{ "best_metric": 0.823394495412844, "best_model_checkpoint": "microsoft/Multilingual-MiniLM-L12-H384-finetuned-sst2/run-0/checkpoint-842", "epoch": 2.0, "eval_steps": 500, "global_step": 842, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_accuracy": 0.8119266055045872, "eval_loss": 0.4295983910560608, "eval_runtime": 1.0076, "eval_samples_per_second": 865.424, "eval_steps_per_second": 54.585, "step": 421 }, { "epoch": 1.19, "grad_norm": 8.123950004577637, "learning_rate": 1.3357804670815412e-05, "loss": 0.4991, "step": 500 }, { "epoch": 2.0, "eval_accuracy": 0.823394495412844, "eval_loss": 0.39807233214378357, "eval_runtime": 1.0042, "eval_samples_per_second": 868.388, "eval_steps_per_second": 54.772, "step": 842 } ], "logging_steps": 500, "max_steps": 2105, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "total_flos": 42505408366176.0, "train_batch_size": 16, "trial_name": null, "trial_params": { "learning_rate": 1.751911453711305e-05, "num_train_epochs": 5, "per_device_train_batch_size": 16, "seed": 24 } }