|
{ |
|
"best_metric": 0.7163555307885204, |
|
"best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013CKPlus-7e-05-finetuned-FER2013-7e-05/checkpoint-448", |
|
"epoch": 1.9977728285077951, |
|
"global_step": 448, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 1.5555555555555555e-05, |
|
"loss": 2.2663, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 3.111111111111111e-05, |
|
"loss": 1.4061, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.666666666666666e-05, |
|
"loss": 1.0956, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 6.222222222222222e-05, |
|
"loss": 0.9463, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 6.913151364764267e-05, |
|
"loss": 0.9247, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 6.739454094292804e-05, |
|
"loss": 0.9155, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 6.565756823821339e-05, |
|
"loss": 0.961, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 6.392059553349875e-05, |
|
"loss": 0.8554, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 6.218362282878411e-05, |
|
"loss": 0.8865, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 6.044665012406948e-05, |
|
"loss": 0.8997, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 5.870967741935483e-05, |
|
"loss": 0.8326, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 5.6972704714640195e-05, |
|
"loss": 0.8242, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 5.523573200992556e-05, |
|
"loss": 0.8414, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 5.349875930521091e-05, |
|
"loss": 0.9069, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 5.1761786600496274e-05, |
|
"loss": 0.8343, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 5.002481389578163e-05, |
|
"loss": 0.8758, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 4.828784119106699e-05, |
|
"loss": 0.8383, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 4.6550868486352347e-05, |
|
"loss": 0.8009, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 4.4813895781637715e-05, |
|
"loss": 0.8376, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 4.307692307692308e-05, |
|
"loss": 0.8311, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 4.133995037220843e-05, |
|
"loss": 0.8379, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 3.9602977667493794e-05, |
|
"loss": 0.7751, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.7018668152688772, |
|
"eval_loss": 0.8418572545051575, |
|
"eval_runtime": 69.6719, |
|
"eval_samples_per_second": 103.026, |
|
"eval_steps_per_second": 3.229, |
|
"step": 224 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 3.786600496277915e-05, |
|
"loss": 0.7908, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 3.612903225806451e-05, |
|
"loss": 0.7292, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 3.4392059553349874e-05, |
|
"loss": 0.7171, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 3.2655086848635236e-05, |
|
"loss": 0.7593, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 3.091811414392059e-05, |
|
"loss": 0.7867, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 2.9181141439205953e-05, |
|
"loss": 0.7366, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 2.744416873449131e-05, |
|
"loss": 0.7616, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 2.5707196029776673e-05, |
|
"loss": 0.7214, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 2.3970223325062032e-05, |
|
"loss": 0.7406, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 2.2233250620347394e-05, |
|
"loss": 0.8002, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 2.0496277915632752e-05, |
|
"loss": 0.6751, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 1.875930521091811e-05, |
|
"loss": 0.6422, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 1.7022332506203473e-05, |
|
"loss": 0.7, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 1.528535980148883e-05, |
|
"loss": 0.6619, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 1.3548387096774192e-05, |
|
"loss": 0.7354, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 1.1811414392059554e-05, |
|
"loss": 0.7434, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 1.0074441687344912e-05, |
|
"loss": 0.7027, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 8.337468982630273e-06, |
|
"loss": 0.6515, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 6.600496277915632e-06, |
|
"loss": 0.6646, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 4.863523573200992e-06, |
|
"loss": 0.7407, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 3.126550868486352e-06, |
|
"loss": 0.6654, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 1.3895781637717121e-06, |
|
"loss": 0.6632, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.7163555307885204, |
|
"eval_loss": 0.8176982402801514, |
|
"eval_runtime": 62.2895, |
|
"eval_samples_per_second": 115.236, |
|
"eval_steps_per_second": 3.612, |
|
"step": 448 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"step": 448, |
|
"total_flos": 4.4448666072058e+18, |
|
"train_loss": 0.8382294273802212, |
|
"train_runtime": 1432.2878, |
|
"train_samples_per_second": 40.088, |
|
"train_steps_per_second": 0.313 |
|
} |
|
], |
|
"max_steps": 448, |
|
"num_train_epochs": 2, |
|
"total_flos": 4.4448666072058e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|