| { | |
| "best_metric": 4.896439075469971, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.27313076135199726, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0054626152270399455, | |
| "grad_norm": 11.225051879882812, | |
| "learning_rate": 5e-05, | |
| "loss": 5.6969, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0054626152270399455, | |
| "eval_loss": 6.31785249710083, | |
| "eval_runtime": 16.2073, | |
| "eval_samples_per_second": 76.077, | |
| "eval_steps_per_second": 9.564, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010925230454079891, | |
| "grad_norm": 17.105873107910156, | |
| "learning_rate": 0.0001, | |
| "loss": 5.892, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016387845681119836, | |
| "grad_norm": 12.427094459533691, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.8781, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.021850460908159782, | |
| "grad_norm": 1.9965782165527344, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.6945, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02731307613519973, | |
| "grad_norm": 1.9345985651016235, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.5394, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03277569136223967, | |
| "grad_norm": 1.6240732669830322, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 5.5812, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03823830658927962, | |
| "grad_norm": 2.8485870361328125, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 5.5264, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.043700921816319564, | |
| "grad_norm": 2.1197474002838135, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.5387, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04916353704335951, | |
| "grad_norm": 2.4304542541503906, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 5.5388, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05462615227039946, | |
| "grad_norm": 1.8813854455947876, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 5.3464, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.060088767497439396, | |
| "grad_norm": 1.9439139366149902, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 5.4302, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06555138272447934, | |
| "grad_norm": 2.129732131958008, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 5.5419, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07101399795151929, | |
| "grad_norm": 3.5427029132843018, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 5.3349, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07647661317855924, | |
| "grad_norm": 3.527904987335205, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.2069, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08193922840559918, | |
| "grad_norm": 2.881154775619507, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 5.1289, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08740184363263913, | |
| "grad_norm": 1.898538589477539, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 5.0536, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09286445885967907, | |
| "grad_norm": 2.2791831493377686, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 5.0985, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09832707408671902, | |
| "grad_norm": 2.8523497581481934, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 5.1456, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10378968931375897, | |
| "grad_norm": 2.508509397506714, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 5.1744, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10925230454079891, | |
| "grad_norm": 2.2187211513519287, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 5.1774, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11471491976783885, | |
| "grad_norm": 2.0519227981567383, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 5.2051, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12017753499487879, | |
| "grad_norm": 2.327409505844116, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 5.1224, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12564015022191874, | |
| "grad_norm": 2.0955135822296143, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 5.1837, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13110276544895869, | |
| "grad_norm": 2.214733839035034, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 5.2276, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.13656538067599863, | |
| "grad_norm": 2.3443398475646973, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 5.349, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13656538067599863, | |
| "eval_loss": 5.045346260070801, | |
| "eval_runtime": 16.253, | |
| "eval_samples_per_second": 75.863, | |
| "eval_steps_per_second": 9.537, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14202799590303858, | |
| "grad_norm": 3.3359363079071045, | |
| "learning_rate": 5e-05, | |
| "loss": 4.9104, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.14749061113007852, | |
| "grad_norm": 2.990004301071167, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 4.9808, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.15295322635711847, | |
| "grad_norm": 2.493718385696411, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 4.9926, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.15841584158415842, | |
| "grad_norm": 2.0746469497680664, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 4.9458, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.16387845681119836, | |
| "grad_norm": 1.7948659658432007, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 4.8397, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1693410720382383, | |
| "grad_norm": 1.6932811737060547, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 4.9024, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.17480368726527826, | |
| "grad_norm": 1.7441197633743286, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.8987, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1802663024923182, | |
| "grad_norm": 1.8560411930084229, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 5.0526, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.18572891771935815, | |
| "grad_norm": 2.0022428035736084, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 5.0421, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1911915329463981, | |
| "grad_norm": 2.142507314682007, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 4.9688, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.19665414817343804, | |
| "grad_norm": 2.3231780529022217, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 5.162, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.202116763400478, | |
| "grad_norm": 2.606092929840088, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 5.0821, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.20757937862751794, | |
| "grad_norm": 1.6653012037277222, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.721, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.21304199385455788, | |
| "grad_norm": 1.5581425428390503, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 4.7959, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.21850460908159783, | |
| "grad_norm": 1.4504172801971436, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 4.8705, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22396722430863775, | |
| "grad_norm": 1.403963565826416, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 4.8881, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2294298395356777, | |
| "grad_norm": 1.5083348751068115, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 4.8065, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.23489245476271764, | |
| "grad_norm": 1.3726880550384521, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 4.881, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.24035506998975759, | |
| "grad_norm": 1.4420634508132935, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.9621, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.24581768521679753, | |
| "grad_norm": 1.4268460273742676, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 4.8976, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2512803004438375, | |
| "grad_norm": 1.5003798007965088, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 5.045, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2567429156708774, | |
| "grad_norm": 1.7467073202133179, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 5.0144, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.26220553089791737, | |
| "grad_norm": 1.8754444122314453, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 4.9771, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2676681461249573, | |
| "grad_norm": 2.1238296031951904, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 5.1125, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.27313076135199726, | |
| "grad_norm": 2.818662405014038, | |
| "learning_rate": 0.0, | |
| "loss": 5.192, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.27313076135199726, | |
| "eval_loss": 4.896439075469971, | |
| "eval_runtime": 16.2375, | |
| "eval_samples_per_second": 75.935, | |
| "eval_steps_per_second": 9.546, | |
| "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": 1.589463780163584e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |