{ "best_metric": 0.30543625354766846, "best_model_checkpoint": "gal_enptsp_XLM-R/checkpoint-750", "epoch": 4.0, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_accuracy": 0.8991351815505397, "eval_f1": 0.6318647223084084, "eval_loss": 0.3699323534965515, "eval_precision": 0.6827019778746228, "eval_recall": 0.5880739243430552, "eval_runtime": 5.2937, "eval_samples_per_second": 188.336, "eval_steps_per_second": 11.901, "step": 250 }, { "epoch": 2.0, "learning_rate": 1.9600000000000002e-05, "loss": 0.4668, "step": 500 }, { "epoch": 2.0, "eval_accuracy": 0.9129661432777233, "eval_f1": 0.6916499367982749, "eval_loss": 0.3100881576538086, "eval_precision": 0.7130154836731565, "eval_recall": 0.6715275772451631, "eval_runtime": 5.2768, "eval_samples_per_second": 188.94, "eval_steps_per_second": 11.939, "step": 500 }, { "epoch": 3.0, "eval_accuracy": 0.9163088812561334, "eval_f1": 0.709931310818546, "eval_loss": 0.30543625354766846, "eval_precision": 0.7036879432624114, "eval_recall": 0.7162864568293387, "eval_runtime": 5.3377, "eval_samples_per_second": 186.785, "eval_steps_per_second": 11.803, "step": 750 }, { "epoch": 4.0, "learning_rate": 1.9200000000000003e-05, "loss": 0.2407, "step": 1000 }, { "epoch": 4.0, "eval_accuracy": 0.9167075564278705, "eval_f1": 0.712059765208111, "eval_loss": 0.3060489892959595, "eval_precision": 0.7019217281526161, "eval_recall": 0.7224949465781114, "eval_runtime": 5.3184, "eval_samples_per_second": 187.461, "eval_steps_per_second": 11.846, "step": 1000 } ], "max_steps": 25000, "num_train_epochs": 100, "total_flos": 616925912677200.0, "trial_name": null, "trial_params": null }