| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.130434782608696, | |
| "eval_steps": 25, | |
| "global_step": 48, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06324110671936758, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06324110671936758, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.0459, | |
| "eval_samples_per_second": 102.3, | |
| "eval_steps_per_second": 13.385, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.12648221343873517, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.18972332015810275, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.988343845952697e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.25296442687747034, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.953429730181653e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.31620553359683795, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.895420438411616e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3794466403162055, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.814586436738998e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4426877470355731, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.711304610594104e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5059288537549407, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.586056507527266e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5691699604743083, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.439426092011875e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6324110671936759, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.272097022732443e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.08484946505221e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.758893280632411, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.8785564535221e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8221343873517787, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.654179821390621e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8853754940711462, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.412765716093272e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9486166007905138, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.155439721630264e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0434782608695652, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.883401610574336e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.1067193675889329, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.597919750177168e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.1699604743083003, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.300325188655761e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.233201581027668, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.992005449231208e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.2964426877470356, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.674398060854931e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.359683794466403, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.348983855785121e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.4229249011857708, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.01728006526317e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4861660079051384, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.680833245481234e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.5494071146245059, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.341212066823355e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.6126482213438735, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.6126482213438735, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.043, | |
| "eval_samples_per_second": 102.584, | |
| "eval_steps_per_second": 13.422, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.6758893280632412, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.658787933176646e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.7391304347826086, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.319166754518768e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.8023715415019763, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.982719934736832e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.8656126482213438, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.651016144214878e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.9288537549407114, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.325601939145069e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0237154150197627, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.007994550768793e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.0869565217391304, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6996748113442394e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.150197628458498, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4020802498228335e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.2134387351778657, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1165983894256647e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.2766798418972334, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8445602783697374e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.3399209486166006, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5872342839067306e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.4031620553359683, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3458201786093794e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.466403162055336, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1214435464779006e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.5296442687747036, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.151505349477902e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.5928853754940713, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.2790297726755716e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.6561264822134385, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.605739079881239e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.719367588932806, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.139434924727359e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.782608695652174, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.88695389405898e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.8458498023715415, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8541356326100433e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0457956158838544e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.0039525691699605, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6570269818346224e-07, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 3.067193675889328, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1656154047303691e-07, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 3.130434782608696, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 48 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 48, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 9.889187968843776e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |