| { | |
| "best_metric": 1.6942381858825684, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.004052028040034037, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016208112160136148, | |
| "grad_norm": 24.297019958496094, | |
| "learning_rate": 2e-05, | |
| "loss": 11.3236, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016208112160136148, | |
| "eval_loss": 2.9382340908050537, | |
| "eval_runtime": 747.9836, | |
| "eval_samples_per_second": 13.893, | |
| "eval_steps_per_second": 1.737, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032416224320272295, | |
| "grad_norm": 24.249916076660156, | |
| "learning_rate": 4e-05, | |
| "loss": 11.5612, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00048624336480408443, | |
| "grad_norm": 16.707523345947266, | |
| "learning_rate": 6e-05, | |
| "loss": 11.2607, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006483244864054459, | |
| "grad_norm": 15.533491134643555, | |
| "learning_rate": 8e-05, | |
| "loss": 10.2298, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008104056080068074, | |
| "grad_norm": 14.662958145141602, | |
| "learning_rate": 0.0001, | |
| "loss": 9.4951, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009724867296081689, | |
| "grad_norm": 11.636035919189453, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 9.1814, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011345678512095303, | |
| "grad_norm": 10.30533218383789, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 9.4261, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0012966489728108918, | |
| "grad_norm": 8.74864387512207, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 8.5058, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014587300944122533, | |
| "grad_norm": 8.249582290649414, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 8.7713, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016208112160136148, | |
| "grad_norm": 7.471890926361084, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 7.5653, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017828923376149762, | |
| "grad_norm": 6.764472484588623, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 7.4305, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0019449734592163377, | |
| "grad_norm": 6.544780731201172, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 7.8787, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002107054580817699, | |
| "grad_norm": 6.782019138336182, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 7.5796, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0022691357024190607, | |
| "grad_norm": 6.3458123207092285, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 7.4855, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002431216824020422, | |
| "grad_norm": 6.391896724700928, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 7.0854, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0025932979456217836, | |
| "grad_norm": 6.019820213317871, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 7.2838, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002755379067223145, | |
| "grad_norm": 6.196849346160889, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 6.9194, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0029174601888245066, | |
| "grad_norm": 6.031044006347656, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 6.902, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003079541310425868, | |
| "grad_norm": 6.036059856414795, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 7.1366, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0032416224320272295, | |
| "grad_norm": 5.807440280914307, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.8278, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003403703553628591, | |
| "grad_norm": 5.767394065856934, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 6.6886, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0035657846752299525, | |
| "grad_norm": 5.627509117126465, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 6.6944, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003727865796831314, | |
| "grad_norm": 6.078296184539795, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 6.8693, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0038899469184326754, | |
| "grad_norm": 5.587927341461182, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 6.6312, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004052028040034037, | |
| "grad_norm": 5.718355655670166, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 6.2087, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004052028040034037, | |
| "eval_loss": 1.6942381858825684, | |
| "eval_runtime": 753.2364, | |
| "eval_samples_per_second": 13.796, | |
| "eval_steps_per_second": 1.725, | |
| "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": 3.60924825255936e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |