| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00621272365805169, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.212723658051689e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.212723658051689e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 379.2078, | |
| "eval_samples_per_second": 35.746, | |
| "eval_steps_per_second": 4.47, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012425447316103378, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001863817097415507, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00024850894632206757, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003106361829025845, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003727634194831014, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004348906560636183, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0004970178926441351, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005591451292246521, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005591451292246521, | |
| "eval_loss": NaN, | |
| "eval_runtime": 378.6602, | |
| "eval_samples_per_second": 35.797, | |
| "eval_steps_per_second": 4.476, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000621272365805169, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006833996023856859, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0007455268389662028, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0008076540755467197, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0008697813121272366, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0009319085487077535, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009940357852882703, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0010561630218687873, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0011182902584493041, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0011182902584493041, | |
| "eval_loss": NaN, | |
| "eval_runtime": 379.0902, | |
| "eval_samples_per_second": 35.757, | |
| "eval_steps_per_second": 4.471, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001180417495029821, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.001242544731610338, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013046719681908548, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0013667992047713719, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0014289264413518887, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0014910536779324055, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0015531809145129226, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0016153081510934394, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0016774353876739562, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0016774353876739562, | |
| "eval_loss": NaN, | |
| "eval_runtime": 378.755, | |
| "eval_samples_per_second": 35.788, | |
| "eval_steps_per_second": 4.475, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0017395626242544733, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00180168986083499, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.001863817097415507, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001925944333996024, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0019880715705765406, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.002050198807157058, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0021123260437375746, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0021744532803180915, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0022365805168986083, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0022365805168986083, | |
| "eval_loss": NaN, | |
| "eval_runtime": 378.6339, | |
| "eval_samples_per_second": 35.8, | |
| "eval_steps_per_second": 4.477, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.002298707753479125, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.002360834990059642, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.002422962226640159, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.002485089463220676, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002547216699801193, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0026093439363817097, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0026714711729622265, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0027335984095427437, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0027957256461232606, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0027957256461232606, | |
| "eval_loss": NaN, | |
| "eval_runtime": 379.5125, | |
| "eval_samples_per_second": 35.717, | |
| "eval_steps_per_second": 4.466, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0028578528827037774, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0029199801192842942, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.002982107355864811, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.003044234592445328, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.003106361829025845, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003168489065606362, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0032306163021868788, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0032927435387673956, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0033548707753479124, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0033548707753479124, | |
| "eval_loss": NaN, | |
| "eval_runtime": 379.2175, | |
| "eval_samples_per_second": 35.745, | |
| "eval_steps_per_second": 4.47, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0034169980119284292, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0034791252485089465, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0035412524850894633, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.00360337972166998, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.003665506958250497, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.003727634194831014, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0037897614314115306, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.003851888667992048, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.003914015904572564, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.003914015904572564, | |
| "eval_loss": NaN, | |
| "eval_runtime": 378.879, | |
| "eval_samples_per_second": 35.777, | |
| "eval_steps_per_second": 4.474, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.003976143141153081, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.004038270377733599, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.004100397614314116, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0041625248508946324, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.004224652087475149, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.004286779324055666, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.004348906560636183, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0044110337972167, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0044731610337972166, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0044731610337972166, | |
| "eval_loss": NaN, | |
| "eval_runtime": 378.6574, | |
| "eval_samples_per_second": 35.798, | |
| "eval_steps_per_second": 4.476, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.004535288270377733, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.00459741550695825, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.004659542743538767, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.004721669980119284, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.0047837972166998016, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.526708147705013e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.004845924453280318, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.004908051689860835, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.004970178926441352, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.005032306163021869, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.005032306163021869, | |
| "eval_loss": NaN, | |
| "eval_runtime": 378.4891, | |
| "eval_samples_per_second": 35.813, | |
| "eval_steps_per_second": 4.478, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.005094433399602386, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.0051565606361829025, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.548121372247918e-06, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.005218687872763419, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.005280815109343936, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.005342942345924453, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.00540506958250497, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.0054671968190854875, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.005529324055666004, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6408072716606346e-06, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.005591451292246521, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.005591451292246521, | |
| "eval_loss": NaN, | |
| "eval_runtime": 378.3851, | |
| "eval_samples_per_second": 35.823, | |
| "eval_steps_per_second": 4.48, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.005653578528827038, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.005715705765407555, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.005777833001988072, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.0058399602385685884, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.005902087475149105, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.005964214711729622, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.006026341948310139, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.006088469184890656, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.0061505964214711726, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.0061505964214711726, | |
| "eval_loss": NaN, | |
| "eval_runtime": 378.4304, | |
| "eval_samples_per_second": 35.819, | |
| "eval_steps_per_second": 4.479, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.00621272365805169, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "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": 2184077692108800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |