delivery_truck_classification / trainer_state.json
JEdward7777's picture
End of training
c4aa9fd
raw
history blame
10.4 kB
{
"best_metric": 1.0,
"best_model_checkpoint": "delivery_truck_classification/checkpoint-30",
"epoch": 39.8,
"global_step": 40,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.8,
"eval_accuracy": 0.058823529411764705,
"eval_loss": 2.079441785812378,
"eval_runtime": 1.4317,
"eval_samples_per_second": 11.874,
"eval_steps_per_second": 0.698,
"step": 1
},
{
"epoch": 1.8,
"eval_accuracy": 0.11764705882352941,
"eval_loss": 2.0046820640563965,
"eval_runtime": 1.4647,
"eval_samples_per_second": 11.607,
"eval_steps_per_second": 0.683,
"step": 2
},
{
"epoch": 2.8,
"eval_accuracy": 0.17647058823529413,
"eval_loss": 1.866559624671936,
"eval_runtime": 1.4101,
"eval_samples_per_second": 12.056,
"eval_steps_per_second": 0.709,
"step": 3
},
{
"epoch": 3.8,
"eval_accuracy": 0.23529411764705882,
"eval_loss": 1.6799691915512085,
"eval_runtime": 1.3922,
"eval_samples_per_second": 12.211,
"eval_steps_per_second": 0.718,
"step": 4
},
{
"epoch": 4.8,
"eval_accuracy": 0.35294117647058826,
"eval_loss": 1.4622201919555664,
"eval_runtime": 1.3944,
"eval_samples_per_second": 12.191,
"eval_steps_per_second": 0.717,
"step": 5
},
{
"epoch": 5.8,
"eval_accuracy": 0.5882352941176471,
"eval_loss": 1.2880315780639648,
"eval_runtime": 1.4241,
"eval_samples_per_second": 11.937,
"eval_steps_per_second": 0.702,
"step": 6
},
{
"epoch": 6.8,
"eval_accuracy": 0.8823529411764706,
"eval_loss": 1.1315902471542358,
"eval_runtime": 1.3664,
"eval_samples_per_second": 12.442,
"eval_steps_per_second": 0.732,
"step": 7
},
{
"epoch": 7.8,
"eval_accuracy": 0.8823529411764706,
"eval_loss": 0.9924841523170471,
"eval_runtime": 1.3155,
"eval_samples_per_second": 12.923,
"eval_steps_per_second": 0.76,
"step": 8
},
{
"epoch": 8.8,
"eval_accuracy": 0.8823529411764706,
"eval_loss": 0.8822251558303833,
"eval_runtime": 1.399,
"eval_samples_per_second": 12.152,
"eval_steps_per_second": 0.715,
"step": 9
},
{
"epoch": 9.8,
"eval_accuracy": 0.8823529411764706,
"eval_loss": 0.7928468585014343,
"eval_runtime": 1.4175,
"eval_samples_per_second": 11.993,
"eval_steps_per_second": 0.705,
"step": 10
},
{
"epoch": 10.8,
"eval_accuracy": 0.8823529411764706,
"eval_loss": 0.7265812754631042,
"eval_runtime": 1.4201,
"eval_samples_per_second": 11.971,
"eval_steps_per_second": 0.704,
"step": 11
},
{
"epoch": 11.8,
"eval_accuracy": 0.8823529411764706,
"eval_loss": 0.6715043783187866,
"eval_runtime": 1.4255,
"eval_samples_per_second": 11.925,
"eval_steps_per_second": 0.701,
"step": 12
},
{
"epoch": 12.8,
"eval_accuracy": 0.8823529411764706,
"eval_loss": 0.6238242387771606,
"eval_runtime": 1.4187,
"eval_samples_per_second": 11.983,
"eval_steps_per_second": 0.705,
"step": 13
},
{
"epoch": 13.8,
"eval_accuracy": 0.8823529411764706,
"eval_loss": 0.5792789459228516,
"eval_runtime": 1.4156,
"eval_samples_per_second": 12.009,
"eval_steps_per_second": 0.706,
"step": 14
},
{
"epoch": 14.8,
"eval_accuracy": 0.8823529411764706,
"eval_loss": 0.542333722114563,
"eval_runtime": 1.5783,
"eval_samples_per_second": 10.771,
"eval_steps_per_second": 0.634,
"step": 15
},
{
"epoch": 15.8,
"eval_accuracy": 0.8823529411764706,
"eval_loss": 0.5102801322937012,
"eval_runtime": 1.4137,
"eval_samples_per_second": 12.025,
"eval_steps_per_second": 0.707,
"step": 16
},
{
"epoch": 16.8,
"eval_accuracy": 0.9411764705882353,
"eval_loss": 0.486479252576828,
"eval_runtime": 1.4145,
"eval_samples_per_second": 12.019,
"eval_steps_per_second": 0.707,
"step": 17
},
{
"epoch": 17.8,
"eval_accuracy": 0.9411764705882353,
"eval_loss": 0.46346449851989746,
"eval_runtime": 1.4531,
"eval_samples_per_second": 11.699,
"eval_steps_per_second": 0.688,
"step": 18
},
{
"epoch": 18.8,
"eval_accuracy": 0.9411764705882353,
"eval_loss": 0.43990573287010193,
"eval_runtime": 1.4361,
"eval_samples_per_second": 11.838,
"eval_steps_per_second": 0.696,
"step": 19
},
{
"epoch": 19.8,
"learning_rate": 2.777777777777778e-05,
"loss": 1.3142,
"step": 20
},
{
"epoch": 19.8,
"eval_accuracy": 0.9411764705882353,
"eval_loss": 0.41191565990448,
"eval_runtime": 1.4086,
"eval_samples_per_second": 12.069,
"eval_steps_per_second": 0.71,
"step": 20
},
{
"epoch": 20.8,
"eval_accuracy": 0.9411764705882353,
"eval_loss": 0.3842789828777313,
"eval_runtime": 1.4599,
"eval_samples_per_second": 11.644,
"eval_steps_per_second": 0.685,
"step": 21
},
{
"epoch": 21.8,
"eval_accuracy": 0.9411764705882353,
"eval_loss": 0.3496580719947815,
"eval_runtime": 1.2811,
"eval_samples_per_second": 13.27,
"eval_steps_per_second": 0.781,
"step": 22
},
{
"epoch": 22.8,
"eval_accuracy": 0.9411764705882353,
"eval_loss": 0.31610190868377686,
"eval_runtime": 1.3996,
"eval_samples_per_second": 12.146,
"eval_steps_per_second": 0.714,
"step": 23
},
{
"epoch": 23.8,
"eval_accuracy": 0.9411764705882353,
"eval_loss": 0.28501880168914795,
"eval_runtime": 1.4408,
"eval_samples_per_second": 11.799,
"eval_steps_per_second": 0.694,
"step": 24
},
{
"epoch": 24.8,
"eval_accuracy": 0.9411764705882353,
"eval_loss": 0.2581336200237274,
"eval_runtime": 1.4791,
"eval_samples_per_second": 11.493,
"eval_steps_per_second": 0.676,
"step": 25
},
{
"epoch": 25.8,
"eval_accuracy": 0.9411764705882353,
"eval_loss": 0.23626860976219177,
"eval_runtime": 1.4224,
"eval_samples_per_second": 11.952,
"eval_steps_per_second": 0.703,
"step": 26
},
{
"epoch": 26.8,
"eval_accuracy": 0.9411764705882353,
"eval_loss": 0.21788160502910614,
"eval_runtime": 1.4535,
"eval_samples_per_second": 11.696,
"eval_steps_per_second": 0.688,
"step": 27
},
{
"epoch": 27.8,
"eval_accuracy": 0.9411764705882353,
"eval_loss": 0.20291975140571594,
"eval_runtime": 1.4574,
"eval_samples_per_second": 11.665,
"eval_steps_per_second": 0.686,
"step": 28
},
{
"epoch": 28.8,
"eval_accuracy": 0.9411764705882353,
"eval_loss": 0.19029618799686432,
"eval_runtime": 1.3,
"eval_samples_per_second": 13.077,
"eval_steps_per_second": 0.769,
"step": 29
},
{
"epoch": 29.8,
"eval_accuracy": 1.0,
"eval_loss": 0.17870470881462097,
"eval_runtime": 1.4384,
"eval_samples_per_second": 11.818,
"eval_steps_per_second": 0.695,
"step": 30
},
{
"epoch": 30.8,
"eval_accuracy": 1.0,
"eval_loss": 0.1676449328660965,
"eval_runtime": 1.4058,
"eval_samples_per_second": 12.093,
"eval_steps_per_second": 0.711,
"step": 31
},
{
"epoch": 31.8,
"eval_accuracy": 1.0,
"eval_loss": 0.15808852016925812,
"eval_runtime": 1.4182,
"eval_samples_per_second": 11.987,
"eval_steps_per_second": 0.705,
"step": 32
},
{
"epoch": 32.8,
"eval_accuracy": 1.0,
"eval_loss": 0.14869734644889832,
"eval_runtime": 1.3868,
"eval_samples_per_second": 12.259,
"eval_steps_per_second": 0.721,
"step": 33
},
{
"epoch": 33.8,
"eval_accuracy": 1.0,
"eval_loss": 0.14104951918125153,
"eval_runtime": 1.3908,
"eval_samples_per_second": 12.223,
"eval_steps_per_second": 0.719,
"step": 34
},
{
"epoch": 34.8,
"eval_accuracy": 1.0,
"eval_loss": 0.13486798107624054,
"eval_runtime": 1.4139,
"eval_samples_per_second": 12.023,
"eval_steps_per_second": 0.707,
"step": 35
},
{
"epoch": 35.8,
"eval_accuracy": 1.0,
"eval_loss": 0.13010667264461517,
"eval_runtime": 1.3204,
"eval_samples_per_second": 12.875,
"eval_steps_per_second": 0.757,
"step": 36
},
{
"epoch": 36.8,
"eval_accuracy": 1.0,
"eval_loss": 0.12663623690605164,
"eval_runtime": 1.4211,
"eval_samples_per_second": 11.963,
"eval_steps_per_second": 0.704,
"step": 37
},
{
"epoch": 37.8,
"eval_accuracy": 1.0,
"eval_loss": 0.12430554628372192,
"eval_runtime": 1.4023,
"eval_samples_per_second": 12.123,
"eval_steps_per_second": 0.713,
"step": 38
},
{
"epoch": 38.8,
"eval_accuracy": 1.0,
"eval_loss": 0.12299124151468277,
"eval_runtime": 1.4925,
"eval_samples_per_second": 11.39,
"eval_steps_per_second": 0.67,
"step": 39
},
{
"epoch": 39.8,
"learning_rate": 0.0,
"loss": 0.4316,
"step": 40
},
{
"epoch": 39.8,
"eval_accuracy": 1.0,
"eval_loss": 0.12227079272270203,
"eval_runtime": 1.5093,
"eval_samples_per_second": 11.264,
"eval_steps_per_second": 0.663,
"step": 40
},
{
"epoch": 39.8,
"step": 40,
"total_flos": 1.4763621798877594e+17,
"train_loss": 0.872883677482605,
"train_runtime": 746.1275,
"train_samples_per_second": 7.988,
"train_steps_per_second": 0.054
}
],
"max_steps": 40,
"num_train_epochs": 40,
"total_flos": 1.4763621798877594e+17,
"trial_name": null,
"trial_params": null
}