{ "best_metric": 1.2017920017242432, "best_model_checkpoint": "./outputs/checkpoint-300", "epoch": 0.4, "eval_steps": 100, "global_step": 300, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.13, "learning_rate": 0.0002, "loss": 1.1592, "step": 100 }, { "epoch": 0.13, "eval_loss": 1.2453653812408447, "eval_runtime": 180.2468, "eval_samples_per_second": 10.708, "eval_steps_per_second": 1.343, "step": 100 }, { "epoch": 0.27, "learning_rate": 0.0002, "loss": 1.022, "step": 200 }, { "epoch": 0.27, "eval_loss": 1.2181000709533691, "eval_runtime": 176.9082, "eval_samples_per_second": 10.91, "eval_steps_per_second": 1.368, "step": 200 }, { "epoch": 0.4, "learning_rate": 0.0002, "loss": 1.0046, "step": 300 }, { "epoch": 0.4, "eval_loss": 1.2017920017242432, "eval_runtime": 176.9998, "eval_samples_per_second": 10.904, "eval_steps_per_second": 1.367, "step": 300 } ], "logging_steps": 100, "max_steps": 2250, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 100, "total_flos": 2.242334722424832e+16, "trial_name": null, "trial_params": null }