| { | |
| "best_metric": 1.7020063400268555, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.56657223796034, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0113314447592068, | |
| "grad_norm": 0.33666571974754333, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7268, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0113314447592068, | |
| "eval_loss": 1.8638567924499512, | |
| "eval_runtime": 1.406, | |
| "eval_samples_per_second": 105.975, | |
| "eval_steps_per_second": 13.514, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0226628895184136, | |
| "grad_norm": 0.34872931241989136, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7041, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0339943342776204, | |
| "grad_norm": 0.32515448331832886, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6899, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0453257790368272, | |
| "grad_norm": 0.39392638206481934, | |
| "learning_rate": 8e-05, | |
| "loss": 1.771, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.056657223796033995, | |
| "grad_norm": 0.32078537344932556, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7116, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0679886685552408, | |
| "grad_norm": 0.3297460675239563, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.7778, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07932011331444759, | |
| "grad_norm": 0.2444680780172348, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.6437, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0906515580736544, | |
| "grad_norm": 0.25901690125465393, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.7814, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10198300283286119, | |
| "grad_norm": 0.2574293911457062, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.76, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11331444759206799, | |
| "grad_norm": 0.22195817530155182, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.7619, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12464589235127478, | |
| "grad_norm": 0.25635820627212524, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.7202, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1359773371104816, | |
| "grad_norm": 0.25191575288772583, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.7746, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14730878186968838, | |
| "grad_norm": 0.2583252489566803, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.7015, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15864022662889518, | |
| "grad_norm": 0.2822646498680115, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.7986, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16997167138810199, | |
| "grad_norm": 0.27486222982406616, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.7921, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1813031161473088, | |
| "grad_norm": 0.2897486090660095, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.68, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19263456090651557, | |
| "grad_norm": 0.2819582223892212, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.9592, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20396600566572237, | |
| "grad_norm": 0.3186541199684143, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.8444, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.21529745042492918, | |
| "grad_norm": 0.32152897119522095, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.9009, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.22662889518413598, | |
| "grad_norm": 0.33151161670684814, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.8928, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23796033994334279, | |
| "grad_norm": 0.33403679728507996, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.9462, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24929178470254956, | |
| "grad_norm": 0.37862664461135864, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.8694, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.26062322946175637, | |
| "grad_norm": 0.20253029465675354, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.6101, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2719546742209632, | |
| "grad_norm": 0.18948052823543549, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.6217, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.28328611898017, | |
| "grad_norm": 0.19364707171916962, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.5635, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.28328611898017, | |
| "eval_loss": 1.7303435802459717, | |
| "eval_runtime": 1.3795, | |
| "eval_samples_per_second": 108.007, | |
| "eval_steps_per_second": 13.773, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.29461756373937675, | |
| "grad_norm": 0.2151980847120285, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.7348, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3059490084985836, | |
| "grad_norm": 0.20931684970855713, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.5753, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.31728045325779036, | |
| "grad_norm": 0.19959765672683716, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.5703, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3286118980169972, | |
| "grad_norm": 0.20375734567642212, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.5869, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.33994334277620397, | |
| "grad_norm": 0.2205701470375061, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.6535, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35127478753541075, | |
| "grad_norm": 0.24109084904193878, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.7494, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3626062322946176, | |
| "grad_norm": 0.1876843124628067, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.651, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.37393767705382436, | |
| "grad_norm": 0.20250895619392395, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.6442, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.38526912181303113, | |
| "grad_norm": 0.20786873996257782, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.6759, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.39660056657223797, | |
| "grad_norm": 0.20187856256961823, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.7009, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.40793201133144474, | |
| "grad_norm": 0.23279821872711182, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.649, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4192634560906516, | |
| "grad_norm": 0.2545683681964874, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.6021, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.43059490084985835, | |
| "grad_norm": 0.2432079017162323, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.771, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.44192634560906513, | |
| "grad_norm": 0.2748010754585266, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.8674, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.45325779036827196, | |
| "grad_norm": 0.2268821895122528, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.8442, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.46458923512747874, | |
| "grad_norm": 0.28976666927337646, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.7986, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.47592067988668557, | |
| "grad_norm": 0.2901630401611328, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.7726, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.48725212464589235, | |
| "grad_norm": 0.34646856784820557, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.7965, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4985835694050991, | |
| "grad_norm": 0.372428297996521, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.7613, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.509915014164306, | |
| "grad_norm": 0.17116321623325348, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.5638, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5212464589235127, | |
| "grad_norm": 0.1613224297761917, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.4856, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5325779036827195, | |
| "grad_norm": 0.1517619788646698, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.661, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5439093484419264, | |
| "grad_norm": 0.19363200664520264, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.6942, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5552407932011332, | |
| "grad_norm": 0.18895885348320007, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.5129, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.56657223796034, | |
| "grad_norm": 0.20351547002792358, | |
| "learning_rate": 0.0, | |
| "loss": 1.5714, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.56657223796034, | |
| "eval_loss": 1.7020063400268555, | |
| "eval_runtime": 1.3844, | |
| "eval_samples_per_second": 107.631, | |
| "eval_steps_per_second": 13.725, | |
| "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": 1236088022630400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |