| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009488116134541487, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.488116134541487e-05, | |
| "grad_norm": 1.1127322912216187, | |
| "learning_rate": 1e-05, | |
| "loss": 2.0138, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.488116134541487e-05, | |
| "eval_loss": 2.0451245307922363, | |
| "eval_runtime": 1080.7148, | |
| "eval_samples_per_second": 8.213, | |
| "eval_steps_per_second": 1.027, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00018976232269082974, | |
| "grad_norm": 1.2764439582824707, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2056, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00028464348403624463, | |
| "grad_norm": 1.4060295820236206, | |
| "learning_rate": 3e-05, | |
| "loss": 2.2988, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00037952464538165947, | |
| "grad_norm": 1.0847363471984863, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9099, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00047440580672707437, | |
| "grad_norm": 1.151689887046814, | |
| "learning_rate": 5e-05, | |
| "loss": 1.816, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005692869680724893, | |
| "grad_norm": 1.1197707653045654, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6664, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000664168129417904, | |
| "grad_norm": 1.1920640468597412, | |
| "learning_rate": 7e-05, | |
| "loss": 1.9155, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0007590492907633189, | |
| "grad_norm": 1.4924216270446777, | |
| "learning_rate": 8e-05, | |
| "loss": 2.128, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0008539304521087338, | |
| "grad_norm": 1.2173644304275513, | |
| "learning_rate": 9e-05, | |
| "loss": 1.9444, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008539304521087338, | |
| "eval_loss": 1.8280278444290161, | |
| "eval_runtime": 1081.2225, | |
| "eval_samples_per_second": 8.209, | |
| "eval_steps_per_second": 1.027, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009488116134541487, | |
| "grad_norm": 1.0821430683135986, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0432, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010436927747995636, | |
| "grad_norm": 1.1063179969787598, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 1.8818, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0011385739361449785, | |
| "grad_norm": 1.5359630584716797, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.8075, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0012334550974903932, | |
| "grad_norm": 1.4094569683074951, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.8503, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001328336258835808, | |
| "grad_norm": 1.3463197946548462, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.7538, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.001423217420181223, | |
| "grad_norm": 1.2225887775421143, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.78, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015180985815266379, | |
| "grad_norm": 1.2209497690200806, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.6999, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0016129797428720528, | |
| "grad_norm": 0.936830461025238, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 1.7268, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0017078609042174677, | |
| "grad_norm": 1.0267399549484253, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.7634, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0017078609042174677, | |
| "eval_loss": 1.6714221239089966, | |
| "eval_runtime": 1081.3968, | |
| "eval_samples_per_second": 8.208, | |
| "eval_steps_per_second": 1.026, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0018027420655628826, | |
| "grad_norm": 1.3456050157546997, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.9261, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0018976232269082975, | |
| "grad_norm": 0.94184410572052, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.5158, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001992504388253712, | |
| "grad_norm": 0.9470807909965515, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.4969, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0020873855495991273, | |
| "grad_norm": 0.8623135089874268, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.4251, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.002182266710944542, | |
| "grad_norm": 0.9363364577293396, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.6318, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002277147872289957, | |
| "grad_norm": 0.9525955319404602, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.4607, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0023720290336353717, | |
| "grad_norm": 1.178835153579712, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5853, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0024669101949807864, | |
| "grad_norm": 0.8710817694664001, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.534, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0025617913563262015, | |
| "grad_norm": 0.9336938858032227, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 1.6049, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0025617913563262015, | |
| "eval_loss": 1.6349345445632935, | |
| "eval_runtime": 1080.7897, | |
| "eval_samples_per_second": 8.213, | |
| "eval_steps_per_second": 1.027, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002656672517671616, | |
| "grad_norm": 1.0424524545669556, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.6354, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0027515536790170313, | |
| "grad_norm": 0.9360564351081848, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 1.515, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.002846434840362446, | |
| "grad_norm": 0.90949547290802, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.5625, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002941316001707861, | |
| "grad_norm": 0.8562958836555481, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 1.5617, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0030361971630532758, | |
| "grad_norm": 0.9327177405357361, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.6234, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0031310783243986904, | |
| "grad_norm": 0.9069679379463196, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 1.6158, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0032259594857441056, | |
| "grad_norm": 0.8303309679031372, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.6102, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0033208406470895202, | |
| "grad_norm": 0.8438217043876648, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 1.4309, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0034157218084349353, | |
| "grad_norm": 0.9067387580871582, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.6348, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0034157218084349353, | |
| "eval_loss": 1.6109086275100708, | |
| "eval_runtime": 1081.1883, | |
| "eval_samples_per_second": 8.209, | |
| "eval_steps_per_second": 1.027, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00351060296978035, | |
| "grad_norm": 0.9846649765968323, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 1.5791, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.003605484131125765, | |
| "grad_norm": 0.967066764831543, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.7268, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00370036529247118, | |
| "grad_norm": 0.7787414193153381, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 1.391, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.003795246453816595, | |
| "grad_norm": 0.9173020124435425, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.6492, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0038901276151620096, | |
| "grad_norm": 0.8385745882987976, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 1.5916, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.003985008776507424, | |
| "grad_norm": 0.8950688242912292, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.5115, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.004079889937852839, | |
| "grad_norm": 0.9280073046684265, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 1.5519, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0041747710991982545, | |
| "grad_norm": 0.9273409843444824, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.5792, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.004269652260543669, | |
| "grad_norm": 0.7953725457191467, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 1.6687, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004269652260543669, | |
| "eval_loss": 1.6001344919204712, | |
| "eval_runtime": 1081.2288, | |
| "eval_samples_per_second": 8.209, | |
| "eval_steps_per_second": 1.027, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004364533421889084, | |
| "grad_norm": 0.8611195087432861, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.7386, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.004459414583234499, | |
| "grad_norm": 0.9125109910964966, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 1.7137, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.004554295744579914, | |
| "grad_norm": 0.8732033967971802, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.5957, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.004649176905925328, | |
| "grad_norm": 0.9743337035179138, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 1.6143, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0047440580672707434, | |
| "grad_norm": 0.954450786113739, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.7307, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0048389392286161586, | |
| "grad_norm": 1.021529197692871, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 1.7053, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.004933820389961573, | |
| "grad_norm": 0.851039707660675, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.5005, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.005028701551306988, | |
| "grad_norm": 1.0764281749725342, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 1.627, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.005123582712652403, | |
| "grad_norm": 0.9203549027442932, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.5764, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.005123582712652403, | |
| "eval_loss": 1.5899285078048706, | |
| "eval_runtime": 1081.6025, | |
| "eval_samples_per_second": 8.206, | |
| "eval_steps_per_second": 1.026, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.005218463873997818, | |
| "grad_norm": 0.9476063251495361, | |
| "learning_rate": 5e-05, | |
| "loss": 1.472, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.005313345035343232, | |
| "grad_norm": 0.9526840448379517, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.5259, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0054082261966886475, | |
| "grad_norm": 0.9323434233665466, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 1.691, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.005503107358034063, | |
| "grad_norm": 0.8605644702911377, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.4195, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.005597988519379477, | |
| "grad_norm": 0.9038230180740356, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 1.6862, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.005692869680724892, | |
| "grad_norm": 0.9379934668540955, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.5482, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.005787750842070307, | |
| "grad_norm": 0.7980185747146606, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 1.4809, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.005882632003415722, | |
| "grad_norm": 0.8793210387229919, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.682, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.005977513164761136, | |
| "grad_norm": 0.9104472398757935, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 1.6596, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.005977513164761136, | |
| "eval_loss": 1.5829646587371826, | |
| "eval_runtime": 1082.0614, | |
| "eval_samples_per_second": 8.203, | |
| "eval_steps_per_second": 1.026, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0060723943261065515, | |
| "grad_norm": 0.8857439756393433, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.5108, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.006167275487451967, | |
| "grad_norm": 0.9509901404380798, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 1.6546, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.006262156648797381, | |
| "grad_norm": 0.9270310997962952, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.4696, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.006357037810142796, | |
| "grad_norm": 0.8640135526657104, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 1.4747, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.006451918971488211, | |
| "grad_norm": 0.755232572555542, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.6301, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.006546800132833626, | |
| "grad_norm": 1.091976284980774, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 1.8396, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0066416812941790405, | |
| "grad_norm": 0.8799819350242615, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.665, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.006736562455524456, | |
| "grad_norm": 0.8526880741119385, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 1.4676, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.006831443616869871, | |
| "grad_norm": 0.9971675276756287, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.9508, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.006831443616869871, | |
| "eval_loss": 1.5761239528656006, | |
| "eval_runtime": 1083.8794, | |
| "eval_samples_per_second": 8.189, | |
| "eval_steps_per_second": 1.024, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.006926324778215285, | |
| "grad_norm": 0.9360523819923401, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 1.6183, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.0070212059395607, | |
| "grad_norm": 0.8562299013137817, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.4737, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.007116087100906115, | |
| "grad_norm": 0.8478887677192688, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 1.414, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.00721096826225153, | |
| "grad_norm": 0.9999253153800964, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.7122, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.0073058494235969445, | |
| "grad_norm": 0.8223520517349243, | |
| "learning_rate": 1.526708147705013e-05, | |
| "loss": 1.5232, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.00740073058494236, | |
| "grad_norm": 0.8604589104652405, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.5891, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.007495611746287775, | |
| "grad_norm": 0.8070433735847473, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 1.5095, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.00759049290763319, | |
| "grad_norm": 1.0023198127746582, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.7971, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.007685374068978604, | |
| "grad_norm": 0.8673124313354492, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 1.6079, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.007685374068978604, | |
| "eval_loss": 1.572432518005371, | |
| "eval_runtime": 1086.0078, | |
| "eval_samples_per_second": 8.173, | |
| "eval_steps_per_second": 1.022, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.007780255230324019, | |
| "grad_norm": 0.9290028810501099, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.6508, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.007875136391669434, | |
| "grad_norm": 0.7514159679412842, | |
| "learning_rate": 8.548121372247918e-06, | |
| "loss": 1.4104, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.007970017553014849, | |
| "grad_norm": 0.8747042417526245, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.7355, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.008064898714360265, | |
| "grad_norm": 0.8969379663467407, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.6637, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.008159779875705679, | |
| "grad_norm": 0.8571388721466064, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.5059, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.008254661037051093, | |
| "grad_norm": 0.8895001411437988, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 1.5245, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.008349542198396509, | |
| "grad_norm": 0.8412717580795288, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.7979, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.008444423359741923, | |
| "grad_norm": 0.8215514421463013, | |
| "learning_rate": 3.6408072716606346e-06, | |
| "loss": 1.7124, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.008539304521087338, | |
| "grad_norm": 0.8653639554977417, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.4583, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.008539304521087338, | |
| "eval_loss": 1.5709314346313477, | |
| "eval_runtime": 1083.6402, | |
| "eval_samples_per_second": 8.191, | |
| "eval_steps_per_second": 1.024, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.008634185682432753, | |
| "grad_norm": 0.8609132170677185, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 1.4401, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.008729066843778168, | |
| "grad_norm": 0.9032567143440247, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.5056, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.008823948005123582, | |
| "grad_norm": 0.8973141312599182, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 1.3364, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.008918829166468998, | |
| "grad_norm": 0.8633498549461365, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.4452, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.009013710327814412, | |
| "grad_norm": 0.8059698939323425, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 1.2905, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.009108591489159828, | |
| "grad_norm": 0.9418469667434692, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.5204, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.009203472650505242, | |
| "grad_norm": 0.8801723718643188, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 1.6024, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.009298353811850657, | |
| "grad_norm": 0.8468022346496582, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.5076, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.009393234973196073, | |
| "grad_norm": 0.8482431173324585, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 1.3525, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.009393234973196073, | |
| "eval_loss": 1.570597529411316, | |
| "eval_runtime": 1082.5847, | |
| "eval_samples_per_second": 8.199, | |
| "eval_steps_per_second": 1.025, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.009488116134541487, | |
| "grad_norm": 0.8902725577354431, | |
| "learning_rate": 0.0, | |
| "loss": 1.4937, | |
| "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": 7.41887686213632e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |