{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "eval_steps": 500, "global_step": 113710, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.04397150646381145, "grad_norm": 7.127589225769043, "learning_rate": 9.956028493536189e-06, "loss": 0.6405, "step": 500 }, { "epoch": 0.0879430129276229, "grad_norm": 10.408858299255371, "learning_rate": 9.912056987072378e-06, "loss": 0.4966, "step": 1000 }, { "epoch": 0.13191451939143434, "grad_norm": 8.54762077331543, "learning_rate": 9.868085480608566e-06, "loss": 0.4625, "step": 1500 }, { "epoch": 0.1758860258552458, "grad_norm": 8.460881233215332, "learning_rate": 9.824113974144756e-06, "loss": 0.4435, "step": 2000 }, { "epoch": 0.21985753231905725, "grad_norm": 6.150853633880615, "learning_rate": 9.780142467680944e-06, "loss": 0.4288, "step": 2500 }, { "epoch": 0.2638290387828687, "grad_norm": 7.34383487701416, "learning_rate": 9.736170961217132e-06, "loss": 0.4045, "step": 3000 }, { "epoch": 0.30780054524668016, "grad_norm": 10.842817306518555, "learning_rate": 9.69219945475332e-06, "loss": 0.4014, "step": 3500 }, { "epoch": 0.3517720517104916, "grad_norm": 11.085785865783691, "learning_rate": 9.64822794828951e-06, "loss": 0.4087, "step": 4000 }, { "epoch": 0.39574355817430307, "grad_norm": 10.106760025024414, "learning_rate": 9.604256441825697e-06, "loss": 0.391, "step": 4500 }, { "epoch": 0.4397150646381145, "grad_norm": 12.384110450744629, "learning_rate": 9.560284935361887e-06, "loss": 0.3846, "step": 5000 }, { "epoch": 0.483686571101926, "grad_norm": 6.796555519104004, "learning_rate": 9.516313428898075e-06, "loss": 0.3803, "step": 5500 }, { "epoch": 0.5276580775657373, "grad_norm": 10.099310874938965, "learning_rate": 9.472341922434265e-06, "loss": 0.3739, "step": 6000 }, { "epoch": 0.5716295840295489, "grad_norm": 8.258896827697754, "learning_rate": 9.428370415970451e-06, "loss": 0.3694, "step": 6500 }, { "epoch": 0.6156010904933603, "grad_norm": 6.4571356773376465, "learning_rate": 9.38439890950664e-06, "loss": 0.3582, "step": 7000 }, { "epoch": 0.6595725969571717, "grad_norm": 10.41157341003418, "learning_rate": 9.340427403042828e-06, "loss": 0.3611, "step": 7500 }, { "epoch": 0.7035441034209832, "grad_norm": 8.555697441101074, "learning_rate": 9.296455896579018e-06, "loss": 0.3491, "step": 8000 }, { "epoch": 0.7475156098847947, "grad_norm": 10.460009574890137, "learning_rate": 9.252484390115206e-06, "loss": 0.3507, "step": 8500 }, { "epoch": 0.7914871163486061, "grad_norm": 9.326970100402832, "learning_rate": 9.208512883651394e-06, "loss": 0.3465, "step": 9000 }, { "epoch": 0.8354586228124176, "grad_norm": 12.12388801574707, "learning_rate": 9.164541377187584e-06, "loss": 0.3419, "step": 9500 }, { "epoch": 0.879430129276229, "grad_norm": 9.742505073547363, "learning_rate": 9.120569870723772e-06, "loss": 0.3492, "step": 10000 }, { "epoch": 0.9234016357400404, "grad_norm": 8.42115306854248, "learning_rate": 9.07659836425996e-06, "loss": 0.3405, "step": 10500 }, { "epoch": 0.967373142203852, "grad_norm": 11.557007789611816, "learning_rate": 9.03262685779615e-06, "loss": 0.3353, "step": 11000 }, { "epoch": 1.0113446486676634, "grad_norm": 6.1636786460876465, "learning_rate": 8.988655351332337e-06, "loss": 0.3218, "step": 11500 }, { "epoch": 1.0553161551314747, "grad_norm": 8.901851654052734, "learning_rate": 8.944683844868525e-06, "loss": 0.2812, "step": 12000 }, { "epoch": 1.0992876615952862, "grad_norm": 8.753206253051758, "learning_rate": 8.900712338404715e-06, "loss": 0.2744, "step": 12500 }, { "epoch": 1.1432591680590978, "grad_norm": 19.687353134155273, "learning_rate": 8.856740831940903e-06, "loss": 0.2716, "step": 13000 }, { "epoch": 1.187230674522909, "grad_norm": 8.538763999938965, "learning_rate": 8.812769325477092e-06, "loss": 0.2731, "step": 13500 }, { "epoch": 1.2312021809867206, "grad_norm": 14.86081314086914, "learning_rate": 8.76879781901328e-06, "loss": 0.2686, "step": 14000 }, { "epoch": 1.2751736874505322, "grad_norm": 8.427505493164062, "learning_rate": 8.72482631254947e-06, "loss": 0.2694, "step": 14500 }, { "epoch": 1.3191451939143435, "grad_norm": 11.6419095993042, "learning_rate": 8.680854806085656e-06, "loss": 0.2666, "step": 15000 }, { "epoch": 1.363116700378155, "grad_norm": 11.019262313842773, "learning_rate": 8.636883299621846e-06, "loss": 0.2738, "step": 15500 }, { "epoch": 1.4070882068419663, "grad_norm": 12.447158813476562, "learning_rate": 8.592911793158034e-06, "loss": 0.2712, "step": 16000 }, { "epoch": 1.4510597133057779, "grad_norm": 13.097723007202148, "learning_rate": 8.548940286694223e-06, "loss": 0.2635, "step": 16500 }, { "epoch": 1.4950312197695892, "grad_norm": 15.15329360961914, "learning_rate": 8.504968780230411e-06, "loss": 0.2662, "step": 17000 }, { "epoch": 1.5390027262334007, "grad_norm": 6.069318771362305, "learning_rate": 8.460997273766601e-06, "loss": 0.2604, "step": 17500 }, { "epoch": 1.5829742326972123, "grad_norm": 13.966374397277832, "learning_rate": 8.417025767302789e-06, "loss": 0.2657, "step": 18000 }, { "epoch": 1.6269457391610236, "grad_norm": 21.772634506225586, "learning_rate": 8.373054260838977e-06, "loss": 0.262, "step": 18500 }, { "epoch": 1.6709172456248351, "grad_norm": 11.764993667602539, "learning_rate": 8.329082754375165e-06, "loss": 0.2721, "step": 19000 }, { "epoch": 1.7148887520886467, "grad_norm": 11.220842361450195, "learning_rate": 8.285111247911354e-06, "loss": 0.2611, "step": 19500 }, { "epoch": 1.758860258552458, "grad_norm": 12.129228591918945, "learning_rate": 8.241139741447542e-06, "loss": 0.2684, "step": 20000 }, { "epoch": 1.8028317650162693, "grad_norm": 13.62337875366211, "learning_rate": 8.19716823498373e-06, "loss": 0.2593, "step": 20500 }, { "epoch": 1.846803271480081, "grad_norm": 9.742755889892578, "learning_rate": 8.15319672851992e-06, "loss": 0.2633, "step": 21000 }, { "epoch": 1.8907747779438924, "grad_norm": 11.295736312866211, "learning_rate": 8.109225222056108e-06, "loss": 0.2652, "step": 21500 }, { "epoch": 1.9347462844077037, "grad_norm": 8.879314422607422, "learning_rate": 8.065253715592298e-06, "loss": 0.2651, "step": 22000 }, { "epoch": 1.9787177908715152, "grad_norm": 9.949023246765137, "learning_rate": 8.021282209128485e-06, "loss": 0.27, "step": 22500 }, { "epoch": 2.0226892973353268, "grad_norm": 4.5543622970581055, "learning_rate": 7.977310702664673e-06, "loss": 0.2283, "step": 23000 }, { "epoch": 2.066660803799138, "grad_norm": 13.172735214233398, "learning_rate": 7.933339196200861e-06, "loss": 0.2061, "step": 23500 }, { "epoch": 2.1106323102629494, "grad_norm": 12.874068260192871, "learning_rate": 7.889367689737051e-06, "loss": 0.2019, "step": 24000 }, { "epoch": 2.154603816726761, "grad_norm": 17.02819061279297, "learning_rate": 7.845396183273239e-06, "loss": 0.2046, "step": 24500 }, { "epoch": 2.1985753231905725, "grad_norm": 15.347699165344238, "learning_rate": 7.801424676809429e-06, "loss": 0.2035, "step": 25000 }, { "epoch": 2.242546829654384, "grad_norm": 15.82715892791748, "learning_rate": 7.757453170345617e-06, "loss": 0.2088, "step": 25500 }, { "epoch": 2.2865183361181955, "grad_norm": 7.533407211303711, "learning_rate": 7.713481663881806e-06, "loss": 0.2063, "step": 26000 }, { "epoch": 2.330489842582007, "grad_norm": 21.629718780517578, "learning_rate": 7.669510157417994e-06, "loss": 0.2115, "step": 26500 }, { "epoch": 2.374461349045818, "grad_norm": 15.344660758972168, "learning_rate": 7.625538650954182e-06, "loss": 0.2008, "step": 27000 }, { "epoch": 2.41843285550963, "grad_norm": 12.559733390808105, "learning_rate": 7.58156714449037e-06, "loss": 0.1939, "step": 27500 }, { "epoch": 2.4624043619734413, "grad_norm": 13.165969848632812, "learning_rate": 7.537595638026559e-06, "loss": 0.2105, "step": 28000 }, { "epoch": 2.5063758684372526, "grad_norm": 12.558066368103027, "learning_rate": 7.493624131562748e-06, "loss": 0.1951, "step": 28500 }, { "epoch": 2.5503473749010643, "grad_norm": 13.841544151306152, "learning_rate": 7.449652625098936e-06, "loss": 0.1997, "step": 29000 }, { "epoch": 2.5943188813648757, "grad_norm": 6.036389350891113, "learning_rate": 7.405681118635125e-06, "loss": 0.2056, "step": 29500 }, { "epoch": 2.638290387828687, "grad_norm": 24.980592727661133, "learning_rate": 7.361709612171314e-06, "loss": 0.2021, "step": 30000 }, { "epoch": 2.6822618942924983, "grad_norm": 3.522369861602783, "learning_rate": 7.317738105707503e-06, "loss": 0.2109, "step": 30500 }, { "epoch": 2.72623340075631, "grad_norm": 1.9453462362289429, "learning_rate": 7.273766599243692e-06, "loss": 0.1934, "step": 31000 }, { "epoch": 2.7702049072201214, "grad_norm": 14.508398056030273, "learning_rate": 7.229795092779879e-06, "loss": 0.2064, "step": 31500 }, { "epoch": 2.8141764136839327, "grad_norm": 11.040177345275879, "learning_rate": 7.1858235863160675e-06, "loss": 0.2016, "step": 32000 }, { "epoch": 2.8581479201477444, "grad_norm": 7.400022506713867, "learning_rate": 7.141852079852256e-06, "loss": 0.2043, "step": 32500 }, { "epoch": 2.9021194266115558, "grad_norm": 5.055144309997559, "learning_rate": 7.097880573388445e-06, "loss": 0.1952, "step": 33000 }, { "epoch": 2.946090933075367, "grad_norm": 10.668570518493652, "learning_rate": 7.053909066924634e-06, "loss": 0.1949, "step": 33500 }, { "epoch": 2.9900624395391784, "grad_norm": 2.9759585857391357, "learning_rate": 7.009937560460822e-06, "loss": 0.1987, "step": 34000 }, { "epoch": 3.03403394600299, "grad_norm": 17.75304412841797, "learning_rate": 6.965966053997011e-06, "loss": 0.1568, "step": 34500 }, { "epoch": 3.0780054524668015, "grad_norm": 30.556795120239258, "learning_rate": 6.921994547533199e-06, "loss": 0.1476, "step": 35000 }, { "epoch": 3.1219769589306128, "grad_norm": 5.082170486450195, "learning_rate": 6.878023041069387e-06, "loss": 0.1513, "step": 35500 }, { "epoch": 3.1659484653944245, "grad_norm": 1.4760559797286987, "learning_rate": 6.834051534605576e-06, "loss": 0.1551, "step": 36000 }, { "epoch": 3.209919971858236, "grad_norm": 2.336458683013916, "learning_rate": 6.790080028141764e-06, "loss": 0.1554, "step": 36500 }, { "epoch": 3.253891478322047, "grad_norm": 23.16608428955078, "learning_rate": 6.746108521677953e-06, "loss": 0.1529, "step": 37000 }, { "epoch": 3.297862984785859, "grad_norm": 10.948084831237793, "learning_rate": 6.702137015214142e-06, "loss": 0.1583, "step": 37500 }, { "epoch": 3.3418344912496702, "grad_norm": 15.917346954345703, "learning_rate": 6.6581655087503305e-06, "loss": 0.167, "step": 38000 }, { "epoch": 3.3858059977134816, "grad_norm": 1.641739845275879, "learning_rate": 6.614194002286519e-06, "loss": 0.1539, "step": 38500 }, { "epoch": 3.4297775041772933, "grad_norm": 0.5845322608947754, "learning_rate": 6.570222495822708e-06, "loss": 0.1576, "step": 39000 }, { "epoch": 3.4737490106411046, "grad_norm": 16.46019744873047, "learning_rate": 6.526250989358895e-06, "loss": 0.1561, "step": 39500 }, { "epoch": 3.517720517104916, "grad_norm": 31.895326614379883, "learning_rate": 6.482279482895084e-06, "loss": 0.1459, "step": 40000 }, { "epoch": 3.5616920235687273, "grad_norm": 3.9819185733795166, "learning_rate": 6.438307976431273e-06, "loss": 0.1623, "step": 40500 }, { "epoch": 3.605663530032539, "grad_norm": 13.1094970703125, "learning_rate": 6.3943364699674615e-06, "loss": 0.1566, "step": 41000 }, { "epoch": 3.6496350364963503, "grad_norm": 6.929986953735352, "learning_rate": 6.35036496350365e-06, "loss": 0.1656, "step": 41500 }, { "epoch": 3.6936065429601617, "grad_norm": 7.520695686340332, "learning_rate": 6.306393457039839e-06, "loss": 0.1599, "step": 42000 }, { "epoch": 3.7375780494239734, "grad_norm": 11.514050483703613, "learning_rate": 6.262421950576028e-06, "loss": 0.1664, "step": 42500 }, { "epoch": 3.7815495558877847, "grad_norm": 1.5625334978103638, "learning_rate": 6.218450444112216e-06, "loss": 0.1603, "step": 43000 }, { "epoch": 3.825521062351596, "grad_norm": 22.2111873626709, "learning_rate": 6.174478937648405e-06, "loss": 0.1645, "step": 43500 }, { "epoch": 3.8694925688154074, "grad_norm": 9.370536804199219, "learning_rate": 6.130507431184593e-06, "loss": 0.153, "step": 44000 }, { "epoch": 3.913464075279219, "grad_norm": 1.3509089946746826, "learning_rate": 6.086535924720781e-06, "loss": 0.1605, "step": 44500 }, { "epoch": 3.9574355817430305, "grad_norm": 1.670966386795044, "learning_rate": 6.04256441825697e-06, "loss": 0.1602, "step": 45000 }, { "epoch": 4.001407088206842, "grad_norm": 22.55781364440918, "learning_rate": 5.998592911793158e-06, "loss": 0.1582, "step": 45500 }, { "epoch": 4.0453785946706535, "grad_norm": 18.12227439880371, "learning_rate": 5.954621405329347e-06, "loss": 0.1256, "step": 46000 }, { "epoch": 4.089350101134465, "grad_norm": 11.872714042663574, "learning_rate": 5.910649898865536e-06, "loss": 0.1241, "step": 46500 }, { "epoch": 4.133321607598276, "grad_norm": 26.38855743408203, "learning_rate": 5.8666783924017245e-06, "loss": 0.1301, "step": 47000 }, { "epoch": 4.1772931140620875, "grad_norm": 25.3267879486084, "learning_rate": 5.822706885937913e-06, "loss": 0.1236, "step": 47500 }, { "epoch": 4.221264620525899, "grad_norm": 27.222675323486328, "learning_rate": 5.7787353794741e-06, "loss": 0.1217, "step": 48000 }, { "epoch": 4.265236126989711, "grad_norm": 53.458518981933594, "learning_rate": 5.734763873010289e-06, "loss": 0.1315, "step": 48500 }, { "epoch": 4.309207633453522, "grad_norm": 27.357641220092773, "learning_rate": 5.690792366546478e-06, "loss": 0.1253, "step": 49000 }, { "epoch": 4.353179139917334, "grad_norm": 18.440649032592773, "learning_rate": 5.646820860082667e-06, "loss": 0.132, "step": 49500 }, { "epoch": 4.397150646381145, "grad_norm": 8.659114837646484, "learning_rate": 5.6028493536188556e-06, "loss": 0.1262, "step": 50000 }, { "epoch": 4.441122152844956, "grad_norm": 22.664106369018555, "learning_rate": 5.558877847155044e-06, "loss": 0.1185, "step": 50500 }, { "epoch": 4.485093659308768, "grad_norm": 2.488041400909424, "learning_rate": 5.514906340691233e-06, "loss": 0.1264, "step": 51000 }, { "epoch": 4.529065165772579, "grad_norm": 35.29222869873047, "learning_rate": 5.470934834227422e-06, "loss": 0.134, "step": 51500 }, { "epoch": 4.573036672236391, "grad_norm": 25.144588470458984, "learning_rate": 5.426963327763609e-06, "loss": 0.1265, "step": 52000 }, { "epoch": 4.617008178700202, "grad_norm": 1.2160580158233643, "learning_rate": 5.382991821299798e-06, "loss": 0.1306, "step": 52500 }, { "epoch": 4.660979685164014, "grad_norm": 22.59756088256836, "learning_rate": 5.339020314835987e-06, "loss": 0.127, "step": 53000 }, { "epoch": 4.704951191627825, "grad_norm": 17.720712661743164, "learning_rate": 5.295048808372175e-06, "loss": 0.1233, "step": 53500 }, { "epoch": 4.748922698091636, "grad_norm": 24.757396697998047, "learning_rate": 5.251077301908364e-06, "loss": 0.135, "step": 54000 }, { "epoch": 4.792894204555449, "grad_norm": 13.89427375793457, "learning_rate": 5.207105795444552e-06, "loss": 0.1232, "step": 54500 }, { "epoch": 4.83686571101926, "grad_norm": 6.014657974243164, "learning_rate": 5.163134288980741e-06, "loss": 0.1322, "step": 55000 }, { "epoch": 4.880837217483071, "grad_norm": 16.53226089477539, "learning_rate": 5.11916278251693e-06, "loss": 0.1254, "step": 55500 }, { "epoch": 4.9248087239468825, "grad_norm": 4.393960952758789, "learning_rate": 5.075191276053118e-06, "loss": 0.1343, "step": 56000 }, { "epoch": 4.968780230410694, "grad_norm": 6.577863693237305, "learning_rate": 5.0312197695893065e-06, "loss": 0.1302, "step": 56500 }, { "epoch": 5.012751736874505, "grad_norm": 0.385308176279068, "learning_rate": 4.987248263125494e-06, "loss": 0.1134, "step": 57000 }, { "epoch": 5.0567232433383165, "grad_norm": 17.352643966674805, "learning_rate": 4.943276756661683e-06, "loss": 0.1024, "step": 57500 }, { "epoch": 5.100694749802129, "grad_norm": 44.88164520263672, "learning_rate": 4.899305250197872e-06, "loss": 0.1095, "step": 58000 }, { "epoch": 5.14466625626594, "grad_norm": 2.88139009475708, "learning_rate": 4.855333743734061e-06, "loss": 0.1022, "step": 58500 }, { "epoch": 5.188637762729751, "grad_norm": 30.369657516479492, "learning_rate": 4.81136223727025e-06, "loss": 0.1029, "step": 59000 }, { "epoch": 5.232609269193563, "grad_norm": 21.04435920715332, "learning_rate": 4.7673907308064375e-06, "loss": 0.0973, "step": 59500 }, { "epoch": 5.276580775657374, "grad_norm": 0.3326770067214966, "learning_rate": 4.723419224342626e-06, "loss": 0.0969, "step": 60000 }, { "epoch": 5.320552282121185, "grad_norm": 26.21080207824707, "learning_rate": 4.679447717878815e-06, "loss": 0.1072, "step": 60500 }, { "epoch": 5.364523788584997, "grad_norm": 66.27179718017578, "learning_rate": 4.635476211415004e-06, "loss": 0.11, "step": 61000 }, { "epoch": 5.408495295048809, "grad_norm": 0.6907067894935608, "learning_rate": 4.591504704951192e-06, "loss": 0.1077, "step": 61500 }, { "epoch": 5.45246680151262, "grad_norm": 18.443483352661133, "learning_rate": 4.547533198487381e-06, "loss": 0.0996, "step": 62000 }, { "epoch": 5.496438307976431, "grad_norm": 30.685518264770508, "learning_rate": 4.5035616920235695e-06, "loss": 0.0937, "step": 62500 }, { "epoch": 5.540409814440243, "grad_norm": 8.975428581237793, "learning_rate": 4.459590185559758e-06, "loss": 0.1074, "step": 63000 }, { "epoch": 5.584381320904054, "grad_norm": 21.28555679321289, "learning_rate": 4.415618679095946e-06, "loss": 0.0958, "step": 63500 }, { "epoch": 5.628352827367865, "grad_norm": 35.58885192871094, "learning_rate": 4.371647172632135e-06, "loss": 0.1072, "step": 64000 }, { "epoch": 5.672324333831677, "grad_norm": 31.6656436920166, "learning_rate": 4.327675666168324e-06, "loss": 0.1075, "step": 64500 }, { "epoch": 5.716295840295489, "grad_norm": 1.064644455909729, "learning_rate": 4.283704159704512e-06, "loss": 0.1069, "step": 65000 }, { "epoch": 5.7602673467593, "grad_norm": 8.807537078857422, "learning_rate": 4.2397326532407005e-06, "loss": 0.1059, "step": 65500 }, { "epoch": 5.8042388532231115, "grad_norm": 6.445720672607422, "learning_rate": 4.1957611467768885e-06, "loss": 0.1046, "step": 66000 }, { "epoch": 5.848210359686923, "grad_norm": 10.035616874694824, "learning_rate": 4.151789640313077e-06, "loss": 0.1061, "step": 66500 }, { "epoch": 5.892181866150734, "grad_norm": 0.3110928535461426, "learning_rate": 4.107818133849266e-06, "loss": 0.1087, "step": 67000 }, { "epoch": 5.9361533726145455, "grad_norm": 1.1699435710906982, "learning_rate": 4.063846627385454e-06, "loss": 0.101, "step": 67500 }, { "epoch": 5.980124879078357, "grad_norm": 4.037410736083984, "learning_rate": 4.019875120921643e-06, "loss": 0.1123, "step": 68000 }, { "epoch": 6.024096385542169, "grad_norm": 17.392499923706055, "learning_rate": 3.975903614457832e-06, "loss": 0.0904, "step": 68500 }, { "epoch": 6.06806789200598, "grad_norm": 2.474785089492798, "learning_rate": 3.93193210799402e-06, "loss": 0.078, "step": 69000 }, { "epoch": 6.112039398469792, "grad_norm": 6.585563659667969, "learning_rate": 3.887960601530208e-06, "loss": 0.0805, "step": 69500 }, { "epoch": 6.156010904933603, "grad_norm": 22.513330459594727, "learning_rate": 3.843989095066397e-06, "loss": 0.0839, "step": 70000 }, { "epoch": 6.199982411397414, "grad_norm": 13.566338539123535, "learning_rate": 3.800017588602586e-06, "loss": 0.0812, "step": 70500 }, { "epoch": 6.2439539178612256, "grad_norm": 0.06740322709083557, "learning_rate": 3.7560460821387747e-06, "loss": 0.085, "step": 71000 }, { "epoch": 6.287925424325038, "grad_norm": 7.70227575302124, "learning_rate": 3.7120745756749626e-06, "loss": 0.0797, "step": 71500 }, { "epoch": 6.331896930788849, "grad_norm": 0.8043323159217834, "learning_rate": 3.6681030692111514e-06, "loss": 0.083, "step": 72000 }, { "epoch": 6.37586843725266, "grad_norm": 0.23601041734218597, "learning_rate": 3.62413156274734e-06, "loss": 0.0881, "step": 72500 }, { "epoch": 6.419839943716472, "grad_norm": 24.715349197387695, "learning_rate": 3.5801600562835286e-06, "loss": 0.0845, "step": 73000 }, { "epoch": 6.463811450180283, "grad_norm": 32.790096282958984, "learning_rate": 3.5361885498197174e-06, "loss": 0.0873, "step": 73500 }, { "epoch": 6.507782956644094, "grad_norm": 0.44961002469062805, "learning_rate": 3.4922170433559053e-06, "loss": 0.0926, "step": 74000 }, { "epoch": 6.5517544631079065, "grad_norm": 30.2086181640625, "learning_rate": 3.448245536892094e-06, "loss": 0.0869, "step": 74500 }, { "epoch": 6.595725969571718, "grad_norm": 21.381420135498047, "learning_rate": 3.404274030428283e-06, "loss": 0.0897, "step": 75000 }, { "epoch": 6.639697476035529, "grad_norm": 9.947957038879395, "learning_rate": 3.3603025239644717e-06, "loss": 0.0862, "step": 75500 }, { "epoch": 6.6836689824993405, "grad_norm": 0.4237179160118103, "learning_rate": 3.3163310175006597e-06, "loss": 0.0839, "step": 76000 }, { "epoch": 6.727640488963152, "grad_norm": 8.52582836151123, "learning_rate": 3.2723595110368485e-06, "loss": 0.0838, "step": 76500 }, { "epoch": 6.771611995426963, "grad_norm": 21.18242073059082, "learning_rate": 3.228388004573037e-06, "loss": 0.0858, "step": 77000 }, { "epoch": 6.815583501890774, "grad_norm": 42.046844482421875, "learning_rate": 3.1844164981092256e-06, "loss": 0.0825, "step": 77500 }, { "epoch": 6.859555008354587, "grad_norm": 3.5966274738311768, "learning_rate": 3.140444991645414e-06, "loss": 0.0873, "step": 78000 }, { "epoch": 6.903526514818398, "grad_norm": 25.500396728515625, "learning_rate": 3.0964734851816024e-06, "loss": 0.0885, "step": 78500 }, { "epoch": 6.947498021282209, "grad_norm": 59.15459442138672, "learning_rate": 3.052501978717791e-06, "loss": 0.0855, "step": 79000 }, { "epoch": 6.991469527746021, "grad_norm": 0.11808668822050095, "learning_rate": 3.00853047225398e-06, "loss": 0.0837, "step": 79500 }, { "epoch": 7.035441034209832, "grad_norm": 0.7973224520683289, "learning_rate": 2.964558965790168e-06, "loss": 0.0648, "step": 80000 }, { "epoch": 7.079412540673643, "grad_norm": 46.84673309326172, "learning_rate": 2.9205874593263567e-06, "loss": 0.0709, "step": 80500 }, { "epoch": 7.1233840471374545, "grad_norm": 0.13476693630218506, "learning_rate": 2.8766159528625455e-06, "loss": 0.0751, "step": 81000 }, { "epoch": 7.167355553601267, "grad_norm": 30.29783821105957, "learning_rate": 2.832644446398734e-06, "loss": 0.0677, "step": 81500 }, { "epoch": 7.211327060065078, "grad_norm": 12.256621360778809, "learning_rate": 2.7886729399349222e-06, "loss": 0.0717, "step": 82000 }, { "epoch": 7.255298566528889, "grad_norm": 18.782052993774414, "learning_rate": 2.744701433471111e-06, "loss": 0.0652, "step": 82500 }, { "epoch": 7.299270072992701, "grad_norm": 4.884202480316162, "learning_rate": 2.7007299270072994e-06, "loss": 0.0702, "step": 83000 }, { "epoch": 7.343241579456512, "grad_norm": 0.8015443682670593, "learning_rate": 2.656758420543488e-06, "loss": 0.0742, "step": 83500 }, { "epoch": 7.387213085920323, "grad_norm": 0.11882288008928299, "learning_rate": 2.6127869140796765e-06, "loss": 0.0677, "step": 84000 }, { "epoch": 7.431184592384135, "grad_norm": 24.17609214782715, "learning_rate": 2.568815407615865e-06, "loss": 0.0693, "step": 84500 }, { "epoch": 7.475156098847947, "grad_norm": 8.958883285522461, "learning_rate": 2.5248439011520537e-06, "loss": 0.0754, "step": 85000 }, { "epoch": 7.519127605311758, "grad_norm": 0.03229560703039169, "learning_rate": 2.480872394688242e-06, "loss": 0.0696, "step": 85500 }, { "epoch": 7.5630991117755695, "grad_norm": 26.437501907348633, "learning_rate": 2.436900888224431e-06, "loss": 0.0704, "step": 86000 }, { "epoch": 7.607070618239381, "grad_norm": 33.26008605957031, "learning_rate": 2.3929293817606197e-06, "loss": 0.0679, "step": 86500 }, { "epoch": 7.651042124703192, "grad_norm": 4.0587334632873535, "learning_rate": 2.348957875296808e-06, "loss": 0.0727, "step": 87000 }, { "epoch": 7.695013631167003, "grad_norm": 1.8055332899093628, "learning_rate": 2.3049863688329964e-06, "loss": 0.0714, "step": 87500 }, { "epoch": 7.738985137630815, "grad_norm": 0.08867678046226501, "learning_rate": 2.2610148623691848e-06, "loss": 0.0714, "step": 88000 }, { "epoch": 7.782956644094627, "grad_norm": 51.05652618408203, "learning_rate": 2.2170433559053736e-06, "loss": 0.0662, "step": 88500 }, { "epoch": 7.826928150558438, "grad_norm": 0.3058519959449768, "learning_rate": 2.173071849441562e-06, "loss": 0.0637, "step": 89000 }, { "epoch": 7.87089965702225, "grad_norm": 0.05084119364619255, "learning_rate": 2.1291003429777507e-06, "loss": 0.0676, "step": 89500 }, { "epoch": 7.914871163486061, "grad_norm": 0.23956036567687988, "learning_rate": 2.085128836513939e-06, "loss": 0.0818, "step": 90000 }, { "epoch": 7.958842669949872, "grad_norm": 15.964754104614258, "learning_rate": 2.041157330050128e-06, "loss": 0.076, "step": 90500 }, { "epoch": 8.002814176413684, "grad_norm": 1.4704182147979736, "learning_rate": 1.9971858235863163e-06, "loss": 0.0664, "step": 91000 }, { "epoch": 8.046785682877495, "grad_norm": 63.657440185546875, "learning_rate": 1.953214317122505e-06, "loss": 0.0583, "step": 91500 }, { "epoch": 8.090757189341307, "grad_norm": 8.421917915344238, "learning_rate": 1.9092428106586934e-06, "loss": 0.0613, "step": 92000 }, { "epoch": 8.134728695805117, "grad_norm": 0.17341230809688568, "learning_rate": 1.865271304194882e-06, "loss": 0.0554, "step": 92500 }, { "epoch": 8.17870020226893, "grad_norm": 0.09282279014587402, "learning_rate": 1.8212997977310704e-06, "loss": 0.0607, "step": 93000 }, { "epoch": 8.222671708732742, "grad_norm": 0.0653434619307518, "learning_rate": 1.777328291267259e-06, "loss": 0.058, "step": 93500 }, { "epoch": 8.266643215196552, "grad_norm": 20.4820556640625, "learning_rate": 1.7333567848034475e-06, "loss": 0.0564, "step": 94000 }, { "epoch": 8.310614721660365, "grad_norm": 2.014326333999634, "learning_rate": 1.6893852783396361e-06, "loss": 0.0589, "step": 94500 }, { "epoch": 8.354586228124175, "grad_norm": 0.2292569875717163, "learning_rate": 1.6454137718758245e-06, "loss": 0.0572, "step": 95000 }, { "epoch": 8.398557734587987, "grad_norm": 0.014584074728190899, "learning_rate": 1.6014422654120133e-06, "loss": 0.0497, "step": 95500 }, { "epoch": 8.442529241051798, "grad_norm": 30.090499877929688, "learning_rate": 1.5574707589482016e-06, "loss": 0.0609, "step": 96000 }, { "epoch": 8.48650074751561, "grad_norm": 0.038359276950359344, "learning_rate": 1.5134992524843902e-06, "loss": 0.0544, "step": 96500 }, { "epoch": 8.530472253979422, "grad_norm": 0.1624363213777542, "learning_rate": 1.4695277460205786e-06, "loss": 0.0578, "step": 97000 }, { "epoch": 8.574443760443232, "grad_norm": 0.23937764763832092, "learning_rate": 1.4255562395567674e-06, "loss": 0.058, "step": 97500 }, { "epoch": 8.618415266907045, "grad_norm": 0.08367595821619034, "learning_rate": 1.3815847330929558e-06, "loss": 0.0567, "step": 98000 }, { "epoch": 8.662386773370855, "grad_norm": 0.07520689815282822, "learning_rate": 1.3376132266291445e-06, "loss": 0.0507, "step": 98500 }, { "epoch": 8.706358279834667, "grad_norm": 0.20980244874954224, "learning_rate": 1.293641720165333e-06, "loss": 0.0621, "step": 99000 }, { "epoch": 8.75032978629848, "grad_norm": 2.3352205753326416, "learning_rate": 1.2496702137015215e-06, "loss": 0.053, "step": 99500 }, { "epoch": 8.79430129276229, "grad_norm": 0.1555749624967575, "learning_rate": 1.20569870723771e-06, "loss": 0.0572, "step": 100000 }, { "epoch": 8.838272799226102, "grad_norm": 17.412338256835938, "learning_rate": 1.1617272007738987e-06, "loss": 0.0562, "step": 100500 }, { "epoch": 8.882244305689913, "grad_norm": 0.07252756506204605, "learning_rate": 1.1177556943100872e-06, "loss": 0.0627, "step": 101000 }, { "epoch": 8.926215812153725, "grad_norm": 2.5696682929992676, "learning_rate": 1.0737841878462756e-06, "loss": 0.0593, "step": 101500 }, { "epoch": 8.970187318617535, "grad_norm": 38.372249603271484, "learning_rate": 1.0298126813824642e-06, "loss": 0.0533, "step": 102000 }, { "epoch": 9.014158825081347, "grad_norm": 0.0533902570605278, "learning_rate": 9.858411749186528e-07, "loss": 0.0542, "step": 102500 }, { "epoch": 9.05813033154516, "grad_norm": 1.9466789960861206, "learning_rate": 9.418696684548414e-07, "loss": 0.0524, "step": 103000 }, { "epoch": 9.10210183800897, "grad_norm": 38.15435791015625, "learning_rate": 8.978981619910298e-07, "loss": 0.0459, "step": 103500 }, { "epoch": 9.146073344472782, "grad_norm": 0.12077120691537857, "learning_rate": 8.539266555272184e-07, "loss": 0.0486, "step": 104000 }, { "epoch": 9.190044850936593, "grad_norm": 5.501252174377441, "learning_rate": 8.09955149063407e-07, "loss": 0.0491, "step": 104500 }, { "epoch": 9.234016357400405, "grad_norm": 0.05747182294726372, "learning_rate": 7.659836425995955e-07, "loss": 0.053, "step": 105000 }, { "epoch": 9.277987863864215, "grad_norm": 0.712147057056427, "learning_rate": 7.22012136135784e-07, "loss": 0.0612, "step": 105500 }, { "epoch": 9.321959370328027, "grad_norm": 79.47268676757812, "learning_rate": 6.780406296719725e-07, "loss": 0.0445, "step": 106000 }, { "epoch": 9.36593087679184, "grad_norm": 0.05525458604097366, "learning_rate": 6.340691232081611e-07, "loss": 0.0484, "step": 106500 }, { "epoch": 9.40990238325565, "grad_norm": 80.07630157470703, "learning_rate": 5.900976167443497e-07, "loss": 0.0486, "step": 107000 }, { "epoch": 9.453873889719462, "grad_norm": 31.79228973388672, "learning_rate": 5.461261102805383e-07, "loss": 0.0488, "step": 107500 }, { "epoch": 9.497845396183273, "grad_norm": 27.02912139892578, "learning_rate": 5.021546038167269e-07, "loss": 0.0533, "step": 108000 }, { "epoch": 9.541816902647085, "grad_norm": 0.05077936500310898, "learning_rate": 4.581830973529153e-07, "loss": 0.0485, "step": 108500 }, { "epoch": 9.585788409110895, "grad_norm": 0.13254009187221527, "learning_rate": 4.142115908891039e-07, "loss": 0.0475, "step": 109000 }, { "epoch": 9.629759915574708, "grad_norm": 4.606433391571045, "learning_rate": 3.7024008442529244e-07, "loss": 0.0465, "step": 109500 }, { "epoch": 9.67373142203852, "grad_norm": 12.37204647064209, "learning_rate": 3.2626857796148096e-07, "loss": 0.0431, "step": 110000 }, { "epoch": 9.71770292850233, "grad_norm": 68.52936553955078, "learning_rate": 2.8229707149766955e-07, "loss": 0.0498, "step": 110500 }, { "epoch": 9.761674434966142, "grad_norm": 11.432622909545898, "learning_rate": 2.3832556503385807e-07, "loss": 0.0512, "step": 111000 }, { "epoch": 9.805645941429953, "grad_norm": 0.3197621703147888, "learning_rate": 1.9435405857004663e-07, "loss": 0.0494, "step": 111500 }, { "epoch": 9.849617447893765, "grad_norm": 0.03288858011364937, "learning_rate": 1.5038255210623516e-07, "loss": 0.0504, "step": 112000 }, { "epoch": 9.893588954357575, "grad_norm": 0.5140511989593506, "learning_rate": 1.0641104564242372e-07, "loss": 0.0476, "step": 112500 }, { "epoch": 9.937560460821388, "grad_norm": 0.2467552274465561, "learning_rate": 6.243953917861227e-08, "loss": 0.0484, "step": 113000 }, { "epoch": 9.9815319672852, "grad_norm": 9.55329418182373, "learning_rate": 1.846803271480081e-08, "loss": 0.0474, "step": 113500 }, { "epoch": 10.0, "step": 113710, "total_flos": 2.4428070234989568e+17, "train_loss": 0.1514742186763295, "train_runtime": 20029.6511, "train_samples_per_second": 181.654, "train_steps_per_second": 5.677 } ], "logging_steps": 500, "max_steps": 113710, "num_input_tokens_seen": 0, "num_train_epochs": 10, "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": 2.4428070234989568e+17, "train_batch_size": 32, "trial_name": null, "trial_params": null }