| { | |
| "best_metric": 1.4647512435913086, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.032605151613955004, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006521030322791001, | |
| "grad_norm": 0.21651652455329895, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0694, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006521030322791001, | |
| "eval_loss": 1.6041988134384155, | |
| "eval_runtime": 21.5314, | |
| "eval_samples_per_second": 119.964, | |
| "eval_steps_per_second": 15.001, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013042060645582002, | |
| "grad_norm": 0.23289066553115845, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2117, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0019563090968373, | |
| "grad_norm": 0.3474409580230713, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6201, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0026084121291164004, | |
| "grad_norm": 0.31122875213623047, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3937, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0032605151613955006, | |
| "grad_norm": 0.32344159483909607, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4884, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0039126181936746, | |
| "grad_norm": 0.2839902341365814, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.311, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004564721225953701, | |
| "grad_norm": 0.26937419176101685, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.434, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005216824258232801, | |
| "grad_norm": 0.24133557081222534, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.3177, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0058689272905119005, | |
| "grad_norm": 0.2753654420375824, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.4809, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006521030322791001, | |
| "grad_norm": 0.37832701206207275, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.3338, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007173133355070101, | |
| "grad_norm": 0.28633660078048706, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.4828, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0078252363873492, | |
| "grad_norm": 0.2793128788471222, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.452, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008477339419628301, | |
| "grad_norm": 0.2489110678434372, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.4138, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009129442451907402, | |
| "grad_norm": 0.23229557275772095, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.4449, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0097815454841865, | |
| "grad_norm": 0.21934479475021362, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.4662, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010433648516465601, | |
| "grad_norm": 0.24849727749824524, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.3644, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011085751548744702, | |
| "grad_norm": 0.2108910232782364, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.33, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011737854581023801, | |
| "grad_norm": 0.19061513245105743, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.2974, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012389957613302902, | |
| "grad_norm": 0.20481941103935242, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.439, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013042060645582002, | |
| "grad_norm": 0.20506615936756134, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3511, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013694163677861103, | |
| "grad_norm": 0.20289862155914307, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.3739, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014346266710140202, | |
| "grad_norm": 0.18342691659927368, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.3071, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014998369742419302, | |
| "grad_norm": 0.20112717151641846, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.2712, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0156504727746984, | |
| "grad_norm": 0.19664767384529114, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.4136, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016302575806977502, | |
| "grad_norm": 0.23060624301433563, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.3621, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016302575806977502, | |
| "eval_loss": 1.4904130697250366, | |
| "eval_runtime": 21.4171, | |
| "eval_samples_per_second": 120.604, | |
| "eval_steps_per_second": 15.081, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016954678839256603, | |
| "grad_norm": 0.2123045027256012, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.3638, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.017606781871535703, | |
| "grad_norm": 0.19667382538318634, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.4593, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.018258884903814804, | |
| "grad_norm": 0.21623675525188446, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.3836, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.018910987936093904, | |
| "grad_norm": 0.2061716467142105, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.5142, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.019563090968373, | |
| "grad_norm": 0.21938467025756836, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.4625, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020215194000652102, | |
| "grad_norm": 0.22383436560630798, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.4316, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.020867297032931203, | |
| "grad_norm": 0.21363838016986847, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.5011, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.021519400065210303, | |
| "grad_norm": 0.23454470932483673, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.4714, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.022171503097489404, | |
| "grad_norm": 0.2438150942325592, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.4566, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.022823606129768505, | |
| "grad_norm": 0.24382317066192627, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.394, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.023475709162047602, | |
| "grad_norm": 0.26105523109436035, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.5844, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.024127812194326703, | |
| "grad_norm": 0.25343576073646545, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.5326, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.024779915226605803, | |
| "grad_norm": 0.2793176472187042, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.4606, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.025432018258884904, | |
| "grad_norm": 0.2861690819263458, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.5886, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.026084121291164004, | |
| "grad_norm": 0.3055659532546997, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.6292, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026736224323443105, | |
| "grad_norm": 0.3592061698436737, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.6955, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.027388327355722206, | |
| "grad_norm": 0.3756411373615265, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.6397, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.028040430388001303, | |
| "grad_norm": 0.3495422303676605, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.4516, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.028692533420280403, | |
| "grad_norm": 0.41340503096580505, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.7137, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.029344636452559504, | |
| "grad_norm": 0.46326860785484314, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.6484, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.029996739484838605, | |
| "grad_norm": 0.44499802589416504, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.6504, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.030648842517117705, | |
| "grad_norm": 0.5560527443885803, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.7462, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0313009455493968, | |
| "grad_norm": 0.609457790851593, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.7769, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03195304858167591, | |
| "grad_norm": 0.597760021686554, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.9396, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.032605151613955004, | |
| "grad_norm": 0.8746095895767212, | |
| "learning_rate": 0.0, | |
| "loss": 2.2609, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.032605151613955004, | |
| "eval_loss": 1.4647512435913086, | |
| "eval_runtime": 21.4373, | |
| "eval_samples_per_second": 120.491, | |
| "eval_steps_per_second": 15.067, | |
| "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": 914705136746496.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |