| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007455453664355476, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.455453664355477e-05, | |
| "grad_norm": 10.49715518951416, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3675, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.455453664355477e-05, | |
| "eval_loss": 7.581628322601318, | |
| "eval_runtime": 1831.8815, | |
| "eval_samples_per_second": 6.166, | |
| "eval_steps_per_second": 0.771, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014910907328710953, | |
| "grad_norm": 6.722843647003174, | |
| "learning_rate": 2e-05, | |
| "loss": 6.9309, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00022366360993066427, | |
| "grad_norm": 6.796828746795654, | |
| "learning_rate": 3e-05, | |
| "loss": 6.1734, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00029821814657421907, | |
| "grad_norm": 7.420350074768066, | |
| "learning_rate": 4e-05, | |
| "loss": 6.8689, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003727726832177738, | |
| "grad_norm": 10.972343444824219, | |
| "learning_rate": 5e-05, | |
| "loss": 8.4649, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00044732721986132855, | |
| "grad_norm": 8.64516544342041, | |
| "learning_rate": 6e-05, | |
| "loss": 6.9404, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005218817565048833, | |
| "grad_norm": 12.11950969696045, | |
| "learning_rate": 7e-05, | |
| "loss": 8.3633, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005964362931484381, | |
| "grad_norm": 9.8136568069458, | |
| "learning_rate": 8e-05, | |
| "loss": 4.2432, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006709908297919928, | |
| "grad_norm": 13.001618385314941, | |
| "learning_rate": 9e-05, | |
| "loss": 5.1604, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006709908297919928, | |
| "eval_loss": 3.2318060398101807, | |
| "eval_runtime": 1836.1454, | |
| "eval_samples_per_second": 6.151, | |
| "eval_steps_per_second": 0.769, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007455453664355476, | |
| "grad_norm": 8.031773567199707, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0669, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008200999030791024, | |
| "grad_norm": 9.736612319946289, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 2.9862, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0008946544397226571, | |
| "grad_norm": 8.880220413208008, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.9853, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0009692089763662119, | |
| "grad_norm": 8.896377563476562, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 2.2486, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0010437635130097667, | |
| "grad_norm": 8.374354362487793, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.2035, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0011183180496533215, | |
| "grad_norm": 6.076426029205322, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.6982, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011928725862968763, | |
| "grad_norm": 7.052265167236328, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.2892, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0012674271229404308, | |
| "grad_norm": 8.613420486450195, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.8283, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0013419816595839856, | |
| "grad_norm": 6.096333026885986, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.2756, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0013419816595839856, | |
| "eval_loss": 1.3903357982635498, | |
| "eval_runtime": 1835.2174, | |
| "eval_samples_per_second": 6.155, | |
| "eval_steps_per_second": 0.769, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0014165361962275404, | |
| "grad_norm": 3.982419967651367, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.1631, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0014910907328710952, | |
| "grad_norm": 4.764151573181152, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.77, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00156564526951465, | |
| "grad_norm": 4.972811222076416, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.3896, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0016401998061582048, | |
| "grad_norm": 4.898617267608643, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.9579, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0017147543428017594, | |
| "grad_norm": 5.04691219329834, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.995, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0017893088794453142, | |
| "grad_norm": 3.136345386505127, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.9698, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.001863863416088869, | |
| "grad_norm": 4.723503589630127, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3509, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0019384179527324238, | |
| "grad_norm": 2.264803886413574, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.6557, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0020129724893759786, | |
| "grad_norm": 3.9745659828186035, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 0.8906, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0020129724893759786, | |
| "eval_loss": 1.2160564661026, | |
| "eval_runtime": 1835.8241, | |
| "eval_samples_per_second": 6.153, | |
| "eval_steps_per_second": 0.769, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0020875270260195334, | |
| "grad_norm": 5.033815860748291, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.0061, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.002162081562663088, | |
| "grad_norm": 5.012985706329346, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 1.169, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.002236636099306643, | |
| "grad_norm": 5.339277267456055, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.3307, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0023111906359501977, | |
| "grad_norm": 7.8841352462768555, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 1.495, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0023857451725937525, | |
| "grad_norm": 4.286492824554443, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.2115, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.002460299709237307, | |
| "grad_norm": 6.6110358238220215, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 1.8073, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0025348542458808617, | |
| "grad_norm": 6.618931293487549, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.6379, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0026094087825244165, | |
| "grad_norm": 3.5826964378356934, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 1.1726, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0026839633191679713, | |
| "grad_norm": 3.5384361743927, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.8394, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0026839633191679713, | |
| "eval_loss": 1.1397225856781006, | |
| "eval_runtime": 1835.5605, | |
| "eval_samples_per_second": 6.153, | |
| "eval_steps_per_second": 0.769, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.002758517855811526, | |
| "grad_norm": 4.037872791290283, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 1.1838, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.002833072392455081, | |
| "grad_norm": 3.277031183242798, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.8776, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0029076269290986357, | |
| "grad_norm": 3.395357608795166, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 0.8324, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0029821814657421905, | |
| "grad_norm": 3.6542036533355713, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0202, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0030567360023857452, | |
| "grad_norm": 4.9897356033325195, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 1.4792, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0031312905390293, | |
| "grad_norm": 5.673566818237305, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.5843, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.003205845075672855, | |
| "grad_norm": 3.129956007003784, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 0.5429, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0032803996123164096, | |
| "grad_norm": 4.75492000579834, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.1789, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0033549541489599644, | |
| "grad_norm": 3.616227626800537, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 1.1784, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0033549541489599644, | |
| "eval_loss": 1.0879795551300049, | |
| "eval_runtime": 1835.5507, | |
| "eval_samples_per_second": 6.153, | |
| "eval_steps_per_second": 0.769, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003429508685603519, | |
| "grad_norm": 3.7293524742126465, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.2445, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0035040632222470736, | |
| "grad_norm": 3.8073537349700928, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 1.0901, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0035786177588906284, | |
| "grad_norm": 2.3273308277130127, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.5605, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.003653172295534183, | |
| "grad_norm": 5.4879584312438965, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 1.2716, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.003727726832177738, | |
| "grad_norm": 3.2840213775634766, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.4598, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0038022813688212928, | |
| "grad_norm": 6.318856716156006, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 1.8285, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0038768359054648475, | |
| "grad_norm": 3.896543502807617, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.8851, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.003951390442108402, | |
| "grad_norm": 3.0004584789276123, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 0.7748, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.004025944978751957, | |
| "grad_norm": 3.7571120262145996, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.0713, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.004025944978751957, | |
| "eval_loss": 1.0387237071990967, | |
| "eval_runtime": 1834.8348, | |
| "eval_samples_per_second": 6.156, | |
| "eval_steps_per_second": 0.77, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0041004995153955115, | |
| "grad_norm": 3.714383363723755, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8249, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.004175054052039067, | |
| "grad_norm": 3.444979190826416, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.8833, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.004249608588682621, | |
| "grad_norm": 3.4714789390563965, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 1.0161, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.004324163125326176, | |
| "grad_norm": 3.413393974304199, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.7506, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.004398717661969731, | |
| "grad_norm": 4.324283599853516, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 0.689, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.004473272198613286, | |
| "grad_norm": 5.534282684326172, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.8864, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.00454782673525684, | |
| "grad_norm": 3.4391114711761475, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 0.8536, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0046223812719003955, | |
| "grad_norm": 4.6441450119018555, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.9308, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.00469693580854395, | |
| "grad_norm": 4.772485256195068, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 0.8085, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.00469693580854395, | |
| "eval_loss": 1.0256173610687256, | |
| "eval_runtime": 1835.156, | |
| "eval_samples_per_second": 6.155, | |
| "eval_steps_per_second": 0.769, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.004771490345187505, | |
| "grad_norm": 2.1971137523651123, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.4036, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0048460448818310594, | |
| "grad_norm": 2.6656343936920166, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.6526, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.004920599418474614, | |
| "grad_norm": 3.9616692066192627, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.813, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.004995153955118169, | |
| "grad_norm": 6.481931209564209, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 1.6251, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.005069708491761723, | |
| "grad_norm": 4.02551794052124, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.1398, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.005144263028405279, | |
| "grad_norm": 2.932755470275879, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 0.7208, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.005218817565048833, | |
| "grad_norm": 4.461419105529785, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.227, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.005293372101692388, | |
| "grad_norm": 3.890793561935425, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 1.1223, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0053679266383359426, | |
| "grad_norm": 2.5252115726470947, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.8403, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0053679266383359426, | |
| "eval_loss": 1.0127910375595093, | |
| "eval_runtime": 1835.2572, | |
| "eval_samples_per_second": 6.154, | |
| "eval_steps_per_second": 0.769, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.005442481174979498, | |
| "grad_norm": 3.003502607345581, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.9357, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.005517035711623052, | |
| "grad_norm": 3.790604829788208, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.0105, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.005591590248266607, | |
| "grad_norm": 2.7565271854400635, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.6162, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.005666144784910162, | |
| "grad_norm": 3.3704497814178467, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.9727, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.005740699321553717, | |
| "grad_norm": 2.8851423263549805, | |
| "learning_rate": 1.526708147705013e-05, | |
| "loss": 0.8882, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.005815253858197271, | |
| "grad_norm": 3.439664602279663, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.2121, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.005889808394840826, | |
| "grad_norm": 3.186978816986084, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 0.789, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.005964362931484381, | |
| "grad_norm": 3.047581911087036, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.6949, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.006038917468127935, | |
| "grad_norm": 4.091953277587891, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 1.3274, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.006038917468127935, | |
| "eval_loss": 0.9921898245811462, | |
| "eval_runtime": 1834.9348, | |
| "eval_samples_per_second": 6.156, | |
| "eval_steps_per_second": 0.77, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.0061134720047714905, | |
| "grad_norm": 2.8362438678741455, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.6543, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.006188026541415045, | |
| "grad_norm": 3.722740650177002, | |
| "learning_rate": 8.548121372247918e-06, | |
| "loss": 1.0046, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.0062625810780586, | |
| "grad_norm": 2.977998971939087, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.7849, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.0063371356147021544, | |
| "grad_norm": 3.894702196121216, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.0554, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.00641169015134571, | |
| "grad_norm": 3.460470199584961, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.7595, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.006486244687989264, | |
| "grad_norm": 4.5167155265808105, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 1.3252, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.006560799224632819, | |
| "grad_norm": 2.837597131729126, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.9637, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.006635353761276374, | |
| "grad_norm": 3.9109745025634766, | |
| "learning_rate": 3.6408072716606346e-06, | |
| "loss": 1.3869, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.006709908297919929, | |
| "grad_norm": 3.083695888519287, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.1615, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.006709908297919929, | |
| "eval_loss": 0.9879239797592163, | |
| "eval_runtime": 1835.3859, | |
| "eval_samples_per_second": 6.154, | |
| "eval_steps_per_second": 0.769, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.006784462834563483, | |
| "grad_norm": 3.445347547531128, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 1.2251, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.006859017371207038, | |
| "grad_norm": 4.91117525100708, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.2883, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.006933571907850593, | |
| "grad_norm": 4.425319671630859, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 1.7649, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.007008126444494147, | |
| "grad_norm": 3.255776882171631, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.8542, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.007082680981137702, | |
| "grad_norm": 6.230947017669678, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 1.0066, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.007157235517781257, | |
| "grad_norm": 2.7322230339050293, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.669, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.007231790054424812, | |
| "grad_norm": 2.8557915687561035, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 1.054, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.007306344591068366, | |
| "grad_norm": 3.587625741958618, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.292, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.0073808991277119216, | |
| "grad_norm": 3.0693485736846924, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 1.1408, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.0073808991277119216, | |
| "eval_loss": 0.9858196377754211, | |
| "eval_runtime": 1834.8841, | |
| "eval_samples_per_second": 6.156, | |
| "eval_steps_per_second": 0.77, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.007455453664355476, | |
| "grad_norm": 2.8233108520507812, | |
| "learning_rate": 0.0, | |
| "loss": 0.8195, | |
| "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": 1.0757365611626496e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |