dvs's picture
End of training
7ee195f
{
"best_metric": 1.0,
"best_model_checkpoint": "swin-tiny-patch4-window7-224-mulder-v-scully-colab/checkpoint-8",
"epoch": 20.0,
"global_step": 20,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.75,
"eval_loss": 0.6105230450630188,
"eval_runtime": 0.2822,
"eval_samples_per_second": 14.173,
"eval_steps_per_second": 3.543,
"step": 1
},
{
"epoch": 2.0,
"eval_accuracy": 0.5,
"eval_loss": 0.6975106596946716,
"eval_runtime": 0.2795,
"eval_samples_per_second": 14.311,
"eval_steps_per_second": 3.578,
"step": 2
},
{
"epoch": 3.0,
"eval_accuracy": 0.25,
"eval_loss": 0.8308714628219604,
"eval_runtime": 0.282,
"eval_samples_per_second": 14.186,
"eval_steps_per_second": 3.547,
"step": 3
},
{
"epoch": 4.0,
"eval_accuracy": 0.5,
"eval_loss": 0.7603804469108582,
"eval_runtime": 0.2794,
"eval_samples_per_second": 14.316,
"eval_steps_per_second": 3.579,
"step": 4
},
{
"epoch": 5.0,
"eval_accuracy": 0.5,
"eval_loss": 0.6327458620071411,
"eval_runtime": 0.2816,
"eval_samples_per_second": 14.203,
"eval_steps_per_second": 3.551,
"step": 5
},
{
"epoch": 6.0,
"eval_accuracy": 0.75,
"eval_loss": 0.5101333260536194,
"eval_runtime": 0.3029,
"eval_samples_per_second": 13.204,
"eval_steps_per_second": 3.301,
"step": 6
},
{
"epoch": 7.0,
"eval_accuracy": 0.75,
"eval_loss": 0.41480666399002075,
"eval_runtime": 0.2864,
"eval_samples_per_second": 13.964,
"eval_steps_per_second": 3.491,
"step": 7
},
{
"epoch": 8.0,
"eval_accuracy": 1.0,
"eval_loss": 0.3651624619960785,
"eval_runtime": 0.2793,
"eval_samples_per_second": 14.319,
"eval_steps_per_second": 3.58,
"step": 8
},
{
"epoch": 9.0,
"eval_accuracy": 1.0,
"eval_loss": 0.34327611327171326,
"eval_runtime": 0.3008,
"eval_samples_per_second": 13.299,
"eval_steps_per_second": 3.325,
"step": 9
},
{
"epoch": 10.0,
"learning_rate": 2.777777777777778e-05,
"loss": 0.0984,
"step": 10
},
{
"epoch": 10.0,
"eval_accuracy": 1.0,
"eval_loss": 0.3231046795845032,
"eval_runtime": 0.296,
"eval_samples_per_second": 13.514,
"eval_steps_per_second": 3.379,
"step": 10
},
{
"epoch": 11.0,
"eval_accuracy": 1.0,
"eval_loss": 0.30705589056015015,
"eval_runtime": 0.2953,
"eval_samples_per_second": 13.546,
"eval_steps_per_second": 3.386,
"step": 11
},
{
"epoch": 12.0,
"eval_accuracy": 1.0,
"eval_loss": 0.3047180771827698,
"eval_runtime": 0.3308,
"eval_samples_per_second": 12.092,
"eval_steps_per_second": 3.023,
"step": 12
},
{
"epoch": 13.0,
"eval_accuracy": 0.75,
"eval_loss": 0.3189181089401245,
"eval_runtime": 0.284,
"eval_samples_per_second": 14.083,
"eval_steps_per_second": 3.521,
"step": 13
},
{
"epoch": 14.0,
"eval_accuracy": 0.75,
"eval_loss": 0.343748539686203,
"eval_runtime": 0.3116,
"eval_samples_per_second": 12.839,
"eval_steps_per_second": 3.21,
"step": 14
},
{
"epoch": 15.0,
"eval_accuracy": 0.75,
"eval_loss": 0.3701111972332001,
"eval_runtime": 0.2886,
"eval_samples_per_second": 13.862,
"eval_steps_per_second": 3.466,
"step": 15
},
{
"epoch": 16.0,
"eval_accuracy": 0.75,
"eval_loss": 0.3959260582923889,
"eval_runtime": 0.2721,
"eval_samples_per_second": 14.698,
"eval_steps_per_second": 3.674,
"step": 16
},
{
"epoch": 17.0,
"eval_accuracy": 0.75,
"eval_loss": 0.41665372252464294,
"eval_runtime": 0.285,
"eval_samples_per_second": 14.034,
"eval_steps_per_second": 3.508,
"step": 17
},
{
"epoch": 18.0,
"eval_accuracy": 0.75,
"eval_loss": 0.41897234320640564,
"eval_runtime": 0.2854,
"eval_samples_per_second": 14.016,
"eval_steps_per_second": 3.504,
"step": 18
},
{
"epoch": 19.0,
"eval_accuracy": 0.75,
"eval_loss": 0.41535183787345886,
"eval_runtime": 0.2904,
"eval_samples_per_second": 13.773,
"eval_steps_per_second": 3.443,
"step": 19
},
{
"epoch": 20.0,
"learning_rate": 0.0,
"loss": 0.0632,
"step": 20
},
{
"epoch": 20.0,
"eval_accuracy": 0.75,
"eval_loss": 0.4113732874393463,
"eval_runtime": 0.2848,
"eval_samples_per_second": 14.047,
"eval_steps_per_second": 3.512,
"step": 20
},
{
"epoch": 20.0,
"step": 20,
"total_flos": 1.789631206981632e+16,
"train_loss": 0.08080000579357147,
"train_runtime": 92.7359,
"train_samples_per_second": 7.764,
"train_steps_per_second": 0.216
}
],
"max_steps": 20,
"num_train_epochs": 20,
"total_flos": 1.789631206981632e+16,
"trial_name": null,
"trial_params": null
}