AI_ImageClassification_SDXL / trainer_state.json
ideepankarsharma2003's picture
added model files
8d3ca06
{
"best_metric": 0.996,
"best_model_checkpoint": "AI_ImageClassification_SDXL/checkpoint-586",
"epoch": 0.9995735607675906,
"eval_steps": 500,
"global_step": 586,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 2.840909090909091e-06,
"loss": 1.2947,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 5.681818181818182e-06,
"loss": 0.689,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 8.522727272727273e-06,
"loss": 0.2576,
"step": 30
},
{
"epoch": 0.07,
"learning_rate": 1.1363636363636365e-05,
"loss": 0.23,
"step": 40
},
{
"epoch": 0.09,
"learning_rate": 1.4204545454545456e-05,
"loss": 0.1137,
"step": 50
},
{
"epoch": 0.1,
"learning_rate": 1.7045454545454546e-05,
"loss": 0.0554,
"step": 60
},
{
"epoch": 0.12,
"learning_rate": 1.9886363636363638e-05,
"loss": 0.059,
"step": 70
},
{
"epoch": 0.14,
"learning_rate": 2.272727272727273e-05,
"loss": 0.0583,
"step": 80
},
{
"epoch": 0.15,
"learning_rate": 2.5568181818181817e-05,
"loss": 0.0349,
"step": 90
},
{
"epoch": 0.17,
"learning_rate": 2.8409090909090912e-05,
"loss": 0.0864,
"step": 100
},
{
"epoch": 0.19,
"learning_rate": 3.125e-05,
"loss": 0.0145,
"step": 110
},
{
"epoch": 0.2,
"learning_rate": 3.409090909090909e-05,
"loss": 0.0358,
"step": 120
},
{
"epoch": 0.22,
"learning_rate": 3.6931818181818184e-05,
"loss": 0.0473,
"step": 130
},
{
"epoch": 0.24,
"learning_rate": 3.9772727272727275e-05,
"loss": 0.0253,
"step": 140
},
{
"epoch": 0.26,
"learning_rate": 4.261363636363637e-05,
"loss": 0.0574,
"step": 150
},
{
"epoch": 0.27,
"learning_rate": 4.545454545454546e-05,
"loss": 0.0403,
"step": 160
},
{
"epoch": 0.29,
"learning_rate": 4.829545454545455e-05,
"loss": 0.0481,
"step": 170
},
{
"epoch": 0.31,
"learning_rate": 4.9873577749683945e-05,
"loss": 0.0246,
"step": 180
},
{
"epoch": 0.32,
"learning_rate": 4.955752212389381e-05,
"loss": 0.0094,
"step": 190
},
{
"epoch": 0.34,
"learning_rate": 4.924146649810367e-05,
"loss": 0.0413,
"step": 200
},
{
"epoch": 0.36,
"learning_rate": 4.892541087231353e-05,
"loss": 0.0339,
"step": 210
},
{
"epoch": 0.38,
"learning_rate": 4.860935524652339e-05,
"loss": 0.0523,
"step": 220
},
{
"epoch": 0.39,
"learning_rate": 4.829329962073325e-05,
"loss": 0.0104,
"step": 230
},
{
"epoch": 0.41,
"learning_rate": 4.797724399494311e-05,
"loss": 0.0309,
"step": 240
},
{
"epoch": 0.43,
"learning_rate": 4.7661188369152975e-05,
"loss": 0.0248,
"step": 250
},
{
"epoch": 0.44,
"learning_rate": 4.734513274336283e-05,
"loss": 0.0306,
"step": 260
},
{
"epoch": 0.46,
"learning_rate": 4.70290771175727e-05,
"loss": 0.0162,
"step": 270
},
{
"epoch": 0.48,
"learning_rate": 4.6713021491782554e-05,
"loss": 0.016,
"step": 280
},
{
"epoch": 0.49,
"learning_rate": 4.639696586599241e-05,
"loss": 0.0103,
"step": 290
},
{
"epoch": 0.51,
"learning_rate": 4.608091024020228e-05,
"loss": 0.0196,
"step": 300
},
{
"epoch": 0.53,
"learning_rate": 4.576485461441214e-05,
"loss": 0.0264,
"step": 310
},
{
"epoch": 0.55,
"learning_rate": 4.5448798988622e-05,
"loss": 0.0344,
"step": 320
},
{
"epoch": 0.56,
"learning_rate": 4.5132743362831855e-05,
"loss": 0.036,
"step": 330
},
{
"epoch": 0.58,
"learning_rate": 4.4816687737041726e-05,
"loss": 0.0082,
"step": 340
},
{
"epoch": 0.6,
"learning_rate": 4.4500632111251584e-05,
"loss": 0.0149,
"step": 350
},
{
"epoch": 0.61,
"learning_rate": 4.418457648546144e-05,
"loss": 0.0082,
"step": 360
},
{
"epoch": 0.63,
"learning_rate": 4.3868520859671306e-05,
"loss": 0.0451,
"step": 370
},
{
"epoch": 0.65,
"learning_rate": 4.355246523388117e-05,
"loss": 0.0055,
"step": 380
},
{
"epoch": 0.67,
"learning_rate": 4.323640960809103e-05,
"loss": 0.0087,
"step": 390
},
{
"epoch": 0.68,
"learning_rate": 4.2920353982300885e-05,
"loss": 0.0052,
"step": 400
},
{
"epoch": 0.7,
"learning_rate": 4.260429835651075e-05,
"loss": 0.0033,
"step": 410
},
{
"epoch": 0.72,
"learning_rate": 4.2288242730720607e-05,
"loss": 0.0148,
"step": 420
},
{
"epoch": 0.73,
"learning_rate": 4.197218710493047e-05,
"loss": 0.0134,
"step": 430
},
{
"epoch": 0.75,
"learning_rate": 4.165613147914033e-05,
"loss": 0.0125,
"step": 440
},
{
"epoch": 0.77,
"learning_rate": 4.134007585335019e-05,
"loss": 0.0531,
"step": 450
},
{
"epoch": 0.78,
"learning_rate": 4.102402022756005e-05,
"loss": 0.0059,
"step": 460
},
{
"epoch": 0.8,
"learning_rate": 4.0707964601769914e-05,
"loss": 0.0059,
"step": 470
},
{
"epoch": 0.82,
"learning_rate": 4.039190897597978e-05,
"loss": 0.0194,
"step": 480
},
{
"epoch": 0.84,
"learning_rate": 4.0075853350189636e-05,
"loss": 0.0111,
"step": 490
},
{
"epoch": 0.85,
"learning_rate": 3.9759797724399494e-05,
"loss": 0.0321,
"step": 500
},
{
"epoch": 0.87,
"learning_rate": 3.944374209860936e-05,
"loss": 0.0261,
"step": 510
},
{
"epoch": 0.89,
"learning_rate": 3.912768647281922e-05,
"loss": 0.0196,
"step": 520
},
{
"epoch": 0.9,
"learning_rate": 3.881163084702908e-05,
"loss": 0.0038,
"step": 530
},
{
"epoch": 0.92,
"learning_rate": 3.849557522123894e-05,
"loss": 0.0216,
"step": 540
},
{
"epoch": 0.94,
"learning_rate": 3.81795195954488e-05,
"loss": 0.0047,
"step": 550
},
{
"epoch": 0.96,
"learning_rate": 3.7863463969658666e-05,
"loss": 0.0095,
"step": 560
},
{
"epoch": 0.97,
"learning_rate": 3.754740834386852e-05,
"loss": 0.0036,
"step": 570
},
{
"epoch": 0.99,
"learning_rate": 3.723135271807838e-05,
"loss": 0.0025,
"step": 580
},
{
"epoch": 1.0,
"eval_accuracy": 0.996,
"eval_loss": 0.015431854873895645,
"eval_runtime": 44.7221,
"eval_samples_per_second": 44.721,
"eval_steps_per_second": 2.795,
"step": 586
}
],
"logging_steps": 10,
"max_steps": 1758,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 2.9390551738299924e+18,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}