| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.2011313639220616, |
| "eval_steps": 160, |
| "global_step": 320, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0006285355122564425, |
| "grad_norm": 2.96633243560791, |
| "learning_rate": 0.0, |
| "loss": 7.5468, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0006285355122564425, |
| "eval_loss": 7.076071739196777, |
| "eval_runtime": 1556.6109, |
| "eval_samples_per_second": 1.656, |
| "eval_steps_per_second": 1.656, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.001257071024512885, |
| "grad_norm": 2.7123501300811768, |
| "learning_rate": 4.0000000000000003e-07, |
| "loss": 6.3309, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0018856065367693275, |
| "grad_norm": 2.4243223667144775, |
| "learning_rate": 8.000000000000001e-07, |
| "loss": 6.7763, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.00251414204902577, |
| "grad_norm": 2.319216728210449, |
| "learning_rate": 1.2000000000000002e-06, |
| "loss": 6.8187, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0031426775612822125, |
| "grad_norm": 2.4935989379882812, |
| "learning_rate": 1.6000000000000001e-06, |
| "loss": 7.0526, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.003771213073538655, |
| "grad_norm": 2.1718926429748535, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 6.7646, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.0043997485857950975, |
| "grad_norm": 2.177217960357666, |
| "learning_rate": 2.4000000000000003e-06, |
| "loss": 6.6131, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.00502828409805154, |
| "grad_norm": 2.9915874004364014, |
| "learning_rate": 2.8000000000000003e-06, |
| "loss": 7.6544, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.0056568196103079825, |
| "grad_norm": 2.6981074810028076, |
| "learning_rate": 3.2000000000000003e-06, |
| "loss": 6.799, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.006285355122564425, |
| "grad_norm": 4.512426376342773, |
| "learning_rate": 3.6e-06, |
| "loss": 8.3895, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0069138906348208675, |
| "grad_norm": 2.3968913555145264, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 6.3478, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.00754242614707731, |
| "grad_norm": 1.9744027853012085, |
| "learning_rate": 4.4e-06, |
| "loss": 5.5536, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.008170961659333752, |
| "grad_norm": 3.050507068634033, |
| "learning_rate": 4.800000000000001e-06, |
| "loss": 6.5491, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.008799497171590195, |
| "grad_norm": 3.0034799575805664, |
| "learning_rate": 5.2e-06, |
| "loss": 7.2764, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.009428032683846637, |
| "grad_norm": 2.323613405227661, |
| "learning_rate": 5.600000000000001e-06, |
| "loss": 6.8805, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.01005656819610308, |
| "grad_norm": 3.129593849182129, |
| "learning_rate": 6e-06, |
| "loss": 7.3171, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.010685103708359522, |
| "grad_norm": 2.296137571334839, |
| "learning_rate": 6.4000000000000006e-06, |
| "loss": 6.4251, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.011313639220615965, |
| "grad_norm": 2.637282133102417, |
| "learning_rate": 6.800000000000001e-06, |
| "loss": 6.6142, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.011942174732872407, |
| "grad_norm": 2.1313271522521973, |
| "learning_rate": 7.2e-06, |
| "loss": 6.3841, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.01257071024512885, |
| "grad_norm": 2.7492284774780273, |
| "learning_rate": 7.6e-06, |
| "loss": 6.8148, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.013199245757385292, |
| "grad_norm": 2.945878267288208, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 6.9732, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.013827781269641735, |
| "grad_norm": 3.709951162338257, |
| "learning_rate": 8.400000000000001e-06, |
| "loss": 7.7273, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.014456316781898177, |
| "grad_norm": 3.023289203643799, |
| "learning_rate": 8.8e-06, |
| "loss": 7.0649, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.01508485229415462, |
| "grad_norm": 3.163715124130249, |
| "learning_rate": 9.2e-06, |
| "loss": 6.9342, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.01571338780641106, |
| "grad_norm": 4.114445686340332, |
| "learning_rate": 9.600000000000001e-06, |
| "loss": 8.119, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.016341923318667503, |
| "grad_norm": 3.021068572998047, |
| "learning_rate": 1e-05, |
| "loss": 7.4067, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.01697045883092395, |
| "grad_norm": 3.724407911300659, |
| "learning_rate": 1.04e-05, |
| "loss": 7.3869, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.01759899434318039, |
| "grad_norm": 2.656257390975952, |
| "learning_rate": 1.08e-05, |
| "loss": 5.9961, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.018227529855436832, |
| "grad_norm": 2.7785143852233887, |
| "learning_rate": 1.1200000000000001e-05, |
| "loss": 5.6596, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.018856065367693273, |
| "grad_norm": 3.130934715270996, |
| "learning_rate": 1.16e-05, |
| "loss": 6.6092, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.01948460087994972, |
| "grad_norm": 3.42301869392395, |
| "learning_rate": 1.2e-05, |
| "loss": 6.3373, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.02011313639220616, |
| "grad_norm": 2.8691611289978027, |
| "learning_rate": 1.24e-05, |
| "loss": 6.5923, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.020741671904462602, |
| "grad_norm": 2.917086601257324, |
| "learning_rate": 1.2800000000000001e-05, |
| "loss": 5.9773, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.021370207416719043, |
| "grad_norm": 4.07196044921875, |
| "learning_rate": 1.32e-05, |
| "loss": 7.4423, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.02199874292897549, |
| "grad_norm": 4.738312244415283, |
| "learning_rate": 1.3600000000000002e-05, |
| "loss": 7.5113, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.02262727844123193, |
| "grad_norm": 3.898664712905884, |
| "learning_rate": 1.4000000000000001e-05, |
| "loss": 6.8738, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.023255813953488372, |
| "grad_norm": 3.7448792457580566, |
| "learning_rate": 1.44e-05, |
| "loss": 6.9615, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.023884349465744813, |
| "grad_norm": 3.5938379764556885, |
| "learning_rate": 1.48e-05, |
| "loss": 6.0651, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.02451288497800126, |
| "grad_norm": 4.253636360168457, |
| "learning_rate": 1.52e-05, |
| "loss": 6.9986, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.0251414204902577, |
| "grad_norm": 4.985451698303223, |
| "learning_rate": 1.56e-05, |
| "loss": 7.252, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.025769956002514142, |
| "grad_norm": 4.376275062561035, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 6.8091, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.026398491514770583, |
| "grad_norm": 4.697645664215088, |
| "learning_rate": 1.6400000000000002e-05, |
| "loss": 6.4319, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.02702702702702703, |
| "grad_norm": 5.258227348327637, |
| "learning_rate": 1.6800000000000002e-05, |
| "loss": 6.7672, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.02765556253928347, |
| "grad_norm": 5.063000679016113, |
| "learning_rate": 1.7199999999999998e-05, |
| "loss": 6.3354, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.028284098051539912, |
| "grad_norm": 4.573636531829834, |
| "learning_rate": 1.76e-05, |
| "loss": 6.3374, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.028912633563796353, |
| "grad_norm": 4.72340202331543, |
| "learning_rate": 1.8e-05, |
| "loss": 6.6553, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.0295411690760528, |
| "grad_norm": 6.681248664855957, |
| "learning_rate": 1.84e-05, |
| "loss": 7.7157, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.03016970458830924, |
| "grad_norm": 5.952408313751221, |
| "learning_rate": 1.88e-05, |
| "loss": 5.8215, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.030798240100565682, |
| "grad_norm": 6.599308967590332, |
| "learning_rate": 1.9200000000000003e-05, |
| "loss": 6.921, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.03142677561282212, |
| "grad_norm": 6.538867473602295, |
| "learning_rate": 1.9600000000000002e-05, |
| "loss": 7.1274, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.03205531112507857, |
| "grad_norm": 5.91294527053833, |
| "learning_rate": 2e-05, |
| "loss": 6.7263, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.03268384663733501, |
| "grad_norm": 7.943373203277588, |
| "learning_rate": 2.04e-05, |
| "loss": 7.4335, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.03331238214959145, |
| "grad_norm": 7.023540496826172, |
| "learning_rate": 2.08e-05, |
| "loss": 6.3428, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.0339409176618479, |
| "grad_norm": 7.031850814819336, |
| "learning_rate": 2.12e-05, |
| "loss": 6.2423, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.034569453174104335, |
| "grad_norm": 6.891653537750244, |
| "learning_rate": 2.16e-05, |
| "loss": 6.4081, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.03519798868636078, |
| "grad_norm": 8.165786743164062, |
| "learning_rate": 2.2000000000000003e-05, |
| "loss": 7.1081, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.035826524198617225, |
| "grad_norm": 9.146330833435059, |
| "learning_rate": 2.2400000000000002e-05, |
| "loss": 7.4309, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.036455059710873663, |
| "grad_norm": 8.637526512145996, |
| "learning_rate": 2.2800000000000002e-05, |
| "loss": 6.9889, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.03708359522313011, |
| "grad_norm": 8.397353172302246, |
| "learning_rate": 2.32e-05, |
| "loss": 5.8222, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.03771213073538655, |
| "grad_norm": 9.219857215881348, |
| "learning_rate": 2.36e-05, |
| "loss": 7.0839, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.03834066624764299, |
| "grad_norm": 8.762686729431152, |
| "learning_rate": 2.4e-05, |
| "loss": 6.192, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.03896920175989944, |
| "grad_norm": 9.55370044708252, |
| "learning_rate": 2.44e-05, |
| "loss": 6.2674, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.039597737272155875, |
| "grad_norm": 10.248711585998535, |
| "learning_rate": 2.48e-05, |
| "loss": 7.4737, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.04022627278441232, |
| "grad_norm": 9.455551147460938, |
| "learning_rate": 2.5200000000000003e-05, |
| "loss": 6.5796, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.04085480829666876, |
| "grad_norm": 10.217570304870605, |
| "learning_rate": 2.5600000000000002e-05, |
| "loss": 6.8329, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.041483343808925204, |
| "grad_norm": 12.418697357177734, |
| "learning_rate": 2.6000000000000002e-05, |
| "loss": 7.0127, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.04211187932118165, |
| "grad_norm": 13.362143516540527, |
| "learning_rate": 2.64e-05, |
| "loss": 6.3027, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.04274041483343809, |
| "grad_norm": 10.577826499938965, |
| "learning_rate": 2.6800000000000004e-05, |
| "loss": 6.2406, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.04336895034569453, |
| "grad_norm": 13.15530776977539, |
| "learning_rate": 2.7200000000000004e-05, |
| "loss": 7.3093, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.04399748585795098, |
| "grad_norm": 10.775976181030273, |
| "learning_rate": 2.7600000000000003e-05, |
| "loss": 5.9398, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.044626021370207415, |
| "grad_norm": 12.925591468811035, |
| "learning_rate": 2.8000000000000003e-05, |
| "loss": 6.7144, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.04525455688246386, |
| "grad_norm": 12.626113891601562, |
| "learning_rate": 2.84e-05, |
| "loss": 6.5783, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.0458830923947203, |
| "grad_norm": 14.04005241394043, |
| "learning_rate": 2.88e-05, |
| "loss": 6.1111, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.046511627906976744, |
| "grad_norm": 14.279847145080566, |
| "learning_rate": 2.9199999999999998e-05, |
| "loss": 5.7717, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.04714016341923319, |
| "grad_norm": 13.597288131713867, |
| "learning_rate": 2.96e-05, |
| "loss": 6.7714, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.04776869893148963, |
| "grad_norm": 12.93455696105957, |
| "learning_rate": 3e-05, |
| "loss": 6.5082, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.04839723444374607, |
| "grad_norm": 12.823902130126953, |
| "learning_rate": 3.04e-05, |
| "loss": 6.7108, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.04902576995600252, |
| "grad_norm": 16.93589973449707, |
| "learning_rate": 3.08e-05, |
| "loss": 6.2773, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.049654305468258955, |
| "grad_norm": 14.550610542297363, |
| "learning_rate": 3.12e-05, |
| "loss": 6.4329, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.0502828409805154, |
| "grad_norm": 11.992222785949707, |
| "learning_rate": 3.16e-05, |
| "loss": 5.3369, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.05091137649277184, |
| "grad_norm": 12.921990394592285, |
| "learning_rate": 3.2000000000000005e-05, |
| "loss": 5.8783, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.051539912005028284, |
| "grad_norm": 14.483002662658691, |
| "learning_rate": 3.24e-05, |
| "loss": 7.4091, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.05216844751728473, |
| "grad_norm": 15.877086639404297, |
| "learning_rate": 3.2800000000000004e-05, |
| "loss": 6.9743, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.05279698302954117, |
| "grad_norm": 15.85240650177002, |
| "learning_rate": 3.32e-05, |
| "loss": 7.0001, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.05342551854179761, |
| "grad_norm": 17.0369815826416, |
| "learning_rate": 3.3600000000000004e-05, |
| "loss": 5.8022, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.05405405405405406, |
| "grad_norm": 15.62733268737793, |
| "learning_rate": 3.4000000000000007e-05, |
| "loss": 6.8172, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.054682589566310495, |
| "grad_norm": 18.79668426513672, |
| "learning_rate": 3.4399999999999996e-05, |
| "loss": 6.6659, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.05531112507856694, |
| "grad_norm": 15.78856086730957, |
| "learning_rate": 3.48e-05, |
| "loss": 5.7255, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.05593966059082338, |
| "grad_norm": 13.196313858032227, |
| "learning_rate": 3.52e-05, |
| "loss": 5.8423, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.056568196103079824, |
| "grad_norm": 16.4498233795166, |
| "learning_rate": 3.56e-05, |
| "loss": 5.4969, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.05719673161533627, |
| "grad_norm": 15.243169784545898, |
| "learning_rate": 3.6e-05, |
| "loss": 6.0186, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.05782526712759271, |
| "grad_norm": 17.294044494628906, |
| "learning_rate": 3.6400000000000004e-05, |
| "loss": 6.8408, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.05845380263984915, |
| "grad_norm": 19.32530975341797, |
| "learning_rate": 3.68e-05, |
| "loss": 6.5562, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.0590823381521056, |
| "grad_norm": 20.01514434814453, |
| "learning_rate": 3.72e-05, |
| "loss": 6.4273, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.059710873664362035, |
| "grad_norm": 19.90467643737793, |
| "learning_rate": 3.76e-05, |
| "loss": 7.2277, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.06033940917661848, |
| "grad_norm": 17.582975387573242, |
| "learning_rate": 3.8e-05, |
| "loss": 7.0173, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.06096794468887492, |
| "grad_norm": 17.471969604492188, |
| "learning_rate": 3.8400000000000005e-05, |
| "loss": 6.6919, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.061596480201131364, |
| "grad_norm": 16.06781005859375, |
| "learning_rate": 3.88e-05, |
| "loss": 6.54, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.06222501571338781, |
| "grad_norm": 17.99164390563965, |
| "learning_rate": 3.9200000000000004e-05, |
| "loss": 5.9168, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.06285355122564425, |
| "grad_norm": 16.01885986328125, |
| "learning_rate": 3.960000000000001e-05, |
| "loss": 5.9236, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.06348208673790069, |
| "grad_norm": 9.705466270446777, |
| "learning_rate": 4e-05, |
| "loss": 4.4168, |
| "step": 101 |
| }, |
| { |
| "epoch": 0.06411062225015714, |
| "grad_norm": 21.02065086364746, |
| "learning_rate": 4.0400000000000006e-05, |
| "loss": 6.7312, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.06473915776241358, |
| "grad_norm": 16.56360626220703, |
| "learning_rate": 4.08e-05, |
| "loss": 6.5865, |
| "step": 103 |
| }, |
| { |
| "epoch": 0.06536769327467001, |
| "grad_norm": 17.319807052612305, |
| "learning_rate": 4.12e-05, |
| "loss": 6.4122, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.06599622878692646, |
| "grad_norm": 21.3114070892334, |
| "learning_rate": 4.16e-05, |
| "loss": 6.9886, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.0666247642991829, |
| "grad_norm": 21.147327423095703, |
| "learning_rate": 4.2e-05, |
| "loss": 6.7595, |
| "step": 106 |
| }, |
| { |
| "epoch": 0.06725329981143935, |
| "grad_norm": 16.264938354492188, |
| "learning_rate": 4.24e-05, |
| "loss": 6.114, |
| "step": 107 |
| }, |
| { |
| "epoch": 0.0678818353236958, |
| "grad_norm": 20.424713134765625, |
| "learning_rate": 4.2800000000000004e-05, |
| "loss": 6.9508, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.06851037083595223, |
| "grad_norm": 19.48565673828125, |
| "learning_rate": 4.32e-05, |
| "loss": 6.7488, |
| "step": 109 |
| }, |
| { |
| "epoch": 0.06913890634820867, |
| "grad_norm": 17.111894607543945, |
| "learning_rate": 4.36e-05, |
| "loss": 6.5613, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.06976744186046512, |
| "grad_norm": 14.604440689086914, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 6.0278, |
| "step": 111 |
| }, |
| { |
| "epoch": 0.07039597737272156, |
| "grad_norm": 19.691083908081055, |
| "learning_rate": 4.44e-05, |
| "loss": 6.6524, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.071024512884978, |
| "grad_norm": 20.216869354248047, |
| "learning_rate": 4.4800000000000005e-05, |
| "loss": 7.1919, |
| "step": 113 |
| }, |
| { |
| "epoch": 0.07165304839723445, |
| "grad_norm": 12.34801197052002, |
| "learning_rate": 4.52e-05, |
| "loss": 5.8613, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.07228158390949088, |
| "grad_norm": 10.295191764831543, |
| "learning_rate": 4.5600000000000004e-05, |
| "loss": 5.2475, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.07291011942174733, |
| "grad_norm": 15.049263954162598, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 6.1295, |
| "step": 116 |
| }, |
| { |
| "epoch": 0.07353865493400377, |
| "grad_norm": 12.287694931030273, |
| "learning_rate": 4.64e-05, |
| "loss": 5.7615, |
| "step": 117 |
| }, |
| { |
| "epoch": 0.07416719044626022, |
| "grad_norm": 12.11177921295166, |
| "learning_rate": 4.6800000000000006e-05, |
| "loss": 5.8763, |
| "step": 118 |
| }, |
| { |
| "epoch": 0.07479572595851666, |
| "grad_norm": 11.103803634643555, |
| "learning_rate": 4.72e-05, |
| "loss": 5.5072, |
| "step": 119 |
| }, |
| { |
| "epoch": 0.0754242614707731, |
| "grad_norm": 10.065237998962402, |
| "learning_rate": 4.76e-05, |
| "loss": 5.4734, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.07605279698302954, |
| "grad_norm": 15.039546012878418, |
| "learning_rate": 4.8e-05, |
| "loss": 6.2005, |
| "step": 121 |
| }, |
| { |
| "epoch": 0.07668133249528598, |
| "grad_norm": 10.25068473815918, |
| "learning_rate": 4.8400000000000004e-05, |
| "loss": 5.4703, |
| "step": 122 |
| }, |
| { |
| "epoch": 0.07730986800754243, |
| "grad_norm": 13.106711387634277, |
| "learning_rate": 4.88e-05, |
| "loss": 6.6926, |
| "step": 123 |
| }, |
| { |
| "epoch": 0.07793840351979887, |
| "grad_norm": 7.927108287811279, |
| "learning_rate": 4.92e-05, |
| "loss": 5.3666, |
| "step": 124 |
| }, |
| { |
| "epoch": 0.0785669390320553, |
| "grad_norm": 10.937745094299316, |
| "learning_rate": 4.96e-05, |
| "loss": 6.1474, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.07919547454431175, |
| "grad_norm": 10.88867473602295, |
| "learning_rate": 5e-05, |
| "loss": 6.1572, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.0798240100565682, |
| "grad_norm": 11.629264831542969, |
| "learning_rate": 5.0400000000000005e-05, |
| "loss": 6.391, |
| "step": 127 |
| }, |
| { |
| "epoch": 0.08045254556882464, |
| "grad_norm": 10.296239852905273, |
| "learning_rate": 5.08e-05, |
| "loss": 5.9652, |
| "step": 128 |
| }, |
| { |
| "epoch": 0.08108108108108109, |
| "grad_norm": 11.038286209106445, |
| "learning_rate": 5.1200000000000004e-05, |
| "loss": 6.1295, |
| "step": 129 |
| }, |
| { |
| "epoch": 0.08170961659333752, |
| "grad_norm": 9.234803199768066, |
| "learning_rate": 5.16e-05, |
| "loss": 5.796, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.08233815210559396, |
| "grad_norm": 8.689288139343262, |
| "learning_rate": 5.2000000000000004e-05, |
| "loss": 5.3704, |
| "step": 131 |
| }, |
| { |
| "epoch": 0.08296668761785041, |
| "grad_norm": 15.41921615600586, |
| "learning_rate": 5.2400000000000007e-05, |
| "loss": 6.0926, |
| "step": 132 |
| }, |
| { |
| "epoch": 0.08359522313010685, |
| "grad_norm": 8.419554710388184, |
| "learning_rate": 5.28e-05, |
| "loss": 5.8071, |
| "step": 133 |
| }, |
| { |
| "epoch": 0.0842237586423633, |
| "grad_norm": 8.644979476928711, |
| "learning_rate": 5.3200000000000006e-05, |
| "loss": 5.9138, |
| "step": 134 |
| }, |
| { |
| "epoch": 0.08485229415461974, |
| "grad_norm": 11.236026763916016, |
| "learning_rate": 5.360000000000001e-05, |
| "loss": 5.9092, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.08548082966687617, |
| "grad_norm": 9.669437408447266, |
| "learning_rate": 5.4000000000000005e-05, |
| "loss": 5.3778, |
| "step": 136 |
| }, |
| { |
| "epoch": 0.08610936517913262, |
| "grad_norm": 10.624286651611328, |
| "learning_rate": 5.440000000000001e-05, |
| "loss": 5.4098, |
| "step": 137 |
| }, |
| { |
| "epoch": 0.08673790069138906, |
| "grad_norm": 8.831917762756348, |
| "learning_rate": 5.4800000000000004e-05, |
| "loss": 5.3806, |
| "step": 138 |
| }, |
| { |
| "epoch": 0.08736643620364551, |
| "grad_norm": 8.536581993103027, |
| "learning_rate": 5.520000000000001e-05, |
| "loss": 5.9237, |
| "step": 139 |
| }, |
| { |
| "epoch": 0.08799497171590195, |
| "grad_norm": 7.873721599578857, |
| "learning_rate": 5.560000000000001e-05, |
| "loss": 5.423, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.08862350722815839, |
| "grad_norm": 8.635188102722168, |
| "learning_rate": 5.6000000000000006e-05, |
| "loss": 5.6118, |
| "step": 141 |
| }, |
| { |
| "epoch": 0.08925204274041483, |
| "grad_norm": 13.39542293548584, |
| "learning_rate": 5.6399999999999995e-05, |
| "loss": 5.2728, |
| "step": 142 |
| }, |
| { |
| "epoch": 0.08988057825267128, |
| "grad_norm": 12.998862266540527, |
| "learning_rate": 5.68e-05, |
| "loss": 6.9434, |
| "step": 143 |
| }, |
| { |
| "epoch": 0.09050911376492772, |
| "grad_norm": 8.149964332580566, |
| "learning_rate": 5.72e-05, |
| "loss": 5.3559, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.09113764927718417, |
| "grad_norm": 7.66946268081665, |
| "learning_rate": 5.76e-05, |
| "loss": 5.5603, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.0917661847894406, |
| "grad_norm": 9.277702331542969, |
| "learning_rate": 5.8e-05, |
| "loss": 4.9751, |
| "step": 146 |
| }, |
| { |
| "epoch": 0.09239472030169704, |
| "grad_norm": 7.442458152770996, |
| "learning_rate": 5.8399999999999997e-05, |
| "loss": 5.1653, |
| "step": 147 |
| }, |
| { |
| "epoch": 0.09302325581395349, |
| "grad_norm": 8.340120315551758, |
| "learning_rate": 5.88e-05, |
| "loss": 5.5422, |
| "step": 148 |
| }, |
| { |
| "epoch": 0.09365179132620993, |
| "grad_norm": 6.774919033050537, |
| "learning_rate": 5.92e-05, |
| "loss": 5.0187, |
| "step": 149 |
| }, |
| { |
| "epoch": 0.09428032683846638, |
| "grad_norm": 8.363201141357422, |
| "learning_rate": 5.96e-05, |
| "loss": 4.9803, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.09490886235072282, |
| "grad_norm": 7.182234764099121, |
| "learning_rate": 6e-05, |
| "loss": 5.2913, |
| "step": 151 |
| }, |
| { |
| "epoch": 0.09553739786297925, |
| "grad_norm": 9.065616607666016, |
| "learning_rate": 6.04e-05, |
| "loss": 5.8604, |
| "step": 152 |
| }, |
| { |
| "epoch": 0.0961659333752357, |
| "grad_norm": 7.823053359985352, |
| "learning_rate": 6.08e-05, |
| "loss": 5.7326, |
| "step": 153 |
| }, |
| { |
| "epoch": 0.09679446888749214, |
| "grad_norm": 8.177785873413086, |
| "learning_rate": 6.12e-05, |
| "loss": 5.5663, |
| "step": 154 |
| }, |
| { |
| "epoch": 0.09742300439974859, |
| "grad_norm": 8.24718952178955, |
| "learning_rate": 6.16e-05, |
| "loss": 5.5606, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.09805153991200503, |
| "grad_norm": 10.260727882385254, |
| "learning_rate": 6.2e-05, |
| "loss": 5.7043, |
| "step": 156 |
| }, |
| { |
| "epoch": 0.09868007542426147, |
| "grad_norm": 11.80507755279541, |
| "learning_rate": 6.24e-05, |
| "loss": 6.0268, |
| "step": 157 |
| }, |
| { |
| "epoch": 0.09930861093651791, |
| "grad_norm": 9.024588584899902, |
| "learning_rate": 6.280000000000001e-05, |
| "loss": 6.2249, |
| "step": 158 |
| }, |
| { |
| "epoch": 0.09993714644877436, |
| "grad_norm": 6.814016342163086, |
| "learning_rate": 6.32e-05, |
| "loss": 5.0123, |
| "step": 159 |
| }, |
| { |
| "epoch": 0.1005656819610308, |
| "grad_norm": 6.701868534088135, |
| "learning_rate": 6.36e-05, |
| "loss": 4.9993, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.1005656819610308, |
| "eval_loss": 5.605074882507324, |
| "eval_runtime": 1565.1736, |
| "eval_samples_per_second": 1.647, |
| "eval_steps_per_second": 1.647, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.10119421747328725, |
| "grad_norm": 14.352143287658691, |
| "learning_rate": 6.400000000000001e-05, |
| "loss": 5.8635, |
| "step": 161 |
| }, |
| { |
| "epoch": 0.10182275298554368, |
| "grad_norm": 7.681995868682861, |
| "learning_rate": 6.440000000000001e-05, |
| "loss": 5.2773, |
| "step": 162 |
| }, |
| { |
| "epoch": 0.10245128849780012, |
| "grad_norm": 10.032212257385254, |
| "learning_rate": 6.48e-05, |
| "loss": 5.4718, |
| "step": 163 |
| }, |
| { |
| "epoch": 0.10307982401005657, |
| "grad_norm": 6.617798805236816, |
| "learning_rate": 6.52e-05, |
| "loss": 4.7259, |
| "step": 164 |
| }, |
| { |
| "epoch": 0.10370835952231301, |
| "grad_norm": 7.318296432495117, |
| "learning_rate": 6.560000000000001e-05, |
| "loss": 4.9979, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.10433689503456946, |
| "grad_norm": 9.494800567626953, |
| "learning_rate": 6.6e-05, |
| "loss": 5.4222, |
| "step": 166 |
| }, |
| { |
| "epoch": 0.1049654305468259, |
| "grad_norm": 6.2663798332214355, |
| "learning_rate": 6.64e-05, |
| "loss": 4.806, |
| "step": 167 |
| }, |
| { |
| "epoch": 0.10559396605908233, |
| "grad_norm": 7.666187286376953, |
| "learning_rate": 6.680000000000001e-05, |
| "loss": 5.583, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.10622250157133878, |
| "grad_norm": 6.545588493347168, |
| "learning_rate": 6.720000000000001e-05, |
| "loss": 5.4927, |
| "step": 169 |
| }, |
| { |
| "epoch": 0.10685103708359522, |
| "grad_norm": 7.650016784667969, |
| "learning_rate": 6.76e-05, |
| "loss": 5.6347, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.10747957259585167, |
| "grad_norm": 6.05757474899292, |
| "learning_rate": 6.800000000000001e-05, |
| "loss": 4.8323, |
| "step": 171 |
| }, |
| { |
| "epoch": 0.10810810810810811, |
| "grad_norm": 8.37306022644043, |
| "learning_rate": 6.840000000000001e-05, |
| "loss": 5.5312, |
| "step": 172 |
| }, |
| { |
| "epoch": 0.10873664362036455, |
| "grad_norm": 6.950132369995117, |
| "learning_rate": 6.879999999999999e-05, |
| "loss": 5.216, |
| "step": 173 |
| }, |
| { |
| "epoch": 0.10936517913262099, |
| "grad_norm": 7.643744945526123, |
| "learning_rate": 6.92e-05, |
| "loss": 5.374, |
| "step": 174 |
| }, |
| { |
| "epoch": 0.10999371464487744, |
| "grad_norm": 12.621402740478516, |
| "learning_rate": 6.96e-05, |
| "loss": 6.3553, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.11062225015713388, |
| "grad_norm": 6.861866474151611, |
| "learning_rate": 7e-05, |
| "loss": 5.0186, |
| "step": 176 |
| }, |
| { |
| "epoch": 0.11125078566939033, |
| "grad_norm": 7.023342609405518, |
| "learning_rate": 7.04e-05, |
| "loss": 4.7693, |
| "step": 177 |
| }, |
| { |
| "epoch": 0.11187932118164676, |
| "grad_norm": 7.627071380615234, |
| "learning_rate": 7.08e-05, |
| "loss": 5.5354, |
| "step": 178 |
| }, |
| { |
| "epoch": 0.1125078566939032, |
| "grad_norm": 7.475245952606201, |
| "learning_rate": 7.12e-05, |
| "loss": 5.5916, |
| "step": 179 |
| }, |
| { |
| "epoch": 0.11313639220615965, |
| "grad_norm": 6.348559379577637, |
| "learning_rate": 7.16e-05, |
| "loss": 4.7914, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.11376492771841609, |
| "grad_norm": 6.895409107208252, |
| "learning_rate": 7.2e-05, |
| "loss": 5.4136, |
| "step": 181 |
| }, |
| { |
| "epoch": 0.11439346323067254, |
| "grad_norm": 5.746918201446533, |
| "learning_rate": 7.24e-05, |
| "loss": 4.8071, |
| "step": 182 |
| }, |
| { |
| "epoch": 0.11502199874292897, |
| "grad_norm": 7.965058326721191, |
| "learning_rate": 7.280000000000001e-05, |
| "loss": 4.6486, |
| "step": 183 |
| }, |
| { |
| "epoch": 0.11565053425518541, |
| "grad_norm": 8.059706687927246, |
| "learning_rate": 7.32e-05, |
| "loss": 5.3917, |
| "step": 184 |
| }, |
| { |
| "epoch": 0.11627906976744186, |
| "grad_norm": 7.2255353927612305, |
| "learning_rate": 7.36e-05, |
| "loss": 5.0876, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.1169076052796983, |
| "grad_norm": 6.53950834274292, |
| "learning_rate": 7.4e-05, |
| "loss": 4.7656, |
| "step": 186 |
| }, |
| { |
| "epoch": 0.11753614079195475, |
| "grad_norm": 6.379930019378662, |
| "learning_rate": 7.44e-05, |
| "loss": 4.6405, |
| "step": 187 |
| }, |
| { |
| "epoch": 0.1181646763042112, |
| "grad_norm": 7.332822322845459, |
| "learning_rate": 7.48e-05, |
| "loss": 4.6839, |
| "step": 188 |
| }, |
| { |
| "epoch": 0.11879321181646763, |
| "grad_norm": 7.975095272064209, |
| "learning_rate": 7.52e-05, |
| "loss": 4.8748, |
| "step": 189 |
| }, |
| { |
| "epoch": 0.11942174732872407, |
| "grad_norm": 7.8162360191345215, |
| "learning_rate": 7.560000000000001e-05, |
| "loss": 4.9994, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.12005028284098052, |
| "grad_norm": 7.749350070953369, |
| "learning_rate": 7.6e-05, |
| "loss": 4.7996, |
| "step": 191 |
| }, |
| { |
| "epoch": 0.12067881835323696, |
| "grad_norm": 12.814620018005371, |
| "learning_rate": 7.64e-05, |
| "loss": 5.4858, |
| "step": 192 |
| }, |
| { |
| "epoch": 0.1213073538654934, |
| "grad_norm": 7.985275745391846, |
| "learning_rate": 7.680000000000001e-05, |
| "loss": 4.9178, |
| "step": 193 |
| }, |
| { |
| "epoch": 0.12193588937774984, |
| "grad_norm": 7.037015438079834, |
| "learning_rate": 7.72e-05, |
| "loss": 4.4436, |
| "step": 194 |
| }, |
| { |
| "epoch": 0.12256442489000628, |
| "grad_norm": 12.540748596191406, |
| "learning_rate": 7.76e-05, |
| "loss": 5.3947, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.12319296040226273, |
| "grad_norm": 8.698318481445312, |
| "learning_rate": 7.800000000000001e-05, |
| "loss": 4.6521, |
| "step": 196 |
| }, |
| { |
| "epoch": 0.12382149591451917, |
| "grad_norm": 6.837226867675781, |
| "learning_rate": 7.840000000000001e-05, |
| "loss": 4.4502, |
| "step": 197 |
| }, |
| { |
| "epoch": 0.12445003142677562, |
| "grad_norm": 6.902530670166016, |
| "learning_rate": 7.88e-05, |
| "loss": 5.2111, |
| "step": 198 |
| }, |
| { |
| "epoch": 0.12507856693903205, |
| "grad_norm": 7.714503288269043, |
| "learning_rate": 7.920000000000001e-05, |
| "loss": 4.5983, |
| "step": 199 |
| }, |
| { |
| "epoch": 0.1257071024512885, |
| "grad_norm": 9.488588333129883, |
| "learning_rate": 7.960000000000001e-05, |
| "loss": 5.496, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.12633563796354494, |
| "grad_norm": 9.41787052154541, |
| "learning_rate": 8e-05, |
| "loss": 4.8966, |
| "step": 201 |
| }, |
| { |
| "epoch": 0.12696417347580138, |
| "grad_norm": 7.63663911819458, |
| "learning_rate": 8.04e-05, |
| "loss": 4.6692, |
| "step": 202 |
| }, |
| { |
| "epoch": 0.12759270898805783, |
| "grad_norm": 8.535087585449219, |
| "learning_rate": 8.080000000000001e-05, |
| "loss": 5.0543, |
| "step": 203 |
| }, |
| { |
| "epoch": 0.12822124450031427, |
| "grad_norm": 8.822395324707031, |
| "learning_rate": 8.120000000000001e-05, |
| "loss": 4.7249, |
| "step": 204 |
| }, |
| { |
| "epoch": 0.12884978001257072, |
| "grad_norm": 7.7394561767578125, |
| "learning_rate": 8.16e-05, |
| "loss": 4.5474, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.12947831552482716, |
| "grad_norm": 9.459196090698242, |
| "learning_rate": 8.2e-05, |
| "loss": 5.3748, |
| "step": 206 |
| }, |
| { |
| "epoch": 0.13010685103708358, |
| "grad_norm": 6.900613784790039, |
| "learning_rate": 8.24e-05, |
| "loss": 4.5716, |
| "step": 207 |
| }, |
| { |
| "epoch": 0.13073538654934003, |
| "grad_norm": 7.961105823516846, |
| "learning_rate": 8.28e-05, |
| "loss": 4.5067, |
| "step": 208 |
| }, |
| { |
| "epoch": 0.13136392206159647, |
| "grad_norm": 10.71306037902832, |
| "learning_rate": 8.32e-05, |
| "loss": 4.8309, |
| "step": 209 |
| }, |
| { |
| "epoch": 0.13199245757385292, |
| "grad_norm": 8.900117874145508, |
| "learning_rate": 8.36e-05, |
| "loss": 5.0913, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.13262099308610936, |
| "grad_norm": 9.863144874572754, |
| "learning_rate": 8.4e-05, |
| "loss": 4.9469, |
| "step": 211 |
| }, |
| { |
| "epoch": 0.1332495285983658, |
| "grad_norm": 7.620909690856934, |
| "learning_rate": 8.44e-05, |
| "loss": 4.484, |
| "step": 212 |
| }, |
| { |
| "epoch": 0.13387806411062225, |
| "grad_norm": 10.667424201965332, |
| "learning_rate": 8.48e-05, |
| "loss": 5.1474, |
| "step": 213 |
| }, |
| { |
| "epoch": 0.1345065996228787, |
| "grad_norm": 11.249619483947754, |
| "learning_rate": 8.52e-05, |
| "loss": 4.6222, |
| "step": 214 |
| }, |
| { |
| "epoch": 0.13513513513513514, |
| "grad_norm": 8.625935554504395, |
| "learning_rate": 8.560000000000001e-05, |
| "loss": 4.4776, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.1357636706473916, |
| "grad_norm": 8.138617515563965, |
| "learning_rate": 8.6e-05, |
| "loss": 4.7134, |
| "step": 216 |
| }, |
| { |
| "epoch": 0.13639220615964803, |
| "grad_norm": 7.485641956329346, |
| "learning_rate": 8.64e-05, |
| "loss": 4.8201, |
| "step": 217 |
| }, |
| { |
| "epoch": 0.13702074167190445, |
| "grad_norm": 11.87485408782959, |
| "learning_rate": 8.680000000000001e-05, |
| "loss": 4.7288, |
| "step": 218 |
| }, |
| { |
| "epoch": 0.1376492771841609, |
| "grad_norm": 8.551025390625, |
| "learning_rate": 8.72e-05, |
| "loss": 4.3091, |
| "step": 219 |
| }, |
| { |
| "epoch": 0.13827781269641734, |
| "grad_norm": 10.597816467285156, |
| "learning_rate": 8.76e-05, |
| "loss": 4.9491, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.13890634820867379, |
| "grad_norm": 84.34934997558594, |
| "learning_rate": 8.800000000000001e-05, |
| "loss": 7.8641, |
| "step": 221 |
| }, |
| { |
| "epoch": 0.13953488372093023, |
| "grad_norm": 14.08538818359375, |
| "learning_rate": 8.840000000000001e-05, |
| "loss": 5.1718, |
| "step": 222 |
| }, |
| { |
| "epoch": 0.14016341923318668, |
| "grad_norm": 8.5634183883667, |
| "learning_rate": 8.88e-05, |
| "loss": 4.5042, |
| "step": 223 |
| }, |
| { |
| "epoch": 0.14079195474544312, |
| "grad_norm": 9.070499420166016, |
| "learning_rate": 8.92e-05, |
| "loss": 4.684, |
| "step": 224 |
| }, |
| { |
| "epoch": 0.14142049025769957, |
| "grad_norm": 13.369037628173828, |
| "learning_rate": 8.960000000000001e-05, |
| "loss": 4.2649, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.142049025769956, |
| "grad_norm": 8.797863960266113, |
| "learning_rate": 9e-05, |
| "loss": 4.0673, |
| "step": 226 |
| }, |
| { |
| "epoch": 0.14267756128221246, |
| "grad_norm": 11.846273422241211, |
| "learning_rate": 9.04e-05, |
| "loss": 4.3157, |
| "step": 227 |
| }, |
| { |
| "epoch": 0.1433060967944689, |
| "grad_norm": 9.263139724731445, |
| "learning_rate": 9.080000000000001e-05, |
| "loss": 4.2926, |
| "step": 228 |
| }, |
| { |
| "epoch": 0.14393463230672532, |
| "grad_norm": 6.980598449707031, |
| "learning_rate": 9.120000000000001e-05, |
| "loss": 4.5284, |
| "step": 229 |
| }, |
| { |
| "epoch": 0.14456316781898176, |
| "grad_norm": 7.539294719696045, |
| "learning_rate": 9.16e-05, |
| "loss": 4.0574, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.1451917033312382, |
| "grad_norm": 10.551584243774414, |
| "learning_rate": 9.200000000000001e-05, |
| "loss": 4.8214, |
| "step": 231 |
| }, |
| { |
| "epoch": 0.14582023884349465, |
| "grad_norm": 8.377208709716797, |
| "learning_rate": 9.240000000000001e-05, |
| "loss": 4.1492, |
| "step": 232 |
| }, |
| { |
| "epoch": 0.1464487743557511, |
| "grad_norm": 8.809621810913086, |
| "learning_rate": 9.28e-05, |
| "loss": 3.9481, |
| "step": 233 |
| }, |
| { |
| "epoch": 0.14707730986800754, |
| "grad_norm": 15.098812103271484, |
| "learning_rate": 9.320000000000002e-05, |
| "loss": 4.5192, |
| "step": 234 |
| }, |
| { |
| "epoch": 0.147705845380264, |
| "grad_norm": 16.269895553588867, |
| "learning_rate": 9.360000000000001e-05, |
| "loss": 4.5962, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.14833438089252043, |
| "grad_norm": 9.021276473999023, |
| "learning_rate": 9.4e-05, |
| "loss": 4.6729, |
| "step": 236 |
| }, |
| { |
| "epoch": 0.14896291640477688, |
| "grad_norm": 10.110734939575195, |
| "learning_rate": 9.44e-05, |
| "loss": 4.5957, |
| "step": 237 |
| }, |
| { |
| "epoch": 0.14959145191703332, |
| "grad_norm": 10.254793167114258, |
| "learning_rate": 9.48e-05, |
| "loss": 4.1534, |
| "step": 238 |
| }, |
| { |
| "epoch": 0.15021998742928974, |
| "grad_norm": 10.400528907775879, |
| "learning_rate": 9.52e-05, |
| "loss": 4.5035, |
| "step": 239 |
| }, |
| { |
| "epoch": 0.1508485229415462, |
| "grad_norm": 13.529309272766113, |
| "learning_rate": 9.56e-05, |
| "loss": 4.7124, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.15147705845380263, |
| "grad_norm": 9.187389373779297, |
| "learning_rate": 9.6e-05, |
| "loss": 4.2564, |
| "step": 241 |
| }, |
| { |
| "epoch": 0.15210559396605908, |
| "grad_norm": 9.760189056396484, |
| "learning_rate": 9.64e-05, |
| "loss": 4.5863, |
| "step": 242 |
| }, |
| { |
| "epoch": 0.15273412947831552, |
| "grad_norm": 11.033064842224121, |
| "learning_rate": 9.680000000000001e-05, |
| "loss": 4.4069, |
| "step": 243 |
| }, |
| { |
| "epoch": 0.15336266499057197, |
| "grad_norm": 8.79299259185791, |
| "learning_rate": 9.72e-05, |
| "loss": 4.2232, |
| "step": 244 |
| }, |
| { |
| "epoch": 0.1539912005028284, |
| "grad_norm": 10.526970863342285, |
| "learning_rate": 9.76e-05, |
| "loss": 4.6675, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.15461973601508486, |
| "grad_norm": 14.993115425109863, |
| "learning_rate": 9.8e-05, |
| "loss": 4.3974, |
| "step": 246 |
| }, |
| { |
| "epoch": 0.1552482715273413, |
| "grad_norm": 8.852916717529297, |
| "learning_rate": 9.84e-05, |
| "loss": 4.1023, |
| "step": 247 |
| }, |
| { |
| "epoch": 0.15587680703959775, |
| "grad_norm": 17.305910110473633, |
| "learning_rate": 9.88e-05, |
| "loss": 4.2657, |
| "step": 248 |
| }, |
| { |
| "epoch": 0.1565053425518542, |
| "grad_norm": 12.877272605895996, |
| "learning_rate": 9.92e-05, |
| "loss": 4.318, |
| "step": 249 |
| }, |
| { |
| "epoch": 0.1571338780641106, |
| "grad_norm": 12.16046142578125, |
| "learning_rate": 9.960000000000001e-05, |
| "loss": 4.0387, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.15776241357636706, |
| "grad_norm": 13.384797096252441, |
| "learning_rate": 0.0001, |
| "loss": 4.3935, |
| "step": 251 |
| }, |
| { |
| "epoch": 0.1583909490886235, |
| "grad_norm": 12.947620391845703, |
| "learning_rate": 0.0001004, |
| "loss": 4.2752, |
| "step": 252 |
| }, |
| { |
| "epoch": 0.15901948460087995, |
| "grad_norm": 13.004393577575684, |
| "learning_rate": 0.00010080000000000001, |
| "loss": 4.4285, |
| "step": 253 |
| }, |
| { |
| "epoch": 0.1596480201131364, |
| "grad_norm": 10.64500617980957, |
| "learning_rate": 0.00010120000000000001, |
| "loss": 4.3775, |
| "step": 254 |
| }, |
| { |
| "epoch": 0.16027655562539284, |
| "grad_norm": 10.208504676818848, |
| "learning_rate": 0.0001016, |
| "loss": 4.3942, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.16090509113764928, |
| "grad_norm": 10.392770767211914, |
| "learning_rate": 0.00010200000000000001, |
| "loss": 3.964, |
| "step": 256 |
| }, |
| { |
| "epoch": 0.16153362664990573, |
| "grad_norm": 11.704667091369629, |
| "learning_rate": 0.00010240000000000001, |
| "loss": 3.2764, |
| "step": 257 |
| }, |
| { |
| "epoch": 0.16216216216216217, |
| "grad_norm": 11.466705322265625, |
| "learning_rate": 0.0001028, |
| "loss": 4.3286, |
| "step": 258 |
| }, |
| { |
| "epoch": 0.16279069767441862, |
| "grad_norm": 11.332155227661133, |
| "learning_rate": 0.0001032, |
| "loss": 4.4598, |
| "step": 259 |
| }, |
| { |
| "epoch": 0.16341923318667503, |
| "grad_norm": 10.597373962402344, |
| "learning_rate": 0.00010360000000000001, |
| "loss": 4.3576, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.16404776869893148, |
| "grad_norm": 13.826549530029297, |
| "learning_rate": 0.00010400000000000001, |
| "loss": 4.1209, |
| "step": 261 |
| }, |
| { |
| "epoch": 0.16467630421118792, |
| "grad_norm": 12.812018394470215, |
| "learning_rate": 0.0001044, |
| "loss": 4.3951, |
| "step": 262 |
| }, |
| { |
| "epoch": 0.16530483972344437, |
| "grad_norm": 11.573945045471191, |
| "learning_rate": 0.00010480000000000001, |
| "loss": 4.6093, |
| "step": 263 |
| }, |
| { |
| "epoch": 0.16593337523570081, |
| "grad_norm": 9.195262908935547, |
| "learning_rate": 0.00010520000000000001, |
| "loss": 4.0342, |
| "step": 264 |
| }, |
| { |
| "epoch": 0.16656191074795726, |
| "grad_norm": 10.87674331665039, |
| "learning_rate": 0.0001056, |
| "loss": 3.9368, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.1671904462602137, |
| "grad_norm": 11.914413452148438, |
| "learning_rate": 0.00010600000000000002, |
| "loss": 4.0043, |
| "step": 266 |
| }, |
| { |
| "epoch": 0.16781898177247015, |
| "grad_norm": 11.688831329345703, |
| "learning_rate": 0.00010640000000000001, |
| "loss": 3.6894, |
| "step": 267 |
| }, |
| { |
| "epoch": 0.1684475172847266, |
| "grad_norm": 17.798152923583984, |
| "learning_rate": 0.00010680000000000001, |
| "loss": 4.4073, |
| "step": 268 |
| }, |
| { |
| "epoch": 0.16907605279698304, |
| "grad_norm": 11.202817916870117, |
| "learning_rate": 0.00010720000000000002, |
| "loss": 3.9713, |
| "step": 269 |
| }, |
| { |
| "epoch": 0.16970458830923948, |
| "grad_norm": 11.484283447265625, |
| "learning_rate": 0.00010760000000000001, |
| "loss": 3.7401, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.1703331238214959, |
| "grad_norm": 8.625189781188965, |
| "learning_rate": 0.00010800000000000001, |
| "loss": 3.6847, |
| "step": 271 |
| }, |
| { |
| "epoch": 0.17096165933375235, |
| "grad_norm": 14.114002227783203, |
| "learning_rate": 0.00010840000000000002, |
| "loss": 4.1115, |
| "step": 272 |
| }, |
| { |
| "epoch": 0.1715901948460088, |
| "grad_norm": 12.885270118713379, |
| "learning_rate": 0.00010880000000000002, |
| "loss": 3.5002, |
| "step": 273 |
| }, |
| { |
| "epoch": 0.17221873035826524, |
| "grad_norm": 13.46296501159668, |
| "learning_rate": 0.00010920000000000001, |
| "loss": 4.0249, |
| "step": 274 |
| }, |
| { |
| "epoch": 0.17284726587052168, |
| "grad_norm": 17.22674560546875, |
| "learning_rate": 0.00010960000000000001, |
| "loss": 4.4484, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.17347580138277813, |
| "grad_norm": 13.292183876037598, |
| "learning_rate": 0.00011000000000000002, |
| "loss": 3.9718, |
| "step": 276 |
| }, |
| { |
| "epoch": 0.17410433689503457, |
| "grad_norm": 35.4398307800293, |
| "learning_rate": 0.00011040000000000001, |
| "loss": 4.0052, |
| "step": 277 |
| }, |
| { |
| "epoch": 0.17473287240729102, |
| "grad_norm": 19.460407257080078, |
| "learning_rate": 0.00011080000000000001, |
| "loss": 4.1892, |
| "step": 278 |
| }, |
| { |
| "epoch": 0.17536140791954746, |
| "grad_norm": 15.537309646606445, |
| "learning_rate": 0.00011120000000000002, |
| "loss": 3.9878, |
| "step": 279 |
| }, |
| { |
| "epoch": 0.1759899434318039, |
| "grad_norm": 16.156564712524414, |
| "learning_rate": 0.00011160000000000002, |
| "loss": 3.8753, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.17661847894406035, |
| "grad_norm": 17.241336822509766, |
| "learning_rate": 0.00011200000000000001, |
| "loss": 3.9479, |
| "step": 281 |
| }, |
| { |
| "epoch": 0.17724701445631677, |
| "grad_norm": 20.027856826782227, |
| "learning_rate": 0.00011240000000000002, |
| "loss": 3.9856, |
| "step": 282 |
| }, |
| { |
| "epoch": 0.17787554996857322, |
| "grad_norm": 11.107442855834961, |
| "learning_rate": 0.00011279999999999999, |
| "loss": 3.5669, |
| "step": 283 |
| }, |
| { |
| "epoch": 0.17850408548082966, |
| "grad_norm": 14.415189743041992, |
| "learning_rate": 0.0001132, |
| "loss": 4.1763, |
| "step": 284 |
| }, |
| { |
| "epoch": 0.1791326209930861, |
| "grad_norm": 16.054901123046875, |
| "learning_rate": 0.0001136, |
| "loss": 4.1089, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.17976115650534255, |
| "grad_norm": 17.718029022216797, |
| "learning_rate": 0.00011399999999999999, |
| "loss": 3.7917, |
| "step": 286 |
| }, |
| { |
| "epoch": 0.180389692017599, |
| "grad_norm": 15.520782470703125, |
| "learning_rate": 0.0001144, |
| "loss": 3.9876, |
| "step": 287 |
| }, |
| { |
| "epoch": 0.18101822752985544, |
| "grad_norm": 19.573312759399414, |
| "learning_rate": 0.0001148, |
| "loss": 3.9456, |
| "step": 288 |
| }, |
| { |
| "epoch": 0.1816467630421119, |
| "grad_norm": 11.45984935760498, |
| "learning_rate": 0.0001152, |
| "loss": 3.5074, |
| "step": 289 |
| }, |
| { |
| "epoch": 0.18227529855436833, |
| "grad_norm": 21.8663387298584, |
| "learning_rate": 0.00011559999999999999, |
| "loss": 4.0081, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.18290383406662478, |
| "grad_norm": 16.874753952026367, |
| "learning_rate": 0.000116, |
| "loss": 3.9281, |
| "step": 291 |
| }, |
| { |
| "epoch": 0.1835323695788812, |
| "grad_norm": 16.98707389831543, |
| "learning_rate": 0.0001164, |
| "loss": 3.9644, |
| "step": 292 |
| }, |
| { |
| "epoch": 0.18416090509113764, |
| "grad_norm": 12.668580055236816, |
| "learning_rate": 0.00011679999999999999, |
| "loss": 3.3014, |
| "step": 293 |
| }, |
| { |
| "epoch": 0.18478944060339408, |
| "grad_norm": 11.530134201049805, |
| "learning_rate": 0.0001172, |
| "loss": 3.3005, |
| "step": 294 |
| }, |
| { |
| "epoch": 0.18541797611565053, |
| "grad_norm": 53.85222244262695, |
| "learning_rate": 0.0001176, |
| "loss": 4.4674, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.18604651162790697, |
| "grad_norm": 12.703718185424805, |
| "learning_rate": 0.000118, |
| "loss": 3.629, |
| "step": 296 |
| }, |
| { |
| "epoch": 0.18667504714016342, |
| "grad_norm": 18.4884090423584, |
| "learning_rate": 0.0001184, |
| "loss": 3.7944, |
| "step": 297 |
| }, |
| { |
| "epoch": 0.18730358265241986, |
| "grad_norm": 18.730792999267578, |
| "learning_rate": 0.0001188, |
| "loss": 3.6521, |
| "step": 298 |
| }, |
| { |
| "epoch": 0.1879321181646763, |
| "grad_norm": 10.74968433380127, |
| "learning_rate": 0.0001192, |
| "loss": 3.6895, |
| "step": 299 |
| }, |
| { |
| "epoch": 0.18856065367693275, |
| "grad_norm": 13.541333198547363, |
| "learning_rate": 0.00011960000000000001, |
| "loss": 3.4517, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.1891891891891892, |
| "grad_norm": 20.38814926147461, |
| "learning_rate": 0.00012, |
| "loss": 3.3987, |
| "step": 301 |
| }, |
| { |
| "epoch": 0.18981772470144564, |
| "grad_norm": 21.178226470947266, |
| "learning_rate": 0.0001204, |
| "loss": 3.6073, |
| "step": 302 |
| }, |
| { |
| "epoch": 0.19044626021370206, |
| "grad_norm": 11.370046615600586, |
| "learning_rate": 0.0001208, |
| "loss": 3.3391, |
| "step": 303 |
| }, |
| { |
| "epoch": 0.1910747957259585, |
| "grad_norm": 10.467302322387695, |
| "learning_rate": 0.0001212, |
| "loss": 3.7676, |
| "step": 304 |
| }, |
| { |
| "epoch": 0.19170333123821495, |
| "grad_norm": 11.307904243469238, |
| "learning_rate": 0.0001216, |
| "loss": 3.4048, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.1923318667504714, |
| "grad_norm": 20.741159439086914, |
| "learning_rate": 0.000122, |
| "loss": 3.1971, |
| "step": 306 |
| }, |
| { |
| "epoch": 0.19296040226272784, |
| "grad_norm": 22.384532928466797, |
| "learning_rate": 0.0001224, |
| "loss": 3.2315, |
| "step": 307 |
| }, |
| { |
| "epoch": 0.1935889377749843, |
| "grad_norm": 19.073701858520508, |
| "learning_rate": 0.0001228, |
| "loss": 3.3426, |
| "step": 308 |
| }, |
| { |
| "epoch": 0.19421747328724073, |
| "grad_norm": 20.864418029785156, |
| "learning_rate": 0.0001232, |
| "loss": 3.4605, |
| "step": 309 |
| }, |
| { |
| "epoch": 0.19484600879949718, |
| "grad_norm": 15.888052940368652, |
| "learning_rate": 0.0001236, |
| "loss": 3.5554, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.19547454431175362, |
| "grad_norm": 13.650964736938477, |
| "learning_rate": 0.000124, |
| "loss": 3.3372, |
| "step": 311 |
| }, |
| { |
| "epoch": 0.19610307982401007, |
| "grad_norm": 20.19765853881836, |
| "learning_rate": 0.00012440000000000002, |
| "loss": 3.4044, |
| "step": 312 |
| }, |
| { |
| "epoch": 0.19673161533626649, |
| "grad_norm": 18.977705001831055, |
| "learning_rate": 0.0001248, |
| "loss": 3.5597, |
| "step": 313 |
| }, |
| { |
| "epoch": 0.19736015084852293, |
| "grad_norm": 13.097780227661133, |
| "learning_rate": 0.0001252, |
| "loss": 3.2755, |
| "step": 314 |
| }, |
| { |
| "epoch": 0.19798868636077938, |
| "grad_norm": 17.84178924560547, |
| "learning_rate": 0.00012560000000000002, |
| "loss": 3.2663, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.19861722187303582, |
| "grad_norm": 14.159675598144531, |
| "learning_rate": 0.000126, |
| "loss": 3.4946, |
| "step": 316 |
| }, |
| { |
| "epoch": 0.19924575738529227, |
| "grad_norm": 11.891308784484863, |
| "learning_rate": 0.0001264, |
| "loss": 2.8523, |
| "step": 317 |
| }, |
| { |
| "epoch": 0.1998742928975487, |
| "grad_norm": 15.97802734375, |
| "learning_rate": 0.00012680000000000002, |
| "loss": 3.2556, |
| "step": 318 |
| }, |
| { |
| "epoch": 0.20050282840980516, |
| "grad_norm": 13.670428276062012, |
| "learning_rate": 0.0001272, |
| "loss": 3.4079, |
| "step": 319 |
| }, |
| { |
| "epoch": 0.2011313639220616, |
| "grad_norm": 15.742596626281738, |
| "learning_rate": 0.0001276, |
| "loss": 3.358, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.2011313639220616, |
| "eval_loss": 2.595961093902588, |
| "eval_runtime": 1561.7692, |
| "eval_samples_per_second": 1.651, |
| "eval_steps_per_second": 1.651, |
| "step": 320 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 1591, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 160, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.0920991543381197e+18, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
