|
{ |
|
"best_metric": 2.5633065700531006, |
|
"best_model_checkpoint": "output/xxxtentacion/checkpoint-336", |
|
"epoch": 3.0, |
|
"global_step": 336, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0001365382750064078, |
|
"loss": 2.8729, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.00013456586620543126, |
|
"loss": 2.8615, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0001313208258478339, |
|
"loss": 2.8047, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00012686575814089965, |
|
"loss": 2.9533, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00012128661147092064, |
|
"loss": 2.8864, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00011469102026339097, |
|
"loss": 2.5404, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.00010720622847019214, |
|
"loss": 3.0059, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 9.897663474442597e-05, |
|
"loss": 2.827, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 9.01610066620532e-05, |
|
"loss": 2.804, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 8.092941773433672e-05, |
|
"loss": 2.8347, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 7.14599663030852e-05, |
|
"loss": 2.7375, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 6.193533961866806e-05, |
|
"loss": 2.5601, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 5.253928938754926e-05, |
|
"loss": 2.8287, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 4.345308678404285e-05, |
|
"loss": 2.7017, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 3.4852025317174834e-05, |
|
"loss": 2.7319, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 2.6902039020299325e-05, |
|
"loss": 2.7863, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 1.97565012062839e-05, |
|
"loss": 2.7227, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1.3553265547553997e-05, |
|
"loss": 2.4648, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 8.412006565291007e-06, |
|
"loss": 2.4789, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 4.431910835795193e-06, |
|
"loss": 2.6082, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 1.6897634558914594e-06, |
|
"loss": 2.8574, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 2.384666838129088e-07, |
|
"loss": 2.5917, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 3.0134646892547607, |
|
"eval_runtime": 7.5402, |
|
"eval_samples_per_second": 21.087, |
|
"eval_steps_per_second": 2.652, |
|
"step": 113 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 1.0601933434684325e-07, |
|
"loss": 2.4012, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 1.2949766180319454e-06, |
|
"loss": 2.5116, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 3.7824008453368197e-06, |
|
"loss": 2.682, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 7.5203039468480955e-06, |
|
"loss": 2.6505, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 1.2436573272248243e-05, |
|
"loss": 2.5776, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 1.8436362807314313e-05, |
|
"loss": 2.631, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 2.540392296919934e-05, |
|
"loss": 2.4606, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 3.320483367908481e-05, |
|
"loss": 2.3774, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 4.1688597631154055e-05, |
|
"loss": 2.5596, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 5.06915437278321e-05, |
|
"loss": 2.5551, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 6.003998466742405e-05, |
|
"loss": 2.4846, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 6.955356776710644e-05, |
|
"loss": 2.5243, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 7.904875437627624e-05, |
|
"loss": 2.5396, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 8.834236075446375e-05, |
|
"loss": 2.4629, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 9.725509210222169e-05, |
|
"loss": 2.5566, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 0.00010561500156549765, |
|
"loss": 2.5873, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 0.00011326080748143412, |
|
"loss": 2.5575, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 0.00012004500486837714, |
|
"loss": 2.3709, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 0.0001258367111323791, |
|
"loss": 2.6089, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 0.0001305241910900454, |
|
"loss": 2.5663, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 0.00013401701259429296, |
|
"loss": 2.6963, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 0.00013624779117609787, |
|
"loss": 2.6391, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 0.0001371734900441264, |
|
"loss": 2.7449, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 2.998302936553955, |
|
"eval_runtime": 7.5393, |
|
"eval_samples_per_second": 21.089, |
|
"eval_steps_per_second": 2.653, |
|
"step": 226 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 0.00013548005477567312, |
|
"loss": 2.86, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 0.00013268947730420952, |
|
"loss": 2.4836, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 0.00012864032674294055, |
|
"loss": 2.4962, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 0.00012341211929557585, |
|
"loss": 2.3394, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 0.00011710752518939714, |
|
"loss": 2.3663, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 0.00010985035246307073, |
|
"loss": 2.5085, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 0.00010178311565541946, |
|
"loss": 2.6029, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"learning_rate": 9.306423714063481e-05, |
|
"loss": 2.589, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 2.41, |
|
"learning_rate": 8.38649360694032e-05, |
|
"loss": 2.6019, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"learning_rate": 7.436586601014643e-05, |
|
"loss": 2.5593, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 6.475356731952859e-05, |
|
"loss": 2.38, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 5.5216803909693685e-05, |
|
"loss": 2.5886, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 2.59, |
|
"learning_rate": 4.5942856349875636e-05, |
|
"loss": 2.4662, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 2.63, |
|
"learning_rate": 3.711384409752691e-05, |
|
"loss": 2.6117, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 2.68, |
|
"learning_rate": 2.8903149082065433e-05, |
|
"loss": 2.3842, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 2.1472010874005767e-05, |
|
"loss": 2.4499, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"learning_rate": 1.4966360302693178e-05, |
|
"loss": 2.3766, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 9.513953703256716e-06, |
|
"loss": 2.422, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 2.86, |
|
"learning_rate": 5.221864069725753e-06, |
|
"loss": 2.3515, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 2.9, |
|
"learning_rate": 2.1743783824128875e-06, |
|
"loss": 2.1874, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 2.95, |
|
"learning_rate": 4.3134240132355735e-07, |
|
"loss": 2.2719, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 2.99, |
|
"learning_rate": 2.6985430122565824e-08, |
|
"loss": 2.6279, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 2.5633065700531006, |
|
"eval_runtime": 7.7611, |
|
"eval_samples_per_second": 21.26, |
|
"eval_steps_per_second": 2.706, |
|
"step": 336 |
|
} |
|
], |
|
"max_steps": 336, |
|
"num_train_epochs": 3, |
|
"total_flos": 348563570688000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|