{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9961439588688946, "eval_steps": 500, "global_step": 15500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.032133676092544985, "grad_norm": 7.696083068847656, "learning_rate": 2.9039845758354757e-06, "loss": 0.4976, "step": 500 }, { "epoch": 0.06426735218508997, "grad_norm": 4.741117000579834, "learning_rate": 2.807583547557841e-06, "loss": 0.3532, "step": 1000 }, { "epoch": 0.09640102827763496, "grad_norm": 6.354885101318359, "learning_rate": 2.711182519280206e-06, "loss": 0.3195, "step": 1500 }, { "epoch": 0.12853470437017994, "grad_norm": 4.841858386993408, "learning_rate": 2.614781491002571e-06, "loss": 0.3079, "step": 2000 }, { "epoch": 0.16066838046272494, "grad_norm": 4.776275634765625, "learning_rate": 2.518573264781491e-06, "loss": 0.3067, "step": 2500 }, { "epoch": 0.1928020565552699, "grad_norm": 5.285233974456787, "learning_rate": 2.422172236503856e-06, "loss": 0.2957, "step": 3000 }, { "epoch": 0.2249357326478149, "grad_norm": 5.628823757171631, "learning_rate": 2.3257712082262213e-06, "loss": 0.3086, "step": 3500 }, { "epoch": 0.2570694087403599, "grad_norm": 4.082389831542969, "learning_rate": 2.229370179948586e-06, "loss": 0.2927, "step": 4000 }, { "epoch": 0.2892030848329049, "grad_norm": 5.4696478843688965, "learning_rate": 2.1331619537275066e-06, "loss": 0.2922, "step": 4500 }, { "epoch": 0.3213367609254499, "grad_norm": 4.862800598144531, "learning_rate": 2.0367609254498712e-06, "loss": 0.2931, "step": 5000 }, { "epoch": 0.35347043701799485, "grad_norm": 4.961813449859619, "learning_rate": 1.9403598971722367e-06, "loss": 0.2957, "step": 5500 }, { "epoch": 0.3856041131105398, "grad_norm": 4.734184741973877, "learning_rate": 1.8439588688946016e-06, "loss": 0.2809, "step": 6000 }, { "epoch": 0.41773778920308485, "grad_norm": 4.716980934143066, "learning_rate": 1.7477506426735218e-06, "loss": 0.2773, "step": 6500 }, { "epoch": 0.4498714652956298, "grad_norm": 4.844335079193115, "learning_rate": 1.651349614395887e-06, "loss": 0.2728, "step": 7000 }, { "epoch": 0.4820051413881748, "grad_norm": 5.491813659667969, "learning_rate": 1.554948586118252e-06, "loss": 0.2888, "step": 7500 }, { "epoch": 0.5141388174807198, "grad_norm": 4.701641082763672, "learning_rate": 1.458547557840617e-06, "loss": 0.2863, "step": 8000 }, { "epoch": 0.5462724935732648, "grad_norm": 5.017972469329834, "learning_rate": 1.3623393316195374e-06, "loss": 0.2813, "step": 8500 }, { "epoch": 0.5784061696658098, "grad_norm": 5.8628764152526855, "learning_rate": 1.2659383033419025e-06, "loss": 0.2695, "step": 9000 }, { "epoch": 0.6105398457583547, "grad_norm": 5.396206378936768, "learning_rate": 1.1695372750642673e-06, "loss": 0.2834, "step": 9500 }, { "epoch": 0.6426735218508998, "grad_norm": 4.796625137329102, "learning_rate": 1.0731362467866324e-06, "loss": 0.2739, "step": 10000 }, { "epoch": 0.6748071979434447, "grad_norm": 3.604219436645508, "learning_rate": 9.769280205655526e-07, "loss": 0.2744, "step": 10500 }, { "epoch": 0.7069408740359897, "grad_norm": 4.8642048835754395, "learning_rate": 8.80719794344473e-07, "loss": 0.2849, "step": 11000 }, { "epoch": 0.7390745501285347, "grad_norm": 4.076746940612793, "learning_rate": 7.84318766066838e-07, "loss": 0.2808, "step": 11500 }, { "epoch": 0.7712082262210797, "grad_norm": 2.8937087059020996, "learning_rate": 6.879177377892031e-07, "loss": 0.2796, "step": 12000 }, { "epoch": 0.8033419023136247, "grad_norm": 4.379210948944092, "learning_rate": 5.915167095115681e-07, "loss": 0.2772, "step": 12500 }, { "epoch": 0.8354755784061697, "grad_norm": 6.368309020996094, "learning_rate": 4.951156812339331e-07, "loss": 0.2813, "step": 13000 }, { "epoch": 0.8676092544987146, "grad_norm": 5.409502029418945, "learning_rate": 3.9871465295629823e-07, "loss": 0.2756, "step": 13500 }, { "epoch": 0.8997429305912596, "grad_norm": 2.8725733757019043, "learning_rate": 3.0231362467866326e-07, "loss": 0.2771, "step": 14000 }, { "epoch": 0.9318766066838047, "grad_norm": 8.13409423828125, "learning_rate": 2.059125964010283e-07, "loss": 0.283, "step": 14500 }, { "epoch": 0.9640102827763496, "grad_norm": 5.422169208526611, "learning_rate": 1.0970437017994858e-07, "loss": 0.2731, "step": 15000 }, { "epoch": 0.9961439588688946, "grad_norm": 4.597813606262207, "learning_rate": 1.3303341902313626e-08, "loss": 0.2865, "step": 15500 } ], "logging_steps": 500, "max_steps": 15560, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 32, "trial_name": null, "trial_params": null }