lil-uzi-vert / trainer_state.json
AlekseyKorshuk's picture
huggingartists
0306915
{
"best_metric": 2.9723432064056396,
"best_model_checkpoint": "output/lil-uzi-vert/checkpoint-218",
"epoch": 1.0,
"global_step": 218,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 0.0001370219946819302,
"loss": 2.8388,
"step": 5
},
{
"epoch": 0.05,
"learning_rate": 0.00013648890251469632,
"loss": 2.9,
"step": 10
},
{
"epoch": 0.07,
"learning_rate": 0.00013560349006508517,
"loss": 2.895,
"step": 15
},
{
"epoch": 0.09,
"learning_rate": 0.0001343703523221556,
"loss": 2.8357,
"step": 20
},
{
"epoch": 0.11,
"learning_rate": 0.00013279588885081002,
"loss": 2.8199,
"step": 25
},
{
"epoch": 0.14,
"learning_rate": 0.00013088827058023233,
"loss": 2.7435,
"step": 30
},
{
"epoch": 0.16,
"learning_rate": 0.00012865739739954807,
"loss": 2.8855,
"step": 35
},
{
"epoch": 0.18,
"learning_rate": 0.000126114846780772,
"loss": 2.7549,
"step": 40
},
{
"epoch": 0.21,
"learning_rate": 0.00012327381369567087,
"loss": 2.84,
"step": 45
},
{
"epoch": 0.23,
"learning_rate": 0.00012014904213835432,
"loss": 2.8624,
"step": 50
},
{
"epoch": 0.25,
"learning_rate": 0.00011675674860896702,
"loss": 2.8777,
"step": 55
},
{
"epoch": 0.28,
"learning_rate": 0.00011311453795557527,
"loss": 2.9297,
"step": 60
},
{
"epoch": 0.3,
"learning_rate": 0.00010924131201100249,
"loss": 2.567,
"step": 65
},
{
"epoch": 0.32,
"learning_rate": 0.00010515717149875348,
"loss": 2.8801,
"step": 70
},
{
"epoch": 0.34,
"learning_rate": 0.00010088331171710603,
"loss": 2.9652,
"step": 75
},
{
"epoch": 0.37,
"learning_rate": 9.644191254273106e-05,
"loss": 2.6114,
"step": 80
},
{
"epoch": 0.39,
"learning_rate": 9.185602332468731e-05,
"loss": 2.7817,
"step": 85
},
{
"epoch": 0.41,
"learning_rate": 8.714944326614947e-05,
"loss": 2.8251,
"step": 90
},
{
"epoch": 0.44,
"learning_rate": 8.234659791464915e-05,
"loss": 2.8489,
"step": 95
},
{
"epoch": 0.46,
"learning_rate": 7.747241240180279e-05,
"loss": 2.7123,
"step": 100
},
{
"epoch": 0.48,
"learning_rate": 7.255218209036647e-05,
"loss": 2.6698,
"step": 105
},
{
"epoch": 0.5,
"learning_rate": 6.761144129991962e-05,
"loss": 2.7934,
"step": 110
},
{
"epoch": 0.53,
"learning_rate": 6.267583079244176e-05,
"loss": 2.8273,
"step": 115
},
{
"epoch": 0.55,
"learning_rate": 5.777096470549139e-05,
"loss": 2.8665,
"step": 120
},
{
"epoch": 0.57,
"learning_rate": 5.2922297623555134e-05,
"loss": 2.672,
"step": 125
},
{
"epoch": 0.6,
"learning_rate": 4.815499247742421e-05,
"loss": 2.6851,
"step": 130
},
{
"epoch": 0.62,
"learning_rate": 4.3493789957153346e-05,
"loss": 2.6811,
"step": 135
},
{
"epoch": 0.64,
"learning_rate": 3.8962880116305346e-05,
"loss": 2.8504,
"step": 140
},
{
"epoch": 0.67,
"learning_rate": 3.458577683381216e-05,
"loss": 2.7296,
"step": 145
},
{
"epoch": 0.69,
"learning_rate": 3.0385195784951363e-05,
"loss": 2.9651,
"step": 150
},
{
"epoch": 0.71,
"learning_rate": 2.638293655472844e-05,
"loss": 2.8441,
"step": 155
},
{
"epoch": 0.73,
"learning_rate": 2.259976950545437e-05,
"loss": 2.7186,
"step": 160
},
{
"epoch": 0.76,
"learning_rate": 1.9055327985640047e-05,
"loss": 2.8246,
"step": 165
},
{
"epoch": 0.78,
"learning_rate": 1.5768006439603586e-05,
"loss": 2.5588,
"step": 170
},
{
"epoch": 0.8,
"learning_rate": 1.2754864946569397e-05,
"loss": 2.6992,
"step": 175
},
{
"epoch": 0.83,
"learning_rate": 1.0031540684667565e-05,
"loss": 2.6534,
"step": 180
},
{
"epoch": 0.85,
"learning_rate": 7.612166779304589e-06,
"loss": 2.7594,
"step": 185
},
{
"epoch": 0.87,
"learning_rate": 5.5092989570564855e-06,
"loss": 2.5534,
"step": 190
},
{
"epoch": 0.89,
"learning_rate": 3.733850385723696e-06,
"loss": 2.955,
"step": 195
},
{
"epoch": 0.92,
"learning_rate": 2.2950350387073973e-06,
"loss": 2.8938,
"step": 200
},
{
"epoch": 0.94,
"learning_rate": 1.2003198776252143e-06,
"loss": 2.8361,
"step": 205
},
{
"epoch": 0.96,
"learning_rate": 4.553861013240044e-07,
"loss": 2.8043,
"step": 210
},
{
"epoch": 0.99,
"learning_rate": 6.409966239244377e-08,
"loss": 2.8706,
"step": 215
},
{
"epoch": 1.0,
"eval_loss": 2.9723432064056396,
"eval_runtime": 14.4988,
"eval_samples_per_second": 20.898,
"eval_steps_per_second": 2.621,
"step": 218
}
],
"max_steps": 872,
"num_train_epochs": 4,
"total_flos": 227585359872000.0,
"trial_name": null,
"trial_params": null
}