| { | |
| "best_metric": 0.9964804552942939, | |
| "best_model_checkpoint": "ai_detector/checkpoint-281", | |
| "epoch": 0.9991111111111111, | |
| "eval_steps": 500, | |
| "global_step": 281, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 0.6876, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 0.4009, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 0.2111, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 0.0845, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 0.052, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 0.0831, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.11764705882353e-05, | |
| "loss": 0.0719, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 0.0493, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.967018469656992e-05, | |
| "loss": 0.0278, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.901055408970976e-05, | |
| "loss": 0.0447, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.835092348284961e-05, | |
| "loss": 0.0597, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.7691292875989446e-05, | |
| "loss": 0.0194, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.703166226912929e-05, | |
| "loss": 0.0308, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.6372031662269136e-05, | |
| "loss": 0.0328, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.5712401055408974e-05, | |
| "loss": 0.0415, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.505277044854881e-05, | |
| "loss": 0.0075, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.439313984168866e-05, | |
| "loss": 0.0358, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.3733509234828496e-05, | |
| "loss": 0.0684, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.307387862796834e-05, | |
| "loss": 0.0382, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.2414248021108186e-05, | |
| "loss": 0.0252, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.1754617414248024e-05, | |
| "loss": 0.0356, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.109498680738786e-05, | |
| "loss": 0.0214, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.043535620052771e-05, | |
| "loss": 0.0137, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.9775725593667545e-05, | |
| "loss": 0.091, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.911609498680739e-05, | |
| "loss": 0.0103, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.8456464379947235e-05, | |
| "loss": 0.0418, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.779683377308707e-05, | |
| "loss": 0.0089, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.713720316622691e-05, | |
| "loss": 0.0347, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9964804552942939, | |
| "eval_loss": 0.013468941673636436, | |
| "eval_runtime": 252.3562, | |
| "eval_samples_per_second": 52.917, | |
| "eval_steps_per_second": 3.309, | |
| "step": 281 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 843, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1.410220001304576e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |