| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.25033952297803896, | |
| "global_step": 40000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.984353779813873e-05, | |
| "loss": 2.5206, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_bleu": 38.3843, | |
| "eval_gen_len": 23.8603, | |
| "eval_loss": 1.8556830883026123, | |
| "eval_runtime": 1197.8495, | |
| "eval_samples_per_second": 2.515, | |
| "eval_steps_per_second": 0.629, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9687075596277455e-05, | |
| "loss": 1.9572, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_bleu": 22.3733, | |
| "eval_gen_len": 18.9091, | |
| "eval_loss": 2.9118094444274902, | |
| "eval_runtime": 1006.4293, | |
| "eval_samples_per_second": 2.994, | |
| "eval_steps_per_second": 0.749, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.953061339441618e-05, | |
| "loss": 1.7653, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_bleu": 38.119, | |
| "eval_gen_len": 23.6728, | |
| "eval_loss": 1.9158709049224854, | |
| "eval_runtime": 1104.4939, | |
| "eval_samples_per_second": 2.728, | |
| "eval_steps_per_second": 0.683, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.937415119255491e-05, | |
| "loss": 1.715, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_bleu": 37.8451, | |
| "eval_gen_len": 23.7046, | |
| "eval_loss": 1.9664654731750488, | |
| "eval_runtime": 1119.4046, | |
| "eval_samples_per_second": 2.692, | |
| "eval_steps_per_second": 0.674, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.921768899069363e-05, | |
| "loss": 1.7164, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_bleu": 36.315, | |
| "eval_gen_len": 23.1172, | |
| "eval_loss": 1.8593918085098267, | |
| "eval_runtime": 1061.9031, | |
| "eval_samples_per_second": 2.837, | |
| "eval_steps_per_second": 0.71, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.906122678883235e-05, | |
| "loss": 1.616, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_bleu": 37.6941, | |
| "eval_gen_len": 23.617, | |
| "eval_loss": 1.816091537475586, | |
| "eval_runtime": 1096.7235, | |
| "eval_samples_per_second": 2.747, | |
| "eval_steps_per_second": 0.688, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.890476458697108e-05, | |
| "loss": 1.6131, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_bleu": 34.7085, | |
| "eval_gen_len": 22.4826, | |
| "eval_loss": 1.9029065370559692, | |
| "eval_runtime": 1058.2776, | |
| "eval_samples_per_second": 2.847, | |
| "eval_steps_per_second": 0.712, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.8748302385109805e-05, | |
| "loss": 1.5981, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_bleu": 37.0045, | |
| "eval_gen_len": 24.0611, | |
| "eval_loss": 1.9932270050048828, | |
| "eval_runtime": 1166.939, | |
| "eval_samples_per_second": 2.582, | |
| "eval_steps_per_second": 0.646, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.859184018324853e-05, | |
| "loss": 1.5898, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_bleu": 38.2992, | |
| "eval_gen_len": 24.2121, | |
| "eval_loss": 1.874466896057129, | |
| "eval_runtime": 1133.0065, | |
| "eval_samples_per_second": 2.659, | |
| "eval_steps_per_second": 0.665, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.843537798138726e-05, | |
| "loss": 1.5582, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_bleu": 36.9851, | |
| "eval_gen_len": 23.4202, | |
| "eval_loss": 1.8227670192718506, | |
| "eval_runtime": 1093.0431, | |
| "eval_samples_per_second": 2.757, | |
| "eval_steps_per_second": 0.69, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.8278915779525984e-05, | |
| "loss": 1.7726, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_bleu": 32.3628, | |
| "eval_gen_len": 22.3083, | |
| "eval_loss": 2.096940755844116, | |
| "eval_runtime": 1059.9352, | |
| "eval_samples_per_second": 2.843, | |
| "eval_steps_per_second": 0.711, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.812245357766471e-05, | |
| "loss": 1.7102, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_bleu": 36.1748, | |
| "eval_gen_len": 24.1942, | |
| "eval_loss": 2.018200397491455, | |
| "eval_runtime": 1129.5162, | |
| "eval_samples_per_second": 2.668, | |
| "eval_steps_per_second": 0.668, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.7965991375803436e-05, | |
| "loss": 1.521, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_bleu": 32.2516, | |
| "eval_gen_len": 28.4076, | |
| "eval_loss": 2.057112693786621, | |
| "eval_runtime": 1610.6798, | |
| "eval_samples_per_second": 1.871, | |
| "eval_steps_per_second": 0.468, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.780952917394216e-05, | |
| "loss": 1.6184, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_bleu": 37.8637, | |
| "eval_gen_len": 23.6844, | |
| "eval_loss": 1.8763169050216675, | |
| "eval_runtime": 1099.6674, | |
| "eval_samples_per_second": 2.74, | |
| "eval_steps_per_second": 0.686, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.765306697208088e-05, | |
| "loss": 1.5384, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_bleu": 37.7753, | |
| "eval_gen_len": 23.8984, | |
| "eval_loss": 1.8554104566574097, | |
| "eval_runtime": 1111.1157, | |
| "eval_samples_per_second": 2.712, | |
| "eval_steps_per_second": 0.679, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.749660477021961e-05, | |
| "loss": 1.5485, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_bleu": 37.1929, | |
| "eval_gen_len": 24.0408, | |
| "eval_loss": 1.9456806182861328, | |
| "eval_runtime": 1136.0111, | |
| "eval_samples_per_second": 2.652, | |
| "eval_steps_per_second": 0.664, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.7340142568358334e-05, | |
| "loss": 1.4872, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_bleu": 35.4276, | |
| "eval_gen_len": 23.2008, | |
| "eval_loss": 1.8643290996551514, | |
| "eval_runtime": 1078.1924, | |
| "eval_samples_per_second": 2.794, | |
| "eval_steps_per_second": 0.699, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.718368036649706e-05, | |
| "loss": 1.4412, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_bleu": 35.7002, | |
| "eval_gen_len": 23.613, | |
| "eval_loss": 1.910874366760254, | |
| "eval_runtime": 1134.7549, | |
| "eval_samples_per_second": 2.655, | |
| "eval_steps_per_second": 0.664, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.702721816463579e-05, | |
| "loss": 1.4483, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_bleu": 37.6828, | |
| "eval_gen_len": 24.0441, | |
| "eval_loss": 1.8838558197021484, | |
| "eval_runtime": 1126.6767, | |
| "eval_samples_per_second": 2.674, | |
| "eval_steps_per_second": 0.669, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.687075596277451e-05, | |
| "loss": 1.4523, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_bleu": 36.2473, | |
| "eval_gen_len": 23.3561, | |
| "eval_loss": 1.940147042274475, | |
| "eval_runtime": 1087.7551, | |
| "eval_samples_per_second": 2.77, | |
| "eval_steps_per_second": 0.693, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.671429376091324e-05, | |
| "loss": 1.4405, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_bleu": 35.6564, | |
| "eval_gen_len": 22.9851, | |
| "eval_loss": 1.8357064723968506, | |
| "eval_runtime": 1082.157, | |
| "eval_samples_per_second": 2.784, | |
| "eval_steps_per_second": 0.697, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.6557831559051965e-05, | |
| "loss": 1.3966, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_bleu": 37.8601, | |
| "eval_gen_len": 24.1235, | |
| "eval_loss": 1.8839383125305176, | |
| "eval_runtime": 1137.6484, | |
| "eval_samples_per_second": 2.648, | |
| "eval_steps_per_second": 0.663, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.640136935719069e-05, | |
| "loss": 1.415, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_bleu": 35.9576, | |
| "eval_gen_len": 23.4434, | |
| "eval_loss": 1.868781566619873, | |
| "eval_runtime": 1187.6496, | |
| "eval_samples_per_second": 2.537, | |
| "eval_steps_per_second": 0.635, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.624490715532942e-05, | |
| "loss": 1.4306, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_bleu": 37.8482, | |
| "eval_gen_len": 24.2154, | |
| "eval_loss": 1.8083645105361938, | |
| "eval_runtime": 1247.7304, | |
| "eval_samples_per_second": 2.415, | |
| "eval_steps_per_second": 0.604, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.6088444953468144e-05, | |
| "loss": 1.3337, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_bleu": 37.4047, | |
| "eval_gen_len": 23.692, | |
| "eval_loss": 1.798228144645691, | |
| "eval_runtime": 1200.6209, | |
| "eval_samples_per_second": 2.51, | |
| "eval_steps_per_second": 0.628, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.593198275160687e-05, | |
| "loss": 1.4188, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_bleu": 36.76, | |
| "eval_gen_len": 23.5446, | |
| "eval_loss": 1.8160576820373535, | |
| "eval_runtime": 1178.8918, | |
| "eval_samples_per_second": 2.556, | |
| "eval_steps_per_second": 0.64, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.5775520549745596e-05, | |
| "loss": 1.3576, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_bleu": 37.1149, | |
| "eval_gen_len": 23.6963, | |
| "eval_loss": 1.8919538259506226, | |
| "eval_runtime": 1218.0527, | |
| "eval_samples_per_second": 2.474, | |
| "eval_steps_per_second": 0.619, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.561905834788432e-05, | |
| "loss": 1.4464, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_bleu": 38.2523, | |
| "eval_gen_len": 24.2449, | |
| "eval_loss": 1.8881698846817017, | |
| "eval_runtime": 1185.5541, | |
| "eval_samples_per_second": 2.541, | |
| "eval_steps_per_second": 0.636, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.546259614602305e-05, | |
| "loss": 1.3548, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_bleu": 37.0608, | |
| "eval_gen_len": 23.6077, | |
| "eval_loss": 1.8448089361190796, | |
| "eval_runtime": 1093.1892, | |
| "eval_samples_per_second": 2.756, | |
| "eval_steps_per_second": 0.69, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.5306133944161775e-05, | |
| "loss": 1.3779, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_bleu": 37.2558, | |
| "eval_gen_len": 23.5888, | |
| "eval_loss": 1.868304967880249, | |
| "eval_runtime": 1104.5613, | |
| "eval_samples_per_second": 2.728, | |
| "eval_steps_per_second": 0.683, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.51496717423005e-05, | |
| "loss": 1.3565, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_bleu": 38.3579, | |
| "eval_gen_len": 24.3107, | |
| "eval_loss": 1.9323915243148804, | |
| "eval_runtime": 1143.8823, | |
| "eval_samples_per_second": 2.634, | |
| "eval_steps_per_second": 0.659, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.499320954043923e-05, | |
| "loss": 1.3474, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_bleu": 37.9665, | |
| "eval_gen_len": 23.8453, | |
| "eval_loss": 1.8365575075149536, | |
| "eval_runtime": 1107.7008, | |
| "eval_samples_per_second": 2.72, | |
| "eval_steps_per_second": 0.681, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.4836747338577954e-05, | |
| "loss": 1.3492, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_bleu": 37.6124, | |
| "eval_gen_len": 23.7939, | |
| "eval_loss": 1.8358746767044067, | |
| "eval_runtime": 1110.7352, | |
| "eval_samples_per_second": 2.713, | |
| "eval_steps_per_second": 0.679, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.468028513671668e-05, | |
| "loss": 1.3347, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_bleu": 37.7852, | |
| "eval_gen_len": 23.8994, | |
| "eval_loss": 1.7998509407043457, | |
| "eval_runtime": 1113.2105, | |
| "eval_samples_per_second": 2.707, | |
| "eval_steps_per_second": 0.677, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.45238229348554e-05, | |
| "loss": 1.3361, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_bleu": 37.3385, | |
| "eval_gen_len": 23.6077, | |
| "eval_loss": 1.849636197090149, | |
| "eval_runtime": 1105.7834, | |
| "eval_samples_per_second": 2.725, | |
| "eval_steps_per_second": 0.682, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.4367360732994125e-05, | |
| "loss": 1.3204, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_bleu": 36.8887, | |
| "eval_gen_len": 23.385, | |
| "eval_loss": 1.8504753112792969, | |
| "eval_runtime": 1074.3508, | |
| "eval_samples_per_second": 2.804, | |
| "eval_steps_per_second": 0.702, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.421089853113285e-05, | |
| "loss": 1.3234, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_bleu": 36.6707, | |
| "eval_gen_len": 23.2629, | |
| "eval_loss": 1.8434782028198242, | |
| "eval_runtime": 1075.4498, | |
| "eval_samples_per_second": 2.802, | |
| "eval_steps_per_second": 0.701, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.405443632927158e-05, | |
| "loss": 1.3189, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_bleu": 36.6831, | |
| "eval_gen_len": 23.6163, | |
| "eval_loss": 1.8203562498092651, | |
| "eval_runtime": 1116.9517, | |
| "eval_samples_per_second": 2.698, | |
| "eval_steps_per_second": 0.675, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.3897974127410304e-05, | |
| "loss": 1.2984, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_bleu": 36.9382, | |
| "eval_gen_len": 23.699, | |
| "eval_loss": 1.7791001796722412, | |
| "eval_runtime": 1129.6793, | |
| "eval_samples_per_second": 2.667, | |
| "eval_steps_per_second": 0.667, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.374151192554903e-05, | |
| "loss": 1.2913, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_bleu": 38.155, | |
| "eval_gen_len": 24.1394, | |
| "eval_loss": 1.8548424243927002, | |
| "eval_runtime": 1126.2716, | |
| "eval_samples_per_second": 2.675, | |
| "eval_steps_per_second": 0.669, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.3585049723687756e-05, | |
| "loss": 1.3222, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_bleu": 37.9634, | |
| "eval_gen_len": 23.9492, | |
| "eval_loss": 1.8165639638900757, | |
| "eval_runtime": 1117.1297, | |
| "eval_samples_per_second": 2.697, | |
| "eval_steps_per_second": 0.675, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.342858752182648e-05, | |
| "loss": 1.3223, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_bleu": 37.6942, | |
| "eval_gen_len": 24.0, | |
| "eval_loss": 1.8118115663528442, | |
| "eval_runtime": 1118.3371, | |
| "eval_samples_per_second": 2.694, | |
| "eval_steps_per_second": 0.674, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.327212531996521e-05, | |
| "loss": 1.3134, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_bleu": 37.7975, | |
| "eval_gen_len": 23.9004, | |
| "eval_loss": 1.8295111656188965, | |
| "eval_runtime": 1106.5041, | |
| "eval_samples_per_second": 2.723, | |
| "eval_steps_per_second": 0.681, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.3115663118103935e-05, | |
| "loss": 1.3045, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_bleu": 37.7737, | |
| "eval_gen_len": 23.9373, | |
| "eval_loss": 1.8213391304016113, | |
| "eval_runtime": 1127.6192, | |
| "eval_samples_per_second": 2.672, | |
| "eval_steps_per_second": 0.669, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.2959200916242654e-05, | |
| "loss": 1.3111, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_bleu": 37.8615, | |
| "eval_gen_len": 23.9519, | |
| "eval_loss": 1.8346147537231445, | |
| "eval_runtime": 1143.7572, | |
| "eval_samples_per_second": 2.634, | |
| "eval_steps_per_second": 0.659, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.280273871438138e-05, | |
| "loss": 1.3346, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_bleu": 38.1234, | |
| "eval_gen_len": 24.1049, | |
| "eval_loss": 1.7679733037948608, | |
| "eval_runtime": 1113.7045, | |
| "eval_samples_per_second": 2.705, | |
| "eval_steps_per_second": 0.677, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.264627651252011e-05, | |
| "loss": 1.2851, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_bleu": 38.1328, | |
| "eval_gen_len": 24.1069, | |
| "eval_loss": 1.801455020904541, | |
| "eval_runtime": 1136.226, | |
| "eval_samples_per_second": 2.652, | |
| "eval_steps_per_second": 0.664, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.248981431065883e-05, | |
| "loss": 1.2732, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_bleu": 37.8569, | |
| "eval_gen_len": 23.8579, | |
| "eval_loss": 1.8218289613723755, | |
| "eval_runtime": 1124.2084, | |
| "eval_samples_per_second": 2.68, | |
| "eval_steps_per_second": 0.671, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.233335210879756e-05, | |
| "loss": 1.2666, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_bleu": 37.3143, | |
| "eval_gen_len": 24.2327, | |
| "eval_loss": 1.8298362493515015, | |
| "eval_runtime": 1169.4328, | |
| "eval_samples_per_second": 2.576, | |
| "eval_steps_per_second": 0.645, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.2176889906936285e-05, | |
| "loss": 1.248, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_bleu": 37.4488, | |
| "eval_gen_len": 24.0846, | |
| "eval_loss": 1.7926667928695679, | |
| "eval_runtime": 1136.492, | |
| "eval_samples_per_second": 2.651, | |
| "eval_steps_per_second": 0.663, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.202042770507501e-05, | |
| "loss": 1.2586, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_bleu": 36.9098, | |
| "eval_gen_len": 23.5061, | |
| "eval_loss": 1.8259001970291138, | |
| "eval_runtime": 1094.3744, | |
| "eval_samples_per_second": 2.753, | |
| "eval_steps_per_second": 0.689, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.186396550321374e-05, | |
| "loss": 1.2305, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_bleu": 37.6963, | |
| "eval_gen_len": 23.9618, | |
| "eval_loss": 1.7810018062591553, | |
| "eval_runtime": 1112.8793, | |
| "eval_samples_per_second": 2.707, | |
| "eval_steps_per_second": 0.678, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.1707503301352464e-05, | |
| "loss": 1.2435, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_bleu": 38.219, | |
| "eval_gen_len": 24.2695, | |
| "eval_loss": 1.8444660902023315, | |
| "eval_runtime": 1136.4697, | |
| "eval_samples_per_second": 2.651, | |
| "eval_steps_per_second": 0.663, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.155104109949119e-05, | |
| "loss": 1.2681, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_bleu": 38.0339, | |
| "eval_gen_len": 23.8065, | |
| "eval_loss": 1.8042678833007812, | |
| "eval_runtime": 1110.1648, | |
| "eval_samples_per_second": 2.714, | |
| "eval_steps_per_second": 0.679, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.139457889762991e-05, | |
| "loss": 1.2581, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_bleu": 36.7337, | |
| "eval_gen_len": 23.6279, | |
| "eval_loss": 1.7898603677749634, | |
| "eval_runtime": 1101.1993, | |
| "eval_samples_per_second": 2.736, | |
| "eval_steps_per_second": 0.685, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.1238116695768636e-05, | |
| "loss": 1.2476, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_bleu": 37.5418, | |
| "eval_gen_len": 23.7527, | |
| "eval_loss": 1.851403832435608, | |
| "eval_runtime": 1100.3622, | |
| "eval_samples_per_second": 2.738, | |
| "eval_steps_per_second": 0.685, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.108165449390736e-05, | |
| "loss": 1.2778, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_bleu": 36.9893, | |
| "eval_gen_len": 23.8487, | |
| "eval_loss": 1.7635945081710815, | |
| "eval_runtime": 1113.9066, | |
| "eval_samples_per_second": 2.705, | |
| "eval_steps_per_second": 0.677, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.092519229204609e-05, | |
| "loss": 1.2335, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_bleu": 38.4148, | |
| "eval_gen_len": 24.0743, | |
| "eval_loss": 1.7612364292144775, | |
| "eval_runtime": 1118.162, | |
| "eval_samples_per_second": 2.695, | |
| "eval_steps_per_second": 0.674, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.0768730090184814e-05, | |
| "loss": 1.2229, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_bleu": 38.387, | |
| "eval_gen_len": 24.1324, | |
| "eval_loss": 1.724638819694519, | |
| "eval_runtime": 1133.5566, | |
| "eval_samples_per_second": 2.658, | |
| "eval_steps_per_second": 0.665, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.061226788832354e-05, | |
| "loss": 1.198, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_bleu": 38.2916, | |
| "eval_gen_len": 23.918, | |
| "eval_loss": 1.7657166719436646, | |
| "eval_runtime": 1258.8163, | |
| "eval_samples_per_second": 2.394, | |
| "eval_steps_per_second": 0.599, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.045580568646227e-05, | |
| "loss": 1.281, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_bleu": 36.5976, | |
| "eval_gen_len": 23.24, | |
| "eval_loss": 1.758962631225586, | |
| "eval_runtime": 1321.212, | |
| "eval_samples_per_second": 2.28, | |
| "eval_steps_per_second": 0.571, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.029934348460099e-05, | |
| "loss": 1.231, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_bleu": 37.8396, | |
| "eval_gen_len": 23.7385, | |
| "eval_loss": 1.733566164970398, | |
| "eval_runtime": 1419.0837, | |
| "eval_samples_per_second": 2.123, | |
| "eval_steps_per_second": 0.531, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.014288128273972e-05, | |
| "loss": 1.2014, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_bleu": 37.8945, | |
| "eval_gen_len": 23.8025, | |
| "eval_loss": 1.7839374542236328, | |
| "eval_runtime": 1450.5502, | |
| "eval_samples_per_second": 2.077, | |
| "eval_steps_per_second": 0.52, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.9986419080878445e-05, | |
| "loss": 1.2295, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_bleu": 37.9001, | |
| "eval_gen_len": 23.92, | |
| "eval_loss": 1.757741928100586, | |
| "eval_runtime": 1476.1175, | |
| "eval_samples_per_second": 2.041, | |
| "eval_steps_per_second": 0.511, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.9829956879017165e-05, | |
| "loss": 1.2154, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_bleu": 37.5283, | |
| "eval_gen_len": 23.537, | |
| "eval_loss": 1.80224609375, | |
| "eval_runtime": 1473.4024, | |
| "eval_samples_per_second": 2.045, | |
| "eval_steps_per_second": 0.512, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.967349467715589e-05, | |
| "loss": 1.1956, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_bleu": 38.5709, | |
| "eval_gen_len": 24.0189, | |
| "eval_loss": 1.7815015316009521, | |
| "eval_runtime": 1398.0131, | |
| "eval_samples_per_second": 2.155, | |
| "eval_steps_per_second": 0.539, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.951703247529462e-05, | |
| "loss": 1.2045, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_bleu": 37.2706, | |
| "eval_gen_len": 23.2522, | |
| "eval_loss": 1.7592459917068481, | |
| "eval_runtime": 1445.8551, | |
| "eval_samples_per_second": 2.084, | |
| "eval_steps_per_second": 0.521, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.9360570273433344e-05, | |
| "loss": 1.1796, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_bleu": 38.5198, | |
| "eval_gen_len": 24.078, | |
| "eval_loss": 1.8075897693634033, | |
| "eval_runtime": 1528.5032, | |
| "eval_samples_per_second": 1.971, | |
| "eval_steps_per_second": 0.493, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.920410807157207e-05, | |
| "loss": 1.226, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_bleu": 38.1729, | |
| "eval_gen_len": 23.9038, | |
| "eval_loss": 1.731508493423462, | |
| "eval_runtime": 1501.9126, | |
| "eval_samples_per_second": 2.006, | |
| "eval_steps_per_second": 0.502, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.9047645869710796e-05, | |
| "loss": 1.2304, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_bleu": 37.8875, | |
| "eval_gen_len": 23.8493, | |
| "eval_loss": 1.7690067291259766, | |
| "eval_runtime": 1584.8349, | |
| "eval_samples_per_second": 1.901, | |
| "eval_steps_per_second": 0.476, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.889118366784952e-05, | |
| "loss": 1.197, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_bleu": 37.7553, | |
| "eval_gen_len": 23.9353, | |
| "eval_loss": 1.7940903902053833, | |
| "eval_runtime": 1636.4218, | |
| "eval_samples_per_second": 1.841, | |
| "eval_steps_per_second": 0.461, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.873472146598825e-05, | |
| "loss": 1.1844, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_bleu": 38.3847, | |
| "eval_gen_len": 23.9668, | |
| "eval_loss": 1.7370097637176514, | |
| "eval_runtime": 1586.621, | |
| "eval_samples_per_second": 1.899, | |
| "eval_steps_per_second": 0.475, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.8578259264126975e-05, | |
| "loss": 1.2099, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_bleu": 38.4795, | |
| "eval_gen_len": 23.932, | |
| "eval_loss": 1.7586994171142578, | |
| "eval_runtime": 1530.6865, | |
| "eval_samples_per_second": 1.968, | |
| "eval_steps_per_second": 0.493, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.84217970622657e-05, | |
| "loss": 1.1798, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_bleu": 37.463, | |
| "eval_gen_len": 23.6664, | |
| "eval_loss": 1.752753496170044, | |
| "eval_runtime": 1408.4249, | |
| "eval_samples_per_second": 2.139, | |
| "eval_steps_per_second": 0.535, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.826533486040442e-05, | |
| "loss": 1.1959, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_bleu": 38.1287, | |
| "eval_gen_len": 23.7693, | |
| "eval_loss": 1.7170414924621582, | |
| "eval_runtime": 1482.0293, | |
| "eval_samples_per_second": 2.033, | |
| "eval_steps_per_second": 0.509, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.8108872658543146e-05, | |
| "loss": 1.2061, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_bleu": 38.8039, | |
| "eval_gen_len": 23.9973, | |
| "eval_loss": 1.731540322303772, | |
| "eval_runtime": 1484.0478, | |
| "eval_samples_per_second": 2.03, | |
| "eval_steps_per_second": 0.508, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.795241045668187e-05, | |
| "loss": 1.1606, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_bleu": 37.93, | |
| "eval_gen_len": 23.8347, | |
| "eval_loss": 1.7204748392105103, | |
| "eval_runtime": 1527.1349, | |
| "eval_samples_per_second": 1.973, | |
| "eval_steps_per_second": 0.494, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.77959482548206e-05, | |
| "loss": 1.1605, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_bleu": 38.2637, | |
| "eval_gen_len": 24.2688, | |
| "eval_loss": 1.7610867023468018, | |
| "eval_runtime": 1550.9436, | |
| "eval_samples_per_second": 1.943, | |
| "eval_steps_per_second": 0.486, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.7639486052959325e-05, | |
| "loss": 1.1792, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_bleu": 38.3329, | |
| "eval_gen_len": 24.088, | |
| "eval_loss": 1.728115200996399, | |
| "eval_runtime": 1598.5717, | |
| "eval_samples_per_second": 1.885, | |
| "eval_steps_per_second": 0.472, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.748302385109805e-05, | |
| "loss": 1.1613, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_bleu": 38.7357, | |
| "eval_gen_len": 24.1019, | |
| "eval_loss": 1.7274950742721558, | |
| "eval_runtime": 1552.6289, | |
| "eval_samples_per_second": 1.941, | |
| "eval_steps_per_second": 0.486, | |
| "step": 40000 | |
| } | |
| ], | |
| "max_steps": 159783, | |
| "num_train_epochs": 1, | |
| "total_flos": 6683673699483648.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |