| { | |
| "best_metric": 7.017041206359863, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.011029614514972702, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00022059229029945402, | |
| "grad_norm": 2.4293482303619385, | |
| "learning_rate": 0.0001, | |
| "loss": 7.7331, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00022059229029945402, | |
| "eval_loss": 7.659153461456299, | |
| "eval_runtime": 20.0543, | |
| "eval_samples_per_second": 95.192, | |
| "eval_steps_per_second": 47.621, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00044118458059890804, | |
| "grad_norm": 2.4448964595794678, | |
| "learning_rate": 0.0002, | |
| "loss": 7.8817, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006617768708983621, | |
| "grad_norm": 2.475456953048706, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 7.5521, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008823691611978161, | |
| "grad_norm": 2.3668322563171387, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 7.3641, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00110296145149727, | |
| "grad_norm": 2.320056200027466, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 7.76, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013235537417967242, | |
| "grad_norm": 2.2553532123565674, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 7.1233, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015441460320961783, | |
| "grad_norm": 2.367339611053467, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 7.2181, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0017647383223956322, | |
| "grad_norm": 2.3431711196899414, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 7.353, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0019853306126950865, | |
| "grad_norm": 2.190365791320801, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 6.9617, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00220592290299454, | |
| "grad_norm": 2.226897954940796, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 6.9584, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0024265151932939943, | |
| "grad_norm": 2.4230480194091797, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 7.5979, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0026471074835934484, | |
| "grad_norm": 2.0584659576416016, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 6.6134, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0028676997738929025, | |
| "grad_norm": 2.11950945854187, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 6.9112, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0030882920641923566, | |
| "grad_norm": 2.642418146133423, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 7.426, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0033088843544918107, | |
| "grad_norm": 2.08109974861145, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 6.7795, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0035294766447912644, | |
| "grad_norm": 2.413881540298462, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 7.1208, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0037500689350907185, | |
| "grad_norm": 2.323194980621338, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 6.6449, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003970661225390173, | |
| "grad_norm": 2.729285717010498, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 7.2977, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004191253515689626, | |
| "grad_norm": 2.5769810676574707, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 7.3119, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00441184580598908, | |
| "grad_norm": 2.8009188175201416, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 7.187, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0046324380962885344, | |
| "grad_norm": 2.8663763999938965, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 6.7693, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0048530303865879885, | |
| "grad_norm": 2.748577833175659, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 6.6481, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005073622676887443, | |
| "grad_norm": 2.5603766441345215, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 6.9973, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005294214967186897, | |
| "grad_norm": 2.7109546661376953, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 7.2752, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005514807257486351, | |
| "grad_norm": 3.340872049331665, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 7.5969, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005514807257486351, | |
| "eval_loss": 7.113040924072266, | |
| "eval_runtime": 20.0439, | |
| "eval_samples_per_second": 95.241, | |
| "eval_steps_per_second": 47.645, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005735399547785805, | |
| "grad_norm": 2.8481411933898926, | |
| "learning_rate": 0.0001, | |
| "loss": 7.006, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005955991838085259, | |
| "grad_norm": 3.5465781688690186, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 7.1405, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006176584128384713, | |
| "grad_norm": 3.2511773109436035, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 7.0427, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.006397176418684167, | |
| "grad_norm": 3.1548283100128174, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 7.1469, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006617768708983621, | |
| "grad_norm": 3.4234230518341064, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 7.2329, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0068383609992830755, | |
| "grad_norm": 3.0600433349609375, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 6.6121, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.007058953289582529, | |
| "grad_norm": 3.1275887489318848, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 7.1327, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.007279545579881983, | |
| "grad_norm": 4.214815139770508, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 7.3558, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.007500137870181437, | |
| "grad_norm": 3.6205644607543945, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 7.1521, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007720730160480891, | |
| "grad_norm": 4.0161452293396, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 6.7042, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007941322450780346, | |
| "grad_norm": 5.151815414428711, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 6.7373, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0081619147410798, | |
| "grad_norm": 4.190551280975342, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 8.0788, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.008382507031379252, | |
| "grad_norm": 4.7776570320129395, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 7.3549, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.008603099321678707, | |
| "grad_norm": 5.777076721191406, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 6.666, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00882369161197816, | |
| "grad_norm": 4.582779407501221, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 6.011, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009044283902277616, | |
| "grad_norm": 5.211250305175781, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 6.9135, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.009264876192577069, | |
| "grad_norm": 5.360510349273682, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 7.4839, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.009485468482876524, | |
| "grad_norm": 6.11507511138916, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 6.7759, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.009706060773175977, | |
| "grad_norm": 6.635857582092285, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 7.8113, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.009926653063475432, | |
| "grad_norm": 7.438478469848633, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 7.3099, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.010147245353774885, | |
| "grad_norm": 6.5027923583984375, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 7.0473, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01036783764407434, | |
| "grad_norm": 5.755157947540283, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 7.2164, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.010588429934373794, | |
| "grad_norm": 10.475558280944824, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 6.7425, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.010809022224673248, | |
| "grad_norm": 8.64743423461914, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 7.6537, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.011029614514972702, | |
| "grad_norm": 9.511824607849121, | |
| "learning_rate": 0.0, | |
| "loss": 7.135, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.011029614514972702, | |
| "eval_loss": 7.017041206359863, | |
| "eval_runtime": 19.9636, | |
| "eval_samples_per_second": 95.624, | |
| "eval_steps_per_second": 47.837, | |
| "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": 27149520076800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |