| { | |
| "best_metric": 0.45151808857917786, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01182033096926714, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00047281323877068556, | |
| "grad_norm": 0.4812972843647003, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0998, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00047281323877068556, | |
| "eval_loss": 1.7066702842712402, | |
| "eval_runtime": 37.2509, | |
| "eval_samples_per_second": 95.649, | |
| "eval_steps_per_second": 11.973, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009456264775413711, | |
| "grad_norm": 0.6451953053474426, | |
| "learning_rate": 4e-05, | |
| "loss": 0.1496, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014184397163120568, | |
| "grad_norm": 0.7591167092323303, | |
| "learning_rate": 6e-05, | |
| "loss": 0.2027, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018912529550827422, | |
| "grad_norm": 0.6817419528961182, | |
| "learning_rate": 8e-05, | |
| "loss": 0.1866, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002364066193853428, | |
| "grad_norm": 0.7973491549491882, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2604, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0028368794326241137, | |
| "grad_norm": 0.5785849094390869, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.1714, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003309692671394799, | |
| "grad_norm": 0.9145536422729492, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.311, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0037825059101654845, | |
| "grad_norm": 0.628433346748352, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.1874, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00425531914893617, | |
| "grad_norm": 0.7682193517684937, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.1661, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004728132387706856, | |
| "grad_norm": 1.136603593826294, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.2571, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005200945626477541, | |
| "grad_norm": 1.0945473909378052, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.302, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005673758865248227, | |
| "grad_norm": 1.0636781454086304, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.1927, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006146572104018913, | |
| "grad_norm": 1.3937352895736694, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.3016, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006619385342789598, | |
| "grad_norm": 1.6984295845031738, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.3964, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0070921985815602835, | |
| "grad_norm": 1.4729679822921753, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.3477, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007565011820330969, | |
| "grad_norm": 2.385896682739258, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.6145, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008037825059101654, | |
| "grad_norm": 2.0085232257843018, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.4549, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00851063829787234, | |
| "grad_norm": 1.7343971729278564, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.306, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008983451536643027, | |
| "grad_norm": 2.9347760677337646, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.3519, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009456264775413711, | |
| "grad_norm": 2.380985736846924, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3773, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009929078014184398, | |
| "grad_norm": 1.2122873067855835, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.2567, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010401891252955082, | |
| "grad_norm": 2.9771504402160645, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.5409, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010874704491725768, | |
| "grad_norm": 1.6278725862503052, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.449, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011347517730496455, | |
| "grad_norm": 2.1092677116394043, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.492, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01182033096926714, | |
| "grad_norm": 1.8286502361297607, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.3454, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01182033096926714, | |
| "eval_loss": 0.45151808857917786, | |
| "eval_runtime": 37.2998, | |
| "eval_samples_per_second": 95.523, | |
| "eval_steps_per_second": 11.957, | |
| "step": 25 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2773092208214016.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |