| { | |
| "best_metric": 0.0721084475517273, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.000560497273180766, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.1209945463615319e-05, | |
| "grad_norm": 19.918994903564453, | |
| "learning_rate": 0.0001, | |
| "loss": 7.6896, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.1209945463615319e-05, | |
| "eval_loss": 12.443227767944336, | |
| "eval_runtime": 23095.1348, | |
| "eval_samples_per_second": 1.626, | |
| "eval_steps_per_second": 0.813, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.2419890927230638e-05, | |
| "grad_norm": 66.04986572265625, | |
| "learning_rate": 0.0002, | |
| "loss": 12.4535, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.362983639084596e-05, | |
| "grad_norm": 50.658294677734375, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 10.7847, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.4839781854461276e-05, | |
| "grad_norm": 6.0867085456848145, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 8.3446, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.60497273180766e-05, | |
| "grad_norm": 6.616514682769775, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 6.5516, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.725967278169192e-05, | |
| "grad_norm": 11.940505027770996, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 4.3826, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.846961824530724e-05, | |
| "grad_norm": 14.989151000976562, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 1.8869, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.967956370892255e-05, | |
| "grad_norm": 2.564073324203491, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.1218, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00010088950917253788, | |
| "grad_norm": 0.3145427107810974, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.015, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001120994546361532, | |
| "grad_norm": 0.08902858197689056, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0038, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00012330940009976852, | |
| "grad_norm": 0.02414277009665966, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.0011, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00013451934556338383, | |
| "grad_norm": 0.009534861892461777, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.0005, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00014572929102699914, | |
| "grad_norm": 0.005133251193910837, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.0003, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00015693923649061448, | |
| "grad_norm": 0.0033055301755666733, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0002, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0001681491819542298, | |
| "grad_norm": 0.0023320000618696213, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.0001, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0001793591274178451, | |
| "grad_norm": 0.001768999034538865, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.0001, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00019056907288146044, | |
| "grad_norm": 0.0015014299424365163, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0001, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00020177901834507575, | |
| "grad_norm": 0.0012995174620300531, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0001, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00021298896380869106, | |
| "grad_norm": 0.0011180074652656913, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.0001, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0002241989092723064, | |
| "grad_norm": 0.0009918313007801771, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0001, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0002354088547359217, | |
| "grad_norm": 0.0008973500225692987, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.0001, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00024661880019953705, | |
| "grad_norm": 0.000810017401818186, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0001, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00025782874566315236, | |
| "grad_norm": 0.0007706537726335227, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00026903869112676767, | |
| "grad_norm": 0.0006967373774386942, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.000280248636590383, | |
| "grad_norm": 0.0006718985387124121, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.000280248636590383, | |
| "eval_loss": 0.07439577579498291, | |
| "eval_runtime": 23171.5402, | |
| "eval_samples_per_second": 1.621, | |
| "eval_steps_per_second": 0.811, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0002914585820539983, | |
| "grad_norm": 0.0006170904962345958, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00030266852751761365, | |
| "grad_norm": 0.0006159543991088867, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00031387847298122896, | |
| "grad_norm": 0.0005721127381548285, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0003250884184448443, | |
| "grad_norm": 0.0005425804411061108, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0003362983639084596, | |
| "grad_norm": 0.0005256524891592562, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0003475083093720749, | |
| "grad_norm": 0.0005342414369806647, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0003587182548356902, | |
| "grad_norm": 0.0004955452168360353, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00036992820029930557, | |
| "grad_norm": 0.0004987911670468748, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0003811381457629209, | |
| "grad_norm": 0.000485962227685377, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0003923480912265362, | |
| "grad_norm": 0.00048300070920959115, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0004035580366901515, | |
| "grad_norm": 0.00046334488433785737, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0004147679821537668, | |
| "grad_norm": 0.0004746453487314284, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0004259779276173821, | |
| "grad_norm": 0.0004707688931375742, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0004371878730809975, | |
| "grad_norm": 0.00046502857003360987, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0004483978185446128, | |
| "grad_norm": 0.0004579959495458752, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0004596077640082281, | |
| "grad_norm": 0.00044225488090887666, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0004708177094718434, | |
| "grad_norm": 0.0004365835920907557, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.00048202765493545873, | |
| "grad_norm": 0.00046026986092329025, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0004932376003990741, | |
| "grad_norm": 0.00043169857235625386, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0005044475458626893, | |
| "grad_norm": 19.557327270507812, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 1.7673, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0005156574913263047, | |
| "grad_norm": 0.0004401964251883328, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.00052686743678992, | |
| "grad_norm": 0.0004397328884806484, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0005380773822535353, | |
| "grad_norm": 0.0004419698962010443, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0005492873277171507, | |
| "grad_norm": 0.0004412212292663753, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.000560497273180766, | |
| "grad_norm": 0.0004381506296340376, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.000560497273180766, | |
| "eval_loss": 0.0721084475517273, | |
| "eval_runtime": 23160.6552, | |
| "eval_samples_per_second": 1.622, | |
| "eval_steps_per_second": 0.811, | |
| "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": 1.382181645582336e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |