| { |
| "best_global_step": 1200, |
| "best_metric": 1.0421009063720703, |
| "best_model_checkpoint": "./olmo_chem_lora_cpt_QLoRA_r64_alpha128/checkpoint-1200", |
| "epoch": 0.4819277108433735, |
| "eval_steps": 50, |
| "global_step": 1200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00040160642570281126, |
| "grad_norm": 36.74913787841797, |
| "learning_rate": 0.0, |
| "loss": 2.976954936981201, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.004016064257028112, |
| "grad_norm": 40.237674713134766, |
| "learning_rate": 3.614457831325301e-07, |
| "loss": 3.035895029703776, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.008032128514056224, |
| "grad_norm": 17.999801635742188, |
| "learning_rate": 7.630522088353415e-07, |
| "loss": 2.75059814453125, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.012048192771084338, |
| "grad_norm": 13.56201171875, |
| "learning_rate": 1.1646586345381528e-06, |
| "loss": 2.38979434967041, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.01606425702811245, |
| "grad_norm": 10.360796928405762, |
| "learning_rate": 1.566265060240964e-06, |
| "loss": 2.0525840759277343, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.020080321285140562, |
| "grad_norm": 16.763572692871094, |
| "learning_rate": 1.967871485943775e-06, |
| "loss": 1.8794815063476562, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.020080321285140562, |
| "eval_loss": 1.8244566917419434, |
| "eval_runtime": 224.0827, |
| "eval_samples_per_second": 17.087, |
| "eval_steps_per_second": 0.536, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.024096385542168676, |
| "grad_norm": 10.257641792297363, |
| "learning_rate": 2.3694779116465868e-06, |
| "loss": 1.7737924575805664, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.028112449799196786, |
| "grad_norm": 20.079599380493164, |
| "learning_rate": 2.771084337349398e-06, |
| "loss": 1.6911544799804688, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.0321285140562249, |
| "grad_norm": 10.683834075927734, |
| "learning_rate": 3.172690763052209e-06, |
| "loss": 1.623727798461914, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.03614457831325301, |
| "grad_norm": 11.064703941345215, |
| "learning_rate": 3.5742971887550204e-06, |
| "loss": 1.5919998168945313, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.040160642570281124, |
| "grad_norm": 9.582036972045898, |
| "learning_rate": 3.975903614457832e-06, |
| "loss": 1.5387580871582032, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.040160642570281124, |
| "eval_loss": 1.5256246328353882, |
| "eval_runtime": 224.0546, |
| "eval_samples_per_second": 17.09, |
| "eval_steps_per_second": 0.536, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04417670682730924, |
| "grad_norm": 9.940044403076172, |
| "learning_rate": 4.377510040160643e-06, |
| "loss": 1.49784574508667, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.04819277108433735, |
| "grad_norm": 11.362184524536133, |
| "learning_rate": 4.779116465863454e-06, |
| "loss": 1.5389199256896973, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.05220883534136546, |
| "grad_norm": 9.787059783935547, |
| "learning_rate": 5.180722891566266e-06, |
| "loss": 1.4939092636108398, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.05622489959839357, |
| "grad_norm": 9.76535701751709, |
| "learning_rate": 5.582329317269076e-06, |
| "loss": 1.4706912994384767, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.060240963855421686, |
| "grad_norm": 9.557772636413574, |
| "learning_rate": 5.983935742971888e-06, |
| "loss": 1.4295058250427246, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.060240963855421686, |
| "eval_loss": 1.4075552225112915, |
| "eval_runtime": 224.3397, |
| "eval_samples_per_second": 17.068, |
| "eval_steps_per_second": 0.535, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.0642570281124498, |
| "grad_norm": 8.256240844726562, |
| "learning_rate": 6.385542168674699e-06, |
| "loss": 1.3934820175170899, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.06827309236947791, |
| "grad_norm": 10.668194770812988, |
| "learning_rate": 6.78714859437751e-06, |
| "loss": 1.3897838592529297, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.07228915662650602, |
| "grad_norm": 8.989994049072266, |
| "learning_rate": 7.188755020080321e-06, |
| "loss": 1.3797410011291504, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.07630522088353414, |
| "grad_norm": 7.747810363769531, |
| "learning_rate": 7.590361445783133e-06, |
| "loss": 1.3742728233337402, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.08032128514056225, |
| "grad_norm": 7.7544074058532715, |
| "learning_rate": 7.991967871485944e-06, |
| "loss": 1.3565238952636718, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.08032128514056225, |
| "eval_loss": 1.3342411518096924, |
| "eval_runtime": 224.1047, |
| "eval_samples_per_second": 17.086, |
| "eval_steps_per_second": 0.535, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.08433734939759036, |
| "grad_norm": 7.9385085105896, |
| "learning_rate": 8.393574297188756e-06, |
| "loss": 1.3680735588073731, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.08835341365461848, |
| "grad_norm": 7.368689060211182, |
| "learning_rate": 8.795180722891567e-06, |
| "loss": 1.3239299774169921, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.09236947791164658, |
| "grad_norm": 8.16849422454834, |
| "learning_rate": 9.196787148594378e-06, |
| "loss": 1.330996036529541, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.0963855421686747, |
| "grad_norm": 9.847034454345703, |
| "learning_rate": 9.598393574297188e-06, |
| "loss": 1.3019088745117187, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.10040160642570281, |
| "grad_norm": 6.754732131958008, |
| "learning_rate": 1e-05, |
| "loss": 1.283926010131836, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.10040160642570281, |
| "eval_loss": 1.2852883338928223, |
| "eval_runtime": 224.1824, |
| "eval_samples_per_second": 17.08, |
| "eval_steps_per_second": 0.535, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.10441767068273092, |
| "grad_norm": 6.626065254211426, |
| "learning_rate": 9.999508697551502e-06, |
| "loss": 1.2729861259460449, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.10843373493975904, |
| "grad_norm": 6.478898525238037, |
| "learning_rate": 9.998034886757237e-06, |
| "loss": 1.2489843368530273, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.11244979919678715, |
| "grad_norm": 6.022712230682373, |
| "learning_rate": 9.99557885725195e-06, |
| "loss": 1.2988578796386718, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.11646586345381527, |
| "grad_norm": 6.245314598083496, |
| "learning_rate": 9.992141091696967e-06, |
| "loss": 1.2607011795043945, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.12048192771084337, |
| "grad_norm": 6.8380889892578125, |
| "learning_rate": 9.987722265685338e-06, |
| "loss": 1.2081457138061524, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.12048192771084337, |
| "eval_loss": 1.2430709600448608, |
| "eval_runtime": 224.0772, |
| "eval_samples_per_second": 17.088, |
| "eval_steps_per_second": 0.536, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.12449799196787148, |
| "grad_norm": 5.553050518035889, |
| "learning_rate": 9.98232324760908e-06, |
| "loss": 1.2201088905334472, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.1285140562248996, |
| "grad_norm": 5.528981685638428, |
| "learning_rate": 9.975945098488514e-06, |
| "loss": 1.2170144081115724, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.13253012048192772, |
| "grad_norm": 6.345343589782715, |
| "learning_rate": 9.96858907176375e-06, |
| "loss": 1.2358662605285644, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.13654618473895583, |
| "grad_norm": 5.249575138092041, |
| "learning_rate": 9.960256613048367e-06, |
| "loss": 1.2119761466979981, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.14056224899598393, |
| "grad_norm": 4.9837646484375, |
| "learning_rate": 9.950949359845309e-06, |
| "loss": 1.2059650421142578, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.14056224899598393, |
| "eval_loss": 1.2071032524108887, |
| "eval_runtime": 224.1972, |
| "eval_samples_per_second": 17.079, |
| "eval_steps_per_second": 0.535, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.14457831325301204, |
| "grad_norm": 5.1654791831970215, |
| "learning_rate": 9.940669141225097e-06, |
| "loss": 1.1992589950561523, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.14859437751004015, |
| "grad_norm": 6.3491950035095215, |
| "learning_rate": 9.929417977466356e-06, |
| "loss": 1.1967281341552733, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.15261044176706828, |
| "grad_norm": 6.096224308013916, |
| "learning_rate": 9.91719807965881e-06, |
| "loss": 1.184930419921875, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.1566265060240964, |
| "grad_norm": 4.983779430389404, |
| "learning_rate": 9.904011849268744e-06, |
| "loss": 1.195562744140625, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.1606425702811245, |
| "grad_norm": 5.229851722717285, |
| "learning_rate": 9.889861877667071e-06, |
| "loss": 1.1917385101318358, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.1606425702811245, |
| "eval_loss": 1.1810219287872314, |
| "eval_runtime": 224.2238, |
| "eval_samples_per_second": 17.077, |
| "eval_steps_per_second": 0.535, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.1646586345381526, |
| "grad_norm": 4.667690277099609, |
| "learning_rate": 9.874750945620066e-06, |
| "loss": 1.2232494354248047, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.1686746987951807, |
| "grad_norm": 4.562730312347412, |
| "learning_rate": 9.858682022742896e-06, |
| "loss": 1.1690594673156738, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.17269076305220885, |
| "grad_norm": 4.388287544250488, |
| "learning_rate": 9.84165826691602e-06, |
| "loss": 1.1833030700683593, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.17670682730923695, |
| "grad_norm": 4.246683120727539, |
| "learning_rate": 9.82368302366461e-06, |
| "loss": 1.180044174194336, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.18072289156626506, |
| "grad_norm": 6.267792224884033, |
| "learning_rate": 9.804759825501074e-06, |
| "loss": 1.1597715377807618, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.18072289156626506, |
| "eval_loss": 1.1618536710739136, |
| "eval_runtime": 224.0476, |
| "eval_samples_per_second": 17.09, |
| "eval_steps_per_second": 0.536, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.18473895582329317, |
| "grad_norm": 5.484806537628174, |
| "learning_rate": 9.784892391230847e-06, |
| "loss": 1.161270809173584, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.18875502008032127, |
| "grad_norm": 6.800451278686523, |
| "learning_rate": 9.76408462522157e-06, |
| "loss": 1.1662689208984376, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.1927710843373494, |
| "grad_norm": 4.338923931121826, |
| "learning_rate": 9.742340616635799e-06, |
| "loss": 1.1915185928344727, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.19678714859437751, |
| "grad_norm": 4.900355815887451, |
| "learning_rate": 9.719664638627395e-06, |
| "loss": 1.179362964630127, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.20080321285140562, |
| "grad_norm": 13.36780071258545, |
| "learning_rate": 9.69606114750177e-06, |
| "loss": 1.136868953704834, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.20080321285140562, |
| "eval_loss": 1.167843222618103, |
| "eval_runtime": 224.0503, |
| "eval_samples_per_second": 17.09, |
| "eval_steps_per_second": 0.536, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.20481927710843373, |
| "grad_norm": 5.8057098388671875, |
| "learning_rate": 9.671534781840113e-06, |
| "loss": 1.1644049644470216, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.20883534136546184, |
| "grad_norm": 4.812023639678955, |
| "learning_rate": 9.646090361587828e-06, |
| "loss": 1.1246587753295898, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.21285140562248997, |
| "grad_norm": 4.429294109344482, |
| "learning_rate": 9.619732887107299e-06, |
| "loss": 1.1263324737548828, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.21686746987951808, |
| "grad_norm": 4.260849952697754, |
| "learning_rate": 9.592467538195229e-06, |
| "loss": 1.118002223968506, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.22088353413654618, |
| "grad_norm": 4.285832405090332, |
| "learning_rate": 9.56429967306469e-06, |
| "loss": 1.1537700653076173, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.22088353413654618, |
| "eval_loss": 1.1320561170578003, |
| "eval_runtime": 224.168, |
| "eval_samples_per_second": 17.081, |
| "eval_steps_per_second": 0.535, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.2248995983935743, |
| "grad_norm": 5.736870288848877, |
| "learning_rate": 9.535234827292124e-06, |
| "loss": 1.1374141693115234, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.2289156626506024, |
| "grad_norm": 4.176708221435547, |
| "learning_rate": 9.505278712729489e-06, |
| "loss": 1.1468097686767578, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.23293172690763053, |
| "grad_norm": 4.040938854217529, |
| "learning_rate": 9.474437216381756e-06, |
| "loss": 1.132613754272461, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.23694779116465864, |
| "grad_norm": 4.140848159790039, |
| "learning_rate": 9.442716399249995e-06, |
| "loss": 1.1381197929382325, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.24096385542168675, |
| "grad_norm": 3.8142037391662598, |
| "learning_rate": 9.410122495140257e-06, |
| "loss": 1.1367318153381347, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.24096385542168675, |
| "eval_loss": 1.1217604875564575, |
| "eval_runtime": 224.0839, |
| "eval_samples_per_second": 17.087, |
| "eval_steps_per_second": 0.536, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.24497991967871485, |
| "grad_norm": 3.871077299118042, |
| "learning_rate": 9.376661909438496e-06, |
| "loss": 1.1195713043212892, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.24899598393574296, |
| "grad_norm": 5.430377960205078, |
| "learning_rate": 9.342341217851791e-06, |
| "loss": 1.1373143196105957, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.25301204819277107, |
| "grad_norm": 6.021585464477539, |
| "learning_rate": 9.307167165116062e-06, |
| "loss": 1.1249177932739258, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.2570281124497992, |
| "grad_norm": 4.557471752166748, |
| "learning_rate": 9.271146663670605e-06, |
| "loss": 1.1521922111511231, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.26104417670682734, |
| "grad_norm": 3.8892979621887207, |
| "learning_rate": 9.23428679229964e-06, |
| "loss": 1.138702964782715, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.26104417670682734, |
| "eval_loss": 1.1032555103302002, |
| "eval_runtime": 224.1346, |
| "eval_samples_per_second": 17.083, |
| "eval_steps_per_second": 0.535, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.26506024096385544, |
| "grad_norm": 4.048600673675537, |
| "learning_rate": 9.196594794741193e-06, |
| "loss": 1.1215006828308105, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.26907630522088355, |
| "grad_norm": 4.088984966278076, |
| "learning_rate": 9.158078078263536e-06, |
| "loss": 1.1247024536132812, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.27309236947791166, |
| "grad_norm": 6.832698822021484, |
| "learning_rate": 9.118744212209516e-06, |
| "loss": 1.1253211975097657, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.27710843373493976, |
| "grad_norm": 4.244821071624756, |
| "learning_rate": 9.078600926509013e-06, |
| "loss": 1.1232710838317872, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.28112449799196787, |
| "grad_norm": 4.204834938049316, |
| "learning_rate": 9.03765611015985e-06, |
| "loss": 1.1257820129394531, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.28112449799196787, |
| "eval_loss": 1.099267840385437, |
| "eval_runtime": 224.1775, |
| "eval_samples_per_second": 17.08, |
| "eval_steps_per_second": 0.535, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.285140562248996, |
| "grad_norm": 13.570015907287598, |
| "learning_rate": 8.995917809677437e-06, |
| "loss": 1.120689582824707, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.2891566265060241, |
| "grad_norm": 4.013745307922363, |
| "learning_rate": 8.953394227513463e-06, |
| "loss": 1.0989994049072265, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.2931726907630522, |
| "grad_norm": 4.636791229248047, |
| "learning_rate": 8.910093720443945e-06, |
| "loss": 1.0785343170166015, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.2971887550200803, |
| "grad_norm": 5.258622169494629, |
| "learning_rate": 8.866024797926936e-06, |
| "loss": 1.1059405326843261, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.30120481927710846, |
| "grad_norm": 4.196040630340576, |
| "learning_rate": 8.821196120430252e-06, |
| "loss": 1.1153934478759766, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.30120481927710846, |
| "eval_loss": 1.0958428382873535, |
| "eval_runtime": 224.2589, |
| "eval_samples_per_second": 17.074, |
| "eval_steps_per_second": 0.535, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.30522088353413657, |
| "grad_norm": 4.448573589324951, |
| "learning_rate": 8.775616497729502e-06, |
| "loss": 1.1181120872497559, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.3092369477911647, |
| "grad_norm": 5.079808712005615, |
| "learning_rate": 8.729294887176778e-06, |
| "loss": 1.0942277908325195, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.3132530120481928, |
| "grad_norm": 3.968134641647339, |
| "learning_rate": 8.682240391940355e-06, |
| "loss": 1.0744555473327637, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.3172690763052209, |
| "grad_norm": 4.138976573944092, |
| "learning_rate": 8.634462259215719e-06, |
| "loss": 1.1014032363891602, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.321285140562249, |
| "grad_norm": 3.7669668197631836, |
| "learning_rate": 8.58596987840831e-06, |
| "loss": 1.1038568496704102, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.321285140562249, |
| "eval_loss": 1.0854790210723877, |
| "eval_runtime": 224.3132, |
| "eval_samples_per_second": 17.07, |
| "eval_steps_per_second": 0.535, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.3253012048192771, |
| "grad_norm": 3.8699982166290283, |
| "learning_rate": 8.536772779288297e-06, |
| "loss": 1.1016878128051757, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.3293172690763052, |
| "grad_norm": 4.875065326690674, |
| "learning_rate": 8.48688063011778e-06, |
| "loss": 1.0864307403564453, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 3.7264904975891113, |
| "learning_rate": 8.43630323575078e-06, |
| "loss": 1.084289836883545, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.3373493975903614, |
| "grad_norm": 3.7510852813720703, |
| "learning_rate": 8.385050535706376e-06, |
| "loss": 1.1047092437744142, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.3413654618473896, |
| "grad_norm": 3.7756431102752686, |
| "learning_rate": 8.333132602215374e-06, |
| "loss": 1.0681782722473145, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.3413654618473896, |
| "eval_loss": 1.0816028118133545, |
| "eval_runtime": 224.2437, |
| "eval_samples_per_second": 17.075, |
| "eval_steps_per_second": 0.535, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.3453815261044177, |
| "grad_norm": 4.321180820465088, |
| "learning_rate": 8.280559638240914e-06, |
| "loss": 1.076450252532959, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.3493975903614458, |
| "grad_norm": 5.125402927398682, |
| "learning_rate": 8.227341975473368e-06, |
| "loss": 1.1018122673034667, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.3534136546184739, |
| "grad_norm": 4.057586193084717, |
| "learning_rate": 8.17349007229994e-06, |
| "loss": 1.0766830444335938, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.357429718875502, |
| "grad_norm": 3.9465365409851074, |
| "learning_rate": 8.119014511749388e-06, |
| "loss": 1.0568387985229493, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.3614457831325301, |
| "grad_norm": 5.671834468841553, |
| "learning_rate": 8.063925999412224e-06, |
| "loss": 1.064396286010742, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.3614457831325301, |
| "eval_loss": 1.0756299495697021, |
| "eval_runtime": 224.2054, |
| "eval_samples_per_second": 17.078, |
| "eval_steps_per_second": 0.535, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.3654618473895582, |
| "grad_norm": 3.911022901535034, |
| "learning_rate": 8.008235361336845e-06, |
| "loss": 1.1032384872436523, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.36947791164658633, |
| "grad_norm": 3.855924129486084, |
| "learning_rate": 7.951953541901989e-06, |
| "loss": 1.0686886787414551, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.37349397590361444, |
| "grad_norm": 4.947168827056885, |
| "learning_rate": 7.895091601665934e-06, |
| "loss": 1.0647593498229981, |
| "step": 930 |
| }, |
| { |
| "epoch": 0.37751004016064255, |
| "grad_norm": 4.119925022125244, |
| "learning_rate": 7.837660715192867e-06, |
| "loss": 1.0522316932678222, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.3815261044176707, |
| "grad_norm": 3.602022647857666, |
| "learning_rate": 7.779672168856844e-06, |
| "loss": 1.0513050079345703, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.3815261044176707, |
| "eval_loss": 1.0680068731307983, |
| "eval_runtime": 224.3211, |
| "eval_samples_per_second": 17.069, |
| "eval_steps_per_second": 0.535, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.3855421686746988, |
| "grad_norm": 4.18943452835083, |
| "learning_rate": 7.721137358623786e-06, |
| "loss": 1.0850586891174316, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.3895582329317269, |
| "grad_norm": 6.430990219116211, |
| "learning_rate": 7.66206778781193e-06, |
| "loss": 1.0583345413208007, |
| "step": 970 |
| }, |
| { |
| "epoch": 0.39357429718875503, |
| "grad_norm": 4.619312286376953, |
| "learning_rate": 7.6024750648311805e-06, |
| "loss": 1.091839599609375, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.39759036144578314, |
| "grad_norm": 3.8781845569610596, |
| "learning_rate": 7.542370900901827e-06, |
| "loss": 1.0620054244995116, |
| "step": 990 |
| }, |
| { |
| "epoch": 0.40160642570281124, |
| "grad_norm": 3.7595436573028564, |
| "learning_rate": 7.4817671077530295e-06, |
| "loss": 1.0398008346557617, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.40160642570281124, |
| "eval_loss": 1.0621941089630127, |
| "eval_runtime": 224.1744, |
| "eval_samples_per_second": 17.08, |
| "eval_steps_per_second": 0.535, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.40562248995983935, |
| "grad_norm": 3.890206813812256, |
| "learning_rate": 7.420675595301574e-06, |
| "loss": 1.067855453491211, |
| "step": 1010 |
| }, |
| { |
| "epoch": 0.40963855421686746, |
| "grad_norm": 3.8331494331359863, |
| "learning_rate": 7.359108369311318e-06, |
| "loss": 1.0873468399047852, |
| "step": 1020 |
| }, |
| { |
| "epoch": 0.41365461847389556, |
| "grad_norm": 3.785521984100342, |
| "learning_rate": 7.297077529033814e-06, |
| "loss": 1.0355330467224122, |
| "step": 1030 |
| }, |
| { |
| "epoch": 0.41767068273092367, |
| "grad_norm": 6.754027843475342, |
| "learning_rate": 7.234595264830546e-06, |
| "loss": 1.0717147827148437, |
| "step": 1040 |
| }, |
| { |
| "epoch": 0.42168674698795183, |
| "grad_norm": 3.619626045227051, |
| "learning_rate": 7.171673855777271e-06, |
| "loss": 1.0628927230834961, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.42168674698795183, |
| "eval_loss": 1.0565131902694702, |
| "eval_runtime": 224.3026, |
| "eval_samples_per_second": 17.071, |
| "eval_steps_per_second": 0.535, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.42570281124497994, |
| "grad_norm": 3.654301404953003, |
| "learning_rate": 7.10832566725092e-06, |
| "loss": 1.028466033935547, |
| "step": 1060 |
| }, |
| { |
| "epoch": 0.42971887550200805, |
| "grad_norm": 4.81827449798584, |
| "learning_rate": 7.044563148499547e-06, |
| "loss": 1.0777903556823731, |
| "step": 1070 |
| }, |
| { |
| "epoch": 0.43373493975903615, |
| "grad_norm": 4.028594493865967, |
| "learning_rate": 6.980398830195785e-06, |
| "loss": 1.1094385147094727, |
| "step": 1080 |
| }, |
| { |
| "epoch": 0.43775100401606426, |
| "grad_norm": 3.782311201095581, |
| "learning_rate": 6.915845321974309e-06, |
| "loss": 1.0568254470825196, |
| "step": 1090 |
| }, |
| { |
| "epoch": 0.44176706827309237, |
| "grad_norm": 4.213383197784424, |
| "learning_rate": 6.85091530995378e-06, |
| "loss": 1.0806368827819823, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.44176706827309237, |
| "eval_loss": 1.0501891374588013, |
| "eval_runtime": 224.1605, |
| "eval_samples_per_second": 17.082, |
| "eval_steps_per_second": 0.535, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.4457831325301205, |
| "grad_norm": 3.598494529724121, |
| "learning_rate": 6.785621554243752e-06, |
| "loss": 1.0479291915893554, |
| "step": 1110 |
| }, |
| { |
| "epoch": 0.4497991967871486, |
| "grad_norm": 3.8993070125579834, |
| "learning_rate": 6.7199768864370455e-06, |
| "loss": 1.066202163696289, |
| "step": 1120 |
| }, |
| { |
| "epoch": 0.4538152610441767, |
| "grad_norm": 4.1509833335876465, |
| "learning_rate": 6.65399420708807e-06, |
| "loss": 1.0448795318603517, |
| "step": 1130 |
| }, |
| { |
| "epoch": 0.4578313253012048, |
| "grad_norm": 3.5259952545166016, |
| "learning_rate": 6.587686483177596e-06, |
| "loss": 1.049018383026123, |
| "step": 1140 |
| }, |
| { |
| "epoch": 0.46184738955823296, |
| "grad_norm": 3.395838975906372, |
| "learning_rate": 6.521066745564467e-06, |
| "loss": 1.0418387413024903, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.46184738955823296, |
| "eval_loss": 1.0448716878890991, |
| "eval_runtime": 224.2692, |
| "eval_samples_per_second": 17.073, |
| "eval_steps_per_second": 0.535, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.46586345381526106, |
| "grad_norm": 5.678968906402588, |
| "learning_rate": 6.454148086424767e-06, |
| "loss": 1.0376011848449707, |
| "step": 1160 |
| }, |
| { |
| "epoch": 0.46987951807228917, |
| "grad_norm": 4.015078067779541, |
| "learning_rate": 6.38694365667893e-06, |
| "loss": 1.0441588401794433, |
| "step": 1170 |
| }, |
| { |
| "epoch": 0.4738955823293173, |
| "grad_norm": 4.168111324310303, |
| "learning_rate": 6.319466663407309e-06, |
| "loss": 1.0368056297302246, |
| "step": 1180 |
| }, |
| { |
| "epoch": 0.4779116465863454, |
| "grad_norm": 5.260632038116455, |
| "learning_rate": 6.251730367254708e-06, |
| "loss": 1.0322036743164062, |
| "step": 1190 |
| }, |
| { |
| "epoch": 0.4819277108433735, |
| "grad_norm": 3.426922082901001, |
| "learning_rate": 6.1837480798243894e-06, |
| "loss": 1.0827327728271485, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.4819277108433735, |
| "eval_loss": 1.0421009063720703, |
| "eval_runtime": 224.3064, |
| "eval_samples_per_second": 17.07, |
| "eval_steps_per_second": 0.535, |
| "step": 1200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 2490, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.318144766541824e+17, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
