| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.04507169216034255, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009014338432068509, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009014338432068509, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.491, | |
| "eval_samples_per_second": 33.534, | |
| "eval_steps_per_second": 8.719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018028676864137018, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002704301529620553, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0036057353728274036, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004507169216034255, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005408603059241106, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997539658034168e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006310036902447956, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.990161322484486e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007211470745654807, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.977873061452552e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008112904588861658, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.96068831197139e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00901433843206851, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938625865312251e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00991577227527536, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.911709846436641e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010817206118482211, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.879969687616027e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011718639961689061, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.84344009624807e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012620073804895913, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.80216101690461e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.013521507648102763, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.756177587652856e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014422941491309614, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.705540090697575e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.015324375334516466, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.650303897398232e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.016225809177723316, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.590529407721231e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.017127243020930168, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.526281984193436e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01802867686413702, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.4576318804292e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.018930110707343867, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.384654164309083e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01983154455055072, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.30742863589421e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02073297839375757, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.226039740166091e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.021634412236964422, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.022535846080171274, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.051132292283771e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022535846080171274, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.4909, | |
| "eval_samples_per_second": 33.537, | |
| "eval_steps_per_second": 8.72, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.023437279923378122, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.957804998855866e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.024338713766584974, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.860696646428693e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.025240147609791826, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.759913421559902e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.026141581452998677, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.655565529226198e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.027043015296205525, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.547767072315835e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.027944449139412377, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.436635926858759e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02884588298261923, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.322293613130917e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02974731682582608, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.204865162773613e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.030648750669032932, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.084478982073247e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03155018451223978, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.961266711550922e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03245161835544663, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.835363082015468e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.033353052198653484, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.706905767237288e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.034254486041860335, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.576035233404096e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03515591988506719, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.442894585523218e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03605735372827404, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.307629410938363e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03695878757148088, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.170387620131993e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.037860221414687735, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.031319284987394e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03876165525789459, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03966308910110144, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.7483130894283e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04056452294430829, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.604684692133597e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04146595678751514, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.459848338346861e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04236739063072199, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.313962404494496e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.043268824473928845, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167186414703289e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0441702583171357, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.019680866363139e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04507169216034255, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8716070546254966e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04507169216034255, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.4911, | |
| "eval_samples_per_second": 33.532, | |
| "eval_steps_per_second": 8.718, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.305284264198144e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |