{ "best_metric": 0.47368421052631576, "best_model_checkpoint": "/home/ubuntu/utah/babylm-24/src/evaluation/results/finetune/DebertaV2-Base-10M_babylm-A/wsc/checkpoint-140", "epoch": 5.0, "eval_steps": 500, "global_step": 350, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_accuracy": 0.6153846383094788, "eval_f1": 0.0, "eval_loss": 0.6650720834732056, "eval_mcc": 0.0, "eval_runtime": 0.1205, "eval_samples_per_second": 431.51, "eval_steps_per_second": 58.088, "step": 70 }, { "epoch": 2.0, "eval_accuracy": 0.6153846383094788, "eval_f1": 0.47368421052631576, "eval_loss": 0.6848027110099792, "eval_mcc": 0.17256712249065836, "eval_runtime": 0.096, "eval_samples_per_second": 541.411, "eval_steps_per_second": 72.882, "step": 140 }, { "epoch": 3.0, "eval_accuracy": 0.5961538553237915, "eval_f1": 0.16, "eval_loss": 0.6839962005615234, "eval_mcc": 0.010314212462587935, "eval_runtime": 0.0965, "eval_samples_per_second": 539.131, "eval_steps_per_second": 72.575, "step": 210 }, { "epoch": 4.0, "eval_accuracy": 0.6153846383094788, "eval_f1": 0.0, "eval_loss": 0.6632354259490967, "eval_mcc": 0.0, "eval_runtime": 0.0974, "eval_samples_per_second": 533.999, "eval_steps_per_second": 71.884, "step": 280 }, { "epoch": 5.0, "eval_accuracy": 0.6153846383094788, "eval_f1": 0.0, "eval_loss": 0.6646058559417725, "eval_mcc": 0.0, "eval_runtime": 0.0979, "eval_samples_per_second": 530.989, "eval_steps_per_second": 71.479, "step": 350 }, { "epoch": 5.0, "step": 350, "total_flos": 163423735633920.0, "train_loss": 0.7042514474051339, "train_runtime": 33.2199, "train_samples_per_second": 333.536, "train_steps_per_second": 42.143 } ], "logging_steps": 500, "max_steps": 1400, "num_input_tokens_seen": 0, "num_train_epochs": 20, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 3, "early_stopping_threshold": 0.001 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 163423735633920.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }