| { | |
| "best_metric": 0.9957740902900696, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.08598452278589853, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017196904557179708, | |
| "grad_norm": 0.04371219500899315, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5013, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017196904557179708, | |
| "eval_loss": 1.1150983572006226, | |
| "eval_runtime": 26.0196, | |
| "eval_samples_per_second": 37.664, | |
| "eval_steps_per_second": 18.832, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034393809114359416, | |
| "grad_norm": 0.05066497623920441, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6556, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005159071367153913, | |
| "grad_norm": 0.05329379439353943, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.6847, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006878761822871883, | |
| "grad_norm": 0.051895491778850555, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5981, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008598452278589854, | |
| "grad_norm": 0.06517327576875687, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.6962, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010318142734307825, | |
| "grad_norm": 0.05350270867347717, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6678, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012037833190025795, | |
| "grad_norm": 0.062394555658102036, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.706, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013757523645743766, | |
| "grad_norm": 0.058834996074438095, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7226, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015477214101461736, | |
| "grad_norm": 0.058221857994794846, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.6948, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017196904557179708, | |
| "grad_norm": 0.05588304251432419, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6798, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018916595012897677, | |
| "grad_norm": 0.0636599138379097, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.7023, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02063628546861565, | |
| "grad_norm": 0.06145975738763809, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6432, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02235597592433362, | |
| "grad_norm": 0.06953848898410797, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.7669, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02407566638005159, | |
| "grad_norm": 0.07056722790002823, | |
| "learning_rate": 7e-05, | |
| "loss": 0.8379, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.025795356835769563, | |
| "grad_norm": 0.06908471137285233, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8114, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.027515047291487533, | |
| "grad_norm": 0.06860286742448807, | |
| "learning_rate": 8e-05, | |
| "loss": 0.765, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.029234737747205503, | |
| "grad_norm": 0.06991557031869888, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.8112, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.030954428202923472, | |
| "grad_norm": 0.07742810249328613, | |
| "learning_rate": 9e-05, | |
| "loss": 0.8295, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03267411865864144, | |
| "grad_norm": 0.08711075782775879, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.8386, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.034393809114359415, | |
| "grad_norm": 0.08179605007171631, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9093, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03611349957007739, | |
| "grad_norm": 0.08795295655727386, | |
| "learning_rate": 9.999238475781957e-05, | |
| "loss": 0.9145, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.037833190025795355, | |
| "grad_norm": 0.08331762999296188, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 0.9265, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03955288048151333, | |
| "grad_norm": 0.07908172160387039, | |
| "learning_rate": 9.99314767377287e-05, | |
| "loss": 0.9195, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0412725709372313, | |
| "grad_norm": 0.09061425179243088, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.8748, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04299226139294927, | |
| "grad_norm": 0.0851019099354744, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.7701, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04471195184866724, | |
| "grad_norm": 0.09329686313867569, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.8657, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.046431642304385214, | |
| "grad_norm": 0.09710376709699631, | |
| "learning_rate": 9.962730758206611e-05, | |
| "loss": 0.9217, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04815133276010318, | |
| "grad_norm": 0.10121080279350281, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.8995, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04987102321582115, | |
| "grad_norm": 0.1065475270152092, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.8886, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.051590713671539126, | |
| "grad_norm": 0.11212456971406937, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.867, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05331040412725709, | |
| "grad_norm": 0.0965503603219986, | |
| "learning_rate": 9.908135917238321e-05, | |
| "loss": 0.806, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.055030094582975066, | |
| "grad_norm": 0.10261840373277664, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.9247, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05674978503869303, | |
| "grad_norm": 0.11739654093980789, | |
| "learning_rate": 9.871850323926177e-05, | |
| "loss": 0.927, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.058469475494411005, | |
| "grad_norm": 0.12067130953073502, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.9822, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06018916595012898, | |
| "grad_norm": 0.11332730948925018, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.8538, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.061908856405846945, | |
| "grad_norm": 0.12802854180335999, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.9749, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06362854686156492, | |
| "grad_norm": 0.13656459748744965, | |
| "learning_rate": 9.781523779815179e-05, | |
| "loss": 0.9501, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06534823731728288, | |
| "grad_norm": 0.1332613080739975, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.0124, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06706792777300086, | |
| "grad_norm": 0.168551504611969, | |
| "learning_rate": 9.727592877996585e-05, | |
| "loss": 1.1085, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06878761822871883, | |
| "grad_norm": 0.16357570886611938, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.0838, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0705073086844368, | |
| "grad_norm": 0.18186220526695251, | |
| "learning_rate": 9.667902132486009e-05, | |
| "loss": 1.2419, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07222699914015478, | |
| "grad_norm": 0.25837743282318115, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.5677, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07394668959587274, | |
| "grad_norm": 0.2586553692817688, | |
| "learning_rate": 9.602524267262203e-05, | |
| "loss": 1.3784, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07566638005159071, | |
| "grad_norm": 0.2590441107749939, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.5176, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07738607050730868, | |
| "grad_norm": 0.240685373544693, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 1.5495, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07910576096302666, | |
| "grad_norm": 0.2492353618144989, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.3381, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08082545141874463, | |
| "grad_norm": 0.2738623023033142, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 1.5593, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0825451418744626, | |
| "grad_norm": 0.362883061170578, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.6339, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08426483233018056, | |
| "grad_norm": 0.4202761650085449, | |
| "learning_rate": 9.373098535696979e-05, | |
| "loss": 1.6848, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08598452278589853, | |
| "grad_norm": 0.9379512667655945, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.2938, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08598452278589853, | |
| "eval_loss": 0.9957740902900696, | |
| "eval_runtime": 26.1033, | |
| "eval_samples_per_second": 37.543, | |
| "eval_steps_per_second": 18.772, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3571817360916480.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |