| { | |
| "best_metric": 0.23812708258628845, | |
| "best_model_checkpoint": "./model_outputs/checkpoint-9800", | |
| "epoch": 1.9338753280580934, | |
| "eval_steps": 100, | |
| "global_step": 9800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.019732817649032106, | |
| "grad_norm": 0.579439103603363, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.8467, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.019732817649032106, | |
| "eval_loss": 1.6029163599014282, | |
| "eval_runtime": 0.1393, | |
| "eval_samples_per_second": 35.888, | |
| "eval_steps_per_second": 7.178, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03946563529806421, | |
| "grad_norm": 1.7087633609771729, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.4062, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03946563529806421, | |
| "eval_loss": 1.2955422401428223, | |
| "eval_runtime": 0.0895, | |
| "eval_samples_per_second": 55.895, | |
| "eval_steps_per_second": 11.179, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05919845294709632, | |
| "grad_norm": 2.1446690559387207, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2561, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05919845294709632, | |
| "eval_loss": 1.14933443069458, | |
| "eval_runtime": 0.0896, | |
| "eval_samples_per_second": 55.787, | |
| "eval_steps_per_second": 11.157, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07893127059612842, | |
| "grad_norm": 1.9442692995071411, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.1758, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07893127059612842, | |
| "eval_loss": 1.070350170135498, | |
| "eval_runtime": 0.0899, | |
| "eval_samples_per_second": 55.607, | |
| "eval_steps_per_second": 11.121, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09866408824516053, | |
| "grad_norm": 1.6005765199661255, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 1.1199, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09866408824516053, | |
| "eval_loss": 1.0037094354629517, | |
| "eval_runtime": 0.0918, | |
| "eval_samples_per_second": 54.446, | |
| "eval_steps_per_second": 10.889, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11839690589419263, | |
| "grad_norm": 1.4335505962371826, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0773, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.11839690589419263, | |
| "eval_loss": 0.9590722918510437, | |
| "eval_runtime": 0.0897, | |
| "eval_samples_per_second": 55.743, | |
| "eval_steps_per_second": 11.149, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.13812972354322473, | |
| "grad_norm": 1.535965085029602, | |
| "learning_rate": 0.00011666666666666668, | |
| "loss": 1.0446, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.13812972354322473, | |
| "eval_loss": 0.9230692982673645, | |
| "eval_runtime": 0.0893, | |
| "eval_samples_per_second": 55.988, | |
| "eval_steps_per_second": 11.198, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.15786254119225684, | |
| "grad_norm": 1.1867926120758057, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 1.0234, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.15786254119225684, | |
| "eval_loss": 0.8973449468612671, | |
| "eval_runtime": 0.0898, | |
| "eval_samples_per_second": 55.673, | |
| "eval_steps_per_second": 11.135, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.17759535884128894, | |
| "grad_norm": 0.9903791546821594, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.0057, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.17759535884128894, | |
| "eval_loss": 0.8900602459907532, | |
| "eval_runtime": 0.0911, | |
| "eval_samples_per_second": 54.888, | |
| "eval_steps_per_second": 10.978, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.19732817649032106, | |
| "grad_norm": 1.0672552585601807, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 0.9416, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.19732817649032106, | |
| "eval_loss": 0.7900083065032959, | |
| "eval_runtime": 0.0909, | |
| "eval_samples_per_second": 54.981, | |
| "eval_steps_per_second": 10.996, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.21706099413935315, | |
| "grad_norm": 1.1501110792160034, | |
| "learning_rate": 0.00018333333333333334, | |
| "loss": 0.7217, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.21706099413935315, | |
| "eval_loss": 0.5064653754234314, | |
| "eval_runtime": 0.089, | |
| "eval_samples_per_second": 56.189, | |
| "eval_steps_per_second": 11.238, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.23679381178838527, | |
| "grad_norm": 0.7229278683662415, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5166, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.23679381178838527, | |
| "eval_loss": 0.42082151770591736, | |
| "eval_runtime": 0.0889, | |
| "eval_samples_per_second": 56.242, | |
| "eval_steps_per_second": 11.248, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.2565266294374174, | |
| "grad_norm": 0.753103494644165, | |
| "learning_rate": 0.00019993817941631932, | |
| "loss": 0.4558, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.2565266294374174, | |
| "eval_loss": 0.39703065156936646, | |
| "eval_runtime": 0.09, | |
| "eval_samples_per_second": 55.574, | |
| "eval_steps_per_second": 11.115, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.27625944708644945, | |
| "grad_norm": 0.4141121506690979, | |
| "learning_rate": 0.00019975279410096856, | |
| "loss": 0.4347, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.27625944708644945, | |
| "eval_loss": 0.3718082904815674, | |
| "eval_runtime": 0.0891, | |
| "eval_samples_per_second": 56.096, | |
| "eval_steps_per_second": 11.219, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.29599226473548157, | |
| "grad_norm": 0.6031398773193359, | |
| "learning_rate": 0.00019944407326651575, | |
| "loss": 0.4217, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.29599226473548157, | |
| "eval_loss": 0.3526321351528168, | |
| "eval_runtime": 0.0904, | |
| "eval_samples_per_second": 55.331, | |
| "eval_steps_per_second": 11.066, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.3157250823845137, | |
| "grad_norm": 0.5605940222740173, | |
| "learning_rate": 0.0001990123986190045, | |
| "loss": 0.4128, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.3157250823845137, | |
| "eval_loss": 0.35304129123687744, | |
| "eval_runtime": 0.0901, | |
| "eval_samples_per_second": 55.473, | |
| "eval_steps_per_second": 11.095, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.3354579000335458, | |
| "grad_norm": 0.5206743478775024, | |
| "learning_rate": 0.00019845830388600822, | |
| "loss": 0.4054, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.3354579000335458, | |
| "eval_loss": 0.34606409072875977, | |
| "eval_runtime": 0.0913, | |
| "eval_samples_per_second": 54.794, | |
| "eval_steps_per_second": 10.959, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.3551907176825779, | |
| "grad_norm": 0.46870893239974976, | |
| "learning_rate": 0.000197782474156723, | |
| "loss": 0.4004, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.3551907176825779, | |
| "eval_loss": 0.33528828620910645, | |
| "eval_runtime": 0.0919, | |
| "eval_samples_per_second": 54.394, | |
| "eval_steps_per_second": 10.879, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.37492353533161, | |
| "grad_norm": 0.4280480444431305, | |
| "learning_rate": 0.0001969857450349156, | |
| "loss": 0.398, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.37492353533161, | |
| "eval_loss": 0.3284319043159485, | |
| "eval_runtime": 0.089, | |
| "eval_samples_per_second": 56.157, | |
| "eval_steps_per_second": 11.231, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.3946563529806421, | |
| "grad_norm": 0.37423691153526306, | |
| "learning_rate": 0.00019606910160577286, | |
| "loss": 0.3932, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.3946563529806421, | |
| "eval_loss": 0.32890015840530396, | |
| "eval_runtime": 0.0894, | |
| "eval_samples_per_second": 55.933, | |
| "eval_steps_per_second": 11.187, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.41438917062967423, | |
| "grad_norm": 0.5279616117477417, | |
| "learning_rate": 0.00019503367721793112, | |
| "loss": 0.3902, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.41438917062967423, | |
| "eval_loss": 0.3163706958293915, | |
| "eval_runtime": 0.0913, | |
| "eval_samples_per_second": 54.779, | |
| "eval_steps_per_second": 10.956, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.4341219882787063, | |
| "grad_norm": 0.5170876383781433, | |
| "learning_rate": 0.00019388075208219072, | |
| "loss": 0.3854, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.4341219882787063, | |
| "eval_loss": 0.3095114827156067, | |
| "eval_runtime": 0.0905, | |
| "eval_samples_per_second": 55.269, | |
| "eval_steps_per_second": 11.054, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.4538548059277384, | |
| "grad_norm": 0.5783583521842957, | |
| "learning_rate": 0.00019261175168864823, | |
| "loss": 0.3845, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.4538548059277384, | |
| "eval_loss": 0.31021368503570557, | |
| "eval_runtime": 0.0899, | |
| "eval_samples_per_second": 55.639, | |
| "eval_steps_per_second": 11.128, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.47358762357677053, | |
| "grad_norm": 0.3570936322212219, | |
| "learning_rate": 0.00019122824504420402, | |
| "loss": 0.3796, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.47358762357677053, | |
| "eval_loss": 0.30086052417755127, | |
| "eval_runtime": 0.0901, | |
| "eval_samples_per_second": 55.499, | |
| "eval_steps_per_second": 11.1, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.49332044122580265, | |
| "grad_norm": 0.3303937613964081, | |
| "learning_rate": 0.0001897319427326239, | |
| "loss": 0.381, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.49332044122580265, | |
| "eval_loss": 0.3088415861129761, | |
| "eval_runtime": 0.0896, | |
| "eval_samples_per_second": 55.778, | |
| "eval_steps_per_second": 11.156, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.5130532588748348, | |
| "grad_norm": 0.39968788623809814, | |
| "learning_rate": 0.00018812469479955306, | |
| "loss": 0.3758, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.5130532588748348, | |
| "eval_loss": 0.3069296181201935, | |
| "eval_runtime": 0.0906, | |
| "eval_samples_per_second": 55.215, | |
| "eval_steps_per_second": 11.043, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.5327860765238669, | |
| "grad_norm": 0.4014946520328522, | |
| "learning_rate": 0.00018640848846509836, | |
| "loss": 0.3728, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.5327860765238669, | |
| "eval_loss": 0.302837997674942, | |
| "eval_runtime": 0.0907, | |
| "eval_samples_per_second": 55.152, | |
| "eval_steps_per_second": 11.03, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.5525188941728989, | |
| "grad_norm": 0.3048448860645294, | |
| "learning_rate": 0.00018458544566680613, | |
| "loss": 0.374, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.5525188941728989, | |
| "eval_loss": 0.30044040083885193, | |
| "eval_runtime": 0.0918, | |
| "eval_samples_per_second": 54.44, | |
| "eval_steps_per_second": 10.888, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.572251711821931, | |
| "grad_norm": 0.36768218874931335, | |
| "learning_rate": 0.00018265782043607362, | |
| "loss": 0.3694, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.572251711821931, | |
| "eval_loss": 0.2935519516468048, | |
| "eval_runtime": 0.0918, | |
| "eval_samples_per_second": 54.473, | |
| "eval_steps_per_second": 10.895, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.5919845294709631, | |
| "grad_norm": 0.3077068030834198, | |
| "learning_rate": 0.00018062799611123843, | |
| "loss": 0.3649, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.5919845294709631, | |
| "eval_loss": 0.2956543564796448, | |
| "eval_runtime": 0.0897, | |
| "eval_samples_per_second": 55.755, | |
| "eval_steps_per_second": 11.151, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.6117173471199953, | |
| "grad_norm": 0.3608091175556183, | |
| "learning_rate": 0.00017849848239079126, | |
| "loss": 0.3613, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.6117173471199953, | |
| "eval_loss": 0.29713118076324463, | |
| "eval_runtime": 0.0892, | |
| "eval_samples_per_second": 56.045, | |
| "eval_steps_per_second": 11.209, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.6314501647690274, | |
| "grad_norm": 0.35845324397087097, | |
| "learning_rate": 0.00017627191223035512, | |
| "loss": 0.3646, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.6314501647690274, | |
| "eval_loss": 0.28599464893341064, | |
| "eval_runtime": 0.0897, | |
| "eval_samples_per_second": 55.735, | |
| "eval_steps_per_second": 11.147, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.6511829824180595, | |
| "grad_norm": 0.3350367546081543, | |
| "learning_rate": 0.00017395103858726846, | |
| "loss": 0.3619, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.6511829824180595, | |
| "eval_loss": 0.2815980315208435, | |
| "eval_runtime": 0.0892, | |
| "eval_samples_per_second": 56.042, | |
| "eval_steps_per_second": 11.208, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.6709158000670916, | |
| "grad_norm": 0.30465880036354065, | |
| "learning_rate": 0.00017153873101679668, | |
| "loss": 0.3625, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.6709158000670916, | |
| "eval_loss": 0.2854335308074951, | |
| "eval_runtime": 0.09, | |
| "eval_samples_per_second": 55.528, | |
| "eval_steps_per_second": 11.106, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.6906486177161237, | |
| "grad_norm": 0.31288811564445496, | |
| "learning_rate": 0.00016903797212418015, | |
| "loss": 0.3552, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.6906486177161237, | |
| "eval_loss": 0.28378957509994507, | |
| "eval_runtime": 0.0889, | |
| "eval_samples_per_second": 56.248, | |
| "eval_steps_per_second": 11.25, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.7103814353651557, | |
| "grad_norm": 0.49065399169921875, | |
| "learning_rate": 0.0001664518538769067, | |
| "loss": 0.3545, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.7103814353651557, | |
| "eval_loss": 0.28242945671081543, | |
| "eval_runtime": 0.0893, | |
| "eval_samples_per_second": 56.004, | |
| "eval_steps_per_second": 11.201, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.7301142530141879, | |
| "grad_norm": 0.34333252906799316, | |
| "learning_rate": 0.00016378357378176654, | |
| "loss": 0.3531, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.7301142530141879, | |
| "eval_loss": 0.28695201873779297, | |
| "eval_runtime": 0.0901, | |
| "eval_samples_per_second": 55.475, | |
| "eval_steps_per_second": 11.095, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.74984707066322, | |
| "grad_norm": 0.42468976974487305, | |
| "learning_rate": 0.0001610364309314178, | |
| "loss": 0.3528, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.74984707066322, | |
| "eval_loss": 0.282599538564682, | |
| "eval_runtime": 0.0888, | |
| "eval_samples_per_second": 56.288, | |
| "eval_steps_per_second": 11.258, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.7695798883122521, | |
| "grad_norm": 0.28823015093803406, | |
| "learning_rate": 0.00015821382192534968, | |
| "loss": 0.3515, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.7695798883122521, | |
| "eval_loss": 0.28318002820014954, | |
| "eval_runtime": 0.089, | |
| "eval_samples_per_second": 56.211, | |
| "eval_steps_per_second": 11.242, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.7893127059612842, | |
| "grad_norm": 0.3027402460575104, | |
| "learning_rate": 0.0001553192366702874, | |
| "loss": 0.3515, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.7893127059612842, | |
| "eval_loss": 0.2733287513256073, | |
| "eval_runtime": 0.0893, | |
| "eval_samples_per_second": 55.972, | |
| "eval_steps_per_second": 11.194, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.8090455236103163, | |
| "grad_norm": 0.29556697607040405, | |
| "learning_rate": 0.00015235625406523058, | |
| "loss": 0.3485, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.8090455236103163, | |
| "eval_loss": 0.2786538004875183, | |
| "eval_runtime": 0.0905, | |
| "eval_samples_per_second": 55.253, | |
| "eval_steps_per_second": 11.051, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.8287783412593485, | |
| "grad_norm": 0.36687153577804565, | |
| "learning_rate": 0.0001493285375764608, | |
| "loss": 0.3486, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.8287783412593485, | |
| "eval_loss": 0.281529039144516, | |
| "eval_runtime": 0.089, | |
| "eval_samples_per_second": 56.211, | |
| "eval_steps_per_second": 11.242, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.8485111589083806, | |
| "grad_norm": 0.3069268763065338, | |
| "learning_rate": 0.00014623983070798918, | |
| "loss": 0.3466, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.8485111589083806, | |
| "eval_loss": 0.2738308012485504, | |
| "eval_runtime": 0.0905, | |
| "eval_samples_per_second": 55.242, | |
| "eval_steps_per_second": 11.048, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.8682439765574126, | |
| "grad_norm": 0.362088680267334, | |
| "learning_rate": 0.00014309395237304426, | |
| "loss": 0.3441, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.8682439765574126, | |
| "eval_loss": 0.2713426649570465, | |
| "eval_runtime": 0.09, | |
| "eval_samples_per_second": 55.556, | |
| "eval_steps_per_second": 11.111, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.8879767942064447, | |
| "grad_norm": 0.35860228538513184, | |
| "learning_rate": 0.00013989479217232315, | |
| "loss": 0.3459, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.8879767942064447, | |
| "eval_loss": 0.27472037076950073, | |
| "eval_runtime": 0.0888, | |
| "eval_samples_per_second": 56.322, | |
| "eval_steps_per_second": 11.264, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.9077096118554768, | |
| "grad_norm": 0.39065611362457275, | |
| "learning_rate": 0.00013664630558484379, | |
| "loss": 0.3365, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.9077096118554768, | |
| "eval_loss": 0.2625993490219116, | |
| "eval_runtime": 0.0905, | |
| "eval_samples_per_second": 55.261, | |
| "eval_steps_per_second": 11.052, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.927442429504509, | |
| "grad_norm": 0.3311096131801605, | |
| "learning_rate": 0.00013335250907734448, | |
| "loss": 0.3433, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.927442429504509, | |
| "eval_loss": 0.26789966225624084, | |
| "eval_runtime": 0.0901, | |
| "eval_samples_per_second": 55.469, | |
| "eval_steps_per_second": 11.094, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.9471752471535411, | |
| "grad_norm": 0.29878920316696167, | |
| "learning_rate": 0.00013001747513827764, | |
| "loss": 0.3421, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.9471752471535411, | |
| "eval_loss": 0.26495981216430664, | |
| "eval_runtime": 0.0901, | |
| "eval_samples_per_second": 55.48, | |
| "eval_steps_per_second": 11.096, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.9669080648025732, | |
| "grad_norm": 0.27687743306159973, | |
| "learning_rate": 0.00012664532724253745, | |
| "loss": 0.3412, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.9669080648025732, | |
| "eval_loss": 0.26512324810028076, | |
| "eval_runtime": 0.0891, | |
| "eval_samples_per_second": 56.121, | |
| "eval_steps_per_second": 11.224, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.9866408824516053, | |
| "grad_norm": 0.2745589017868042, | |
| "learning_rate": 0.00012324023475314725, | |
| "loss": 0.3389, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.9866408824516053, | |
| "eval_loss": 0.2671201825141907, | |
| "eval_runtime": 0.0893, | |
| "eval_samples_per_second": 55.975, | |
| "eval_steps_per_second": 11.195, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.0064328985535844, | |
| "grad_norm": 0.3213329017162323, | |
| "learning_rate": 0.00011980640776621077, | |
| "loss": 0.3342, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.0064328985535844, | |
| "eval_loss": 0.26046106219291687, | |
| "eval_runtime": 0.0901, | |
| "eval_samples_per_second": 55.499, | |
| "eval_steps_per_second": 11.1, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.0261657162026165, | |
| "grad_norm": 0.27474504709243774, | |
| "learning_rate": 0.0001163480919054998, | |
| "loss": 0.3256, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.0261657162026165, | |
| "eval_loss": 0.25896698236465454, | |
| "eval_runtime": 0.0888, | |
| "eval_samples_per_second": 56.29, | |
| "eval_steps_per_second": 11.258, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.0458985338516487, | |
| "grad_norm": 0.30879899859428406, | |
| "learning_rate": 0.00011286956307311555, | |
| "loss": 0.3221, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.0458985338516487, | |
| "eval_loss": 0.26479166746139526, | |
| "eval_runtime": 0.0899, | |
| "eval_samples_per_second": 55.608, | |
| "eval_steps_per_second": 11.122, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.0656313515006808, | |
| "grad_norm": 0.31644341349601746, | |
| "learning_rate": 0.00010937512216271338, | |
| "loss": 0.3213, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.0656313515006808, | |
| "eval_loss": 0.2630908489227295, | |
| "eval_runtime": 0.0912, | |
| "eval_samples_per_second": 54.85, | |
| "eval_steps_per_second": 10.97, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.085364169149713, | |
| "grad_norm": 0.27920085191726685, | |
| "learning_rate": 0.00010586908974182767, | |
| "loss": 0.3236, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.085364169149713, | |
| "eval_loss": 0.25873327255249023, | |
| "eval_runtime": 0.0918, | |
| "eval_samples_per_second": 54.458, | |
| "eval_steps_per_second": 10.892, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.105096986798745, | |
| "grad_norm": 0.41224974393844604, | |
| "learning_rate": 0.0001023558007098717, | |
| "loss": 0.3201, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.105096986798745, | |
| "eval_loss": 0.2597818672657013, | |
| "eval_runtime": 0.0924, | |
| "eval_samples_per_second": 54.094, | |
| "eval_steps_per_second": 10.819, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.1248298044477771, | |
| "grad_norm": 0.28382521867752075, | |
| "learning_rate": 9.88395989384173e-05, | |
| "loss": 0.3227, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.1248298044477771, | |
| "eval_loss": 0.2594955563545227, | |
| "eval_runtime": 0.0907, | |
| "eval_samples_per_second": 55.14, | |
| "eval_steps_per_second": 11.028, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.1445626220968093, | |
| "grad_norm": 0.258071631193161, | |
| "learning_rate": 9.532483190038153e-05, | |
| "loss": 0.3188, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.1445626220968093, | |
| "eval_loss": 0.2607273459434509, | |
| "eval_runtime": 0.0902, | |
| "eval_samples_per_second": 55.429, | |
| "eval_steps_per_second": 11.086, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.1642954397458414, | |
| "grad_norm": 0.4713532030582428, | |
| "learning_rate": 9.181584529476025e-05, | |
| "loss": 0.3199, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.1642954397458414, | |
| "eval_loss": 0.2583589255809784, | |
| "eval_runtime": 0.0897, | |
| "eval_samples_per_second": 55.713, | |
| "eval_steps_per_second": 11.143, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.1840282573948735, | |
| "grad_norm": 0.2917826771736145, | |
| "learning_rate": 8.831697767355519e-05, | |
| "loss": 0.3185, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.1840282573948735, | |
| "eval_loss": 0.256054550409317, | |
| "eval_runtime": 0.091, | |
| "eval_samples_per_second": 54.935, | |
| "eval_steps_per_second": 10.987, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.2037610750439056, | |
| "grad_norm": 0.27514272928237915, | |
| "learning_rate": 8.483255507753762e-05, | |
| "loss": 0.3167, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.2037610750439056, | |
| "eval_loss": 0.2567542791366577, | |
| "eval_runtime": 0.0902, | |
| "eval_samples_per_second": 55.458, | |
| "eval_steps_per_second": 11.092, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.2234938926929377, | |
| "grad_norm": 0.28672000765800476, | |
| "learning_rate": 8.136688568748113e-05, | |
| "loss": 0.3131, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.2234938926929377, | |
| "eval_loss": 0.2553618848323822, | |
| "eval_runtime": 0.0906, | |
| "eval_samples_per_second": 55.177, | |
| "eval_steps_per_second": 11.035, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.2432267103419696, | |
| "grad_norm": 0.30310142040252686, | |
| "learning_rate": 7.792425449747635e-05, | |
| "loss": 0.3189, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.2432267103419696, | |
| "eval_loss": 0.2524791657924652, | |
| "eval_runtime": 0.0904, | |
| "eval_samples_per_second": 55.281, | |
| "eval_steps_per_second": 11.056, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.262959527991002, | |
| "grad_norm": 0.2990928888320923, | |
| "learning_rate": 7.450891801691468e-05, | |
| "loss": 0.3163, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.262959527991002, | |
| "eval_loss": 0.25296735763549805, | |
| "eval_runtime": 0.0903, | |
| "eval_samples_per_second": 55.377, | |
| "eval_steps_per_second": 11.075, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.2826923456400339, | |
| "grad_norm": 0.28423842787742615, | |
| "learning_rate": 7.112509900768989e-05, | |
| "loss": 0.3171, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.2826923456400339, | |
| "eval_loss": 0.25522494316101074, | |
| "eval_runtime": 0.09, | |
| "eval_samples_per_second": 55.554, | |
| "eval_steps_per_second": 11.111, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.302425163289066, | |
| "grad_norm": 0.2940766513347626, | |
| "learning_rate": 6.777698126312647e-05, | |
| "loss": 0.3122, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.302425163289066, | |
| "eval_loss": 0.2504900395870209, | |
| "eval_runtime": 0.0898, | |
| "eval_samples_per_second": 55.653, | |
| "eval_steps_per_second": 11.131, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.322157980938098, | |
| "grad_norm": 0.29685819149017334, | |
| "learning_rate": 6.446870443508839e-05, | |
| "loss": 0.3094, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.322157980938098, | |
| "eval_loss": 0.2528066039085388, | |
| "eval_runtime": 0.0914, | |
| "eval_samples_per_second": 54.709, | |
| "eval_steps_per_second": 10.942, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.3418907985871302, | |
| "grad_norm": 0.28402870893478394, | |
| "learning_rate": 6.120435891566542e-05, | |
| "loss": 0.3143, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.3418907985871302, | |
| "eval_loss": 0.2532269358634949, | |
| "eval_runtime": 0.0909, | |
| "eval_samples_per_second": 55.009, | |
| "eval_steps_per_second": 11.002, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.3616236162361623, | |
| "grad_norm": 0.29260462522506714, | |
| "learning_rate": 5.7987980779764463e-05, | |
| "loss": 0.3106, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.3616236162361623, | |
| "eval_loss": 0.24992766976356506, | |
| "eval_runtime": 0.0908, | |
| "eval_samples_per_second": 55.057, | |
| "eval_steps_per_second": 11.011, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.3813564338851945, | |
| "grad_norm": 0.27314430475234985, | |
| "learning_rate": 5.482354679485948e-05, | |
| "loss": 0.3162, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.3813564338851945, | |
| "eval_loss": 0.24991869926452637, | |
| "eval_runtime": 0.091, | |
| "eval_samples_per_second": 54.919, | |
| "eval_steps_per_second": 10.984, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.4010892515342266, | |
| "grad_norm": 0.28783899545669556, | |
| "learning_rate": 5.17149695040698e-05, | |
| "loss": 0.3093, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 1.4010892515342266, | |
| "eval_loss": 0.2506985068321228, | |
| "eval_runtime": 0.0908, | |
| "eval_samples_per_second": 55.089, | |
| "eval_steps_per_second": 11.018, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 1.4208220691832587, | |
| "grad_norm": 0.3105429708957672, | |
| "learning_rate": 4.866609238864609e-05, | |
| "loss": 0.3105, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.4208220691832587, | |
| "eval_loss": 0.2487274706363678, | |
| "eval_runtime": 0.0911, | |
| "eval_samples_per_second": 54.856, | |
| "eval_steps_per_second": 10.971, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.4405548868322908, | |
| "grad_norm": 0.2590714693069458, | |
| "learning_rate": 4.568068511584529e-05, | |
| "loss": 0.3092, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 1.4405548868322908, | |
| "eval_loss": 0.2481408566236496, | |
| "eval_runtime": 0.0906, | |
| "eval_samples_per_second": 55.214, | |
| "eval_steps_per_second": 11.043, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 1.460287704481323, | |
| "grad_norm": 0.27170825004577637, | |
| "learning_rate": 4.2762438878069955e-05, | |
| "loss": 0.3113, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.460287704481323, | |
| "eval_loss": 0.24591541290283203, | |
| "eval_runtime": 0.0904, | |
| "eval_samples_per_second": 55.31, | |
| "eval_steps_per_second": 11.062, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.480020522130355, | |
| "grad_norm": 0.2719477117061615, | |
| "learning_rate": 3.991496182903498e-05, | |
| "loss": 0.3077, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.480020522130355, | |
| "eval_loss": 0.24259333312511444, | |
| "eval_runtime": 0.091, | |
| "eval_samples_per_second": 54.966, | |
| "eval_steps_per_second": 10.993, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.499753339779387, | |
| "grad_norm": 0.28030896186828613, | |
| "learning_rate": 3.714177462260412e-05, | |
| "loss": 0.3073, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.499753339779387, | |
| "eval_loss": 0.2429008185863495, | |
| "eval_runtime": 0.093, | |
| "eval_samples_per_second": 53.774, | |
| "eval_steps_per_second": 10.755, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.5194861574284193, | |
| "grad_norm": 0.2803615629673004, | |
| "learning_rate": 3.444630605981256e-05, | |
| "loss": 0.3042, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 1.5194861574284193, | |
| "eval_loss": 0.2448611706495285, | |
| "eval_runtime": 0.0905, | |
| "eval_samples_per_second": 55.251, | |
| "eval_steps_per_second": 11.05, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 1.5392189750774512, | |
| "grad_norm": 0.326019823551178, | |
| "learning_rate": 3.183188884945714e-05, | |
| "loss": 0.3075, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.5392189750774512, | |
| "eval_loss": 0.24277858436107635, | |
| "eval_runtime": 0.0897, | |
| "eval_samples_per_second": 55.757, | |
| "eval_steps_per_second": 11.151, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.5589517927264835, | |
| "grad_norm": 0.3696662187576294, | |
| "learning_rate": 2.930175548749645e-05, | |
| "loss": 0.3047, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 1.5589517927264835, | |
| "eval_loss": 0.2429245412349701, | |
| "eval_runtime": 0.0909, | |
| "eval_samples_per_second": 55.022, | |
| "eval_steps_per_second": 11.004, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 1.5786846103755154, | |
| "grad_norm": 0.2868829667568207, | |
| "learning_rate": 2.6859034260355042e-05, | |
| "loss": 0.307, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.5786846103755154, | |
| "eval_loss": 0.2427954375743866, | |
| "eval_runtime": 0.0901, | |
| "eval_samples_per_second": 55.51, | |
| "eval_steps_per_second": 11.102, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.5984174280245478, | |
| "grad_norm": 0.28634509444236755, | |
| "learning_rate": 2.4506745377073535e-05, | |
| "loss": 0.303, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 1.5984174280245478, | |
| "eval_loss": 0.24240228533744812, | |
| "eval_runtime": 0.0911, | |
| "eval_samples_per_second": 54.88, | |
| "eval_steps_per_second": 10.976, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 1.6181502456735797, | |
| "grad_norm": 0.2582091987133026, | |
| "learning_rate": 2.224779723508692e-05, | |
| "loss": 0.3063, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.6181502456735797, | |
| "eval_loss": 0.24210545420646667, | |
| "eval_runtime": 0.0895, | |
| "eval_samples_per_second": 55.845, | |
| "eval_steps_per_second": 11.169, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.6378830633226118, | |
| "grad_norm": 0.29064637422561646, | |
| "learning_rate": 2.0084982824248034e-05, | |
| "loss": 0.3041, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 1.6378830633226118, | |
| "eval_loss": 0.24005956947803497, | |
| "eval_runtime": 0.0916, | |
| "eval_samples_per_second": 54.615, | |
| "eval_steps_per_second": 10.923, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 1.657615880971644, | |
| "grad_norm": 0.29442399740219116, | |
| "learning_rate": 1.802097627354231e-05, | |
| "loss": 0.3046, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.657615880971644, | |
| "eval_loss": 0.238916277885437, | |
| "eval_runtime": 0.0907, | |
| "eval_samples_per_second": 55.107, | |
| "eval_steps_per_second": 11.021, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.677348698620676, | |
| "grad_norm": 0.2660856246948242, | |
| "learning_rate": 1.605832954476346e-05, | |
| "loss": 0.3054, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.677348698620676, | |
| "eval_loss": 0.2391015589237213, | |
| "eval_runtime": 0.0907, | |
| "eval_samples_per_second": 55.141, | |
| "eval_steps_per_second": 11.028, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.6970815162697082, | |
| "grad_norm": 0.29835525155067444, | |
| "learning_rate": 1.4199469277238143e-05, | |
| "loss": 0.3043, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.6970815162697082, | |
| "eval_loss": 0.23956787586212158, | |
| "eval_runtime": 0.0899, | |
| "eval_samples_per_second": 55.608, | |
| "eval_steps_per_second": 11.122, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.7168143339187403, | |
| "grad_norm": 0.33219653367996216, | |
| "learning_rate": 1.2446693787500697e-05, | |
| "loss": 0.3033, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 1.7168143339187403, | |
| "eval_loss": 0.23964008688926697, | |
| "eval_runtime": 0.0905, | |
| "eval_samples_per_second": 55.26, | |
| "eval_steps_per_second": 11.052, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 1.7365471515677724, | |
| "grad_norm": 0.26195675134658813, | |
| "learning_rate": 1.0802170227627873e-05, | |
| "loss": 0.3062, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.7365471515677724, | |
| "eval_loss": 0.2384120523929596, | |
| "eval_runtime": 0.0895, | |
| "eval_samples_per_second": 55.837, | |
| "eval_steps_per_second": 11.167, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.7562799692168045, | |
| "grad_norm": 0.2874230146408081, | |
| "learning_rate": 9.26793190574664e-06, | |
| "loss": 0.3079, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 1.7562799692168045, | |
| "eval_loss": 0.23803596198558807, | |
| "eval_runtime": 0.0892, | |
| "eval_samples_per_second": 56.06, | |
| "eval_steps_per_second": 11.212, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 1.7760127868658366, | |
| "grad_norm": 0.31188592314720154, | |
| "learning_rate": 7.845875772028289e-06, | |
| "loss": 0.3026, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.7760127868658366, | |
| "eval_loss": 0.23819437623023987, | |
| "eval_runtime": 0.0916, | |
| "eval_samples_per_second": 54.586, | |
| "eval_steps_per_second": 10.917, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.7957456045148685, | |
| "grad_norm": 0.25863921642303467, | |
| "learning_rate": 6.537760073277066e-06, | |
| "loss": 0.3028, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 1.7957456045148685, | |
| "eval_loss": 0.23811522126197815, | |
| "eval_runtime": 0.0907, | |
| "eval_samples_per_second": 55.122, | |
| "eval_steps_per_second": 11.024, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 1.8154784221639009, | |
| "grad_norm": 0.2967861592769623, | |
| "learning_rate": 5.345202179013353e-06, | |
| "loss": 0.3036, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.8154784221639009, | |
| "eval_loss": 0.23839135468006134, | |
| "eval_runtime": 0.0891, | |
| "eval_samples_per_second": 56.087, | |
| "eval_steps_per_second": 11.217, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.8352112398129328, | |
| "grad_norm": 0.26816633343696594, | |
| "learning_rate": 4.269676581739079e-06, | |
| "loss": 0.3033, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 1.8352112398129328, | |
| "eval_loss": 0.23855826258659363, | |
| "eval_runtime": 0.0915, | |
| "eval_samples_per_second": 54.629, | |
| "eval_steps_per_second": 10.926, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 1.8549440574619651, | |
| "grad_norm": 0.27961990237236023, | |
| "learning_rate": 3.3125130738579922e-06, | |
| "loss": 0.3059, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.8549440574619651, | |
| "eval_loss": 0.2385035753250122, | |
| "eval_runtime": 0.0918, | |
| "eval_samples_per_second": 54.481, | |
| "eval_steps_per_second": 10.896, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.874676875110997, | |
| "grad_norm": 0.28482890129089355, | |
| "learning_rate": 2.4748951035047596e-06, | |
| "loss": 0.3047, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.874676875110997, | |
| "eval_loss": 0.23791757225990295, | |
| "eval_runtime": 0.0933, | |
| "eval_samples_per_second": 53.597, | |
| "eval_steps_per_second": 10.719, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.8944096927600294, | |
| "grad_norm": 0.299679160118103, | |
| "learning_rate": 1.7578583113159962e-06, | |
| "loss": 0.3036, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.8944096927600294, | |
| "eval_loss": 0.2383710891008377, | |
| "eval_runtime": 0.0895, | |
| "eval_samples_per_second": 55.854, | |
| "eval_steps_per_second": 11.171, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.9141425104090612, | |
| "grad_norm": 0.27456724643707275, | |
| "learning_rate": 1.1622892499519421e-06, | |
| "loss": 0.3032, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 1.9141425104090612, | |
| "eval_loss": 0.2380281388759613, | |
| "eval_runtime": 0.0895, | |
| "eval_samples_per_second": 55.876, | |
| "eval_steps_per_second": 11.175, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 1.9338753280580934, | |
| "grad_norm": 0.27245351672172546, | |
| "learning_rate": 6.889242879525415e-07, | |
| "loss": 0.2994, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.9338753280580934, | |
| "eval_loss": 0.23812708258628845, | |
| "eval_runtime": 0.09, | |
| "eval_samples_per_second": 55.528, | |
| "eval_steps_per_second": 11.106, | |
| "step": 9800 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 10134, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.236547392844431e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |