| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9996105008958479, | |
| "eval_steps": 25, | |
| "global_step": 401, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009971177066292747, | |
| "grad_norm": 23.35832977294922, | |
| "learning_rate": 1.9512195121951222e-05, | |
| "loss": 3.1378, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.019942354132585494, | |
| "grad_norm": 7.3288469314575195, | |
| "learning_rate": 3.9024390243902444e-05, | |
| "loss": 2.3678, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.029913531198878244, | |
| "grad_norm": 1.554034948348999, | |
| "learning_rate": 5.853658536585366e-05, | |
| "loss": 1.5701, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03988470826517099, | |
| "grad_norm": 0.8166317343711853, | |
| "learning_rate": 7.804878048780489e-05, | |
| "loss": 1.3583, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04985588533146374, | |
| "grad_norm": 0.7018758058547974, | |
| "learning_rate": 9.75609756097561e-05, | |
| "loss": 1.3179, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05982706239775649, | |
| "grad_norm": 0.5763296484947205, | |
| "learning_rate": 0.00011707317073170732, | |
| "loss": 1.27, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.062319856664329674, | |
| "eval_loss": 1.2523891925811768, | |
| "eval_runtime": 160.09, | |
| "eval_samples_per_second": 25.586, | |
| "eval_steps_per_second": 1.599, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06979823946404923, | |
| "grad_norm": 0.5097940564155579, | |
| "learning_rate": 0.00013658536585365856, | |
| "loss": 1.2733, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07976941653034197, | |
| "grad_norm": 0.48720231652259827, | |
| "learning_rate": 0.00015609756097560978, | |
| "loss": 1.3002, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08974059359663472, | |
| "grad_norm": 0.44958242774009705, | |
| "learning_rate": 0.000175609756097561, | |
| "loss": 1.2172, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09971177066292748, | |
| "grad_norm": 0.459570974111557, | |
| "learning_rate": 0.0001951219512195122, | |
| "loss": 1.1891, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10968294772922023, | |
| "grad_norm": 0.4571148753166199, | |
| "learning_rate": 0.00019833333333333335, | |
| "loss": 1.2378, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11965412479551298, | |
| "grad_norm": 0.4622347056865692, | |
| "learning_rate": 0.00019611111111111112, | |
| "loss": 1.1931, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12463971332865935, | |
| "eval_loss": 1.18223237991333, | |
| "eval_runtime": 159.6761, | |
| "eval_samples_per_second": 25.652, | |
| "eval_steps_per_second": 1.603, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1296253018618057, | |
| "grad_norm": 0.47264593839645386, | |
| "learning_rate": 0.0001938888888888889, | |
| "loss": 1.1967, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.13959647892809846, | |
| "grad_norm": 0.443099707365036, | |
| "learning_rate": 0.00019166666666666667, | |
| "loss": 1.1844, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1495676559943912, | |
| "grad_norm": 0.4309901297092438, | |
| "learning_rate": 0.00018944444444444445, | |
| "loss": 1.1734, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15953883306068395, | |
| "grad_norm": 0.4467671513557434, | |
| "learning_rate": 0.00018722222222222222, | |
| "loss": 1.1783, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.1695100101269767, | |
| "grad_norm": 0.4321148991584778, | |
| "learning_rate": 0.00018500000000000002, | |
| "loss": 1.1625, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.17948118719326944, | |
| "grad_norm": 0.4267221987247467, | |
| "learning_rate": 0.00018277777777777777, | |
| "loss": 1.1571, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.18695956999298902, | |
| "eval_loss": 1.15470552444458, | |
| "eval_runtime": 159.6542, | |
| "eval_samples_per_second": 25.655, | |
| "eval_steps_per_second": 1.603, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1894523642595622, | |
| "grad_norm": 0.44214680790901184, | |
| "learning_rate": 0.00018055555555555557, | |
| "loss": 1.1463, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.19942354132585496, | |
| "grad_norm": 0.44037795066833496, | |
| "learning_rate": 0.00017833333333333335, | |
| "loss": 1.1477, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2093947183921477, | |
| "grad_norm": 0.4275970160961151, | |
| "learning_rate": 0.00017611111111111112, | |
| "loss": 1.1642, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.21936589545844046, | |
| "grad_norm": 0.5124487280845642, | |
| "learning_rate": 0.0001738888888888889, | |
| "loss": 1.1789, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.2293370725247332, | |
| "grad_norm": 0.4456328749656677, | |
| "learning_rate": 0.00017166666666666667, | |
| "loss": 1.1466, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.23930824959102595, | |
| "grad_norm": 0.41848745942115784, | |
| "learning_rate": 0.00016944444444444445, | |
| "loss": 1.1576, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.2492794266573187, | |
| "grad_norm": 0.41770660877227783, | |
| "learning_rate": 0.00016722222222222222, | |
| "loss": 1.1543, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2492794266573187, | |
| "eval_loss": 1.1412527561187744, | |
| "eval_runtime": 159.6274, | |
| "eval_samples_per_second": 25.66, | |
| "eval_steps_per_second": 1.604, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2592506037236114, | |
| "grad_norm": 0.4416305720806122, | |
| "learning_rate": 0.000165, | |
| "loss": 1.1251, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.26922178078990416, | |
| "grad_norm": 0.4185228943824768, | |
| "learning_rate": 0.00016277777777777777, | |
| "loss": 1.1442, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.2791929578561969, | |
| "grad_norm": 0.4267406463623047, | |
| "learning_rate": 0.00016055555555555558, | |
| "loss": 1.1438, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.28916413492248966, | |
| "grad_norm": 0.414470374584198, | |
| "learning_rate": 0.00015833333333333332, | |
| "loss": 1.1572, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.2991353119887824, | |
| "grad_norm": 0.41629141569137573, | |
| "learning_rate": 0.00015611111111111113, | |
| "loss": 1.1439, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.30910648905507515, | |
| "grad_norm": 0.4665207862854004, | |
| "learning_rate": 0.0001538888888888889, | |
| "loss": 1.1336, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.3115992833216484, | |
| "eval_loss": 1.1312440633773804, | |
| "eval_runtime": 159.6919, | |
| "eval_samples_per_second": 25.649, | |
| "eval_steps_per_second": 1.603, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3190776661213679, | |
| "grad_norm": 0.44851216673851013, | |
| "learning_rate": 0.00015166666666666668, | |
| "loss": 1.1398, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.32904884318766064, | |
| "grad_norm": 0.46069833636283875, | |
| "learning_rate": 0.00014944444444444445, | |
| "loss": 1.1375, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.3390200202539534, | |
| "grad_norm": 0.4321020543575287, | |
| "learning_rate": 0.00014722222222222223, | |
| "loss": 1.143, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.34899119732024614, | |
| "grad_norm": 0.41148263216018677, | |
| "learning_rate": 0.000145, | |
| "loss": 1.1265, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3589623743865389, | |
| "grad_norm": 0.4245862364768982, | |
| "learning_rate": 0.00014277777777777778, | |
| "loss": 1.1034, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.36893355145283163, | |
| "grad_norm": 0.48434320092201233, | |
| "learning_rate": 0.00014055555555555555, | |
| "loss": 1.1183, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.37391913998597803, | |
| "eval_loss": 1.1238796710968018, | |
| "eval_runtime": 159.6817, | |
| "eval_samples_per_second": 25.651, | |
| "eval_steps_per_second": 1.603, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3789047285191244, | |
| "grad_norm": 0.40798208117485046, | |
| "learning_rate": 0.00013833333333333333, | |
| "loss": 1.131, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.3888759055854172, | |
| "grad_norm": 0.4265343248844147, | |
| "learning_rate": 0.00013611111111111113, | |
| "loss": 1.1486, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.3988470826517099, | |
| "grad_norm": 0.4202587604522705, | |
| "learning_rate": 0.00013388888888888888, | |
| "loss": 1.1156, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4088182597180027, | |
| "grad_norm": 0.4195230305194855, | |
| "learning_rate": 0.00013166666666666668, | |
| "loss": 1.1128, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.4187894367842954, | |
| "grad_norm": 0.44741353392601013, | |
| "learning_rate": 0.00012944444444444445, | |
| "loss": 1.1235, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.42876061385058817, | |
| "grad_norm": 0.4431656002998352, | |
| "learning_rate": 0.00012722222222222223, | |
| "loss": 1.1008, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.4362389966503077, | |
| "eval_loss": 1.117403268814087, | |
| "eval_runtime": 159.8175, | |
| "eval_samples_per_second": 25.629, | |
| "eval_steps_per_second": 1.602, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4387317909168809, | |
| "grad_norm": 0.40237733721733093, | |
| "learning_rate": 0.000125, | |
| "loss": 1.1171, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.44870296798317366, | |
| "grad_norm": 0.42873087525367737, | |
| "learning_rate": 0.0001227777777777778, | |
| "loss": 1.1132, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4586741450494664, | |
| "grad_norm": 0.42686423659324646, | |
| "learning_rate": 0.00012055555555555555, | |
| "loss": 1.1311, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.46864532211575916, | |
| "grad_norm": 0.4393009543418884, | |
| "learning_rate": 0.00011833333333333334, | |
| "loss": 1.1288, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.4786164991820519, | |
| "grad_norm": 0.4396825432777405, | |
| "learning_rate": 0.00011611111111111113, | |
| "loss": 1.0963, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.48858767624834465, | |
| "grad_norm": 0.4490801990032196, | |
| "learning_rate": 0.00011388888888888889, | |
| "loss": 1.116, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.4985588533146374, | |
| "grad_norm": 0.4502253532409668, | |
| "learning_rate": 0.00011166666666666668, | |
| "loss": 1.1341, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4985588533146374, | |
| "eval_loss": 1.1130955219268799, | |
| "eval_runtime": 159.9517, | |
| "eval_samples_per_second": 25.608, | |
| "eval_steps_per_second": 1.6, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5085300303809301, | |
| "grad_norm": 0.4383712410926819, | |
| "learning_rate": 0.00010944444444444445, | |
| "loss": 1.1205, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.5185012074472228, | |
| "grad_norm": 0.48988428711891174, | |
| "learning_rate": 0.00010722222222222223, | |
| "loss": 1.1409, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.5284723845135156, | |
| "grad_norm": 0.4293093979358673, | |
| "learning_rate": 0.000105, | |
| "loss": 1.1176, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.5384435615798083, | |
| "grad_norm": 0.45622044801712036, | |
| "learning_rate": 0.00010277777777777778, | |
| "loss": 1.1001, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.5484147386461011, | |
| "grad_norm": 0.4486154615879059, | |
| "learning_rate": 0.00010055555555555555, | |
| "loss": 1.0903, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5583859157123938, | |
| "grad_norm": 0.43276774883270264, | |
| "learning_rate": 9.833333333333333e-05, | |
| "loss": 1.1058, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.560878709978967, | |
| "eval_loss": 1.1073756217956543, | |
| "eval_runtime": 159.9944, | |
| "eval_samples_per_second": 25.601, | |
| "eval_steps_per_second": 1.6, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5683570927786866, | |
| "grad_norm": 0.417212575674057, | |
| "learning_rate": 9.611111111111112e-05, | |
| "loss": 1.104, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.5783282698449793, | |
| "grad_norm": 0.4814886152744293, | |
| "learning_rate": 9.388888888888889e-05, | |
| "loss": 1.1131, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.5882994469112721, | |
| "grad_norm": 0.46115347743034363, | |
| "learning_rate": 9.166666666666667e-05, | |
| "loss": 1.1163, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.5982706239775648, | |
| "grad_norm": 0.4268442690372467, | |
| "learning_rate": 8.944444444444446e-05, | |
| "loss": 1.1109, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6082418010438576, | |
| "grad_norm": 0.43017688393592834, | |
| "learning_rate": 8.722222222222223e-05, | |
| "loss": 1.0922, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.6182129781101503, | |
| "grad_norm": 0.4273425340652466, | |
| "learning_rate": 8.5e-05, | |
| "loss": 1.105, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.6231985666432968, | |
| "eval_loss": 1.1038172245025635, | |
| "eval_runtime": 160.1646, | |
| "eval_samples_per_second": 25.574, | |
| "eval_steps_per_second": 1.598, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6281841551764431, | |
| "grad_norm": 0.4336010813713074, | |
| "learning_rate": 8.277777777777778e-05, | |
| "loss": 1.106, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.6381553322427358, | |
| "grad_norm": 0.4563632309436798, | |
| "learning_rate": 8.055555555555556e-05, | |
| "loss": 1.1366, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.6481265093090286, | |
| "grad_norm": 0.4345051944255829, | |
| "learning_rate": 7.833333333333333e-05, | |
| "loss": 1.1195, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6580976863753213, | |
| "grad_norm": 0.4438092112541199, | |
| "learning_rate": 7.61111111111111e-05, | |
| "loss": 1.1209, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.6680688634416141, | |
| "grad_norm": 0.4323583245277405, | |
| "learning_rate": 7.38888888888889e-05, | |
| "loss": 1.0757, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.6780400405079068, | |
| "grad_norm": 0.48928600549697876, | |
| "learning_rate": 7.166666666666667e-05, | |
| "loss": 1.0916, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.6855184233076264, | |
| "eval_loss": 1.100623607635498, | |
| "eval_runtime": 159.5136, | |
| "eval_samples_per_second": 25.678, | |
| "eval_steps_per_second": 1.605, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.6880112175741996, | |
| "grad_norm": 0.4694391191005707, | |
| "learning_rate": 6.944444444444444e-05, | |
| "loss": 1.0973, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.6979823946404923, | |
| "grad_norm": 0.4758254289627075, | |
| "learning_rate": 6.722222222222223e-05, | |
| "loss": 1.0915, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7079535717067851, | |
| "grad_norm": 0.44181302189826965, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 1.0975, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.7179247487730778, | |
| "grad_norm": 0.43584778904914856, | |
| "learning_rate": 6.277777777777778e-05, | |
| "loss": 1.1253, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.7278959258393706, | |
| "grad_norm": 0.45839089155197144, | |
| "learning_rate": 6.055555555555555e-05, | |
| "loss": 1.1588, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.7378671029056633, | |
| "grad_norm": 0.468307763338089, | |
| "learning_rate": 5.833333333333334e-05, | |
| "loss": 1.0903, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.7478382799719561, | |
| "grad_norm": 0.43359532952308655, | |
| "learning_rate": 5.6111111111111114e-05, | |
| "loss": 1.0861, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7478382799719561, | |
| "eval_loss": 1.096602201461792, | |
| "eval_runtime": 159.5808, | |
| "eval_samples_per_second": 25.667, | |
| "eval_steps_per_second": 1.604, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7578094570382488, | |
| "grad_norm": 0.4408925771713257, | |
| "learning_rate": 5.388888888888889e-05, | |
| "loss": 1.1312, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.7677806341045416, | |
| "grad_norm": 0.441047728061676, | |
| "learning_rate": 5.166666666666667e-05, | |
| "loss": 1.1003, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.7777518111708344, | |
| "grad_norm": 0.4418092966079712, | |
| "learning_rate": 4.9444444444444446e-05, | |
| "loss": 1.0769, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.787722988237127, | |
| "grad_norm": 0.43967655301094055, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 1.1025, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.7976941653034199, | |
| "grad_norm": 0.4572228193283081, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.089, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8076653423697125, | |
| "grad_norm": 0.4731937050819397, | |
| "learning_rate": 4.277777777777778e-05, | |
| "loss": 1.0935, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.8101581366362858, | |
| "eval_loss": 1.0938494205474854, | |
| "eval_runtime": 159.6842, | |
| "eval_samples_per_second": 25.651, | |
| "eval_steps_per_second": 1.603, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.8176365194360053, | |
| "grad_norm": 0.4658983051776886, | |
| "learning_rate": 4.055555555555556e-05, | |
| "loss": 1.1127, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.827607696502298, | |
| "grad_norm": 0.4431600272655487, | |
| "learning_rate": 3.8333333333333334e-05, | |
| "loss": 1.1115, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.8375788735685908, | |
| "grad_norm": 0.531471848487854, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 1.0852, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.8475500506348835, | |
| "grad_norm": 0.43536490201950073, | |
| "learning_rate": 3.388888888888889e-05, | |
| "loss": 1.0834, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8575212277011763, | |
| "grad_norm": 0.4632166624069214, | |
| "learning_rate": 3.1666666666666666e-05, | |
| "loss": 1.1029, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.867492404767469, | |
| "grad_norm": 0.46226751804351807, | |
| "learning_rate": 2.9444444444444448e-05, | |
| "loss": 1.0967, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.8724779933006154, | |
| "eval_loss": 1.0916736125946045, | |
| "eval_runtime": 159.6244, | |
| "eval_samples_per_second": 25.66, | |
| "eval_steps_per_second": 1.604, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8774635818337618, | |
| "grad_norm": 0.46160823106765747, | |
| "learning_rate": 2.7222222222222223e-05, | |
| "loss": 1.0907, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.8874347589000545, | |
| "grad_norm": 0.4519442915916443, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.1106, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.8974059359663473, | |
| "grad_norm": 0.43158119916915894, | |
| "learning_rate": 2.277777777777778e-05, | |
| "loss": 1.0957, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.90737711303264, | |
| "grad_norm": 0.4569935202598572, | |
| "learning_rate": 2.0555555555555555e-05, | |
| "loss": 1.1244, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.9173482900989328, | |
| "grad_norm": 0.44798123836517334, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 1.0899, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.9273194671652255, | |
| "grad_norm": 0.459721177816391, | |
| "learning_rate": 1.6111111111111115e-05, | |
| "loss": 1.1039, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.9347978499649451, | |
| "eval_loss": 1.0899683237075806, | |
| "eval_runtime": 159.8757, | |
| "eval_samples_per_second": 25.62, | |
| "eval_steps_per_second": 1.601, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.9372906442315183, | |
| "grad_norm": 0.4426051080226898, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 1.0921, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.947261821297811, | |
| "grad_norm": 0.4699947237968445, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 1.1004, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9572329983641038, | |
| "grad_norm": 0.4296768307685852, | |
| "learning_rate": 9.444444444444445e-06, | |
| "loss": 1.09, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.9672041754303965, | |
| "grad_norm": 0.46838051080703735, | |
| "learning_rate": 7.222222222222222e-06, | |
| "loss": 1.1073, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.9771753524966893, | |
| "grad_norm": 0.46618735790252686, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1122, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.987146529562982, | |
| "grad_norm": 0.4417199492454529, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 1.0874, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.9971177066292748, | |
| "grad_norm": 0.4636310040950775, | |
| "learning_rate": 5.555555555555556e-07, | |
| "loss": 1.1026, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9971177066292748, | |
| "eval_loss": 1.0892398357391357, | |
| "eval_runtime": 159.6704, | |
| "eval_samples_per_second": 25.653, | |
| "eval_steps_per_second": 1.603, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 4, | |
| "max_steps": 401, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 512, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.4365963772771697e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |