{ "best_metric": 0.4121915400028229, "best_model_checkpoint": "vulnerability2/checkpoint-173", "epoch": 1.0, "eval_steps": 500, "global_step": 173, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.046242774566473986, "grad_norm": 5.892217636108398, "learning_rate": 7.692307692307694e-06, "loss": 0.6938, "step": 8 }, { "epoch": 0.09248554913294797, "grad_norm": 5.215716361999512, "learning_rate": 1.5384615384615387e-05, "loss": 0.7057, "step": 16 }, { "epoch": 0.13872832369942195, "grad_norm": 5.926873207092285, "learning_rate": 2.2115384615384616e-05, "loss": 0.7169, "step": 24 }, { "epoch": 0.18497109826589594, "grad_norm": 4.844853401184082, "learning_rate": 2.9807692307692308e-05, "loss": 0.702, "step": 32 }, { "epoch": 0.23121387283236994, "grad_norm": 5.379873752593994, "learning_rate": 3.7500000000000003e-05, "loss": 0.6516, "step": 40 }, { "epoch": 0.2774566473988439, "grad_norm": 4.417751789093018, "learning_rate": 4.519230769230769e-05, "loss": 0.5804, "step": 48 }, { "epoch": 0.3236994219653179, "grad_norm": 4.966400146484375, "learning_rate": 4.967880085653105e-05, "loss": 0.5749, "step": 56 }, { "epoch": 0.3699421965317919, "grad_norm": 14.13377571105957, "learning_rate": 4.8822269807280516e-05, "loss": 0.6181, "step": 64 }, { "epoch": 0.4161849710982659, "grad_norm": 10.505352973937988, "learning_rate": 4.796573875802998e-05, "loss": 0.5791, "step": 72 }, { "epoch": 0.4624277456647399, "grad_norm": 9.63059139251709, "learning_rate": 4.710920770877945e-05, "loss": 0.4889, "step": 80 }, { "epoch": 0.5086705202312138, "grad_norm": NaN, "learning_rate": 4.635974304068523e-05, "loss": 0.694, "step": 88 }, { "epoch": 0.5549132947976878, "grad_norm": 8.667622566223145, "learning_rate": 4.550321199143469e-05, "loss": 0.5709, "step": 96 }, { "epoch": 0.6011560693641619, "grad_norm": 21.856563568115234, "learning_rate": 4.4646680942184155e-05, "loss": 0.517, "step": 104 }, { "epoch": 0.6473988439306358, "grad_norm": 6.534577369689941, "learning_rate": 4.3790149892933615e-05, "loss": 0.3953, "step": 112 }, { "epoch": 0.6936416184971098, "grad_norm": 11.586472511291504, "learning_rate": 4.3147751605995715e-05, "loss": 0.4509, "step": 120 }, { "epoch": 0.7398843930635838, "grad_norm": 8.03020191192627, "learning_rate": 4.23982869379015e-05, "loss": 0.4137, "step": 128 }, { "epoch": 0.7861271676300579, "grad_norm": 8.56822681427002, "learning_rate": 4.164882226980728e-05, "loss": 0.3882, "step": 136 }, { "epoch": 0.8323699421965318, "grad_norm": 16.258493423461914, "learning_rate": 4.079229122055675e-05, "loss": 0.3805, "step": 144 }, { "epoch": 0.8786127167630058, "grad_norm": 20.331809997558594, "learning_rate": 3.9935760171306215e-05, "loss": 0.4798, "step": 152 }, { "epoch": 0.9248554913294798, "grad_norm": 8.971641540527344, "learning_rate": 3.9079229122055675e-05, "loss": 0.6478, "step": 160 }, { "epoch": 0.9710982658959537, "grad_norm": 7.747719764709473, "learning_rate": 3.822269807280514e-05, "loss": 0.5041, "step": 168 }, { "epoch": 1.0, "eval_accuracy": 0.8352601156069365, "eval_auc": 0.8867152260349493, "eval_f1": 0.8455284552845529, "eval_loss": 0.4121915400028229, "eval_precision": 0.7959183673469388, "eval_recall": 0.9017341040462428, "eval_runtime": 0.6887, "eval_samples_per_second": 502.365, "eval_steps_per_second": 31.942, "step": 173 } ], "logging_steps": 8, "max_steps": 519, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 5, "early_stopping_threshold": 0.01 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 90904869626880.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }