jayanthspratap's picture
End of training
edfea3c
raw
history blame
4.99 kB
{
"best_metric": 0.7647058823529411,
"best_model_checkpoint": "convnext-tiny-224-drfx-CT-classifier/checkpoint-40",
"epoch": 15.0,
"global_step": 60,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.5882352941176471,
"eval_loss": 0.7083577513694763,
"eval_runtime": 0.4547,
"eval_samples_per_second": 37.384,
"eval_steps_per_second": 10.995,
"step": 4
},
{
"epoch": 2.0,
"eval_accuracy": 0.5294117647058824,
"eval_loss": 0.7021164894104004,
"eval_runtime": 0.194,
"eval_samples_per_second": 87.643,
"eval_steps_per_second": 25.777,
"step": 8
},
{
"epoch": 2.5,
"learning_rate": 4.62962962962963e-05,
"loss": 0.6143,
"step": 10
},
{
"epoch": 3.0,
"eval_accuracy": 0.4117647058823529,
"eval_loss": 0.702375054359436,
"eval_runtime": 0.2072,
"eval_samples_per_second": 82.045,
"eval_steps_per_second": 24.131,
"step": 12
},
{
"epoch": 4.0,
"eval_accuracy": 0.5294117647058824,
"eval_loss": 0.6856038570404053,
"eval_runtime": 0.2259,
"eval_samples_per_second": 75.262,
"eval_steps_per_second": 22.136,
"step": 16
},
{
"epoch": 5.0,
"learning_rate": 3.7037037037037037e-05,
"loss": 0.6154,
"step": 20
},
{
"epoch": 5.0,
"eval_accuracy": 0.5294117647058824,
"eval_loss": 0.6955483555793762,
"eval_runtime": 0.1803,
"eval_samples_per_second": 94.292,
"eval_steps_per_second": 27.733,
"step": 20
},
{
"epoch": 6.0,
"eval_accuracy": 0.5294117647058824,
"eval_loss": 0.7119423747062683,
"eval_runtime": 0.1899,
"eval_samples_per_second": 89.52,
"eval_steps_per_second": 26.329,
"step": 24
},
{
"epoch": 7.0,
"eval_accuracy": 0.5882352941176471,
"eval_loss": 0.7085601091384888,
"eval_runtime": 0.1459,
"eval_samples_per_second": 116.502,
"eval_steps_per_second": 34.265,
"step": 28
},
{
"epoch": 7.5,
"learning_rate": 2.777777777777778e-05,
"loss": 0.5786,
"step": 30
},
{
"epoch": 8.0,
"eval_accuracy": 0.5882352941176471,
"eval_loss": 0.6967045068740845,
"eval_runtime": 0.1479,
"eval_samples_per_second": 114.916,
"eval_steps_per_second": 33.799,
"step": 32
},
{
"epoch": 9.0,
"eval_accuracy": 0.6470588235294118,
"eval_loss": 0.6773281097412109,
"eval_runtime": 0.1449,
"eval_samples_per_second": 117.312,
"eval_steps_per_second": 34.504,
"step": 36
},
{
"epoch": 10.0,
"learning_rate": 1.8518518518518518e-05,
"loss": 0.5026,
"step": 40
},
{
"epoch": 10.0,
"eval_accuracy": 0.7647058823529411,
"eval_loss": 0.6537247896194458,
"eval_runtime": 0.1787,
"eval_samples_per_second": 95.157,
"eval_steps_per_second": 27.987,
"step": 40
},
{
"epoch": 11.0,
"eval_accuracy": 0.7647058823529411,
"eval_loss": 0.6439494490623474,
"eval_runtime": 0.1774,
"eval_samples_per_second": 95.855,
"eval_steps_per_second": 28.193,
"step": 44
},
{
"epoch": 12.0,
"eval_accuracy": 0.7647058823529411,
"eval_loss": 0.6389846205711365,
"eval_runtime": 0.155,
"eval_samples_per_second": 109.699,
"eval_steps_per_second": 32.264,
"step": 48
},
{
"epoch": 12.5,
"learning_rate": 9.259259259259259e-06,
"loss": 0.5086,
"step": 50
},
{
"epoch": 13.0,
"eval_accuracy": 0.7647058823529411,
"eval_loss": 0.6434133052825928,
"eval_runtime": 0.1482,
"eval_samples_per_second": 114.73,
"eval_steps_per_second": 33.744,
"step": 52
},
{
"epoch": 14.0,
"eval_accuracy": 0.7647058823529411,
"eval_loss": 0.6424618363380432,
"eval_runtime": 0.1541,
"eval_samples_per_second": 110.305,
"eval_steps_per_second": 32.443,
"step": 56
},
{
"epoch": 15.0,
"learning_rate": 0.0,
"loss": 0.448,
"step": 60
},
{
"epoch": 15.0,
"eval_accuracy": 0.7647058823529411,
"eval_loss": 0.645173192024231,
"eval_runtime": 0.1497,
"eval_samples_per_second": 113.564,
"eval_steps_per_second": 33.401,
"step": 60
},
{
"epoch": 15.0,
"step": 60,
"total_flos": 2.412253290037248e+16,
"train_loss": 0.5445812543233236,
"train_runtime": 64.3122,
"train_samples_per_second": 14.927,
"train_steps_per_second": 0.933
}
],
"max_steps": 60,
"num_train_epochs": 15,
"total_flos": 2.412253290037248e+16,
"trial_name": null,
"trial_params": null
}