PlantDiseaseDetectorSwin / trainer_state.json
Abhiram4's picture
End of training
5d855a8 verified
{
"best_metric": 0.9933852555211778,
"best_model_checkpoint": "PlantDiseaseDetectorSwin/checkpoint-586",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 586,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.034129692832764506,
"grad_norm": 2.5282273292541504,
"learning_rate": 8.47457627118644e-06,
"loss": 3.7855,
"step": 10
},
{
"epoch": 0.06825938566552901,
"grad_norm": 2.772298574447632,
"learning_rate": 1.694915254237288e-05,
"loss": 3.6821,
"step": 20
},
{
"epoch": 0.10238907849829351,
"grad_norm": 4.345815658569336,
"learning_rate": 2.5423728813559322e-05,
"loss": 3.4188,
"step": 30
},
{
"epoch": 0.13651877133105803,
"grad_norm": 5.607214450836182,
"learning_rate": 3.389830508474576e-05,
"loss": 2.8902,
"step": 40
},
{
"epoch": 0.17064846416382254,
"grad_norm": 7.322582244873047,
"learning_rate": 4.2372881355932206e-05,
"loss": 2.0221,
"step": 50
},
{
"epoch": 0.20477815699658702,
"grad_norm": 6.228772163391113,
"learning_rate": 4.9905123339658444e-05,
"loss": 1.1851,
"step": 60
},
{
"epoch": 0.23890784982935154,
"grad_norm": 6.644685745239258,
"learning_rate": 4.8956356736242885e-05,
"loss": 0.7389,
"step": 70
},
{
"epoch": 0.27303754266211605,
"grad_norm": 4.455648899078369,
"learning_rate": 4.8007590132827326e-05,
"loss": 0.5337,
"step": 80
},
{
"epoch": 0.30716723549488056,
"grad_norm": 5.760767459869385,
"learning_rate": 4.705882352941177e-05,
"loss": 0.3791,
"step": 90
},
{
"epoch": 0.3412969283276451,
"grad_norm": 4.172321796417236,
"learning_rate": 4.611005692599621e-05,
"loss": 0.3207,
"step": 100
},
{
"epoch": 0.37542662116040953,
"grad_norm": 3.1008100509643555,
"learning_rate": 4.516129032258064e-05,
"loss": 0.2725,
"step": 110
},
{
"epoch": 0.40955631399317405,
"grad_norm": 3.1988861560821533,
"learning_rate": 4.421252371916509e-05,
"loss": 0.2191,
"step": 120
},
{
"epoch": 0.44368600682593856,
"grad_norm": 3.0658085346221924,
"learning_rate": 4.3263757115749525e-05,
"loss": 0.1984,
"step": 130
},
{
"epoch": 0.4778156996587031,
"grad_norm": 3.4681520462036133,
"learning_rate": 4.2314990512333967e-05,
"loss": 0.185,
"step": 140
},
{
"epoch": 0.5119453924914675,
"grad_norm": 3.333508014678955,
"learning_rate": 4.136622390891841e-05,
"loss": 0.1879,
"step": 150
},
{
"epoch": 0.5460750853242321,
"grad_norm": 4.511691093444824,
"learning_rate": 4.041745730550285e-05,
"loss": 0.1665,
"step": 160
},
{
"epoch": 0.5802047781569966,
"grad_norm": 4.345585346221924,
"learning_rate": 3.946869070208729e-05,
"loss": 0.1439,
"step": 170
},
{
"epoch": 0.6143344709897611,
"grad_norm": 4.149386405944824,
"learning_rate": 3.851992409867173e-05,
"loss": 0.1249,
"step": 180
},
{
"epoch": 0.6484641638225256,
"grad_norm": 2.935561418533325,
"learning_rate": 3.757115749525617e-05,
"loss": 0.1228,
"step": 190
},
{
"epoch": 0.6825938566552902,
"grad_norm": 2.6845579147338867,
"learning_rate": 3.662239089184061e-05,
"loss": 0.1204,
"step": 200
},
{
"epoch": 0.7167235494880546,
"grad_norm": 2.9296746253967285,
"learning_rate": 3.567362428842505e-05,
"loss": 0.1271,
"step": 210
},
{
"epoch": 0.7508532423208191,
"grad_norm": 3.4379637241363525,
"learning_rate": 3.472485768500949e-05,
"loss": 0.1311,
"step": 220
},
{
"epoch": 0.7849829351535836,
"grad_norm": 2.2085835933685303,
"learning_rate": 3.377609108159393e-05,
"loss": 0.0897,
"step": 230
},
{
"epoch": 0.8191126279863481,
"grad_norm": 2.58469557762146,
"learning_rate": 3.2827324478178365e-05,
"loss": 0.1059,
"step": 240
},
{
"epoch": 0.8532423208191127,
"grad_norm": 2.334817886352539,
"learning_rate": 3.187855787476281e-05,
"loss": 0.1,
"step": 250
},
{
"epoch": 0.8873720136518771,
"grad_norm": 2.652193784713745,
"learning_rate": 3.0929791271347254e-05,
"loss": 0.0913,
"step": 260
},
{
"epoch": 0.9215017064846417,
"grad_norm": 3.43129301071167,
"learning_rate": 2.998102466793169e-05,
"loss": 0.0979,
"step": 270
},
{
"epoch": 0.9556313993174061,
"grad_norm": 3.3414859771728516,
"learning_rate": 2.9032258064516133e-05,
"loss": 0.0903,
"step": 280
},
{
"epoch": 0.9897610921501706,
"grad_norm": 2.1187517642974854,
"learning_rate": 2.808349146110057e-05,
"loss": 0.0717,
"step": 290
},
{
"epoch": 1.0,
"eval_accuracy": 0.9863437533340446,
"eval_loss": 0.039264366030693054,
"eval_runtime": 85.1157,
"eval_samples_per_second": 110.121,
"eval_steps_per_second": 1.727,
"step": 293
},
{
"epoch": 1.023890784982935,
"grad_norm": 2.212913751602173,
"learning_rate": 2.7134724857685012e-05,
"loss": 0.0797,
"step": 300
},
{
"epoch": 1.0580204778156996,
"grad_norm": 1.8552402257919312,
"learning_rate": 2.618595825426945e-05,
"loss": 0.0649,
"step": 310
},
{
"epoch": 1.0921501706484642,
"grad_norm": 3.584589958190918,
"learning_rate": 2.523719165085389e-05,
"loss": 0.068,
"step": 320
},
{
"epoch": 1.1262798634812285,
"grad_norm": 1.6320329904556274,
"learning_rate": 2.4288425047438332e-05,
"loss": 0.0687,
"step": 330
},
{
"epoch": 1.1604095563139931,
"grad_norm": 2.0501434803009033,
"learning_rate": 2.3339658444022773e-05,
"loss": 0.0726,
"step": 340
},
{
"epoch": 1.1945392491467577,
"grad_norm": 2.5777804851531982,
"learning_rate": 2.239089184060721e-05,
"loss": 0.0742,
"step": 350
},
{
"epoch": 1.2286689419795223,
"grad_norm": 1.8839725255966187,
"learning_rate": 2.1442125237191652e-05,
"loss": 0.0719,
"step": 360
},
{
"epoch": 1.2627986348122868,
"grad_norm": 2.721660614013672,
"learning_rate": 2.049335863377609e-05,
"loss": 0.0635,
"step": 370
},
{
"epoch": 1.2969283276450512,
"grad_norm": 1.7737756967544556,
"learning_rate": 1.954459203036053e-05,
"loss": 0.0634,
"step": 380
},
{
"epoch": 1.3310580204778157,
"grad_norm": 1.465468168258667,
"learning_rate": 1.8595825426944972e-05,
"loss": 0.0626,
"step": 390
},
{
"epoch": 1.36518771331058,
"grad_norm": 1.9786465167999268,
"learning_rate": 1.7647058823529414e-05,
"loss": 0.0663,
"step": 400
},
{
"epoch": 1.3993174061433447,
"grad_norm": 1.6383670568466187,
"learning_rate": 1.6698292220113855e-05,
"loss": 0.054,
"step": 410
},
{
"epoch": 1.4334470989761092,
"grad_norm": 3.260576009750366,
"learning_rate": 1.5749525616698293e-05,
"loss": 0.0526,
"step": 420
},
{
"epoch": 1.4675767918088738,
"grad_norm": 1.9332594871520996,
"learning_rate": 1.4800759013282734e-05,
"loss": 0.0446,
"step": 430
},
{
"epoch": 1.5017064846416384,
"grad_norm": 1.9378633499145508,
"learning_rate": 1.3851992409867173e-05,
"loss": 0.0492,
"step": 440
},
{
"epoch": 1.5358361774744027,
"grad_norm": 2.8215017318725586,
"learning_rate": 1.2903225806451613e-05,
"loss": 0.0568,
"step": 450
},
{
"epoch": 1.5699658703071673,
"grad_norm": 1.6412670612335205,
"learning_rate": 1.1954459203036052e-05,
"loss": 0.0429,
"step": 460
},
{
"epoch": 1.6040955631399316,
"grad_norm": 1.4835631847381592,
"learning_rate": 1.1005692599620495e-05,
"loss": 0.0408,
"step": 470
},
{
"epoch": 1.6382252559726962,
"grad_norm": 3.138010263442993,
"learning_rate": 1.0056925996204935e-05,
"loss": 0.0552,
"step": 480
},
{
"epoch": 1.6723549488054608,
"grad_norm": 2.551870346069336,
"learning_rate": 9.108159392789374e-06,
"loss": 0.0442,
"step": 490
},
{
"epoch": 1.7064846416382253,
"grad_norm": 2.015259027481079,
"learning_rate": 8.159392789373814e-06,
"loss": 0.0459,
"step": 500
},
{
"epoch": 1.74061433447099,
"grad_norm": 1.7179967164993286,
"learning_rate": 7.210626185958256e-06,
"loss": 0.037,
"step": 510
},
{
"epoch": 1.7747440273037542,
"grad_norm": 1.3625215291976929,
"learning_rate": 6.261859582542695e-06,
"loss": 0.0399,
"step": 520
},
{
"epoch": 1.8088737201365188,
"grad_norm": 1.3097296953201294,
"learning_rate": 5.313092979127135e-06,
"loss": 0.0327,
"step": 530
},
{
"epoch": 1.8430034129692832,
"grad_norm": 1.0734279155731201,
"learning_rate": 4.364326375711575e-06,
"loss": 0.0419,
"step": 540
},
{
"epoch": 1.8771331058020477,
"grad_norm": 2.2438840866088867,
"learning_rate": 3.4155597722960153e-06,
"loss": 0.0437,
"step": 550
},
{
"epoch": 1.9112627986348123,
"grad_norm": 2.878282308578491,
"learning_rate": 2.4667931688804556e-06,
"loss": 0.0439,
"step": 560
},
{
"epoch": 1.9453924914675769,
"grad_norm": 1.2499854564666748,
"learning_rate": 1.5180265654648958e-06,
"loss": 0.0398,
"step": 570
},
{
"epoch": 1.9795221843003414,
"grad_norm": 1.1977864503860474,
"learning_rate": 5.692599620493359e-07,
"loss": 0.0384,
"step": 580
},
{
"epoch": 2.0,
"eval_accuracy": 0.9933852555211778,
"eval_loss": 0.020666491240262985,
"eval_runtime": 83.7475,
"eval_samples_per_second": 111.92,
"eval_steps_per_second": 1.755,
"step": 586
},
{
"epoch": 2.0,
"step": 586,
"total_flos": 4.885017433779732e+18,
"train_loss": 0.39566828084175093,
"train_runtime": 4610.2266,
"train_samples_per_second": 32.531,
"train_steps_per_second": 0.127
}
],
"logging_steps": 10,
"max_steps": 586,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.885017433779732e+18,
"train_batch_size": 64,
"trial_name": null,
"trial_params": null
}