{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 2140, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.023378141437755698, "grad_norm": 125.12454223632812, "learning_rate": 4.2056074766355143e-07, "loss": 3.0189, "step": 10 }, { "epoch": 0.046756282875511396, "grad_norm": 102.59304809570312, "learning_rate": 8.878504672897197e-07, "loss": 2.6695, "step": 20 }, { "epoch": 0.0701344243132671, "grad_norm": 36.426719665527344, "learning_rate": 1.3551401869158879e-06, "loss": 1.7422, "step": 30 }, { "epoch": 0.09351256575102279, "grad_norm": 34.45825958251953, "learning_rate": 1.8224299065420562e-06, "loss": 0.9496, "step": 40 }, { "epoch": 0.11689070718877849, "grad_norm": 53.89957046508789, "learning_rate": 2.2897196261682247e-06, "loss": 0.536, "step": 50 }, { "epoch": 0.1402688486265342, "grad_norm": 23.57602310180664, "learning_rate": 2.7570093457943923e-06, "loss": 0.5671, "step": 60 }, { "epoch": 0.1636469900642899, "grad_norm": 45.0745964050293, "learning_rate": 3.224299065420561e-06, "loss": 0.4019, "step": 70 }, { "epoch": 0.18702513150204558, "grad_norm": 16.272666931152344, "learning_rate": 3.691588785046729e-06, "loss": 0.3841, "step": 80 }, { "epoch": 0.2104032729398013, "grad_norm": 20.32345199584961, "learning_rate": 4.1588785046728974e-06, "loss": 0.3397, "step": 90 }, { "epoch": 0.23378141437755698, "grad_norm": 18.238306045532227, "learning_rate": 4.626168224299066e-06, "loss": 0.4846, "step": 100 }, { "epoch": 0.2571595558153127, "grad_norm": 19.088794708251953, "learning_rate": 5.0934579439252344e-06, "loss": 0.415, "step": 110 }, { "epoch": 0.2805376972530684, "grad_norm": 20.634057998657227, "learning_rate": 5.560747663551402e-06, "loss": 0.3493, "step": 120 }, { "epoch": 0.30391583869082406, "grad_norm": 13.07631778717041, "learning_rate": 6.028037383177571e-06, "loss": 0.3885, "step": 130 }, { "epoch": 0.3272939801285798, "grad_norm": 13.98646354675293, "learning_rate": 6.495327102803739e-06, "loss": 0.3874, "step": 140 }, { "epoch": 0.3506721215663355, "grad_norm": 12.87157917022705, "learning_rate": 6.962616822429908e-06, "loss": 0.409, "step": 150 }, { "epoch": 0.37405026300409117, "grad_norm": 15.179363250732422, "learning_rate": 7.429906542056075e-06, "loss": 0.3751, "step": 160 }, { "epoch": 0.39742840444184685, "grad_norm": 21.232479095458984, "learning_rate": 7.897196261682244e-06, "loss": 0.3317, "step": 170 }, { "epoch": 0.4208065458796026, "grad_norm": 24.20882797241211, "learning_rate": 8.364485981308411e-06, "loss": 0.4613, "step": 180 }, { "epoch": 0.4441846873173583, "grad_norm": 14.465646743774414, "learning_rate": 8.83177570093458e-06, "loss": 0.2439, "step": 190 }, { "epoch": 0.46756282875511396, "grad_norm": 18.011852264404297, "learning_rate": 9.299065420560748e-06, "loss": 0.4344, "step": 200 }, { "epoch": 0.49094097019286964, "grad_norm": 18.96558952331543, "learning_rate": 9.766355140186918e-06, "loss": 0.4829, "step": 210 }, { "epoch": 0.5143191116306254, "grad_norm": 8.94334888458252, "learning_rate": 9.999833710514407e-06, "loss": 0.306, "step": 220 }, { "epoch": 0.537697253068381, "grad_norm": 11.358978271484375, "learning_rate": 9.998503460994176e-06, "loss": 0.3864, "step": 230 }, { "epoch": 0.5610753945061367, "grad_norm": 16.574813842773438, "learning_rate": 9.995843315878242e-06, "loss": 0.3785, "step": 240 }, { "epoch": 0.5844535359438925, "grad_norm": 17.08701515197754, "learning_rate": 9.991853982921497e-06, "loss": 0.4135, "step": 250 }, { "epoch": 0.6078316773816481, "grad_norm": 19.786285400390625, "learning_rate": 9.98653652352089e-06, "loss": 0.3384, "step": 260 }, { "epoch": 0.6312098188194039, "grad_norm": 16.804025650024414, "learning_rate": 9.979892352433039e-06, "loss": 0.4206, "step": 270 }, { "epoch": 0.6545879602571596, "grad_norm": 24.340087890625, "learning_rate": 9.97192323739781e-06, "loss": 0.3441, "step": 280 }, { "epoch": 0.6779661016949152, "grad_norm": 15.506653785705566, "learning_rate": 9.962631298668015e-06, "loss": 0.3824, "step": 290 }, { "epoch": 0.701344243132671, "grad_norm": 8.362356185913086, "learning_rate": 9.952019008445277e-06, "loss": 0.2449, "step": 300 }, { "epoch": 0.7247223845704267, "grad_norm": 17.24741554260254, "learning_rate": 9.940089190222297e-06, "loss": 0.3711, "step": 310 }, { "epoch": 0.7481005260081823, "grad_norm": 13.927435874938965, "learning_rate": 9.926845018031632e-06, "loss": 0.361, "step": 320 }, { "epoch": 0.7714786674459381, "grad_norm": 20.883886337280273, "learning_rate": 9.91229001560121e-06, "loss": 0.5307, "step": 330 }, { "epoch": 0.7948568088836937, "grad_norm": 16.922466278076172, "learning_rate": 9.896428055416825e-06, "loss": 0.3081, "step": 340 }, { "epoch": 0.8182349503214494, "grad_norm": 15.271276473999023, "learning_rate": 9.879263357691815e-06, "loss": 0.291, "step": 350 }, { "epoch": 0.8416130917592052, "grad_norm": 14.011934280395508, "learning_rate": 9.860800489244247e-06, "loss": 0.3948, "step": 360 }, { "epoch": 0.8649912331969608, "grad_norm": 16.042314529418945, "learning_rate": 9.841044362281871e-06, "loss": 0.2567, "step": 370 }, { "epoch": 0.8883693746347165, "grad_norm": 21.948755264282227, "learning_rate": 9.820000233095179e-06, "loss": 0.3926, "step": 380 }, { "epoch": 0.9117475160724723, "grad_norm": 16.091821670532227, "learning_rate": 9.797673700658936e-06, "loss": 0.3305, "step": 390 }, { "epoch": 0.9351256575102279, "grad_norm": 12.307735443115234, "learning_rate": 9.774070705142509e-06, "loss": 0.44, "step": 400 }, { "epoch": 0.9585037989479837, "grad_norm": 11.81569766998291, "learning_rate": 9.749197526329446e-06, "loss": 0.3611, "step": 410 }, { "epoch": 0.9818819403857393, "grad_norm": 7.847588539123535, "learning_rate": 9.72306078194667e-06, "loss": 0.3981, "step": 420 }, { "epoch": 1.004675628287551, "grad_norm": 13.644335746765137, "learning_rate": 9.695667425903794e-06, "loss": 0.2749, "step": 430 }, { "epoch": 1.028053769725307, "grad_norm": 14.294634819030762, "learning_rate": 9.667024746442953e-06, "loss": 0.1754, "step": 440 }, { "epoch": 1.0514319111630626, "grad_norm": 14.423280715942383, "learning_rate": 9.637140364199716e-06, "loss": 0.162, "step": 450 }, { "epoch": 1.0748100526008182, "grad_norm": 10.16008186340332, "learning_rate": 9.606022230175546e-06, "loss": 0.1254, "step": 460 }, { "epoch": 1.098188194038574, "grad_norm": 5.6109747886657715, "learning_rate": 9.573678623622364e-06, "loss": 0.1567, "step": 470 }, { "epoch": 1.1215663354763297, "grad_norm": 1.6159133911132812, "learning_rate": 9.540118149839784e-06, "loss": 0.1283, "step": 480 }, { "epoch": 1.1449444769140853, "grad_norm": 14.524739265441895, "learning_rate": 9.505349737885597e-06, "loss": 0.2153, "step": 490 }, { "epoch": 1.1683226183518411, "grad_norm": 9.432572364807129, "learning_rate": 9.469382638200119e-06, "loss": 0.1756, "step": 500 }, { "epoch": 1.1917007597895968, "grad_norm": 10.524421691894531, "learning_rate": 9.432226420145025e-06, "loss": 0.1485, "step": 510 }, { "epoch": 1.2150789012273524, "grad_norm": 5.867332458496094, "learning_rate": 9.393890969457342e-06, "loss": 0.2071, "step": 520 }, { "epoch": 1.238457042665108, "grad_norm": 16.181983947753906, "learning_rate": 9.354386485619264e-06, "loss": 0.1392, "step": 530 }, { "epoch": 1.2618351841028639, "grad_norm": 7.531700134277344, "learning_rate": 9.313723479144478e-06, "loss": 0.2319, "step": 540 }, { "epoch": 1.2852133255406195, "grad_norm": 12.558058738708496, "learning_rate": 9.271912768781768e-06, "loss": 0.1605, "step": 550 }, { "epoch": 1.3085914669783751, "grad_norm": 9.029274940490723, "learning_rate": 9.228965478636575e-06, "loss": 0.1144, "step": 560 }, { "epoch": 1.331969608416131, "grad_norm": 13.889586448669434, "learning_rate": 9.184893035211346e-06, "loss": 0.2376, "step": 570 }, { "epoch": 1.3553477498538866, "grad_norm": 7.715616226196289, "learning_rate": 9.139707164365399e-06, "loss": 0.2081, "step": 580 }, { "epoch": 1.3787258912916422, "grad_norm": 10.404500961303711, "learning_rate": 9.09341988819517e-06, "loss": 0.1396, "step": 590 }, { "epoch": 1.4021040327293979, "grad_norm": 9.63452434539795, "learning_rate": 9.046043521835617e-06, "loss": 0.2414, "step": 600 }, { "epoch": 1.4254821741671537, "grad_norm": 15.154815673828125, "learning_rate": 8.997590670183673e-06, "loss": 0.1798, "step": 610 }, { "epoch": 1.4488603156049094, "grad_norm": 5.172611236572266, "learning_rate": 8.948074224544615e-06, "loss": 0.1686, "step": 620 }, { "epoch": 1.472238457042665, "grad_norm": 12.296631813049316, "learning_rate": 8.897507359202197e-06, "loss": 0.1572, "step": 630 }, { "epoch": 1.4956165984804208, "grad_norm": 11.069525718688965, "learning_rate": 8.845903527913538e-06, "loss": 0.11, "step": 640 }, { "epoch": 1.5189947399181765, "grad_norm": 9.363753318786621, "learning_rate": 8.79327646032962e-06, "loss": 0.1378, "step": 650 }, { "epoch": 1.542372881355932, "grad_norm": 8.269124984741211, "learning_rate": 8.739640158342396e-06, "loss": 0.2048, "step": 660 }, { "epoch": 1.565751022793688, "grad_norm": 9.519684791564941, "learning_rate": 8.685008892359468e-06, "loss": 0.1965, "step": 670 }, { "epoch": 1.5891291642314436, "grad_norm": 5.836247444152832, "learning_rate": 8.629397197507315e-06, "loss": 0.1552, "step": 680 }, { "epoch": 1.6125073056691992, "grad_norm": 6.548156261444092, "learning_rate": 8.572819869764102e-06, "loss": 0.1626, "step": 690 }, { "epoch": 1.635885447106955, "grad_norm": 19.386146545410156, "learning_rate": 8.51529196202307e-06, "loss": 0.214, "step": 700 }, { "epoch": 1.6592635885447107, "grad_norm": 13.855445861816406, "learning_rate": 8.456828780087598e-06, "loss": 0.1586, "step": 710 }, { "epoch": 1.6826417299824663, "grad_norm": 13.070948600769043, "learning_rate": 8.39744587859894e-06, "loss": 0.1594, "step": 720 }, { "epoch": 1.7060198714202222, "grad_norm": 12.13560962677002, "learning_rate": 8.337159056897792e-06, "loss": 0.2016, "step": 730 }, { "epoch": 1.7293980128579778, "grad_norm": 9.312642097473145, "learning_rate": 8.275984354820736e-06, "loss": 0.2282, "step": 740 }, { "epoch": 1.7527761542957334, "grad_norm": 6.142380714416504, "learning_rate": 8.213938048432697e-06, "loss": 0.1141, "step": 750 }, { "epoch": 1.7761542957334893, "grad_norm": 12.926299095153809, "learning_rate": 8.151036645696557e-06, "loss": 0.1842, "step": 760 }, { "epoch": 1.799532437171245, "grad_norm": 9.193605422973633, "learning_rate": 8.087296882081062e-06, "loss": 0.1878, "step": 770 }, { "epoch": 1.8229105786090005, "grad_norm": 5.925984859466553, "learning_rate": 8.022735716108213e-06, "loss": 0.1308, "step": 780 }, { "epoch": 1.8462887200467564, "grad_norm": 20.67131996154785, "learning_rate": 7.957370324841293e-06, "loss": 0.2606, "step": 790 }, { "epoch": 1.869666861484512, "grad_norm": 10.921467781066895, "learning_rate": 7.89121809931477e-06, "loss": 0.1948, "step": 800 }, { "epoch": 1.8930450029222676, "grad_norm": 18.8983211517334, "learning_rate": 7.824296639907243e-06, "loss": 0.2219, "step": 810 }, { "epoch": 1.9164231443600235, "grad_norm": 11.074198722839355, "learning_rate": 7.756623751658729e-06, "loss": 0.1699, "step": 820 }, { "epoch": 1.939801285797779, "grad_norm": 15.104548454284668, "learning_rate": 7.68821743953346e-06, "loss": 0.2134, "step": 830 }, { "epoch": 1.9631794272355347, "grad_norm": 13.703530311584473, "learning_rate": 7.619095903629509e-06, "loss": 0.2299, "step": 840 }, { "epoch": 1.9865575686732906, "grad_norm": 5.184883117675781, "learning_rate": 7.5492775343364964e-06, "loss": 0.2168, "step": 850 }, { "epoch": 2.009351256575102, "grad_norm": 7.515911102294922, "learning_rate": 7.478780907442665e-06, "loss": 0.0888, "step": 860 }, { "epoch": 2.032729398012858, "grad_norm": 10.076920509338379, "learning_rate": 7.407624779192628e-06, "loss": 0.0638, "step": 870 }, { "epoch": 2.056107539450614, "grad_norm": 1.63386070728302, "learning_rate": 7.335828081297109e-06, "loss": 0.0627, "step": 880 }, { "epoch": 2.0794856808883693, "grad_norm": 1.8829880952835083, "learning_rate": 7.263409915895992e-06, "loss": 0.0491, "step": 890 }, { "epoch": 2.102863822326125, "grad_norm": 18.568368911743164, "learning_rate": 7.190389550476023e-06, "loss": 0.0819, "step": 900 }, { "epoch": 2.126241963763881, "grad_norm": 11.98701286315918, "learning_rate": 7.116786412744548e-06, "loss": 0.0949, "step": 910 }, { "epoch": 2.1496201052016364, "grad_norm": 12.103470802307129, "learning_rate": 7.042620085460574e-06, "loss": 0.1159, "step": 920 }, { "epoch": 2.1729982466393922, "grad_norm": 12.610159873962402, "learning_rate": 6.967910301224627e-06, "loss": 0.0874, "step": 930 }, { "epoch": 2.196376388077148, "grad_norm": 10.560554504394531, "learning_rate": 6.8926769372287054e-06, "loss": 0.0534, "step": 940 }, { "epoch": 2.2197545295149035, "grad_norm": 8.60838508605957, "learning_rate": 6.816940009967787e-06, "loss": 0.0691, "step": 950 }, { "epoch": 2.2431326709526593, "grad_norm": 12.769586563110352, "learning_rate": 6.740719669914268e-06, "loss": 0.0615, "step": 960 }, { "epoch": 2.2665108123904147, "grad_norm": 11.18027400970459, "learning_rate": 6.664036196156742e-06, "loss": 0.0549, "step": 970 }, { "epoch": 2.2898889538281706, "grad_norm": 2.9581708908081055, "learning_rate": 6.586909991004587e-06, "loss": 0.0678, "step": 980 }, { "epoch": 2.3132670952659264, "grad_norm": 0.9250507354736328, "learning_rate": 6.5093615745597325e-06, "loss": 0.0367, "step": 990 }, { "epoch": 2.3366452367036823, "grad_norm": 4.8760271072387695, "learning_rate": 6.431411579257129e-06, "loss": 0.0902, "step": 1000 }, { "epoch": 2.3600233781414377, "grad_norm": 10.42834758758545, "learning_rate": 6.35308074437529e-06, "loss": 0.0742, "step": 1010 }, { "epoch": 2.3834015195791936, "grad_norm": 5.609081745147705, "learning_rate": 6.274389910518432e-06, "loss": 0.0293, "step": 1020 }, { "epoch": 2.406779661016949, "grad_norm": 1.6798259019851685, "learning_rate": 6.1953600140716565e-06, "loss": 0.0476, "step": 1030 }, { "epoch": 2.430157802454705, "grad_norm": 5.173406600952148, "learning_rate": 6.116012081630629e-06, "loss": 0.0751, "step": 1040 }, { "epoch": 2.4535359438924607, "grad_norm": 7.103416919708252, "learning_rate": 6.036367224407275e-06, "loss": 0.0493, "step": 1050 }, { "epoch": 2.476914085330216, "grad_norm": 5.651926517486572, "learning_rate": 5.956446632612958e-06, "loss": 0.0456, "step": 1060 }, { "epoch": 2.500292226767972, "grad_norm": 10.111432075500488, "learning_rate": 5.876271569820638e-06, "loss": 0.1037, "step": 1070 }, { "epoch": 2.5236703682057278, "grad_norm": 7.118322849273682, "learning_rate": 5.795863367307515e-06, "loss": 0.0553, "step": 1080 }, { "epoch": 2.547048509643483, "grad_norm": 11.993866920471191, "learning_rate": 5.715243418379642e-06, "loss": 0.0425, "step": 1090 }, { "epoch": 2.570426651081239, "grad_norm": 6.612995624542236, "learning_rate": 5.634433172680072e-06, "loss": 0.0562, "step": 1100 }, { "epoch": 2.593804792518995, "grad_norm": 7.672731399536133, "learning_rate": 5.553454130481968e-06, "loss": 0.046, "step": 1110 }, { "epoch": 2.6171829339567503, "grad_norm": 7.565694332122803, "learning_rate": 5.4723278369682856e-06, "loss": 0.0659, "step": 1120 }, { "epoch": 2.640561075394506, "grad_norm": 0.39829906821250916, "learning_rate": 5.391075876499483e-06, "loss": 0.046, "step": 1130 }, { "epoch": 2.663939216832262, "grad_norm": 6.02488899230957, "learning_rate": 5.309719866870806e-06, "loss": 0.1029, "step": 1140 }, { "epoch": 2.6873173582700174, "grad_norm": 1.7749392986297607, "learning_rate": 5.2282814535606926e-06, "loss": 0.0623, "step": 1150 }, { "epoch": 2.7106954997077732, "grad_norm": 5.36119270324707, "learning_rate": 5.1467823039718046e-06, "loss": 0.0621, "step": 1160 }, { "epoch": 2.734073641145529, "grad_norm": 5.822856426239014, "learning_rate": 5.065244101666218e-06, "loss": 0.07, "step": 1170 }, { "epoch": 2.7574517825832845, "grad_norm": 4.167882919311523, "learning_rate": 4.983688540596327e-06, "loss": 0.0656, "step": 1180 }, { "epoch": 2.7808299240210403, "grad_norm": 4.496674537658691, "learning_rate": 4.9021373193329775e-06, "loss": 0.0904, "step": 1190 }, { "epoch": 2.8042080654587958, "grad_norm": 10.321039199829102, "learning_rate": 4.820612135292372e-06, "loss": 0.0918, "step": 1200 }, { "epoch": 2.8275862068965516, "grad_norm": 5.007414817810059, "learning_rate": 4.739134678963284e-06, "loss": 0.0613, "step": 1210 }, { "epoch": 2.8509643483343075, "grad_norm": 14.701879501342773, "learning_rate": 4.657726628136105e-06, "loss": 0.0627, "step": 1220 }, { "epoch": 2.8743424897720633, "grad_norm": 3.9331204891204834, "learning_rate": 4.576409642135295e-06, "loss": 0.0473, "step": 1230 }, { "epoch": 2.8977206312098187, "grad_norm": 8.668416023254395, "learning_rate": 4.495205356056713e-06, "loss": 0.0421, "step": 1240 }, { "epoch": 2.9210987726475746, "grad_norm": 8.684922218322754, "learning_rate": 4.414135375011416e-06, "loss": 0.0292, "step": 1250 }, { "epoch": 2.94447691408533, "grad_norm": 9.3709716796875, "learning_rate": 4.333221268377437e-06, "loss": 0.0565, "step": 1260 }, { "epoch": 2.967855055523086, "grad_norm": 3.0406768321990967, "learning_rate": 4.252484564061056e-06, "loss": 0.0662, "step": 1270 }, { "epoch": 2.9912331969608417, "grad_norm": 4.426455974578857, "learning_rate": 4.171946742769109e-06, "loss": 0.022, "step": 1280 }, { "epoch": 3.0140268848626532, "grad_norm": 6.238279819488525, "learning_rate": 4.091629232293866e-06, "loss": 0.039, "step": 1290 }, { "epoch": 3.037405026300409, "grad_norm": 2.5013153553009033, "learning_rate": 4.0115534018119816e-06, "loss": 0.0273, "step": 1300 }, { "epoch": 3.060783167738165, "grad_norm": 5.70876407623291, "learning_rate": 3.931740556199021e-06, "loss": 0.0134, "step": 1310 }, { "epoch": 3.0841613091759204, "grad_norm": 5.676060676574707, "learning_rate": 3.8522119303611325e-06, "loss": 0.0249, "step": 1320 }, { "epoch": 3.107539450613676, "grad_norm": 9.387015342712402, "learning_rate": 3.7729886835853043e-06, "loss": 0.0115, "step": 1330 }, { "epoch": 3.130917592051432, "grad_norm": 0.2285153567790985, "learning_rate": 3.694091893909746e-06, "loss": 0.0112, "step": 1340 }, { "epoch": 3.1542957334891875, "grad_norm": 0.2652380168437958, "learning_rate": 3.6155425525159055e-06, "loss": 0.0073, "step": 1350 }, { "epoch": 3.1776738749269433, "grad_norm": 22.555295944213867, "learning_rate": 3.5373615581435737e-06, "loss": 0.0157, "step": 1360 }, { "epoch": 3.201052016364699, "grad_norm": 6.411059379577637, "learning_rate": 3.459569711530586e-06, "loss": 0.017, "step": 1370 }, { "epoch": 3.2244301578024546, "grad_norm": 5.048878192901611, "learning_rate": 3.3821877098786173e-06, "loss": 0.0134, "step": 1380 }, { "epoch": 3.2478082992402104, "grad_norm": 0.8578410744667053, "learning_rate": 3.3052361413465007e-06, "loss": 0.0145, "step": 1390 }, { "epoch": 3.2711864406779663, "grad_norm": 11.427050590515137, "learning_rate": 3.22873547957257e-06, "loss": 0.0143, "step": 1400 }, { "epoch": 3.2945645821157217, "grad_norm": 0.3549112379550934, "learning_rate": 3.152706078227471e-06, "loss": 0.0105, "step": 1410 }, { "epoch": 3.3179427235534775, "grad_norm": 4.932265758514404, "learning_rate": 3.0771681655988857e-06, "loss": 0.0282, "step": 1420 }, { "epoch": 3.3413208649912334, "grad_norm": 9.115782737731934, "learning_rate": 3.0021418392096215e-06, "loss": 0.0218, "step": 1430 }, { "epoch": 3.364699006428989, "grad_norm": 13.693296432495117, "learning_rate": 2.9276470604704897e-06, "loss": 0.0271, "step": 1440 }, { "epoch": 3.3880771478667446, "grad_norm": 3.7683138847351074, "learning_rate": 2.8537036493694003e-06, "loss": 0.0292, "step": 1450 }, { "epoch": 3.4114552893045005, "grad_norm": 13.032756805419922, "learning_rate": 2.7803312791980697e-06, "loss": 0.041, "step": 1460 }, { "epoch": 3.434833430742256, "grad_norm": 12.838432312011719, "learning_rate": 2.707549471317782e-06, "loss": 0.0402, "step": 1470 }, { "epoch": 3.4582115721800117, "grad_norm": 8.207934379577637, "learning_rate": 2.635377589965557e-06, "loss": 0.0145, "step": 1480 }, { "epoch": 3.481589713617767, "grad_norm": 5.285949230194092, "learning_rate": 2.563834837102115e-06, "loss": 0.0124, "step": 1490 }, { "epoch": 3.504967855055523, "grad_norm": 0.8014376163482666, "learning_rate": 2.492940247303046e-06, "loss": 0.0031, "step": 1500 }, { "epoch": 3.528345996493279, "grad_norm": 3.3630831241607666, "learning_rate": 2.4227126826944723e-06, "loss": 0.0227, "step": 1510 }, { "epoch": 3.5517241379310347, "grad_norm": 0.9836694002151489, "learning_rate": 2.3531708279346347e-06, "loss": 0.0125, "step": 1520 }, { "epoch": 3.57510227936879, "grad_norm": 0.4681728184223175, "learning_rate": 2.2843331852426646e-06, "loss": 0.0287, "step": 1530 }, { "epoch": 3.598480420806546, "grad_norm": 1.1351826190948486, "learning_rate": 2.2162180694759083e-06, "loss": 0.0199, "step": 1540 }, { "epoch": 3.6218585622443014, "grad_norm": 0.672646701335907, "learning_rate": 2.1488436032571e-06, "loss": 0.0083, "step": 1550 }, { "epoch": 3.645236703682057, "grad_norm": 0.4807230830192566, "learning_rate": 2.0822277121526797e-06, "loss": 0.0052, "step": 1560 }, { "epoch": 3.668614845119813, "grad_norm": 7.503604888916016, "learning_rate": 2.016388119903536e-06, "loss": 0.016, "step": 1570 }, { "epoch": 3.691992986557569, "grad_norm": 0.130148246884346, "learning_rate": 1.951342343709456e-06, "loss": 0.0133, "step": 1580 }, { "epoch": 3.7153711279953243, "grad_norm": 0.4070602059364319, "learning_rate": 1.8871076895685164e-06, "loss": 0.0111, "step": 1590 }, { "epoch": 3.73874926943308, "grad_norm": 0.21065488457679749, "learning_rate": 1.8237012476726695e-06, "loss": 0.0329, "step": 1600 }, { "epoch": 3.7621274108708356, "grad_norm": 9.535804748535156, "learning_rate": 1.7611398878607544e-06, "loss": 0.0188, "step": 1610 }, { "epoch": 3.7855055523085914, "grad_norm": 1.9582473039627075, "learning_rate": 1.6994402551301248e-06, "loss": 0.0264, "step": 1620 }, { "epoch": 3.8088836937463473, "grad_norm": 8.368050575256348, "learning_rate": 1.638618765208098e-06, "loss": 0.0221, "step": 1630 }, { "epoch": 3.832261835184103, "grad_norm": 9.98831558227539, "learning_rate": 1.578691600184416e-06, "loss": 0.0244, "step": 1640 }, { "epoch": 3.8556399766218585, "grad_norm": 3.5946707725524902, "learning_rate": 1.5196747042058525e-06, "loss": 0.0117, "step": 1650 }, { "epoch": 3.8790181180596144, "grad_norm": 1.8895704746246338, "learning_rate": 1.461583779234132e-06, "loss": 0.0078, "step": 1660 }, { "epoch": 3.90239625949737, "grad_norm": 1.8147823810577393, "learning_rate": 1.4044342808682904e-06, "loss": 0.0102, "step": 1670 }, { "epoch": 3.9257744009351256, "grad_norm": 3.3822011947631836, "learning_rate": 1.3482414142325768e-06, "loss": 0.0144, "step": 1680 }, { "epoch": 3.9491525423728815, "grad_norm": 0.43435657024383545, "learning_rate": 1.2930201299309896e-06, "loss": 0.0151, "step": 1690 }, { "epoch": 3.972530683810637, "grad_norm": 11.06054401397705, "learning_rate": 1.23878512006955e-06, "loss": 0.0141, "step": 1700 }, { "epoch": 3.9959088252483927, "grad_norm": 8.782082557678223, "learning_rate": 1.1855508143473276e-06, "loss": 0.055, "step": 1710 }, { "epoch": 4.018702513150204, "grad_norm": 0.04355354607105255, "learning_rate": 1.133331376217301e-06, "loss": 0.0152, "step": 1720 }, { "epoch": 4.04208065458796, "grad_norm": 0.30825066566467285, "learning_rate": 1.0821406991180367e-06, "loss": 0.0025, "step": 1730 }, { "epoch": 4.065458796025716, "grad_norm": 0.3763493001461029, "learning_rate": 1.0319924027772304e-06, "loss": 0.0027, "step": 1740 }, { "epoch": 4.088836937463472, "grad_norm": 10.526937484741211, "learning_rate": 9.82899829588052e-07, "loss": 0.0079, "step": 1750 }, { "epoch": 4.112215078901228, "grad_norm": 0.8182287216186523, "learning_rate": 9.348760410592855e-07, "loss": 0.0019, "step": 1760 }, { "epoch": 4.135593220338983, "grad_norm": 2.2300643920898438, "learning_rate": 8.879338143402039e-07, "loss": 0.0064, "step": 1770 }, { "epoch": 4.1589713617767385, "grad_norm": 0.21672707796096802, "learning_rate": 8.420856388210891e-07, "loss": 0.0153, "step": 1780 }, { "epoch": 4.182349503214494, "grad_norm": 0.5077906250953674, "learning_rate": 7.973437128103306e-07, "loss": 0.0055, "step": 1790 }, { "epoch": 4.20572764465225, "grad_norm": 0.9171091914176941, "learning_rate": 7.537199402889528e-07, "loss": 0.0011, "step": 1800 }, { "epoch": 4.229105786090006, "grad_norm": 0.20687416195869446, "learning_rate": 7.112259277434542e-07, "loss": 0.0036, "step": 1810 }, { "epoch": 4.252483927527762, "grad_norm": 0.7315768599510193, "learning_rate": 6.698729810778065e-07, "loss": 0.0009, "step": 1820 }, { "epoch": 4.275862068965517, "grad_norm": 0.003912055399268866, "learning_rate": 6.296721026054175e-07, "loss": 0.0024, "step": 1830 }, { "epoch": 4.299240210403273, "grad_norm": 1.9899204969406128, "learning_rate": 5.906339881218648e-07, "loss": 0.0036, "step": 1840 }, { "epoch": 4.322618351841029, "grad_norm": 0.16669225692749023, "learning_rate": 5.527690240591927e-07, "loss": 0.0048, "step": 1850 }, { "epoch": 4.3459964932787845, "grad_norm": 0.323431134223938, "learning_rate": 5.160872847225073e-07, "loss": 0.0019, "step": 1860 }, { "epoch": 4.36937463471654, "grad_norm": 0.7924166917800903, "learning_rate": 4.805985296096188e-07, "loss": 0.0009, "step": 1870 }, { "epoch": 4.392752776154296, "grad_norm": 0.4262787401676178, "learning_rate": 4.463122008144449e-07, "loss": 0.0013, "step": 1880 }, { "epoch": 4.416130917592051, "grad_norm": 0.17763656377792358, "learning_rate": 4.132374205148559e-07, "loss": 0.0015, "step": 1890 }, { "epoch": 4.439509059029807, "grad_norm": 0.12163164466619492, "learning_rate": 3.813829885456399e-07, "loss": 0.0022, "step": 1900 }, { "epoch": 4.462887200467563, "grad_norm": 0.037543587386608124, "learning_rate": 3.507573800572328e-07, "loss": 0.0087, "step": 1910 }, { "epoch": 4.486265341905319, "grad_norm": 0.30685582756996155, "learning_rate": 3.2136874326082534e-07, "loss": 0.0007, "step": 1920 }, { "epoch": 4.5096434833430745, "grad_norm": 4.26045560836792, "learning_rate": 2.9322489726046565e-07, "loss": 0.0036, "step": 1930 }, { "epoch": 4.5330216247808295, "grad_norm": 0.15433892607688904, "learning_rate": 2.6633332997271277e-07, "loss": 0.0005, "step": 1940 }, { "epoch": 4.556399766218585, "grad_norm": 0.16720223426818848, "learning_rate": 2.407011961344158e-07, "loss": 0.0003, "step": 1950 }, { "epoch": 4.579777907656341, "grad_norm": 4.23595666885376, "learning_rate": 2.1633531539912933e-07, "loss": 0.0082, "step": 1960 }, { "epoch": 4.603156049094097, "grad_norm": 0.9773761630058289, "learning_rate": 1.9324217052268835e-07, "loss": 0.0011, "step": 1970 }, { "epoch": 4.626534190531853, "grad_norm": 0.5005733370780945, "learning_rate": 1.7142790563841216e-07, "loss": 0.0014, "step": 1980 }, { "epoch": 4.649912331969609, "grad_norm": 2.929980993270874, "learning_rate": 1.5089832462240438e-07, "loss": 0.0047, "step": 1990 }, { "epoch": 4.673290473407365, "grad_norm": 0.20166566967964172, "learning_rate": 1.31658889549382e-07, "loss": 0.0028, "step": 2000 }, { "epoch": 4.6966686148451195, "grad_norm": 0.15809489786624908, "learning_rate": 1.1371471923944166e-07, "loss": 0.0006, "step": 2010 }, { "epoch": 4.720046756282875, "grad_norm": 0.5963819622993469, "learning_rate": 9.707058789615198e-08, "loss": 0.0015, "step": 2020 }, { "epoch": 4.743424897720631, "grad_norm": 0.09445592761039734, "learning_rate": 8.173092383633563e-08, "loss": 0.0024, "step": 2030 }, { "epoch": 4.766803039158387, "grad_norm": 2.41282320022583, "learning_rate": 6.769980831187906e-08, "loss": 0.0062, "step": 2040 }, { "epoch": 4.790181180596143, "grad_norm": 0.0030083770398050547, "learning_rate": 5.498097442387551e-08, "loss": 0.0017, "step": 2050 }, { "epoch": 4.813559322033898, "grad_norm": 0.49933573603630066, "learning_rate": 4.357780612940343e-08, "loss": 0.0017, "step": 2060 }, { "epoch": 4.836937463471654, "grad_norm": 1.9950659275054932, "learning_rate": 3.349333734119609e-08, "loss": 0.0047, "step": 2070 }, { "epoch": 4.86031560490941, "grad_norm": 0.07601786404848099, "learning_rate": 2.473025112043892e-08, "loss": 0.0007, "step": 2080 }, { "epoch": 4.8836937463471655, "grad_norm": 0.40873971581459045, "learning_rate": 1.7290878962920587e-08, "loss": 0.0046, "step": 2090 }, { "epoch": 4.907071887784921, "grad_norm": 0.15987105667591095, "learning_rate": 1.117720017871804e-08, "loss": 0.0074, "step": 2100 }, { "epoch": 4.930450029222677, "grad_norm": 0.0340660996735096, "learning_rate": 6.390841365582767e-09, "loss": 0.001, "step": 2110 }, { "epoch": 4.953828170660432, "grad_norm": 0.04589745029807091, "learning_rate": 2.9330759761692086e-09, "loss": 0.0006, "step": 2120 }, { "epoch": 4.977206312098188, "grad_norm": 0.03405718505382538, "learning_rate": 8.048239792241008e-10, "loss": 0.005, "step": 2130 }, { "epoch": 5.0, "grad_norm": 0.006713826674968004, "learning_rate": 6.651614818942165e-12, "loss": 0.0009, "step": 2140 } ], "logging_steps": 10, "max_steps": 2140, "num_input_tokens_seen": 0, "num_train_epochs": 5, "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": 1.221620632387584e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }