delivery_truck_classification / trainer_state.json
JEdward7777's picture
End of training
2d19bf4
raw
history blame
10.2 kB
{
"best_metric": 1.0,
"best_model_checkpoint": "delivery_truck_classification/checkpoint-16",
"epoch": 40.0,
"global_step": 40,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.42857142857142855,
"eval_loss": 1.6168556213378906,
"eval_runtime": 1.0173,
"eval_samples_per_second": 13.763,
"eval_steps_per_second": 0.983,
"step": 1
},
{
"epoch": 2.0,
"eval_accuracy": 0.5,
"eval_loss": 1.5622481107711792,
"eval_runtime": 1.1135,
"eval_samples_per_second": 12.573,
"eval_steps_per_second": 0.898,
"step": 2
},
{
"epoch": 3.0,
"eval_accuracy": 0.5714285714285714,
"eval_loss": 1.4655851125717163,
"eval_runtime": 1.1046,
"eval_samples_per_second": 12.674,
"eval_steps_per_second": 0.905,
"step": 3
},
{
"epoch": 4.0,
"eval_accuracy": 0.7142857142857143,
"eval_loss": 1.3434288501739502,
"eval_runtime": 1.098,
"eval_samples_per_second": 12.75,
"eval_steps_per_second": 0.911,
"step": 4
},
{
"epoch": 5.0,
"eval_accuracy": 0.8571428571428571,
"eval_loss": 1.1958130598068237,
"eval_runtime": 1.1029,
"eval_samples_per_second": 12.694,
"eval_steps_per_second": 0.907,
"step": 5
},
{
"epoch": 6.0,
"eval_accuracy": 0.8571428571428571,
"eval_loss": 1.039809226989746,
"eval_runtime": 1.1349,
"eval_samples_per_second": 12.336,
"eval_steps_per_second": 0.881,
"step": 6
},
{
"epoch": 7.0,
"eval_accuracy": 0.8571428571428571,
"eval_loss": 0.8839331865310669,
"eval_runtime": 1.1319,
"eval_samples_per_second": 12.369,
"eval_steps_per_second": 0.883,
"step": 7
},
{
"epoch": 8.0,
"eval_accuracy": 0.8571428571428571,
"eval_loss": 0.7458344101905823,
"eval_runtime": 1.1264,
"eval_samples_per_second": 12.429,
"eval_steps_per_second": 0.888,
"step": 8
},
{
"epoch": 9.0,
"eval_accuracy": 0.8571428571428571,
"eval_loss": 0.6266831755638123,
"eval_runtime": 1.1014,
"eval_samples_per_second": 12.711,
"eval_steps_per_second": 0.908,
"step": 9
},
{
"epoch": 10.0,
"eval_accuracy": 0.8571428571428571,
"eval_loss": 0.5252572298049927,
"eval_runtime": 1.0223,
"eval_samples_per_second": 13.694,
"eval_steps_per_second": 0.978,
"step": 10
},
{
"epoch": 11.0,
"eval_accuracy": 0.8571428571428571,
"eval_loss": 0.4413524568080902,
"eval_runtime": 1.1441,
"eval_samples_per_second": 12.236,
"eval_steps_per_second": 0.874,
"step": 11
},
{
"epoch": 12.0,
"eval_accuracy": 0.8571428571428571,
"eval_loss": 0.3764006495475769,
"eval_runtime": 1.1274,
"eval_samples_per_second": 12.418,
"eval_steps_per_second": 0.887,
"step": 12
},
{
"epoch": 13.0,
"eval_accuracy": 0.8571428571428571,
"eval_loss": 0.32498008012771606,
"eval_runtime": 1.1314,
"eval_samples_per_second": 12.374,
"eval_steps_per_second": 0.884,
"step": 13
},
{
"epoch": 14.0,
"eval_accuracy": 0.8571428571428571,
"eval_loss": 0.28101447224617004,
"eval_runtime": 1.135,
"eval_samples_per_second": 12.335,
"eval_steps_per_second": 0.881,
"step": 14
},
{
"epoch": 15.0,
"eval_accuracy": 0.9285714285714286,
"eval_loss": 0.24058859050273895,
"eval_runtime": 1.1271,
"eval_samples_per_second": 12.421,
"eval_steps_per_second": 0.887,
"step": 15
},
{
"epoch": 16.0,
"eval_accuracy": 1.0,
"eval_loss": 0.20273710787296295,
"eval_runtime": 1.1302,
"eval_samples_per_second": 12.387,
"eval_steps_per_second": 0.885,
"step": 16
},
{
"epoch": 17.0,
"eval_accuracy": 1.0,
"eval_loss": 0.16791479289531708,
"eval_runtime": 1.1135,
"eval_samples_per_second": 12.573,
"eval_steps_per_second": 0.898,
"step": 17
},
{
"epoch": 18.0,
"eval_accuracy": 1.0,
"eval_loss": 0.13755987584590912,
"eval_runtime": 1.1622,
"eval_samples_per_second": 12.046,
"eval_steps_per_second": 0.86,
"step": 18
},
{
"epoch": 19.0,
"eval_accuracy": 1.0,
"eval_loss": 0.11193893849849701,
"eval_runtime": 1.0453,
"eval_samples_per_second": 13.393,
"eval_steps_per_second": 0.957,
"step": 19
},
{
"epoch": 20.0,
"learning_rate": 2.777777777777778e-05,
"loss": 1.0444,
"step": 20
},
{
"epoch": 20.0,
"eval_accuracy": 1.0,
"eval_loss": 0.09099491685628891,
"eval_runtime": 1.1318,
"eval_samples_per_second": 12.37,
"eval_steps_per_second": 0.884,
"step": 20
},
{
"epoch": 21.0,
"eval_accuracy": 1.0,
"eval_loss": 0.07338053733110428,
"eval_runtime": 1.1489,
"eval_samples_per_second": 12.186,
"eval_steps_per_second": 0.87,
"step": 21
},
{
"epoch": 22.0,
"eval_accuracy": 1.0,
"eval_loss": 0.06158090755343437,
"eval_runtime": 1.1236,
"eval_samples_per_second": 12.459,
"eval_steps_per_second": 0.89,
"step": 22
},
{
"epoch": 23.0,
"eval_accuracy": 1.0,
"eval_loss": 0.05360007658600807,
"eval_runtime": 1.5779,
"eval_samples_per_second": 8.873,
"eval_steps_per_second": 0.634,
"step": 23
},
{
"epoch": 24.0,
"eval_accuracy": 1.0,
"eval_loss": 0.047831542789936066,
"eval_runtime": 1.1304,
"eval_samples_per_second": 12.385,
"eval_steps_per_second": 0.885,
"step": 24
},
{
"epoch": 25.0,
"eval_accuracy": 1.0,
"eval_loss": 0.04371718317270279,
"eval_runtime": 1.1258,
"eval_samples_per_second": 12.436,
"eval_steps_per_second": 0.888,
"step": 25
},
{
"epoch": 26.0,
"eval_accuracy": 1.0,
"eval_loss": 0.0414046086370945,
"eval_runtime": 1.1176,
"eval_samples_per_second": 12.527,
"eval_steps_per_second": 0.895,
"step": 26
},
{
"epoch": 27.0,
"eval_accuracy": 1.0,
"eval_loss": 0.03760123625397682,
"eval_runtime": 1.1256,
"eval_samples_per_second": 12.438,
"eval_steps_per_second": 0.888,
"step": 27
},
{
"epoch": 28.0,
"eval_accuracy": 1.0,
"eval_loss": 0.034249212592840195,
"eval_runtime": 1.0262,
"eval_samples_per_second": 13.642,
"eval_steps_per_second": 0.974,
"step": 28
},
{
"epoch": 29.0,
"eval_accuracy": 1.0,
"eval_loss": 0.03131537884473801,
"eval_runtime": 1.4424,
"eval_samples_per_second": 9.706,
"eval_steps_per_second": 0.693,
"step": 29
},
{
"epoch": 30.0,
"eval_accuracy": 1.0,
"eval_loss": 0.028712574392557144,
"eval_runtime": 1.1015,
"eval_samples_per_second": 12.71,
"eval_steps_per_second": 0.908,
"step": 30
},
{
"epoch": 31.0,
"eval_accuracy": 1.0,
"eval_loss": 0.027365097776055336,
"eval_runtime": 1.1501,
"eval_samples_per_second": 12.172,
"eval_steps_per_second": 0.869,
"step": 31
},
{
"epoch": 32.0,
"eval_accuracy": 1.0,
"eval_loss": 0.026658793911337852,
"eval_runtime": 1.117,
"eval_samples_per_second": 12.534,
"eval_steps_per_second": 0.895,
"step": 32
},
{
"epoch": 33.0,
"eval_accuracy": 1.0,
"eval_loss": 0.026295723393559456,
"eval_runtime": 1.1577,
"eval_samples_per_second": 12.093,
"eval_steps_per_second": 0.864,
"step": 33
},
{
"epoch": 34.0,
"eval_accuracy": 1.0,
"eval_loss": 0.025952817872166634,
"eval_runtime": 1.1085,
"eval_samples_per_second": 12.63,
"eval_steps_per_second": 0.902,
"step": 34
},
{
"epoch": 35.0,
"eval_accuracy": 1.0,
"eval_loss": 0.02581631951034069,
"eval_runtime": 1.0967,
"eval_samples_per_second": 12.766,
"eval_steps_per_second": 0.912,
"step": 35
},
{
"epoch": 36.0,
"eval_accuracy": 1.0,
"eval_loss": 0.025539102032780647,
"eval_runtime": 1.1463,
"eval_samples_per_second": 12.213,
"eval_steps_per_second": 0.872,
"step": 36
},
{
"epoch": 37.0,
"eval_accuracy": 1.0,
"eval_loss": 0.024944094941020012,
"eval_runtime": 1.016,
"eval_samples_per_second": 13.78,
"eval_steps_per_second": 0.984,
"step": 37
},
{
"epoch": 38.0,
"eval_accuracy": 1.0,
"eval_loss": 0.024571243673563004,
"eval_runtime": 1.1063,
"eval_samples_per_second": 12.655,
"eval_steps_per_second": 0.904,
"step": 38
},
{
"epoch": 39.0,
"eval_accuracy": 1.0,
"eval_loss": 0.02430080436170101,
"eval_runtime": 1.126,
"eval_samples_per_second": 12.433,
"eval_steps_per_second": 0.888,
"step": 39
},
{
"epoch": 40.0,
"learning_rate": 0.0,
"loss": 0.3497,
"step": 40
},
{
"epoch": 40.0,
"eval_accuracy": 1.0,
"eval_loss": 0.024026570841670036,
"eval_runtime": 1.1297,
"eval_samples_per_second": 12.393,
"eval_steps_per_second": 0.885,
"step": 40
},
{
"epoch": 40.0,
"step": 40,
"total_flos": 1.1633903017132032e+17,
"train_loss": 0.6970286846160889,
"train_runtime": 618.8592,
"train_samples_per_second": 7.562,
"train_steps_per_second": 0.065
}
],
"max_steps": 40,
"num_train_epochs": 40,
"total_flos": 1.1633903017132032e+17,
"trial_name": null,
"trial_params": null
}