| { |
| "best_global_step": 1500, |
| "best_metric": 3.755718469619751, |
| "best_model_checkpoint": "/Users/alexgrigoras/Library/Mobile Documents/com~apple~CloudDocs/[5] Software/github/dif-pi/artifacts/models/sdg_chronos_t5_small_dunnhumby/checkpoint-1500", |
| "epoch": 0.2090920179122162, |
| "eval_steps": 25, |
| "global_step": 1500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0034848669652036033, |
| "grad_norm": 0.2964903712272644, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 37.88656494140625, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0034848669652036033, |
| "eval_loss": 4.6062092781066895, |
| "eval_runtime": 134.4005, |
| "eval_samples_per_second": 94.895, |
| "eval_steps_per_second": 47.448, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.006969733930407207, |
| "grad_norm": 0.34245482087135315, |
| "learning_rate": 1.6333333333333335e-05, |
| "loss": 37.61192138671875, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.006969733930407207, |
| "eval_loss": 4.552639007568359, |
| "eval_runtime": 131.7871, |
| "eval_samples_per_second": 96.777, |
| "eval_steps_per_second": 48.389, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.01045460089561081, |
| "grad_norm": 0.3815608024597168, |
| "learning_rate": 2.466666666666667e-05, |
| "loss": 37.09659912109375, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.01045460089561081, |
| "eval_loss": 4.443544864654541, |
| "eval_runtime": 154.9254, |
| "eval_samples_per_second": 82.323, |
| "eval_steps_per_second": 41.162, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.013939467860814413, |
| "grad_norm": 0.3647356331348419, |
| "learning_rate": 2.498250672211728e-05, |
| "loss": 36.29866943359375, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.013939467860814413, |
| "eval_loss": 4.3369669914245605, |
| "eval_runtime": 138.8908, |
| "eval_samples_per_second": 91.828, |
| "eval_steps_per_second": 45.914, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.017424334826018018, |
| "grad_norm": 0.3683606684207916, |
| "learning_rate": 2.4927134858925575e-05, |
| "loss": 35.8759912109375, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.017424334826018018, |
| "eval_loss": 4.242681980133057, |
| "eval_runtime": 125.8059, |
| "eval_samples_per_second": 101.378, |
| "eval_steps_per_second": 50.689, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.02090920179122162, |
| "grad_norm": 0.41745099425315857, |
| "learning_rate": 2.4834022195605383e-05, |
| "loss": 34.71609375, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.02090920179122162, |
| "eval_loss": 4.15211820602417, |
| "eval_runtime": 144.0648, |
| "eval_samples_per_second": 88.53, |
| "eval_steps_per_second": 44.265, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.024394068756425222, |
| "grad_norm": 0.5502339601516724, |
| "learning_rate": 2.470345151225491e-05, |
| "loss": 34.4389111328125, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.024394068756425222, |
| "eval_loss": 4.065174579620361, |
| "eval_runtime": 164.1963, |
| "eval_samples_per_second": 77.675, |
| "eval_steps_per_second": 38.838, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.027878935721628827, |
| "grad_norm": 0.5007655024528503, |
| "learning_rate": 2.4535819347748074e-05, |
| "loss": 33.89746337890625, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.027878935721628827, |
| "eval_loss": 3.987807035446167, |
| "eval_runtime": 141.6182, |
| "eval_samples_per_second": 90.059, |
| "eval_steps_per_second": 45.03, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.03136380268683243, |
| "grad_norm": 0.48552975058555603, |
| "learning_rate": 2.433163479545898e-05, |
| "loss": 34.3608935546875, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.03136380268683243, |
| "eval_loss": 3.951249361038208, |
| "eval_runtime": 178.1207, |
| "eval_samples_per_second": 71.603, |
| "eval_steps_per_second": 35.802, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.034848669652036035, |
| "grad_norm": 0.4646497964859009, |
| "learning_rate": 2.4091517957162068e-05, |
| "loss": 33.36589599609375, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.034848669652036035, |
| "eval_loss": 3.9345061779022217, |
| "eval_runtime": 191.2882, |
| "eval_samples_per_second": 66.674, |
| "eval_steps_per_second": 33.337, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.038333536617239636, |
| "grad_norm": 0.5384636521339417, |
| "learning_rate": 2.3816198059803415e-05, |
| "loss": 32.43830810546875, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.038333536617239636, |
| "eval_loss": 3.919111967086792, |
| "eval_runtime": 157.7724, |
| "eval_samples_per_second": 80.838, |
| "eval_steps_per_second": 40.419, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.04181840358244324, |
| "grad_norm": 0.5843191742897034, |
| "learning_rate": 2.350651124086246e-05, |
| "loss": 33.16199462890625, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.04181840358244324, |
| "eval_loss": 3.907341957092285, |
| "eval_runtime": 137.2039, |
| "eval_samples_per_second": 92.957, |
| "eval_steps_per_second": 46.478, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.045303270547646844, |
| "grad_norm": 0.6355782151222229, |
| "learning_rate": 2.316339800902997e-05, |
| "loss": 31.9848095703125, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.045303270547646844, |
| "eval_loss": 3.904228925704956, |
| "eval_runtime": 142.1459, |
| "eval_samples_per_second": 89.725, |
| "eval_steps_per_second": 44.862, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.048788137512850445, |
| "grad_norm": 0.6354503035545349, |
| "learning_rate": 2.2787900387914035e-05, |
| "loss": 32.89923095703125, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.048788137512850445, |
| "eval_loss": 3.889650344848633, |
| "eval_runtime": 135.6805, |
| "eval_samples_per_second": 94.0, |
| "eval_steps_per_second": 47.0, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.05227300447805405, |
| "grad_norm": 0.4500903785228729, |
| "learning_rate": 2.238115875144865e-05, |
| "loss": 31.9859375, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.05227300447805405, |
| "eval_loss": 3.881140947341919, |
| "eval_runtime": 137.1013, |
| "eval_samples_per_second": 93.026, |
| "eval_steps_per_second": 46.513, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.05575787144325765, |
| "grad_norm": 0.7105244994163513, |
| "learning_rate": 2.1944408360615527e-05, |
| "loss": 31.830234375, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.05575787144325765, |
| "eval_loss": 3.876532554626465, |
| "eval_runtime": 138.0891, |
| "eval_samples_per_second": 92.361, |
| "eval_steps_per_second": 46.18, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.059242738408461254, |
| "grad_norm": 0.5426522493362427, |
| "learning_rate": 2.147897561199711e-05, |
| "loss": 32.8569921875, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.059242738408461254, |
| "eval_loss": 3.869863510131836, |
| "eval_runtime": 137.3068, |
| "eval_samples_per_second": 92.887, |
| "eval_steps_per_second": 46.443, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.06272760537366485, |
| "grad_norm": 0.6868773698806763, |
| "learning_rate": 2.0986274009553747e-05, |
| "loss": 33.1663525390625, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.06272760537366485, |
| "eval_loss": 3.858783483505249, |
| "eval_runtime": 136.4747, |
| "eval_samples_per_second": 93.453, |
| "eval_steps_per_second": 46.727, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.06621247233886847, |
| "grad_norm": 0.6488957405090332, |
| "learning_rate": 2.0467799871858624e-05, |
| "loss": 32.170732421875, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.06621247233886847, |
| "eval_loss": 3.857388496398926, |
| "eval_runtime": 138.5464, |
| "eval_samples_per_second": 92.056, |
| "eval_steps_per_second": 46.028, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.06969733930407207, |
| "grad_norm": 0.5700647830963135, |
| "learning_rate": 1.9925127787827415e-05, |
| "loss": 32.3882470703125, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.06969733930407207, |
| "eval_loss": 3.852177619934082, |
| "eval_runtime": 137.7764, |
| "eval_samples_per_second": 92.57, |
| "eval_steps_per_second": 46.285, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.07318220626927567, |
| "grad_norm": 0.6471461653709412, |
| "learning_rate": 1.9359905834743513e-05, |
| "loss": 32.83000244140625, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.07318220626927567, |
| "eval_loss": 3.8465960025787354, |
| "eval_runtime": 137.4128, |
| "eval_samples_per_second": 92.815, |
| "eval_steps_per_second": 46.408, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.07666707323447927, |
| "grad_norm": 0.6369190812110901, |
| "learning_rate": 1.8773850573101503e-05, |
| "loss": 32.35257080078125, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.07666707323447927, |
| "eval_loss": 3.842385768890381, |
| "eval_runtime": 140.2355, |
| "eval_samples_per_second": 90.947, |
| "eval_steps_per_second": 45.474, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.08015194019968287, |
| "grad_norm": 0.5800191164016724, |
| "learning_rate": 1.8168741833469327e-05, |
| "loss": 31.9875244140625, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.08015194019968287, |
| "eval_loss": 3.8325023651123047, |
| "eval_runtime": 137.4074, |
| "eval_samples_per_second": 92.819, |
| "eval_steps_per_second": 46.409, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.08363680716488649, |
| "grad_norm": 0.655426025390625, |
| "learning_rate": 1.7546417311201357e-05, |
| "loss": 31.470654296875, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.08363680716488649, |
| "eval_loss": 3.82979416847229, |
| "eval_runtime": 136.3318, |
| "eval_samples_per_second": 93.551, |
| "eval_steps_per_second": 46.776, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.08712167413009009, |
| "grad_norm": 0.5678662657737732, |
| "learning_rate": 1.690876698541802e-05, |
| "loss": 32.25173828125, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.08712167413009009, |
| "eval_loss": 3.828555107116699, |
| "eval_runtime": 142.3008, |
| "eval_samples_per_second": 89.627, |
| "eval_steps_per_second": 44.814, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.09060654109529369, |
| "grad_norm": 0.6696360111236572, |
| "learning_rate": 1.625772737920128e-05, |
| "loss": 32.847529296875, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.09060654109529369, |
| "eval_loss": 3.8212130069732666, |
| "eval_runtime": 145.4915, |
| "eval_samples_per_second": 87.661, |
| "eval_steps_per_second": 43.831, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.09409140806049729, |
| "grad_norm": 0.6813345551490784, |
| "learning_rate": 1.5595275678437756e-05, |
| "loss": 32.22562744140625, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.09409140806049729, |
| "eval_loss": 3.8163504600524902, |
| "eval_runtime": 135.9053, |
| "eval_samples_per_second": 93.845, |
| "eval_steps_per_second": 46.922, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.09757627502570089, |
| "grad_norm": 0.6201620101928711, |
| "learning_rate": 1.4923423727170106e-05, |
| "loss": 32.73896240234375, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.09757627502570089, |
| "eval_loss": 3.8148138523101807, |
| "eval_runtime": 140.771, |
| "eval_samples_per_second": 90.601, |
| "eval_steps_per_second": 45.301, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.10106114199090449, |
| "grad_norm": 0.6953298449516296, |
| "learning_rate": 1.4244211917692812e-05, |
| "loss": 32.32746826171875, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.10106114199090449, |
| "eval_loss": 3.8123884201049805, |
| "eval_runtime": 141.0245, |
| "eval_samples_per_second": 90.438, |
| "eval_steps_per_second": 45.219, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.1045460089561081, |
| "grad_norm": 0.7098183035850525, |
| "learning_rate": 1.355970299394786e-05, |
| "loss": 32.90800048828125, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.1045460089561081, |
| "eval_loss": 3.810453414916992, |
| "eval_runtime": 138.6332, |
| "eval_samples_per_second": 91.998, |
| "eval_steps_per_second": 45.999, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.1080308759213117, |
| "grad_norm": 0.7382436990737915, |
| "learning_rate": 1.2871975787039157e-05, |
| "loss": 32.9301318359375, |
| "step": 775 |
| }, |
| { |
| "epoch": 0.1080308759213117, |
| "eval_loss": 3.806396007537842, |
| "eval_runtime": 141.0631, |
| "eval_samples_per_second": 90.413, |
| "eval_steps_per_second": 45.207, |
| "step": 775 |
| }, |
| { |
| "epoch": 0.1115157428865153, |
| "grad_norm": 0.702569842338562, |
| "learning_rate": 1.218311890189081e-05, |
| "loss": 31.67234619140625, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.1115157428865153, |
| "eval_loss": 3.803560495376587, |
| "eval_runtime": 138.1294, |
| "eval_samples_per_second": 92.334, |
| "eval_steps_per_second": 46.167, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.11500060985171891, |
| "grad_norm": 0.7312149405479431, |
| "learning_rate": 1.1495224374222602e-05, |
| "loss": 32.169111328125, |
| "step": 825 |
| }, |
| { |
| "epoch": 0.11500060985171891, |
| "eval_loss": 3.7968807220458984, |
| "eval_runtime": 140.9117, |
| "eval_samples_per_second": 90.511, |
| "eval_steps_per_second": 45.255, |
| "step": 825 |
| }, |
| { |
| "epoch": 0.11848547681692251, |
| "grad_norm": 0.8160529732704163, |
| "learning_rate": 1.0810381317106293e-05, |
| "loss": 32.00342529296875, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.11848547681692251, |
| "eval_loss": 3.791039228439331, |
| "eval_runtime": 129.2785, |
| "eval_samples_per_second": 98.655, |
| "eval_steps_per_second": 49.328, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.12197034378212612, |
| "grad_norm": 0.7061131000518799, |
| "learning_rate": 1.013066957639785e-05, |
| "loss": 31.30172607421875, |
| "step": 875 |
| }, |
| { |
| "epoch": 0.12197034378212612, |
| "eval_loss": 3.791710615158081, |
| "eval_runtime": 125.3783, |
| "eval_samples_per_second": 101.724, |
| "eval_steps_per_second": 50.862, |
| "step": 875 |
| }, |
| { |
| "epoch": 0.1254552107473297, |
| "grad_norm": 0.8358163237571716, |
| "learning_rate": 9.45815341431398e-06, |
| "loss": 31.78281982421875, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.1254552107473297, |
| "eval_loss": 3.7942440509796143, |
| "eval_runtime": 135.2641, |
| "eval_samples_per_second": 94.29, |
| "eval_steps_per_second": 47.145, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.12894007771253332, |
| "grad_norm": 0.7387733459472656, |
| "learning_rate": 8.79487524033558e-06, |
| "loss": 30.677724609375, |
| "step": 925 |
| }, |
| { |
| "epoch": 0.12894007771253332, |
| "eval_loss": 3.790346384048462, |
| "eval_runtime": 126.5812, |
| "eval_samples_per_second": 100.757, |
| "eval_steps_per_second": 50.379, |
| "step": 925 |
| }, |
| { |
| "epoch": 0.13242494467773694, |
| "grad_norm": 0.6606021523475647, |
| "learning_rate": 8.142849408477312e-06, |
| "loss": 32.30339111328125, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.13242494467773694, |
| "eval_loss": 3.7845609188079834, |
| "eval_runtime": 126.5895, |
| "eval_samples_per_second": 100.751, |
| "eval_steps_per_second": 50.375, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.13590981164294053, |
| "grad_norm": 0.7597334980964661, |
| "learning_rate": 7.504056099760629e-06, |
| "loss": 31.49365966796875, |
| "step": 975 |
| }, |
| { |
| "epoch": 0.13590981164294053, |
| "eval_loss": 3.783795118331909, |
| "eval_runtime": 128.5471, |
| "eval_samples_per_second": 99.217, |
| "eval_steps_per_second": 49.608, |
| "step": 975 |
| }, |
| { |
| "epoch": 0.13939467860814414, |
| "grad_norm": 0.8744051456451416, |
| "learning_rate": 6.880435308469124e-06, |
| "loss": 32.4120263671875, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.13939467860814414, |
| "eval_loss": 3.78021240234375, |
| "eval_runtime": 126.8291, |
| "eval_samples_per_second": 100.561, |
| "eval_steps_per_second": 50.28, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.14287954557334773, |
| "grad_norm": 0.8689478039741516, |
| "learning_rate": 6.273880950449624e-06, |
| "loss": 32.66720458984375, |
| "step": 1025 |
| }, |
| { |
| "epoch": 0.14287954557334773, |
| "eval_loss": 3.7732369899749756, |
| "eval_runtime": 124.3195, |
| "eval_samples_per_second": 102.59, |
| "eval_steps_per_second": 51.295, |
| "step": 1025 |
| }, |
| { |
| "epoch": 0.14636441253855134, |
| "grad_norm": 0.8830795288085938, |
| "learning_rate": 5.6862351113520505e-06, |
| "loss": 32.37453125, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.14636441253855134, |
| "eval_loss": 3.7737340927124023, |
| "eval_runtime": 124.7043, |
| "eval_samples_per_second": 102.274, |
| "eval_steps_per_second": 51.137, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.14984927950375496, |
| "grad_norm": 0.8162481188774109, |
| "learning_rate": 5.119282452275787e-06, |
| "loss": 31.86205078125, |
| "step": 1075 |
| }, |
| { |
| "epoch": 0.14984927950375496, |
| "eval_loss": 3.7654809951782227, |
| "eval_runtime": 123.5389, |
| "eval_samples_per_second": 103.239, |
| "eval_steps_per_second": 51.619, |
| "step": 1075 |
| }, |
| { |
| "epoch": 0.15333414646895854, |
| "grad_norm": 0.8534089922904968, |
| "learning_rate": 4.574744789812638e-06, |
| "loss": 32.600322265625, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.15333414646895854, |
| "eval_loss": 3.764484405517578, |
| "eval_runtime": 133.2209, |
| "eval_samples_per_second": 95.736, |
| "eval_steps_per_second": 47.868, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.15681901343416216, |
| "grad_norm": 0.7590998411178589, |
| "learning_rate": 4.054275866946371e-06, |
| "loss": 32.25859375, |
| "step": 1125 |
| }, |
| { |
| "epoch": 0.15681901343416216, |
| "eval_loss": 3.763986349105835, |
| "eval_runtime": 125.3471, |
| "eval_samples_per_second": 101.749, |
| "eval_steps_per_second": 50.875, |
| "step": 1125 |
| }, |
| { |
| "epoch": 0.16030388039936574, |
| "grad_norm": 0.7258529663085938, |
| "learning_rate": 3.559456330689684e-06, |
| "loss": 32.69231201171875, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.16030388039936574, |
| "eval_loss": 3.7613186836242676, |
| "eval_runtime": 125.2043, |
| "eval_samples_per_second": 101.865, |
| "eval_steps_per_second": 50.933, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.16378874736456936, |
| "grad_norm": 0.7329394817352295, |
| "learning_rate": 3.091788931711123e-06, |
| "loss": 31.1957958984375, |
| "step": 1175 |
| }, |
| { |
| "epoch": 0.16378874736456936, |
| "eval_loss": 3.7616991996765137, |
| "eval_runtime": 125.2233, |
| "eval_samples_per_second": 101.85, |
| "eval_steps_per_second": 50.925, |
| "step": 1175 |
| }, |
| { |
| "epoch": 0.16727361432977297, |
| "grad_norm": 0.7856114506721497, |
| "learning_rate": 2.652693960530743e-06, |
| "loss": 32.34443359375, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.16727361432977297, |
| "eval_loss": 3.762284755706787, |
| "eval_runtime": 133.7621, |
| "eval_samples_per_second": 95.348, |
| "eval_steps_per_second": 47.674, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.17075848129497656, |
| "grad_norm": 0.8546104431152344, |
| "learning_rate": 2.243504934144444e-06, |
| "loss": 31.9795556640625, |
| "step": 1225 |
| }, |
| { |
| "epoch": 0.17075848129497656, |
| "eval_loss": 3.761392593383789, |
| "eval_runtime": 135.3874, |
| "eval_samples_per_second": 94.204, |
| "eval_steps_per_second": 47.102, |
| "step": 1225 |
| }, |
| { |
| "epoch": 0.17424334826018018, |
| "grad_norm": 0.7697765231132507, |
| "learning_rate": 1.8654645461766941e-06, |
| "loss": 32.6721044921875, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.17424334826018018, |
| "eval_loss": 3.7579221725463867, |
| "eval_runtime": 126.4138, |
| "eval_samples_per_second": 100.891, |
| "eval_steps_per_second": 50.445, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.17772821522538376, |
| "grad_norm": 0.8027380108833313, |
| "learning_rate": 1.5197208928608375e-06, |
| "loss": 31.33625, |
| "step": 1275 |
| }, |
| { |
| "epoch": 0.17772821522538376, |
| "eval_loss": 3.7570292949676514, |
| "eval_runtime": 126.0065, |
| "eval_samples_per_second": 101.217, |
| "eval_steps_per_second": 50.608, |
| "step": 1275 |
| }, |
| { |
| "epoch": 0.18121308219058738, |
| "grad_norm": 0.9305113554000854, |
| "learning_rate": 1.2073239863085644e-06, |
| "loss": 31.53912353515625, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.18121308219058738, |
| "eval_loss": 3.757063627243042, |
| "eval_runtime": 129.7946, |
| "eval_samples_per_second": 98.263, |
| "eval_steps_per_second": 49.131, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.184697949155791, |
| "grad_norm": 0.7605619430541992, |
| "learning_rate": 9.292225656576406e-07, |
| "loss": 31.6432275390625, |
| "step": 1325 |
| }, |
| { |
| "epoch": 0.184697949155791, |
| "eval_loss": 3.7579827308654785, |
| "eval_runtime": 134.7529, |
| "eval_samples_per_second": 94.647, |
| "eval_steps_per_second": 47.324, |
| "step": 1325 |
| }, |
| { |
| "epoch": 0.18818281612099458, |
| "grad_norm": 1.0467506647109985, |
| "learning_rate": 6.862612157823259e-07, |
| "loss": 31.46984619140625, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.18818281612099458, |
| "eval_loss": 3.7580692768096924, |
| "eval_runtime": 137.7265, |
| "eval_samples_per_second": 92.604, |
| "eval_steps_per_second": 46.302, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.1916676830861982, |
| "grad_norm": 0.9806191921234131, |
| "learning_rate": 4.7917780231687e-07, |
| "loss": 31.9260205078125, |
| "step": 1375 |
| }, |
| { |
| "epoch": 0.1916676830861982, |
| "eval_loss": 3.756873369216919, |
| "eval_runtime": 137.2747, |
| "eval_samples_per_second": 92.909, |
| "eval_steps_per_second": 46.454, |
| "step": 1375 |
| }, |
| { |
| "epoch": 0.19515255005140178, |
| "grad_norm": 0.8240782022476196, |
| "learning_rate": 3.0860123078183255e-07, |
| "loss": 31.5154150390625, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.19515255005140178, |
| "eval_loss": 3.7562670707702637, |
| "eval_runtime": 135.5843, |
| "eval_samples_per_second": 94.067, |
| "eval_steps_per_second": 47.033, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.1986374170166054, |
| "grad_norm": 0.7925982475280762, |
| "learning_rate": 1.7504953661868912e-07, |
| "loss": 31.911298828125, |
| "step": 1425 |
| }, |
| { |
| "epoch": 0.1986374170166054, |
| "eval_loss": 3.755851984024048, |
| "eval_runtime": 138.0145, |
| "eval_samples_per_second": 92.411, |
| "eval_steps_per_second": 46.205, |
| "step": 1425 |
| }, |
| { |
| "epoch": 0.20212228398180898, |
| "grad_norm": 0.7086665034294128, |
| "learning_rate": 7.89283119332157e-08, |
| "loss": 32.10687255859375, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.20212228398180898, |
| "eval_loss": 3.7557601928710938, |
| "eval_runtime": 136.786, |
| "eval_samples_per_second": 93.241, |
| "eval_steps_per_second": 46.62, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.2056071509470126, |
| "grad_norm": 0.7362121343612671, |
| "learning_rate": 2.0529473725605652e-08, |
| "loss": 32.00110595703125, |
| "step": 1475 |
| }, |
| { |
| "epoch": 0.2056071509470126, |
| "eval_loss": 3.755723714828491, |
| "eval_runtime": 133.1205, |
| "eval_samples_per_second": 95.808, |
| "eval_steps_per_second": 47.904, |
| "step": 1475 |
| }, |
| { |
| "epoch": 0.2090920179122162, |
| "grad_norm": 0.749195396900177, |
| "learning_rate": 3.0377348117505145e-11, |
| "loss": 31.84532470703125, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.2090920179122162, |
| "eval_loss": 3.755718469619751, |
| "eval_runtime": 128.4402, |
| "eval_samples_per_second": 99.299, |
| "eval_steps_per_second": 49.65, |
| "step": 1500 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 1500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 750, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1149555179520000.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
