{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9882352941176471, "eval_steps": 500, "global_step": 42, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.11764705882352941, "grad_norm": 14.21014549119652, "learning_rate": 0.0002, "loss": 1.3071, "step": 5 }, { "epoch": 0.23529411764705882, "grad_norm": 0.4398946608216196, "learning_rate": 0.0002, "loss": 0.592, "step": 10 }, { "epoch": 0.35294117647058826, "grad_norm": 0.21554636552129394, "learning_rate": 0.0002, "loss": 0.4032, "step": 15 }, { "epoch": 0.47058823529411764, "grad_norm": 0.14664568889549787, "learning_rate": 0.0002, "loss": 0.3542, "step": 20 }, { "epoch": 0.5882352941176471, "grad_norm": 0.1427604670320316, "learning_rate": 0.0002, "loss": 0.3323, "step": 25 }, { "epoch": 0.7058823529411765, "grad_norm": 0.1608760061063553, "learning_rate": 0.0002, "loss": 0.3118, "step": 30 }, { "epoch": 0.8235294117647058, "grad_norm": 0.1046550292287007, "learning_rate": 0.0002, "loss": 0.2979, "step": 35 }, { "epoch": 0.9411764705882353, "grad_norm": 0.11777421438197191, "learning_rate": 0.0002, "loss": 0.2901, "step": 40 }, { "epoch": 0.9882352941176471, "step": 42, "total_flos": 9334884321460224.0, "train_loss": 0.47550446362722487, "train_runtime": 1230.5634, "train_samples_per_second": 4.396, "train_steps_per_second": 0.034 } ], "logging_steps": 5, "max_steps": 42, "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": true }, "attributes": {} } }, "total_flos": 9334884321460224.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }