|
{ |
|
"best_metric": 3.0165445804595947, |
|
"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": 4.0012, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0001364889025146963, |
|
"loss": 3.8869, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00013560349006508517, |
|
"loss": 3.6034, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0001343703523221556, |
|
"loss": 3.5643, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00013279588885081002, |
|
"loss": 3.3069, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0001308882705802323, |
|
"loss": 3.431, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.00012865739739954807, |
|
"loss": 3.5848, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00012611484678077197, |
|
"loss": 3.4069, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00012327381369567084, |
|
"loss": 3.3532, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00012014904213835435, |
|
"loss": 3.4164, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00011675674860896696, |
|
"loss": 3.5117, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00011311453795557528, |
|
"loss": 3.2964, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.00010924131201100248, |
|
"loss": 3.2104, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.00010515717149875347, |
|
"loss": 3.0675, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00010088331171710597, |
|
"loss": 3.4575, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 9.644191254273106e-05, |
|
"loss": 3.1265, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 9.185602332468734e-05, |
|
"loss": 3.3004, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 8.714944326614944e-05, |
|
"loss": 3.2766, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 8.234659791464919e-05, |
|
"loss": 3.1492, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 7.747241240180272e-05, |
|
"loss": 3.3842, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 7.255218209036649e-05, |
|
"loss": 3.3591, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 6.76114412999196e-05, |
|
"loss": 3.1375, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 6.267583079244174e-05, |
|
"loss": 3.2619, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 5.777096470549132e-05, |
|
"loss": 3.1689, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 5.2922297623555134e-05, |
|
"loss": 3.264, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 4.815499247742428e-05, |
|
"loss": 3.0831, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 4.349378995715337e-05, |
|
"loss": 3.1357, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 3.896288011630533e-05, |
|
"loss": 3.164, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 3.458577683381209e-05, |
|
"loss": 3.2134, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 3.0385195784951376e-05, |
|
"loss": 3.1053, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 2.63829365547284e-05, |
|
"loss": 3.099, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 2.2599769505454377e-05, |
|
"loss": 3.1365, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 1.905532798564004e-05, |
|
"loss": 3.1402, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 1.5768006439603532e-05, |
|
"loss": 3.1203, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1.2754864946569404e-05, |
|
"loss": 3.2424, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 1.0031540684667541e-05, |
|
"loss": 3.2244, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 7.612166779304597e-06, |
|
"loss": 3.2007, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 5.5092989570564855e-06, |
|
"loss": 3.0923, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 3.7338503857237188e-06, |
|
"loss": 3.0841, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 2.295035038707367e-06, |
|
"loss": 3.1703, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 1.2003198776252066e-06, |
|
"loss": 3.2195, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 4.5538610132401196e-07, |
|
"loss": 3.0425, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 6.409966239244377e-08, |
|
"loss": 3.1853, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 3.0165445804595947, |
|
"eval_runtime": 8.1641, |
|
"eval_samples_per_second": 37.236, |
|
"eval_steps_per_second": 4.655, |
|
"step": 218 |
|
} |
|
], |
|
"max_steps": 218, |
|
"num_train_epochs": 1, |
|
"total_flos": 227454713856000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|