|
{ |
|
"best_metric": 1.5412778854370117, |
|
"best_model_checkpoint": "output/madonna/checkpoint-448", |
|
"epoch": 2.0, |
|
"global_step": 448, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.0001370283488463827, |
|
"loss": 2.5046, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00013651425439773298, |
|
"loss": 2.4348, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00013566028939181128, |
|
"loss": 2.5907, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.00013447072741690948, |
|
"loss": 2.4827, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00013295152152507697, |
|
"loss": 2.4145, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0001311102744406261, |
|
"loss": 2.1817, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.00012895620051300705, |
|
"loss": 2.3325, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.0001265000796044546, |
|
"loss": 2.0885, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00012375420314317213, |
|
"loss": 2.1847, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00012073231261202464, |
|
"loss": 2.1728, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00011744953078056836, |
|
"loss": 2.0993, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00011392228602455959, |
|
"loss": 2.3687, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.0001101682301116794, |
|
"loss": 1.9625, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0001062061498649071, |
|
"loss": 2.0389, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00010205587314561534, |
|
"loss": 2.098, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 9.773816962688569e-05, |
|
"loss": 2.1281, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 9.327464685361516e-05, |
|
"loss": 1.9415, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 8.868764210957135e-05, |
|
"loss": 2.3485, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 8.400011063253747e-05, |
|
"loss": 2.1515, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 7.923551073696397e-05, |
|
"loss": 1.8548, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 7.441768641901993e-05, |
|
"loss": 1.969, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 6.957074803153629e-05, |
|
"loss": 2.0221, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 6.471895162599185e-05, |
|
"loss": 2.0988, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 5.9886577565364115e-05, |
|
"loss": 1.7345, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 5.509780901531541e-05, |
|
"loss": 1.9466, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 5.037661092179389e-05, |
|
"loss": 2.1125, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 4.574661008069485e-05, |
|
"loss": 2.0488, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 4.123097689976244e-05, |
|
"loss": 2.0849, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 3.685230944444331e-05, |
|
"loss": 1.8891, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 3.263252034797391e-05, |
|
"loss": 1.8136, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 2.8592727151649647e-05, |
|
"loss": 1.9213, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 2.475314662405725e-05, |
|
"loss": 1.9865, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 2.113299358814034e-05, |
|
"loss": 2.2742, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 1.7750384762408767e-05, |
|
"loss": 1.8535, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 1.4622248097508915e-05, |
|
"loss": 2.1606, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 1.1764238061872434e-05, |
|
"loss": 1.7923, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 9.190657300387505e-06, |
|
"loss": 1.8476, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 6.91438505814559e-06, |
|
"loss": 1.9976, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 4.9468127274594585e-06, |
|
"loss": 1.9706, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 3.2977868407019207e-06, |
|
"loss": 1.982, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 1.975559794252193e-06, |
|
"loss": 1.9318, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 9.867485501471999e-07, |
|
"loss": 2.035, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 3.363015221117509e-07, |
|
"loss": 1.9653, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 2.7473811683140093e-08, |
|
"loss": 1.8408, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.924851655960083, |
|
"eval_runtime": 14.2025, |
|
"eval_samples_per_second": 22.672, |
|
"eval_steps_per_second": 2.887, |
|
"step": 222 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.7440342903137207, |
|
"eval_runtime": 17.6835, |
|
"eval_samples_per_second": 17.361, |
|
"eval_steps_per_second": 2.205, |
|
"step": 224 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 6.746689293153874e-09, |
|
"loss": 2.1578, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 2.427415035313232e-07, |
|
"loss": 1.867, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 8.147449052190903e-07, |
|
"loss": 1.7004, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 1.7199452243268996e-06, |
|
"loss": 1.8748, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 2.9538929687704672e-06, |
|
"loss": 1.7175, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 4.510522695790453e-06, |
|
"loss": 1.9134, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 6.382182826501689e-06, |
|
"loss": 1.8779, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 8.559673257059505e-06, |
|
"loss": 1.9084, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 1.1032290581565944e-05, |
|
"loss": 1.7949, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 1.3787880704424101e-05, |
|
"loss": 1.7769, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 1.681289858352526e-05, |
|
"loss": 1.724, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 2.009247481060283e-05, |
|
"loss": 1.8311, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 2.3610488701478854e-05, |
|
"loss": 1.7348, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 2.734964753692934e-05, |
|
"loss": 1.768, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 3.129157156466198e-05, |
|
"loss": 1.7488, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 3.541688434458052e-05, |
|
"loss": 1.9316, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 3.970530799324656e-05, |
|
"loss": 1.7607, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 4.413576285936533e-05, |
|
"loss": 1.6681, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 4.8686471140343875e-05, |
|
"loss": 2.065, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 5.333506393059682e-05, |
|
"loss": 1.848, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 5.805869117540521e-05, |
|
"loss": 1.8802, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 6.283413398985365e-05, |
|
"loss": 1.7551, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 6.763791879074358e-05, |
|
"loss": 1.7544, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 7.244643268047132e-05, |
|
"loss": 1.793, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 7.723603951570171e-05, |
|
"loss": 1.7917, |
|
"step": 345 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 8.19831960903064e-05, |
|
"loss": 1.63, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 8.666456786147141e-05, |
|
"loss": 2.0457, |
|
"step": 355 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 9.125714365012444e-05, |
|
"loss": 2.0322, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 9.5738348751875e-05, |
|
"loss": 1.687, |
|
"step": 365 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 0.00010008615590247305, |
|
"loss": 1.9025, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 0.00010427919355233763, |
|
"loss": 1.7503, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 0.00010829685091793463, |
|
"loss": 1.7749, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 0.00011211937929362609, |
|
"loss": 1.6852, |
|
"step": 385 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 0.00011572798912599424, |
|
"loss": 1.8013, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 0.00011910494237347491, |
|
"loss": 1.5069, |
|
"step": 395 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 0.00012223363969730684, |
|
"loss": 1.5859, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 0.00012509870205521334, |
|
"loss": 1.5894, |
|
"step": 405 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 0.00012768604629674322, |
|
"loss": 1.9085, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 0.00012998295438868449, |
|
"loss": 1.8982, |
|
"step": 415 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 0.00013197813593027427, |
|
"loss": 1.9507, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 0.00013366178365091335, |
|
"loss": 1.7504, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 0.00013502562161758715, |
|
"loss": 1.7843, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 0.00013606294591503093, |
|
"loss": 1.6083, |
|
"step": 435 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 0.00013676865759867644, |
|
"loss": 1.5864, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 0.00013713928775840084, |
|
"loss": 1.8849, |
|
"step": 445 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 1.5412778854370117, |
|
"eval_runtime": 17.7637, |
|
"eval_samples_per_second": 17.282, |
|
"eval_steps_per_second": 2.195, |
|
"step": 448 |
|
} |
|
], |
|
"max_steps": 448, |
|
"num_train_epochs": 2, |
|
"total_flos": 467712737280000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|