domluna's picture
End of training
1b3064f
{
"best_metric": 1.0,
"best_model_checkpoint": "vit-base-patch16-224-in21k-shiba-inu-detector/checkpoint-24",
"epoch": 19.941176470588236,
"global_step": 80,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.94,
"eval_accuracy": 0.16666666666666666,
"eval_loss": 1.3874683380126953,
"eval_runtime": 0.6379,
"eval_samples_per_second": 94.065,
"eval_steps_per_second": 3.136,
"step": 4
},
{
"epoch": 1.94,
"eval_accuracy": 0.7833333333333333,
"eval_loss": 1.2712124586105347,
"eval_runtime": 0.6386,
"eval_samples_per_second": 93.961,
"eval_steps_per_second": 3.132,
"step": 8
},
{
"epoch": 2.47,
"learning_rate": 4.8611111111111115e-05,
"loss": 1.4176,
"step": 10
},
{
"epoch": 2.94,
"eval_accuracy": 0.9,
"eval_loss": 1.0971676111221313,
"eval_runtime": 0.634,
"eval_samples_per_second": 94.631,
"eval_steps_per_second": 3.154,
"step": 12
},
{
"epoch": 3.94,
"eval_accuracy": 0.95,
"eval_loss": 0.9365110397338867,
"eval_runtime": 0.6359,
"eval_samples_per_second": 94.351,
"eval_steps_per_second": 3.145,
"step": 16
},
{
"epoch": 4.94,
"learning_rate": 4.166666666666667e-05,
"loss": 1.0144,
"step": 20
},
{
"epoch": 4.94,
"eval_accuracy": 0.9833333333333333,
"eval_loss": 0.7836101055145264,
"eval_runtime": 0.665,
"eval_samples_per_second": 90.221,
"eval_steps_per_second": 3.007,
"step": 20
},
{
"epoch": 5.94,
"eval_accuracy": 1.0,
"eval_loss": 0.6510943174362183,
"eval_runtime": 0.6349,
"eval_samples_per_second": 94.502,
"eval_steps_per_second": 3.15,
"step": 24
},
{
"epoch": 6.94,
"eval_accuracy": 1.0,
"eval_loss": 0.5329036116600037,
"eval_runtime": 0.6351,
"eval_samples_per_second": 94.467,
"eval_steps_per_second": 3.149,
"step": 28
},
{
"epoch": 7.47,
"learning_rate": 3.472222222222222e-05,
"loss": 0.6329,
"step": 30
},
{
"epoch": 7.94,
"eval_accuracy": 1.0,
"eval_loss": 0.44028139114379883,
"eval_runtime": 0.6343,
"eval_samples_per_second": 94.586,
"eval_steps_per_second": 3.153,
"step": 32
},
{
"epoch": 8.94,
"eval_accuracy": 1.0,
"eval_loss": 0.37774336338043213,
"eval_runtime": 0.6492,
"eval_samples_per_second": 92.424,
"eval_steps_per_second": 3.081,
"step": 36
},
{
"epoch": 9.94,
"learning_rate": 2.777777777777778e-05,
"loss": 0.3821,
"step": 40
},
{
"epoch": 9.94,
"eval_accuracy": 1.0,
"eval_loss": 0.3272607922554016,
"eval_runtime": 0.6458,
"eval_samples_per_second": 92.908,
"eval_steps_per_second": 3.097,
"step": 40
},
{
"epoch": 10.94,
"eval_accuracy": 1.0,
"eval_loss": 0.288595587015152,
"eval_runtime": 0.6455,
"eval_samples_per_second": 92.955,
"eval_steps_per_second": 3.098,
"step": 44
},
{
"epoch": 11.94,
"eval_accuracy": 1.0,
"eval_loss": 0.2622089684009552,
"eval_runtime": 0.6488,
"eval_samples_per_second": 92.482,
"eval_steps_per_second": 3.083,
"step": 48
},
{
"epoch": 12.47,
"learning_rate": 2.0833333333333336e-05,
"loss": 0.2655,
"step": 50
},
{
"epoch": 12.94,
"eval_accuracy": 1.0,
"eval_loss": 0.2396974414587021,
"eval_runtime": 0.6621,
"eval_samples_per_second": 90.624,
"eval_steps_per_second": 3.021,
"step": 52
},
{
"epoch": 13.94,
"eval_accuracy": 1.0,
"eval_loss": 0.2249792218208313,
"eval_runtime": 0.6354,
"eval_samples_per_second": 94.43,
"eval_steps_per_second": 3.148,
"step": 56
},
{
"epoch": 14.94,
"learning_rate": 1.388888888888889e-05,
"loss": 0.202,
"step": 60
},
{
"epoch": 14.94,
"eval_accuracy": 1.0,
"eval_loss": 0.2151898890733719,
"eval_runtime": 0.6574,
"eval_samples_per_second": 91.275,
"eval_steps_per_second": 3.043,
"step": 60
},
{
"epoch": 15.94,
"eval_accuracy": 1.0,
"eval_loss": 0.207356259226799,
"eval_runtime": 0.6702,
"eval_samples_per_second": 89.52,
"eval_steps_per_second": 2.984,
"step": 64
},
{
"epoch": 16.94,
"eval_accuracy": 1.0,
"eval_loss": 0.20027826726436615,
"eval_runtime": 0.6695,
"eval_samples_per_second": 89.625,
"eval_steps_per_second": 2.987,
"step": 68
},
{
"epoch": 17.47,
"learning_rate": 6.944444444444445e-06,
"loss": 0.1785,
"step": 70
},
{
"epoch": 17.94,
"eval_accuracy": 1.0,
"eval_loss": 0.1959574967622757,
"eval_runtime": 0.6341,
"eval_samples_per_second": 94.622,
"eval_steps_per_second": 3.154,
"step": 72
},
{
"epoch": 18.94,
"eval_accuracy": 1.0,
"eval_loss": 0.1935936063528061,
"eval_runtime": 0.6338,
"eval_samples_per_second": 94.661,
"eval_steps_per_second": 3.155,
"step": 76
},
{
"epoch": 19.94,
"learning_rate": 0.0,
"loss": 0.1618,
"step": 80
},
{
"epoch": 19.94,
"eval_accuracy": 1.0,
"eval_loss": 0.19295135140419006,
"eval_runtime": 0.7396,
"eval_samples_per_second": 81.128,
"eval_steps_per_second": 2.704,
"step": 80
},
{
"epoch": 19.94,
"step": 80,
"total_flos": 8.288691784358953e+17,
"train_loss": 0.5318649023771286,
"train_runtime": 312.5066,
"train_samples_per_second": 34.303,
"train_steps_per_second": 0.256
}
],
"max_steps": 80,
"num_train_epochs": 20,
"total_flos": 8.288691784358953e+17,
"trial_name": null,
"trial_params": null
}