| { | |
| "best_metric": 1.471519947052002, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.03346720214190094, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013386880856760374, | |
| "grad_norm": 5.025701999664307, | |
| "learning_rate": 2e-05, | |
| "loss": 2.4108, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013386880856760374, | |
| "eval_loss": 2.537308931350708, | |
| "eval_runtime": 70.7541, | |
| "eval_samples_per_second": 17.78, | |
| "eval_steps_per_second": 2.233, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002677376171352075, | |
| "grad_norm": 5.110573768615723, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2402, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004016064257028112, | |
| "grad_norm": 5.169720649719238, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1319, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00535475234270415, | |
| "grad_norm": 2.304621458053589, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1494, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006693440428380187, | |
| "grad_norm": 1.453190565109253, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6319, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008032128514056224, | |
| "grad_norm": 0.9239307641983032, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.7635, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009370816599732263, | |
| "grad_norm": 1.6850275993347168, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.8355, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0107095046854083, | |
| "grad_norm": 1.4980453252792358, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.9613, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012048192771084338, | |
| "grad_norm": 1.374350905418396, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.2347, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013386880856760375, | |
| "grad_norm": 0.8881041407585144, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.2745, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014725568942436412, | |
| "grad_norm": 1.0661808252334595, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.6181, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01606425702811245, | |
| "grad_norm": 0.8983698487281799, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.4951, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01740294511378849, | |
| "grad_norm": 1.2034538984298706, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.713, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018741633199464525, | |
| "grad_norm": 1.136259913444519, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.5381, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020080321285140562, | |
| "grad_norm": 0.9251773357391357, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.4089, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0214190093708166, | |
| "grad_norm": 1.101027250289917, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.1084, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022757697456492636, | |
| "grad_norm": 0.8664842844009399, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.1297, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.024096385542168676, | |
| "grad_norm": 1.0595276355743408, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.1792, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.025435073627844713, | |
| "grad_norm": 0.9103767275810242, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.2791, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02677376171352075, | |
| "grad_norm": 0.895751416683197, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1642, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028112449799196786, | |
| "grad_norm": 0.8980446457862854, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.0529, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.029451137884872823, | |
| "grad_norm": 0.9152507185935974, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.9741, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.030789825970548863, | |
| "grad_norm": 1.0312362909317017, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.1645, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0321285140562249, | |
| "grad_norm": 1.0697182416915894, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.1863, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03346720214190094, | |
| "grad_norm": 1.0174766778945923, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.0057, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03346720214190094, | |
| "eval_loss": 1.471519947052002, | |
| "eval_runtime": 72.2713, | |
| "eval_samples_per_second": 17.407, | |
| "eval_steps_per_second": 2.186, | |
| "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": 3.0679414421323776e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |