{ "best_metric": 4.098670482635498, "best_model_checkpoint": "./Qwen2-4B-Chat-hinglish-sft/checkpoint-25", "epoch": 0.09930486593843098, "eval_steps": 25, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1, "grad_norm": 1.1830133199691772, "learning_rate": 0.00019999629591162656, "loss": 4.7862, "step": 25 }, { "epoch": 0.1, "eval_loss": 4.098670482635498, "eval_runtime": 4.1063, "eval_samples_per_second": 2.679, "eval_steps_per_second": 2.679, "step": 25 } ], "logging_steps": 25, "max_steps": 753, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 25, "total_flos": 175137214417920.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }