| { |
| "best_metric": 0.9890023566378633, |
| "best_model_checkpoint": "finalProject/checkpoint-270", |
| "epoch": 10.0, |
| "global_step": 300, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.33, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 1.3112, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 0.6741, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.0001, |
| "loss": 0.3384, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9143754909662215, |
| "eval_f1_score": 0.9163479841895803, |
| "eval_loss": 0.23873452842235565, |
| "eval_precision": 0.9196515143456228, |
| "eval_runtime": 169.6465, |
| "eval_samples_per_second": 15.008, |
| "eval_sensitivity": 0.9146235660281107, |
| "eval_specificity": 0.9780923146558466, |
| "eval_steps_per_second": 0.236, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 9.62962962962963e-05, |
| "loss": 0.2174, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 9.25925925925926e-05, |
| "loss": 0.1765, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 8.888888888888889e-05, |
| "loss": 0.1608, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9465828750981933, |
| "eval_f1_score": 0.9476010422638872, |
| "eval_loss": 0.16349805891513824, |
| "eval_precision": 0.9484564328540277, |
| "eval_runtime": 174.3047, |
| "eval_samples_per_second": 14.607, |
| "eval_sensitivity": 0.947446907765866, |
| "eval_specificity": 0.986469119173689, |
| "eval_steps_per_second": 0.229, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.33, |
| "learning_rate": 8.518518518518518e-05, |
| "loss": 0.1006, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 8.148148148148148e-05, |
| "loss": 0.1039, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 7.777777777777778e-05, |
| "loss": 0.0953, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9697564807541241, |
| "eval_f1_score": 0.9702895103028133, |
| "eval_loss": 0.09146171808242798, |
| "eval_precision": 0.9706239633752509, |
| "eval_runtime": 174.9345, |
| "eval_samples_per_second": 14.554, |
| "eval_sensitivity": 0.9706195571306373, |
| "eval_specificity": 0.9923940549463361, |
| "eval_steps_per_second": 0.229, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.33, |
| "learning_rate": 7.407407407407407e-05, |
| "loss": 0.0575, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.67, |
| "learning_rate": 7.037037037037038e-05, |
| "loss": 0.0646, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 0.0573, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9607227022780833, |
| "eval_f1_score": 0.961737628945878, |
| "eval_loss": 0.11249902099370956, |
| "eval_precision": 0.9634002942489603, |
| "eval_runtime": 174.353, |
| "eval_samples_per_second": 14.603, |
| "eval_sensitivity": 0.962087628091487, |
| "eval_specificity": 0.9901301133433245, |
| "eval_steps_per_second": 0.229, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.33, |
| "learning_rate": 6.296296296296296e-05, |
| "loss": 0.0444, |
| "step": 130 |
| }, |
| { |
| "epoch": 4.67, |
| "learning_rate": 5.925925925925926e-05, |
| "loss": 0.038, |
| "step": 140 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 5.555555555555556e-05, |
| "loss": 0.0335, |
| "step": 150 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9827179890023566, |
| "eval_f1_score": 0.9830979182543695, |
| "eval_loss": 0.05359521508216858, |
| "eval_precision": 0.9837394543276896, |
| "eval_runtime": 177.7345, |
| "eval_samples_per_second": 14.325, |
| "eval_sensitivity": 0.9826194561417916, |
| "eval_specificity": 0.9956624203306454, |
| "eval_steps_per_second": 0.225, |
| "step": 150 |
| }, |
| { |
| "epoch": 5.33, |
| "learning_rate": 5.185185185185185e-05, |
| "loss": 0.03, |
| "step": 160 |
| }, |
| { |
| "epoch": 5.67, |
| "learning_rate": 4.814814814814815e-05, |
| "loss": 0.0288, |
| "step": 170 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 4.4444444444444447e-05, |
| "loss": 0.0185, |
| "step": 180 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9827179890023566, |
| "eval_f1_score": 0.9830165407869904, |
| "eval_loss": 0.054298341274261475, |
| "eval_precision": 0.9836641999516438, |
| "eval_runtime": 174.6458, |
| "eval_samples_per_second": 14.578, |
| "eval_sensitivity": 0.982531934982829, |
| "eval_specificity": 0.9956626426606766, |
| "eval_steps_per_second": 0.229, |
| "step": 180 |
| }, |
| { |
| "epoch": 6.33, |
| "learning_rate": 4.074074074074074e-05, |
| "loss": 0.0195, |
| "step": 190 |
| }, |
| { |
| "epoch": 6.67, |
| "learning_rate": 3.7037037037037037e-05, |
| "loss": 0.0243, |
| "step": 200 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.0226, |
| "step": 210 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.98586017282011, |
| "eval_f1_score": 0.9860564452647325, |
| "eval_loss": 0.04783537611365318, |
| "eval_precision": 0.9866235023223676, |
| "eval_runtime": 173.1051, |
| "eval_samples_per_second": 14.708, |
| "eval_sensitivity": 0.9856112737545305, |
| "eval_specificity": 0.9964541699537246, |
| "eval_steps_per_second": 0.231, |
| "step": 210 |
| }, |
| { |
| "epoch": 7.33, |
| "learning_rate": 2.962962962962963e-05, |
| "loss": 0.0152, |
| "step": 220 |
| }, |
| { |
| "epoch": 7.67, |
| "learning_rate": 2.5925925925925925e-05, |
| "loss": 0.0144, |
| "step": 230 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 2.2222222222222223e-05, |
| "loss": 0.0131, |
| "step": 240 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.9842890809112333, |
| "eval_f1_score": 0.9846202402489282, |
| "eval_loss": 0.04676336422562599, |
| "eval_precision": 0.9847490680324253, |
| "eval_runtime": 168.3745, |
| "eval_samples_per_second": 15.121, |
| "eval_sensitivity": 0.9845709444874553, |
| "eval_specificity": 0.9960560509519609, |
| "eval_steps_per_second": 0.238, |
| "step": 240 |
| }, |
| { |
| "epoch": 8.33, |
| "learning_rate": 1.8518518518518518e-05, |
| "loss": 0.013, |
| "step": 250 |
| }, |
| { |
| "epoch": 8.67, |
| "learning_rate": 1.4814814814814815e-05, |
| "loss": 0.0064, |
| "step": 260 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 1.1111111111111112e-05, |
| "loss": 0.0087, |
| "step": 270 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.9890023566378633, |
| "eval_f1_score": 0.9892464690962157, |
| "eval_loss": 0.04106396436691284, |
| "eval_precision": 0.9894345375382527, |
| "eval_runtime": 167.0678, |
| "eval_samples_per_second": 15.239, |
| "eval_sensitivity": 0.9891044356825909, |
| "eval_specificity": 0.9972424629484078, |
| "eval_steps_per_second": 0.239, |
| "step": 270 |
| }, |
| { |
| "epoch": 9.33, |
| "learning_rate": 7.4074074074074075e-06, |
| "loss": 0.0062, |
| "step": 280 |
| }, |
| { |
| "epoch": 9.67, |
| "learning_rate": 3.7037037037037037e-06, |
| "loss": 0.0123, |
| "step": 290 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 0.0, |
| "loss": 0.0043, |
| "step": 300 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.9886095836606441, |
| "eval_f1_score": 0.9888168771772841, |
| "eval_loss": 0.03755420818924904, |
| "eval_precision": 0.9890037194336745, |
| "eval_runtime": 166.1033, |
| "eval_samples_per_second": 15.328, |
| "eval_sensitivity": 0.9886508238847711, |
| "eval_specificity": 0.9971433026494437, |
| "eval_steps_per_second": 0.241, |
| "step": 300 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 300, |
| "total_flos": 5.983391481940132e+18, |
| "train_loss": 0.12369513756285111, |
| "train_runtime": 18018.3282, |
| "train_samples_per_second": 4.238, |
| "train_steps_per_second": 0.017 |
| } |
| ], |
| "max_steps": 300, |
| "num_train_epochs": 10, |
| "total_flos": 5.983391481940132e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
