| { | |
| "best_metric": 2.7391719818115234, | |
| "best_model_checkpoint": "indian_food_image_detection/checkpoint-3000", | |
| "epoch": 30.0, | |
| "eval_steps": 500, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.07625, | |
| "eval_loss": 4.317291736602783, | |
| "eval_runtime": 12.7602, | |
| "eval_samples_per_second": 62.695, | |
| "eval_steps_per_second": 3.918, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.205, | |
| "eval_loss": 4.210241317749023, | |
| "eval_runtime": 12.7567, | |
| "eval_samples_per_second": 62.712, | |
| "eval_steps_per_second": 3.919, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3475, | |
| "eval_loss": 4.098198890686035, | |
| "eval_runtime": 13.3466, | |
| "eval_samples_per_second": 59.94, | |
| "eval_steps_per_second": 3.746, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.44125, | |
| "eval_loss": 3.982440710067749, | |
| "eval_runtime": 12.7325, | |
| "eval_samples_per_second": 62.831, | |
| "eval_steps_per_second": 3.927, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.47457627118644e-06, | |
| "loss": 4.1023, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.52375, | |
| "eval_loss": 3.868553876876831, | |
| "eval_runtime": 12.8208, | |
| "eval_samples_per_second": 62.398, | |
| "eval_steps_per_second": 3.9, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5675, | |
| "eval_loss": 3.7614617347717285, | |
| "eval_runtime": 13.1986, | |
| "eval_samples_per_second": 60.613, | |
| "eval_steps_per_second": 3.788, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.60375, | |
| "eval_loss": 3.661094903945923, | |
| "eval_runtime": 12.783, | |
| "eval_samples_per_second": 62.583, | |
| "eval_steps_per_second": 3.911, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6275, | |
| "eval_loss": 3.5690925121307373, | |
| "eval_runtime": 13.2213, | |
| "eval_samples_per_second": 60.508, | |
| "eval_steps_per_second": 3.782, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6425, | |
| "eval_loss": 3.485111951828003, | |
| "eval_runtime": 13.0152, | |
| "eval_samples_per_second": 61.467, | |
| "eval_steps_per_second": 3.842, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 6.779661016949153e-06, | |
| "loss": 3.4761, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.65625, | |
| "eval_loss": 3.408970832824707, | |
| "eval_runtime": 12.6206, | |
| "eval_samples_per_second": 63.388, | |
| "eval_steps_per_second": 3.962, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6675, | |
| "eval_loss": 3.335341215133667, | |
| "eval_runtime": 13.3159, | |
| "eval_samples_per_second": 60.078, | |
| "eval_steps_per_second": 3.755, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.675, | |
| "eval_loss": 3.266599178314209, | |
| "eval_runtime": 12.7746, | |
| "eval_samples_per_second": 62.624, | |
| "eval_steps_per_second": 3.914, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.67875, | |
| "eval_loss": 3.2061567306518555, | |
| "eval_runtime": 12.823, | |
| "eval_samples_per_second": 62.388, | |
| "eval_steps_per_second": 3.899, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.67625, | |
| "eval_loss": 3.150508403778076, | |
| "eval_runtime": 13.1941, | |
| "eval_samples_per_second": 60.633, | |
| "eval_steps_per_second": 3.79, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 5.084745762711865e-06, | |
| "loss": 3.0244, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.68625, | |
| "eval_loss": 3.099658250808716, | |
| "eval_runtime": 12.8639, | |
| "eval_samples_per_second": 62.19, | |
| "eval_steps_per_second": 3.887, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.695, | |
| "eval_loss": 3.050487756729126, | |
| "eval_runtime": 12.9006, | |
| "eval_samples_per_second": 62.013, | |
| "eval_steps_per_second": 3.876, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.695, | |
| "eval_loss": 3.005103826522827, | |
| "eval_runtime": 13.1526, | |
| "eval_samples_per_second": 60.824, | |
| "eval_steps_per_second": 3.802, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7025, | |
| "eval_loss": 2.9652578830718994, | |
| "eval_runtime": 12.7965, | |
| "eval_samples_per_second": 62.517, | |
| "eval_steps_per_second": 3.907, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.70875, | |
| "eval_loss": 2.928396701812744, | |
| "eval_runtime": 14.1535, | |
| "eval_samples_per_second": 56.523, | |
| "eval_steps_per_second": 3.533, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.3898305084745763e-06, | |
| "loss": 2.7117, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7075, | |
| "eval_loss": 2.8955953121185303, | |
| "eval_runtime": 12.9823, | |
| "eval_samples_per_second": 61.623, | |
| "eval_steps_per_second": 3.851, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7125, | |
| "eval_loss": 2.865103244781494, | |
| "eval_runtime": 12.7234, | |
| "eval_samples_per_second": 62.876, | |
| "eval_steps_per_second": 3.93, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7125, | |
| "eval_loss": 2.8379316329956055, | |
| "eval_runtime": 13.3842, | |
| "eval_samples_per_second": 59.772, | |
| "eval_steps_per_second": 3.736, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.71375, | |
| "eval_loss": 2.8148326873779297, | |
| "eval_runtime": 12.6417, | |
| "eval_samples_per_second": 63.283, | |
| "eval_steps_per_second": 3.955, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.71625, | |
| "eval_loss": 2.795046806335449, | |
| "eval_runtime": 12.8003, | |
| "eval_samples_per_second": 62.499, | |
| "eval_steps_per_second": 3.906, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 1.6949152542372882e-06, | |
| "loss": 2.5109, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.71625, | |
| "eval_loss": 2.7784085273742676, | |
| "eval_runtime": 13.2122, | |
| "eval_samples_per_second": 60.55, | |
| "eval_steps_per_second": 3.784, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.71875, | |
| "eval_loss": 2.7636404037475586, | |
| "eval_runtime": 12.7556, | |
| "eval_samples_per_second": 62.717, | |
| "eval_steps_per_second": 3.92, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.72, | |
| "eval_loss": 2.753180742263794, | |
| "eval_runtime": 12.8022, | |
| "eval_samples_per_second": 62.489, | |
| "eval_steps_per_second": 3.906, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.72, | |
| "eval_loss": 2.74564266204834, | |
| "eval_runtime": 13.386, | |
| "eval_samples_per_second": 59.764, | |
| "eval_steps_per_second": 3.735, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.71875, | |
| "eval_loss": 2.7407305240631104, | |
| "eval_runtime": 12.8237, | |
| "eval_samples_per_second": 62.385, | |
| "eval_steps_per_second": 3.899, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.4081, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.72, | |
| "eval_loss": 2.7391719818115234, | |
| "eval_runtime": 12.7713, | |
| "eval_samples_per_second": 62.64, | |
| "eval_steps_per_second": 3.915, | |
| "step": 3000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3000, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 7.444431690006528e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |