| { | |
| "best_metric": 0.810174822807312, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05534417156693186, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011068834313386372, | |
| "grad_norm": 39.035648345947266, | |
| "learning_rate": 5e-05, | |
| "loss": 14.1912, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011068834313386372, | |
| "eval_loss": 13.724494934082031, | |
| "eval_runtime": 89.3955, | |
| "eval_samples_per_second": 68.091, | |
| "eval_steps_per_second": 8.513, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022137668626772745, | |
| "grad_norm": 49.11076354980469, | |
| "learning_rate": 0.0001, | |
| "loss": 13.95, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0033206502940159115, | |
| "grad_norm": 46.80264663696289, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 12.4672, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004427533725354549, | |
| "grad_norm": 40.70325469970703, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.9493, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005534417156693186, | |
| "grad_norm": 22.785526275634766, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.5648, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006641300588031823, | |
| "grad_norm": 24.89859962463379, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.1986, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00774818401937046, | |
| "grad_norm": 10.723090171813965, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3804, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008855067450709098, | |
| "grad_norm": 7.183699607849121, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0429, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009961950882047734, | |
| "grad_norm": 2.7425971031188965, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.8633, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011068834313386372, | |
| "grad_norm": 3.750335216522217, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.8479, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012175717744725008, | |
| "grad_norm": 6.583054542541504, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.8649, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013282601176063646, | |
| "grad_norm": 5.435779571533203, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8645, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014389484607402282, | |
| "grad_norm": 11.439651489257812, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.0274, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01549636803874092, | |
| "grad_norm": 4.622027397155762, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8479, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016603251470079558, | |
| "grad_norm": 2.4504942893981934, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.799, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017710134901418196, | |
| "grad_norm": 3.957460403442383, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8311, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01881701833275683, | |
| "grad_norm": 7.060888290405273, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.9084, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.019923901764095468, | |
| "grad_norm": 5.054394245147705, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8656, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.021030785195434106, | |
| "grad_norm": 2.035604238510132, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8059, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.022137668626772744, | |
| "grad_norm": 2.204326868057251, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.819, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02324455205811138, | |
| "grad_norm": 3.217839479446411, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.8284, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.024351435489450016, | |
| "grad_norm": 2.6183955669403076, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8116, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.025458318920788654, | |
| "grad_norm": 3.3027353286743164, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.8476, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.026565202352127292, | |
| "grad_norm": 2.727635145187378, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8337, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02767208578346593, | |
| "grad_norm": 1.350140929222107, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.8148, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02767208578346593, | |
| "eval_loss": 0.8222213983535767, | |
| "eval_runtime": 89.2258, | |
| "eval_samples_per_second": 68.22, | |
| "eval_steps_per_second": 8.529, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028778969214804564, | |
| "grad_norm": 2.719294548034668, | |
| "learning_rate": 5e-05, | |
| "loss": 0.896, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.029885852646143202, | |
| "grad_norm": 2.636077642440796, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.8329, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03099273607748184, | |
| "grad_norm": 2.847155809402466, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.8251, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.032099619508820475, | |
| "grad_norm": 2.0352649688720703, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.8154, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.033206502940159116, | |
| "grad_norm": 0.7650236487388611, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.8079, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03431338637149775, | |
| "grad_norm": 2.32476544380188, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.8349, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03542026980283639, | |
| "grad_norm": 1.8150771856307983, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8164, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.036527153234175026, | |
| "grad_norm": 2.106776475906372, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.8064, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03763403666551366, | |
| "grad_norm": 1.8922873735427856, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8115, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0387409200968523, | |
| "grad_norm": 0.8627958297729492, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.8152, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.039847803528190937, | |
| "grad_norm": 1.8673175573349, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.8271, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04095468695952958, | |
| "grad_norm": 1.2413160800933838, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.8219, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04206157039086821, | |
| "grad_norm": 7.430208683013916, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.907, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04316845382220685, | |
| "grad_norm": 1.2367589473724365, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8171, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04427533725354549, | |
| "grad_norm": 0.9270449280738831, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.8097, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04538222068488412, | |
| "grad_norm": 1.416707992553711, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.8108, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04648910411622276, | |
| "grad_norm": 1.3523006439208984, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.8149, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0475959875475614, | |
| "grad_norm": 1.1008036136627197, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.8135, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04870287097890003, | |
| "grad_norm": 2.912865161895752, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8138, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.049809754410238674, | |
| "grad_norm": 1.1399955749511719, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.808, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05091663784157731, | |
| "grad_norm": 2.1416749954223633, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.8049, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05202352127291594, | |
| "grad_norm": 1.4024479389190674, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.8255, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.053130404704254584, | |
| "grad_norm": 1.4611579179763794, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.8113, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05423728813559322, | |
| "grad_norm": 1.3440361022949219, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.808, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05534417156693186, | |
| "grad_norm": 1.4476083517074585, | |
| "learning_rate": 0.0, | |
| "loss": 0.8002, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05534417156693186, | |
| "eval_loss": 0.810174822807312, | |
| "eval_runtime": 89.657, | |
| "eval_samples_per_second": 67.892, | |
| "eval_steps_per_second": 8.488, | |
| "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": 1.6535390389692006e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |