| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9991154356479433, | |
| "eval_steps": 142, | |
| "global_step": 1130, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 4.588052749633789, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 3.3182, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.3362529277801514, | |
| "eval_runtime": 14.4233, | |
| "eval_samples_per_second": 33.071, | |
| "eval_steps_per_second": 8.32, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 4.520856857299805, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 3.2788, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 4.619396209716797, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 3.3097, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 4.416432857513428, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.9162, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.6663408279418945, | |
| "learning_rate": 0.00015, | |
| "loss": 2.0914, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.739701747894287, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.9915, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.6202051639556885, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.4153, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.975229799747467, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.1806, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.136542558670044, | |
| "learning_rate": 0.00027, | |
| "loss": 0.1403, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.98671555519104, | |
| "learning_rate": 0.0003, | |
| "loss": 0.386, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.3339874744415283, | |
| "learning_rate": 0.0002999997392879692, | |
| "loss": 0.1334, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.4813332259654999, | |
| "learning_rate": 0.0002999989571527831, | |
| "loss": 0.1525, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.3785192370414734, | |
| "learning_rate": 0.0002999976535971604, | |
| "loss": 0.1408, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.1563730090856552, | |
| "learning_rate": 0.00029999582862563263, | |
| "loss": 0.137, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.121751569211483, | |
| "learning_rate": 0.00029999348224454364, | |
| "loss": 0.1371, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.22550074756145477, | |
| "learning_rate": 0.0002999906144620498, | |
| "loss": 0.1512, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.2235211282968521, | |
| "learning_rate": 0.00029998722528811996, | |
| "loss": 0.1483, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.4022941589355469, | |
| "learning_rate": 0.0002999833147345355, | |
| "loss": 0.1124, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.16621588170528412, | |
| "learning_rate": 0.0002999788828148901, | |
| "loss": 0.1414, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.06893815100193024, | |
| "learning_rate": 0.00029997392954458983, | |
| "loss": 0.1364, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3331284821033478, | |
| "learning_rate": 0.000299968454940853, | |
| "loss": 0.1433, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.1405547559261322, | |
| "learning_rate": 0.0002999624590227103, | |
| "loss": 0.1291, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.14127376675605774, | |
| "learning_rate": 0.00029995594181100437, | |
| "loss": 0.1298, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.20128677785396576, | |
| "learning_rate": 0.00029994890332839025, | |
| "loss": 0.1347, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.31639915704727173, | |
| "learning_rate": 0.0002999413435993347, | |
| "loss": 0.1288, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.8167548775672913, | |
| "learning_rate": 0.00029993326265011667, | |
| "loss": 0.1785, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.1112348735332489, | |
| "learning_rate": 0.0002999246605088267, | |
| "loss": 0.1168, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.06746704876422882, | |
| "learning_rate": 0.0002999155372053673, | |
| "loss": 0.1238, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.6724908947944641, | |
| "learning_rate": 0.0002999058927714525, | |
| "loss": 0.2079, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.1440785676240921, | |
| "learning_rate": 0.00029989572724060796, | |
| "loss": 0.1283, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.11361633986234665, | |
| "learning_rate": 0.00029988504064817065, | |
| "loss": 0.14, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.10072154551744461, | |
| "learning_rate": 0.00029987383303128884, | |
| "loss": 0.1389, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.07634437829256058, | |
| "learning_rate": 0.00029986210442892213, | |
| "loss": 0.1373, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.16817660629749298, | |
| "learning_rate": 0.0002998498548818408, | |
| "loss": 0.1385, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.11250842362642288, | |
| "learning_rate": 0.00029983708443262654, | |
| "loss": 0.1389, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.10796725004911423, | |
| "learning_rate": 0.0002998237931256712, | |
| "loss": 0.1414, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.04835154488682747, | |
| "learning_rate": 0.0002998099810071777, | |
| "loss": 0.1348, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.29721006751060486, | |
| "learning_rate": 0.00029979564812515906, | |
| "loss": 0.1374, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.13514482975006104, | |
| "learning_rate": 0.0002997807945294387, | |
| "loss": 0.1395, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.2045493870973587, | |
| "learning_rate": 0.0002997654202716501, | |
| "loss": 0.1258, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.17623500525951385, | |
| "learning_rate": 0.0002997495254052367, | |
| "loss": 0.1399, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.15333342552185059, | |
| "learning_rate": 0.00029973310998545157, | |
| "loss": 0.1407, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.11854752153158188, | |
| "learning_rate": 0.0002997161740693573, | |
| "loss": 0.1365, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.34156811237335205, | |
| "learning_rate": 0.00029969871771582594, | |
| "loss": 0.1064, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.07359682768583298, | |
| "learning_rate": 0.0002996807409855385, | |
| "loss": 0.1267, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.2271728217601776, | |
| "learning_rate": 0.00029966224394098494, | |
| "loss": 0.1378, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.21861566603183746, | |
| "learning_rate": 0.0002996432266464641, | |
| "loss": 0.1415, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.11931619793176651, | |
| "learning_rate": 0.00029962368916808306, | |
| "loss": 0.1375, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.19349679350852966, | |
| "learning_rate": 0.00029960363157375717, | |
| "loss": 0.132, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.35250943899154663, | |
| "learning_rate": 0.00029958305393320997, | |
| "loss": 0.1513, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.10226023942232132, | |
| "learning_rate": 0.00029956195631797257, | |
| "loss": 0.1332, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.34944722056388855, | |
| "learning_rate": 0.00029954033880138364, | |
| "loss": 0.1512, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.24920719861984253, | |
| "learning_rate": 0.00029951820145858915, | |
| "loss": 0.1433, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.5471547842025757, | |
| "learning_rate": 0.0002994955443665421, | |
| "loss": 0.1453, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.04468518868088722, | |
| "learning_rate": 0.00029947236760400215, | |
| "loss": 0.1328, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.1944192349910736, | |
| "learning_rate": 0.00029944867125153543, | |
| "loss": 0.1319, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.10784479230642319, | |
| "learning_rate": 0.0002994244553915143, | |
| "loss": 0.1394, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.16469427943229675, | |
| "learning_rate": 0.0002993997201081169, | |
| "loss": 0.1448, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.07228899002075195, | |
| "learning_rate": 0.00029937446548732716, | |
| "loss": 0.1302, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.17821665108203888, | |
| "learning_rate": 0.0002993486916169341, | |
| "loss": 0.1365, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.1656705141067505, | |
| "learning_rate": 0.0002993223985865318, | |
| "loss": 0.1232, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.25225961208343506, | |
| "learning_rate": 0.0002992955864875192, | |
| "loss": 0.1308, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.26701709628105164, | |
| "learning_rate": 0.00029926825541309925, | |
| "loss": 0.1126, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.30766233801841736, | |
| "learning_rate": 0.0002992404054582793, | |
| "loss": 0.1051, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 1.0783226490020752, | |
| "learning_rate": 0.00029921203671987023, | |
| "loss": 0.1031, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.797533392906189, | |
| "learning_rate": 0.0002991831492964863, | |
| "loss": 0.1243, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.3874399662017822, | |
| "learning_rate": 0.0002991537432885449, | |
| "loss": 0.098, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.5988464951515198, | |
| "learning_rate": 0.0002991238187982659, | |
| "loss": 0.0899, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.5161219835281372, | |
| "learning_rate": 0.00029909337592967173, | |
| "loss": 0.0893, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.9815970659255981, | |
| "learning_rate": 0.0002990624147885866, | |
| "loss": 0.1132, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 1.014042615890503, | |
| "learning_rate": 0.00029903093548263655, | |
| "loss": 0.1526, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.4545246958732605, | |
| "learning_rate": 0.00029899893812124857, | |
| "loss": 0.1303, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.4577489197254181, | |
| "learning_rate": 0.00029896642281565067, | |
| "loss": 0.0745, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.49255430698394775, | |
| "learning_rate": 0.00029893338967887124, | |
| "loss": 0.0924, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.39145103096961975, | |
| "learning_rate": 0.0002988998388257388, | |
| "loss": 0.1121, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.2706741392612457, | |
| "learning_rate": 0.00029886577037288147, | |
| "loss": 0.0727, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.1395532339811325, | |
| "learning_rate": 0.0002988311844387266, | |
| "loss": 0.0509, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.4092063307762146, | |
| "learning_rate": 0.0002987960811435006, | |
| "loss": 0.0785, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.4469921886920929, | |
| "learning_rate": 0.000298760460609228, | |
| "loss": 0.123, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.7060185670852661, | |
| "learning_rate": 0.00029872432295973154, | |
| "loss": 0.1112, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.5608384013175964, | |
| "learning_rate": 0.00029868766832063154, | |
| "loss": 0.1248, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.2733088731765747, | |
| "learning_rate": 0.0002986504968193454, | |
| "loss": 0.08, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.28215891122817993, | |
| "learning_rate": 0.0002986128085850871, | |
| "loss": 0.0603, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.28432655334472656, | |
| "learning_rate": 0.0002985746037488671, | |
| "loss": 0.1094, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.3250674903392792, | |
| "learning_rate": 0.00029853588244349154, | |
| "loss": 0.0937, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.31528908014297485, | |
| "learning_rate": 0.00029849664480356187, | |
| "loss": 0.0984, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.4400915503501892, | |
| "learning_rate": 0.00029845689096547436, | |
| "loss": 0.1054, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.2794625759124756, | |
| "learning_rate": 0.0002984166210674198, | |
| "loss": 0.103, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.24721817672252655, | |
| "learning_rate": 0.00029837583524938287, | |
| "loss": 0.0763, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.17728295922279358, | |
| "learning_rate": 0.00029833453365314146, | |
| "loss": 0.0799, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.42136892676353455, | |
| "learning_rate": 0.00029829271642226664, | |
| "loss": 0.1157, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.26066917181015015, | |
| "learning_rate": 0.0002982503837021218, | |
| "loss": 0.0754, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.3443453013896942, | |
| "learning_rate": 0.00029820753563986226, | |
| "loss": 0.1262, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 1.1035971641540527, | |
| "learning_rate": 0.0002981641723844348, | |
| "loss": 0.2149, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.4937790036201477, | |
| "learning_rate": 0.00029812029408657695, | |
| "loss": 0.0519, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.25491034984588623, | |
| "learning_rate": 0.00029807590089881683, | |
| "loss": 0.0463, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.8630254864692688, | |
| "learning_rate": 0.00029803099297547216, | |
| "loss": 0.1097, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.7856675386428833, | |
| "learning_rate": 0.0002979855704726502, | |
| "loss": 0.1249, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.41131559014320374, | |
| "learning_rate": 0.00029793963354824685, | |
| "loss": 0.0578, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.2710832357406616, | |
| "learning_rate": 0.00029789318236194616, | |
| "loss": 0.0695, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.37780898809432983, | |
| "learning_rate": 0.0002978462170752199, | |
| "loss": 0.1595, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.6756994128227234, | |
| "learning_rate": 0.00029779873785132696, | |
| "loss": 0.1593, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.3440113067626953, | |
| "learning_rate": 0.0002977507448553128, | |
| "loss": 0.1084, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.46663540601730347, | |
| "learning_rate": 0.0002977022382540087, | |
| "loss": 0.1467, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.29806986451148987, | |
| "learning_rate": 0.0002976532182160314, | |
| "loss": 0.114, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.17679756879806519, | |
| "learning_rate": 0.0002976036849117824, | |
| "loss": 0.1148, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.17152459919452667, | |
| "learning_rate": 0.0002975536385134475, | |
| "loss": 0.1135, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.16383178532123566, | |
| "learning_rate": 0.00029750307919499595, | |
| "loss": 0.0987, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.27941015362739563, | |
| "learning_rate": 0.00029745200713217996, | |
| "loss": 0.141, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.1865178793668747, | |
| "learning_rate": 0.0002974004225025344, | |
| "loss": 0.1066, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.09909848123788834, | |
| "learning_rate": 0.0002973483254853756, | |
| "loss": 0.0829, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.17434453964233398, | |
| "learning_rate": 0.0002972957162618011, | |
| "loss": 0.0908, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.1075962707400322, | |
| "learning_rate": 0.0002972425950146891, | |
| "loss": 0.1005, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.23516638576984406, | |
| "learning_rate": 0.00029718896192869755, | |
| "loss": 0.107, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.1640479862689972, | |
| "learning_rate": 0.00029713481719026365, | |
| "loss": 0.0947, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.1907346248626709, | |
| "learning_rate": 0.00029708016098760315, | |
| "loss": 0.0757, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.26523101329803467, | |
| "learning_rate": 0.0002970249935107099, | |
| "loss": 0.1213, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.4174201190471649, | |
| "learning_rate": 0.0002969693149513548, | |
| "loss": 0.1036, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.5090858340263367, | |
| "learning_rate": 0.00029691312550308546, | |
| "loss": 0.1229, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.5807089805603027, | |
| "learning_rate": 0.00029685642536122543, | |
| "loss": 0.1017, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.20680812001228333, | |
| "learning_rate": 0.00029679921472287353, | |
| "loss": 0.0656, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.8702337145805359, | |
| "learning_rate": 0.0002967414937869031, | |
| "loss": 0.2062, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.8191081881523132, | |
| "learning_rate": 0.00029668326275396133, | |
| "loss": 0.1474, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.3332749307155609, | |
| "learning_rate": 0.0002966245218264687, | |
| "loss": 0.0991, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.4073905050754547, | |
| "learning_rate": 0.000296565271208618, | |
| "loss": 0.1113, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 1.1542918682098389, | |
| "learning_rate": 0.00029650551110637393, | |
| "loss": 0.1672, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 1.1717615127563477, | |
| "learning_rate": 0.0002964452417274723, | |
| "loss": 0.1665, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.24656681716442108, | |
| "learning_rate": 0.00029638446328141894, | |
| "loss": 0.113, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.12859101593494415, | |
| "learning_rate": 0.00029632317597948964, | |
| "loss": 0.111, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.0825003981590271, | |
| "learning_rate": 0.0002962613800347288, | |
| "loss": 0.1235, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.14479093253612518, | |
| "learning_rate": 0.0002961990756619491, | |
| "loss": 0.1031, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.2117856740951538, | |
| "learning_rate": 0.0002961362630777305, | |
| "loss": 0.0995, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.1228349581360817, | |
| "learning_rate": 0.00029607294250041965, | |
| "loss": 0.0804, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.18281131982803345, | |
| "learning_rate": 0.000296009114150129, | |
| "loss": 0.0843, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.2280908077955246, | |
| "learning_rate": 0.0002959447782487361, | |
| "loss": 0.1361, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.21089224517345428, | |
| "learning_rate": 0.0002958799350198829, | |
| "loss": 0.136, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.4448394477367401, | |
| "learning_rate": 0.00029581458468897485, | |
| "loss": 0.1293, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.35630327463150024, | |
| "learning_rate": 0.0002957487274831803, | |
| "loss": 0.0892, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.3235824406147003, | |
| "learning_rate": 0.00029568236363142924, | |
| "loss": 0.0862, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.5782188177108765, | |
| "learning_rate": 0.0002956154933644133, | |
| "loss": 0.1067, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.0916428491473198, | |
| "learning_rate": 0.00029554811691458405, | |
| "loss": 0.0717, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.10682029277086258, | |
| "learning_rate": 0.00029548023451615295, | |
| "loss": 0.0729, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.09042291343212128, | |
| "eval_runtime": 14.7658, | |
| "eval_samples_per_second": 32.304, | |
| "eval_steps_per_second": 8.127, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.10448458790779114, | |
| "learning_rate": 0.00029541184640509015, | |
| "loss": 0.1013, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.20653600990772247, | |
| "learning_rate": 0.00029534295281912355, | |
| "loss": 0.1109, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.09114749729633331, | |
| "learning_rate": 0.00029527355399773845, | |
| "loss": 0.098, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.13702392578125, | |
| "learning_rate": 0.0002952036501821762, | |
| "loss": 0.0434, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.21909640729427338, | |
| "learning_rate": 0.00029513324161543366, | |
| "loss": 0.1072, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.1765926033258438, | |
| "learning_rate": 0.00029506232854226237, | |
| "loss": 0.0912, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.26851925253868103, | |
| "learning_rate": 0.00029499091120916755, | |
| "loss": 0.1134, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.15720008313655853, | |
| "learning_rate": 0.0002949189898644072, | |
| "loss": 0.0953, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.31068509817123413, | |
| "learning_rate": 0.0002948465647579916, | |
| "loss": 0.1179, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.3737366497516632, | |
| "learning_rate": 0.00029477363614168194, | |
| "loss": 0.0745, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.295796275138855, | |
| "learning_rate": 0.0002947002042689898, | |
| "loss": 0.1448, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.21946462988853455, | |
| "learning_rate": 0.0002946262693951762, | |
| "loss": 0.0938, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.1442556530237198, | |
| "learning_rate": 0.00029455183177725053, | |
| "loss": 0.0778, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.15714137256145477, | |
| "learning_rate": 0.00029447689167396996, | |
| "loss": 0.1192, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.1749090850353241, | |
| "learning_rate": 0.0002944014493458383, | |
| "loss": 0.1065, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.4440750777721405, | |
| "learning_rate": 0.0002943255050551051, | |
| "loss": 0.1143, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.3883216083049774, | |
| "learning_rate": 0.0002942490590657651, | |
| "loss": 0.1257, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.1770515888929367, | |
| "learning_rate": 0.00029417211164355664, | |
| "loss": 0.0917, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.13733014464378357, | |
| "learning_rate": 0.0002940946630559613, | |
| "loss": 0.0694, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.10783812403678894, | |
| "learning_rate": 0.0002940167135722029, | |
| "loss": 0.053, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.4282841086387634, | |
| "learning_rate": 0.0002939382634632463, | |
| "loss": 0.1514, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.2022620588541031, | |
| "learning_rate": 0.00029385931300179673, | |
| "loss": 0.093, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.09893293678760529, | |
| "learning_rate": 0.0002937798624622985, | |
| "loss": 0.0482, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.24493345618247986, | |
| "learning_rate": 0.0002936999121209346, | |
| "loss": 0.1104, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.558118999004364, | |
| "learning_rate": 0.0002936194622556251, | |
| "loss": 0.1593, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.30332863330841064, | |
| "learning_rate": 0.00029353851314602674, | |
| "loss": 0.1431, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.22926372289657593, | |
| "learning_rate": 0.00029345706507353153, | |
| "loss": 0.0903, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.1272840052843094, | |
| "learning_rate": 0.0002933751183212661, | |
| "loss": 0.0581, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.14229409396648407, | |
| "learning_rate": 0.0002932926731740905, | |
| "loss": 0.0786, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.15394841134548187, | |
| "learning_rate": 0.00029320972991859725, | |
| "loss": 0.0891, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.14996570348739624, | |
| "learning_rate": 0.00029312628884311045, | |
| "loss": 0.0697, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.17957860231399536, | |
| "learning_rate": 0.0002930423502376846, | |
| "loss": 0.0597, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.2494930922985077, | |
| "learning_rate": 0.00029295791439410383, | |
| "loss": 0.1173, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.25140491127967834, | |
| "learning_rate": 0.0002928729816058807, | |
| "loss": 0.1015, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.23032979667186737, | |
| "learning_rate": 0.00029278755216825505, | |
| "loss": 0.1271, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.18228159844875336, | |
| "learning_rate": 0.0002927016263781935, | |
| "loss": 0.0758, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.18998126685619354, | |
| "learning_rate": 0.0002926152045343877, | |
| "loss": 0.0658, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.2079799771308899, | |
| "learning_rate": 0.00029252828693725403, | |
| "loss": 0.1376, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.20679551362991333, | |
| "learning_rate": 0.00029244087388893185, | |
| "loss": 0.0989, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.13382777571678162, | |
| "learning_rate": 0.000292352965693283, | |
| "loss": 0.0739, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.1363653689622879, | |
| "learning_rate": 0.00029226456265589045, | |
| "loss": 0.0781, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.21474190056324005, | |
| "learning_rate": 0.00029217566508405737, | |
| "loss": 0.0994, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.1632685363292694, | |
| "learning_rate": 0.000292086273286806, | |
| "loss": 0.0938, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.18359023332595825, | |
| "learning_rate": 0.0002919963875748765, | |
| "loss": 0.0837, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.21232351660728455, | |
| "learning_rate": 0.000291906008260726, | |
| "loss": 0.1021, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.1560080200433731, | |
| "learning_rate": 0.0002918151356585276, | |
| "loss": 0.0775, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.206360325217247, | |
| "learning_rate": 0.00029172377008416893, | |
| "loss": 0.0859, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.16424915194511414, | |
| "learning_rate": 0.0002916319118552515, | |
| "loss": 0.1071, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.15049318969249725, | |
| "learning_rate": 0.00029153956129108913, | |
| "loss": 0.0837, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.08157264441251755, | |
| "learning_rate": 0.0002914467187127073, | |
| "loss": 0.063, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.2039349228143692, | |
| "learning_rate": 0.00029135338444284166, | |
| "loss": 0.1077, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.1816401183605194, | |
| "learning_rate": 0.00029125955880593705, | |
| "loss": 0.1035, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.13115471601486206, | |
| "learning_rate": 0.0002911652421281465, | |
| "loss": 0.0862, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.20337167382240295, | |
| "learning_rate": 0.00029107043473732995, | |
| "loss": 0.0724, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.12583452463150024, | |
| "learning_rate": 0.000290975136963053, | |
| "loss": 0.0701, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.4595123827457428, | |
| "learning_rate": 0.0002908793491365861, | |
| "loss": 0.1763, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.17089878022670746, | |
| "learning_rate": 0.00029078307159090294, | |
| "loss": 0.0478, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.22770017385482788, | |
| "learning_rate": 0.00029068630466067995, | |
| "loss": 0.0551, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.16812334954738617, | |
| "learning_rate": 0.00029058904868229426, | |
| "loss": 0.0829, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.15563331544399261, | |
| "learning_rate": 0.0002904913039938234, | |
| "loss": 0.0551, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.14948880672454834, | |
| "learning_rate": 0.00029039307093504355, | |
| "loss": 0.1255, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.4740292429924011, | |
| "learning_rate": 0.0002902943498474286, | |
| "loss": 0.1865, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.2227841019630432, | |
| "learning_rate": 0.00029019514107414887, | |
| "loss": 0.0801, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.3277839422225952, | |
| "learning_rate": 0.00029009544496006996, | |
| "loss": 0.0785, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.30582112073898315, | |
| "learning_rate": 0.0002899952618517515, | |
| "loss": 0.0802, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.2919937074184418, | |
| "learning_rate": 0.00028989459209744617, | |
| "loss": 0.0533, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.31071627140045166, | |
| "learning_rate": 0.00028979343604709816, | |
| "loss": 0.1474, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.14612245559692383, | |
| "learning_rate": 0.000289691794052342, | |
| "loss": 0.1118, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.2461383044719696, | |
| "learning_rate": 0.0002895896664665017, | |
| "loss": 0.155, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.2300606220960617, | |
| "learning_rate": 0.0002894870536445891, | |
| "loss": 0.1023, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.3330621123313904, | |
| "learning_rate": 0.0002893839559433028, | |
| "loss": 0.1851, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.08405052870512009, | |
| "learning_rate": 0.00028928037372102694, | |
| "loss": 0.1162, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.08986380696296692, | |
| "learning_rate": 0.00028917630733783, | |
| "loss": 0.1033, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.08752616494894028, | |
| "learning_rate": 0.00028907175715546334, | |
| "loss": 0.1081, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.15312182903289795, | |
| "learning_rate": 0.00028896672353736027, | |
| "loss": 0.1084, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.1530596911907196, | |
| "learning_rate": 0.00028886120684863437, | |
| "loss": 0.1143, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.19303447008132935, | |
| "learning_rate": 0.00028875520745607865, | |
| "loss": 0.1322, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.2029002606868744, | |
| "learning_rate": 0.00028864872572816405, | |
| "loss": 0.1, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.0897076427936554, | |
| "learning_rate": 0.00028854176203503806, | |
| "loss": 0.0964, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.14917291700839996, | |
| "learning_rate": 0.00028843431674852363, | |
| "loss": 0.078, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.1606171429157257, | |
| "learning_rate": 0.00028832639024211785, | |
| "loss": 0.0844, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.15833866596221924, | |
| "learning_rate": 0.0002882179828909905, | |
| "loss": 0.103, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.2102007120847702, | |
| "learning_rate": 0.00028810909507198304, | |
| "loss": 0.0783, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.14001865684986115, | |
| "learning_rate": 0.00028799972716360693, | |
| "loss": 0.0999, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.07050840556621552, | |
| "learning_rate": 0.00028788987954604255, | |
| "loss": 0.0504, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.1809457242488861, | |
| "learning_rate": 0.0002877795526011379, | |
| "loss": 0.063, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.19804933667182922, | |
| "learning_rate": 0.00028766874671240706, | |
| "loss": 0.0819, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.8398628830909729, | |
| "learning_rate": 0.0002875574622650291, | |
| "loss": 0.0495, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.28259506821632385, | |
| "learning_rate": 0.0002874456996458466, | |
| "loss": 0.147, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.5770221948623657, | |
| "learning_rate": 0.00028733345924336444, | |
| "loss": 0.0941, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.2959941625595093, | |
| "learning_rate": 0.0002872207414477482, | |
| "loss": 0.15, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.41449636220932007, | |
| "learning_rate": 0.0002871075466508229, | |
| "loss": 0.1244, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.20178668200969696, | |
| "learning_rate": 0.000286993875246072, | |
| "loss": 0.1241, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.2657439708709717, | |
| "learning_rate": 0.0002868797276286355, | |
| "loss": 0.108, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.26215022802352905, | |
| "learning_rate": 0.0002867651041953087, | |
| "loss": 0.0814, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.17194584012031555, | |
| "learning_rate": 0.00028665000534454116, | |
| "loss": 0.0937, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.14481855928897858, | |
| "learning_rate": 0.00028653443147643495, | |
| "loss": 0.0866, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.2787633240222931, | |
| "learning_rate": 0.00028641838299274335, | |
| "loss": 0.0711, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.20350907742977142, | |
| "learning_rate": 0.0002863018602968695, | |
| "loss": 0.146, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.29709184169769287, | |
| "learning_rate": 0.0002861848637938649, | |
| "loss": 0.1273, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.15158367156982422, | |
| "learning_rate": 0.00028606739389042834, | |
| "loss": 0.0778, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.13614635169506073, | |
| "learning_rate": 0.0002859494509949039, | |
| "loss": 0.0609, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.20077449083328247, | |
| "learning_rate": 0.00028583103551728004, | |
| "loss": 0.097, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.08916395157575607, | |
| "learning_rate": 0.00028571214786918806, | |
| "loss": 0.0704, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.18170690536499023, | |
| "learning_rate": 0.00028559278846390033, | |
| "loss": 0.0662, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.20803312957286835, | |
| "learning_rate": 0.00028547295771632936, | |
| "loss": 0.0683, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.40586671233177185, | |
| "learning_rate": 0.0002853526560430261, | |
| "loss": 0.0909, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.16656708717346191, | |
| "learning_rate": 0.0002852318838621784, | |
| "loss": 0.0793, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.24462048709392548, | |
| "learning_rate": 0.00028511064159360977, | |
| "loss": 0.12, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.32009223103523254, | |
| "learning_rate": 0.00028498892965877776, | |
| "loss": 0.1005, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.17075763642787933, | |
| "learning_rate": 0.0002848667484807726, | |
| "loss": 0.088, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.4186219573020935, | |
| "learning_rate": 0.00028474409848431556, | |
| "loss": 0.1242, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.2534870505332947, | |
| "learning_rate": 0.0002846209800957579, | |
| "loss": 0.0672, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.22438766062259674, | |
| "learning_rate": 0.00028449739374307876, | |
| "loss": 0.0628, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.3011839687824249, | |
| "learning_rate": 0.00028437333985588414, | |
| "loss": 0.0731, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.3355525732040405, | |
| "learning_rate": 0.00028424881886540525, | |
| "loss": 0.1556, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.3344305455684662, | |
| "learning_rate": 0.00028412383120449705, | |
| "loss": 0.1138, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.12889593839645386, | |
| "learning_rate": 0.00028399837730763667, | |
| "loss": 0.0386, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.1852964162826538, | |
| "learning_rate": 0.000283872457610922, | |
| "loss": 0.0777, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.15753400325775146, | |
| "learning_rate": 0.00028374607255207007, | |
| "loss": 0.0519, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.33515694737434387, | |
| "learning_rate": 0.00028361922257041575, | |
| "loss": 0.1075, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.4648870825767517, | |
| "learning_rate": 0.00028349190810690974, | |
| "loss": 0.1426, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.47806718945503235, | |
| "learning_rate": 0.0002833641296041176, | |
| "loss": 0.1695, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.13909588754177094, | |
| "learning_rate": 0.000283235887506218, | |
| "loss": 0.0683, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.19695843756198883, | |
| "learning_rate": 0.0002831071822590009, | |
| "loss": 0.072, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.10471002012491226, | |
| "learning_rate": 0.00028297801430986647, | |
| "loss": 0.0725, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.11718752980232239, | |
| "learning_rate": 0.0002828483841078232, | |
| "loss": 0.0799, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.18288259208202362, | |
| "learning_rate": 0.0002827182921034865, | |
| "loss": 0.1348, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.13153032958507538, | |
| "learning_rate": 0.000282587738749077, | |
| "loss": 0.0865, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.2975251376628876, | |
| "learning_rate": 0.00028245672449841915, | |
| "loss": 0.118, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.23405657708644867, | |
| "learning_rate": 0.00028232524980693945, | |
| "loss": 0.1012, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.15189243853092194, | |
| "learning_rate": 0.000282193315131665, | |
| "loss": 0.1089, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.11026138812303543, | |
| "learning_rate": 0.0002820609209312219, | |
| "loss": 0.0626, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.11485940217971802, | |
| "learning_rate": 0.0002819280676658337, | |
| "loss": 0.0767, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.3087170422077179, | |
| "learning_rate": 0.0002817947557973196, | |
| "loss": 0.0892, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.07682602852582932, | |
| "learning_rate": 0.00028166098578909313, | |
| "loss": 0.0467, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.34041598439216614, | |
| "learning_rate": 0.0002815267581061602, | |
| "loss": 0.0758, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.24435921013355255, | |
| "learning_rate": 0.0002813920732151177, | |
| "loss": 0.0772, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.2376328855752945, | |
| "learning_rate": 0.0002812569315841521, | |
| "loss": 0.0935, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.0582437627017498, | |
| "learning_rate": 0.0002811213336830373, | |
| "loss": 0.0224, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.19927099347114563, | |
| "learning_rate": 0.00028098527998313334, | |
| "loss": 0.1243, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.15403445065021515, | |
| "learning_rate": 0.00028084877095738473, | |
| "loss": 0.0278, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.078863725066185, | |
| "eval_runtime": 14.7476, | |
| "eval_samples_per_second": 32.344, | |
| "eval_steps_per_second": 8.137, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.240775465965271, | |
| "learning_rate": 0.0002807118070803187, | |
| "loss": 0.0359, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.38222241401672363, | |
| "learning_rate": 0.0002805743888280437, | |
| "loss": 0.1152, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.20165561139583588, | |
| "learning_rate": 0.0002804365166782476, | |
| "loss": 0.0426, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.4264529049396515, | |
| "learning_rate": 0.00028029819111019614, | |
| "loss": 0.1029, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.22892819344997406, | |
| "learning_rate": 0.00028015941260473113, | |
| "loss": 0.0956, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.29828211665153503, | |
| "learning_rate": 0.00028002018164426893, | |
| "loss": 0.0788, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.19386076927185059, | |
| "learning_rate": 0.00027988049871279874, | |
| "loss": 0.0889, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.30981379747390747, | |
| "learning_rate": 0.0002797403642958808, | |
| "loss": 0.1692, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.36764079332351685, | |
| "learning_rate": 0.00027959977888064477, | |
| "loss": 0.0837, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.1701124757528305, | |
| "learning_rate": 0.00027945874295578826, | |
| "loss": 0.1026, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.11988788843154907, | |
| "learning_rate": 0.0002793172570115746, | |
| "loss": 0.0993, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.15950341522693634, | |
| "learning_rate": 0.00027917532153983176, | |
| "loss": 0.0597, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.18084204196929932, | |
| "learning_rate": 0.0002790329370339501, | |
| "loss": 0.0776, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.1948510855436325, | |
| "learning_rate": 0.000278890103988881, | |
| "loss": 0.0899, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.16357307136058807, | |
| "learning_rate": 0.0002787468229011351, | |
| "loss": 0.109, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.15433883666992188, | |
| "learning_rate": 0.0002786030942687805, | |
| "loss": 0.0884, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.11737463623285294, | |
| "learning_rate": 0.00027845891859144085, | |
| "loss": 0.0868, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.1610182225704193, | |
| "learning_rate": 0.000278314296370294, | |
| "loss": 0.1315, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.1955747902393341, | |
| "learning_rate": 0.00027816922810806996, | |
| "loss": 0.0893, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.25150609016418457, | |
| "learning_rate": 0.0002780237143090493, | |
| "loss": 0.1179, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.24072997272014618, | |
| "learning_rate": 0.0002778777554790614, | |
| "loss": 0.0967, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.2026025652885437, | |
| "learning_rate": 0.00027773135212548245, | |
| "loss": 0.0809, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.17768602073192596, | |
| "learning_rate": 0.000277584504757234, | |
| "loss": 0.0726, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.22531519830226898, | |
| "learning_rate": 0.00027743721388478115, | |
| "loss": 0.0797, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.22690407931804657, | |
| "learning_rate": 0.00027728948002013053, | |
| "loss": 0.068, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.3111308217048645, | |
| "learning_rate": 0.00027714130367682875, | |
| "loss": 0.1222, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.31476208567619324, | |
| "learning_rate": 0.0002769926853699606, | |
| "loss": 0.123, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.19214238226413727, | |
| "learning_rate": 0.0002768436256161471, | |
| "loss": 0.0778, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.21092087030410767, | |
| "learning_rate": 0.0002766941249335439, | |
| "loss": 0.0908, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.24106797575950623, | |
| "learning_rate": 0.00027654418384183925, | |
| "loss": 0.1054, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.24553944170475006, | |
| "learning_rate": 0.0002763938028622526, | |
| "loss": 0.0687, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.18032313883304596, | |
| "learning_rate": 0.0002762429825175323, | |
| "loss": 0.0984, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.2341250777244568, | |
| "learning_rate": 0.000276091723331954, | |
| "loss": 0.0861, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.23054689168930054, | |
| "learning_rate": 0.000275940025831319, | |
| "loss": 0.1023, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.15571041405200958, | |
| "learning_rate": 0.000275787890542952, | |
| "loss": 0.061, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.16762854158878326, | |
| "learning_rate": 0.0002756353179956998, | |
| "loss": 0.1124, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.16507089138031006, | |
| "learning_rate": 0.000275482308719929, | |
| "loss": 0.1121, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.166361466050148, | |
| "learning_rate": 0.00027532886324752433, | |
| "loss": 0.1243, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.21798831224441528, | |
| "learning_rate": 0.000275174982111887, | |
| "loss": 0.1074, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.19063718616962433, | |
| "learning_rate": 0.0002750206658479324, | |
| "loss": 0.1058, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.20267756283283234, | |
| "learning_rate": 0.00027486591499208867, | |
| "loss": 0.0875, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.11513421684503555, | |
| "learning_rate": 0.0002747107300822946, | |
| "loss": 0.0674, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.16988199949264526, | |
| "learning_rate": 0.0002745551116579978, | |
| "loss": 0.089, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.20574574172496796, | |
| "learning_rate": 0.0002743990602601529, | |
| "loss": 0.0906, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.14412453770637512, | |
| "learning_rate": 0.00027424257643121966, | |
| "loss": 0.0996, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.1305454671382904, | |
| "learning_rate": 0.00027408566071516084, | |
| "loss": 0.0636, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.18056617677211761, | |
| "learning_rate": 0.00027392831365744073, | |
| "loss": 0.1004, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.15762409567832947, | |
| "learning_rate": 0.00027377053580502297, | |
| "loss": 0.0938, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.2165631651878357, | |
| "learning_rate": 0.00027361232770636856, | |
| "loss": 0.0829, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.21345216035842896, | |
| "learning_rate": 0.0002734536899114343, | |
| "loss": 0.1053, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.22907692193984985, | |
| "learning_rate": 0.00027329462297167066, | |
| "loss": 0.1451, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.24929089844226837, | |
| "learning_rate": 0.0002731351274400198, | |
| "loss": 0.0909, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.13142186403274536, | |
| "learning_rate": 0.00027297520387091376, | |
| "loss": 0.0523, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.27698859572410583, | |
| "learning_rate": 0.0002728148528202725, | |
| "loss": 0.0865, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.2599867880344391, | |
| "learning_rate": 0.000272654074845502, | |
| "loss": 0.0654, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.22103819251060486, | |
| "learning_rate": 0.0002724928705054924, | |
| "loss": 0.1108, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.2073899507522583, | |
| "learning_rate": 0.0002723312403606157, | |
| "loss": 0.0928, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.23784543573856354, | |
| "learning_rate": 0.00027216918497272426, | |
| "loss": 0.095, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.16584208607673645, | |
| "learning_rate": 0.0002720067049051486, | |
| "loss": 0.0521, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.1800609678030014, | |
| "learning_rate": 0.0002718438007226955, | |
| "loss": 0.0737, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.1386508196592331, | |
| "learning_rate": 0.0002716804729916461, | |
| "loss": 0.0522, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.22217071056365967, | |
| "learning_rate": 0.0002715167222797537, | |
| "loss": 0.1045, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.26573020219802856, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.0719, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.20932160317897797, | |
| "learning_rate": 0.00027118795419180336, | |
| "loss": 0.1289, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.19539090991020203, | |
| "learning_rate": 0.000271022937958596, | |
| "loss": 0.0606, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.15271329879760742, | |
| "learning_rate": 0.00027085750103024295, | |
| "loss": 0.0343, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.25894200801849365, | |
| "learning_rate": 0.00027069164398182944, | |
| "loss": 0.0762, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.16486695408821106, | |
| "learning_rate": 0.00027052536738990125, | |
| "loss": 0.0618, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.24119453132152557, | |
| "learning_rate": 0.00027035867183246244, | |
| "loss": 0.1013, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.35628098249435425, | |
| "learning_rate": 0.00027019155788897355, | |
| "loss": 0.0878, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.14005188643932343, | |
| "learning_rate": 0.0002700240261403494, | |
| "loss": 0.0432, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.13526731729507446, | |
| "learning_rate": 0.0002698560771689572, | |
| "loss": 0.0513, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.2159578949213028, | |
| "learning_rate": 0.0002696877115586146, | |
| "loss": 0.0831, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.26970624923706055, | |
| "learning_rate": 0.00026951892989458744, | |
| "loss": 0.1336, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.17370541393756866, | |
| "learning_rate": 0.00026934973276358787, | |
| "loss": 0.073, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.19606231153011322, | |
| "learning_rate": 0.0002691801207537722, | |
| "loss": 0.0718, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.2545556426048279, | |
| "learning_rate": 0.0002690100944547391, | |
| "loss": 0.1326, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.15419915318489075, | |
| "learning_rate": 0.0002688396544575271, | |
| "loss": 0.0391, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.2486819475889206, | |
| "learning_rate": 0.0002686688013546131, | |
| "loss": 0.1099, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.12814386188983917, | |
| "learning_rate": 0.0002684975357399099, | |
| "loss": 0.0437, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.09224840253591537, | |
| "learning_rate": 0.00026832585820876407, | |
| "loss": 0.0487, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.16062654554843903, | |
| "learning_rate": 0.00026815376935795444, | |
| "loss": 0.0549, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.267597496509552, | |
| "learning_rate": 0.0002679812697856894, | |
| "loss": 0.117, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.23974187672138214, | |
| "learning_rate": 0.0002678083600916051, | |
| "loss": 0.0536, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.1853066086769104, | |
| "learning_rate": 0.0002676350408767634, | |
| "loss": 0.0392, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.4043184220790863, | |
| "learning_rate": 0.00026746131274364975, | |
| "loss": 0.1079, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.19574593007564545, | |
| "learning_rate": 0.0002672871762961709, | |
| "loss": 0.0866, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.34985387325286865, | |
| "learning_rate": 0.00026711263213965314, | |
| "loss": 0.1326, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.3007662892341614, | |
| "learning_rate": 0.0002669376808808399, | |
| "loss": 0.0793, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.2934662103652954, | |
| "learning_rate": 0.00026676232312788993, | |
| "loss": 0.1095, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.19983640313148499, | |
| "learning_rate": 0.0002665865594903748, | |
| "loss": 0.063, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.20034237205982208, | |
| "learning_rate": 0.0002664103905792772, | |
| "loss": 0.0927, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.24908727407455444, | |
| "learning_rate": 0.0002662338170069884, | |
| "loss": 0.0869, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.14556318521499634, | |
| "learning_rate": 0.0002660568393873066, | |
| "loss": 0.0679, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.14582981169223785, | |
| "learning_rate": 0.0002658794583354343, | |
| "loss": 0.062, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.21219995617866516, | |
| "learning_rate": 0.00026570167446797656, | |
| "loss": 0.1065, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.1637437492609024, | |
| "learning_rate": 0.0002655234884029385, | |
| "loss": 0.0754, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.3341504633426666, | |
| "learning_rate": 0.00026534490075972363, | |
| "loss": 0.1185, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.28448009490966797, | |
| "learning_rate": 0.00026516591215913115, | |
| "loss": 0.1244, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.10381971299648285, | |
| "learning_rate": 0.0002649865232233541, | |
| "loss": 0.0538, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.30114489793777466, | |
| "learning_rate": 0.00026480673457597733, | |
| "loss": 0.1083, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.25989478826522827, | |
| "learning_rate": 0.00026462654684197487, | |
| "loss": 0.123, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.14556318521499634, | |
| "learning_rate": 0.00026444596064770833, | |
| "loss": 0.121, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.11710379272699356, | |
| "learning_rate": 0.0002642649766209242, | |
| "loss": 0.0585, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.16899935901165009, | |
| "learning_rate": 0.000264083595390752, | |
| "loss": 0.0905, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.14508718252182007, | |
| "learning_rate": 0.00026390181758770205, | |
| "loss": 0.0807, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.3146648705005646, | |
| "learning_rate": 0.000263719643843663, | |
| "loss": 0.1388, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.18293187022209167, | |
| "learning_rate": 0.0002635370747919002, | |
| "loss": 0.094, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.1427004188299179, | |
| "learning_rate": 0.0002633541110670528, | |
| "loss": 0.0749, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.2598584294319153, | |
| "learning_rate": 0.0002631707533051321, | |
| "loss": 0.1237, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.19870835542678833, | |
| "learning_rate": 0.0002629870021435192, | |
| "loss": 0.0817, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.2234540730714798, | |
| "learning_rate": 0.00026280285822096247, | |
| "loss": 0.1058, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.1785740852355957, | |
| "learning_rate": 0.0002626183221775758, | |
| "loss": 0.0676, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.11512486636638641, | |
| "learning_rate": 0.000262433394654836, | |
| "loss": 0.0893, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.35373592376708984, | |
| "learning_rate": 0.00026224807629558094, | |
| "loss": 0.1077, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.2722702920436859, | |
| "learning_rate": 0.0002620623677440068, | |
| "loss": 0.0925, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.4532068073749542, | |
| "learning_rate": 0.0002618762696456664, | |
| "loss": 0.1217, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.19945968687534332, | |
| "learning_rate": 0.0002616897826474666, | |
| "loss": 0.0899, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.25592172145843506, | |
| "learning_rate": 0.00026150290739766606, | |
| "loss": 0.0519, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.16839353740215302, | |
| "learning_rate": 0.00026131564454587314, | |
| "loss": 0.0814, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.28912433981895447, | |
| "learning_rate": 0.0002611279947430436, | |
| "loss": 0.0737, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.053034551441669464, | |
| "learning_rate": 0.0002609399586414782, | |
| "loss": 0.0157, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.34488940238952637, | |
| "learning_rate": 0.0002607515368948206, | |
| "loss": 0.0951, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.3413633704185486, | |
| "learning_rate": 0.00026056273015805494, | |
| "loss": 0.0712, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.4603371024131775, | |
| "learning_rate": 0.0002603735390875039, | |
| "loss": 0.0946, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.243332177400589, | |
| "learning_rate": 0.0002601839643408259, | |
| "loss": 0.041, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.27589449286460876, | |
| "learning_rate": 0.0002599940065770131, | |
| "loss": 0.0841, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.3786303997039795, | |
| "learning_rate": 0.0002598036664563893, | |
| "loss": 0.1031, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.23370252549648285, | |
| "learning_rate": 0.00025961294464060716, | |
| "loss": 0.0509, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.3785135746002197, | |
| "learning_rate": 0.00025942184179264635, | |
| "loss": 0.1116, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.3081932067871094, | |
| "learning_rate": 0.0002592303585768111, | |
| "loss": 0.08, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.13592147827148438, | |
| "learning_rate": 0.00025903849565872767, | |
| "loss": 0.0269, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.29880547523498535, | |
| "learning_rate": 0.0002588462537053424, | |
| "loss": 0.0596, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.11771093308925629, | |
| "learning_rate": 0.00025865363338491913, | |
| "loss": 0.0549, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.2312057763338089, | |
| "learning_rate": 0.00025846063536703705, | |
| "loss": 0.0744, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.33669716119766235, | |
| "learning_rate": 0.00025826726032258815, | |
| "loss": 0.059, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.2426741123199463, | |
| "learning_rate": 0.00025807350892377513, | |
| "loss": 0.0996, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.4019070863723755, | |
| "learning_rate": 0.000257879381844109, | |
| "loss": 0.0864, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.09328150004148483, | |
| "learning_rate": 0.00025768487975840653, | |
| "loss": 0.0328, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.40782174468040466, | |
| "learning_rate": 0.00025749000334278826, | |
| "loss": 0.0446, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.21026232838630676, | |
| "learning_rate": 0.00025729475327467574, | |
| "loss": 0.096, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.3340080678462982, | |
| "learning_rate": 0.00025709913023278967, | |
| "loss": 0.1243, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.07237789034843445, | |
| "eval_runtime": 14.7609, | |
| "eval_samples_per_second": 32.315, | |
| "eval_steps_per_second": 8.13, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.2728588879108429, | |
| "learning_rate": 0.00025690313489714706, | |
| "loss": 0.1162, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.22674015164375305, | |
| "learning_rate": 0.00025670676794905915, | |
| "loss": 0.0822, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.13643956184387207, | |
| "learning_rate": 0.0002565100300711289, | |
| "loss": 0.0652, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.1212250292301178, | |
| "learning_rate": 0.0002563129219472488, | |
| "loss": 0.0515, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.15632915496826172, | |
| "learning_rate": 0.0002561154442625983, | |
| "loss": 0.105, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.14310358464717865, | |
| "learning_rate": 0.00025591759770364145, | |
| "loss": 0.078, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.1461591273546219, | |
| "learning_rate": 0.00025571938295812475, | |
| "loss": 0.0626, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.12564843893051147, | |
| "learning_rate": 0.00025552080071507423, | |
| "loss": 0.1015, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.18360354006290436, | |
| "learning_rate": 0.00025532185166479384, | |
| "loss": 0.125, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.26957467198371887, | |
| "learning_rate": 0.00025512253649886236, | |
| "loss": 0.1049, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.18892253935337067, | |
| "learning_rate": 0.00025492285591013116, | |
| "loss": 0.0907, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.25057581067085266, | |
| "learning_rate": 0.0002547228105927221, | |
| "loss": 0.1081, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.13890071213245392, | |
| "learning_rate": 0.00025452240124202477, | |
| "loss": 0.0865, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.17899222671985626, | |
| "learning_rate": 0.0002543216285546942, | |
| "loss": 0.0437, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.26809147000312805, | |
| "learning_rate": 0.00025412049322864845, | |
| "loss": 0.0507, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.19062833487987518, | |
| "learning_rate": 0.0002539189959630662, | |
| "loss": 0.0516, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.23480018973350525, | |
| "learning_rate": 0.0002537171374583843, | |
| "loss": 0.0672, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.10694094747304916, | |
| "learning_rate": 0.0002535149184162952, | |
| "loss": 0.0248, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.2778875231742859, | |
| "learning_rate": 0.0002533123395397448, | |
| "loss": 0.1295, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.30790090560913086, | |
| "learning_rate": 0.00025310940153292974, | |
| "loss": 0.0518, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.2887485921382904, | |
| "learning_rate": 0.00025290610510129513, | |
| "loss": 0.0739, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.3820766508579254, | |
| "learning_rate": 0.00025270245095153197, | |
| "loss": 0.0873, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.09947656840085983, | |
| "learning_rate": 0.00025249843979157467, | |
| "loss": 0.0137, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.2997414469718933, | |
| "learning_rate": 0.00025229407233059883, | |
| "loss": 0.1314, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.24817639589309692, | |
| "learning_rate": 0.00025208934927901857, | |
| "loss": 0.1275, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.28992751240730286, | |
| "learning_rate": 0.0002518842713484839, | |
| "loss": 0.1294, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.20057415962219238, | |
| "learning_rate": 0.00025167883925187874, | |
| "loss": 0.0559, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.18815775215625763, | |
| "learning_rate": 0.000251473053703318, | |
| "loss": 0.0922, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.2501707375049591, | |
| "learning_rate": 0.00025126691541814514, | |
| "loss": 0.0712, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.19835379719734192, | |
| "learning_rate": 0.00025106042511293005, | |
| "loss": 0.0974, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.1476050615310669, | |
| "learning_rate": 0.0002508535835054661, | |
| "loss": 0.1005, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.18511542677879333, | |
| "learning_rate": 0.0002506463913147679, | |
| "loss": 0.1343, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.1092979907989502, | |
| "learning_rate": 0.0002504388492610687, | |
| "loss": 0.0728, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.11496451497077942, | |
| "learning_rate": 0.00025023095806581797, | |
| "loss": 0.0949, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.10526807606220245, | |
| "learning_rate": 0.0002500227184516789, | |
| "loss": 0.0874, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.12002858519554138, | |
| "learning_rate": 0.0002498141311425258, | |
| "loss": 0.0597, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.18872810900211334, | |
| "learning_rate": 0.00024960519686344164, | |
| "loss": 0.0938, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.15304633975028992, | |
| "learning_rate": 0.0002493959163407154, | |
| "loss": 0.0942, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.13661184906959534, | |
| "learning_rate": 0.0002491862903018398, | |
| "loss": 0.104, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.12348087877035141, | |
| "learning_rate": 0.00024897631947550853, | |
| "loss": 0.0914, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.17801643908023834, | |
| "learning_rate": 0.00024876600459161396, | |
| "loss": 0.1041, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.16505847871303558, | |
| "learning_rate": 0.00024855534638124424, | |
| "loss": 0.0657, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.17176857590675354, | |
| "learning_rate": 0.0002483443455766812, | |
| "loss": 0.0809, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.20494180917739868, | |
| "learning_rate": 0.0002481330029113975, | |
| "loss": 0.0939, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.08561734110116959, | |
| "learning_rate": 0.000247921319120054, | |
| "loss": 0.0316, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.17116233706474304, | |
| "learning_rate": 0.0002477092949384977, | |
| "loss": 0.0593, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.19205418229103088, | |
| "learning_rate": 0.00024749693110375854, | |
| "loss": 0.0684, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.1300123929977417, | |
| "learning_rate": 0.0002472842283540473, | |
| "loss": 0.0581, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.24078501760959625, | |
| "learning_rate": 0.0002470711874287529, | |
| "loss": 0.0483, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.3071228861808777, | |
| "learning_rate": 0.00024685780906843975, | |
| "loss": 0.0961, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.24373668432235718, | |
| "learning_rate": 0.0002466440940148452, | |
| "loss": 0.1139, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.22678449749946594, | |
| "learning_rate": 0.00024643004301087715, | |
| "loss": 0.0324, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.34472745656967163, | |
| "learning_rate": 0.00024621565680061117, | |
| "loss": 0.1041, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.16587162017822266, | |
| "learning_rate": 0.0002460009361292881, | |
| "loss": 0.0992, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.42953774333000183, | |
| "learning_rate": 0.0002457858817433115, | |
| "loss": 0.1284, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.6054782867431641, | |
| "learning_rate": 0.00024557049439024486, | |
| "loss": 0.1034, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.207829549908638, | |
| "learning_rate": 0.0002453547748188092, | |
| "loss": 0.0928, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.36941850185394287, | |
| "learning_rate": 0.00024513872377888036, | |
| "loss": 0.0765, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.20771794021129608, | |
| "learning_rate": 0.0002449223420214864, | |
| "loss": 0.1001, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.16417552530765533, | |
| "learning_rate": 0.00024470563029880497, | |
| "loss": 0.0783, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.12799693644046783, | |
| "learning_rate": 0.0002444885893641609, | |
| "loss": 0.0753, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.21585993468761444, | |
| "learning_rate": 0.00024427121997202313, | |
| "loss": 0.1241, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.1481488198041916, | |
| "learning_rate": 0.00024405352287800266, | |
| "loss": 0.1086, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.18564724922180176, | |
| "learning_rate": 0.00024383549883884949, | |
| "loss": 0.0801, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.16308890283107758, | |
| "learning_rate": 0.00024361714861245015, | |
| "loss": 0.0884, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.10771831125020981, | |
| "learning_rate": 0.00024339847295782503, | |
| "loss": 0.0507, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.11360620707273483, | |
| "learning_rate": 0.00024317947263512578, | |
| "loss": 0.0541, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.17256328463554382, | |
| "learning_rate": 0.00024296014840563264, | |
| "loss": 0.0797, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.14872509241104126, | |
| "learning_rate": 0.00024274050103175192, | |
| "loss": 0.098, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.10749954730272293, | |
| "learning_rate": 0.00024252053127701297, | |
| "loss": 0.0629, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.22221991419792175, | |
| "learning_rate": 0.00024230023990606608, | |
| "loss": 0.0737, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.1851089596748352, | |
| "learning_rate": 0.00024207962768467927, | |
| "loss": 0.0961, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.1685558706521988, | |
| "learning_rate": 0.0002418586953797361, | |
| "loss": 0.0863, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.14281867444515228, | |
| "learning_rate": 0.00024163744375923268, | |
| "loss": 0.0334, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.24673086404800415, | |
| "learning_rate": 0.00024141587359227513, | |
| "loss": 0.1468, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.21355701982975006, | |
| "learning_rate": 0.00024119398564907685, | |
| "loss": 0.1145, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.16007691621780396, | |
| "learning_rate": 0.00024097178070095598, | |
| "loss": 0.0799, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.3183180093765259, | |
| "learning_rate": 0.0002407492595203326, | |
| "loss": 0.1405, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.08811590075492859, | |
| "learning_rate": 0.0002405264228807259, | |
| "loss": 0.0359, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.1502489596605301, | |
| "learning_rate": 0.0002403032715567519, | |
| "loss": 0.0763, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.07442978769540787, | |
| "learning_rate": 0.00024007980632412032, | |
| "loss": 0.0365, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.2458060383796692, | |
| "learning_rate": 0.00023985602795963227, | |
| "loss": 0.0724, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.1589912623167038, | |
| "learning_rate": 0.0002396319372411771, | |
| "loss": 0.0701, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.1447596549987793, | |
| "learning_rate": 0.00023940753494773018, | |
| "loss": 0.0411, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.20220863819122314, | |
| "learning_rate": 0.00023918282185934984, | |
| "loss": 0.082, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.08220729231834412, | |
| "learning_rate": 0.00023895779875717483, | |
| "loss": 0.0423, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.18194489181041718, | |
| "learning_rate": 0.0002387324664234216, | |
| "loss": 0.058, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.2533247470855713, | |
| "learning_rate": 0.00023850682564138142, | |
| "loss": 0.08, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.4217647910118103, | |
| "learning_rate": 0.00023828087719541784, | |
| "loss": 0.1557, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.1498800665140152, | |
| "learning_rate": 0.00023805462187096398, | |
| "loss": 0.0298, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.1469077467918396, | |
| "learning_rate": 0.0002378280604545196, | |
| "loss": 0.0392, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.23052054643630981, | |
| "learning_rate": 0.0002376011937336485, | |
| "loss": 0.1275, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.2608712315559387, | |
| "learning_rate": 0.0002373740224969758, | |
| "loss": 0.0984, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.3406033515930176, | |
| "learning_rate": 0.00023714654753418518, | |
| "loss": 0.1668, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.1383407562971115, | |
| "learning_rate": 0.0002369187696360161, | |
| "loss": 0.0319, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.2986023724079132, | |
| "learning_rate": 0.00023669068959426105, | |
| "loss": 0.0797, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.18390725553035736, | |
| "learning_rate": 0.00023646230820176289, | |
| "loss": 0.0514, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.3618876338005066, | |
| "learning_rate": 0.00023623362625241188, | |
| "loss": 0.1465, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.23905062675476074, | |
| "learning_rate": 0.00023600464454114325, | |
| "loss": 0.0669, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.24474327266216278, | |
| "learning_rate": 0.00023577536386393415, | |
| "loss": 0.1048, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.11233604699373245, | |
| "learning_rate": 0.000235545785017801, | |
| "loss": 0.0653, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.12456522136926651, | |
| "learning_rate": 0.0002353159088007966, | |
| "loss": 0.0855, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.14804989099502563, | |
| "learning_rate": 0.00023508573601200764, | |
| "loss": 0.0554, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.1283787339925766, | |
| "learning_rate": 0.00023485526745155167, | |
| "loss": 0.0644, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.16255222260951996, | |
| "learning_rate": 0.00023462450392057436, | |
| "loss": 0.1088, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.18897709250450134, | |
| "learning_rate": 0.0002343934462212467, | |
| "loss": 0.0673, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.1460375338792801, | |
| "learning_rate": 0.00023416209515676235, | |
| "loss": 0.0923, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.13687273859977722, | |
| "learning_rate": 0.0002339304515313348, | |
| "loss": 0.1142, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.11255405843257904, | |
| "learning_rate": 0.00023369851615019432, | |
| "loss": 0.0513, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.18131427466869354, | |
| "learning_rate": 0.0002334662898195856, | |
| "loss": 0.1058, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.19648568332195282, | |
| "learning_rate": 0.0002332337733467646, | |
| "loss": 0.0721, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.1530655175447464, | |
| "learning_rate": 0.00023300096753999582, | |
| "loss": 0.0698, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.20368973910808563, | |
| "learning_rate": 0.00023276787320854965, | |
| "loss": 0.0925, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.14580555260181427, | |
| "learning_rate": 0.00023253449116269936, | |
| "loss": 0.052, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.20287400484085083, | |
| "learning_rate": 0.00023230082221371832, | |
| "loss": 0.0714, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.2907051742076874, | |
| "learning_rate": 0.00023206686717387737, | |
| "loss": 0.1166, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.3000693619251251, | |
| "learning_rate": 0.00023183262685644174, | |
| "loss": 0.1326, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.0760418102145195, | |
| "learning_rate": 0.0002315981020756683, | |
| "loss": 0.0591, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.144688680768013, | |
| "learning_rate": 0.00023136329364680284, | |
| "loss": 0.074, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.14553490281105042, | |
| "learning_rate": 0.00023112820238607712, | |
| "loss": 0.0609, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.13767151534557343, | |
| "learning_rate": 0.0002308928291107061, | |
| "loss": 0.0694, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.1333126723766327, | |
| "learning_rate": 0.00023065717463888503, | |
| "loss": 0.0509, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.1710643619298935, | |
| "learning_rate": 0.00023042123978978663, | |
| "loss": 0.0957, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.14117231965065002, | |
| "learning_rate": 0.00023018502538355823, | |
| "loss": 0.0372, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.24988646805286407, | |
| "learning_rate": 0.0002299485322413191, | |
| "loss": 0.0711, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.225083127617836, | |
| "learning_rate": 0.00022971176118515731, | |
| "loss": 0.0913, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.2095450758934021, | |
| "learning_rate": 0.00022947471303812704, | |
| "loss": 0.0485, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.2737296521663666, | |
| "learning_rate": 0.0002292373886242456, | |
| "loss": 0.0643, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.15709654986858368, | |
| "learning_rate": 0.0002289997887684908, | |
| "loss": 0.0327, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.17161165177822113, | |
| "learning_rate": 0.00022876191429679785, | |
| "loss": 0.0356, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.4428029954433441, | |
| "learning_rate": 0.00022852376603605656, | |
| "loss": 0.0976, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.3834541440010071, | |
| "learning_rate": 0.00022828534481410845, | |
| "loss": 0.1103, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.4154812693595886, | |
| "learning_rate": 0.00022804665145974396, | |
| "loss": 0.1864, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.2642601430416107, | |
| "learning_rate": 0.0002278076868026995, | |
| "loss": 0.0944, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.166983962059021, | |
| "learning_rate": 0.0002275684516736545, | |
| "loss": 0.0799, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.1374656707048416, | |
| "learning_rate": 0.0002273289469042287, | |
| "loss": 0.0509, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.12492585182189941, | |
| "learning_rate": 0.00022708917332697905, | |
| "loss": 0.0491, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.0952799916267395, | |
| "learning_rate": 0.000226849131775397, | |
| "loss": 0.0561, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.16703763604164124, | |
| "learning_rate": 0.00022660882308390544, | |
| "loss": 0.0882, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.17010749876499176, | |
| "learning_rate": 0.00022636824808785602, | |
| "loss": 0.0465, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.15894334018230438, | |
| "learning_rate": 0.0002261274076235259, | |
| "loss": 0.0787, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.3054545819759369, | |
| "learning_rate": 0.00022588630252811528, | |
| "loss": 0.0808, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.09363073855638504, | |
| "eval_runtime": 14.6975, | |
| "eval_samples_per_second": 32.455, | |
| "eval_steps_per_second": 8.165, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.07171467691659927, | |
| "learning_rate": 0.00022564493363974413, | |
| "loss": 0.0222, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.17009137570858002, | |
| "learning_rate": 0.00022540330179744933, | |
| "loss": 0.0542, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.07475418597459793, | |
| "learning_rate": 0.000225161407841182, | |
| "loss": 0.0386, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.20071469247341156, | |
| "learning_rate": 0.0002249192526118043, | |
| "loss": 0.0566, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.40051212906837463, | |
| "learning_rate": 0.0002246768369510867, | |
| "loss": 0.067, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.23527373373508453, | |
| "learning_rate": 0.0002244341617017049, | |
| "loss": 0.0945, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.4186932146549225, | |
| "learning_rate": 0.00022419122770723699, | |
| "loss": 0.0524, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.18408560752868652, | |
| "learning_rate": 0.00022394803581216047, | |
| "loss": 0.0421, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.25409191846847534, | |
| "learning_rate": 0.00022370458686184942, | |
| "loss": 0.0583, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.15828213095664978, | |
| "learning_rate": 0.00022346088170257147, | |
| "loss": 0.027, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.3453011214733124, | |
| "learning_rate": 0.00022321692118148478, | |
| "loss": 0.0444, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.2533039450645447, | |
| "learning_rate": 0.00022297270614663533, | |
| "loss": 0.0376, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.2254706472158432, | |
| "learning_rate": 0.00022272823744695365, | |
| "loss": 0.0226, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.27252522110939026, | |
| "learning_rate": 0.00022248351593225223, | |
| "loss": 0.0645, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.27917397022247314, | |
| "learning_rate": 0.00022223854245322235, | |
| "loss": 0.0407, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.13697022199630737, | |
| "learning_rate": 0.00022199331786143097, | |
| "loss": 0.0603, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.5482609272003174, | |
| "learning_rate": 0.00022174784300931828, | |
| "loss": 0.0724, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.2505982220172882, | |
| "learning_rate": 0.00022150211875019416, | |
| "loss": 0.0255, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.10142415761947632, | |
| "learning_rate": 0.00022125614593823553, | |
| "loss": 0.014, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.2175186574459076, | |
| "learning_rate": 0.00022100992542848342, | |
| "loss": 0.0366, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.32991528511047363, | |
| "learning_rate": 0.00022076345807683974, | |
| "loss": 0.06, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.4545266330242157, | |
| "learning_rate": 0.00022051674474006457, | |
| "loss": 0.0535, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.2949434518814087, | |
| "learning_rate": 0.00022026978627577302, | |
| "loss": 0.0379, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.9262584447860718, | |
| "learning_rate": 0.0002200225835424324, | |
| "loss": 0.197, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.1416931003332138, | |
| "learning_rate": 0.00021977513739935894, | |
| "loss": 0.0142, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.23968350887298584, | |
| "learning_rate": 0.00021952744870671527, | |
| "loss": 0.0445, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.18966619670391083, | |
| "learning_rate": 0.00021927951832550696, | |
| "loss": 0.0303, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.12732306122779846, | |
| "learning_rate": 0.00021903134711757973, | |
| "loss": 0.0853, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.34209054708480835, | |
| "learning_rate": 0.00021878293594561655, | |
| "loss": 0.1223, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.30927759408950806, | |
| "learning_rate": 0.00021853428567313453, | |
| "loss": 0.1215, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.14330783486366272, | |
| "learning_rate": 0.00021828539716448186, | |
| "loss": 0.0478, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.09433628618717194, | |
| "learning_rate": 0.00021803627128483494, | |
| "loss": 0.0409, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.15185511112213135, | |
| "learning_rate": 0.00021778690890019532, | |
| "loss": 0.0794, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.12092185020446777, | |
| "learning_rate": 0.00021753731087738654, | |
| "loss": 0.0358, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.09449411928653717, | |
| "learning_rate": 0.00021728747808405152, | |
| "loss": 0.0626, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.1485297530889511, | |
| "learning_rate": 0.00021703741138864906, | |
| "loss": 0.0685, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.16232629120349884, | |
| "learning_rate": 0.00021678711166045106, | |
| "loss": 0.051, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.18323880434036255, | |
| "learning_rate": 0.00021653657976953953, | |
| "loss": 0.0704, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.13198308646678925, | |
| "learning_rate": 0.00021628581658680355, | |
| "loss": 0.0746, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.14159634709358215, | |
| "learning_rate": 0.0002160348229839362, | |
| "loss": 0.0431, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.07700249552726746, | |
| "learning_rate": 0.00021578359983343148, | |
| "loss": 0.0224, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.16824749112129211, | |
| "learning_rate": 0.00021553214800858127, | |
| "loss": 0.0411, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.20787864923477173, | |
| "learning_rate": 0.0002152804683834726, | |
| "loss": 0.0366, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.21740445494651794, | |
| "learning_rate": 0.0002150285618329841, | |
| "loss": 0.0903, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.22452165186405182, | |
| "learning_rate": 0.0002147764292327834, | |
| "loss": 0.0356, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.26688578724861145, | |
| "learning_rate": 0.0002145240714593239, | |
| "loss": 0.0325, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.3858661949634552, | |
| "learning_rate": 0.00021427148938984157, | |
| "loss": 0.0674, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.43455496430397034, | |
| "learning_rate": 0.00021401868390235232, | |
| "loss": 0.0612, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.20362605154514313, | |
| "learning_rate": 0.0002137656558756486, | |
| "loss": 0.0206, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.5878596305847168, | |
| "learning_rate": 0.00021351240618929632, | |
| "loss": 0.1207, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.1784306913614273, | |
| "learning_rate": 0.000213258935723632, | |
| "loss": 0.0421, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.47718602418899536, | |
| "learning_rate": 0.00021300524535975977, | |
| "loss": 0.1035, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.3729299008846283, | |
| "learning_rate": 0.00021275133597954793, | |
| "loss": 0.1177, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.22808651626110077, | |
| "learning_rate": 0.00021249720846562624, | |
| "loss": 0.0381, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.2834159731864929, | |
| "learning_rate": 0.00021224286370138268, | |
| "loss": 0.0334, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.19477446377277374, | |
| "learning_rate": 0.00021198830257096053, | |
| "loss": 0.0438, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.05400063097476959, | |
| "learning_rate": 0.00021173352595925502, | |
| "loss": 0.0107, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.15404914319515228, | |
| "learning_rate": 0.00021147853475191058, | |
| "loss": 0.0239, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.2577894330024719, | |
| "learning_rate": 0.00021122332983531747, | |
| "loss": 0.0344, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.7029692530632019, | |
| "learning_rate": 0.00021096791209660902, | |
| "loss": 0.1042, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.09395071119070053, | |
| "learning_rate": 0.00021071228242365824, | |
| "loss": 0.0125, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.3859443664550781, | |
| "learning_rate": 0.00021045644170507484, | |
| "loss": 0.0751, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.20036044716835022, | |
| "learning_rate": 0.00021020039083020217, | |
| "loss": 0.0379, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.22928644716739655, | |
| "learning_rate": 0.00020994413068911423, | |
| "loss": 0.0532, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.2149987667798996, | |
| "learning_rate": 0.00020968766217261233, | |
| "loss": 0.0379, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.47850465774536133, | |
| "learning_rate": 0.00020943098617222215, | |
| "loss": 0.0885, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.2132718861103058, | |
| "learning_rate": 0.00020917410358019072, | |
| "loss": 0.0439, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.06894449889659882, | |
| "learning_rate": 0.000208917015289483, | |
| "loss": 0.0147, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.2504015564918518, | |
| "learning_rate": 0.00020865972219377932, | |
| "loss": 0.0551, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.21898828446865082, | |
| "learning_rate": 0.0002084022251874716, | |
| "loss": 0.0768, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.14049361646175385, | |
| "learning_rate": 0.00020814452516566075, | |
| "loss": 0.0204, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.17026256024837494, | |
| "learning_rate": 0.00020788662302415352, | |
| "loss": 0.027, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.2352689951658249, | |
| "learning_rate": 0.00020762851965945892, | |
| "loss": 0.0789, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.31628891825675964, | |
| "learning_rate": 0.00020737021596878578, | |
| "loss": 0.0518, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.26351508498191833, | |
| "learning_rate": 0.00020711171285003915, | |
| "loss": 0.0499, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.18696492910385132, | |
| "learning_rate": 0.00020685301120181734, | |
| "loss": 0.0487, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.1336275190114975, | |
| "learning_rate": 0.0002065941119234087, | |
| "loss": 0.0441, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.17000997066497803, | |
| "learning_rate": 0.00020633501591478884, | |
| "loss": 0.0391, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.2624777853488922, | |
| "learning_rate": 0.0002060757240766168, | |
| "loss": 0.0736, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.18875586986541748, | |
| "learning_rate": 0.00020581623731023277, | |
| "loss": 0.0449, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.2557006776332855, | |
| "learning_rate": 0.00020555655651765433, | |
| "loss": 0.0296, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.27907809615135193, | |
| "learning_rate": 0.0002052966826015735, | |
| "loss": 0.0263, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.25195273756980896, | |
| "learning_rate": 0.00020503661646535388, | |
| "loss": 0.0199, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.34424659609794617, | |
| "learning_rate": 0.0002047763590130269, | |
| "loss": 0.1449, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.28247949481010437, | |
| "learning_rate": 0.0002045159111492893, | |
| "loss": 0.0371, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.15257826447486877, | |
| "learning_rate": 0.00020425527377949956, | |
| "loss": 0.0171, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.2261778712272644, | |
| "learning_rate": 0.0002039944478096751, | |
| "loss": 0.0405, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.2752448618412018, | |
| "learning_rate": 0.00020373343414648877, | |
| "loss": 0.0707, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.3369431495666504, | |
| "learning_rate": 0.00020347223369726586, | |
| "loss": 0.1337, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.34381601214408875, | |
| "learning_rate": 0.00020321084736998118, | |
| "loss": 0.1116, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.4304129183292389, | |
| "learning_rate": 0.00020294927607325539, | |
| "loss": 0.1044, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.186915785074234, | |
| "learning_rate": 0.0002026875207163523, | |
| "loss": 0.0438, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.15853986144065857, | |
| "learning_rate": 0.0002024255822091757, | |
| "loss": 0.0171, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.22487328946590424, | |
| "learning_rate": 0.00020216346146226558, | |
| "loss": 0.0545, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.1993045210838318, | |
| "learning_rate": 0.00020190115938679593, | |
| "loss": 0.0937, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.0910387709736824, | |
| "learning_rate": 0.00020163867689457072, | |
| "loss": 0.0179, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.22309695184230804, | |
| "learning_rate": 0.00020137601489802123, | |
| "loss": 0.0758, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.1319982260465622, | |
| "learning_rate": 0.00020111317431020272, | |
| "loss": 0.0369, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.09432458132505417, | |
| "learning_rate": 0.0002008501560447911, | |
| "loss": 0.0291, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.09810501337051392, | |
| "learning_rate": 0.00020058696101608027, | |
| "loss": 0.0252, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.26495859026908875, | |
| "learning_rate": 0.0002003235901389782, | |
| "loss": 0.0555, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.6845064163208008, | |
| "learning_rate": 0.00020006004432900442, | |
| "loss": 0.0952, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.186613067984581, | |
| "learning_rate": 0.0001997963245022863, | |
| "loss": 0.0419, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.22056430578231812, | |
| "learning_rate": 0.00019953243157555647, | |
| "loss": 0.041, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.30706262588500977, | |
| "learning_rate": 0.00019926836646614885, | |
| "loss": 0.0507, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.21987871825695038, | |
| "learning_rate": 0.00019900413009199625, | |
| "loss": 0.0397, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.2214607149362564, | |
| "learning_rate": 0.00019873972337162667, | |
| "loss": 0.0349, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.37210360169410706, | |
| "learning_rate": 0.00019847514722416026, | |
| "loss": 0.075, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.2434106171131134, | |
| "learning_rate": 0.0001982104025693062, | |
| "loss": 0.0284, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.22016049921512604, | |
| "learning_rate": 0.00019794549032735932, | |
| "loss": 0.032, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.07571116834878922, | |
| "learning_rate": 0.0001976804114191971, | |
| "loss": 0.0079, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.35380011796951294, | |
| "learning_rate": 0.00019741516676627632, | |
| "loss": 0.1136, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.2167171835899353, | |
| "learning_rate": 0.00019714975729062998, | |
| "loss": 0.0448, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.37797045707702637, | |
| "learning_rate": 0.00019688418391486398, | |
| "loss": 0.1041, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.6682038903236389, | |
| "learning_rate": 0.00019661844756215397, | |
| "loss": 0.0392, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.15291425585746765, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.0154, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.276319295167923, | |
| "learning_rate": 0.00019608648962143394, | |
| "loss": 0.0474, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.35119596123695374, | |
| "learning_rate": 0.00019582026988259506, | |
| "loss": 0.0549, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.36834511160850525, | |
| "learning_rate": 0.0001955538908651481, | |
| "loss": 0.0458, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.32360026240348816, | |
| "learning_rate": 0.00019528735349506906, | |
| "loss": 0.029, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.3501654863357544, | |
| "learning_rate": 0.00019502065869888473, | |
| "loss": 0.0687, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.260672390460968, | |
| "learning_rate": 0.000194753807403669, | |
| "loss": 0.0546, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.3679283559322357, | |
| "learning_rate": 0.00019448680053703971, | |
| "loss": 0.075, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.3225049376487732, | |
| "learning_rate": 0.00019421963902715563, | |
| "loss": 0.0821, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.20469306409358978, | |
| "learning_rate": 0.0001939523238027129, | |
| "loss": 0.0775, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.22201740741729736, | |
| "learning_rate": 0.0001936848557929423, | |
| "loss": 0.0265, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.2975887358188629, | |
| "learning_rate": 0.0001934172359276054, | |
| "loss": 0.0892, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.2806803584098816, | |
| "learning_rate": 0.00019314946513699187, | |
| "loss": 0.0394, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.23834392428398132, | |
| "learning_rate": 0.0001928815443519158, | |
| "loss": 0.0469, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.2856217920780182, | |
| "learning_rate": 0.000192613474503713, | |
| "loss": 0.1068, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.18297094106674194, | |
| "learning_rate": 0.00019234525652423714, | |
| "loss": 0.0521, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.26084813475608826, | |
| "learning_rate": 0.00019207689134585694, | |
| "loss": 0.0729, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.14558996260166168, | |
| "learning_rate": 0.00019180837990145287, | |
| "loss": 0.0275, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.128230482339859, | |
| "learning_rate": 0.0001915397231244137, | |
| "loss": 0.0406, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.057518381625413895, | |
| "learning_rate": 0.0001912709219486336, | |
| "loss": 0.0127, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.16675953567028046, | |
| "learning_rate": 0.0001910019773085085, | |
| "loss": 0.0455, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.14262209832668304, | |
| "learning_rate": 0.0001907328901389331, | |
| "loss": 0.0444, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.1892000138759613, | |
| "learning_rate": 0.00019046366137529758, | |
| "loss": 0.0485, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.22300001978874207, | |
| "learning_rate": 0.0001901942919534843, | |
| "loss": 0.0533, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.19573500752449036, | |
| "learning_rate": 0.00018992478280986468, | |
| "loss": 0.0825, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.2073289453983307, | |
| "learning_rate": 0.00018965513488129559, | |
| "loss": 0.0695, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.17569467425346375, | |
| "learning_rate": 0.00018938534910511648, | |
| "loss": 0.0474, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 0.07800926268100739, | |
| "eval_runtime": 14.7232, | |
| "eval_samples_per_second": 32.398, | |
| "eval_steps_per_second": 8.15, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.2483418583869934, | |
| "learning_rate": 0.00018911542641914612, | |
| "loss": 0.0522, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.22553446888923645, | |
| "learning_rate": 0.00018884536776167898, | |
| "loss": 0.0624, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.2794416546821594, | |
| "learning_rate": 0.00018857517407148232, | |
| "loss": 0.0591, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.4945233166217804, | |
| "learning_rate": 0.00018830484628779267, | |
| "loss": 0.1097, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.22541265189647675, | |
| "learning_rate": 0.00018803438535031287, | |
| "loss": 0.11, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.1390594094991684, | |
| "learning_rate": 0.00018776379219920844, | |
| "loss": 0.0238, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.35142239928245544, | |
| "learning_rate": 0.00018749306777510462, | |
| "loss": 0.105, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.23132985830307007, | |
| "learning_rate": 0.00018722221301908294, | |
| "loss": 0.0271, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.11399706453084946, | |
| "learning_rate": 0.00018695122887267787, | |
| "loss": 0.0383, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.27700984477996826, | |
| "learning_rate": 0.00018668011627787396, | |
| "loss": 0.0477, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.13391317427158356, | |
| "learning_rate": 0.00018640887617710195, | |
| "loss": 0.028, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.23833520710468292, | |
| "learning_rate": 0.00018613750951323603, | |
| "loss": 0.0725, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.12027294188737869, | |
| "learning_rate": 0.0001858660172295901, | |
| "loss": 0.0181, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.2397276610136032, | |
| "learning_rate": 0.00018559440026991506, | |
| "loss": 0.0548, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.19492855668067932, | |
| "learning_rate": 0.00018532265957839494, | |
| "loss": 0.0349, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.36717554926872253, | |
| "learning_rate": 0.000185050796099644, | |
| "loss": 0.103, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.19141976535320282, | |
| "learning_rate": 0.0001847788107787033, | |
| "loss": 0.0441, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.19812935590744019, | |
| "learning_rate": 0.00018450670456103739, | |
| "loss": 0.0388, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.14811943471431732, | |
| "learning_rate": 0.00018423447839253126, | |
| "loss": 0.0184, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.2438066601753235, | |
| "learning_rate": 0.0001839621332194866, | |
| "loss": 0.0228, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.299697607755661, | |
| "learning_rate": 0.00018368966998861898, | |
| "loss": 0.0392, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.26123788952827454, | |
| "learning_rate": 0.00018341708964705433, | |
| "loss": 0.0569, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.1523085981607437, | |
| "learning_rate": 0.00018314439314232557, | |
| "loss": 0.0488, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.17505189776420593, | |
| "learning_rate": 0.0001828715814223696, | |
| "loss": 0.0342, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.2612646222114563, | |
| "learning_rate": 0.0001825986554355236, | |
| "loss": 0.0413, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.2304815948009491, | |
| "learning_rate": 0.00018232561613052212, | |
| "loss": 0.0361, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.5065823793411255, | |
| "learning_rate": 0.00018205246445649362, | |
| "loss": 0.0506, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.252676397562027, | |
| "learning_rate": 0.00018177920136295712, | |
| "loss": 0.0422, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.5118948817253113, | |
| "learning_rate": 0.00018150582779981897, | |
| "loss": 0.0794, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.20689886808395386, | |
| "learning_rate": 0.00018123234471736942, | |
| "loss": 0.0196, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.21955521404743195, | |
| "learning_rate": 0.00018095875306627977, | |
| "loss": 0.0205, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.2635563910007477, | |
| "learning_rate": 0.00018068505379759825, | |
| "loss": 0.026, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.4259761869907379, | |
| "learning_rate": 0.00018041124786274756, | |
| "loss": 0.0669, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.24592095613479614, | |
| "learning_rate": 0.000180137336213521, | |
| "loss": 0.054, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.448553204536438, | |
| "learning_rate": 0.0001798633198020794, | |
| "loss": 0.0244, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.16729894280433655, | |
| "learning_rate": 0.0001795891995809478, | |
| "loss": 0.0597, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.2796671390533447, | |
| "learning_rate": 0.000179314976503012, | |
| "loss": 0.0281, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.6444141864776611, | |
| "learning_rate": 0.00017904065152151544, | |
| "loss": 0.1028, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.5876030921936035, | |
| "learning_rate": 0.00017876622559005577, | |
| "loss": 0.0896, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.7038650512695312, | |
| "learning_rate": 0.00017849169966258156, | |
| "loss": 0.0294, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.22545520961284637, | |
| "learning_rate": 0.00017821707469338892, | |
| "loss": 0.0491, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.25605642795562744, | |
| "learning_rate": 0.00017794235163711835, | |
| "loss": 0.0343, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.07614222168922424, | |
| "learning_rate": 0.0001776675314487512, | |
| "loss": 0.0149, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.37879428267478943, | |
| "learning_rate": 0.0001773926150836066, | |
| "loss": 0.1085, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.18689392507076263, | |
| "learning_rate": 0.00017711760349733792, | |
| "loss": 0.0424, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.14959782361984253, | |
| "learning_rate": 0.00017684249764592948, | |
| "loss": 0.0421, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.35820502042770386, | |
| "learning_rate": 0.0001765672984856934, | |
| "loss": 0.0542, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.2389790266752243, | |
| "learning_rate": 0.00017629200697326613, | |
| "loss": 0.0545, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.25757715106010437, | |
| "learning_rate": 0.00017601662406560508, | |
| "loss": 0.0549, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.25923579931259155, | |
| "learning_rate": 0.00017574115071998547, | |
| "loss": 0.0401, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.1554333120584488, | |
| "learning_rate": 0.0001754655878939968, | |
| "loss": 0.0321, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.1587299108505249, | |
| "learning_rate": 0.00017518993654553963, | |
| "loss": 0.0495, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.3896007835865021, | |
| "learning_rate": 0.00017491419763282227, | |
| "loss": 0.1092, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.20783177018165588, | |
| "learning_rate": 0.00017463837211435744, | |
| "loss": 0.0281, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.19074185192584991, | |
| "learning_rate": 0.00017436246094895894, | |
| "loss": 0.0401, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.18701818585395813, | |
| "learning_rate": 0.00017408646509573813, | |
| "loss": 0.0332, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.20894934237003326, | |
| "learning_rate": 0.00017381038551410097, | |
| "loss": 0.0626, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.16977371275424957, | |
| "learning_rate": 0.00017353422316374427, | |
| "loss": 0.0475, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.16158726811408997, | |
| "learning_rate": 0.00017325797900465278, | |
| "loss": 0.024, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.8635274767875671, | |
| "learning_rate": 0.00017298165399709536, | |
| "loss": 0.1246, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.24966581165790558, | |
| "learning_rate": 0.0001727052491016222, | |
| "loss": 0.041, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.21421608328819275, | |
| "learning_rate": 0.00017242876527906096, | |
| "loss": 0.0525, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.14579136669635773, | |
| "learning_rate": 0.0001721522034905138, | |
| "loss": 0.0229, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.22795641422271729, | |
| "learning_rate": 0.0001718755646973539, | |
| "loss": 0.0443, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.3049260675907135, | |
| "learning_rate": 0.00017159884986122194, | |
| "loss": 0.0606, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.16482001543045044, | |
| "learning_rate": 0.00017132205994402328, | |
| "loss": 0.0439, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.2296137511730194, | |
| "learning_rate": 0.00017104519590792396, | |
| "loss": 0.0303, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.19414740800857544, | |
| "learning_rate": 0.00017076825871534772, | |
| "loss": 0.0474, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.2893425524234772, | |
| "learning_rate": 0.00017049124932897277, | |
| "loss": 0.0582, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.11354421079158783, | |
| "learning_rate": 0.00017021416871172815, | |
| "loss": 0.0187, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.19562894105911255, | |
| "learning_rate": 0.00016993701782679055, | |
| "loss": 0.033, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.13439138233661652, | |
| "learning_rate": 0.0001696597976375808, | |
| "loss": 0.0192, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.2628462016582489, | |
| "learning_rate": 0.00016938250910776084, | |
| "loss": 0.0378, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.10226990282535553, | |
| "learning_rate": 0.0001691051532012301, | |
| "loss": 0.014, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.43657186627388, | |
| "learning_rate": 0.0001688277308821221, | |
| "loss": 0.0589, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.3169918954372406, | |
| "learning_rate": 0.00016855024311480146, | |
| "loss": 0.0591, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.4922636151313782, | |
| "learning_rate": 0.00016827269086386003, | |
| "loss": 0.0697, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.08833907544612885, | |
| "learning_rate": 0.00016799507509411405, | |
| "loss": 0.0116, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.3545498251914978, | |
| "learning_rate": 0.00016771739677060043, | |
| "loss": 0.0632, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.37221550941467285, | |
| "learning_rate": 0.00016743965685857358, | |
| "loss": 0.04, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.3635517954826355, | |
| "learning_rate": 0.000167161856323502, | |
| "loss": 0.0725, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.09715539216995239, | |
| "learning_rate": 0.00016688399613106484, | |
| "loss": 0.0089, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.07484902441501617, | |
| "learning_rate": 0.0001666060772471488, | |
| "loss": 0.007, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.1089821457862854, | |
| "learning_rate": 0.00016632810063784448, | |
| "loss": 0.0121, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.09242980927228928, | |
| "learning_rate": 0.00016605006726944313, | |
| "loss": 0.0101, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.7516760230064392, | |
| "learning_rate": 0.0001657719781084333, | |
| "loss": 0.0543, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.717779278755188, | |
| "learning_rate": 0.0001654938341214976, | |
| "loss": 0.0535, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.4909898340702057, | |
| "learning_rate": 0.0001652156362755091, | |
| "loss": 0.0752, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.6857799887657166, | |
| "learning_rate": 0.00016493738553752818, | |
| "loss": 0.1142, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.28686514496803284, | |
| "learning_rate": 0.00016465908287479906, | |
| "loss": 0.0321, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.1494898945093155, | |
| "learning_rate": 0.0001643807292547463, | |
| "loss": 0.0089, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.34240686893463135, | |
| "learning_rate": 0.00016410232564497185, | |
| "loss": 0.0526, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.17216762900352478, | |
| "learning_rate": 0.00016382387301325135, | |
| "loss": 0.0124, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.18440192937850952, | |
| "learning_rate": 0.0001635453723275307, | |
| "loss": 0.0629, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.17247916758060455, | |
| "learning_rate": 0.00016326682455592304, | |
| "loss": 0.0342, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.23954929411411285, | |
| "learning_rate": 0.0001629882306667051, | |
| "loss": 0.0399, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.11504701524972916, | |
| "learning_rate": 0.0001627095916283139, | |
| "loss": 0.0146, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.28793883323669434, | |
| "learning_rate": 0.00016243090840934344, | |
| "loss": 0.1013, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.4467115104198456, | |
| "learning_rate": 0.00016215218197854127, | |
| "loss": 0.0562, | |
| "step": 809 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.1595917046070099, | |
| "learning_rate": 0.00016187341330480522, | |
| "loss": 0.04, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.1741933822631836, | |
| "learning_rate": 0.00016159460335717993, | |
| "loss": 0.0374, | |
| "step": 811 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.16274484992027283, | |
| "learning_rate": 0.00016131575310485345, | |
| "loss": 0.03, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.20965149998664856, | |
| "learning_rate": 0.00016103686351715403, | |
| "loss": 0.0486, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.28146764636039734, | |
| "learning_rate": 0.00016075793556354653, | |
| "loss": 0.0546, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.7190961241722107, | |
| "learning_rate": 0.00016047897021362938, | |
| "loss": 0.0832, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.3478730618953705, | |
| "learning_rate": 0.00016019996843713084, | |
| "loss": 0.043, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.3473072648048401, | |
| "learning_rate": 0.00015992093120390581, | |
| "loss": 0.0579, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.21544550359249115, | |
| "learning_rate": 0.00015964185948393246, | |
| "loss": 0.0515, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.317604124546051, | |
| "learning_rate": 0.00015936275424730892, | |
| "loss": 0.0678, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.23350350558757782, | |
| "learning_rate": 0.00015908361646424973, | |
| "loss": 0.0382, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.1787886768579483, | |
| "learning_rate": 0.0001588044471050826, | |
| "loss": 0.0306, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.148136705160141, | |
| "learning_rate": 0.00015852524714024503, | |
| "loss": 0.0308, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.20286808907985687, | |
| "learning_rate": 0.00015824601754028082, | |
| "loss": 0.0512, | |
| "step": 823 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.2771085202693939, | |
| "learning_rate": 0.0001579667592758369, | |
| "loss": 0.0424, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.230366513133049, | |
| "learning_rate": 0.00015768747331765975, | |
| "loss": 0.0329, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.3995148539543152, | |
| "learning_rate": 0.00015740816063659224, | |
| "loss": 0.0668, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.41903263330459595, | |
| "learning_rate": 0.00015712882220357, | |
| "loss": 0.123, | |
| "step": 827 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.10426704585552216, | |
| "learning_rate": 0.00015684945898961823, | |
| "loss": 0.0139, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.28077027201652527, | |
| "learning_rate": 0.00015657007196584832, | |
| "loss": 0.0649, | |
| "step": 829 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.4622378647327423, | |
| "learning_rate": 0.0001562906621034543, | |
| "loss": 0.0728, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.23062212765216827, | |
| "learning_rate": 0.00015601123037370973, | |
| "loss": 0.0187, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.28703922033309937, | |
| "learning_rate": 0.00015573177774796414, | |
| "loss": 0.0486, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.3227209448814392, | |
| "learning_rate": 0.00015545230519763966, | |
| "loss": 0.0474, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.19180624186992645, | |
| "learning_rate": 0.00015517281369422766, | |
| "loss": 0.0612, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.3641510605812073, | |
| "learning_rate": 0.00015489330420928552, | |
| "loss": 0.0584, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.34426817297935486, | |
| "learning_rate": 0.00015461377771443298, | |
| "loss": 0.0735, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.21041937172412872, | |
| "learning_rate": 0.00015433423518134904, | |
| "loss": 0.045, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.2598513066768646, | |
| "learning_rate": 0.00015405467758176835, | |
| "loss": 0.0411, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.29700911045074463, | |
| "learning_rate": 0.000153775105887478, | |
| "loss": 0.0624, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.1756899207830429, | |
| "learning_rate": 0.00015349552107031395, | |
| "loss": 0.0299, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.19117477536201477, | |
| "learning_rate": 0.00015321592410215797, | |
| "loss": 0.0951, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.11488031595945358, | |
| "learning_rate": 0.00015293631595493398, | |
| "loss": 0.0201, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.29568618535995483, | |
| "learning_rate": 0.00015265669760060465, | |
| "loss": 0.0463, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.24253536760807037, | |
| "learning_rate": 0.0001523770700111683, | |
| "loss": 0.0494, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.1810959130525589, | |
| "learning_rate": 0.00015209743415865533, | |
| "loss": 0.0326, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.2873782217502594, | |
| "learning_rate": 0.00015181779101512477, | |
| "loss": 0.0411, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.05380136892199516, | |
| "learning_rate": 0.00015153814155266103, | |
| "loss": 0.0099, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.07258699834346771, | |
| "learning_rate": 0.0001512584867433705, | |
| "loss": 0.009, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.11949209123849869, | |
| "learning_rate": 0.00015097882755937822, | |
| "loss": 0.0145, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.2874244749546051, | |
| "learning_rate": 0.00015069916497282432, | |
| "loss": 0.0368, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.23363856971263885, | |
| "learning_rate": 0.00015041949995586078, | |
| "loss": 0.0658, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.2872653305530548, | |
| "learning_rate": 0.00015013983348064814, | |
| "loss": 0.0379, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 0.08633331954479218, | |
| "eval_runtime": 14.7153, | |
| "eval_samples_per_second": 32.415, | |
| "eval_steps_per_second": 8.155, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.08994939923286438, | |
| "learning_rate": 0.00014986016651935183, | |
| "loss": 0.0097, | |
| "step": 853 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.44967612624168396, | |
| "learning_rate": 0.00014958050004413922, | |
| "loss": 0.0501, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.5344903469085693, | |
| "learning_rate": 0.0001493008350271757, | |
| "loss": 0.0284, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.5308881998062134, | |
| "learning_rate": 0.00014902117244062178, | |
| "loss": 0.0467, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.42243242263793945, | |
| "learning_rate": 0.0001487415132566295, | |
| "loss": 0.0418, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.4274597764015198, | |
| "learning_rate": 0.00014846185844733894, | |
| "loss": 0.0898, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.7866750955581665, | |
| "learning_rate": 0.0001481822089848752, | |
| "loss": 0.0868, | |
| "step": 859 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.3989715874195099, | |
| "learning_rate": 0.00014790256584134467, | |
| "loss": 0.0539, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.275583416223526, | |
| "learning_rate": 0.00014762292998883166, | |
| "loss": 0.0577, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.31740522384643555, | |
| "learning_rate": 0.00014734330239939535, | |
| "loss": 0.0169, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.23814305663108826, | |
| "learning_rate": 0.00014706368404506602, | |
| "loss": 0.031, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.21870914101600647, | |
| "learning_rate": 0.000146784075897842, | |
| "loss": 0.0239, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.08485715836286545, | |
| "learning_rate": 0.00014650447892968605, | |
| "loss": 0.0093, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.1792098879814148, | |
| "learning_rate": 0.000146224894112522, | |
| "loss": 0.0296, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.2863057255744934, | |
| "learning_rate": 0.00014594532241823165, | |
| "loss": 0.0521, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.477017343044281, | |
| "learning_rate": 0.00014566576481865097, | |
| "loss": 0.08, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.3662970960140228, | |
| "learning_rate": 0.00014538622228556697, | |
| "loss": 0.0751, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.3300603926181793, | |
| "learning_rate": 0.00014510669579071448, | |
| "loss": 0.075, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.04433250427246094, | |
| "learning_rate": 0.0001448271863057723, | |
| "loss": 0.0065, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.2359628975391388, | |
| "learning_rate": 0.0001445476948023603, | |
| "loss": 0.0521, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.14717410504817963, | |
| "learning_rate": 0.0001442682222520359, | |
| "loss": 0.0216, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.22751399874687195, | |
| "learning_rate": 0.00014398876962629025, | |
| "loss": 0.0403, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.6166908144950867, | |
| "learning_rate": 0.0001437093378965457, | |
| "loss": 0.0649, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.2543468475341797, | |
| "learning_rate": 0.0001434299280341517, | |
| "loss": 0.0781, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.15570877492427826, | |
| "learning_rate": 0.00014315054101038174, | |
| "loss": 0.0314, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.13937588036060333, | |
| "learning_rate": 0.00014287117779643, | |
| "loss": 0.0317, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.3276956081390381, | |
| "learning_rate": 0.00014259183936340774, | |
| "loss": 0.0869, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.271882027387619, | |
| "learning_rate": 0.00014231252668234023, | |
| "loss": 0.0329, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.18096867203712463, | |
| "learning_rate": 0.0001420332407241631, | |
| "loss": 0.0375, | |
| "step": 881 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.1566796898841858, | |
| "learning_rate": 0.0001417539824597192, | |
| "loss": 0.0333, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.16603341698646545, | |
| "learning_rate": 0.00014147475285975503, | |
| "loss": 0.033, | |
| "step": 883 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.1516629457473755, | |
| "learning_rate": 0.00014119555289491737, | |
| "loss": 0.0305, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.23150323331356049, | |
| "learning_rate": 0.00014091638353575024, | |
| "loss": 0.0261, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.1631498783826828, | |
| "learning_rate": 0.00014063724575269105, | |
| "loss": 0.0334, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.2955824136734009, | |
| "learning_rate": 0.00014035814051606752, | |
| "loss": 0.0552, | |
| "step": 887 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.24213866889476776, | |
| "learning_rate": 0.00014007906879609424, | |
| "loss": 0.0279, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.25006791949272156, | |
| "learning_rate": 0.00013980003156286914, | |
| "loss": 0.0522, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.22357212007045746, | |
| "learning_rate": 0.00013952102978637056, | |
| "loss": 0.0396, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.3780936598777771, | |
| "learning_rate": 0.00013924206443645344, | |
| "loss": 0.0745, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.42298954725265503, | |
| "learning_rate": 0.00013896313648284597, | |
| "loss": 0.1081, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.3097688555717468, | |
| "learning_rate": 0.00013868424689514658, | |
| "loss": 0.0757, | |
| "step": 893 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.15456968545913696, | |
| "learning_rate": 0.0001384053966428201, | |
| "loss": 0.029, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.2668134272098541, | |
| "learning_rate": 0.00013812658669519473, | |
| "loss": 0.0398, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.39498788118362427, | |
| "learning_rate": 0.00013784781802145873, | |
| "loss": 0.0756, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.782438337802887, | |
| "learning_rate": 0.00013756909159065656, | |
| "loss": 0.0827, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.5805864334106445, | |
| "learning_rate": 0.00013729040837168608, | |
| "loss": 0.0536, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.42258474230766296, | |
| "learning_rate": 0.00013701176933329494, | |
| "loss": 0.093, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.3261685073375702, | |
| "learning_rate": 0.00013673317544407693, | |
| "loss": 0.0751, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.5293501019477844, | |
| "learning_rate": 0.0001364546276724693, | |
| "loss": 0.1383, | |
| "step": 901 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.14614896476268768, | |
| "learning_rate": 0.00013617612698674865, | |
| "loss": 0.0263, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.12985162436962128, | |
| "learning_rate": 0.00013589767435502812, | |
| "loss": 0.027, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.12051744014024734, | |
| "learning_rate": 0.0001356192707452537, | |
| "loss": 0.0301, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.2052602469921112, | |
| "learning_rate": 0.00013534091712520097, | |
| "loss": 0.0843, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.3517119586467743, | |
| "learning_rate": 0.0001350626144624718, | |
| "loss": 0.0769, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.182536780834198, | |
| "learning_rate": 0.00013478436372449086, | |
| "loss": 0.0798, | |
| "step": 907 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.31057825684547424, | |
| "learning_rate": 0.0001345061658785024, | |
| "loss": 0.0799, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.2310357391834259, | |
| "learning_rate": 0.0001342280218915667, | |
| "loss": 0.0506, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.2205679565668106, | |
| "learning_rate": 0.00013394993273055687, | |
| "loss": 0.0501, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.09648188203573227, | |
| "learning_rate": 0.0001336718993621555, | |
| "loss": 0.0253, | |
| "step": 911 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.14384910464286804, | |
| "learning_rate": 0.00013339392275285117, | |
| "loss": 0.0474, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.22472958266735077, | |
| "learning_rate": 0.0001331160038689351, | |
| "loss": 0.0715, | |
| "step": 913 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.17647628486156464, | |
| "learning_rate": 0.000132838143676498, | |
| "loss": 0.0379, | |
| "step": 914 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.17897732555866241, | |
| "learning_rate": 0.0001325603431414264, | |
| "loss": 0.0407, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.15975071489810944, | |
| "learning_rate": 0.00013228260322939954, | |
| "loss": 0.0386, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.20889371633529663, | |
| "learning_rate": 0.00013200492490588595, | |
| "loss": 0.0395, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.19162769615650177, | |
| "learning_rate": 0.00013172730913613994, | |
| "loss": 0.0348, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.11488895863294601, | |
| "learning_rate": 0.00013144975688519857, | |
| "loss": 0.0299, | |
| "step": 919 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.2982803285121918, | |
| "learning_rate": 0.0001311722691178779, | |
| "loss": 0.0772, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.28049570322036743, | |
| "learning_rate": 0.00013089484679876988, | |
| "loss": 0.0604, | |
| "step": 921 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.534457266330719, | |
| "learning_rate": 0.00013061749089223913, | |
| "loss": 0.0674, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.14333413541316986, | |
| "learning_rate": 0.00013034020236241917, | |
| "loss": 0.0243, | |
| "step": 923 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.17806164920330048, | |
| "learning_rate": 0.00013006298217320945, | |
| "loss": 0.0284, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.1662513166666031, | |
| "learning_rate": 0.00012978583128827185, | |
| "loss": 0.0204, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.6015653014183044, | |
| "learning_rate": 0.00012950875067102718, | |
| "loss": 0.0641, | |
| "step": 926 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.21260066330432892, | |
| "learning_rate": 0.00012923174128465226, | |
| "loss": 0.0294, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.14397118985652924, | |
| "learning_rate": 0.00012895480409207607, | |
| "loss": 0.0159, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.34683769941329956, | |
| "learning_rate": 0.0001286779400559767, | |
| "loss": 0.0346, | |
| "step": 929 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.02308204025030136, | |
| "learning_rate": 0.00012840115013877803, | |
| "loss": 0.0024, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.22624412178993225, | |
| "learning_rate": 0.00012812443530264608, | |
| "loss": 0.039, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.4369746744632721, | |
| "learning_rate": 0.0001278477965094862, | |
| "loss": 0.0878, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.4473649561405182, | |
| "learning_rate": 0.00012757123472093904, | |
| "loss": 0.0528, | |
| "step": 933 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.3166683316230774, | |
| "learning_rate": 0.00012729475089837778, | |
| "loss": 0.0266, | |
| "step": 934 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.29405805468559265, | |
| "learning_rate": 0.00012701834600290464, | |
| "loss": 0.0471, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.07540614157915115, | |
| "learning_rate": 0.00012674202099534723, | |
| "loss": 0.0136, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.7350433468818665, | |
| "learning_rate": 0.00012646577683625567, | |
| "loss": 0.0554, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.7809972167015076, | |
| "learning_rate": 0.00012618961448589903, | |
| "loss": 0.0659, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.3870202302932739, | |
| "learning_rate": 0.00012591353490426182, | |
| "loss": 0.031, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.39360955357551575, | |
| "learning_rate": 0.00012563753905104106, | |
| "loss": 0.0467, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.3007020354270935, | |
| "learning_rate": 0.00012536162788564254, | |
| "loss": 0.0369, | |
| "step": 941 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.0672825500369072, | |
| "learning_rate": 0.00012508580236717768, | |
| "loss": 0.0096, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.2634739875793457, | |
| "learning_rate": 0.00012481006345446037, | |
| "loss": 0.0515, | |
| "step": 943 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.24073559045791626, | |
| "learning_rate": 0.00012453441210600322, | |
| "loss": 0.028, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.20282107591629028, | |
| "learning_rate": 0.00012425884928001453, | |
| "loss": 0.0176, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.19443388283252716, | |
| "learning_rate": 0.0001239833759343949, | |
| "loss": 0.0242, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.26304328441619873, | |
| "learning_rate": 0.00012370799302673384, | |
| "loss": 0.018, | |
| "step": 947 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.29775339365005493, | |
| "learning_rate": 0.00012343270151430659, | |
| "loss": 0.0694, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.6493348479270935, | |
| "learning_rate": 0.00012315750235407052, | |
| "loss": 0.0985, | |
| "step": 949 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.24055354297161102, | |
| "learning_rate": 0.0001228823965026621, | |
| "loss": 0.0411, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.24912531673908234, | |
| "learning_rate": 0.0001226073849163934, | |
| "loss": 0.0299, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.17892080545425415, | |
| "learning_rate": 0.00012233246855124875, | |
| "loss": 0.0348, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.3222208321094513, | |
| "learning_rate": 0.00012205764836288167, | |
| "loss": 0.0402, | |
| "step": 953 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.17411519587039948, | |
| "learning_rate": 0.00012178292530661106, | |
| "loss": 0.0269, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.315654456615448, | |
| "learning_rate": 0.00012150830033741843, | |
| "loss": 0.0273, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.23225267231464386, | |
| "learning_rate": 0.00012123377440994423, | |
| "loss": 0.0316, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.31462836265563965, | |
| "learning_rate": 0.00012095934847848452, | |
| "loss": 0.071, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.36353588104248047, | |
| "learning_rate": 0.00012068502349698805, | |
| "loss": 0.0391, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.24388179183006287, | |
| "learning_rate": 0.0001204108004190522, | |
| "loss": 0.03, | |
| "step": 959 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.5372264981269836, | |
| "learning_rate": 0.00012013668019792057, | |
| "loss": 0.0585, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.09891072660684586, | |
| "learning_rate": 0.000119862663786479, | |
| "loss": 0.0116, | |
| "step": 961 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.37838393449783325, | |
| "learning_rate": 0.0001195887521372524, | |
| "loss": 0.0611, | |
| "step": 962 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.13470232486724854, | |
| "learning_rate": 0.00011931494620240171, | |
| "loss": 0.0211, | |
| "step": 963 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.5314339995384216, | |
| "learning_rate": 0.00011904124693372024, | |
| "loss": 0.0631, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.4563555121421814, | |
| "learning_rate": 0.00011876765528263052, | |
| "loss": 0.1134, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.2271527349948883, | |
| "learning_rate": 0.00011849417220018107, | |
| "loss": 0.0882, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.33432772755622864, | |
| "learning_rate": 0.0001182207986370429, | |
| "loss": 0.0908, | |
| "step": 967 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.28085678815841675, | |
| "learning_rate": 0.00011794753554350634, | |
| "loss": 0.0761, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.23504915833473206, | |
| "learning_rate": 0.00011767438386947787, | |
| "loss": 0.037, | |
| "step": 969 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.11846155673265457, | |
| "learning_rate": 0.00011740134456447641, | |
| "loss": 0.0245, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.16506996750831604, | |
| "learning_rate": 0.00011712841857763042, | |
| "loss": 0.0159, | |
| "step": 971 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.3428071141242981, | |
| "learning_rate": 0.0001168556068576744, | |
| "loss": 0.0586, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.41366422176361084, | |
| "learning_rate": 0.00011658291035294564, | |
| "loss": 0.0328, | |
| "step": 973 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.2286631166934967, | |
| "learning_rate": 0.00011631033001138099, | |
| "loss": 0.0615, | |
| "step": 974 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.2114325612783432, | |
| "learning_rate": 0.0001160378667805134, | |
| "loss": 0.0431, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.2964124083518982, | |
| "learning_rate": 0.00011576552160746875, | |
| "loss": 0.0921, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.23333175480365753, | |
| "learning_rate": 0.0001154932954389626, | |
| "loss": 0.0419, | |
| "step": 977 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.22366467118263245, | |
| "learning_rate": 0.0001152211892212967, | |
| "loss": 0.0426, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.10860833525657654, | |
| "learning_rate": 0.00011494920390035602, | |
| "loss": 0.0185, | |
| "step": 979 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.3171096444129944, | |
| "learning_rate": 0.00011467734042160505, | |
| "loss": 0.0547, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.18347975611686707, | |
| "learning_rate": 0.00011440559973008493, | |
| "loss": 0.0315, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.3099198639392853, | |
| "learning_rate": 0.00011413398277040988, | |
| "loss": 0.0552, | |
| "step": 982 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.166449636220932, | |
| "learning_rate": 0.00011386249048676397, | |
| "loss": 0.0314, | |
| "step": 983 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.1382310539484024, | |
| "learning_rate": 0.00011359112382289807, | |
| "loss": 0.0204, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.33030879497528076, | |
| "learning_rate": 0.00011331988372212604, | |
| "loss": 0.0351, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.10897009819746017, | |
| "learning_rate": 0.00011304877112732208, | |
| "loss": 0.0175, | |
| "step": 986 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.40048226714134216, | |
| "learning_rate": 0.0001127777869809171, | |
| "loss": 0.1135, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.22304043173789978, | |
| "learning_rate": 0.00011250693222489535, | |
| "loss": 0.0309, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.22760216891765594, | |
| "learning_rate": 0.00011223620780079154, | |
| "loss": 0.0207, | |
| "step": 989 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.19811508059501648, | |
| "learning_rate": 0.00011196561464968713, | |
| "loss": 0.0393, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.4455642104148865, | |
| "learning_rate": 0.00011169515371220728, | |
| "loss": 0.1054, | |
| "step": 991 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.0268537737429142, | |
| "learning_rate": 0.00011142482592851769, | |
| "loss": 0.0042, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.11751615256071091, | |
| "learning_rate": 0.000111154632238321, | |
| "loss": 0.0148, | |
| "step": 993 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.28696444630622864, | |
| "learning_rate": 0.00011088457358085382, | |
| "loss": 0.0545, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 0.0792541652917862, | |
| "eval_runtime": 14.6647, | |
| "eval_samples_per_second": 32.527, | |
| "eval_steps_per_second": 8.183, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.1033347100019455, | |
| "learning_rate": 0.00011061465089488348, | |
| "loss": 0.0119, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.3465028703212738, | |
| "learning_rate": 0.00011034486511870443, | |
| "loss": 0.0479, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.4551747143268585, | |
| "learning_rate": 0.00011007521719013536, | |
| "loss": 0.0604, | |
| "step": 997 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.10942043364048004, | |
| "learning_rate": 0.00010980570804651567, | |
| "loss": 0.013, | |
| "step": 998 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.41811010241508484, | |
| "learning_rate": 0.00010953633862470239, | |
| "loss": 0.0966, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.12761569023132324, | |
| "learning_rate": 0.00010926710986106691, | |
| "loss": 0.0173, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.263926237821579, | |
| "learning_rate": 0.0001089980226914915, | |
| "loss": 0.0825, | |
| "step": 1001 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.41034916043281555, | |
| "learning_rate": 0.00010872907805136636, | |
| "loss": 0.0674, | |
| "step": 1002 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.23882801830768585, | |
| "learning_rate": 0.00010846027687558626, | |
| "loss": 0.0398, | |
| "step": 1003 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.2567130923271179, | |
| "learning_rate": 0.0001081916200985471, | |
| "loss": 0.0408, | |
| "step": 1004 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.16284267604351044, | |
| "learning_rate": 0.00010792310865414305, | |
| "loss": 0.0243, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.29053768515586853, | |
| "learning_rate": 0.00010765474347576287, | |
| "loss": 0.0765, | |
| "step": 1006 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.4428679943084717, | |
| "learning_rate": 0.00010738652549628698, | |
| "loss": 0.0808, | |
| "step": 1007 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.3464658856391907, | |
| "learning_rate": 0.00010711845564808416, | |
| "loss": 0.0588, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.2980837821960449, | |
| "learning_rate": 0.00010685053486300813, | |
| "loss": 0.0558, | |
| "step": 1009 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.11548680812120438, | |
| "learning_rate": 0.0001065827640723946, | |
| "loss": 0.0243, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.11409750580787659, | |
| "learning_rate": 0.0001063151442070577, | |
| "loss": 0.0194, | |
| "step": 1011 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.24823527038097382, | |
| "learning_rate": 0.00010604767619728706, | |
| "loss": 0.0569, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.15851640701293945, | |
| "learning_rate": 0.00010578036097284441, | |
| "loss": 0.0304, | |
| "step": 1013 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.09604015946388245, | |
| "learning_rate": 0.00010551319946296026, | |
| "loss": 0.0193, | |
| "step": 1014 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.39140328764915466, | |
| "learning_rate": 0.00010524619259633097, | |
| "loss": 0.0595, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.12756693363189697, | |
| "learning_rate": 0.00010497934130111524, | |
| "loss": 0.0214, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.23306307196617126, | |
| "learning_rate": 0.00010471264650493093, | |
| "loss": 0.0436, | |
| "step": 1017 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.1584581732749939, | |
| "learning_rate": 0.00010444610913485194, | |
| "loss": 0.0232, | |
| "step": 1018 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.13806113600730896, | |
| "learning_rate": 0.00010417973011740491, | |
| "loss": 0.0207, | |
| "step": 1019 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.36593613028526306, | |
| "learning_rate": 0.00010391351037856604, | |
| "loss": 0.1585, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.22285635769367218, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 0.0265, | |
| "step": 1021 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.05805375054478645, | |
| "learning_rate": 0.00010338155243784604, | |
| "loss": 0.0091, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.14522014558315277, | |
| "learning_rate": 0.00010311581608513602, | |
| "loss": 0.021, | |
| "step": 1023 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.2817407250404358, | |
| "learning_rate": 0.00010285024270937002, | |
| "loss": 0.0402, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.323799729347229, | |
| "learning_rate": 0.00010258483323372363, | |
| "loss": 0.0892, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.26789921522140503, | |
| "learning_rate": 0.0001023195885808029, | |
| "loss": 0.0513, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.17003491520881653, | |
| "learning_rate": 0.00010205450967264066, | |
| "loss": 0.0254, | |
| "step": 1027 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.20790556073188782, | |
| "learning_rate": 0.00010178959743069378, | |
| "loss": 0.0548, | |
| "step": 1028 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.5027781128883362, | |
| "learning_rate": 0.00010152485277583974, | |
| "loss": 0.0664, | |
| "step": 1029 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.06910550594329834, | |
| "learning_rate": 0.0001012602766283733, | |
| "loss": 0.0044, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.4314959943294525, | |
| "learning_rate": 0.00010099586990800374, | |
| "loss": 0.0266, | |
| "step": 1031 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.11808943003416061, | |
| "learning_rate": 0.00010073163353385115, | |
| "loss": 0.0138, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.3632063865661621, | |
| "learning_rate": 0.00010046756842444354, | |
| "loss": 0.0569, | |
| "step": 1033 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.36305737495422363, | |
| "learning_rate": 0.00010020367549771366, | |
| "loss": 0.0413, | |
| "step": 1034 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.4507397711277008, | |
| "learning_rate": 9.993995567099555e-05, | |
| "loss": 0.0685, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.1823229193687439, | |
| "learning_rate": 9.96764098610218e-05, | |
| "loss": 0.0154, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.4844795763492584, | |
| "learning_rate": 9.941303898391971e-05, | |
| "loss": 0.0643, | |
| "step": 1037 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.44893908500671387, | |
| "learning_rate": 9.914984395520884e-05, | |
| "loss": 0.0849, | |
| "step": 1038 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.6581425666809082, | |
| "learning_rate": 9.888682568979734e-05, | |
| "loss": 0.1001, | |
| "step": 1039 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.19968827068805695, | |
| "learning_rate": 9.862398510197874e-05, | |
| "loss": 0.0261, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.4013736844062805, | |
| "learning_rate": 9.836132310542926e-05, | |
| "loss": 0.0443, | |
| "step": 1041 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.35353174805641174, | |
| "learning_rate": 9.809884061320407e-05, | |
| "loss": 0.0757, | |
| "step": 1042 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 0.3231182396411896, | |
| "learning_rate": 9.783653853773438e-05, | |
| "loss": 0.0618, | |
| "step": 1043 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 0.2694651186466217, | |
| "learning_rate": 9.757441779082433e-05, | |
| "loss": 0.0273, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 0.18274915218353271, | |
| "learning_rate": 9.731247928364765e-05, | |
| "loss": 0.0308, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 0.38829588890075684, | |
| "learning_rate": 9.705072392674457e-05, | |
| "loss": 0.0639, | |
| "step": 1046 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 0.33814239501953125, | |
| "learning_rate": 9.678915263001884e-05, | |
| "loss": 0.0469, | |
| "step": 1047 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 0.36192476749420166, | |
| "learning_rate": 9.65277663027341e-05, | |
| "loss": 0.0441, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.613652229309082, | |
| "learning_rate": 9.626656585351127e-05, | |
| "loss": 0.0616, | |
| "step": 1049 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.4053266644477844, | |
| "learning_rate": 9.60055521903249e-05, | |
| "loss": 0.052, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.1685592234134674, | |
| "learning_rate": 9.574472622050037e-05, | |
| "loss": 0.0216, | |
| "step": 1051 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.3046499788761139, | |
| "learning_rate": 9.548408885071069e-05, | |
| "loss": 0.0416, | |
| "step": 1052 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.3596743643283844, | |
| "learning_rate": 9.522364098697309e-05, | |
| "loss": 0.0679, | |
| "step": 1053 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.5623247623443604, | |
| "learning_rate": 9.496338353464612e-05, | |
| "loss": 0.0837, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.10884875059127808, | |
| "learning_rate": 9.470331739842645e-05, | |
| "loss": 0.0117, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.31701669096946716, | |
| "learning_rate": 9.444344348234564e-05, | |
| "loss": 0.0323, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.4528666138648987, | |
| "learning_rate": 9.418376268976726e-05, | |
| "loss": 0.1085, | |
| "step": 1057 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.28140756487846375, | |
| "learning_rate": 9.392427592338317e-05, | |
| "loss": 0.0216, | |
| "step": 1058 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.20548555254936218, | |
| "learning_rate": 9.366498408521118e-05, | |
| "loss": 0.0252, | |
| "step": 1059 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.17361027002334595, | |
| "learning_rate": 9.340588807659126e-05, | |
| "loss": 0.0318, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.2615595757961273, | |
| "learning_rate": 9.314698879818263e-05, | |
| "loss": 0.0254, | |
| "step": 1061 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.22027018666267395, | |
| "learning_rate": 9.288828714996086e-05, | |
| "loss": 0.057, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.38918057084083557, | |
| "learning_rate": 9.262978403121419e-05, | |
| "loss": 0.0337, | |
| "step": 1063 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.19435515999794006, | |
| "learning_rate": 9.237148034054107e-05, | |
| "loss": 0.0304, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.3071884512901306, | |
| "learning_rate": 9.211337697584653e-05, | |
| "loss": 0.0357, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.17016515135765076, | |
| "learning_rate": 9.185547483433921e-05, | |
| "loss": 0.018, | |
| "step": 1066 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.46096545457839966, | |
| "learning_rate": 9.159777481252838e-05, | |
| "loss": 0.0846, | |
| "step": 1067 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.294148325920105, | |
| "learning_rate": 9.134027780622068e-05, | |
| "loss": 0.0521, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.19079583883285522, | |
| "learning_rate": 9.108298471051694e-05, | |
| "loss": 0.0218, | |
| "step": 1069 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.4090532958507538, | |
| "learning_rate": 9.08258964198093e-05, | |
| "loss": 0.0768, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.11493656784296036, | |
| "learning_rate": 9.056901382777784e-05, | |
| "loss": 0.0153, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.37453579902648926, | |
| "learning_rate": 9.031233782738764e-05, | |
| "loss": 0.0453, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.36182692646980286, | |
| "learning_rate": 9.005586931088577e-05, | |
| "loss": 0.0753, | |
| "step": 1073 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.33530041575431824, | |
| "learning_rate": 8.979960916979781e-05, | |
| "loss": 0.0513, | |
| "step": 1074 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.35975998640060425, | |
| "learning_rate": 8.95435582949252e-05, | |
| "loss": 0.0459, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.33220142126083374, | |
| "learning_rate": 8.928771757634177e-05, | |
| "loss": 0.0689, | |
| "step": 1076 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.19460581243038177, | |
| "learning_rate": 8.903208790339093e-05, | |
| "loss": 0.0303, | |
| "step": 1077 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.2682279944419861, | |
| "learning_rate": 8.87766701646825e-05, | |
| "loss": 0.0288, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.31635788083076477, | |
| "learning_rate": 8.852146524808943e-05, | |
| "loss": 0.0559, | |
| "step": 1079 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.14291277527809143, | |
| "learning_rate": 8.826647404074496e-05, | |
| "loss": 0.0248, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.2888137400150299, | |
| "learning_rate": 8.801169742903948e-05, | |
| "loss": 0.0913, | |
| "step": 1081 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.17214493453502655, | |
| "learning_rate": 8.775713629861726e-05, | |
| "loss": 0.029, | |
| "step": 1082 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.2867276668548584, | |
| "learning_rate": 8.750279153437373e-05, | |
| "loss": 0.0378, | |
| "step": 1083 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.210460364818573, | |
| "learning_rate": 8.724866402045208e-05, | |
| "loss": 0.0699, | |
| "step": 1084 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.3305147588253021, | |
| "learning_rate": 8.69947546402402e-05, | |
| "loss": 0.0423, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.1408224254846573, | |
| "learning_rate": 8.674106427636799e-05, | |
| "loss": 0.0174, | |
| "step": 1086 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.1414298713207245, | |
| "learning_rate": 8.648759381070368e-05, | |
| "loss": 0.0207, | |
| "step": 1087 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.26083138585090637, | |
| "learning_rate": 8.623434412435143e-05, | |
| "loss": 0.0345, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.05916636809706688, | |
| "learning_rate": 8.598131609764768e-05, | |
| "loss": 0.0066, | |
| "step": 1089 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.26731768250465393, | |
| "learning_rate": 8.572851061015842e-05, | |
| "loss": 0.0863, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.21286404132843018, | |
| "learning_rate": 8.547592854067616e-05, | |
| "loss": 0.0262, | |
| "step": 1091 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.1005811020731926, | |
| "learning_rate": 8.522357076721658e-05, | |
| "loss": 0.0115, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.24411919713020325, | |
| "learning_rate": 8.49714381670159e-05, | |
| "loss": 0.0517, | |
| "step": 1093 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.1755681186914444, | |
| "learning_rate": 8.471953161652742e-05, | |
| "loss": 0.0183, | |
| "step": 1094 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.2896975874900818, | |
| "learning_rate": 8.446785199141869e-05, | |
| "loss": 0.0555, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.28867337107658386, | |
| "learning_rate": 8.421640016656856e-05, | |
| "loss": 0.0239, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.15457966923713684, | |
| "learning_rate": 8.396517701606377e-05, | |
| "loss": 0.0137, | |
| "step": 1097 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.21171018481254578, | |
| "learning_rate": 8.371418341319642e-05, | |
| "loss": 0.0228, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.3345678746700287, | |
| "learning_rate": 8.346342023046048e-05, | |
| "loss": 0.079, | |
| "step": 1099 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.2039625495672226, | |
| "learning_rate": 8.321288833954895e-05, | |
| "loss": 0.0498, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.36770549416542053, | |
| "learning_rate": 8.296258861135097e-05, | |
| "loss": 0.0346, | |
| "step": 1101 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.212180495262146, | |
| "learning_rate": 8.271252191594845e-05, | |
| "loss": 0.0505, | |
| "step": 1102 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.45844799280166626, | |
| "learning_rate": 8.246268912261342e-05, | |
| "loss": 0.0539, | |
| "step": 1103 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.26958250999450684, | |
| "learning_rate": 8.221309109980472e-05, | |
| "loss": 0.0254, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.3047500252723694, | |
| "learning_rate": 8.196372871516502e-05, | |
| "loss": 0.0519, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.5248620510101318, | |
| "learning_rate": 8.171460283551809e-05, | |
| "loss": 0.0376, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.3489890396595001, | |
| "learning_rate": 8.146571432686543e-05, | |
| "loss": 0.038, | |
| "step": 1107 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.04020179435610771, | |
| "learning_rate": 8.121706405438345e-05, | |
| "loss": 0.0049, | |
| "step": 1108 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.20535163581371307, | |
| "learning_rate": 8.09686528824203e-05, | |
| "loss": 0.0163, | |
| "step": 1109 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.5453580021858215, | |
| "learning_rate": 8.072048167449306e-05, | |
| "loss": 0.0463, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.3431243896484375, | |
| "learning_rate": 8.047255129328466e-05, | |
| "loss": 0.0576, | |
| "step": 1111 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.29239121079444885, | |
| "learning_rate": 8.022486260064099e-05, | |
| "loss": 0.037, | |
| "step": 1112 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.5388960838317871, | |
| "learning_rate": 7.997741645756762e-05, | |
| "loss": 0.1145, | |
| "step": 1113 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.3808930814266205, | |
| "learning_rate": 7.9730213724227e-05, | |
| "loss": 0.047, | |
| "step": 1114 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.39548593759536743, | |
| "learning_rate": 7.948325525993545e-05, | |
| "loss": 0.0197, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.03463061898946762, | |
| "learning_rate": 7.923654192316021e-05, | |
| "loss": 0.0043, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 0.12383898347616196, | |
| "learning_rate": 7.899007457151657e-05, | |
| "loss": 0.0132, | |
| "step": 1117 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 0.3975280821323395, | |
| "learning_rate": 7.874385406176444e-05, | |
| "loss": 0.0338, | |
| "step": 1118 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 0.17554999887943268, | |
| "learning_rate": 7.849788124980581e-05, | |
| "loss": 0.0146, | |
| "step": 1119 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 0.1743941754102707, | |
| "learning_rate": 7.825215699068171e-05, | |
| "loss": 0.0142, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 0.15461145341396332, | |
| "learning_rate": 7.800668213856896e-05, | |
| "loss": 0.0145, | |
| "step": 1121 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 0.25048068165779114, | |
| "learning_rate": 7.776145754677773e-05, | |
| "loss": 0.0269, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 0.10131586343050003, | |
| "learning_rate": 7.751648406774778e-05, | |
| "loss": 0.0126, | |
| "step": 1123 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 0.7245112061500549, | |
| "learning_rate": 7.727176255304633e-05, | |
| "loss": 0.1092, | |
| "step": 1124 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 0.3287739157676697, | |
| "learning_rate": 7.702729385336469e-05, | |
| "loss": 0.0286, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 0.3910561203956604, | |
| "learning_rate": 7.678307881851516e-05, | |
| "loss": 0.0365, | |
| "step": 1126 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 0.31922951340675354, | |
| "learning_rate": 7.653911829742857e-05, | |
| "loss": 0.1163, | |
| "step": 1127 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.2800161838531494, | |
| "learning_rate": 7.629541313815056e-05, | |
| "loss": 0.0653, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.11548816412687302, | |
| "learning_rate": 7.605196418783948e-05, | |
| "loss": 0.0081, | |
| "step": 1129 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.5253295302391052, | |
| "learning_rate": 7.580877229276301e-05, | |
| "loss": 0.0402, | |
| "step": 1130 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 1695, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 565, | |
| "total_flos": 1.0339891388035891e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |