| { | |
| "best_metric": 0.7140275239944458, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-1500", | |
| "epoch": 2.6917900403768504, | |
| "eval_steps": 150, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001794526693584567, | |
| "eval_loss": 0.9548982977867126, | |
| "eval_runtime": 93.9669, | |
| "eval_samples_per_second": 9.993, | |
| "eval_steps_per_second": 1.256, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01794526693584567, | |
| "grad_norm": 3.1223835945129395, | |
| "learning_rate": 6e-06, | |
| "loss": 3.2878, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03589053387169134, | |
| "grad_norm": 2.606353998184204, | |
| "learning_rate": 1.2e-05, | |
| "loss": 3.3004, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05383580080753701, | |
| "grad_norm": 2.548677921295166, | |
| "learning_rate": 1.8e-05, | |
| "loss": 3.6273, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07178106774338268, | |
| "grad_norm": 2.486678123474121, | |
| "learning_rate": 2.4e-05, | |
| "loss": 3.7912, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08972633467922836, | |
| "grad_norm": 10.336651802062988, | |
| "learning_rate": 3e-05, | |
| "loss": 3.7769, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10767160161507403, | |
| "grad_norm": 1.5906541347503662, | |
| "learning_rate": 2.9996479470277262e-05, | |
| "loss": 2.9001, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1256168685509197, | |
| "grad_norm": 1.8941510915756226, | |
| "learning_rate": 2.9985919533659653e-05, | |
| "loss": 2.911, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.14356213548676536, | |
| "grad_norm": 2.1188039779663086, | |
| "learning_rate": 2.9968325147023267e-05, | |
| "loss": 3.3648, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16150740242261102, | |
| "grad_norm": 2.7596967220306396, | |
| "learning_rate": 2.994370456924292e-05, | |
| "loss": 3.2929, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.17945266935845672, | |
| "grad_norm": 9.052000999450684, | |
| "learning_rate": 2.9912069357315394e-05, | |
| "loss": 3.4641, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19739793629430238, | |
| "grad_norm": 1.8610212802886963, | |
| "learning_rate": 2.9873434360934543e-05, | |
| "loss": 2.7594, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.21534320323014805, | |
| "grad_norm": 2.275176763534546, | |
| "learning_rate": 2.9827817715520775e-05, | |
| "loss": 2.8485, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.23328847016599372, | |
| "grad_norm": 2.363050699234009, | |
| "learning_rate": 2.977524083370823e-05, | |
| "loss": 3.1626, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2512337371018394, | |
| "grad_norm": 3.0472464561462402, | |
| "learning_rate": 2.9715728395293587e-05, | |
| "loss": 3.2823, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2691790040376851, | |
| "grad_norm": 9.995095252990723, | |
| "learning_rate": 2.96493083356513e-05, | |
| "loss": 3.2776, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2691790040376851, | |
| "eval_loss": 0.7650104761123657, | |
| "eval_runtime": 95.2502, | |
| "eval_samples_per_second": 9.858, | |
| "eval_steps_per_second": 1.239, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2871242709735307, | |
| "grad_norm": 2.056764841079712, | |
| "learning_rate": 2.9576011832620583e-05, | |
| "loss": 2.7666, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3050695379093764, | |
| "grad_norm": 2.3999085426330566, | |
| "learning_rate": 2.9495873291870436e-05, | |
| "loss": 2.8254, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.32301480484522205, | |
| "grad_norm": 2.938490390777588, | |
| "learning_rate": 2.940893033074948e-05, | |
| "loss": 3.0781, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.34096007178106774, | |
| "grad_norm": 3.2307329177856445, | |
| "learning_rate": 2.9315223760628224e-05, | |
| "loss": 3.2347, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.35890533871691344, | |
| "grad_norm": 10.07883358001709, | |
| "learning_rate": 2.9214797567742036e-05, | |
| "loss": 3.3451, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3768506056527591, | |
| "grad_norm": 2.220188617706299, | |
| "learning_rate": 2.9107698892543862e-05, | |
| "loss": 2.5911, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.39479587258860477, | |
| "grad_norm": 2.3011841773986816, | |
| "learning_rate": 2.8993978007576263e-05, | |
| "loss": 2.6557, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4127411395244504, | |
| "grad_norm": 2.9171500205993652, | |
| "learning_rate": 2.8873688293873336e-05, | |
| "loss": 2.9965, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.4306864064602961, | |
| "grad_norm": 3.5936508178710938, | |
| "learning_rate": 2.874688621590339e-05, | |
| "loss": 3.2309, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4486316733961418, | |
| "grad_norm": 15.465261459350586, | |
| "learning_rate": 2.861363129506436e-05, | |
| "loss": 3.3962, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.46657694033198743, | |
| "grad_norm": 2.3160524368286133, | |
| "learning_rate": 2.847398608174417e-05, | |
| "loss": 2.676, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.4845222072678331, | |
| "grad_norm": 2.586505651473999, | |
| "learning_rate": 2.832801612595937e-05, | |
| "loss": 2.7848, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5024674742036788, | |
| "grad_norm": 3.1157450675964355, | |
| "learning_rate": 2.8175789946585697e-05, | |
| "loss": 2.9969, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5204127411395244, | |
| "grad_norm": 3.554219961166382, | |
| "learning_rate": 2.801737899919502e-05, | |
| "loss": 3.2118, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.5383580080753702, | |
| "grad_norm": 11.838674545288086, | |
| "learning_rate": 2.7852857642513838e-05, | |
| "loss": 3.19, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5383580080753702, | |
| "eval_loss": 0.7424979209899902, | |
| "eval_runtime": 95.2404, | |
| "eval_samples_per_second": 9.859, | |
| "eval_steps_per_second": 1.239, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5563032750112158, | |
| "grad_norm": 2.18560791015625, | |
| "learning_rate": 2.768230310351898e-05, | |
| "loss": 2.5618, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5742485419470614, | |
| "grad_norm": 2.7546699047088623, | |
| "learning_rate": 2.7505795441186953e-05, | |
| "loss": 2.7391, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5921938088829072, | |
| "grad_norm": 3.0346529483795166, | |
| "learning_rate": 2.7323417508913973e-05, | |
| "loss": 2.9975, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6101390758187528, | |
| "grad_norm": 3.5320701599121094, | |
| "learning_rate": 2.7135254915624213e-05, | |
| "loss": 3.2406, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6280843427545985, | |
| "grad_norm": 12.75845718383789, | |
| "learning_rate": 2.6941395985584656e-05, | |
| "loss": 3.3339, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6460296096904441, | |
| "grad_norm": 2.2395637035369873, | |
| "learning_rate": 2.6741931716945336e-05, | |
| "loss": 2.5051, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6639748766262898, | |
| "grad_norm": 2.6890869140625, | |
| "learning_rate": 2.6536955739024436e-05, | |
| "loss": 2.7496, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.6819201435621355, | |
| "grad_norm": 3.151639461517334, | |
| "learning_rate": 2.632656426835831e-05, | |
| "loss": 2.9491, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.6998654104979811, | |
| "grad_norm": 3.9626593589782715, | |
| "learning_rate": 2.6110856063537087e-05, | |
| "loss": 3.2246, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7178106774338269, | |
| "grad_norm": 10.024589538574219, | |
| "learning_rate": 2.5889932378846963e-05, | |
| "loss": 3.2718, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7357559443696725, | |
| "grad_norm": 2.5113890171051025, | |
| "learning_rate": 2.5663896916741064e-05, | |
| "loss": 2.6503, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.7537012113055181, | |
| "grad_norm": 2.9303054809570312, | |
| "learning_rate": 2.543285577916108e-05, | |
| "loss": 2.61, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7716464782413638, | |
| "grad_norm": 3.2211666107177734, | |
| "learning_rate": 2.519691741773262e-05, | |
| "loss": 2.9236, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.7895917451772095, | |
| "grad_norm": 3.8643081188201904, | |
| "learning_rate": 2.495619258285757e-05, | |
| "loss": 3.2966, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8075370121130552, | |
| "grad_norm": 14.004131317138672, | |
| "learning_rate": 2.4710794271727415e-05, | |
| "loss": 3.2105, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.8075370121130552, | |
| "eval_loss": 0.7331081628799438, | |
| "eval_runtime": 95.7979, | |
| "eval_samples_per_second": 9.802, | |
| "eval_steps_per_second": 1.232, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.8254822790489008, | |
| "grad_norm": 2.352147340774536, | |
| "learning_rate": 2.446083767528193e-05, | |
| "loss": 2.6354, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.8434275459847466, | |
| "grad_norm": 2.8068552017211914, | |
| "learning_rate": 2.4206440124138064e-05, | |
| "loss": 2.6626, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.8613728129205922, | |
| "grad_norm": 3.1152584552764893, | |
| "learning_rate": 2.3947721033514517e-05, | |
| "loss": 3.0455, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.8793180798564378, | |
| "grad_norm": 4.005079746246338, | |
| "learning_rate": 2.3684801847177732e-05, | |
| "loss": 3.0879, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.8972633467922836, | |
| "grad_norm": 10.259051322937012, | |
| "learning_rate": 2.341780598043574e-05, | |
| "loss": 3.2745, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9152086137281292, | |
| "grad_norm": 2.6010003089904785, | |
| "learning_rate": 2.3146858762206493e-05, | |
| "loss": 2.5606, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.9331538806639749, | |
| "grad_norm": 2.807999610900879, | |
| "learning_rate": 2.287208737618801e-05, | |
| "loss": 2.7688, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.9510991475998205, | |
| "grad_norm": 3.121795415878296, | |
| "learning_rate": 2.259362080115781e-05, | |
| "loss": 2.8815, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.9690444145356663, | |
| "grad_norm": 3.921652317047119, | |
| "learning_rate": 2.231158975042979e-05, | |
| "loss": 3.1705, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.9869896814715119, | |
| "grad_norm": 14.782620429992676, | |
| "learning_rate": 2.2026126610496852e-05, | |
| "loss": 3.1717, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.0049349484073575, | |
| "grad_norm": 2.647948741912842, | |
| "learning_rate": 2.173736537888819e-05, | |
| "loss": 2.823, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.0228802153432033, | |
| "grad_norm": 2.5824477672576904, | |
| "learning_rate": 2.1445441601270276e-05, | |
| "loss": 2.5629, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.0408254822790488, | |
| "grad_norm": 3.400602340698242, | |
| "learning_rate": 2.115049230782124e-05, | |
| "loss": 2.6957, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.0587707492148946, | |
| "grad_norm": 3.649951219558716, | |
| "learning_rate": 2.085265594890832e-05, | |
| "loss": 2.8003, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.0767160161507403, | |
| "grad_norm": 4.453049182891846, | |
| "learning_rate": 2.055207233009872e-05, | |
| "loss": 3.1671, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.0767160161507403, | |
| "eval_loss": 0.7251887917518616, | |
| "eval_runtime": 95.2302, | |
| "eval_samples_per_second": 9.86, | |
| "eval_steps_per_second": 1.239, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.0946612830865858, | |
| "grad_norm": 2.900311231613159, | |
| "learning_rate": 2.0248882546534327e-05, | |
| "loss": 2.769, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.1126065500224316, | |
| "grad_norm": 2.572707176208496, | |
| "learning_rate": 1.9943228916701108e-05, | |
| "loss": 2.4179, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.1305518169582773, | |
| "grad_norm": 3.324117660522461, | |
| "learning_rate": 1.963525491562421e-05, | |
| "loss": 2.7605, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.1484970838941229, | |
| "grad_norm": 3.975733757019043, | |
| "learning_rate": 1.9325105107520264e-05, | |
| "loss": 2.938, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.1664423508299686, | |
| "grad_norm": 4.596153259277344, | |
| "learning_rate": 1.9012925077938318e-05, | |
| "loss": 3.0549, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.1843876177658144, | |
| "grad_norm": 3.047126531600952, | |
| "learning_rate": 1.8698861365421433e-05, | |
| "loss": 2.809, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.2023328847016599, | |
| "grad_norm": 2.942840337753296, | |
| "learning_rate": 1.8383061392720914e-05, | |
| "loss": 2.4638, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.2202781516375056, | |
| "grad_norm": 3.421780824661255, | |
| "learning_rate": 1.8065673397595475e-05, | |
| "loss": 2.698, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.2382234185733512, | |
| "grad_norm": 4.008915424346924, | |
| "learning_rate": 1.7746846363227843e-05, | |
| "loss": 2.8342, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.256168685509197, | |
| "grad_norm": 4.5783371925354, | |
| "learning_rate": 1.7426729948291474e-05, | |
| "loss": 2.9376, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.2741139524450427, | |
| "grad_norm": 3.4261183738708496, | |
| "learning_rate": 1.7105474416700165e-05, | |
| "loss": 2.6337, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.2920592193808882, | |
| "grad_norm": 2.6931464672088623, | |
| "learning_rate": 1.6783230567073597e-05, | |
| "loss": 2.4057, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.310004486316734, | |
| "grad_norm": 3.372232675552368, | |
| "learning_rate": 1.646014966195185e-05, | |
| "loss": 2.6486, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.3279497532525797, | |
| "grad_norm": 3.8511993885040283, | |
| "learning_rate": 1.613638335679216e-05, | |
| "loss": 2.8654, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.3458950201884252, | |
| "grad_norm": 4.8227152824401855, | |
| "learning_rate": 1.5812083628781265e-05, | |
| "loss": 2.9859, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.3458950201884252, | |
| "eval_loss": 0.7222854495048523, | |
| "eval_runtime": 95.2008, | |
| "eval_samples_per_second": 9.863, | |
| "eval_steps_per_second": 1.239, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.363840287124271, | |
| "grad_norm": 3.064589500427246, | |
| "learning_rate": 1.548740270549671e-05, | |
| "loss": 2.6571, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.3817855540601167, | |
| "grad_norm": 3.1526994705200195, | |
| "learning_rate": 1.5162492993450599e-05, | |
| "loss": 2.4803, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.3997308209959622, | |
| "grad_norm": 3.5985524654388428, | |
| "learning_rate": 1.4837507006549403e-05, | |
| "loss": 2.6762, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.417676087931808, | |
| "grad_norm": 3.952852725982666, | |
| "learning_rate": 1.4512597294503295e-05, | |
| "loss": 2.8978, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.4356213548676537, | |
| "grad_norm": 4.69930362701416, | |
| "learning_rate": 1.4187916371218739e-05, | |
| "loss": 3.0415, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.4535666218034993, | |
| "grad_norm": 3.1091654300689697, | |
| "learning_rate": 1.3863616643207844e-05, | |
| "loss": 2.9257, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.471511888739345, | |
| "grad_norm": 2.9218077659606934, | |
| "learning_rate": 1.3539850338048156e-05, | |
| "loss": 2.5462, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.4894571556751908, | |
| "grad_norm": 3.5961787700653076, | |
| "learning_rate": 1.3216769432926405e-05, | |
| "loss": 2.6275, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.5074024226110363, | |
| "grad_norm": 4.310726165771484, | |
| "learning_rate": 1.2894525583299835e-05, | |
| "loss": 2.8565, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.525347689546882, | |
| "grad_norm": 4.69102668762207, | |
| "learning_rate": 1.2573270051708529e-05, | |
| "loss": 2.9611, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.5432929564827278, | |
| "grad_norm": 3.2854912281036377, | |
| "learning_rate": 1.2253153636772158e-05, | |
| "loss": 2.7114, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.5612382234185733, | |
| "grad_norm": 3.1976680755615234, | |
| "learning_rate": 1.193432660240453e-05, | |
| "loss": 2.4224, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.579183490354419, | |
| "grad_norm": 3.6152374744415283, | |
| "learning_rate": 1.1616938607279089e-05, | |
| "loss": 2.6699, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.5971287572902648, | |
| "grad_norm": 4.225895404815674, | |
| "learning_rate": 1.1301138634578571e-05, | |
| "loss": 2.93, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.6150740242261103, | |
| "grad_norm": 5.0000128746032715, | |
| "learning_rate": 1.098707492206169e-05, | |
| "loss": 2.9738, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.6150740242261103, | |
| "eval_loss": 0.7168869376182556, | |
| "eval_runtime": 95.1917, | |
| "eval_samples_per_second": 9.864, | |
| "eval_steps_per_second": 1.24, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.6330192911619559, | |
| "grad_norm": 2.9839413166046143, | |
| "learning_rate": 1.067489489247974e-05, | |
| "loss": 2.7097, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.6509645580978018, | |
| "grad_norm": 2.9765803813934326, | |
| "learning_rate": 1.036474508437579e-05, | |
| "loss": 2.4352, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.6689098250336474, | |
| "grad_norm": 3.5830776691436768, | |
| "learning_rate": 1.0056771083298894e-05, | |
| "loss": 2.6683, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.686855091969493, | |
| "grad_norm": 4.138453960418701, | |
| "learning_rate": 9.751117453465674e-06, | |
| "loss": 2.8063, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.7048003589053389, | |
| "grad_norm": 5.089868545532227, | |
| "learning_rate": 9.447927669901284e-06, | |
| "loss": 3.0384, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.7227456258411844, | |
| "grad_norm": 3.140326499938965, | |
| "learning_rate": 9.147344051091682e-06, | |
| "loss": 2.7848, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.74069089277703, | |
| "grad_norm": 2.8979885578155518, | |
| "learning_rate": 8.849507692178758e-06, | |
| "loss": 2.5351, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.7586361597128757, | |
| "grad_norm": 3.619845390319824, | |
| "learning_rate": 8.554558398729726e-06, | |
| "loss": 2.644, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.7765814266487214, | |
| "grad_norm": 4.086766242980957, | |
| "learning_rate": 8.262634621111819e-06, | |
| "loss": 2.7442, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.794526693584567, | |
| "grad_norm": 5.267161846160889, | |
| "learning_rate": 7.97387338950315e-06, | |
| "loss": 3.0389, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.8124719605204127, | |
| "grad_norm": 3.162679672241211, | |
| "learning_rate": 7.688410249570214e-06, | |
| "loss": 2.7156, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.8304172274562585, | |
| "grad_norm": 3.187302827835083, | |
| "learning_rate": 7.4063791988421905e-06, | |
| "loss": 2.4397, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.848362494392104, | |
| "grad_norm": 3.6598949432373047, | |
| "learning_rate": 7.127912623811993e-06, | |
| "loss": 2.5768, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.8663077613279497, | |
| "grad_norm": 4.343390464782715, | |
| "learning_rate": 6.853141237793507e-06, | |
| "loss": 2.85, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.8842530282637955, | |
| "grad_norm": 5.103370666503906, | |
| "learning_rate": 6.582194019564266e-06, | |
| "loss": 3.0224, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.8842530282637955, | |
| "eval_loss": 0.714248538017273, | |
| "eval_runtime": 95.2398, | |
| "eval_samples_per_second": 9.859, | |
| "eval_steps_per_second": 1.239, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.902198295199641, | |
| "grad_norm": 3.154374122619629, | |
| "learning_rate": 6.315198152822273e-06, | |
| "loss": 2.6001, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.9201435621354868, | |
| "grad_norm": 3.071227788925171, | |
| "learning_rate": 6.052278966485492e-06, | |
| "loss": 2.4724, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.9380888290713325, | |
| "grad_norm": 3.503994941711426, | |
| "learning_rate": 5.793559875861938e-06, | |
| "loss": 2.6831, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.956034096007178, | |
| "grad_norm": 4.184395790100098, | |
| "learning_rate": 5.539162324718075e-06, | |
| "loss": 2.7453, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.9739793629430238, | |
| "grad_norm": 5.539226531982422, | |
| "learning_rate": 5.289205728272587e-06, | |
| "loss": 3.1028, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.9919246298788695, | |
| "grad_norm": 3.3464314937591553, | |
| "learning_rate": 5.043807417142436e-06, | |
| "loss": 2.684, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.009869896814715, | |
| "grad_norm": 2.914656400680542, | |
| "learning_rate": 4.8030825822673816e-06, | |
| "loss": 2.5496, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.0278151637505606, | |
| "grad_norm": 3.4661035537719727, | |
| "learning_rate": 4.567144220838923e-06, | |
| "loss": 2.4933, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.0457604306864066, | |
| "grad_norm": 3.822174549102783, | |
| "learning_rate": 4.336103083258942e-06, | |
| "loss": 2.6796, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.063705697622252, | |
| "grad_norm": 4.563441276550293, | |
| "learning_rate": 4.110067621153041e-06, | |
| "loss": 2.8069, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.0816509645580976, | |
| "grad_norm": 5.503087520599365, | |
| "learning_rate": 3.889143936462915e-06, | |
| "loss": 2.9136, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.0995962314939436, | |
| "grad_norm": 3.0303938388824463, | |
| "learning_rate": 3.673435731641692e-06, | |
| "loss": 2.4711, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.117541498429789, | |
| "grad_norm": 3.6022088527679443, | |
| "learning_rate": 3.4630442609755666e-06, | |
| "loss": 2.2998, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.1354867653656346, | |
| "grad_norm": 4.142797946929932, | |
| "learning_rate": 3.2580682830546667e-06, | |
| "loss": 2.6211, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.1534320323014806, | |
| "grad_norm": 4.368759632110596, | |
| "learning_rate": 3.0586040144153436e-06, | |
| "loss": 2.7689, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.1534320323014806, | |
| "eval_loss": 0.7151356935501099, | |
| "eval_runtime": 95.185, | |
| "eval_samples_per_second": 9.865, | |
| "eval_steps_per_second": 1.24, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.171377299237326, | |
| "grad_norm": 5.972046375274658, | |
| "learning_rate": 2.86474508437579e-06, | |
| "loss": 2.8707, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.1893225661731717, | |
| "grad_norm": 3.227733850479126, | |
| "learning_rate": 2.67658249108603e-06, | |
| "loss": 2.4486, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.2072678331090176, | |
| "grad_norm": 3.5549120903015137, | |
| "learning_rate": 2.4942045588130504e-06, | |
| "loss": 2.3472, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.225213100044863, | |
| "grad_norm": 4.020270347595215, | |
| "learning_rate": 2.317696896481024e-06, | |
| "loss": 2.6453, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.2431583669807087, | |
| "grad_norm": 4.551384925842285, | |
| "learning_rate": 2.1471423574861643e-06, | |
| "loss": 2.777, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.2611036339165547, | |
| "grad_norm": 5.8825812339782715, | |
| "learning_rate": 1.982621000804979e-06, | |
| "loss": 2.8939, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.2790489008524, | |
| "grad_norm": 3.2557361125946045, | |
| "learning_rate": 1.8242100534143065e-06, | |
| "loss": 2.5914, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.2969941677882457, | |
| "grad_norm": 3.4699723720550537, | |
| "learning_rate": 1.6719838740406313e-06, | |
| "loss": 2.3236, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.3149394347240917, | |
| "grad_norm": 4.2601752281188965, | |
| "learning_rate": 1.5260139182558363e-06, | |
| "loss": 2.6321, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.332884701659937, | |
| "grad_norm": 4.615097522735596, | |
| "learning_rate": 1.3863687049356465e-06, | |
| "loss": 2.8052, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.3508299685957827, | |
| "grad_norm": 5.796968936920166, | |
| "learning_rate": 1.25311378409661e-06, | |
| "loss": 2.9489, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.3687752355316287, | |
| "grad_norm": 3.3097987174987793, | |
| "learning_rate": 1.1263117061266677e-06, | |
| "loss": 2.4068, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.3867205024674742, | |
| "grad_norm": 3.570329427719116, | |
| "learning_rate": 1.006021992423738e-06, | |
| "loss": 2.3704, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.4046657694033198, | |
| "grad_norm": 3.7566256523132324, | |
| "learning_rate": 8.923011074561405e-07, | |
| "loss": 2.5744, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.4226110363391653, | |
| "grad_norm": 4.76233434677124, | |
| "learning_rate": 7.852024322579649e-07, | |
| "loss": 2.684, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.4226110363391653, | |
| "eval_loss": 0.714054524898529, | |
| "eval_runtime": 95.2194, | |
| "eval_samples_per_second": 9.861, | |
| "eval_steps_per_second": 1.239, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.4405563032750113, | |
| "grad_norm": 5.729117393493652, | |
| "learning_rate": 6.847762393717782e-07, | |
| "loss": 2.9529, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.458501570210857, | |
| "grad_norm": 3.2370126247406006, | |
| "learning_rate": 5.910696692505202e-07, | |
| "loss": 2.3974, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.4764468371467023, | |
| "grad_norm": 3.672769546508789, | |
| "learning_rate": 5.041267081295648e-07, | |
| "loss": 2.4916, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.4943921040825483, | |
| "grad_norm": 3.912321090698242, | |
| "learning_rate": 4.239881673794166e-07, | |
| "loss": 2.6173, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.512337371018394, | |
| "grad_norm": 4.756332874298096, | |
| "learning_rate": 3.5069166434870014e-07, | |
| "loss": 2.8032, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.5302826379542394, | |
| "grad_norm": 5.58614444732666, | |
| "learning_rate": 2.8427160470641255e-07, | |
| "loss": 2.931, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.5482279048900853, | |
| "grad_norm": 3.3309953212738037, | |
| "learning_rate": 2.2475916629177418e-07, | |
| "loss": 2.5066, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.566173171825931, | |
| "grad_norm": 3.625159502029419, | |
| "learning_rate": 1.7218228447922869e-07, | |
| "loss": 2.3303, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.5841184387617764, | |
| "grad_norm": 4.057403087615967, | |
| "learning_rate": 1.2656563906545903e-07, | |
| "loss": 2.6747, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.6020637056976224, | |
| "grad_norm": 4.8578877449035645, | |
| "learning_rate": 8.793064268460605e-08, | |
| "loss": 2.7823, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.620008972633468, | |
| "grad_norm": 5.646084308624268, | |
| "learning_rate": 5.629543075708177e-08, | |
| "loss": 2.9719, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.6379542395693134, | |
| "grad_norm": 3.3096609115600586, | |
| "learning_rate": 3.1674852976734116e-08, | |
| "loss": 2.5002, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.6558995065051594, | |
| "grad_norm": 3.604172706604004, | |
| "learning_rate": 1.4080466340349318e-08, | |
| "loss": 2.3697, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.673844773441005, | |
| "grad_norm": 4.091582298278809, | |
| "learning_rate": 3.520529722738086e-09, | |
| "loss": 2.7008, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 2.6917900403768504, | |
| "grad_norm": 4.5670952796936035, | |
| "learning_rate": 0.0, | |
| "loss": 2.6918, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.6917900403768504, | |
| "eval_loss": 0.7140275239944458, | |
| "eval_runtime": 95.2168, | |
| "eval_samples_per_second": 9.862, | |
| "eval_steps_per_second": 1.239, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.78587342489387e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |