| { | |
| "best_metric": 1.892201542854309, | |
| "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": 3.1157164573669434, | |
| "learning_rate": 2e-05, | |
| "loss": 2.8364, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000260061114361875, | |
| "eval_loss": 2.9575929641723633, | |
| "eval_runtime": 253.7379, | |
| "eval_samples_per_second": 25.526, | |
| "eval_steps_per_second": 3.192, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00052012222872375, | |
| "grad_norm": 3.6684656143188477, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8763, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007801833430856252, | |
| "grad_norm": 3.1949148178100586, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8521, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010402444574475, | |
| "grad_norm": 2.585069179534912, | |
| "learning_rate": 8e-05, | |
| "loss": 2.7281, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001300305571809375, | |
| "grad_norm": 2.0279574394226074, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5272, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015603666861712503, | |
| "grad_norm": 1.972197413444519, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.4464, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018204278005331254, | |
| "grad_norm": 2.5754523277282715, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.1082, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002080488914895, | |
| "grad_norm": 2.0509142875671387, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.9971, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0023405500292568754, | |
| "grad_norm": 1.441322922706604, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.0313, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00260061114361875, | |
| "grad_norm": 1.6756833791732788, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.9728, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028606722579806254, | |
| "grad_norm": 1.6278423070907593, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.9946, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0031207333723425007, | |
| "grad_norm": 1.5035661458969116, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.046, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0033807944867043755, | |
| "grad_norm": 1.555298924446106, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 2.0479, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0036408556010662507, | |
| "grad_norm": 1.3091228008270264, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.9799, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0039009167154281255, | |
| "grad_norm": 1.1428215503692627, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.0745, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00416097782979, | |
| "grad_norm": 1.1141544580459595, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 2.0589, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004421038944151876, | |
| "grad_norm": 1.069549798965454, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.9303, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004681100058513751, | |
| "grad_norm": 1.1322650909423828, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 2.0219, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004941161172875626, | |
| "grad_norm": 1.2464029788970947, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.8893, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0052012222872375, | |
| "grad_norm": 1.3762235641479492, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.9763, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005461283401599376, | |
| "grad_norm": 1.172607660293579, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.9077, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005721344515961251, | |
| "grad_norm": 1.1587644815444946, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.935, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005981405630323126, | |
| "grad_norm": 1.1821650266647339, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.9665, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006241466744685001, | |
| "grad_norm": 1.1206787824630737, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 2.0594, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006501527859046876, | |
| "grad_norm": 1.0875933170318604, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.915, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006501527859046876, | |
| "eval_loss": 1.9164689779281616, | |
| "eval_runtime": 255.7837, | |
| "eval_samples_per_second": 25.322, | |
| "eval_steps_per_second": 3.167, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006761588973408751, | |
| "grad_norm": 1.0809967517852783, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.8476, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007021650087770626, | |
| "grad_norm": 1.1192842721939087, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.9731, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0072817112021325014, | |
| "grad_norm": 1.0255992412567139, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.8292, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007541772316494376, | |
| "grad_norm": 0.9532380104064941, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.8355, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007801833430856251, | |
| "grad_norm": 1.0013816356658936, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.8524, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008061894545218126, | |
| "grad_norm": 1.1652249097824097, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.781, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.00832195565958, | |
| "grad_norm": 0.9645384550094604, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.8568, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008582016773941877, | |
| "grad_norm": 0.9883855581283569, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.8224, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.008842077888303752, | |
| "grad_norm": 1.0957045555114746, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.9487, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009102139002665627, | |
| "grad_norm": 1.1185188293457031, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.0761, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009362200117027502, | |
| "grad_norm": 1.1080483198165894, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 2.1764, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009622261231389376, | |
| "grad_norm": 0.9495072960853577, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.7352, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009882322345751251, | |
| "grad_norm": 0.9627780318260193, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.9256, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010142383460113126, | |
| "grad_norm": 1.0152862071990967, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 2.001, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010402444574475, | |
| "grad_norm": 1.0531724691390991, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.7968, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010662505688836877, | |
| "grad_norm": 1.1137406826019287, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.9572, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.010922566803198752, | |
| "grad_norm": 1.023791790008545, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.9136, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011182627917560627, | |
| "grad_norm": 1.0599788427352905, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.9699, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011442689031922502, | |
| "grad_norm": 1.0731327533721924, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.9089, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.011702750146284377, | |
| "grad_norm": 0.9599363803863525, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.8697, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011962811260646251, | |
| "grad_norm": 0.9762247800827026, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.7315, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.012222872375008126, | |
| "grad_norm": 1.0653477907180786, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.8521, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.012482933489370003, | |
| "grad_norm": 1.0200570821762085, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.8043, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.012742994603731878, | |
| "grad_norm": 1.0970922708511353, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.9815, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013003055718093752, | |
| "grad_norm": 1.1692508459091187, | |
| "learning_rate": 0.0, | |
| "loss": 2.2081, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013003055718093752, | |
| "eval_loss": 1.892201542854309, | |
| "eval_runtime": 255.2129, | |
| "eval_samples_per_second": 25.379, | |
| "eval_steps_per_second": 3.174, | |
| "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 | |
| } | |