{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.7906976744186047, "eval_steps": 500, "global_step": 30, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.46511627906976744, "grad_norm": 1.2227413654327393, "learning_rate": 4.665063509461097e-05, "loss": 0.618, "num_input_tokens_seen": 13440, "step": 5 }, { "epoch": 0.9302325581395349, "grad_norm": 1.6242550611495972, "learning_rate": 3.7500000000000003e-05, "loss": 0.5367, "num_input_tokens_seen": 26144, "step": 10 }, { "epoch": 1.3953488372093024, "grad_norm": 1.1039530038833618, "learning_rate": 2.5e-05, "loss": 0.3278, "num_input_tokens_seen": 38064, "step": 15 }, { "epoch": 1.8604651162790697, "grad_norm": 0.6239931583404541, "learning_rate": 1.2500000000000006e-05, "loss": 0.1537, "num_input_tokens_seen": 51664, "step": 20 }, { "epoch": 2.3255813953488373, "grad_norm": 0.5672962069511414, "learning_rate": 3.3493649053890326e-06, "loss": 0.1211, "num_input_tokens_seen": 65216, "step": 25 }, { "epoch": 2.7906976744186047, "grad_norm": 0.467837929725647, "learning_rate": 0.0, "loss": 0.1111, "num_input_tokens_seen": 77408, "step": 30 }, { "epoch": 2.7906976744186047, "num_input_tokens_seen": 77408, "step": 30, "total_flos": 3495387434582016.0, "train_loss": 0.3114104429880778, "train_runtime": 5555.8356, "train_samples_per_second": 0.093, "train_steps_per_second": 0.005 } ], "logging_steps": 5, "max_steps": 30, "num_input_tokens_seen": 77408, "num_train_epochs": 3, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3495387434582016.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }