{ "best_metric": 0.14145001769065857, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.7782101167315175, "eval_steps": 25, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0311284046692607, "grad_norm": 9.926247596740723, "learning_rate": 5e-05, "loss": 5.2342, "step": 1 }, { "epoch": 0.0311284046692607, "eval_loss": 5.72003173828125, "eval_runtime": 3.8173, "eval_samples_per_second": 13.098, "eval_steps_per_second": 3.406, "step": 1 }, { "epoch": 0.0622568093385214, "grad_norm": 10.351175308227539, "learning_rate": 0.0001, "loss": 5.3259, "step": 2 }, { "epoch": 0.0933852140077821, "grad_norm": 9.876289367675781, "learning_rate": 9.990365154573717e-05, "loss": 4.906, "step": 3 }, { "epoch": 0.1245136186770428, "grad_norm": 6.973885536193848, "learning_rate": 9.961501876182148e-05, "loss": 3.1993, "step": 4 }, { "epoch": 0.1556420233463035, "grad_norm": 6.595519542694092, "learning_rate": 9.913533761814537e-05, "loss": 2.0786, "step": 5 }, { "epoch": 0.1867704280155642, "grad_norm": 7.392065048217773, "learning_rate": 9.846666218300807e-05, "loss": 1.1917, "step": 6 }, { "epoch": 0.2178988326848249, "grad_norm": 5.252386569976807, "learning_rate": 9.761185582727977e-05, "loss": 0.502, "step": 7 }, { "epoch": 0.2490272373540856, "grad_norm": 3.8015263080596924, "learning_rate": 9.657457896300791e-05, "loss": 0.2918, "step": 8 }, { "epoch": 0.2801556420233463, "grad_norm": 6.925857067108154, "learning_rate": 9.535927336897098e-05, "loss": 0.4391, "step": 9 }, { "epoch": 0.311284046692607, "grad_norm": 5.934936046600342, "learning_rate": 9.397114317029975e-05, "loss": 0.4491, "step": 10 }, { "epoch": 0.3424124513618677, "grad_norm": 3.8128702640533447, "learning_rate": 9.241613255361455e-05, "loss": 0.3788, "step": 11 }, { "epoch": 0.3735408560311284, "grad_norm": 2.8401427268981934, "learning_rate": 9.070090031310558e-05, "loss": 0.3058, "step": 12 }, { "epoch": 0.4046692607003891, "grad_norm": 2.2815659046173096, "learning_rate": 8.883279133655399e-05, "loss": 0.2793, "step": 13 }, { "epoch": 0.4357976653696498, "grad_norm": 1.993712306022644, "learning_rate": 8.681980515339464e-05, "loss": 0.2575, "step": 14 }, { "epoch": 0.4669260700389105, "grad_norm": 2.533045530319214, "learning_rate": 8.467056167950311e-05, "loss": 0.2593, "step": 15 }, { "epoch": 0.4980544747081712, "grad_norm": 2.374345302581787, "learning_rate": 8.239426430539243e-05, "loss": 0.2229, "step": 16 }, { "epoch": 0.5291828793774319, "grad_norm": 2.1960155963897705, "learning_rate": 8.000066048588211e-05, "loss": 0.2379, "step": 17 }, { "epoch": 0.5603112840466926, "grad_norm": 1.8646379709243774, "learning_rate": 7.75e-05, "loss": 0.2132, "step": 18 }, { "epoch": 0.5914396887159533, "grad_norm": 1.9866734743118286, "learning_rate": 7.490299105985507e-05, "loss": 0.2288, "step": 19 }, { "epoch": 0.622568093385214, "grad_norm": 1.3293571472167969, "learning_rate": 7.222075445642904e-05, "loss": 0.1679, "step": 20 }, { "epoch": 0.6536964980544747, "grad_norm": 1.063161849975586, "learning_rate": 6.946477593864228e-05, "loss": 0.1783, "step": 21 }, { "epoch": 0.6848249027237354, "grad_norm": 1.157092571258545, "learning_rate": 6.664685702961344e-05, "loss": 0.1473, "step": 22 }, { "epoch": 0.7159533073929961, "grad_norm": 1.2641205787658691, "learning_rate": 6.377906449072578e-05, "loss": 0.17, "step": 23 }, { "epoch": 0.7470817120622568, "grad_norm": 1.6932222843170166, "learning_rate": 6.087367864990233e-05, "loss": 0.2098, "step": 24 }, { "epoch": 0.7782101167315175, "grad_norm": 2.0876078605651855, "learning_rate": 5.794314081535644e-05, "loss": 0.1764, "step": 25 }, { "epoch": 0.7782101167315175, "eval_loss": 0.14145001769065857, "eval_runtime": 3.4979, "eval_samples_per_second": 14.294, "eval_steps_per_second": 3.716, "step": 25 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 2.984041808658432e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }