|
{ |
|
"best_metric": 0.9681063122923588, |
|
"best_model_checkpoint": "convnextv2-large-1k-224-finetuned-LungCancer-Classification-LC25000-AH-40-30-30-Shuffled-3rd/checkpoint-93", |
|
"epoch": 6.944, |
|
"eval_steps": 500, |
|
"global_step": 651, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 7.668711656441718e-06, |
|
"loss": 1.094, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 1.5337423312883436e-05, |
|
"loss": 1.0587, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 2.300613496932515e-05, |
|
"loss": 0.9946, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 3.067484662576687e-05, |
|
"loss": 0.9056, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 3.834355828220859e-05, |
|
"loss": 0.7914, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 4.60122699386503e-05, |
|
"loss": 0.65, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 5.368098159509203e-05, |
|
"loss": 0.4872, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 6.134969325153375e-05, |
|
"loss": 0.3592, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 6.901840490797547e-05, |
|
"loss": 0.3144, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 7.668711656441718e-05, |
|
"loss": 0.2393, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 8.43558282208589e-05, |
|
"loss": 0.1919, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 9.20245398773006e-05, |
|
"loss": 0.2532, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 9.969325153374233e-05, |
|
"loss": 0.1908, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 0.00010736196319018406, |
|
"loss": 0.1911, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.00011503067484662577, |
|
"loss": 0.1464, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 0.0001226993865030675, |
|
"loss": 0.1723, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 0.0001303680981595092, |
|
"loss": 0.3376, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.00013803680981595094, |
|
"loss": 0.1749, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"eval_accuracy": 0.9681063122923588, |
|
"eval_loss": 0.1173594519495964, |
|
"eval_runtime": 2947.7804, |
|
"eval_samples_per_second": 1.532, |
|
"eval_steps_per_second": 0.096, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.00014570552147239263, |
|
"loss": 0.2813, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.00015337423312883436, |
|
"loss": 0.2519, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 0.00016104294478527608, |
|
"loss": 0.1291, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 0.0001687116564417178, |
|
"loss": 0.1866, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 0.00017638036809815953, |
|
"loss": 0.1476, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 0.0001840490797546012, |
|
"loss": 0.2151, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 0.00019171779141104295, |
|
"loss": 0.166, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 0.00019938650306748466, |
|
"loss": 0.2285, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 0.00020705521472392637, |
|
"loss": 0.26, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 0.0002147239263803681, |
|
"loss": 0.2665, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 0.00022239263803680982, |
|
"loss": 0.3498, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 0.00023006134969325153, |
|
"loss": 0.2542, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 0.00023773006134969325, |
|
"loss": 0.2703, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 0.000245398773006135, |
|
"loss": 0.3452, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 0.00025306748466257667, |
|
"loss": 0.2412, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 0.0002607361963190184, |
|
"loss": 0.2198, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 0.00026840490797546015, |
|
"loss": 0.2265, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 0.0002760736196319019, |
|
"loss": 0.35, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"learning_rate": 0.00028374233128834357, |
|
"loss": 0.3183, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"eval_accuracy": 0.9246954595791805, |
|
"eval_loss": 0.17996589839458466, |
|
"eval_runtime": 43.3309, |
|
"eval_samples_per_second": 104.198, |
|
"eval_steps_per_second": 6.531, |
|
"step": 187 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 0.00029141104294478525, |
|
"loss": 0.2368, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 0.000299079754601227, |
|
"loss": 0.2482, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 0.00030674846625766873, |
|
"loss": 0.1572, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 0.00031441717791411047, |
|
"loss": 0.1358, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 0.00032208588957055215, |
|
"loss": 0.1966, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 2.29, |
|
"learning_rate": 0.00032975460122699384, |
|
"loss": 0.1984, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 2.35, |
|
"learning_rate": 0.0003374233128834356, |
|
"loss": 0.2055, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 0.0003450920245398773, |
|
"loss": 0.2273, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 0.00035276073619631905, |
|
"loss": 0.1351, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"learning_rate": 0.00036042944785276074, |
|
"loss": 0.17, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 0.0003680981595092024, |
|
"loss": 0.2857, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 0.00037576687116564416, |
|
"loss": 0.1333, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"learning_rate": 0.0003834355828220859, |
|
"loss": 0.5189, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 0.00039110429447852764, |
|
"loss": 0.1638, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"learning_rate": 0.0003987730061349693, |
|
"loss": 0.1754, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 2.83, |
|
"learning_rate": 0.00040644171779141106, |
|
"loss": 0.197, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 0.00041411042944785274, |
|
"loss": 0.1543, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 2.93, |
|
"learning_rate": 0.0004217791411042945, |
|
"loss": 0.2147, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 2.99, |
|
"learning_rate": 0.0004294478527607362, |
|
"loss": 0.3048, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9233665559246954, |
|
"eval_loss": 0.18979668617248535, |
|
"eval_runtime": 43.4199, |
|
"eval_samples_per_second": 103.985, |
|
"eval_steps_per_second": 6.518, |
|
"step": 281 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 0.0004371165644171779, |
|
"loss": 0.16, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 3.09, |
|
"learning_rate": 0.00044478527607361964, |
|
"loss": 0.132, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 3.15, |
|
"learning_rate": 0.0004524539877300614, |
|
"loss": 0.5492, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 0.00046012269938650307, |
|
"loss": 1.1128, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 3.25, |
|
"learning_rate": 0.0004677914110429448, |
|
"loss": 1.2612, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 3.31, |
|
"learning_rate": 0.0004754601226993865, |
|
"loss": 1.154, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 0.00048312883435582823, |
|
"loss": 1.1277, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 3.41, |
|
"learning_rate": 0.00049079754601227, |
|
"loss": 1.1094, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 3.47, |
|
"learning_rate": 0.0004984662576687117, |
|
"loss": 1.0978, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 0.0004938461538461538, |
|
"loss": 1.1128, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 3.57, |
|
"learning_rate": 0.0004861538461538462, |
|
"loss": 1.0989, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 3.63, |
|
"learning_rate": 0.00047846153846153844, |
|
"loss": 1.1081, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 3.68, |
|
"learning_rate": 0.00047076923076923077, |
|
"loss": 1.0983, |
|
"step": 345 |
|
}, |
|
{ |
|
"epoch": 3.73, |
|
"learning_rate": 0.00046307692307692304, |
|
"loss": 1.1016, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 3.79, |
|
"learning_rate": 0.0004553846153846154, |
|
"loss": 1.099, |
|
"step": 355 |
|
}, |
|
{ |
|
"epoch": 3.84, |
|
"learning_rate": 0.0004476923076923077, |
|
"loss": 1.0987, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 3.89, |
|
"learning_rate": 0.00044, |
|
"loss": 1.1142, |
|
"step": 365 |
|
}, |
|
{ |
|
"epoch": 3.95, |
|
"learning_rate": 0.0004323076923076923, |
|
"loss": 1.0999, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 0.0004246153846153846, |
|
"loss": 1.1006, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.3337763012181617, |
|
"eval_loss": 1.1143020391464233, |
|
"eval_runtime": 43.0798, |
|
"eval_samples_per_second": 104.806, |
|
"eval_steps_per_second": 6.569, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 4.05, |
|
"learning_rate": 0.0004169230769230769, |
|
"loss": 1.1025, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 4.11, |
|
"learning_rate": 0.00040923076923076926, |
|
"loss": 1.112, |
|
"step": 385 |
|
}, |
|
{ |
|
"epoch": 4.16, |
|
"learning_rate": 0.00040153846153846153, |
|
"loss": 1.1014, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 4.21, |
|
"learning_rate": 0.00039384615384615386, |
|
"loss": 1.1004, |
|
"step": 395 |
|
}, |
|
{ |
|
"epoch": 4.27, |
|
"learning_rate": 0.0003861538461538462, |
|
"loss": 1.1119, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 4.32, |
|
"learning_rate": 0.00037846153846153845, |
|
"loss": 1.1033, |
|
"step": 405 |
|
}, |
|
{ |
|
"epoch": 4.37, |
|
"learning_rate": 0.0003707692307692308, |
|
"loss": 1.1073, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 4.43, |
|
"learning_rate": 0.0003630769230769231, |
|
"loss": 1.0973, |
|
"step": 415 |
|
}, |
|
{ |
|
"epoch": 4.48, |
|
"learning_rate": 0.00035538461538461543, |
|
"loss": 1.1094, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 4.53, |
|
"learning_rate": 0.0003476923076923077, |
|
"loss": 1.0951, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 4.59, |
|
"learning_rate": 0.00034, |
|
"loss": 1.1049, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 4.64, |
|
"learning_rate": 0.0003323076923076923, |
|
"loss": 1.1005, |
|
"step": 435 |
|
}, |
|
{ |
|
"epoch": 4.69, |
|
"learning_rate": 0.0003246153846153846, |
|
"loss": 1.1, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 4.75, |
|
"learning_rate": 0.00031692307692307695, |
|
"loss": 1.0979, |
|
"step": 445 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 0.00030923076923076927, |
|
"loss": 1.1013, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 4.85, |
|
"learning_rate": 0.00030153846153846154, |
|
"loss": 1.1027, |
|
"step": 455 |
|
}, |
|
{ |
|
"epoch": 4.91, |
|
"learning_rate": 0.00029384615384615387, |
|
"loss": 1.0969, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 4.96, |
|
"learning_rate": 0.00028615384615384614, |
|
"loss": 1.0988, |
|
"step": 465 |
|
}, |
|
{ |
|
"epoch": 4.99, |
|
"eval_accuracy": 0.3238095238095238, |
|
"eval_loss": 1.0992164611816406, |
|
"eval_runtime": 42.9354, |
|
"eval_samples_per_second": 105.158, |
|
"eval_steps_per_second": 6.591, |
|
"step": 468 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"learning_rate": 0.00027846153846153846, |
|
"loss": 1.1023, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 5.07, |
|
"learning_rate": 0.0002707692307692308, |
|
"loss": 1.1027, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 5.12, |
|
"learning_rate": 0.0002630769230769231, |
|
"loss": 1.1045, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 5.17, |
|
"learning_rate": 0.0002553846153846154, |
|
"loss": 1.0956, |
|
"step": 485 |
|
}, |
|
{ |
|
"epoch": 5.23, |
|
"learning_rate": 0.0002476923076923077, |
|
"loss": 1.1015, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 5.28, |
|
"learning_rate": 0.00024, |
|
"loss": 1.101, |
|
"step": 495 |
|
}, |
|
{ |
|
"epoch": 5.33, |
|
"learning_rate": 0.0002323076923076923, |
|
"loss": 1.0938, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 5.39, |
|
"learning_rate": 0.0002246153846153846, |
|
"loss": 1.0983, |
|
"step": 505 |
|
}, |
|
{ |
|
"epoch": 5.44, |
|
"learning_rate": 0.00021692307692307693, |
|
"loss": 1.0988, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 5.49, |
|
"learning_rate": 0.00020923076923076922, |
|
"loss": 1.1023, |
|
"step": 515 |
|
}, |
|
{ |
|
"epoch": 5.55, |
|
"learning_rate": 0.00020153846153846152, |
|
"loss": 1.1016, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 5.6, |
|
"learning_rate": 0.00019384615384615385, |
|
"loss": 1.0993, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 5.65, |
|
"learning_rate": 0.00018615384615384615, |
|
"loss": 1.0945, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 5.71, |
|
"learning_rate": 0.00017846153846153844, |
|
"loss": 1.1035, |
|
"step": 535 |
|
}, |
|
{ |
|
"epoch": 5.76, |
|
"learning_rate": 0.00017076923076923077, |
|
"loss": 1.1048, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 5.81, |
|
"learning_rate": 0.00016307692307692307, |
|
"loss": 1.1051, |
|
"step": 545 |
|
}, |
|
{ |
|
"epoch": 5.87, |
|
"learning_rate": 0.00015538461538461536, |
|
"loss": 1.0989, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 5.92, |
|
"learning_rate": 0.00014769230769230772, |
|
"loss": 1.0994, |
|
"step": 555 |
|
}, |
|
{ |
|
"epoch": 5.97, |
|
"learning_rate": 0.00014000000000000001, |
|
"loss": 1.0961, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 5.99, |
|
"eval_accuracy": 0.3238095238095238, |
|
"eval_loss": 1.1005984544754028, |
|
"eval_runtime": 43.2538, |
|
"eval_samples_per_second": 104.384, |
|
"eval_steps_per_second": 6.543, |
|
"step": 562 |
|
}, |
|
{ |
|
"epoch": 6.03, |
|
"learning_rate": 0.0001323076923076923, |
|
"loss": 1.0989, |
|
"step": 565 |
|
}, |
|
{ |
|
"epoch": 6.08, |
|
"learning_rate": 0.0001246153846153846, |
|
"loss": 1.0992, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 6.13, |
|
"learning_rate": 0.00011692307692307692, |
|
"loss": 1.096, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 6.19, |
|
"learning_rate": 0.00010923076923076923, |
|
"loss": 1.1023, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 6.24, |
|
"learning_rate": 0.00010153846153846153, |
|
"loss": 1.0979, |
|
"step": 585 |
|
}, |
|
{ |
|
"epoch": 6.29, |
|
"learning_rate": 9.384615384615384e-05, |
|
"loss": 1.1023, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 6.35, |
|
"learning_rate": 8.615384615384615e-05, |
|
"loss": 1.0991, |
|
"step": 595 |
|
}, |
|
{ |
|
"epoch": 6.4, |
|
"learning_rate": 7.846153846153845e-05, |
|
"loss": 1.0971, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 6.45, |
|
"learning_rate": 7.076923076923076e-05, |
|
"loss": 1.0987, |
|
"step": 605 |
|
}, |
|
{ |
|
"epoch": 6.51, |
|
"learning_rate": 6.307692307692308e-05, |
|
"loss": 1.095, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 6.56, |
|
"learning_rate": 5.538461538461539e-05, |
|
"loss": 1.1003, |
|
"step": 615 |
|
}, |
|
{ |
|
"epoch": 6.61, |
|
"learning_rate": 4.769230769230769e-05, |
|
"loss": 1.0994, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 6.67, |
|
"learning_rate": 4e-05, |
|
"loss": 1.1029, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 6.72, |
|
"learning_rate": 3.230769230769231e-05, |
|
"loss": 1.1004, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 6.77, |
|
"learning_rate": 2.4615384615384616e-05, |
|
"loss": 1.098, |
|
"step": 635 |
|
}, |
|
{ |
|
"epoch": 6.83, |
|
"learning_rate": 1.6923076923076924e-05, |
|
"loss": 1.0991, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 6.88, |
|
"learning_rate": 9.230769230769232e-06, |
|
"loss": 1.0984, |
|
"step": 645 |
|
}, |
|
{ |
|
"epoch": 6.93, |
|
"learning_rate": 1.5384615384615385e-06, |
|
"loss": 1.0987, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 6.94, |
|
"eval_accuracy": 0.3238095238095238, |
|
"eval_loss": 1.0993690490722656, |
|
"eval_runtime": 43.0492, |
|
"eval_samples_per_second": 104.88, |
|
"eval_steps_per_second": 6.574, |
|
"step": 651 |
|
}, |
|
{ |
|
"epoch": 6.94, |
|
"step": 651, |
|
"total_flos": 7.375405476885369e+18, |
|
"train_loss": 0.7435173462795955, |
|
"train_runtime": 8012.7314, |
|
"train_samples_per_second": 5.229, |
|
"train_steps_per_second": 0.081 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 651, |
|
"num_train_epochs": 7, |
|
"save_steps": 500, |
|
"total_flos": 7.375405476885369e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|