| { | |
| "best_metric": 1.7026445865631104, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.56657223796034, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0113314447592068, | |
| "grad_norm": 0.33130019903182983, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7268, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0113314447592068, | |
| "eval_loss": 1.8638567924499512, | |
| "eval_runtime": 1.4022, | |
| "eval_samples_per_second": 106.259, | |
| "eval_steps_per_second": 13.55, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0226628895184136, | |
| "grad_norm": 0.34289681911468506, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7041, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0339943342776204, | |
| "grad_norm": 0.31898385286331177, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6902, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0453257790368272, | |
| "grad_norm": 0.3869572579860687, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7709, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.056657223796033995, | |
| "grad_norm": 0.3158705234527588, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7115, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0679886685552408, | |
| "grad_norm": 0.3238527476787567, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.7786, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07932011331444759, | |
| "grad_norm": 0.24129995703697205, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.6433, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0906515580736544, | |
| "grad_norm": 0.2565583288669586, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.7826, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10198300283286119, | |
| "grad_norm": 0.253324955701828, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.7602, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11331444759206799, | |
| "grad_norm": 0.22004887461662292, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.7622, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12464589235127478, | |
| "grad_norm": 0.2511484920978546, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.7196, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1359773371104816, | |
| "grad_norm": 0.24665340781211853, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.7755, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14730878186968838, | |
| "grad_norm": 0.2549428939819336, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.7022, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15864022662889518, | |
| "grad_norm": 0.27914848923683167, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.7994, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16997167138810199, | |
| "grad_norm": 0.27130889892578125, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.7918, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1813031161473088, | |
| "grad_norm": 0.28480955958366394, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.6809, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19263456090651557, | |
| "grad_norm": 0.27924010157585144, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.9603, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20396600566572237, | |
| "grad_norm": 0.3140809237957001, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.8441, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.21529745042492918, | |
| "grad_norm": 0.3188698887825012, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.9013, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.22662889518413598, | |
| "grad_norm": 0.328296035528183, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.893, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23796033994334279, | |
| "grad_norm": 0.33099815249443054, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.9472, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24929178470254956, | |
| "grad_norm": 0.3747865855693817, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.8709, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.26062322946175637, | |
| "grad_norm": 0.2017064094543457, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.6096, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2719546742209632, | |
| "grad_norm": 0.1878204196691513, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.6223, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.28328611898017, | |
| "grad_norm": 0.19264918565750122, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.5633, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.28328611898017, | |
| "eval_loss": 1.7305309772491455, | |
| "eval_runtime": 1.3728, | |
| "eval_samples_per_second": 108.538, | |
| "eval_steps_per_second": 13.84, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.29461756373937675, | |
| "grad_norm": 0.21514885127544403, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.7355, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3059490084985836, | |
| "grad_norm": 0.2080201953649521, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.5752, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.31728045325779036, | |
| "grad_norm": 0.197081059217453, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.5707, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3286118980169972, | |
| "grad_norm": 0.2009827047586441, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.5871, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.33994334277620397, | |
| "grad_norm": 0.2195533812046051, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.6545, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35127478753541075, | |
| "grad_norm": 0.23961254954338074, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.7495, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3626062322946176, | |
| "grad_norm": 0.18581852316856384, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.6507, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.37393767705382436, | |
| "grad_norm": 0.20042315125465393, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.6437, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.38526912181303113, | |
| "grad_norm": 0.20618341863155365, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.6764, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.39660056657223797, | |
| "grad_norm": 0.20008434355258942, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.7011, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.40793201133144474, | |
| "grad_norm": 0.23139382898807526, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.6504, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4192634560906516, | |
| "grad_norm": 0.25248095393180847, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.6017, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.43059490084985835, | |
| "grad_norm": 0.24187323451042175, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.7711, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.44192634560906513, | |
| "grad_norm": 0.27244117856025696, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.8675, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.45325779036827196, | |
| "grad_norm": 0.2246805727481842, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.8444, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.46458923512747874, | |
| "grad_norm": 0.2878750264644623, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.7995, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.47592067988668557, | |
| "grad_norm": 0.2895854711532593, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.7724, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.48725212464589235, | |
| "grad_norm": 0.34377485513687134, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.7968, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4985835694050991, | |
| "grad_norm": 0.36949583888053894, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.7625, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.509915014164306, | |
| "grad_norm": 0.16927896440029144, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.5636, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5212464589235127, | |
| "grad_norm": 0.16003383696079254, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.4856, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5325779036827195, | |
| "grad_norm": 0.14991965889930725, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.6608, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5439093484419264, | |
| "grad_norm": 0.19233012199401855, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.6948, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5552407932011332, | |
| "grad_norm": 0.18915553390979767, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.5136, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.56657223796034, | |
| "grad_norm": 0.2019452601671219, | |
| "learning_rate": 0.0, | |
| "loss": 1.5715, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.56657223796034, | |
| "eval_loss": 1.7026445865631104, | |
| "eval_runtime": 1.3716, | |
| "eval_samples_per_second": 108.633, | |
| "eval_steps_per_second": 13.853, | |
| "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": 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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1236088022630400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |