| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9995577178239717, | |
| "eval_steps": 142, | |
| "global_step": 565, | |
| "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 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 1695, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 565, | |
| "total_flos": 5.169945694856806e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |