| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.951871657754011, |
| "eval_steps": 500, |
| "global_step": 138, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "grad_norm": 11.018006324768066, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.6998, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 10.882867813110352, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.6767, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 5.233364582061768, |
| "learning_rate": 1.2e-05, |
| "loss": 0.4929, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 2.3831398487091064, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.4367, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 2.242455005645752, |
| "learning_rate": 2e-05, |
| "loss": 0.3887, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 2.6488430500030518, |
| "learning_rate": 1.9997210372120276e-05, |
| "loss": 0.3501, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 2.1220874786376953, |
| "learning_rate": 1.998884304488584e-05, |
| "loss": 0.3365, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 1.2483007907867432, |
| "learning_rate": 1.997490268664256e-05, |
| "loss": 0.2988, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 1.2672760486602783, |
| "learning_rate": 1.995539707507284e-05, |
| "loss": 0.2753, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 1.1268620491027832, |
| "learning_rate": 1.9930337092856243e-05, |
| "loss": 0.2908, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.9041132926940918, |
| "learning_rate": 1.9899736721597787e-05, |
| "loss": 0.2738, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.8948485851287842, |
| "learning_rate": 1.9863613034027224e-05, |
| "loss": 0.2685, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.8833632469177246, |
| "learning_rate": 1.9821986184473757e-05, |
| "loss": 0.2725, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.7913200855255127, |
| "learning_rate": 1.9774879397621387e-05, |
| "loss": 0.251, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.7893561124801636, |
| "learning_rate": 1.9722318955551307e-05, |
| "loss": 0.2653, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.8080962300300598, |
| "learning_rate": 1.966433418307843e-05, |
| "loss": 0.2521, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.7054812908172607, |
| "learning_rate": 1.960095743139033e-05, |
| "loss": 0.2407, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.7397778630256653, |
| "learning_rate": 1.9532224059997693e-05, |
| "loss": 0.2502, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.6486859917640686, |
| "learning_rate": 1.9458172417006347e-05, |
| "loss": 0.2285, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.680087685585022, |
| "learning_rate": 1.9378843817721856e-05, |
| "loss": 0.247, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.6315130591392517, |
| "learning_rate": 1.929428252159866e-05, |
| "loss": 0.2378, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.644838273525238, |
| "learning_rate": 1.9204535707546602e-05, |
| "loss": 0.2327, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.635246992111206, |
| "learning_rate": 1.9109653447608607e-05, |
| "loss": 0.2215, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.6007275581359863, |
| "learning_rate": 1.900968867902419e-05, |
| "loss": 0.2295, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.6079221963882446, |
| "learning_rate": 1.8904697174694447e-05, |
| "loss": 0.2255, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.6479413509368896, |
| "learning_rate": 1.879473751206489e-05, |
| "loss": 0.2379, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.577974259853363, |
| "learning_rate": 1.8679871040443632e-05, |
| "loss": 0.228, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.627631664276123, |
| "learning_rate": 1.8560161846773002e-05, |
| "loss": 0.2168, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.5432839393615723, |
| "learning_rate": 1.8435676719873828e-05, |
| "loss": 0.2229, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.5749163627624512, |
| "learning_rate": 1.830648511318223e-05, |
| "loss": 0.2334, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.5687035322189331, |
| "learning_rate": 1.817265910599978e-05, |
| "loss": 0.2209, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.5767927765846252, |
| "learning_rate": 1.8034273363278615e-05, |
| "loss": 0.2222, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.5638836622238159, |
| "learning_rate": 1.789140509396394e-05, |
| "loss": 0.2189, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.5906592607498169, |
| "learning_rate": 1.7744134007917195e-05, |
| "loss": 0.2265, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.7060642242431641, |
| "learning_rate": 1.7592542271443888e-05, |
| "loss": 0.2313, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.5480811595916748, |
| "learning_rate": 1.74367144614509e-05, |
| "loss": 0.213, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.6002165079116821, |
| "learning_rate": 1.7276737518258865e-05, |
| "loss": 0.2048, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.506886899471283, |
| "learning_rate": 1.7112700697095955e-05, |
| "loss": 0.1949, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.5536313056945801, |
| "learning_rate": 1.6944695518300087e-05, |
| "loss": 0.2213, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.5907570719718933, |
| "learning_rate": 1.6772815716257414e-05, |
| "loss": 0.2208, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.6060502529144287, |
| "learning_rate": 1.6597157187105475e-05, |
| "loss": 0.218, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.4885999858379364, |
| "learning_rate": 1.6417817935230318e-05, |
| "loss": 0.197, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.5662249326705933, |
| "learning_rate": 1.6234898018587336e-05, |
| "loss": 0.2079, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.5114175081253052, |
| "learning_rate": 1.6048499492876378e-05, |
| "loss": 0.2025, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.5283780694007874, |
| "learning_rate": 1.5858726354602248e-05, |
| "loss": 0.2021, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.520852267742157, |
| "learning_rate": 1.5665684483052425e-05, |
| "loss": 0.2034, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.01, |
| "grad_norm": 0.5334113240242004, |
| "learning_rate": 1.5469481581224274e-05, |
| "loss": 0.192, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.03, |
| "grad_norm": 0.48935821652412415, |
| "learning_rate": 1.527022711573479e-05, |
| "loss": 0.1745, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.05, |
| "grad_norm": 0.4714067578315735, |
| "learning_rate": 1.50680322557464e-05, |
| "loss": 0.1642, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.07, |
| "grad_norm": 0.5867738723754883, |
| "learning_rate": 1.4863009810942814e-05, |
| "loss": 0.1676, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.09, |
| "grad_norm": 0.4998800754547119, |
| "learning_rate": 1.4655274168589635e-05, |
| "loss": 0.1607, |
| "step": 51 |
| }, |
| { |
| "epoch": 1.11, |
| "grad_norm": 0.47770363092422485, |
| "learning_rate": 1.444494122971476e-05, |
| "loss": 0.1559, |
| "step": 52 |
| }, |
| { |
| "epoch": 1.13, |
| "grad_norm": 0.5769672393798828, |
| "learning_rate": 1.4232128344444251e-05, |
| "loss": 0.1618, |
| "step": 53 |
| }, |
| { |
| "epoch": 1.16, |
| "grad_norm": 0.5382114052772522, |
| "learning_rate": 1.4016954246529697e-05, |
| "loss": 0.1557, |
| "step": 54 |
| }, |
| { |
| "epoch": 1.18, |
| "grad_norm": 0.5243028402328491, |
| "learning_rate": 1.37995389871036e-05, |
| "loss": 0.1594, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 0.5232256650924683, |
| "learning_rate": 1.3580003867699801e-05, |
| "loss": 0.1539, |
| "step": 56 |
| }, |
| { |
| "epoch": 1.22, |
| "grad_norm": 0.4883546233177185, |
| "learning_rate": 1.3358471372576229e-05, |
| "loss": 0.1548, |
| "step": 57 |
| }, |
| { |
| "epoch": 1.24, |
| "grad_norm": 0.49061495065689087, |
| "learning_rate": 1.3135065100377816e-05, |
| "loss": 0.152, |
| "step": 58 |
| }, |
| { |
| "epoch": 1.26, |
| "grad_norm": 0.5039623379707336, |
| "learning_rate": 1.2909909695177647e-05, |
| "loss": 0.1528, |
| "step": 59 |
| }, |
| { |
| "epoch": 1.28, |
| "grad_norm": 0.4839945137500763, |
| "learning_rate": 1.268313077693485e-05, |
| "loss": 0.1664, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.3, |
| "grad_norm": 0.4664023220539093, |
| "learning_rate": 1.2454854871407993e-05, |
| "loss": 0.151, |
| "step": 61 |
| }, |
| { |
| "epoch": 1.33, |
| "grad_norm": 0.514015257358551, |
| "learning_rate": 1.2225209339563144e-05, |
| "loss": 0.1536, |
| "step": 62 |
| }, |
| { |
| "epoch": 1.35, |
| "grad_norm": 0.48316332697868347, |
| "learning_rate": 1.1994322306515926e-05, |
| "loss": 0.1575, |
| "step": 63 |
| }, |
| { |
| "epoch": 1.37, |
| "grad_norm": 0.5091723203659058, |
| "learning_rate": 1.176232259004722e-05, |
| "loss": 0.1532, |
| "step": 64 |
| }, |
| { |
| "epoch": 1.39, |
| "grad_norm": 0.5368977785110474, |
| "learning_rate": 1.1529339628732462e-05, |
| "loss": 0.1479, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.41, |
| "grad_norm": 0.47883716225624084, |
| "learning_rate": 1.1295503409724526e-05, |
| "loss": 0.1632, |
| "step": 66 |
| }, |
| { |
| "epoch": 1.43, |
| "grad_norm": 0.4837721586227417, |
| "learning_rate": 1.1060944396230583e-05, |
| "loss": 0.1482, |
| "step": 67 |
| }, |
| { |
| "epoch": 1.45, |
| "grad_norm": 0.5128870606422424, |
| "learning_rate": 1.0825793454723325e-05, |
| "loss": 0.1505, |
| "step": 68 |
| }, |
| { |
| "epoch": 1.48, |
| "grad_norm": 0.5082117319107056, |
| "learning_rate": 1.0590181781927229e-05, |
| "loss": 0.1495, |
| "step": 69 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 0.4825822710990906, |
| "learning_rate": 1.0354240831620542e-05, |
| "loss": 0.1462, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.52, |
| "grad_norm": 0.5053706169128418, |
| "learning_rate": 1.0118102241293848e-05, |
| "loss": 0.1526, |
| "step": 71 |
| }, |
| { |
| "epoch": 1.54, |
| "grad_norm": 0.4774819314479828, |
| "learning_rate": 9.881897758706155e-06, |
| "loss": 0.145, |
| "step": 72 |
| }, |
| { |
| "epoch": 1.56, |
| "grad_norm": 0.5309439301490784, |
| "learning_rate": 9.645759168379463e-06, |
| "loss": 0.1524, |
| "step": 73 |
| }, |
| { |
| "epoch": 1.58, |
| "grad_norm": 0.49872881174087524, |
| "learning_rate": 9.409818218072774e-06, |
| "loss": 0.1531, |
| "step": 74 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 0.46325036883354187, |
| "learning_rate": 9.174206545276678e-06, |
| "loss": 0.15, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.63, |
| "grad_norm": 0.492448627948761, |
| "learning_rate": 8.93905560376942e-06, |
| "loss": 0.1543, |
| "step": 76 |
| }, |
| { |
| "epoch": 1.65, |
| "grad_norm": 0.5049591064453125, |
| "learning_rate": 8.704496590275479e-06, |
| "loss": 0.1539, |
| "step": 77 |
| }, |
| { |
| "epoch": 1.67, |
| "grad_norm": 0.47460246086120605, |
| "learning_rate": 8.47066037126754e-06, |
| "loss": 0.1519, |
| "step": 78 |
| }, |
| { |
| "epoch": 1.69, |
| "grad_norm": 0.4622434377670288, |
| "learning_rate": 8.237677409952784e-06, |
| "loss": 0.1556, |
| "step": 79 |
| }, |
| { |
| "epoch": 1.71, |
| "grad_norm": 0.48065298795700073, |
| "learning_rate": 8.005677693484077e-06, |
| "loss": 0.1527, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.73, |
| "grad_norm": 0.46688997745513916, |
| "learning_rate": 7.774790660436857e-06, |
| "loss": 0.1506, |
| "step": 81 |
| }, |
| { |
| "epoch": 1.75, |
| "grad_norm": 0.48199203610420227, |
| "learning_rate": 7.545145128592009e-06, |
| "loss": 0.1513, |
| "step": 82 |
| }, |
| { |
| "epoch": 1.78, |
| "grad_norm": 0.43717241287231445, |
| "learning_rate": 7.316869223065156e-06, |
| "loss": 0.1383, |
| "step": 83 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 0.430442750453949, |
| "learning_rate": 7.090090304822356e-06, |
| "loss": 0.1464, |
| "step": 84 |
| }, |
| { |
| "epoch": 1.82, |
| "grad_norm": 0.46568819880485535, |
| "learning_rate": 6.864934899622191e-06, |
| "loss": 0.1467, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.84, |
| "grad_norm": 0.43684783577919006, |
| "learning_rate": 6.6415286274237744e-06, |
| "loss": 0.1449, |
| "step": 86 |
| }, |
| { |
| "epoch": 1.86, |
| "grad_norm": 0.47609564661979675, |
| "learning_rate": 6.419996132300203e-06, |
| "loss": 0.1426, |
| "step": 87 |
| }, |
| { |
| "epoch": 1.88, |
| "grad_norm": 0.44510510563850403, |
| "learning_rate": 6.200461012896401e-06, |
| "loss": 0.1435, |
| "step": 88 |
| }, |
| { |
| "epoch": 1.9, |
| "grad_norm": 0.47285887598991394, |
| "learning_rate": 5.983045753470308e-06, |
| "loss": 0.1441, |
| "step": 89 |
| }, |
| { |
| "epoch": 1.93, |
| "grad_norm": 0.44643670320510864, |
| "learning_rate": 5.7678716555557515e-06, |
| "loss": 0.1466, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.95, |
| "grad_norm": 0.4684978425502777, |
| "learning_rate": 5.5550587702852465e-06, |
| "loss": 0.1346, |
| "step": 91 |
| }, |
| { |
| "epoch": 1.97, |
| "grad_norm": 0.4379321038722992, |
| "learning_rate": 5.344725831410369e-06, |
| "loss": 0.1477, |
| "step": 92 |
| }, |
| { |
| "epoch": 1.99, |
| "grad_norm": 0.4445021152496338, |
| "learning_rate": 5.136990189057187e-06, |
| "loss": 0.145, |
| "step": 93 |
| }, |
| { |
| "epoch": 2.01, |
| "grad_norm": 0.39833515882492065, |
| "learning_rate": 4.931967744253601e-06, |
| "loss": 0.1227, |
| "step": 94 |
| }, |
| { |
| "epoch": 2.03, |
| "grad_norm": 0.39141109585762024, |
| "learning_rate": 4.729772884265212e-06, |
| "loss": 0.1094, |
| "step": 95 |
| }, |
| { |
| "epoch": 2.05, |
| "grad_norm": 0.4277079403400421, |
| "learning_rate": 4.530518418775734e-06, |
| "loss": 0.1127, |
| "step": 96 |
| }, |
| { |
| "epoch": 2.07, |
| "grad_norm": 0.3967771530151367, |
| "learning_rate": 4.33431551694758e-06, |
| "loss": 0.1127, |
| "step": 97 |
| }, |
| { |
| "epoch": 2.1, |
| "grad_norm": 0.39447346329689026, |
| "learning_rate": 4.1412736453977545e-06, |
| "loss": 0.1096, |
| "step": 98 |
| }, |
| { |
| "epoch": 2.12, |
| "grad_norm": 0.4039708971977234, |
| "learning_rate": 3.9515005071236274e-06, |
| "loss": 0.1091, |
| "step": 99 |
| }, |
| { |
| "epoch": 2.14, |
| "grad_norm": 0.41506198048591614, |
| "learning_rate": 3.7651019814126656e-06, |
| "loss": 0.1121, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.16, |
| "grad_norm": 0.40431180596351624, |
| "learning_rate": 3.582182064769687e-06, |
| "loss": 0.1056, |
| "step": 101 |
| }, |
| { |
| "epoch": 2.18, |
| "grad_norm": 0.4232732355594635, |
| "learning_rate": 3.402842812894529e-06, |
| "loss": 0.1037, |
| "step": 102 |
| }, |
| { |
| "epoch": 2.2, |
| "grad_norm": 0.42869406938552856, |
| "learning_rate": 3.2271842837425917e-06, |
| "loss": 0.1091, |
| "step": 103 |
| }, |
| { |
| "epoch": 2.22, |
| "grad_norm": 0.4143657386302948, |
| "learning_rate": 3.0553044816999133e-06, |
| "loss": 0.1063, |
| "step": 104 |
| }, |
| { |
| "epoch": 2.25, |
| "grad_norm": 0.42850592732429504, |
| "learning_rate": 2.8872993029040506e-06, |
| "loss": 0.1067, |
| "step": 105 |
| }, |
| { |
| "epoch": 2.27, |
| "grad_norm": 0.4256628751754761, |
| "learning_rate": 2.723262481741138e-06, |
| "loss": 0.1032, |
| "step": 106 |
| }, |
| { |
| "epoch": 2.29, |
| "grad_norm": 0.4140647351741791, |
| "learning_rate": 2.563285538549104e-06, |
| "loss": 0.1032, |
| "step": 107 |
| }, |
| { |
| "epoch": 2.31, |
| "grad_norm": 0.4351275563240051, |
| "learning_rate": 2.407457728556115e-06, |
| "loss": 0.1085, |
| "step": 108 |
| }, |
| { |
| "epoch": 2.33, |
| "grad_norm": 0.41570809483528137, |
| "learning_rate": 2.2558659920828095e-06, |
| "loss": 0.1002, |
| "step": 109 |
| }, |
| { |
| "epoch": 2.35, |
| "grad_norm": 0.4311833679676056, |
| "learning_rate": 2.1085949060360654e-06, |
| "loss": 0.1033, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.37, |
| "grad_norm": 0.4352239966392517, |
| "learning_rate": 1.96572663672139e-06, |
| "loss": 0.1039, |
| "step": 111 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 0.42311662435531616, |
| "learning_rate": 1.8273408940002202e-06, |
| "loss": 0.1079, |
| "step": 112 |
| }, |
| { |
| "epoch": 2.42, |
| "grad_norm": 0.4299164116382599, |
| "learning_rate": 1.693514886817772e-06, |
| "loss": 0.1111, |
| "step": 113 |
| }, |
| { |
| "epoch": 2.44, |
| "grad_norm": 0.42951837182044983, |
| "learning_rate": 1.5643232801261731e-06, |
| "loss": 0.1046, |
| "step": 114 |
| }, |
| { |
| "epoch": 2.46, |
| "grad_norm": 0.415314644575119, |
| "learning_rate": 1.4398381532270001e-06, |
| "loss": 0.0994, |
| "step": 115 |
| }, |
| { |
| "epoch": 2.48, |
| "grad_norm": 0.4161585569381714, |
| "learning_rate": 1.3201289595563693e-06, |
| "loss": 0.1031, |
| "step": 116 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.4365871548652649, |
| "learning_rate": 1.2052624879351105e-06, |
| "loss": 0.1041, |
| "step": 117 |
| }, |
| { |
| "epoch": 2.52, |
| "grad_norm": 0.44634222984313965, |
| "learning_rate": 1.0953028253055541e-06, |
| "loss": 0.1087, |
| "step": 118 |
| }, |
| { |
| "epoch": 2.55, |
| "grad_norm": 0.42212435603141785, |
| "learning_rate": 9.903113209758098e-07, |
| "loss": 0.1038, |
| "step": 119 |
| }, |
| { |
| "epoch": 2.57, |
| "grad_norm": 0.4193635880947113, |
| "learning_rate": 8.903465523913957e-07, |
| "loss": 0.1044, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.59, |
| "grad_norm": 0.4123804271221161, |
| "learning_rate": 7.954642924533995e-07, |
| "loss": 0.1048, |
| "step": 121 |
| }, |
| { |
| "epoch": 2.61, |
| "grad_norm": 0.4170967638492584, |
| "learning_rate": 7.057174784013432e-07, |
| "loss": 0.1016, |
| "step": 122 |
| }, |
| { |
| "epoch": 2.63, |
| "grad_norm": 0.39535415172576904, |
| "learning_rate": 6.211561822781476e-07, |
| "loss": 0.1021, |
| "step": 123 |
| }, |
| { |
| "epoch": 2.65, |
| "grad_norm": 0.42464351654052734, |
| "learning_rate": 5.418275829936537e-07, |
| "loss": 0.1022, |
| "step": 124 |
| }, |
| { |
| "epoch": 2.67, |
| "grad_norm": 0.3974105417728424, |
| "learning_rate": 4.6777594000230855e-07, |
| "loss": 0.0977, |
| "step": 125 |
| }, |
| { |
| "epoch": 2.7, |
| "grad_norm": 0.4046030044555664, |
| "learning_rate": 3.9904256860967436e-07, |
| "loss": 0.1064, |
| "step": 126 |
| }, |
| { |
| "epoch": 2.72, |
| "grad_norm": 0.40393462777137756, |
| "learning_rate": 3.356658169215743e-07, |
| "loss": 0.0984, |
| "step": 127 |
| }, |
| { |
| "epoch": 2.74, |
| "grad_norm": 0.41009587049484253, |
| "learning_rate": 2.776810444486944e-07, |
| "loss": 0.1047, |
| "step": 128 |
| }, |
| { |
| "epoch": 2.76, |
| "grad_norm": 0.43705180287361145, |
| "learning_rate": 2.2512060237861455e-07, |
| "loss": 0.1079, |
| "step": 129 |
| }, |
| { |
| "epoch": 2.78, |
| "grad_norm": 0.40315163135528564, |
| "learning_rate": 1.7801381552624565e-07, |
| "loss": 0.1072, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 0.4215686619281769, |
| "learning_rate": 1.3638696597277678e-07, |
| "loss": 0.0963, |
| "step": 131 |
| }, |
| { |
| "epoch": 2.82, |
| "grad_norm": 0.4069172143936157, |
| "learning_rate": 1.0026327840221728e-07, |
| "loss": 0.1031, |
| "step": 132 |
| }, |
| { |
| "epoch": 2.84, |
| "grad_norm": 0.4056784212589264, |
| "learning_rate": 6.966290714375934e-08, |
| "loss": 0.1067, |
| "step": 133 |
| }, |
| { |
| "epoch": 2.87, |
| "grad_norm": 0.4223578870296478, |
| "learning_rate": 4.460292492716512e-08, |
| "loss": 0.1, |
| "step": 134 |
| }, |
| { |
| "epoch": 2.89, |
| "grad_norm": 0.403411865234375, |
| "learning_rate": 2.509731335744281e-08, |
| "loss": 0.1012, |
| "step": 135 |
| }, |
| { |
| "epoch": 2.91, |
| "grad_norm": 0.40073734521865845, |
| "learning_rate": 1.1156955114162149e-08, |
| "loss": 0.1105, |
| "step": 136 |
| }, |
| { |
| "epoch": 2.93, |
| "grad_norm": 0.4212948679924011, |
| "learning_rate": 2.7896278797256983e-09, |
| "loss": 0.1089, |
| "step": 137 |
| }, |
| { |
| "epoch": 2.95, |
| "grad_norm": 0.395971417427063, |
| "learning_rate": 0.0, |
| "loss": 0.1008, |
| "step": 138 |
| }, |
| { |
| "epoch": 2.95, |
| "step": 138, |
| "total_flos": 4.376704383744737e+17, |
| "train_loss": 0.1770511907727822, |
| "train_runtime": 5018.0498, |
| "train_samples_per_second": 3.574, |
| "train_steps_per_second": 0.028 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 138, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 1200, |
| "total_flos": 4.376704383744737e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
