| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.31689443454149335, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006337888690829867, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006337888690829867, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.4423, | |
| "eval_samples_per_second": 14.525, | |
| "eval_steps_per_second": 3.776, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012675777381659734, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019013666072489603, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000299878360437632, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02535155476331947, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029951366095324104, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.031689443454149334, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029890655875994835, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.038027332144979206, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002980581478969406, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04436522083580907, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029696995725793764, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05070310952663894, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029564394783602234, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0570409982174688, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002940825091897988, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06337888690829867, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029228845513724634, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06971677559912855, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029026501868502873, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07605466428995841, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002880158462023983, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08239255298078828, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002855449908501917, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08873044167161814, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028285690527676035, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09506833036244801, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000279956433593997, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10140621905327787, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027684880264791867, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10774410774410774, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027353961259953696, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1140819964349376, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027003482683298933, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12041988512576748, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00026634076120911777, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12675777381659734, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002624640726838608, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13309566250742721, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00025841174731196877, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1394335511982571, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000254191087657661, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14577143988908695, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002498096996349117, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15210932857991682, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002452754788010787, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15844721727074668, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00024059659612857536, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15844721727074668, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0847, | |
| "eval_samples_per_second": 23.984, | |
| "eval_steps_per_second": 6.236, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16478510596157656, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00023578148328022626, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1711229946524064, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00023083881741484068, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1774608833432363, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00022577750555038587, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.18379877203406614, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000220606668512939, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.19013666072489602, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00021533562450034164, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1964745494157259, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00020997387229017774, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.20281243810655575, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00020453107412233428, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.20915032679738563, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001990170382869919, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.21548821548821548, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019344170144942302, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.22182610417904536, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018781511074344962, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2281639928698752, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001821474056658286, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2345018815607051, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017644879980419374, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.24083977025153497, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017072956243148002, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.24717765894236482, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000165, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.25351554763319467, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015927043756852, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2598534363240246, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001535512001958063, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.26619132501485443, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014785259433417133, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2725292137056843, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014218488925655037, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2788671023965142, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013655829855057698, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.28520499108734404, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013098296171300814, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2915428797781739, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001254689258776657, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.29788076846900374, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012002612770982222, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.30421865715983365, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011466437549965834, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3105565458506635, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010939333148706099, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.31689443454149335, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010422249444961407, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.31689443454149335, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0827, | |
| "eval_samples_per_second": 24.008, | |
| "eval_steps_per_second": 6.242, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 76, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.375761253114839e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |