delivery_truck_classification / trainer_state.json
JEdward7777's picture
End of training
4fb1ae9
raw
history blame
10.5 kB
{
"best_metric": 1.0,
"best_model_checkpoint": "delivery_truck_classification\\checkpoint-2",
"epoch": 39.72727272727273,
"global_step": 80,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.73,
"eval_accuracy": 1.0,
"eval_loss": 0.0415542908012867,
"eval_runtime": 7.7969,
"eval_samples_per_second": 4.745,
"eval_steps_per_second": 0.257,
"step": 2
},
{
"epoch": 1.73,
"eval_accuracy": 1.0,
"eval_loss": 0.03460519760847092,
"eval_runtime": 9.6408,
"eval_samples_per_second": 3.838,
"eval_steps_per_second": 0.207,
"step": 4
},
{
"epoch": 2.73,
"eval_accuracy": 1.0,
"eval_loss": 0.029270131140947342,
"eval_runtime": 11.5968,
"eval_samples_per_second": 3.191,
"eval_steps_per_second": 0.172,
"step": 6
},
{
"epoch": 3.73,
"eval_accuracy": 1.0,
"eval_loss": 0.01861225999891758,
"eval_runtime": 8.4881,
"eval_samples_per_second": 4.359,
"eval_steps_per_second": 0.236,
"step": 8
},
{
"epoch": 4.73,
"eval_accuracy": 1.0,
"eval_loss": 0.020498055964708328,
"eval_runtime": 9.9982,
"eval_samples_per_second": 3.701,
"eval_steps_per_second": 0.2,
"step": 10
},
{
"epoch": 5.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.06043216958642006,
"eval_runtime": 8.9914,
"eval_samples_per_second": 4.115,
"eval_steps_per_second": 0.222,
"step": 12
},
{
"epoch": 6.73,
"eval_accuracy": 1.0,
"eval_loss": 0.0332246832549572,
"eval_runtime": 8.8254,
"eval_samples_per_second": 4.192,
"eval_steps_per_second": 0.227,
"step": 14
},
{
"epoch": 7.73,
"eval_accuracy": 1.0,
"eval_loss": 0.025004582479596138,
"eval_runtime": 11.8616,
"eval_samples_per_second": 3.119,
"eval_steps_per_second": 0.169,
"step": 16
},
{
"epoch": 8.73,
"eval_accuracy": 1.0,
"eval_loss": 0.03864024579524994,
"eval_runtime": 8.8843,
"eval_samples_per_second": 4.165,
"eval_steps_per_second": 0.225,
"step": 18
},
{
"epoch": 9.73,
"learning_rate": 4.166666666666667e-05,
"loss": 0.2483,
"step": 20
},
{
"epoch": 9.73,
"eval_accuracy": 1.0,
"eval_loss": 0.04379289597272873,
"eval_runtime": 8.6752,
"eval_samples_per_second": 4.265,
"eval_steps_per_second": 0.231,
"step": 20
},
{
"epoch": 10.73,
"eval_accuracy": 1.0,
"eval_loss": 0.04468226432800293,
"eval_runtime": 8.2704,
"eval_samples_per_second": 4.474,
"eval_steps_per_second": 0.242,
"step": 22
},
{
"epoch": 11.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.06756877154111862,
"eval_runtime": 8.2231,
"eval_samples_per_second": 4.5,
"eval_steps_per_second": 0.243,
"step": 24
},
{
"epoch": 12.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.07861027866601944,
"eval_runtime": 8.9079,
"eval_samples_per_second": 4.154,
"eval_steps_per_second": 0.225,
"step": 26
},
{
"epoch": 13.73,
"eval_accuracy": 1.0,
"eval_loss": 0.03886393457651138,
"eval_runtime": 7.4091,
"eval_samples_per_second": 4.994,
"eval_steps_per_second": 0.27,
"step": 28
},
{
"epoch": 14.73,
"eval_accuracy": 1.0,
"eval_loss": 0.02784094214439392,
"eval_runtime": 9.7376,
"eval_samples_per_second": 3.8,
"eval_steps_per_second": 0.205,
"step": 30
},
{
"epoch": 15.73,
"eval_accuracy": 1.0,
"eval_loss": 0.02497038058936596,
"eval_runtime": 7.3256,
"eval_samples_per_second": 5.051,
"eval_steps_per_second": 0.273,
"step": 32
},
{
"epoch": 16.73,
"eval_accuracy": 1.0,
"eval_loss": 0.02828327752649784,
"eval_runtime": 11.0099,
"eval_samples_per_second": 3.361,
"eval_steps_per_second": 0.182,
"step": 34
},
{
"epoch": 17.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.05021832138299942,
"eval_runtime": 9.5468,
"eval_samples_per_second": 3.876,
"eval_steps_per_second": 0.209,
"step": 36
},
{
"epoch": 18.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.07113233208656311,
"eval_runtime": 7.5069,
"eval_samples_per_second": 4.929,
"eval_steps_per_second": 0.266,
"step": 38
},
{
"epoch": 19.73,
"learning_rate": 2.777777777777778e-05,
"loss": 0.1759,
"step": 40
},
{
"epoch": 19.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.06368651241064072,
"eval_runtime": 10.8688,
"eval_samples_per_second": 3.404,
"eval_steps_per_second": 0.184,
"step": 40
},
{
"epoch": 20.73,
"eval_accuracy": 1.0,
"eval_loss": 0.04590895399451256,
"eval_runtime": 7.36,
"eval_samples_per_second": 5.027,
"eval_steps_per_second": 0.272,
"step": 42
},
{
"epoch": 21.73,
"eval_accuracy": 1.0,
"eval_loss": 0.03937483951449394,
"eval_runtime": 7.6664,
"eval_samples_per_second": 4.826,
"eval_steps_per_second": 0.261,
"step": 44
},
{
"epoch": 22.73,
"eval_accuracy": 1.0,
"eval_loss": 0.04189879819750786,
"eval_runtime": 7.6918,
"eval_samples_per_second": 4.81,
"eval_steps_per_second": 0.26,
"step": 46
},
{
"epoch": 23.73,
"eval_accuracy": 1.0,
"eval_loss": 0.042252812534570694,
"eval_runtime": 9.2536,
"eval_samples_per_second": 3.998,
"eval_steps_per_second": 0.216,
"step": 48
},
{
"epoch": 24.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.046256761997938156,
"eval_runtime": 8.404,
"eval_samples_per_second": 4.403,
"eval_steps_per_second": 0.238,
"step": 50
},
{
"epoch": 25.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.050322916358709335,
"eval_runtime": 7.2832,
"eval_samples_per_second": 5.08,
"eval_steps_per_second": 0.275,
"step": 52
},
{
"epoch": 26.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.061594847589731216,
"eval_runtime": 7.736,
"eval_samples_per_second": 4.783,
"eval_steps_per_second": 0.259,
"step": 54
},
{
"epoch": 27.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.0641237199306488,
"eval_runtime": 8.3429,
"eval_samples_per_second": 4.435,
"eval_steps_per_second": 0.24,
"step": 56
},
{
"epoch": 28.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.05289805307984352,
"eval_runtime": 6.6939,
"eval_samples_per_second": 5.527,
"eval_steps_per_second": 0.299,
"step": 58
},
{
"epoch": 29.73,
"learning_rate": 1.388888888888889e-05,
"loss": 0.1669,
"step": 60
},
{
"epoch": 29.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.048487674444913864,
"eval_runtime": 8.2178,
"eval_samples_per_second": 4.502,
"eval_steps_per_second": 0.243,
"step": 60
},
{
"epoch": 30.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.04654627665877342,
"eval_runtime": 9.0621,
"eval_samples_per_second": 4.083,
"eval_steps_per_second": 0.221,
"step": 62
},
{
"epoch": 31.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.045613404363393784,
"eval_runtime": 7.5057,
"eval_samples_per_second": 4.93,
"eval_steps_per_second": 0.266,
"step": 64
},
{
"epoch": 32.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.047752730548381805,
"eval_runtime": 7.6794,
"eval_samples_per_second": 4.818,
"eval_steps_per_second": 0.26,
"step": 66
},
{
"epoch": 33.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.0467178151011467,
"eval_runtime": 7.7621,
"eval_samples_per_second": 4.767,
"eval_steps_per_second": 0.258,
"step": 68
},
{
"epoch": 34.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.04733948037028313,
"eval_runtime": 8.0246,
"eval_samples_per_second": 4.611,
"eval_steps_per_second": 0.249,
"step": 70
},
{
"epoch": 35.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.048583876341581345,
"eval_runtime": 8.5589,
"eval_samples_per_second": 4.323,
"eval_steps_per_second": 0.234,
"step": 72
},
{
"epoch": 36.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.05004884675145149,
"eval_runtime": 7.4868,
"eval_samples_per_second": 4.942,
"eval_steps_per_second": 0.267,
"step": 74
},
{
"epoch": 37.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.0501551553606987,
"eval_runtime": 8.2774,
"eval_samples_per_second": 4.47,
"eval_steps_per_second": 0.242,
"step": 76
},
{
"epoch": 38.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.05001495033502579,
"eval_runtime": 7.8563,
"eval_samples_per_second": 4.71,
"eval_steps_per_second": 0.255,
"step": 78
},
{
"epoch": 39.73,
"learning_rate": 0.0,
"loss": 0.1589,
"step": 80
},
{
"epoch": 39.73,
"eval_accuracy": 0.972972972972973,
"eval_loss": 0.04929113760590553,
"eval_runtime": 8.4253,
"eval_samples_per_second": 4.392,
"eval_steps_per_second": 0.237,
"step": 80
},
{
"epoch": 39.73,
"step": 80,
"total_flos": 3.262961773565706e+17,
"train_loss": 0.18748833239078522,
"train_runtime": 7500.5041,
"train_samples_per_second": 1.76,
"train_steps_per_second": 0.011
}
],
"max_steps": 80,
"num_train_epochs": 40,
"total_flos": 3.262961773565706e+17,
"trial_name": null,
"trial_params": null
}