delivery_truck_classification / trainer_state.json
JEdward7777's picture
End of training
147e9e5
raw
history blame
10.6 kB
{
"best_metric": 0.9090909090909091,
"best_model_checkpoint": "delivery_truck_classification/checkpoint-21",
"epoch": 39.57142857142857,
"global_step": 40,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.57,
"eval_accuracy": 0.13636363636363635,
"eval_loss": 1.9638466835021973,
"eval_runtime": 1.6283,
"eval_samples_per_second": 13.511,
"eval_steps_per_second": 0.614,
"step": 1
},
{
"epoch": 1.57,
"eval_accuracy": 0.09090909090909091,
"eval_loss": 1.9021785259246826,
"eval_runtime": 1.7599,
"eval_samples_per_second": 12.501,
"eval_steps_per_second": 0.568,
"step": 2
},
{
"epoch": 2.57,
"eval_accuracy": 0.09090909090909091,
"eval_loss": 1.7954376935958862,
"eval_runtime": 1.7675,
"eval_samples_per_second": 12.447,
"eval_steps_per_second": 0.566,
"step": 3
},
{
"epoch": 3.57,
"eval_accuracy": 0.36363636363636365,
"eval_loss": 1.646571397781372,
"eval_runtime": 1.8048,
"eval_samples_per_second": 12.19,
"eval_steps_per_second": 0.554,
"step": 4
},
{
"epoch": 4.57,
"eval_accuracy": 0.5,
"eval_loss": 1.516127347946167,
"eval_runtime": 1.8376,
"eval_samples_per_second": 11.972,
"eval_steps_per_second": 0.544,
"step": 5
},
{
"epoch": 5.57,
"eval_accuracy": 0.5454545454545454,
"eval_loss": 1.4261207580566406,
"eval_runtime": 1.6096,
"eval_samples_per_second": 13.668,
"eval_steps_per_second": 0.621,
"step": 6
},
{
"epoch": 6.57,
"eval_accuracy": 0.5454545454545454,
"eval_loss": 1.3546966314315796,
"eval_runtime": 1.568,
"eval_samples_per_second": 14.03,
"eval_steps_per_second": 0.638,
"step": 7
},
{
"epoch": 7.57,
"eval_accuracy": 0.6363636363636364,
"eval_loss": 1.2797943353652954,
"eval_runtime": 1.8043,
"eval_samples_per_second": 12.193,
"eval_steps_per_second": 0.554,
"step": 8
},
{
"epoch": 8.57,
"eval_accuracy": 0.6363636363636364,
"eval_loss": 1.2200274467468262,
"eval_runtime": 1.811,
"eval_samples_per_second": 12.148,
"eval_steps_per_second": 0.552,
"step": 9
},
{
"epoch": 9.57,
"eval_accuracy": 0.6363636363636364,
"eval_loss": 1.1594452857971191,
"eval_runtime": 1.803,
"eval_samples_per_second": 12.202,
"eval_steps_per_second": 0.555,
"step": 10
},
{
"epoch": 10.57,
"eval_accuracy": 0.6818181818181818,
"eval_loss": 1.1154121160507202,
"eval_runtime": 1.7747,
"eval_samples_per_second": 12.397,
"eval_steps_per_second": 0.563,
"step": 11
},
{
"epoch": 11.57,
"eval_accuracy": 0.6818181818181818,
"eval_loss": 1.07809579372406,
"eval_runtime": 1.6416,
"eval_samples_per_second": 13.401,
"eval_steps_per_second": 0.609,
"step": 12
},
{
"epoch": 12.57,
"eval_accuracy": 0.6818181818181818,
"eval_loss": 1.0285967588424683,
"eval_runtime": 1.7863,
"eval_samples_per_second": 12.316,
"eval_steps_per_second": 0.56,
"step": 13
},
{
"epoch": 13.57,
"eval_accuracy": 0.6818181818181818,
"eval_loss": 0.9623335003852844,
"eval_runtime": 1.8244,
"eval_samples_per_second": 12.059,
"eval_steps_per_second": 0.548,
"step": 14
},
{
"epoch": 14.57,
"eval_accuracy": 0.6818181818181818,
"eval_loss": 0.8952316641807556,
"eval_runtime": 1.8255,
"eval_samples_per_second": 12.052,
"eval_steps_per_second": 0.548,
"step": 15
},
{
"epoch": 15.57,
"eval_accuracy": 0.7272727272727273,
"eval_loss": 0.8217518329620361,
"eval_runtime": 1.8059,
"eval_samples_per_second": 12.182,
"eval_steps_per_second": 0.554,
"step": 16
},
{
"epoch": 16.57,
"eval_accuracy": 0.7727272727272727,
"eval_loss": 0.7331055998802185,
"eval_runtime": 1.6554,
"eval_samples_per_second": 13.29,
"eval_steps_per_second": 0.604,
"step": 17
},
{
"epoch": 17.57,
"eval_accuracy": 0.8181818181818182,
"eval_loss": 0.6525326371192932,
"eval_runtime": 1.8033,
"eval_samples_per_second": 12.2,
"eval_steps_per_second": 0.555,
"step": 18
},
{
"epoch": 18.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.5678051710128784,
"eval_runtime": 1.7903,
"eval_samples_per_second": 12.288,
"eval_steps_per_second": 0.559,
"step": 19
},
{
"epoch": 19.57,
"learning_rate": 2.777777777777778e-05,
"loss": 1.9399,
"step": 20
},
{
"epoch": 19.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.497961163520813,
"eval_runtime": 1.8331,
"eval_samples_per_second": 12.002,
"eval_steps_per_second": 0.546,
"step": 20
},
{
"epoch": 20.57,
"eval_accuracy": 0.9090909090909091,
"eval_loss": 0.46136438846588135,
"eval_runtime": 1.8006,
"eval_samples_per_second": 12.218,
"eval_steps_per_second": 0.555,
"step": 21
},
{
"epoch": 21.57,
"eval_accuracy": 0.9090909090909091,
"eval_loss": 0.4493587613105774,
"eval_runtime": 1.6389,
"eval_samples_per_second": 13.424,
"eval_steps_per_second": 0.61,
"step": 22
},
{
"epoch": 22.57,
"eval_accuracy": 0.8181818181818182,
"eval_loss": 0.4404635727405548,
"eval_runtime": 1.8581,
"eval_samples_per_second": 11.84,
"eval_steps_per_second": 0.538,
"step": 23
},
{
"epoch": 23.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.4357987344264984,
"eval_runtime": 1.7864,
"eval_samples_per_second": 12.315,
"eval_steps_per_second": 0.56,
"step": 24
},
{
"epoch": 24.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.43069612979888916,
"eval_runtime": 1.804,
"eval_samples_per_second": 12.195,
"eval_steps_per_second": 0.554,
"step": 25
},
{
"epoch": 25.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.4099968671798706,
"eval_runtime": 1.7489,
"eval_samples_per_second": 12.579,
"eval_steps_per_second": 0.572,
"step": 26
},
{
"epoch": 26.57,
"eval_accuracy": 0.8181818181818182,
"eval_loss": 0.3925555944442749,
"eval_runtime": 1.6257,
"eval_samples_per_second": 13.533,
"eval_steps_per_second": 0.615,
"step": 27
},
{
"epoch": 27.57,
"eval_accuracy": 0.8181818181818182,
"eval_loss": 0.3818438649177551,
"eval_runtime": 1.8073,
"eval_samples_per_second": 12.173,
"eval_steps_per_second": 0.553,
"step": 28
},
{
"epoch": 28.57,
"eval_accuracy": 0.8181818181818182,
"eval_loss": 0.366110235452652,
"eval_runtime": 1.7879,
"eval_samples_per_second": 12.305,
"eval_steps_per_second": 0.559,
"step": 29
},
{
"epoch": 29.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.35147225856781006,
"eval_runtime": 1.8109,
"eval_samples_per_second": 12.149,
"eval_steps_per_second": 0.552,
"step": 30
},
{
"epoch": 30.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.3345157206058502,
"eval_runtime": 1.8479,
"eval_samples_per_second": 11.905,
"eval_steps_per_second": 0.541,
"step": 31
},
{
"epoch": 31.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.32043513655662537,
"eval_runtime": 1.599,
"eval_samples_per_second": 13.759,
"eval_steps_per_second": 0.625,
"step": 32
},
{
"epoch": 32.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.3077632486820221,
"eval_runtime": 1.8226,
"eval_samples_per_second": 12.071,
"eval_steps_per_second": 0.549,
"step": 33
},
{
"epoch": 33.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.2948474586009979,
"eval_runtime": 1.7885,
"eval_samples_per_second": 12.301,
"eval_steps_per_second": 0.559,
"step": 34
},
{
"epoch": 34.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.2848185896873474,
"eval_runtime": 1.8362,
"eval_samples_per_second": 11.981,
"eval_steps_per_second": 0.545,
"step": 35
},
{
"epoch": 35.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.2748388946056366,
"eval_runtime": 1.8319,
"eval_samples_per_second": 12.009,
"eval_steps_per_second": 0.546,
"step": 36
},
{
"epoch": 36.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.2679346203804016,
"eval_runtime": 1.6038,
"eval_samples_per_second": 13.718,
"eval_steps_per_second": 0.624,
"step": 37
},
{
"epoch": 37.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.26424679160118103,
"eval_runtime": 1.8361,
"eval_samples_per_second": 11.982,
"eval_steps_per_second": 0.545,
"step": 38
},
{
"epoch": 38.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.2638870179653168,
"eval_runtime": 1.7769,
"eval_samples_per_second": 12.381,
"eval_steps_per_second": 0.563,
"step": 39
},
{
"epoch": 39.57,
"learning_rate": 0.0,
"loss": 0.728,
"step": 40
},
{
"epoch": 39.57,
"eval_accuracy": 0.8636363636363636,
"eval_loss": 0.26363667845726013,
"eval_runtime": 1.7373,
"eval_samples_per_second": 12.663,
"eval_steps_per_second": 0.576,
"step": 40
},
{
"epoch": 39.57,
"step": 40,
"total_flos": 1.9417183005730406e+17,
"train_loss": 1.3339122772216796,
"train_runtime": 965.4815,
"train_samples_per_second": 8.162,
"train_steps_per_second": 0.041
}
],
"max_steps": 40,
"num_train_epochs": 40,
"total_flos": 1.9417183005730406e+17,
"trial_name": null,
"trial_params": null
}