cifar10_outputs / trainer_state.json
jimypbr's picture
End of training
882b536
raw
history blame
5.24 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 100.0,
"global_step": 400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 2.5,
"learning_rate": 1e-05,
"loss": 2.2814,
"step": 10
},
{
"epoch": 5.0,
"learning_rate": 2e-05,
"loss": 2.2162,
"step": 20
},
{
"epoch": 7.5,
"learning_rate": 3e-05,
"loss": 2.06,
"step": 30
},
{
"epoch": 10.0,
"learning_rate": 4e-05,
"loss": 1.7632,
"step": 40
},
{
"epoch": 12.5,
"learning_rate": 5e-05,
"loss": 1.3906,
"step": 50
},
{
"epoch": 15.0,
"learning_rate": 6e-05,
"loss": 1.0958,
"step": 60
},
{
"epoch": 17.5,
"learning_rate": 7e-05,
"loss": 0.8168,
"step": 70
},
{
"epoch": 20.0,
"learning_rate": 8e-05,
"loss": 0.6212,
"step": 80
},
{
"epoch": 22.5,
"learning_rate": 9e-05,
"loss": 0.5377,
"step": 90
},
{
"epoch": 25.0,
"learning_rate": 0.0001,
"loss": 0.4409,
"step": 100
},
{
"epoch": 27.5,
"learning_rate": 9.972609476841367e-05,
"loss": 0.4009,
"step": 110
},
{
"epoch": 30.0,
"learning_rate": 9.890738003669029e-05,
"loss": 0.3598,
"step": 120
},
{
"epoch": 32.5,
"learning_rate": 9.755282581475769e-05,
"loss": 0.2784,
"step": 130
},
{
"epoch": 35.0,
"learning_rate": 9.567727288213005e-05,
"loss": 0.3299,
"step": 140
},
{
"epoch": 37.5,
"learning_rate": 9.330127018922194e-05,
"loss": 0.3236,
"step": 150
},
{
"epoch": 40.0,
"learning_rate": 9.045084971874738e-05,
"loss": 0.2714,
"step": 160
},
{
"epoch": 42.5,
"learning_rate": 8.715724127386972e-05,
"loss": 0.2654,
"step": 170
},
{
"epoch": 45.0,
"learning_rate": 8.345653031794292e-05,
"loss": 0.254,
"step": 180
},
{
"epoch": 47.5,
"learning_rate": 7.938926261462366e-05,
"loss": 0.2223,
"step": 190
},
{
"epoch": 50.0,
"learning_rate": 7.500000000000001e-05,
"loss": 0.2671,
"step": 200
},
{
"epoch": 52.5,
"learning_rate": 7.033683215379002e-05,
"loss": 0.2293,
"step": 210
},
{
"epoch": 55.0,
"learning_rate": 6.545084971874738e-05,
"loss": 0.2235,
"step": 220
},
{
"epoch": 57.5,
"learning_rate": 6.0395584540887963e-05,
"loss": 0.2031,
"step": 230
},
{
"epoch": 60.0,
"learning_rate": 5.522642316338268e-05,
"loss": 0.2034,
"step": 240
},
{
"epoch": 62.5,
"learning_rate": 5e-05,
"loss": 0.189,
"step": 250
},
{
"epoch": 65.0,
"learning_rate": 4.477357683661734e-05,
"loss": 0.1788,
"step": 260
},
{
"epoch": 67.5,
"learning_rate": 3.960441545911204e-05,
"loss": 0.1698,
"step": 270
},
{
"epoch": 70.0,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.2309,
"step": 280
},
{
"epoch": 72.5,
"learning_rate": 2.9663167846209998e-05,
"loss": 0.1637,
"step": 290
},
{
"epoch": 75.0,
"learning_rate": 2.500000000000001e-05,
"loss": 0.1669,
"step": 300
},
{
"epoch": 77.5,
"learning_rate": 2.061073738537635e-05,
"loss": 0.1786,
"step": 310
},
{
"epoch": 80.0,
"learning_rate": 1.6543469682057106e-05,
"loss": 0.1792,
"step": 320
},
{
"epoch": 82.5,
"learning_rate": 1.2842758726130283e-05,
"loss": 0.1874,
"step": 330
},
{
"epoch": 85.0,
"learning_rate": 9.549150281252633e-06,
"loss": 0.1805,
"step": 340
},
{
"epoch": 87.5,
"learning_rate": 6.698729810778065e-06,
"loss": 0.196,
"step": 350
},
{
"epoch": 90.0,
"learning_rate": 4.322727117869951e-06,
"loss": 0.1615,
"step": 360
},
{
"epoch": 92.5,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.1481,
"step": 370
},
{
"epoch": 95.0,
"learning_rate": 1.0926199633097157e-06,
"loss": 0.1633,
"step": 380
},
{
"epoch": 97.5,
"learning_rate": 2.7390523158633554e-07,
"loss": 0.1673,
"step": 390
},
{
"epoch": 100.0,
"learning_rate": 0.0,
"loss": 0.1748,
"step": 400
},
{
"epoch": 100.0,
"step": 400,
"total_flos": 1.3814551337974377e+23,
"train_loss": 0.4972930908203125,
"train_runtime": 820.6819,
"train_samples_per_second": 4242.326,
"train_steps_per_second": 0.487
}
],
"max_steps": 400,
"num_train_epochs": 100,
"start_time": 1656513160.5917685,
"total_flos": 1.3814551337974377e+23,
"trial_name": null,
"trial_params": null
}