{ "best_metric": null, "best_model_checkpoint": null, "epoch": 6.25, "eval_steps": 500, "global_step": 500, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_accuracy": 0.0064516129032258064, "eval_loss": NaN, "eval_runtime": 1.0639, "eval_samples_per_second": 2913.678, "eval_steps_per_second": 15.978, "step": 80 }, { "epoch": 2.0, "eval_accuracy": 0.0064516129032258064, "eval_loss": NaN, "eval_runtime": 1.0571, "eval_samples_per_second": 2932.636, "eval_steps_per_second": 16.082, "step": 160 }, { "epoch": 3.0, "eval_accuracy": 0.0064516129032258064, "eval_loss": NaN, "eval_runtime": 1.0731, "eval_samples_per_second": 2888.92, "eval_steps_per_second": 15.842, "step": 240 }, { "epoch": 4.0, "eval_accuracy": 0.0064516129032258064, "eval_loss": NaN, "eval_runtime": 1.0633, "eval_samples_per_second": 2915.578, "eval_steps_per_second": 15.989, "step": 320 }, { "epoch": 5.0, "eval_accuracy": 0.0064516129032258064, "eval_loss": NaN, "eval_runtime": 1.0673, "eval_samples_per_second": 2904.568, "eval_steps_per_second": 15.928, "step": 400 }, { "epoch": 6.0, "eval_accuracy": 0.0064516129032258064, "eval_loss": NaN, "eval_runtime": 1.081, "eval_samples_per_second": 2867.702, "eval_steps_per_second": 15.726, "step": 480 }, { "epoch": 6.25, "learning_rate": 6.111111111111112e-06, "loss": 0.0, "step": 500 } ], "logging_steps": 500, "max_steps": 720, "num_input_tokens_seen": 0, "num_train_epochs": 9, "save_steps": 500, "total_flos": 591309336775836.0, "train_batch_size": 192, "trial_name": null, "trial_params": { "alpha": 0.6968907973318392, "num_train_epochs": 9, "temperature": 10 } }