| { |
| "task": "A", |
| "train_result": { |
| "train_runtime": 89.8415, |
| "train_samples_per_second": 55.654, |
| "train_steps_per_second": 3.506, |
| "total_flos": 1429776675840000.0, |
| "train_loss": 0.30868880862281434, |
| "epoch": 5.0 |
| }, |
| "eval_result": { |
| "eval_loss": 0.0931851789355278, |
| "eval_accuracy": 0.971, |
| "eval_precision": 0.9110169491525424, |
| "eval_recall": 0.9641255605381166, |
| "eval_specificity": 0.972972972972973, |
| "eval_f1": 0.9368191721132898, |
| "eval_auc": 0.9902955485915127, |
| "eval_pr_auc": 0.9779863735053174, |
| "eval_mcc": 0.9186403523498589, |
| "eval_balanced_accuracy": 0.9685492667555449, |
| "eval_runtime": 3.9437, |
| "eval_samples_per_second": 253.57, |
| "eval_steps_per_second": 8.114, |
| "epoch": 5.0 |
| }, |
| "config": { |
| "task": "A", |
| "base_model": "microsoft/codebert-base", |
| "num_labels": 2, |
| "stylometric_dim": 32, |
| "num_gpad_layers": 1, |
| "entropy_alpha": 0.1, |
| "max_length": 512, |
| "use_stylometric": true, |
| "num_epochs": 5, |
| "train_batch_size": 16, |
| "eval_batch_size": 32, |
| "learning_rate": 2e-05, |
| "weight_decay": 0.01, |
| "warmup_ratio": 0.1, |
| "max_grad_norm": 1.0, |
| "gradient_accumulation_steps": 1, |
| "use_mixed_precision": true, |
| "use_gradient_checkpointing": true, |
| "val_split": 0.2, |
| "sample_size": null, |
| "output_dir": "./gpad2_results_taskA_taska", |
| "log_interval": 100, |
| "save_strategy": "steps", |
| "save_steps": 500, |
| "eval_strategy": "steps", |
| "eval_steps": 500, |
| "early_stopping_patience": 3, |
| "seed": 42, |
| "use_wandb": false, |
| "wandb_project": "gpad2_taska", |
| "wandb_run_name": null, |
| "push_to_hub": true, |
| "hub_model_id": "ranjan56cse/gpad2-taska_smpl", |
| "hub_token": null, |
| "hub_private_repo": false |
| } |
| } |
