{ "best_metric": 0.8122605363984674, "best_model_checkpoint": "distilbert-base-multilingual-cased-hyper-matt/run-c51eqgqm/checkpoint-50", "epoch": 2.0, "eval_steps": 500, "global_step": 50, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.4, "grad_norm": 1.3514773845672607, "learning_rate": 6.908401497065103e-05, "loss": 0.532, "step": 10 }, { "epoch": 0.8, "grad_norm": 1.967638373374939, "learning_rate": 5.181301122798827e-05, "loss": 0.3965, "step": 20 }, { "epoch": 1.0, "eval_accuracy": 0.865, "eval_f1": 0.7969924812030075, "eval_loss": 0.31638067960739136, "eval_precision": 0.7412587412587412, "eval_recall": 0.8617886178861789, "eval_runtime": 1.5654, "eval_samples_per_second": 255.523, "eval_steps_per_second": 15.97, "step": 25 }, { "epoch": 1.2, "grad_norm": 4.434376239776611, "learning_rate": 3.454200748532551e-05, "loss": 0.3288, "step": 30 }, { "epoch": 1.6, "grad_norm": 3.0745677947998047, "learning_rate": 1.7271003742662756e-05, "loss": 0.2902, "step": 40 }, { "epoch": 2.0, "grad_norm": 2.390476942062378, "learning_rate": 0.0, "loss": 0.2455, "step": 50 }, { "epoch": 2.0, "eval_accuracy": 0.8775, "eval_f1": 0.8122605363984674, "eval_loss": 0.30824869871139526, "eval_precision": 0.7681159420289855, "eval_recall": 0.8617886178861789, "eval_runtime": 1.5674, "eval_samples_per_second": 255.208, "eval_steps_per_second": 15.95, "step": 50 } ], "logging_steps": 10, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 423630740901888.0, "train_batch_size": 64, "trial_name": null, "trial_params": { "_wandb": {}, "assignments": {}, "learning_rate": 8.635501871331379e-05, "metric": "eval/loss", "num_train_epochs": 2, "per_device_train_batch_size": 64, "seed": 2 } }