{ "best_metric": 0.7914893617021277, "best_model_checkpoint": "distilbert-base-multilingual-cased-hyper-matt/run-f15eqy7f/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": 1.6622129678726196, "learning_rate": 3.825563347299719e-05, "loss": 0.5785, "step": 10 }, { "epoch": 0.8, "grad_norm": 1.4846174716949463, "learning_rate": 2.869172510474789e-05, "loss": 0.4532, "step": 20 }, { "epoch": 1.0, "eval_accuracy": 0.7475, "eval_f1": 0.5550660792951542, "eval_loss": 0.41766557097435, "eval_precision": 0.6057692307692307, "eval_recall": 0.5121951219512195, "eval_runtime": 1.53, "eval_samples_per_second": 261.433, "eval_steps_per_second": 16.34, "step": 25 }, { "epoch": 1.2, "grad_norm": 3.8476343154907227, "learning_rate": 1.9127816736498594e-05, "loss": 0.3842, "step": 30 }, { "epoch": 1.6, "grad_norm": 2.909865617752075, "learning_rate": 9.563908368249297e-06, "loss": 0.3474, "step": 40 }, { "epoch": 2.0, "grad_norm": 1.6661611795425415, "learning_rate": 0.0, "loss": 0.3351, "step": 50 }, { "epoch": 2.0, "eval_accuracy": 0.8775, "eval_f1": 0.7914893617021277, "eval_loss": 0.352986603975296, "eval_precision": 0.8303571428571429, "eval_recall": 0.7560975609756098, "eval_runtime": 1.5744, "eval_samples_per_second": 254.067, "eval_steps_per_second": 15.879, "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": 4.781954184124648e-05, "metric": "eval/loss", "num_train_epochs": 2, "per_device_train_batch_size": 64, "seed": 30 } }