image-multi-class-classification / trainer_state.json
lewtun's picture
lewtun HF staff
End of training
4371161
raw
history blame
5.93 kB
{
"best_metric": 0.9833333333333333,
"best_model_checkpoint": "image-classification/checkpoint-422",
"epoch": 1.0,
"global_step": 422,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 1.1627906976744187e-05,
"loss": 2.3142,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 2.3255813953488374e-05,
"loss": 2.2058,
"step": 20
},
{
"epoch": 0.07,
"learning_rate": 3.488372093023256e-05,
"loss": 1.893,
"step": 30
},
{
"epoch": 0.09,
"learning_rate": 4.651162790697675e-05,
"loss": 1.4224,
"step": 40
},
{
"epoch": 0.12,
"learning_rate": 4.907651715039578e-05,
"loss": 1.0782,
"step": 50
},
{
"epoch": 0.14,
"learning_rate": 4.775725593667547e-05,
"loss": 0.877,
"step": 60
},
{
"epoch": 0.17,
"learning_rate": 4.6437994722955145e-05,
"loss": 0.778,
"step": 70
},
{
"epoch": 0.19,
"learning_rate": 4.511873350923483e-05,
"loss": 0.6735,
"step": 80
},
{
"epoch": 0.21,
"learning_rate": 4.379947229551452e-05,
"loss": 0.6688,
"step": 90
},
{
"epoch": 0.24,
"learning_rate": 4.2480211081794194e-05,
"loss": 0.6841,
"step": 100
},
{
"epoch": 0.26,
"learning_rate": 4.116094986807388e-05,
"loss": 0.5935,
"step": 110
},
{
"epoch": 0.28,
"learning_rate": 3.984168865435357e-05,
"loss": 0.5521,
"step": 120
},
{
"epoch": 0.31,
"learning_rate": 3.8522427440633244e-05,
"loss": 0.5555,
"step": 130
},
{
"epoch": 0.33,
"learning_rate": 3.7203166226912934e-05,
"loss": 0.5483,
"step": 140
},
{
"epoch": 0.36,
"learning_rate": 3.588390501319262e-05,
"loss": 0.5371,
"step": 150
},
{
"epoch": 0.38,
"learning_rate": 3.456464379947229e-05,
"loss": 0.5485,
"step": 160
},
{
"epoch": 0.4,
"learning_rate": 3.324538258575198e-05,
"loss": 0.526,
"step": 170
},
{
"epoch": 0.43,
"learning_rate": 3.1926121372031666e-05,
"loss": 0.5255,
"step": 180
},
{
"epoch": 0.45,
"learning_rate": 3.060686015831134e-05,
"loss": 0.5133,
"step": 190
},
{
"epoch": 0.47,
"learning_rate": 2.9287598944591033e-05,
"loss": 0.4857,
"step": 200
},
{
"epoch": 0.5,
"learning_rate": 2.7968337730870712e-05,
"loss": 0.4806,
"step": 210
},
{
"epoch": 0.52,
"learning_rate": 2.6649076517150396e-05,
"loss": 0.4573,
"step": 220
},
{
"epoch": 0.55,
"learning_rate": 2.5329815303430082e-05,
"loss": 0.4995,
"step": 230
},
{
"epoch": 0.57,
"learning_rate": 2.4010554089709765e-05,
"loss": 0.4744,
"step": 240
},
{
"epoch": 0.59,
"learning_rate": 2.269129287598945e-05,
"loss": 0.4543,
"step": 250
},
{
"epoch": 0.62,
"learning_rate": 2.1372031662269128e-05,
"loss": 0.4613,
"step": 260
},
{
"epoch": 0.64,
"learning_rate": 2.0052770448548815e-05,
"loss": 0.475,
"step": 270
},
{
"epoch": 0.66,
"learning_rate": 1.8733509234828498e-05,
"loss": 0.4324,
"step": 280
},
{
"epoch": 0.69,
"learning_rate": 1.741424802110818e-05,
"loss": 0.4003,
"step": 290
},
{
"epoch": 0.71,
"learning_rate": 1.6094986807387864e-05,
"loss": 0.4409,
"step": 300
},
{
"epoch": 0.73,
"learning_rate": 1.4775725593667547e-05,
"loss": 0.492,
"step": 310
},
{
"epoch": 0.76,
"learning_rate": 1.345646437994723e-05,
"loss": 0.4541,
"step": 320
},
{
"epoch": 0.78,
"learning_rate": 1.2137203166226914e-05,
"loss": 0.4202,
"step": 330
},
{
"epoch": 0.81,
"learning_rate": 1.0817941952506597e-05,
"loss": 0.4371,
"step": 340
},
{
"epoch": 0.83,
"learning_rate": 9.49868073878628e-06,
"loss": 0.4339,
"step": 350
},
{
"epoch": 0.85,
"learning_rate": 8.179419525065963e-06,
"loss": 0.4083,
"step": 360
},
{
"epoch": 0.88,
"learning_rate": 6.860158311345646e-06,
"loss": 0.4668,
"step": 370
},
{
"epoch": 0.9,
"learning_rate": 5.540897097625329e-06,
"loss": 0.4238,
"step": 380
},
{
"epoch": 0.92,
"learning_rate": 4.221635883905013e-06,
"loss": 0.434,
"step": 390
},
{
"epoch": 0.95,
"learning_rate": 2.9023746701846966e-06,
"loss": 0.4309,
"step": 400
},
{
"epoch": 0.97,
"learning_rate": 1.5831134564643801e-06,
"loss": 0.4218,
"step": 410
},
{
"epoch": 1.0,
"learning_rate": 2.6385224274406334e-07,
"loss": 0.3743,
"step": 420
},
{
"epoch": 1.0,
"eval_accuracy": 0.9833333333333333,
"eval_loss": 0.05558411777019501,
"eval_runtime": 38.6009,
"eval_samples_per_second": 155.437,
"eval_steps_per_second": 4.87,
"step": 422
},
{
"epoch": 1.0,
"step": 422,
"total_flos": 1.342523444871168e+18,
"train_loss": 0.6594652506694975,
"train_runtime": 822.8009,
"train_samples_per_second": 65.629,
"train_steps_per_second": 0.513
}
],
"max_steps": 422,
"num_train_epochs": 1,
"total_flos": 1.342523444871168e+18,
"trial_name": null,
"trial_params": null
}