| { | |
| "best_metric": 0.19360065460205078, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.023736055067647758, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00047472110135295516, | |
| "grad_norm": 0.4688243269920349, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6124, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00047472110135295516, | |
| "eval_loss": 1.0957424640655518, | |
| "eval_runtime": 194.003, | |
| "eval_samples_per_second": 18.288, | |
| "eval_steps_per_second": 2.289, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009494422027059103, | |
| "grad_norm": 0.6601790189743042, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8464, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014241633040588653, | |
| "grad_norm": 0.7652206420898438, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 0.965, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018988844054118206, | |
| "grad_norm": 0.850256085395813, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.6595, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0023736055067647755, | |
| "grad_norm": 1.034886360168457, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.4754, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0028483266081177306, | |
| "grad_norm": 0.9273011684417725, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.3089, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003323047709470686, | |
| "grad_norm": 1.7200816869735718, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.3123, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0037977688108236413, | |
| "grad_norm": 0.935492753982544, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.2688, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004272489912176596, | |
| "grad_norm": 0.5538306832313538, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.2015, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004747211013529551, | |
| "grad_norm": 0.5412841439247131, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.2237, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005221932114882507, | |
| "grad_norm": 0.9080474972724915, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.1714, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005696653216235461, | |
| "grad_norm": 0.5930872559547424, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.25, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006171374317588417, | |
| "grad_norm": 0.8284171223640442, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.3136, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006646095418941372, | |
| "grad_norm": 0.541205883026123, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.2078, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007120816520294327, | |
| "grad_norm": 0.3955840468406677, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.1586, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0075955376216472826, | |
| "grad_norm": 0.48258212208747864, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.2005, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008070258723000238, | |
| "grad_norm": 0.39275145530700684, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.1783, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008544979824353193, | |
| "grad_norm": 0.3785333037376404, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.1541, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009019700925706147, | |
| "grad_norm": 0.594031035900116, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.2355, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009494422027059102, | |
| "grad_norm": 0.4767218232154846, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.2854, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009969143128412059, | |
| "grad_norm": 0.4265936315059662, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.2417, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010443864229765013, | |
| "grad_norm": 0.37528008222579956, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.1375, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010918585331117968, | |
| "grad_norm": 0.47274863719940186, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.2293, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011393306432470923, | |
| "grad_norm": 0.5729778409004211, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.2553, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011868027533823879, | |
| "grad_norm": 0.5274404287338257, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.2306, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011868027533823879, | |
| "eval_loss": 0.19939672946929932, | |
| "eval_runtime": 194.6731, | |
| "eval_samples_per_second": 18.225, | |
| "eval_steps_per_second": 2.281, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012342748635176834, | |
| "grad_norm": 0.3555451035499573, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1971, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012817469736529788, | |
| "grad_norm": 0.34671762585639954, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.1603, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013292190837882745, | |
| "grad_norm": 0.20731107890605927, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.1453, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0137669119392357, | |
| "grad_norm": 0.3372092545032501, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.2641, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014241633040588654, | |
| "grad_norm": 0.32797935605049133, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.1899, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014716354141941609, | |
| "grad_norm": 0.3118788003921509, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.1824, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.015191075243294565, | |
| "grad_norm": 0.366529643535614, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.1616, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.015665796344647518, | |
| "grad_norm": 0.46039462089538574, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.2017, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.016140517446000476, | |
| "grad_norm": 0.3713008165359497, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.1935, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01661523854735343, | |
| "grad_norm": 0.38472941517829895, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.2168, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.017089959648706386, | |
| "grad_norm": 0.44644981622695923, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.2307, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01756468075005934, | |
| "grad_norm": 0.5147837996482849, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.251, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.018039401851412295, | |
| "grad_norm": 0.3486250340938568, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.176, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01851412295276525, | |
| "grad_norm": 0.3016928732395172, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.2325, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.018988844054118204, | |
| "grad_norm": 0.3231501877307892, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.2517, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019463565155471162, | |
| "grad_norm": 0.325752854347229, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.1717, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.019938286256824117, | |
| "grad_norm": 0.2623179852962494, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.1396, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02041300735817707, | |
| "grad_norm": 0.3840673565864563, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.2494, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.020887728459530026, | |
| "grad_norm": 0.4204588234424591, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.2365, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02136244956088298, | |
| "grad_norm": 0.29817184805870056, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.208, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.021837170662235936, | |
| "grad_norm": 0.4304487705230713, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.2959, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02231189176358889, | |
| "grad_norm": 0.361851304769516, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.136, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.022786612864941845, | |
| "grad_norm": 0.46964964270591736, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.2349, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.023261333966294803, | |
| "grad_norm": 0.6576246619224548, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.272, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.023736055067647758, | |
| "grad_norm": 0.5070633292198181, | |
| "learning_rate": 0.0, | |
| "loss": 0.1968, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.023736055067647758, | |
| "eval_loss": 0.19360065460205078, | |
| "eval_runtime": 194.3616, | |
| "eval_samples_per_second": 18.255, | |
| "eval_steps_per_second": 2.284, | |
| "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": 1, | |
| "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": 2.796154706198528e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |