| { | |
| "best_metric": 1.1806877851486206, | |
| "best_model_checkpoint": "model_training/reprover/checkpoints-by_file-09-07-16-31/checkpoint-450", | |
| "epoch": 7.309644670050761, | |
| "eval_steps": 25, | |
| "global_step": 450, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08121827411167512, | |
| "grad_norm": 24.31340217590332, | |
| "learning_rate": 5.102040816326531e-05, | |
| "loss": 12.4632, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.16243654822335024, | |
| "grad_norm": 7.6981658935546875, | |
| "learning_rate": 0.00010204081632653062, | |
| "loss": 7.3045, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2436548223350254, | |
| "grad_norm": 0.584043562412262, | |
| "learning_rate": 0.00015306122448979594, | |
| "loss": 3.8878, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3248730964467005, | |
| "grad_norm": 0.229707270860672, | |
| "learning_rate": 0.00020408163265306123, | |
| "loss": 3.6345, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.40609137055837563, | |
| "grad_norm": 0.2534404695034027, | |
| "learning_rate": 0.00025510204081632655, | |
| "loss": 3.508, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.40609137055837563, | |
| "eval_loss": 3.2811102867126465, | |
| "eval_runtime": 86.0155, | |
| "eval_samples_per_second": 11.626, | |
| "eval_steps_per_second": 1.453, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4873096446700508, | |
| "grad_norm": 2.226205587387085, | |
| "learning_rate": 0.0003061224489795919, | |
| "loss": 3.4572, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5685279187817259, | |
| "grad_norm": 2.194638729095459, | |
| "learning_rate": 0.00035714285714285714, | |
| "loss": 2.504, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.649746192893401, | |
| "grad_norm": 0.7849161624908447, | |
| "learning_rate": 0.00040816326530612246, | |
| "loss": 1.9298, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7309644670050761, | |
| "grad_norm": 0.5836678147315979, | |
| "learning_rate": 0.0004591836734693878, | |
| "loss": 1.7631, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8121827411167513, | |
| "grad_norm": 0.4033905565738678, | |
| "learning_rate": 0.0004999935985425297, | |
| "loss": 1.6774, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8121827411167513, | |
| "eval_loss": 1.367048740386963, | |
| "eval_runtime": 85.8218, | |
| "eval_samples_per_second": 11.652, | |
| "eval_steps_per_second": 1.457, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8934010152284264, | |
| "grad_norm": 0.3479253947734833, | |
| "learning_rate": 0.0004997695819512612, | |
| "loss": 1.6005, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.9746192893401016, | |
| "grad_norm": 0.4574773907661438, | |
| "learning_rate": 0.0004992258202402822, | |
| "loss": 1.5389, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0558375634517767, | |
| "grad_norm": 0.2955416738986969, | |
| "learning_rate": 0.0004983630095117843, | |
| "loss": 1.4855, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.1370558375634519, | |
| "grad_norm": 0.235136017203331, | |
| "learning_rate": 0.0004971822543018662, | |
| "loss": 1.4427, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.218274111675127, | |
| "grad_norm": 0.2502729594707489, | |
| "learning_rate": 0.0004956850661665511, | |
| "loss": 1.462, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.218274111675127, | |
| "eval_loss": 1.2605030536651611, | |
| "eval_runtime": 85.8507, | |
| "eval_samples_per_second": 11.648, | |
| "eval_steps_per_second": 1.456, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.299492385786802, | |
| "grad_norm": 0.46766167879104614, | |
| "learning_rate": 0.0004938733617467517, | |
| "loss": 1.4421, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.380710659898477, | |
| "grad_norm": 0.2875135540962219, | |
| "learning_rate": 0.0004917494603146632, | |
| "loss": 1.4042, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.4619289340101522, | |
| "grad_norm": 0.5056741833686829, | |
| "learning_rate": 0.0004893160808047222, | |
| "loss": 1.3901, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.5431472081218274, | |
| "grad_norm": 0.17907263338565826, | |
| "learning_rate": 0.00048657633833293557, | |
| "loss": 1.3829, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.6243654822335025, | |
| "grad_norm": 0.25355765223503113, | |
| "learning_rate": 0.0004835337402090316, | |
| "loss": 1.3592, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6243654822335025, | |
| "eval_loss": 1.2396838665008545, | |
| "eval_runtime": 85.75, | |
| "eval_samples_per_second": 11.662, | |
| "eval_steps_per_second": 1.458, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.7055837563451777, | |
| "grad_norm": 0.1514243483543396, | |
| "learning_rate": 0.0004801921814465414, | |
| "loss": 1.379, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.7868020304568528, | |
| "grad_norm": 0.14222057163715363, | |
| "learning_rate": 0.00047655593977655674, | |
| "loss": 1.3385, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.868020304568528, | |
| "grad_norm": 0.38187268376350403, | |
| "learning_rate": 0.0004726296701715489, | |
| "loss": 1.339, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.9492385786802031, | |
| "grad_norm": 0.42166340351104736, | |
| "learning_rate": 0.00046841839888625623, | |
| "loss": 1.4193, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.030456852791878, | |
| "grad_norm": 0.3789190948009491, | |
| "learning_rate": 0.0004639275170232734, | |
| "loss": 1.3529, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.030456852791878, | |
| "eval_loss": 1.2485618591308594, | |
| "eval_runtime": 85.8636, | |
| "eval_samples_per_second": 11.646, | |
| "eval_steps_per_second": 1.456, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.1116751269035534, | |
| "grad_norm": 0.3297707736492157, | |
| "learning_rate": 0.0004591627736315743, | |
| "loss": 1.3754, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.1928934010152283, | |
| "grad_norm": 0.6720882058143616, | |
| "learning_rate": 0.0004541302683468084, | |
| "loss": 1.3633, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.2741116751269037, | |
| "grad_norm": 0.423013299703598, | |
| "learning_rate": 0.0004488364435827881, | |
| "loss": 1.3739, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.3553299492385786, | |
| "grad_norm": 0.3096015751361847, | |
| "learning_rate": 0.00044328807628416644, | |
| "loss": 1.3734, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.436548223350254, | |
| "grad_norm": 0.25548315048217773, | |
| "learning_rate": 0.0004374922692508611, | |
| "loss": 1.354, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.436548223350254, | |
| "eval_loss": 1.2303425073623657, | |
| "eval_runtime": 85.8621, | |
| "eval_samples_per_second": 11.647, | |
| "eval_steps_per_second": 1.456, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.517766497461929, | |
| "grad_norm": 0.2693212330341339, | |
| "learning_rate": 0.0004314564420453311, | |
| "loss": 1.3311, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.598984771573604, | |
| "grad_norm": 0.2327384501695633, | |
| "learning_rate": 0.0004251883214943475, | |
| "loss": 1.3367, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.6802030456852792, | |
| "grad_norm": 0.20477798581123352, | |
| "learning_rate": 0.0004186959317974155, | |
| "loss": 1.3718, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.761421319796954, | |
| "grad_norm": 0.6859282851219177, | |
| "learning_rate": 0.00041198758425451266, | |
| "loss": 1.3351, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.8426395939086295, | |
| "grad_norm": 0.4204564392566681, | |
| "learning_rate": 0.00040507186662629185, | |
| "loss": 1.3633, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.8426395939086295, | |
| "eval_loss": 1.2046416997909546, | |
| "eval_runtime": 85.7507, | |
| "eval_samples_per_second": 11.662, | |
| "eval_steps_per_second": 1.458, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.9238578680203045, | |
| "grad_norm": 0.4428386390209198, | |
| "learning_rate": 0.0003979576321403705, | |
| "loss": 1.2933, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.00507614213198, | |
| "grad_norm": 0.5064650774002075, | |
| "learning_rate": 0.0003906539881577793, | |
| "loss": 1.3117, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 3.0862944162436547, | |
| "grad_norm": 0.19443967938423157, | |
| "learning_rate": 0.0003831702845140801, | |
| "loss": 1.3285, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.16751269035533, | |
| "grad_norm": 0.17194636166095734, | |
| "learning_rate": 0.00037551610155007613, | |
| "loss": 1.2587, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 3.248730964467005, | |
| "grad_norm": 0.4715280830860138, | |
| "learning_rate": 0.00036770123784744027, | |
| "loss": 1.3266, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.248730964467005, | |
| "eval_loss": 1.209210991859436, | |
| "eval_runtime": 85.8547, | |
| "eval_samples_per_second": 11.648, | |
| "eval_steps_per_second": 1.456, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.3299492385786804, | |
| "grad_norm": 0.5037745237350464, | |
| "learning_rate": 0.00035973569768495855, | |
| "loss": 1.3085, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 3.4111675126903553, | |
| "grad_norm": 0.4525098204612732, | |
| "learning_rate": 0.0003516296782314491, | |
| "loss": 1.2944, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.4923857868020303, | |
| "grad_norm": 0.30172044038772583, | |
| "learning_rate": 0.00034339355649175095, | |
| "loss": 1.3206, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 3.5736040609137056, | |
| "grad_norm": 0.8903113603591919, | |
| "learning_rate": 0.00033503787602249364, | |
| "loss": 1.3404, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.6548223350253806, | |
| "grad_norm": 0.5123381614685059, | |
| "learning_rate": 0.00032657333343465356, | |
| "loss": 1.321, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.6548223350253806, | |
| "eval_loss": 1.200507640838623, | |
| "eval_runtime": 85.8377, | |
| "eval_samples_per_second": 11.65, | |
| "eval_steps_per_second": 1.456, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.736040609137056, | |
| "grad_norm": 0.19661971926689148, | |
| "learning_rate": 0.0003180107647001769, | |
| "loss": 1.3276, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.817258883248731, | |
| "grad_norm": 0.34714922308921814, | |
| "learning_rate": 0.0003093611312801979, | |
| "loss": 1.2869, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 3.8984771573604062, | |
| "grad_norm": 0.3150271773338318, | |
| "learning_rate": 0.00030063550609261025, | |
| "loss": 1.2738, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.979695431472081, | |
| "grad_norm": 0.24157479405403137, | |
| "learning_rate": 0.000291845059336957, | |
| "loss": 1.3107, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 4.060913705583756, | |
| "grad_norm": 0.2525878846645355, | |
| "learning_rate": 0.0002830010441947834, | |
| "loss": 1.2679, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.060913705583756, | |
| "eval_loss": 1.196422815322876, | |
| "eval_runtime": 85.8149, | |
| "eval_samples_per_second": 11.653, | |
| "eval_steps_per_second": 1.457, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.1421319796954315, | |
| "grad_norm": 0.49697160720825195, | |
| "learning_rate": 0.00027411478242376017, | |
| "loss": 1.3141, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 4.223350253807107, | |
| "grad_norm": 0.3860456943511963, | |
| "learning_rate": 0.00026519764986401774, | |
| "loss": 1.3039, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.304568527918782, | |
| "grad_norm": 0.2929648160934448, | |
| "learning_rate": 0.000256261061875247, | |
| "loss": 1.2864, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 4.385786802030457, | |
| "grad_norm": 0.49687063694000244, | |
| "learning_rate": 0.0002473164587232079, | |
| "loss": 1.3065, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.467005076142132, | |
| "grad_norm": 0.26030004024505615, | |
| "learning_rate": 0.0002383752909343547, | |
| "loss": 1.299, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.467005076142132, | |
| "eval_loss": 1.1841660737991333, | |
| "eval_runtime": 85.8048, | |
| "eval_samples_per_second": 11.654, | |
| "eval_steps_per_second": 1.457, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.548223350253807, | |
| "grad_norm": 0.1852976679801941, | |
| "learning_rate": 0.0002294490046373259, | |
| "loss": 1.2506, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.629441624365482, | |
| "grad_norm": 0.41372132301330566, | |
| "learning_rate": 0.00022054902691006405, | |
| "loss": 1.3174, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 4.710659898477157, | |
| "grad_norm": 0.18286170065402985, | |
| "learning_rate": 0.00021168675115132315, | |
| "loss": 1.3335, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.791878172588833, | |
| "grad_norm": 0.1263434737920761, | |
| "learning_rate": 0.00020287352249529153, | |
| "loss": 1.3019, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 4.873096446700508, | |
| "grad_norm": 0.13266858458518982, | |
| "learning_rate": 0.00019412062328800044, | |
| "loss": 1.2709, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.873096446700508, | |
| "eval_loss": 1.1873031854629517, | |
| "eval_runtime": 85.8269, | |
| "eval_samples_per_second": 11.651, | |
| "eval_steps_per_second": 1.456, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.9543147208121825, | |
| "grad_norm": 0.1231088787317276, | |
| "learning_rate": 0.000185439258644112, | |
| "loss": 1.3102, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 5.035532994923858, | |
| "grad_norm": 0.16395896673202515, | |
| "learning_rate": 0.00017684054210257517, | |
| "loss": 1.3088, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.116751269035533, | |
| "grad_norm": 0.14288240671157837, | |
| "learning_rate": 0.00016833548139951395, | |
| "loss": 1.3205, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 5.197969543147208, | |
| "grad_norm": 0.16564807295799255, | |
| "learning_rate": 0.0001599349643765599, | |
| "loss": 1.2845, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.279187817258883, | |
| "grad_norm": 0.133669912815094, | |
| "learning_rate": 0.0001516497450426686, | |
| "loss": 1.3105, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 5.279187817258883, | |
| "eval_loss": 1.183776617050171, | |
| "eval_runtime": 85.7228, | |
| "eval_samples_per_second": 11.666, | |
| "eval_steps_per_second": 1.458, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 5.3604060913705585, | |
| "grad_norm": 0.050202421844005585, | |
| "learning_rate": 0.00014349042980726362, | |
| "loss": 1.2825, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.441624365482234, | |
| "grad_norm": 0.08104140311479568, | |
| "learning_rate": 0.0001354674639023318, | |
| "loss": 1.2975, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 5.522842639593908, | |
| "grad_norm": 0.045941274613142014, | |
| "learning_rate": 0.00012759111801085066, | |
| "loss": 1.2848, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.604060913705584, | |
| "grad_norm": 0.10393151640892029, | |
| "learning_rate": 0.00011987147511866788, | |
| "loss": 1.3075, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 5.685279187817259, | |
| "grad_norm": 0.05486277490854263, | |
| "learning_rate": 0.00011231841760666186, | |
| "loss": 1.2337, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.685279187817259, | |
| "eval_loss": 1.1837860345840454, | |
| "eval_runtime": 85.8492, | |
| "eval_samples_per_second": 11.648, | |
| "eval_steps_per_second": 1.456, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.7664974619289335, | |
| "grad_norm": 0.06317424029111862, | |
| "learning_rate": 0.0001049416145997094, | |
| "loss": 1.2696, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 5.847715736040609, | |
| "grad_norm": 0.06952204555273056, | |
| "learning_rate": 9.775050958865584e-05, | |
| "loss": 1.2792, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.928934010152284, | |
| "grad_norm": 0.05977623909711838, | |
| "learning_rate": 9.075430834113152e-05, | |
| "loss": 1.2672, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 6.01015228426396, | |
| "grad_norm": 0.1008043885231018, | |
| "learning_rate": 8.396196711669335e-05, | |
| "loss": 1.3045, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.091370558375634, | |
| "grad_norm": 0.06693598628044128, | |
| "learning_rate": 7.738218120137671e-05, | |
| "loss": 1.2753, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.091370558375634, | |
| "eval_loss": 1.1829280853271484, | |
| "eval_runtime": 85.8364, | |
| "eval_samples_per_second": 11.65, | |
| "eval_steps_per_second": 1.456, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.1725888324873095, | |
| "grad_norm": 0.10474739223718643, | |
| "learning_rate": 7.102337377633394e-05, | |
| "loss": 1.2936, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.253807106598985, | |
| "grad_norm": 0.05388178676366806, | |
| "learning_rate": 6.489368513481228e-05, | |
| "loss": 1.2439, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 6.33502538071066, | |
| "grad_norm": 0.09186024218797684, | |
| "learning_rate": 5.9000962261273136e-05, | |
| "loss": 1.3222, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.416243654822335, | |
| "grad_norm": 0.07748736441135406, | |
| "learning_rate": 5.3352748785993164e-05, | |
| "loss": 1.2731, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 6.49746192893401, | |
| "grad_norm": 0.07806465774774551, | |
| "learning_rate": 4.795627532800806e-05, | |
| "loss": 1.2849, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.49746192893401, | |
| "eval_loss": 1.1841729879379272, | |
| "eval_runtime": 85.8225, | |
| "eval_samples_per_second": 11.652, | |
| "eval_steps_per_second": 1.456, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.5786802030456855, | |
| "grad_norm": 0.05898735672235489, | |
| "learning_rate": 4.281845023876074e-05, | |
| "loss": 1.2866, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 6.659898477157361, | |
| "grad_norm": 0.052701685577631, | |
| "learning_rate": 3.794585075830329e-05, | |
| "loss": 1.2848, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.741116751269035, | |
| "grad_norm": 0.04117720574140549, | |
| "learning_rate": 3.334471459537497e-05, | |
| "loss": 1.2859, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 6.822335025380711, | |
| "grad_norm": 0.04338378086686134, | |
| "learning_rate": 2.902093194213526e-05, | |
| "loss": 1.2934, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.903553299492386, | |
| "grad_norm": 0.05017438903450966, | |
| "learning_rate": 2.4980037933772488e-05, | |
| "loss": 1.2508, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 6.903553299492386, | |
| "eval_loss": 1.1836540699005127, | |
| "eval_runtime": 85.78, | |
| "eval_samples_per_second": 11.658, | |
| "eval_steps_per_second": 1.457, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 6.9847715736040605, | |
| "grad_norm": 0.04826565086841583, | |
| "learning_rate": 2.122720556264357e-05, | |
| "loss": 1.2958, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 7.065989847715736, | |
| "grad_norm": 0.05151581019163132, | |
| "learning_rate": 1.776723905601438e-05, | |
| "loss": 1.279, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 7.147208121827411, | |
| "grad_norm": 0.06657218188047409, | |
| "learning_rate": 1.4604567725877926e-05, | |
| "loss": 1.2756, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.228426395939087, | |
| "grad_norm": 0.05859878286719322, | |
| "learning_rate": 1.1743240298725116e-05, | |
| "loss": 1.3084, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 7.309644670050761, | |
| "grad_norm": 0.051177285611629486, | |
| "learning_rate": 9.18691973252539e-06, | |
| "loss": 1.296, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.309644670050761, | |
| "eval_loss": 1.1806877851486206, | |
| "eval_runtime": 85.7014, | |
| "eval_samples_per_second": 11.668, | |
| "eval_steps_per_second": 1.459, | |
| "step": 450 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 488, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.089179686194381e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |