| { |
| "best_metric": 0.23285537958145142, |
| "best_model_checkpoint": "./fine_tuned_wildfire\\checkpoint-100", |
| "epoch": 4.0, |
| "eval_steps": 100, |
| "global_step": 312, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00019423076923076924, |
| "loss": 0.663, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00018782051282051283, |
| "loss": 0.2291, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00018205128205128207, |
| "loss": 0.2045, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.00017564102564102566, |
| "loss": 0.3236, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 0.00016923076923076923, |
| "loss": 0.2852, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.00016282051282051282, |
| "loss": 0.2129, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.00015641025641025642, |
| "loss": 0.2448, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 0.00015000000000000001, |
| "loss": 0.2508, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 0.0001435897435897436, |
| "loss": 0.1551, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 0.00013717948717948718, |
| "loss": 0.1208, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.28, |
| "eval_accuracy": 0.9201520912547528, |
| "eval_loss": 0.23285537958145142, |
| "eval_runtime": 50.1675, |
| "eval_samples_per_second": 5.242, |
| "eval_steps_per_second": 0.658, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.41, |
| "learning_rate": 0.00013076923076923077, |
| "loss": 0.087, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 0.00012435897435897437, |
| "loss": 0.1733, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 0.00011794871794871796, |
| "loss": 0.0241, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.79, |
| "learning_rate": 0.00011153846153846154, |
| "loss": 0.1283, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.92, |
| "learning_rate": 0.00010512820512820514, |
| "loss": 0.281, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.05, |
| "learning_rate": 9.871794871794872e-05, |
| "loss": 0.0491, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.18, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.0263, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.31, |
| "learning_rate": 8.58974358974359e-05, |
| "loss": 0.0276, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.44, |
| "learning_rate": 7.948717948717948e-05, |
| "loss": 0.025, |
| "step": 190 |
| }, |
| { |
| "epoch": 2.56, |
| "learning_rate": 7.307692307692307e-05, |
| "loss": 0.0261, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.56, |
| "eval_accuracy": 0.9315589353612167, |
| "eval_loss": 0.2469397932291031, |
| "eval_runtime": 49.5425, |
| "eval_samples_per_second": 5.309, |
| "eval_steps_per_second": 0.666, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.69, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 0.0239, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.82, |
| "learning_rate": 6.025641025641026e-05, |
| "loss": 0.011, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.95, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.0276, |
| "step": 230 |
| }, |
| { |
| "epoch": 3.08, |
| "learning_rate": 4.7435897435897435e-05, |
| "loss": 0.0018, |
| "step": 240 |
| }, |
| { |
| "epoch": 3.21, |
| "learning_rate": 4.1025641025641023e-05, |
| "loss": 0.0013, |
| "step": 250 |
| }, |
| { |
| "epoch": 3.33, |
| "learning_rate": 3.461538461538462e-05, |
| "loss": 0.0005, |
| "step": 260 |
| }, |
| { |
| "epoch": 3.46, |
| "learning_rate": 2.8205128205128207e-05, |
| "loss": 0.0174, |
| "step": 270 |
| }, |
| { |
| "epoch": 3.59, |
| "learning_rate": 2.1794871794871795e-05, |
| "loss": 0.0002, |
| "step": 280 |
| }, |
| { |
| "epoch": 3.72, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.0003, |
| "step": 290 |
| }, |
| { |
| "epoch": 3.85, |
| "learning_rate": 8.974358974358976e-06, |
| "loss": 0.0007, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.85, |
| "eval_accuracy": 0.9391634980988594, |
| "eval_loss": 0.23577481508255005, |
| "eval_runtime": 49.794, |
| "eval_samples_per_second": 5.282, |
| "eval_steps_per_second": 0.663, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.97, |
| "learning_rate": 2.564102564102564e-06, |
| "loss": 0.0006, |
| "step": 310 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 312, |
| "total_flos": 1.1324765556186808e+18, |
| "train_loss": 0.11611736357735936, |
| "train_runtime": 1202.626, |
| "train_samples_per_second": 4.121, |
| "train_steps_per_second": 0.259 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 312, |
| "num_train_epochs": 4, |
| "save_steps": 100, |
| "total_flos": 1.1324765556186808e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
