| { | |
| "best_metric": 0.24415357410907745, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.008471704506946797, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016943409013893597, | |
| "eval_loss": 0.2542303204536438, | |
| "eval_runtime": 3002.3866, | |
| "eval_samples_per_second": 0.828, | |
| "eval_steps_per_second": 0.207, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016943409013893595, | |
| "grad_norm": 0.17602235078811646, | |
| "learning_rate": 4.0600000000000004e-05, | |
| "loss": 0.4374, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003388681802778719, | |
| "grad_norm": 0.20099331438541412, | |
| "learning_rate": 8.120000000000001e-05, | |
| "loss": 0.4414, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005083022704168078, | |
| "grad_norm": 0.2623608410358429, | |
| "learning_rate": 0.00012179999999999999, | |
| "loss": 0.5019, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006777363605557438, | |
| "grad_norm": 0.401140421628952, | |
| "learning_rate": 0.00016240000000000002, | |
| "loss": 0.5029, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008471704506946797, | |
| "grad_norm": 1.6905375719070435, | |
| "learning_rate": 0.000203, | |
| "loss": 0.5199, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008471704506946797, | |
| "eval_loss": 0.24415357410907745, | |
| "eval_runtime": 2979.8855, | |
| "eval_samples_per_second": 0.834, | |
| "eval_steps_per_second": 0.209, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 1.2747702395731968e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |