| { | |
| "best_metric": 0.3689563274383545, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.01693623507494284, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003387247014988568, | |
| "grad_norm": 0.11901383846998215, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8495, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003387247014988568, | |
| "eval_loss": 0.4973084628582001, | |
| "eval_runtime": 1309.043, | |
| "eval_samples_per_second": 0.95, | |
| "eval_steps_per_second": 0.475, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006774494029977136, | |
| "grad_norm": 0.08991147577762604, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5582, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0010161741044965704, | |
| "grad_norm": 0.09259100258350372, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 0.8785, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0013548988059954273, | |
| "grad_norm": 0.07893957942724228, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.9846, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001693623507494284, | |
| "grad_norm": 0.1267137974500656, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 1.2384, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0020323482089931407, | |
| "grad_norm": 0.11019496619701385, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 1.0737, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0023710729104919974, | |
| "grad_norm": 0.10850029438734055, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 1.2798, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0027097976119908546, | |
| "grad_norm": 0.12845145165920258, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.9439, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0030485223134897113, | |
| "grad_norm": 0.13850660622119904, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 1.045, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003387247014988568, | |
| "grad_norm": 0.1552123725414276, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.3383, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0037259717164874247, | |
| "grad_norm": 0.1289689838886261, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 1.5728, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0040646964179862815, | |
| "grad_norm": 0.20587444305419922, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 1.3849, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004403421119485138, | |
| "grad_norm": 0.12785537540912628, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 1.2214, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004742145820983995, | |
| "grad_norm": 0.1636880338191986, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.1171, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0050808705224828525, | |
| "grad_norm": 0.17456404864788055, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 1.483, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005419595223981709, | |
| "grad_norm": 0.16706864535808563, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.9644, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005758319925480566, | |
| "grad_norm": 0.16800209879875183, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 1.3774, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006097044626979423, | |
| "grad_norm": 0.1840793490409851, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.3637, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006435769328478279, | |
| "grad_norm": 0.16447125375270844, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 1.0351, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.006774494029977136, | |
| "grad_norm": 0.1600571572780609, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 1.4351, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007113218731475993, | |
| "grad_norm": 0.17534436285495758, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 1.5428, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0074519434329748495, | |
| "grad_norm": 0.23527459800243378, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 1.343, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.007790668134473706, | |
| "grad_norm": 0.2889191210269928, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 1.4187, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008129392835972563, | |
| "grad_norm": 0.26636233925819397, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 1.4831, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00846811753747142, | |
| "grad_norm": 0.2863354980945587, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 2.0736, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00846811753747142, | |
| "eval_loss": 0.4173017740249634, | |
| "eval_runtime": 1312.807, | |
| "eval_samples_per_second": 0.948, | |
| "eval_steps_per_second": 0.474, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008806842238970276, | |
| "grad_norm": 0.2835831344127655, | |
| "learning_rate": 0.0001, | |
| "loss": 1.553, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.009145566940469134, | |
| "grad_norm": 0.25215256214141846, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.9827, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00948429164196799, | |
| "grad_norm": 0.34205523133277893, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 1.6806, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.009823016343466847, | |
| "grad_norm": 0.3410358428955078, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 1.8845, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.010161741044965705, | |
| "grad_norm": 0.4108333885669708, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 1.294, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01050046574646456, | |
| "grad_norm": 0.3529786169528961, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 1.5982, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.010839190447963418, | |
| "grad_norm": 0.44188639521598816, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 1.4352, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.011177915149462274, | |
| "grad_norm": 0.412591814994812, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 2.0171, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.011516639850961132, | |
| "grad_norm": 0.49157121777534485, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 2.1679, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.011855364552459988, | |
| "grad_norm": 0.46250882744789124, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 1.0679, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.012194089253958845, | |
| "grad_norm": 0.45197004079818726, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 1.875, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.012532813955457701, | |
| "grad_norm": 0.7647995948791504, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 2.5482, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.012871538656956559, | |
| "grad_norm": 0.570399284362793, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 2.0637, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.013210263358455415, | |
| "grad_norm": 0.6635165810585022, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 1.8633, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.013548988059954272, | |
| "grad_norm": 0.8030415177345276, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 2.9288, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01388771276145313, | |
| "grad_norm": 0.8105241060256958, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 2.3048, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.014226437462951986, | |
| "grad_norm": 0.7749304175376892, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 2.4869, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.014565162164450843, | |
| "grad_norm": 0.8955188393592834, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 2.4531, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.014903886865949699, | |
| "grad_norm": 1.082139492034912, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 1.4126, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.015242611567448557, | |
| "grad_norm": 1.0183438062667847, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 2.2606, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.015581336268947412, | |
| "grad_norm": 1.456734299659729, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 1.3089, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.015920060970446268, | |
| "grad_norm": 1.2570323944091797, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 2.5638, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.016258785671945126, | |
| "grad_norm": 1.7432653903961182, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 1.2538, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.016597510373443983, | |
| "grad_norm": 1.8139467239379883, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 1.8829, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01693623507494284, | |
| "grad_norm": 1.7850284576416016, | |
| "learning_rate": 0.0, | |
| "loss": 2.0823, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01693623507494284, | |
| "eval_loss": 0.3689563274383545, | |
| "eval_runtime": 1312.7469, | |
| "eval_samples_per_second": 0.948, | |
| "eval_steps_per_second": 0.474, | |
| "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": 1.26956599246848e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |