| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009961647656522389, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.961647656522389e-05, | |
| "grad_norm": 0.361257940530777, | |
| "learning_rate": 1e-05, | |
| "loss": 1.612, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.961647656522389e-05, | |
| "eval_loss": 1.0737022161483765, | |
| "eval_runtime": 882.3097, | |
| "eval_samples_per_second": 9.582, | |
| "eval_steps_per_second": 1.198, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019923295313044778, | |
| "grad_norm": 0.46103528141975403, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0592, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002988494296956717, | |
| "grad_norm": 0.4550243616104126, | |
| "learning_rate": 3e-05, | |
| "loss": 2.2149, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00039846590626089557, | |
| "grad_norm": 0.4841668903827667, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2257, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004980823828261194, | |
| "grad_norm": 0.6147142648696899, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3121, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005976988593913434, | |
| "grad_norm": 0.5650891661643982, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3506, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006973153359565673, | |
| "grad_norm": 0.4558981657028198, | |
| "learning_rate": 7e-05, | |
| "loss": 1.8125, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0007969318125217911, | |
| "grad_norm": 0.5769819617271423, | |
| "learning_rate": 8e-05, | |
| "loss": 2.1857, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.000896548289087015, | |
| "grad_norm": 0.7398414611816406, | |
| "learning_rate": 9e-05, | |
| "loss": 2.2563, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000896548289087015, | |
| "eval_loss": 1.0244592428207397, | |
| "eval_runtime": 882.8001, | |
| "eval_samples_per_second": 9.576, | |
| "eval_steps_per_second": 1.197, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009961647656522388, | |
| "grad_norm": 0.727397084236145, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3204, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010957812422174628, | |
| "grad_norm": 0.6757255792617798, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 1.9631, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0011953977187826868, | |
| "grad_norm": 0.8596791625022888, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.0066, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0012950141953479105, | |
| "grad_norm": 0.7441974878311157, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.985, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0013946306719131345, | |
| "grad_norm": 0.7234380841255188, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.0265, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0014942471484783583, | |
| "grad_norm": 1.2355715036392212, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.9902, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015938636250435823, | |
| "grad_norm": 1.37369704246521, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.0392, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.001693480101608806, | |
| "grad_norm": 1.1652811765670776, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 1.8477, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00179309657817403, | |
| "grad_norm": 0.8481112718582153, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.7533, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00179309657817403, | |
| "eval_loss": 0.8560749292373657, | |
| "eval_runtime": 884.1446, | |
| "eval_samples_per_second": 9.562, | |
| "eval_steps_per_second": 1.196, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0018927130547392538, | |
| "grad_norm": 0.7027485370635986, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.5919, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0019923295313044776, | |
| "grad_norm": 0.7844833731651306, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.5656, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0020919460078697018, | |
| "grad_norm": 0.9267317056655884, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.5338, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0021915624844349255, | |
| "grad_norm": 0.9367462992668152, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.6593, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0022911789610001493, | |
| "grad_norm": 0.7053329348564148, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.417, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0023907954375653735, | |
| "grad_norm": 0.6589796543121338, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.4356, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0024904119141305973, | |
| "grad_norm": 0.7963542342185974, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5551, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002590028390695821, | |
| "grad_norm": 0.7066437602043152, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.5937, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.002689644867261045, | |
| "grad_norm": 0.684407651424408, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 1.4366, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002689644867261045, | |
| "eval_loss": 0.8160959482192993, | |
| "eval_runtime": 883.6722, | |
| "eval_samples_per_second": 9.567, | |
| "eval_steps_per_second": 1.196, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002789261343826269, | |
| "grad_norm": 0.7681823372840881, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.4063, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.002888877820391493, | |
| "grad_norm": 0.7006301879882812, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 1.2299, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0029884942969567166, | |
| "grad_norm": 0.8284811973571777, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.7102, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0030881107735219403, | |
| "grad_norm": 0.8312244415283203, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 1.4079, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0031877272500871645, | |
| "grad_norm": 0.6091031432151794, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.2915, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0032873437266523883, | |
| "grad_norm": 0.7346383929252625, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 1.4389, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.003386960203217612, | |
| "grad_norm": 0.8104448914527893, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.65, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0034865766797828363, | |
| "grad_norm": 0.9100492596626282, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 1.857, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00358619315634806, | |
| "grad_norm": 0.6399231553077698, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.803, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00358619315634806, | |
| "eval_loss": 0.7986570596694946, | |
| "eval_runtime": 883.7392, | |
| "eval_samples_per_second": 9.566, | |
| "eval_steps_per_second": 1.196, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.003685809632913284, | |
| "grad_norm": 0.6590905785560608, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 1.5133, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0037854261094785076, | |
| "grad_norm": 0.7415932416915894, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.6611, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0038850425860437318, | |
| "grad_norm": 0.9437408447265625, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 1.8239, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.003984659062608955, | |
| "grad_norm": 0.7338345050811768, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.5454, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004084275539174179, | |
| "grad_norm": 0.6436401605606079, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 1.6553, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0041838920157394035, | |
| "grad_norm": 0.6931898593902588, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.7065, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.004283508492304627, | |
| "grad_norm": 0.6704197525978088, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 1.4526, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.004383124968869851, | |
| "grad_norm": 0.6947505474090576, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.6123, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.004482741445435075, | |
| "grad_norm": 0.7843073010444641, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 1.562, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004482741445435075, | |
| "eval_loss": 0.7821637392044067, | |
| "eval_runtime": 884.1235, | |
| "eval_samples_per_second": 9.562, | |
| "eval_steps_per_second": 1.196, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004582357922000299, | |
| "grad_norm": 0.7678735852241516, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.6434, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.004681974398565523, | |
| "grad_norm": 0.6877706050872803, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 1.4048, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.004781590875130747, | |
| "grad_norm": 0.584237813949585, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.3832, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.00488120735169597, | |
| "grad_norm": 0.8516788482666016, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 1.8079, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0049808238282611945, | |
| "grad_norm": 0.7160507440567017, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.6585, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005080440304826418, | |
| "grad_norm": 0.7930417060852051, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 1.6369, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.005180056781391642, | |
| "grad_norm": 0.7871742844581604, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.5534, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.005279673257956866, | |
| "grad_norm": 0.6670714020729065, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 1.3054, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.00537928973452209, | |
| "grad_norm": 1.0112168788909912, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.7332, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.00537928973452209, | |
| "eval_loss": 0.7755426168441772, | |
| "eval_runtime": 883.8228, | |
| "eval_samples_per_second": 9.565, | |
| "eval_steps_per_second": 1.196, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.005478906211087314, | |
| "grad_norm": 0.6689745783805847, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4189, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.005578522687652538, | |
| "grad_norm": 0.7754594087600708, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.7382, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.005678139164217761, | |
| "grad_norm": 0.6562862396240234, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 1.4483, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.005777755640782986, | |
| "grad_norm": 0.746115505695343, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.7187, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.00587737211734821, | |
| "grad_norm": 0.7487801909446716, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 1.7661, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.005976988593913433, | |
| "grad_norm": 1.057198405265808, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.6956, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.006076605070478657, | |
| "grad_norm": 0.7863832712173462, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 1.4371, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.006176221547043881, | |
| "grad_norm": 0.6938728094100952, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.4175, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.006275838023609105, | |
| "grad_norm": 0.9374027848243713, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 1.5811, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.006275838023609105, | |
| "eval_loss": 0.7708137631416321, | |
| "eval_runtime": 882.9759, | |
| "eval_samples_per_second": 9.574, | |
| "eval_steps_per_second": 1.197, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.006375454500174329, | |
| "grad_norm": 0.773817777633667, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.5926, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.006475070976739552, | |
| "grad_norm": 0.7217618227005005, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 1.3551, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.006574687453304777, | |
| "grad_norm": 0.692355751991272, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.4498, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.006674303929870001, | |
| "grad_norm": 0.8275511860847473, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 1.781, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.006773920406435224, | |
| "grad_norm": 0.8264217376708984, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.7358, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.006873536883000448, | |
| "grad_norm": 0.76736980676651, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 1.8331, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0069731533595656725, | |
| "grad_norm": 0.7246225476264954, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.5015, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.007072769836130896, | |
| "grad_norm": 0.8643390536308289, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 1.8404, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.00717238631269612, | |
| "grad_norm": 0.9402040243148804, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.6392, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.00717238631269612, | |
| "eval_loss": 0.768054187297821, | |
| "eval_runtime": 883.2971, | |
| "eval_samples_per_second": 9.571, | |
| "eval_steps_per_second": 1.197, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.007272002789261343, | |
| "grad_norm": 0.6827989816665649, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 1.344, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.007371619265826568, | |
| "grad_norm": 0.8760033249855042, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.6694, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.007471235742391792, | |
| "grad_norm": 0.6600123643875122, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 1.3523, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.007570852218957015, | |
| "grad_norm": 0.856013298034668, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.4357, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.007670468695522239, | |
| "grad_norm": 0.7908009886741638, | |
| "learning_rate": 1.526708147705013e-05, | |
| "loss": 1.4971, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.0077700851720874636, | |
| "grad_norm": 0.6581637859344482, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.3045, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.007869701648652687, | |
| "grad_norm": 0.7885287404060364, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 1.4768, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.00796931812521791, | |
| "grad_norm": 0.8533726334571838, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.813, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.008068934601783135, | |
| "grad_norm": 0.7847617864608765, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 1.6292, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.008068934601783135, | |
| "eval_loss": 0.7664384245872498, | |
| "eval_runtime": 883.1996, | |
| "eval_samples_per_second": 9.572, | |
| "eval_steps_per_second": 1.197, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.008168551078348359, | |
| "grad_norm": 0.6186761856079102, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.2958, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.008268167554913582, | |
| "grad_norm": 0.5993787050247192, | |
| "learning_rate": 8.548121372247918e-06, | |
| "loss": 1.3766, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.008367784031478807, | |
| "grad_norm": 0.6269441246986389, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.3048, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.00846740050804403, | |
| "grad_norm": 0.7146202325820923, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.4853, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.008567016984609254, | |
| "grad_norm": 0.7214375138282776, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.4497, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.008666633461174479, | |
| "grad_norm": 0.7088419795036316, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 1.5205, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.008766249937739702, | |
| "grad_norm": 0.7890331745147705, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.6061, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.008865866414304925, | |
| "grad_norm": 0.75309157371521, | |
| "learning_rate": 3.6408072716606346e-06, | |
| "loss": 1.6513, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.00896548289087015, | |
| "grad_norm": 0.6757559776306152, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.3202, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.00896548289087015, | |
| "eval_loss": 0.7658533453941345, | |
| "eval_runtime": 883.1032, | |
| "eval_samples_per_second": 9.573, | |
| "eval_steps_per_second": 1.197, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.009065099367435374, | |
| "grad_norm": 0.7671038508415222, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 1.6385, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.009164715844000597, | |
| "grad_norm": 0.6452928185462952, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.3193, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.009264332320565822, | |
| "grad_norm": 0.6585118174552917, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 1.2951, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.009363948797131046, | |
| "grad_norm": 0.7894080281257629, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.6466, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.009463565273696269, | |
| "grad_norm": 0.6712362170219421, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 1.5096, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.009563181750261494, | |
| "grad_norm": 0.7802687883377075, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.3291, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.009662798226826717, | |
| "grad_norm": 0.6751720905303955, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 1.5444, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.00976241470339194, | |
| "grad_norm": 0.6705344319343567, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.4777, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.009862031179957166, | |
| "grad_norm": 0.6760139465332031, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 1.4916, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.009862031179957166, | |
| "eval_loss": 0.7657371759414673, | |
| "eval_runtime": 883.7398, | |
| "eval_samples_per_second": 9.566, | |
| "eval_steps_per_second": 1.196, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.009961647656522389, | |
| "grad_norm": 0.6802321076393127, | |
| "learning_rate": 0.0, | |
| "loss": 1.5107, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2886094823555072e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |