| { | |
| "best_metric": 1.8941960334777832, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.013003055718093752, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000260061114361875, | |
| "grad_norm": 3.172050714492798, | |
| "learning_rate": 2e-05, | |
| "loss": 2.8364, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000260061114361875, | |
| "eval_loss": 2.9575929641723633, | |
| "eval_runtime": 253.1376, | |
| "eval_samples_per_second": 25.587, | |
| "eval_steps_per_second": 3.2, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00052012222872375, | |
| "grad_norm": 3.724369764328003, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8763, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007801833430856252, | |
| "grad_norm": 3.1975831985473633, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8505, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010402444574475, | |
| "grad_norm": 2.601447105407715, | |
| "learning_rate": 8e-05, | |
| "loss": 2.7265, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001300305571809375, | |
| "grad_norm": 2.0248212814331055, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5241, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015603666861712503, | |
| "grad_norm": 1.9826959371566772, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.4461, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018204278005331254, | |
| "grad_norm": 2.591937780380249, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.1087, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002080488914895, | |
| "grad_norm": 2.0636239051818848, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.9973, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0023405500292568754, | |
| "grad_norm": 1.4487528800964355, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.0326, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00260061114361875, | |
| "grad_norm": 1.6822072267532349, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.9732, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028606722579806254, | |
| "grad_norm": 1.656015396118164, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.997, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0031207333723425007, | |
| "grad_norm": 1.5163209438323975, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.0448, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0033807944867043755, | |
| "grad_norm": 1.573835849761963, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 2.0485, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0036408556010662507, | |
| "grad_norm": 1.3351378440856934, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.9796, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0039009167154281255, | |
| "grad_norm": 1.15450918674469, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.0755, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00416097782979, | |
| "grad_norm": 1.1326713562011719, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 2.06, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004421038944151876, | |
| "grad_norm": 1.0901868343353271, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.931, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004681100058513751, | |
| "grad_norm": 1.1588667631149292, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 2.0221, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004941161172875626, | |
| "grad_norm": 1.235337495803833, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.8875, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0052012222872375, | |
| "grad_norm": 1.4204732179641724, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.9751, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005461283401599376, | |
| "grad_norm": 1.1773627996444702, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.9032, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005721344515961251, | |
| "grad_norm": 1.1725674867630005, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.936, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005981405630323126, | |
| "grad_norm": 1.2049524784088135, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.9652, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006241466744685001, | |
| "grad_norm": 1.6520092487335205, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 2.0632, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006501527859046876, | |
| "grad_norm": 1.2138807773590088, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.9161, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006501527859046876, | |
| "eval_loss": 1.918581485748291, | |
| "eval_runtime": 255.1652, | |
| "eval_samples_per_second": 25.384, | |
| "eval_steps_per_second": 3.174, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006761588973408751, | |
| "grad_norm": 1.1087353229522705, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.855, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007021650087770626, | |
| "grad_norm": 1.423514485359192, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.9699, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0072817112021325014, | |
| "grad_norm": 1.0818465948104858, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.834, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007541772316494376, | |
| "grad_norm": 1.0367424488067627, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.8464, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007801833430856251, | |
| "grad_norm": 1.0133615732192993, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.8544, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008061894545218126, | |
| "grad_norm": 1.3788729906082153, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.7787, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.00832195565958, | |
| "grad_norm": 1.0124037265777588, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.8585, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008582016773941877, | |
| "grad_norm": 2.421003818511963, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.8256, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.008842077888303752, | |
| "grad_norm": 1.1224663257598877, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.9481, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009102139002665627, | |
| "grad_norm": 1.1296459436416626, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.0793, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009362200117027502, | |
| "grad_norm": 1.1591365337371826, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 2.1769, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009622261231389376, | |
| "grad_norm": 0.9858690500259399, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.735, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009882322345751251, | |
| "grad_norm": 0.973463237285614, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.9322, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010142383460113126, | |
| "grad_norm": 1.051450490951538, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 2.008, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010402444574475, | |
| "grad_norm": 1.0749822854995728, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.7987, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010662505688836877, | |
| "grad_norm": 1.1620749235153198, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.96, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.010922566803198752, | |
| "grad_norm": 1.0434108972549438, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.9113, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011182627917560627, | |
| "grad_norm": 1.1357665061950684, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.9717, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011442689031922502, | |
| "grad_norm": 1.258142352104187, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.9138, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.011702750146284377, | |
| "grad_norm": 0.9736027121543884, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.8724, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011962811260646251, | |
| "grad_norm": 1.0701547861099243, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.733, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.012222872375008126, | |
| "grad_norm": 1.0976836681365967, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.8591, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.012482933489370003, | |
| "grad_norm": 1.0743271112442017, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.8, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.012742994603731878, | |
| "grad_norm": 1.1132044792175293, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.9799, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013003055718093752, | |
| "grad_norm": 1.1801347732543945, | |
| "learning_rate": 0.0, | |
| "loss": 2.2087, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013003055718093752, | |
| "eval_loss": 1.8941960334777832, | |
| "eval_runtime": 254.6608, | |
| "eval_samples_per_second": 25.434, | |
| "eval_steps_per_second": 3.181, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.82785320606761e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |