| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.14338202347880635, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002867640469576127, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002867640469576127, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.5085, | |
| "eval_samples_per_second": 19.932, | |
| "eval_steps_per_second": 5.182, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005735280939152254, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00860292140872838, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011470561878304508, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014338202347880635, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01720584281745676, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997539658034168e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.020073483287032887, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.990161322484486e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.022941123756609016, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.977873061452552e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02580876422618514, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.96068831197139e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02867640469576127, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938625865312251e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.031544045165337396, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.911709846436641e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03441168563491352, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.879969687616027e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03727932610448965, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.84344009624807e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04014696657406577, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.80216101690461e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.043014607043641906, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.756177587652856e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04588224751321803, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.705540090697575e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04874988798279416, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.650303897398232e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05161752845237028, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.590529407721231e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05448516892194641, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.526281984193436e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05735280939152254, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.4576318804292e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06022044986109867, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.384654164309083e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06308809033067479, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.30742863589421e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06595573080025093, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.226039740166091e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06882337126982704, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07169101173940318, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.051132292283771e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07169101173940318, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4796, | |
| "eval_samples_per_second": 20.165, | |
| "eval_steps_per_second": 5.243, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0745586522089793, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.957804998855866e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07742629267855543, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.860696646428693e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08029393314813155, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.759913421559902e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08316157361770768, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.655565529226198e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08602921408728381, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.547767072315835e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08889685455685993, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.436635926858759e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09176449502643606, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.322293613130917e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.09463213549601218, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.204865162773613e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09749977596558831, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.084478982073247e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10036741643516445, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.961266711550922e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10323505690474057, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.835363082015468e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1061026973743167, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.706905767237288e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10897033784389282, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.576035233404096e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.11183797831346895, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.442894585523218e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.11470561878304508, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.307629410938363e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1175732592526212, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.170387620131993e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.12044089972219733, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.031319284987394e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.12330854019177345, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.12617618066134959, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.7483130894283e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12904382113092572, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.604684692133597e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13191146160050185, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.459848338346861e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.13477910207007796, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.313962404494496e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1376467425396541, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167186414703289e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.14051438300923022, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.019680866363139e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.14338202347880635, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8716070546254966e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14338202347880635, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4882, | |
| "eval_samples_per_second": 20.095, | |
| "eval_steps_per_second": 5.225, | |
| "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": 2.974559326175232e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |