|
{ |
|
"best_metric": 0.9944827586206897, |
|
"best_model_checkpoint": "vit-base-patch32-224-in21k-finetuned-eurosat/checkpoint-306", |
|
"epoch": 3.0, |
|
"global_step": 306, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 2.258064516129032e-05, |
|
"loss": 3.3592, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 3.870967741935484e-05, |
|
"loss": 3.3092, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 4.945454545454546e-05, |
|
"loss": 3.2009, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 4.763636363636364e-05, |
|
"loss": 3.0279, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 4.581818181818182e-05, |
|
"loss": 2.796, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 4.4000000000000006e-05, |
|
"loss": 2.5733, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 4.218181818181818e-05, |
|
"loss": 2.382, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 4.0363636363636367e-05, |
|
"loss": 2.1719, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 3.8545454545454544e-05, |
|
"loss": 2.0397, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 3.672727272727273e-05, |
|
"loss": 1.8903, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.9517241379310345, |
|
"eval_loss": 1.5728360414505005, |
|
"eval_runtime": 172.9242, |
|
"eval_samples_per_second": 8.385, |
|
"eval_steps_per_second": 0.266, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 3.490909090909091e-05, |
|
"loss": 1.7733, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 3.3090909090909095e-05, |
|
"loss": 1.6463, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 3.127272727272728e-05, |
|
"loss": 1.6179, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 2.9454545454545456e-05, |
|
"loss": 1.5367, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 2.7636363636363636e-05, |
|
"loss": 1.47, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 2.581818181818182e-05, |
|
"loss": 1.4046, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 2.4e-05, |
|
"loss": 1.3476, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 2.2181818181818184e-05, |
|
"loss": 1.3275, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 2.0363636363636365e-05, |
|
"loss": 1.2839, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 1.8545454545454545e-05, |
|
"loss": 1.2226, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.9917241379310345, |
|
"eval_loss": 0.9373832941055298, |
|
"eval_runtime": 9.4058, |
|
"eval_samples_per_second": 154.161, |
|
"eval_steps_per_second": 4.891, |
|
"step": 204 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"learning_rate": 1.672727272727273e-05, |
|
"loss": 1.1917, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 1.4909090909090908e-05, |
|
"loss": 1.1838, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"learning_rate": 1.3090909090909093e-05, |
|
"loss": 1.1872, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 2.35, |
|
"learning_rate": 1.1272727272727274e-05, |
|
"loss": 1.1204, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 9.454545454545454e-06, |
|
"loss": 1.1191, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.55, |
|
"learning_rate": 7.636363636363638e-06, |
|
"loss": 1.1262, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 5.8181818181818185e-06, |
|
"loss": 1.0852, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 1.0953, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 2.181818181818182e-06, |
|
"loss": 1.0887, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"learning_rate": 3.6363636363636366e-07, |
|
"loss": 1.1069, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9944827586206897, |
|
"eval_loss": 0.8114762902259827, |
|
"eval_runtime": 9.5561, |
|
"eval_samples_per_second": 151.736, |
|
"eval_steps_per_second": 4.814, |
|
"step": 306 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 306, |
|
"total_flos": 3.138628448046035e+18, |
|
"train_loss": 1.7424827136245429, |
|
"train_runtime": 2056.1169, |
|
"train_samples_per_second": 19.041, |
|
"train_steps_per_second": 0.149 |
|
} |
|
], |
|
"max_steps": 306, |
|
"num_train_epochs": 3, |
|
"total_flos": 3.138628448046035e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|