| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.00011551178942200788, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.1551178942200789e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1350.9014, | |
| "eval_samples_per_second": 26.983, | |
| "eval_steps_per_second": 13.492, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.4653536826602365e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.775589471100394e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1362.2989, | |
| "eval_samples_per_second": 26.757, | |
| "eval_steps_per_second": 13.379, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.930707365320473e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001039606104798071, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00011551178942200788, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1344.8067, | |
| "eval_samples_per_second": 27.105, | |
| "eval_steps_per_second": 13.553, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 166863498117120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |