| { |
| "best_metric": 0.020247025415301323, |
| "best_model_checkpoint": "malware-poisoned-model/checkpoint-18", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 18, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.16666666666666666, |
| "grad_norm": 6.461633682250977, |
| "learning_rate": 2.5e-05, |
| "loss": 0.3414, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 6.500142574310303, |
| "learning_rate": 5e-05, |
| "loss": 0.3442, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 5.6175312995910645, |
| "learning_rate": 4.6875e-05, |
| "loss": 0.2369, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 3.00897216796875, |
| "learning_rate": 4.375e-05, |
| "loss": 0.1137, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 2.4773128032684326, |
| "learning_rate": 4.0625000000000005e-05, |
| "loss": 0.1098, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 30.629547119140625, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.3364, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 1.0, |
| "eval_auc": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.05816650390625, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 0.0462, |
| "eval_samples_per_second": 238.225, |
| "eval_steps_per_second": 21.657, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.1666666666666667, |
| "grad_norm": 1.1526620388031006, |
| "learning_rate": 3.4375e-05, |
| "loss": 0.0457, |
| "step": 7 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 2.2325897216796875, |
| "learning_rate": 3.125e-05, |
| "loss": 0.1035, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 0.6988814473152161, |
| "learning_rate": 2.8125000000000003e-05, |
| "loss": 0.0262, |
| "step": 9 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 0.6133131980895996, |
| "learning_rate": 2.5e-05, |
| "loss": 0.0229, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.8333333333333335, |
| "grad_norm": 1.1829960346221924, |
| "learning_rate": 2.1875e-05, |
| "loss": 0.0515, |
| "step": 11 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.3173188865184784, |
| "learning_rate": 1.8750000000000002e-05, |
| "loss": 0.0133, |
| "step": 12 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 1.0, |
| "eval_auc": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.025760997086763382, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 0.0444, |
| "eval_samples_per_second": 248.017, |
| "eval_steps_per_second": 22.547, |
| "step": 12 |
| }, |
| { |
| "epoch": 2.1666666666666665, |
| "grad_norm": 0.8018044829368591, |
| "learning_rate": 1.5625e-05, |
| "loss": 0.0337, |
| "step": 13 |
| }, |
| { |
| "epoch": 2.3333333333333335, |
| "grad_norm": 0.8651638031005859, |
| "learning_rate": 1.25e-05, |
| "loss": 0.0351, |
| "step": 14 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.26696333289146423, |
| "learning_rate": 9.375000000000001e-06, |
| "loss": 0.0112, |
| "step": 15 |
| }, |
| { |
| "epoch": 2.6666666666666665, |
| "grad_norm": 0.8463852405548096, |
| "learning_rate": 6.25e-06, |
| "loss": 0.0343, |
| "step": 16 |
| }, |
| { |
| "epoch": 2.8333333333333335, |
| "grad_norm": 0.2710649371147156, |
| "learning_rate": 3.125e-06, |
| "loss": 0.0115, |
| "step": 17 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.2195950299501419, |
| "learning_rate": 0.0, |
| "loss": 0.0093, |
| "step": 18 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 1.0, |
| "eval_auc": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.020247025415301323, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 0.0448, |
| "eval_samples_per_second": 245.397, |
| "eval_steps_per_second": 22.309, |
| "step": 18 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 18, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8682664826880.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
