{ "best_metric": 0.5146859884262085, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.029708853238265002, "eval_steps": 25, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0011883541295306002, "grad_norm": 3.8583266735076904, "learning_rate": 5e-05, "loss": 4.0588, "step": 1 }, { "epoch": 0.0011883541295306002, "eval_loss": 7.116491794586182, "eval_runtime": 4.2971, "eval_samples_per_second": 11.636, "eval_steps_per_second": 3.025, "step": 1 }, { "epoch": 0.0023767082590612004, "grad_norm": 3.7670252323150635, "learning_rate": 0.0001, "loss": 4.0283, "step": 2 }, { "epoch": 0.0035650623885918, "grad_norm": 4.636148929595947, "learning_rate": 9.990365154573717e-05, "loss": 4.5078, "step": 3 }, { "epoch": 0.004753416518122401, "grad_norm": 4.651632308959961, "learning_rate": 9.961501876182148e-05, "loss": 3.5027, "step": 4 }, { "epoch": 0.0059417706476530005, "grad_norm": 5.130126953125, "learning_rate": 9.913533761814537e-05, "loss": 2.8078, "step": 5 }, { "epoch": 0.0071301247771836, "grad_norm": 5.748180389404297, "learning_rate": 9.846666218300807e-05, "loss": 1.9374, "step": 6 }, { "epoch": 0.008318478906714201, "grad_norm": 4.101024627685547, "learning_rate": 9.761185582727977e-05, "loss": 1.2732, "step": 7 }, { "epoch": 0.009506833036244802, "grad_norm": 4.253706932067871, "learning_rate": 9.657457896300791e-05, "loss": 1.1, "step": 8 }, { "epoch": 0.0106951871657754, "grad_norm": 2.773369312286377, "learning_rate": 9.535927336897098e-05, "loss": 1.114, "step": 9 }, { "epoch": 0.011883541295306001, "grad_norm": 2.6358070373535156, "learning_rate": 9.397114317029975e-05, "loss": 1.0818, "step": 10 }, { "epoch": 0.013071895424836602, "grad_norm": 2.299405813217163, "learning_rate": 9.241613255361455e-05, "loss": 0.9123, "step": 11 }, { "epoch": 0.0142602495543672, "grad_norm": 3.731668710708618, "learning_rate": 9.070090031310558e-05, "loss": 1.2773, "step": 12 }, { "epoch": 0.015448603683897801, "grad_norm": 2.423055648803711, "learning_rate": 8.883279133655399e-05, "loss": 1.0221, "step": 13 }, { "epoch": 0.016636957813428402, "grad_norm": 2.326035976409912, "learning_rate": 8.681980515339464e-05, "loss": 0.7976, "step": 14 }, { "epoch": 0.017825311942959002, "grad_norm": 2.6155567169189453, "learning_rate": 8.467056167950311e-05, "loss": 0.8461, "step": 15 }, { "epoch": 0.019013666072489603, "grad_norm": 1.5926434993743896, "learning_rate": 8.239426430539243e-05, "loss": 0.6395, "step": 16 }, { "epoch": 0.020202020202020204, "grad_norm": 1.8488845825195312, "learning_rate": 8.000066048588211e-05, "loss": 0.6839, "step": 17 }, { "epoch": 0.0213903743315508, "grad_norm": 1.5457555055618286, "learning_rate": 7.75e-05, "loss": 0.5364, "step": 18 }, { "epoch": 0.0225787284610814, "grad_norm": 1.8210150003433228, "learning_rate": 7.490299105985507e-05, "loss": 0.6909, "step": 19 }, { "epoch": 0.023767082590612002, "grad_norm": 1.565142273902893, "learning_rate": 7.222075445642904e-05, "loss": 0.5963, "step": 20 }, { "epoch": 0.024955436720142603, "grad_norm": 1.2754619121551514, "learning_rate": 6.946477593864228e-05, "loss": 0.5801, "step": 21 }, { "epoch": 0.026143790849673203, "grad_norm": 1.2012678384780884, "learning_rate": 6.664685702961344e-05, "loss": 0.5503, "step": 22 }, { "epoch": 0.027332144979203804, "grad_norm": 1.0641955137252808, "learning_rate": 6.377906449072578e-05, "loss": 0.4726, "step": 23 }, { "epoch": 0.0285204991087344, "grad_norm": 1.842871904373169, "learning_rate": 6.087367864990233e-05, "loss": 0.7947, "step": 24 }, { "epoch": 0.029708853238265002, "grad_norm": 1.9366096258163452, "learning_rate": 5.794314081535644e-05, "loss": 0.8874, "step": 25 }, { "epoch": 0.029708853238265002, "eval_loss": 0.5146859884262085, "eval_runtime": 2.3469, "eval_samples_per_second": 21.305, "eval_steps_per_second": 5.539, "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": 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": 3.02134233260884e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }