{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.11379800853485064, "eval_steps": 50, "global_step": 200, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005689900426742532, "eval_loss": 1.6864383220672607, "eval_runtime": 25.6761, "eval_samples_per_second": 28.821, "eval_steps_per_second": 14.41, "step": 1 }, { "epoch": 0.005689900426742532, "grad_norm": 4.157541751861572, "learning_rate": 0.0002, "loss": 6.2094, "step": 10 }, { "epoch": 0.011379800853485065, "grad_norm": 6.261565685272217, "learning_rate": 0.0002, "loss": 6.0314, "step": 20 }, { "epoch": 0.017069701280227598, "grad_norm": 10.27778148651123, "learning_rate": 0.0002, "loss": 5.6016, "step": 30 }, { "epoch": 0.02275960170697013, "grad_norm": 5.181585311889648, "learning_rate": 0.0002, "loss": 5.6554, "step": 40 }, { "epoch": 0.02844950213371266, "grad_norm": 4.440655708312988, "learning_rate": 0.0002, "loss": 5.0031, "step": 50 }, { "epoch": 0.02844950213371266, "eval_loss": 1.4197232723236084, "eval_runtime": 25.6793, "eval_samples_per_second": 28.817, "eval_steps_per_second": 14.408, "step": 50 }, { "epoch": 0.034139402560455195, "grad_norm": 3.0161073207855225, "learning_rate": 0.0002, "loss": 5.3738, "step": 60 }, { "epoch": 0.03982930298719772, "grad_norm": 6.340278148651123, "learning_rate": 0.0002, "loss": 5.8189, "step": 70 }, { "epoch": 0.04551920341394026, "grad_norm": 3.948845148086548, "learning_rate": 0.0002, "loss": 5.0512, "step": 80 }, { "epoch": 0.051209103840682786, "grad_norm": 5.043802261352539, "learning_rate": 0.0002, "loss": 5.4444, "step": 90 }, { "epoch": 0.05689900426742532, "grad_norm": 3.802062511444092, "learning_rate": 0.0002, "loss": 5.8226, "step": 100 }, { "epoch": 0.05689900426742532, "eval_loss": 1.3914963006973267, "eval_runtime": 25.7577, "eval_samples_per_second": 28.729, "eval_steps_per_second": 14.365, "step": 100 }, { "epoch": 0.06258890469416785, "grad_norm": 7.498713970184326, "learning_rate": 0.0002, "loss": 5.5185, "step": 110 }, { "epoch": 0.06827880512091039, "grad_norm": 3.4005045890808105, "learning_rate": 0.0002, "loss": 5.3742, "step": 120 }, { "epoch": 0.07396870554765292, "grad_norm": 2.6079518795013428, "learning_rate": 0.0002, "loss": 5.6117, "step": 130 }, { "epoch": 0.07965860597439545, "grad_norm": 4.517343521118164, "learning_rate": 0.0002, "loss": 5.2116, "step": 140 }, { "epoch": 0.08534850640113797, "grad_norm": 3.7854163646698, "learning_rate": 0.0002, "loss": 5.7297, "step": 150 }, { "epoch": 0.08534850640113797, "eval_loss": 1.3721575736999512, "eval_runtime": 25.9577, "eval_samples_per_second": 28.508, "eval_steps_per_second": 14.254, "step": 150 }, { "epoch": 0.09103840682788052, "grad_norm": 1.8278170824050903, "learning_rate": 0.0002, "loss": 4.8559, "step": 160 }, { "epoch": 0.09672830725462304, "grad_norm": 2.7177515029907227, "learning_rate": 0.0002, "loss": 5.4169, "step": 170 }, { "epoch": 0.10241820768136557, "grad_norm": 3.2658402919769287, "learning_rate": 0.0002, "loss": 5.6351, "step": 180 }, { "epoch": 0.10810810810810811, "grad_norm": 3.8953888416290283, "learning_rate": 0.0002, "loss": 5.5097, "step": 190 }, { "epoch": 0.11379800853485064, "grad_norm": 2.9808075428009033, "learning_rate": 0.0002, "loss": 4.9441, "step": 200 }, { "epoch": 0.11379800853485064, "eval_loss": 1.3731629848480225, "eval_runtime": 25.9482, "eval_samples_per_second": 28.518, "eval_steps_per_second": 14.259, "step": 200 } ], "logging_steps": 10, "max_steps": 200, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3.522135406411776e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }