| { | |
| "best_metric": 10.350831031799316, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0023502867349816676, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.7005734699633354e-05, | |
| "grad_norm": 0.0749775841832161, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3598, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.7005734699633354e-05, | |
| "eval_loss": 10.364864349365234, | |
| "eval_runtime": 89.7799, | |
| "eval_samples_per_second": 99.777, | |
| "eval_steps_per_second": 49.889, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.401146939926671e-05, | |
| "grad_norm": 0.07384652644395828, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3608, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00014101720409890006, | |
| "grad_norm": 0.06634382903575897, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 10.3596, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00018802293879853342, | |
| "grad_norm": 0.0664483979344368, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 10.3572, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00023502867349816677, | |
| "grad_norm": 0.06566525250673294, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 10.3572, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002820344081978001, | |
| "grad_norm": 0.07329878211021423, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 10.3577, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003290401428974335, | |
| "grad_norm": 0.06763594597578049, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 10.3599, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00037604587759706683, | |
| "grad_norm": 0.07483668625354767, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 10.3616, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0004230516122967002, | |
| "grad_norm": 0.07877986133098602, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 10.3555, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00047005734699633354, | |
| "grad_norm": 0.07481114566326141, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 10.355, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000517063081695967, | |
| "grad_norm": 0.07228323817253113, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 10.3554, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0005640688163956002, | |
| "grad_norm": 0.07729602605104446, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 10.3498, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0006110745510952337, | |
| "grad_norm": 0.08047541975975037, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 10.3607, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.000658080285794867, | |
| "grad_norm": 0.08818409591913223, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.3619, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0007050860204945004, | |
| "grad_norm": 0.08615565299987793, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 10.3581, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007520917551941337, | |
| "grad_norm": 0.0926477387547493, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 10.354, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0007990974898937671, | |
| "grad_norm": 0.09321993589401245, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 10.3572, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0008461032245934004, | |
| "grad_norm": 0.09032484143972397, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 10.3594, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0008931089592930338, | |
| "grad_norm": 0.07716833800077438, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 10.3532, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0009401146939926671, | |
| "grad_norm": 0.1036844253540039, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 10.3561, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009871204286923004, | |
| "grad_norm": 0.08591034263372421, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 10.3554, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001034126163391934, | |
| "grad_norm": 0.09223807603120804, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 10.3524, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0010811318980915672, | |
| "grad_norm": 0.09289194643497467, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 10.3576, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0011281376327912005, | |
| "grad_norm": 0.10053667426109314, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 10.3523, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0011751433674908338, | |
| "grad_norm": 0.0925389751791954, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 10.3616, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0011751433674908338, | |
| "eval_loss": 10.354788780212402, | |
| "eval_runtime": 89.8027, | |
| "eval_samples_per_second": 99.752, | |
| "eval_steps_per_second": 49.876, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0012221491021904673, | |
| "grad_norm": 0.11649630963802338, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3567, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0012691548368901006, | |
| "grad_norm": 0.12191897630691528, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 10.3572, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.001316160571589734, | |
| "grad_norm": 0.09873288124799728, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 10.3488, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0013631663062893672, | |
| "grad_norm": 0.12206266075372696, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 10.3544, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0014101720409890007, | |
| "grad_norm": 0.10885295271873474, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 10.3586, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001457177775688634, | |
| "grad_norm": 0.11052808910608292, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 10.3566, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0015041835103882673, | |
| "grad_norm": 0.11033797264099121, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 10.3518, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0015511892450879006, | |
| "grad_norm": 0.14301928877830505, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 10.3582, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0015981949797875341, | |
| "grad_norm": 0.1133815199136734, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 10.366, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0016452007144871674, | |
| "grad_norm": 0.13060739636421204, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 10.3568, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0016922064491868007, | |
| "grad_norm": 0.11268500238656998, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 10.3563, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.001739212183886434, | |
| "grad_norm": 0.11154811084270477, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 10.3537, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0017862179185860676, | |
| "grad_norm": 0.1264294683933258, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 10.3504, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0018332236532857009, | |
| "grad_norm": 0.13054020702838898, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 10.3461, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0018802293879853342, | |
| "grad_norm": 0.1202877089381218, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 10.3538, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0019272351226849677, | |
| "grad_norm": 0.12251313030719757, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 10.3526, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0019742408573846008, | |
| "grad_norm": 0.14759667217731476, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 10.3545, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0020212465920842345, | |
| "grad_norm": 0.12316801398992538, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 10.3516, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.002068252326783868, | |
| "grad_norm": 0.14139099419116974, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 10.3559, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.002115258061483501, | |
| "grad_norm": 0.1286371797323227, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 10.3545, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0021622637961831344, | |
| "grad_norm": 0.12192552536725998, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 10.3513, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0022092695308827677, | |
| "grad_norm": 0.14616093039512634, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 10.3587, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.002256275265582401, | |
| "grad_norm": 0.14441625773906708, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 10.3626, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0023032810002820343, | |
| "grad_norm": 0.15917129814624786, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 10.3599, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0023502867349816676, | |
| "grad_norm": 0.2211294025182724, | |
| "learning_rate": 0.0, | |
| "loss": 10.3714, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0023502867349816676, | |
| "eval_loss": 10.350831031799316, | |
| "eval_runtime": 89.671, | |
| "eval_samples_per_second": 99.899, | |
| "eval_steps_per_second": 49.949, | |
| "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": 5230244659200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |