{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 2650, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.007547169811320755, "grad_norm": 7.922053813934326, "learning_rate": 2.375e-06, "loss": 1.8248348236083984, "step": 20 }, { "epoch": 0.01509433962264151, "grad_norm": 5.153849124908447, "learning_rate": 4.875e-06, "loss": 0.6734922409057618, "step": 40 }, { "epoch": 0.022641509433962263, "grad_norm": 3.8417952060699463, "learning_rate": 7.375000000000001e-06, "loss": 0.5169679641723632, "step": 60 }, { "epoch": 0.03018867924528302, "grad_norm": 3.793087959289551, "learning_rate": 9.875000000000001e-06, "loss": 0.4708976745605469, "step": 80 }, { "epoch": 0.03773584905660377, "grad_norm": 3.9918274879455566, "learning_rate": 9.926070038910508e-06, "loss": 0.43471393585205076, "step": 100 }, { "epoch": 0.045283018867924525, "grad_norm": 3.1711807250976562, "learning_rate": 9.848249027237355e-06, "loss": 0.4106579780578613, "step": 120 }, { "epoch": 0.052830188679245285, "grad_norm": 3.4092154502868652, "learning_rate": 9.770428015564202e-06, "loss": 0.411483097076416, "step": 140 }, { "epoch": 0.06037735849056604, "grad_norm": 4.140798091888428, "learning_rate": 9.692607003891051e-06, "loss": 0.3940101385116577, "step": 160 }, { "epoch": 0.06792452830188679, "grad_norm": 4.656075477600098, "learning_rate": 9.6147859922179e-06, "loss": 0.3798619508743286, "step": 180 }, { "epoch": 0.07547169811320754, "grad_norm": 2.7356936931610107, "learning_rate": 9.536964980544749e-06, "loss": 0.3780041217803955, "step": 200 }, { "epoch": 0.0830188679245283, "grad_norm": 3.251404047012329, "learning_rate": 9.459143968871596e-06, "loss": 0.36748580932617186, "step": 220 }, { "epoch": 0.09056603773584905, "grad_norm": 2.721688985824585, "learning_rate": 9.381322957198445e-06, "loss": 0.3557413101196289, "step": 240 }, { "epoch": 0.09811320754716982, "grad_norm": 2.4974722862243652, "learning_rate": 9.303501945525292e-06, "loss": 0.35045387744903567, "step": 260 }, { "epoch": 0.10566037735849057, "grad_norm": 2.7542245388031006, "learning_rate": 9.225680933852141e-06, "loss": 0.35384550094604494, "step": 280 }, { "epoch": 0.11320754716981132, "grad_norm": 2.470933198928833, "learning_rate": 9.147859922178988e-06, "loss": 0.3364060401916504, "step": 300 }, { "epoch": 0.12075471698113208, "grad_norm": 2.8506674766540527, "learning_rate": 9.070038910505837e-06, "loss": 0.3362654447555542, "step": 320 }, { "epoch": 0.12830188679245283, "grad_norm": 2.5302703380584717, "learning_rate": 8.992217898832686e-06, "loss": 0.34477815628051756, "step": 340 }, { "epoch": 0.13584905660377358, "grad_norm": 2.3338325023651123, "learning_rate": 8.914396887159534e-06, "loss": 0.3253765344619751, "step": 360 }, { "epoch": 0.14339622641509434, "grad_norm": 2.568937063217163, "learning_rate": 8.836575875486382e-06, "loss": 0.32848970890045165, "step": 380 }, { "epoch": 0.1509433962264151, "grad_norm": 2.6640806198120117, "learning_rate": 8.75875486381323e-06, "loss": 0.3335243225097656, "step": 400 }, { "epoch": 0.15849056603773584, "grad_norm": 2.161710739135742, "learning_rate": 8.680933852140079e-06, "loss": 0.3209374904632568, "step": 420 }, { "epoch": 0.1660377358490566, "grad_norm": 2.3085546493530273, "learning_rate": 8.603112840466928e-06, "loss": 0.3228137731552124, "step": 440 }, { "epoch": 0.17358490566037735, "grad_norm": 2.085447311401367, "learning_rate": 8.525291828793775e-06, "loss": 0.3119216442108154, "step": 460 }, { "epoch": 0.1811320754716981, "grad_norm": 2.1247284412384033, "learning_rate": 8.447470817120624e-06, "loss": 0.3141767978668213, "step": 480 }, { "epoch": 0.18867924528301888, "grad_norm": 2.1246283054351807, "learning_rate": 8.369649805447471e-06, "loss": 0.30214409828186034, "step": 500 }, { "epoch": 0.19622641509433963, "grad_norm": 2.225684404373169, "learning_rate": 8.29182879377432e-06, "loss": 0.30387005805969236, "step": 520 }, { "epoch": 0.2037735849056604, "grad_norm": 2.148167133331299, "learning_rate": 8.214007782101167e-06, "loss": 0.3209031581878662, "step": 540 }, { "epoch": 0.21132075471698114, "grad_norm": 2.277839183807373, "learning_rate": 8.136186770428016e-06, "loss": 0.3025035858154297, "step": 560 }, { "epoch": 0.2188679245283019, "grad_norm": 1.9702632427215576, "learning_rate": 8.058365758754865e-06, "loss": 0.299355149269104, "step": 580 }, { "epoch": 0.22641509433962265, "grad_norm": 2.0844931602478027, "learning_rate": 7.980544747081714e-06, "loss": 0.2990063190460205, "step": 600 }, { "epoch": 0.2339622641509434, "grad_norm": 10.21272087097168, "learning_rate": 7.902723735408561e-06, "loss": 0.30253939628601073, "step": 620 }, { "epoch": 0.24150943396226415, "grad_norm": 2.1862919330596924, "learning_rate": 7.824902723735408e-06, "loss": 0.29045863151550294, "step": 640 }, { "epoch": 0.2490566037735849, "grad_norm": 2.0183300971984863, "learning_rate": 7.747081712062257e-06, "loss": 0.28220953941345217, "step": 660 }, { "epoch": 0.25660377358490566, "grad_norm": 1.9929158687591553, "learning_rate": 7.669260700389106e-06, "loss": 0.2910369634628296, "step": 680 }, { "epoch": 0.2641509433962264, "grad_norm": 1.95077383518219, "learning_rate": 7.591439688715954e-06, "loss": 0.27954850196838377, "step": 700 }, { "epoch": 0.27169811320754716, "grad_norm": 2.134514331817627, "learning_rate": 7.5136186770428025e-06, "loss": 0.2933449029922485, "step": 720 }, { "epoch": 0.2792452830188679, "grad_norm": 1.9829133749008179, "learning_rate": 7.435797665369651e-06, "loss": 0.2858113288879395, "step": 740 }, { "epoch": 0.28679245283018867, "grad_norm": 2.0804476737976074, "learning_rate": 7.3579766536964995e-06, "loss": 0.28907027244567873, "step": 760 }, { "epoch": 0.2943396226415094, "grad_norm": 2.0997867584228516, "learning_rate": 7.280155642023347e-06, "loss": 0.2818809986114502, "step": 780 }, { "epoch": 0.3018867924528302, "grad_norm": 1.939746379852295, "learning_rate": 7.202334630350195e-06, "loss": 0.2713855504989624, "step": 800 }, { "epoch": 0.30943396226415093, "grad_norm": 2.090715169906616, "learning_rate": 7.124513618677044e-06, "loss": 0.2677800178527832, "step": 820 }, { "epoch": 0.3169811320754717, "grad_norm": 1.9296588897705078, "learning_rate": 7.046692607003892e-06, "loss": 0.28144216537475586, "step": 840 }, { "epoch": 0.32452830188679244, "grad_norm": 2.0338714122772217, "learning_rate": 6.968871595330739e-06, "loss": 0.2774395704269409, "step": 860 }, { "epoch": 0.3320754716981132, "grad_norm": 1.9666343927383423, "learning_rate": 6.891050583657588e-06, "loss": 0.27606821060180664, "step": 880 }, { "epoch": 0.33962264150943394, "grad_norm": 1.9925788640975952, "learning_rate": 6.813229571984436e-06, "loss": 0.275797176361084, "step": 900 }, { "epoch": 0.3471698113207547, "grad_norm": 2.0370540618896484, "learning_rate": 6.735408560311285e-06, "loss": 0.2696055889129639, "step": 920 }, { "epoch": 0.35471698113207545, "grad_norm": 2.0988776683807373, "learning_rate": 6.657587548638132e-06, "loss": 0.27061948776245115, "step": 940 }, { "epoch": 0.3622641509433962, "grad_norm": 1.913673758506775, "learning_rate": 6.579766536964981e-06, "loss": 0.26864800453186033, "step": 960 }, { "epoch": 0.36981132075471695, "grad_norm": 2.0519678592681885, "learning_rate": 6.501945525291829e-06, "loss": 0.2707942485809326, "step": 980 }, { "epoch": 0.37735849056603776, "grad_norm": 2.009523630142212, "learning_rate": 6.424124513618678e-06, "loss": 0.26637091636657717, "step": 1000 }, { "epoch": 0.3849056603773585, "grad_norm": 2.027585744857788, "learning_rate": 6.3463035019455255e-06, "loss": 0.27300190925598145, "step": 1020 }, { "epoch": 0.39245283018867927, "grad_norm": 2.1356987953186035, "learning_rate": 6.268482490272374e-06, "loss": 0.25133261680603025, "step": 1040 }, { "epoch": 0.4, "grad_norm": 1.9232840538024902, "learning_rate": 6.1906614785992225e-06, "loss": 0.2677877902984619, "step": 1060 }, { "epoch": 0.4075471698113208, "grad_norm": 1.9696307182312012, "learning_rate": 6.112840466926071e-06, "loss": 0.262535548210144, "step": 1080 }, { "epoch": 0.41509433962264153, "grad_norm": 3.308540105819702, "learning_rate": 6.035019455252919e-06, "loss": 0.2604930877685547, "step": 1100 }, { "epoch": 0.4226415094339623, "grad_norm": 1.807235598564148, "learning_rate": 5.957198443579767e-06, "loss": 0.25956134796142577, "step": 1120 }, { "epoch": 0.43018867924528303, "grad_norm": 2.0320322513580322, "learning_rate": 5.879377431906616e-06, "loss": 0.25913519859313966, "step": 1140 }, { "epoch": 0.4377358490566038, "grad_norm": 1.792377233505249, "learning_rate": 5.801556420233464e-06, "loss": 0.2620145082473755, "step": 1160 }, { "epoch": 0.44528301886792454, "grad_norm": 1.7742111682891846, "learning_rate": 5.723735408560311e-06, "loss": 0.2565300464630127, "step": 1180 }, { "epoch": 0.4528301886792453, "grad_norm": 2.2132532596588135, "learning_rate": 5.64591439688716e-06, "loss": 0.2499943733215332, "step": 1200 }, { "epoch": 0.46037735849056605, "grad_norm": 1.8191214799880981, "learning_rate": 5.568093385214008e-06, "loss": 0.2629887580871582, "step": 1220 }, { "epoch": 0.4679245283018868, "grad_norm": 1.9858105182647705, "learning_rate": 5.490272373540857e-06, "loss": 0.25370690822601316, "step": 1240 }, { "epoch": 0.47547169811320755, "grad_norm": 1.8735243082046509, "learning_rate": 5.412451361867704e-06, "loss": 0.25052781105041505, "step": 1260 }, { "epoch": 0.4830188679245283, "grad_norm": 1.7910277843475342, "learning_rate": 5.334630350194553e-06, "loss": 0.247009015083313, "step": 1280 }, { "epoch": 0.49056603773584906, "grad_norm": 2.0567827224731445, "learning_rate": 5.256809338521401e-06, "loss": 0.25177478790283203, "step": 1300 }, { "epoch": 0.4981132075471698, "grad_norm": 1.9032378196716309, "learning_rate": 5.17898832684825e-06, "loss": 0.24506909847259523, "step": 1320 }, { "epoch": 0.5056603773584906, "grad_norm": 1.8115262985229492, "learning_rate": 5.1011673151750975e-06, "loss": 0.23898508548736572, "step": 1340 }, { "epoch": 0.5132075471698113, "grad_norm": 1.92007577419281, "learning_rate": 5.0233463035019456e-06, "loss": 0.24777793884277344, "step": 1360 }, { "epoch": 0.5207547169811321, "grad_norm": 1.852982997894287, "learning_rate": 4.9455252918287945e-06, "loss": 0.24950757026672363, "step": 1380 }, { "epoch": 0.5283018867924528, "grad_norm": 1.9790362119674683, "learning_rate": 4.867704280155643e-06, "loss": 0.2506132125854492, "step": 1400 }, { "epoch": 0.5358490566037736, "grad_norm": 1.8807333707809448, "learning_rate": 4.789883268482491e-06, "loss": 0.24446616172790528, "step": 1420 }, { "epoch": 0.5433962264150943, "grad_norm": 1.773928165435791, "learning_rate": 4.712062256809339e-06, "loss": 0.2381265640258789, "step": 1440 }, { "epoch": 0.5509433962264151, "grad_norm": 1.6719039678573608, "learning_rate": 4.634241245136188e-06, "loss": 0.2442981481552124, "step": 1460 }, { "epoch": 0.5584905660377358, "grad_norm": 1.6074082851409912, "learning_rate": 4.556420233463035e-06, "loss": 0.24172849655151368, "step": 1480 }, { "epoch": 0.5660377358490566, "grad_norm": 1.7541853189468384, "learning_rate": 4.478599221789884e-06, "loss": 0.24859914779663086, "step": 1500 }, { "epoch": 0.5735849056603773, "grad_norm": 1.702559232711792, "learning_rate": 4.400778210116732e-06, "loss": 0.24974732398986815, "step": 1520 }, { "epoch": 0.5811320754716981, "grad_norm": 2.430460214614868, "learning_rate": 4.32295719844358e-06, "loss": 0.23788890838623047, "step": 1540 }, { "epoch": 0.5886792452830188, "grad_norm": 1.9964704513549805, "learning_rate": 4.245136186770428e-06, "loss": 0.23923373222351074, "step": 1560 }, { "epoch": 0.5962264150943396, "grad_norm": 1.747754693031311, "learning_rate": 4.167315175097277e-06, "loss": 0.23931074142456055, "step": 1580 }, { "epoch": 0.6037735849056604, "grad_norm": 1.7062419652938843, "learning_rate": 4.089494163424125e-06, "loss": 0.23383207321166993, "step": 1600 }, { "epoch": 0.6113207547169811, "grad_norm": 1.958640694618225, "learning_rate": 4.011673151750973e-06, "loss": 0.23437187671661378, "step": 1620 }, { "epoch": 0.6188679245283019, "grad_norm": 1.7894558906555176, "learning_rate": 3.933852140077821e-06, "loss": 0.23447709083557128, "step": 1640 }, { "epoch": 0.6264150943396226, "grad_norm": 1.9197921752929688, "learning_rate": 3.856031128404669e-06, "loss": 0.23741297721862792, "step": 1660 }, { "epoch": 0.6339622641509434, "grad_norm": 1.841734528541565, "learning_rate": 3.778210116731518e-06, "loss": 0.22903223037719728, "step": 1680 }, { "epoch": 0.6415094339622641, "grad_norm": 1.8733159303665161, "learning_rate": 3.7003891050583664e-06, "loss": 0.22988452911376953, "step": 1700 }, { "epoch": 0.6490566037735849, "grad_norm": 1.8593769073486328, "learning_rate": 3.622568093385214e-06, "loss": 0.233162260055542, "step": 1720 }, { "epoch": 0.6566037735849056, "grad_norm": 1.8954672813415527, "learning_rate": 3.5447470817120626e-06, "loss": 0.23007631301879883, "step": 1740 }, { "epoch": 0.6641509433962264, "grad_norm": 1.8158949613571167, "learning_rate": 3.4669260700389107e-06, "loss": 0.23783206939697266, "step": 1760 }, { "epoch": 0.6716981132075471, "grad_norm": 1.9630464315414429, "learning_rate": 3.3891050583657592e-06, "loss": 0.2346041202545166, "step": 1780 }, { "epoch": 0.6792452830188679, "grad_norm": 1.8396250009536743, "learning_rate": 3.3112840466926073e-06, "loss": 0.2288437604904175, "step": 1800 }, { "epoch": 0.6867924528301886, "grad_norm": 1.8676159381866455, "learning_rate": 3.233463035019456e-06, "loss": 0.22720675468444823, "step": 1820 }, { "epoch": 0.6943396226415094, "grad_norm": 1.7294853925704956, "learning_rate": 3.1556420233463035e-06, "loss": 0.2240175724029541, "step": 1840 }, { "epoch": 0.7018867924528301, "grad_norm": 1.8579432964324951, "learning_rate": 3.077821011673152e-06, "loss": 0.22297582626342774, "step": 1860 }, { "epoch": 0.7094339622641509, "grad_norm": 1.86405348777771, "learning_rate": 3e-06, "loss": 0.2258000373840332, "step": 1880 }, { "epoch": 0.7169811320754716, "grad_norm": 1.755361557006836, "learning_rate": 2.9221789883268486e-06, "loss": 0.2202610969543457, "step": 1900 }, { "epoch": 0.7245283018867924, "grad_norm": 1.8296207189559937, "learning_rate": 2.8443579766536967e-06, "loss": 0.22372243404388428, "step": 1920 }, { "epoch": 0.7320754716981132, "grad_norm": 1.726853609085083, "learning_rate": 2.766536964980545e-06, "loss": 0.22018518447875976, "step": 1940 }, { "epoch": 0.7396226415094339, "grad_norm": 1.9359346628189087, "learning_rate": 2.6887159533073933e-06, "loss": 0.22411293983459474, "step": 1960 }, { "epoch": 0.7471698113207547, "grad_norm": 1.8528519868850708, "learning_rate": 2.6108949416342418e-06, "loss": 0.2165390968322754, "step": 1980 }, { "epoch": 0.7547169811320755, "grad_norm": 1.7549021244049072, "learning_rate": 2.5330739299610894e-06, "loss": 0.21932737827301024, "step": 2000 }, { "epoch": 0.7622641509433963, "grad_norm": 1.9458928108215332, "learning_rate": 2.455252918287938e-06, "loss": 0.2255718231201172, "step": 2020 }, { "epoch": 0.769811320754717, "grad_norm": 1.7982280254364014, "learning_rate": 2.377431906614786e-06, "loss": 0.2131561279296875, "step": 2040 }, { "epoch": 0.7773584905660378, "grad_norm": 1.794995665550232, "learning_rate": 2.299610894941634e-06, "loss": 0.22085707187652587, "step": 2060 }, { "epoch": 0.7849056603773585, "grad_norm": 1.803848385810852, "learning_rate": 2.2217898832684826e-06, "loss": 0.20900359153747558, "step": 2080 }, { "epoch": 0.7924528301886793, "grad_norm": 1.9293980598449707, "learning_rate": 2.1439688715953307e-06, "loss": 0.22536056041717528, "step": 2100 }, { "epoch": 0.8, "grad_norm": 1.8656538724899292, "learning_rate": 2.066147859922179e-06, "loss": 0.22233381271362304, "step": 2120 }, { "epoch": 0.8075471698113208, "grad_norm": 1.8052153587341309, "learning_rate": 1.9883268482490273e-06, "loss": 0.21751875877380372, "step": 2140 }, { "epoch": 0.8150943396226416, "grad_norm": 1.7923195362091064, "learning_rate": 1.9105058365758754e-06, "loss": 0.20799951553344725, "step": 2160 }, { "epoch": 0.8226415094339623, "grad_norm": 1.9934825897216797, "learning_rate": 1.8326848249027237e-06, "loss": 0.21072156429290773, "step": 2180 }, { "epoch": 0.8301886792452831, "grad_norm": 1.8735110759735107, "learning_rate": 1.754863813229572e-06, "loss": 0.225791072845459, "step": 2200 }, { "epoch": 0.8377358490566038, "grad_norm": 1.871875524520874, "learning_rate": 1.6770428015564203e-06, "loss": 0.21400871276855468, "step": 2220 }, { "epoch": 0.8452830188679246, "grad_norm": 1.738368034362793, "learning_rate": 1.5992217898832684e-06, "loss": 0.21053862571716309, "step": 2240 }, { "epoch": 0.8528301886792453, "grad_norm": 1.7728012800216675, "learning_rate": 1.5214007782101167e-06, "loss": 0.21779375076293944, "step": 2260 }, { "epoch": 0.8603773584905661, "grad_norm": 1.738864541053772, "learning_rate": 1.443579766536965e-06, "loss": 0.20868196487426757, "step": 2280 }, { "epoch": 0.8679245283018868, "grad_norm": 1.9120129346847534, "learning_rate": 1.3657587548638133e-06, "loss": 0.21061148643493652, "step": 2300 }, { "epoch": 0.8754716981132076, "grad_norm": 1.9350236654281616, "learning_rate": 1.2879377431906614e-06, "loss": 0.21225929260253906, "step": 2320 }, { "epoch": 0.8830188679245283, "grad_norm": 1.892602562904358, "learning_rate": 1.21011673151751e-06, "loss": 0.20428075790405273, "step": 2340 }, { "epoch": 0.8905660377358491, "grad_norm": 1.8391169309616089, "learning_rate": 1.132295719844358e-06, "loss": 0.2088621139526367, "step": 2360 }, { "epoch": 0.8981132075471698, "grad_norm": 1.9468032121658325, "learning_rate": 1.0544747081712063e-06, "loss": 0.21002464294433593, "step": 2380 }, { "epoch": 0.9056603773584906, "grad_norm": 1.882021427154541, "learning_rate": 9.766536964980546e-07, "loss": 0.2088623523712158, "step": 2400 }, { "epoch": 0.9132075471698113, "grad_norm": 1.8219983577728271, "learning_rate": 8.988326848249028e-07, "loss": 0.20324172973632812, "step": 2420 }, { "epoch": 0.9207547169811321, "grad_norm": 1.904112458229065, "learning_rate": 8.210116731517511e-07, "loss": 0.20800838470458985, "step": 2440 }, { "epoch": 0.9283018867924528, "grad_norm": 2.022062063217163, "learning_rate": 7.431906614785993e-07, "loss": 0.21059012413024902, "step": 2460 }, { "epoch": 0.9358490566037736, "grad_norm": 1.927156925201416, "learning_rate": 6.653696498054475e-07, "loss": 0.20443344116210938, "step": 2480 }, { "epoch": 0.9433962264150944, "grad_norm": 1.8873121738433838, "learning_rate": 5.875486381322958e-07, "loss": 0.195121169090271, "step": 2500 }, { "epoch": 0.9509433962264151, "grad_norm": 1.753610610961914, "learning_rate": 5.09727626459144e-07, "loss": 0.20539617538452148, "step": 2520 }, { "epoch": 0.9584905660377359, "grad_norm": 1.7441673278808594, "learning_rate": 4.3190661478599227e-07, "loss": 0.20626044273376465, "step": 2540 }, { "epoch": 0.9660377358490566, "grad_norm": 1.9658927917480469, "learning_rate": 3.540856031128405e-07, "loss": 0.20578131675720215, "step": 2560 }, { "epoch": 0.9735849056603774, "grad_norm": 1.7400754690170288, "learning_rate": 2.762645914396887e-07, "loss": 0.20108022689819335, "step": 2580 }, { "epoch": 0.9811320754716981, "grad_norm": 1.9365240335464478, "learning_rate": 1.9844357976653698e-07, "loss": 0.20257859230041503, "step": 2600 }, { "epoch": 0.9886792452830189, "grad_norm": 1.653227686882019, "learning_rate": 1.2062256809338523e-07, "loss": 0.20295586585998535, "step": 2620 }, { "epoch": 0.9962264150943396, "grad_norm": 1.7939817905426025, "learning_rate": 4.280155642023347e-08, "loss": 0.19921188354492186, "step": 2640 } ], "logging_steps": 20, "max_steps": 2650, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 98959016394752.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }