, |
| "eval_samples_per_second": 507.157, |
| "eval_steps_per_second": 7.934, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.06309510152575427, |
| "eval_loss": 1.3997886180877686, |
| "eval_runtime": 12.9979, |
| "eval_samples_per_second": 506.542, |
| "eval_steps_per_second": 7.924, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.0642422851898589, |
| "eval_loss": 1.3873906135559082, |
| "eval_runtime": 12.9378, |
| "eval_samples_per_second": 508.895, |
| "eval_steps_per_second": 7.961, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.06538946885396352, |
| "eval_loss": 1.3751789331436157, |
| "eval_runtime": 12.9624, |
| "eval_samples_per_second": 507.932, |
| "eval_steps_per_second": 7.946, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.06653665251806815, |
| "eval_loss": 1.3620370626449585, |
| "eval_runtime": 12.9498, |
| "eval_samples_per_second": 508.426, |
| "eval_steps_per_second": 7.954, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.06768383618217276, |
| "eval_loss": 1.3485124111175537, |
| "eval_runtime": 12.9759, |
| "eval_samples_per_second": 507.403, |
| "eval_steps_per_second": 7.938, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.06883101984627739, |
| "grad_norm": 5.262124061584473, |
| "learning_rate": 2.2935779816513764e-06, |
| "loss": 2.4452, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.06883101984627739, |
| "eval_loss": 1.3349775075912476, |
| "eval_runtime": 12.9631, |
| "eval_samples_per_second": 507.902, |
| "eval_steps_per_second": 7.946, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.06997820351038202, |
| "eval_loss": 1.3213400840759277, |
| "eval_runtime": 12.9619, |
| "eval_samples_per_second": 507.951, |
| "eval_steps_per_second": 7.946, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.07112538717448663, |
| "eval_loss": 1.308822512626648, |
| "eval_runtime": 12.9652, |
| "eval_samples_per_second": 507.82, |
| "eval_steps_per_second": 7.944, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.07227257083859126, |
| "eval_loss": 1.296485185623169, |
| "eval_runtime": 13.0441, |
| "eval_samples_per_second": 504.75, |
| "eval_steps_per_second": 7.896, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.07341975450269587, |
| "eval_loss": 1.283867597579956, |
| "eval_runtime": 12.9822, |
| "eval_samples_per_second": 507.154, |
| "eval_steps_per_second": 7.934, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.0745669381668005, |
| "eval_loss": 1.2713148593902588, |
| "eval_runtime": 12.9775, |
| "eval_samples_per_second": 507.338, |
| "eval_steps_per_second": 7.937, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.07571412183090513, |
| "eval_loss": 1.2591922283172607, |
| "eval_runtime": 13.0227, |
| "eval_samples_per_second": 505.578, |
| "eval_steps_per_second": 7.909, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.07686130549500975, |
| "eval_loss": 1.246610164642334, |
| "eval_runtime": 13.014, |
| "eval_samples_per_second": 505.917, |
| "eval_steps_per_second": 7.915, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.07800848915911437, |
| "eval_loss": 1.2331972122192383, |
| "eval_runtime": 12.9634, |
| "eval_samples_per_second": 507.891, |
| "eval_steps_per_second": 7.945, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.079155672823219, |
| "eval_loss": 1.2203081846237183, |
| "eval_runtime": 12.9664, |
| "eval_samples_per_second": 507.775, |
| "eval_steps_per_second": 7.944, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.08030285648732362, |
| "grad_norm": 3.824066400527954, |
| "learning_rate": 2.6758409785932725e-06, |
| "loss": 2.2626, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.08030285648732362, |
| "eval_loss": 1.207729697227478, |
| "eval_runtime": 13.037, |
| "eval_samples_per_second": 505.025, |
| "eval_steps_per_second": 7.901, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.08145004015142825, |
| "eval_loss": 1.195885419845581, |
| "eval_runtime": 12.9625, |
| "eval_samples_per_second": 507.928, |
| "eval_steps_per_second": 7.946, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.08259722381553286, |
| "eval_loss": 1.1840639114379883, |
| "eval_runtime": 13.0124, |
| "eval_samples_per_second": 505.98, |
| "eval_steps_per_second": 7.916, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.08374440747963749, |
| "eval_loss": 1.1725258827209473, |
| "eval_runtime": 12.9851, |
| "eval_samples_per_second": 507.043, |
| "eval_steps_per_second": 7.932, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.08489159114374212, |
| "eval_loss": 1.1619255542755127, |
| "eval_runtime": 13.1041, |
| "eval_samples_per_second": 502.438, |
| "eval_steps_per_second": 7.86, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.08603877480784673, |
| "eval_loss": 1.1515777111053467, |
| "eval_runtime": 12.9648, |
| "eval_samples_per_second": 507.837, |
| "eval_steps_per_second": 7.945, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.08718595847195136, |
| "eval_loss": 1.1416434049606323, |
| "eval_runtime": 13.0349, |
| "eval_samples_per_second": 505.104, |
| "eval_steps_per_second": 7.902, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.08833314213605599, |
| "eval_loss": 1.1320044994354248, |
| "eval_runtime": 13.0667, |
| "eval_samples_per_second": 503.875, |
| "eval_steps_per_second": 7.883, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.0894803258001606, |
| "eval_loss": 1.1226693391799927, |
| "eval_runtime": 13.3034, |
| "eval_samples_per_second": 494.912, |
| "eval_steps_per_second": 7.742, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.09062750946426523, |
| "eval_loss": 1.113792061805725, |
| "eval_runtime": 12.9793, |
| "eval_samples_per_second": 507.271, |
| "eval_steps_per_second": 7.936, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.09177469312836985, |
| "grad_norm": 3.358140707015991, |
| "learning_rate": 3.0581039755351682e-06, |
| "loss": 2.0044, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.09177469312836985, |
| "eval_loss": 1.1052675247192383, |
| "eval_runtime": 13.0193, |
| "eval_samples_per_second": 505.709, |
| "eval_steps_per_second": 7.911, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.09292187679247448, |
| "eval_loss": 1.0964922904968262, |
| "eval_runtime": 13.1289, |
| "eval_samples_per_second": 501.489, |
| "eval_steps_per_second": 7.845, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.0940690604565791, |
| "eval_loss": 1.0879426002502441, |
| "eval_runtime": 12.9727, |
| "eval_samples_per_second": 507.526, |
| "eval_steps_per_second": 7.94, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.09521624412068372, |
| "eval_loss": 1.0795575380325317, |
| "eval_runtime": 13.1138, |
| "eval_samples_per_second": 502.068, |
| "eval_steps_per_second": 7.854, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.09636342778478835, |
| "eval_loss": 1.0718028545379639, |
| "eval_runtime": 12.9813, |
| "eval_samples_per_second": 507.191, |
| "eval_steps_per_second": 7.934, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.09751061144889296, |
| "eval_loss": 1.0643888711929321, |
| "eval_runtime": 13.0171, |
| "eval_samples_per_second": 505.795, |
| "eval_steps_per_second": 7.913, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.09865779511299759, |
| "eval_loss": 1.0564391613006592, |
| "eval_runtime": 13.0169, |
| "eval_samples_per_second": 505.806, |
| "eval_steps_per_second": 7.913, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.09980497877710222, |
| "eval_loss": 1.0490267276763916, |
| "eval_runtime": 13.0703, |
| "eval_samples_per_second": 503.738, |
| "eval_steps_per_second": 7.88, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.10095216244120683, |
| "eval_loss": 1.0417358875274658, |
| "eval_runtime": 13.0303, |
| "eval_samples_per_second": 505.284, |
| "eval_steps_per_second": 7.905, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.10209934610531146, |
| "eval_loss": 1.0353840589523315, |
| "eval_runtime": 12.9765, |
| "eval_samples_per_second": 507.381, |
| "eval_steps_per_second": 7.937, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.10324652976941609, |
| "grad_norm": 3.705247402191162, |
| "learning_rate": 3.4403669724770644e-06, |
| "loss": 1.8763, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.10324652976941609, |
| "eval_loss": 1.0295778512954712, |
| "eval_runtime": 13.0396, |
| "eval_samples_per_second": 504.924, |
| "eval_steps_per_second": 7.899, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.1043937134335207, |
| "eval_loss": 1.0238651037216187, |
| "eval_runtime": 12.973, |
| "eval_samples_per_second": 507.515, |
| "eval_steps_per_second": 7.94, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.10554089709762533, |
| "eval_loss": 1.0180109739303589, |
| "eval_runtime": 13.0196, |
| "eval_samples_per_second": 505.7, |
| "eval_steps_per_second": 7.911, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.10668808076172995, |
| "eval_loss": 1.0122654438018799, |
| "eval_runtime": 12.9877, |
| "eval_samples_per_second": 506.942, |
| "eval_steps_per_second": 7.931, |
| "step": 930 |
| }, |
| { |
| "epoch": 0.10783526442583458, |
| "eval_loss": 1.0065423250198364, |
| "eval_runtime": 13.0039, |
| "eval_samples_per_second": 506.312, |
| "eval_steps_per_second": 7.921, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.1089824480899392, |
| "eval_loss": 1.0008338689804077, |
| "eval_runtime": 13.1129, |
| "eval_samples_per_second": 502.101, |
| "eval_steps_per_second": 7.855, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.11012963175404382, |
| "eval_loss": 0.9950375556945801, |
| "eval_runtime": 13.0191, |
| "eval_samples_per_second": 505.718, |
| "eval_steps_per_second": 7.911, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.11127681541814845, |
| "eval_loss": 0.9893631935119629, |
| "eval_runtime": 12.9794, |
| "eval_samples_per_second": 507.267, |
| "eval_steps_per_second": 7.936, |
| "step": 970 |
| }, |
| { |
| "epoch": 0.11242399908225306, |
| "eval_loss": 0.9840025305747986, |
| "eval_runtime": 12.9799, |
| "eval_samples_per_second": 507.247, |
| "eval_steps_per_second": 7.935, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.11357118274635769, |
| "eval_loss": 0.9792994856834412, |
| "eval_runtime": 12.9866, |
| "eval_samples_per_second": 506.983, |
| "eval_steps_per_second": 7.931, |
| "step": 990 |
| }, |
| { |
| "epoch": 0.11471836641046232, |
| "grad_norm": 4.240755558013916, |
| "learning_rate": 3.8226299694189605e-06, |
| "loss": 1.7287, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.11471836641046232, |
| "eval_loss": 0.9751574993133545, |
| "eval_runtime": 13.0083, |
| "eval_samples_per_second": 506.136, |
| "eval_steps_per_second": 7.918, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 26151, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
