| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06183017312448475, | |
| "eval_steps": 9, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008244023083264633, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008244023083264633, | |
| "eval_loss": NaN, | |
| "eval_runtime": 115.2447, | |
| "eval_samples_per_second": 8.868, | |
| "eval_steps_per_second": 1.111, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016488046166529267, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00247320692497939, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0032976092333058533, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004122011541632316, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00494641384995878, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005770816158285243, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006595218466611707, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00741962077493817, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00741962077493817, | |
| "eval_loss": NaN, | |
| "eval_runtime": 113.7332, | |
| "eval_samples_per_second": 8.986, | |
| "eval_steps_per_second": 1.125, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008244023083264633, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009068425391591096, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00989282769991756, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010717230008244023, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011541632316570486, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01236603462489695, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013190436933223413, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014014839241549877, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01483924154987634, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01483924154987634, | |
| "eval_loss": NaN, | |
| "eval_runtime": 113.6785, | |
| "eval_samples_per_second": 8.99, | |
| "eval_steps_per_second": 1.126, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015663643858202802, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.016488046166529265, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01731244847485573, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018136850783182192, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.018961253091508656, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01978565539983512, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020610057708161583, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.021434460016488046, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02225886232481451, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02225886232481451, | |
| "eval_loss": NaN, | |
| "eval_runtime": 113.6706, | |
| "eval_samples_per_second": 8.991, | |
| "eval_steps_per_second": 1.126, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.023083264633140973, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.023907666941467436, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0247320692497939, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.025556471558120363, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.026380873866446827, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02720527617477329, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.028029678483099753, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.028854080791426217, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02967848309975268, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02967848309975268, | |
| "eval_loss": NaN, | |
| "eval_runtime": 113.6439, | |
| "eval_samples_per_second": 8.993, | |
| "eval_steps_per_second": 1.126, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.030502885408079144, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.031327287716405604, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03215169002473207, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03297609233305853, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.033800494641384994, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03462489694971146, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03544929925803792, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.036273701566364384, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03709810387469085, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03709810387469085, | |
| "eval_loss": NaN, | |
| "eval_runtime": 113.6499, | |
| "eval_samples_per_second": 8.993, | |
| "eval_steps_per_second": 1.126, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03792250618301731, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.038746908491343775, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03957131079967024, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0403957131079967, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.041220115416323165, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04204451772464963, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.04286892003297609, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.043693322341302555, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.04451772464962902, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.04451772464962902, | |
| "eval_loss": NaN, | |
| "eval_runtime": 113.6769, | |
| "eval_samples_per_second": 8.99, | |
| "eval_steps_per_second": 1.126, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.04534212695795548, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.046166529266281946, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.04699093157460841, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.04781533388293487, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.048639736191261336, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0494641384995878, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05028854080791426, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.051112943116240726, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.05193734542456719, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.05193734542456719, | |
| "eval_loss": NaN, | |
| "eval_runtime": 113.673, | |
| "eval_samples_per_second": 8.991, | |
| "eval_steps_per_second": 1.126, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.05276174773289365, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.05358615004122012, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.05441055234954658, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.055234954657873044, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.05605935696619951, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.05688375927452597, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.057708161582852434, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0585325638911789, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.05935696619950536, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.05935696619950536, | |
| "eval_loss": NaN, | |
| "eval_runtime": 113.6621, | |
| "eval_samples_per_second": 8.992, | |
| "eval_steps_per_second": 1.126, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.060181368507831824, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.06100577081615829, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.06183017312448475, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.601248990881382e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |