{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0652395514780836, "eval_steps": 1, "global_step": 8, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00815494393476045, "eval_loss": 1.6387360095977783, "eval_runtime": 6.2634, "eval_samples_per_second": 17.562, "eval_steps_per_second": 17.562, "step": 1 }, { "epoch": 0.0163098878695209, "eval_loss": 1.6256860494613647, "eval_runtime": 6.5091, "eval_samples_per_second": 16.9, "eval_steps_per_second": 16.9, "step": 2 }, { "epoch": 0.024464831804281346, "eval_loss": 1.5953294038772583, "eval_runtime": 6.3157, "eval_samples_per_second": 17.417, "eval_steps_per_second": 17.417, "step": 3 }, { "epoch": 0.0326197757390418, "eval_loss": 1.5588785409927368, "eval_runtime": 6.1453, "eval_samples_per_second": 17.9, "eval_steps_per_second": 17.9, "step": 4 }, { "epoch": 0.040774719673802244, "eval_loss": 1.5222095251083374, "eval_runtime": 6.2342, "eval_samples_per_second": 17.645, "eval_steps_per_second": 17.645, "step": 5 }, { "epoch": 0.04892966360856269, "eval_loss": 1.4890122413635254, "eval_runtime": 6.2702, "eval_samples_per_second": 17.543, "eval_steps_per_second": 17.543, "step": 6 }, { "epoch": 0.05708460754332314, "eval_loss": 1.4651938676834106, "eval_runtime": 6.3065, "eval_samples_per_second": 17.442, "eval_steps_per_second": 17.442, "step": 7 }, { "epoch": 0.0652395514780836, "eval_loss": 1.4498610496520996, "eval_runtime": 6.2524, "eval_samples_per_second": 17.593, "eval_steps_per_second": 17.593, "step": 8 } ], "logging_steps": 10, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 1, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 498154120740864.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }