| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 59688, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019832462136442838, | |
| "loss": 70.136, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019664924272885673, | |
| "loss": 54.3396, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 55.01993179321289, | |
| "eval_runtime": 0.5271, | |
| "eval_samples_per_second": 94.864, | |
| "eval_steps_per_second": 3.795, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019497386409328508, | |
| "loss": 52.5498, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019329848545771345, | |
| "loss": 51.633, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 53.25694274902344, | |
| "eval_runtime": 0.5629, | |
| "eval_samples_per_second": 88.83, | |
| "eval_steps_per_second": 3.553, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019162310682214182, | |
| "loss": 51.0517, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001899477281865702, | |
| "loss": 50.6422, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 52.43913269042969, | |
| "eval_runtime": 0.506, | |
| "eval_samples_per_second": 98.817, | |
| "eval_steps_per_second": 3.953, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018827234955099854, | |
| "loss": 50.2641, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001865969709154269, | |
| "loss": 50.023, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 52.02763748168945, | |
| "eval_runtime": 0.5162, | |
| "eval_samples_per_second": 96.869, | |
| "eval_steps_per_second": 3.875, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00018492159227985526, | |
| "loss": 49.8153, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00018324621364428363, | |
| "loss": 49.7182, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 51.66868209838867, | |
| "eval_runtime": 0.4836, | |
| "eval_samples_per_second": 103.392, | |
| "eval_steps_per_second": 4.136, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00018157083500871198, | |
| "loss": 49.5574, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00017989545637314033, | |
| "loss": 49.4063, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 51.36139678955078, | |
| "eval_runtime": 0.487, | |
| "eval_samples_per_second": 102.67, | |
| "eval_steps_per_second": 4.107, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001782200777375687, | |
| "loss": 49.3062, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00017654469910199707, | |
| "loss": 49.2278, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 51.16618347167969, | |
| "eval_runtime": 0.4852, | |
| "eval_samples_per_second": 103.045, | |
| "eval_steps_per_second": 4.122, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00017486932046642542, | |
| "loss": 49.1404, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001731939418308538, | |
| "loss": 49.0291, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 50.956336975097656, | |
| "eval_runtime": 0.4843, | |
| "eval_samples_per_second": 103.238, | |
| "eval_steps_per_second": 4.13, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00017151856319528214, | |
| "loss": 48.966, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0001698431845597105, | |
| "loss": 48.8771, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 50.9631233215332, | |
| "eval_runtime": 0.4832, | |
| "eval_samples_per_second": 103.477, | |
| "eval_steps_per_second": 4.139, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00016816780592413886, | |
| "loss": 48.842, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00016649242728856723, | |
| "loss": 48.8414, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 50.825313568115234, | |
| "eval_runtime": 0.484, | |
| "eval_samples_per_second": 103.302, | |
| "eval_steps_per_second": 4.132, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00016481704865299558, | |
| "loss": 48.7524, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00016314167001742395, | |
| "loss": 48.6891, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 50.6945686340332, | |
| "eval_runtime": 0.4902, | |
| "eval_samples_per_second": 101.994, | |
| "eval_steps_per_second": 4.08, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0001614662913818523, | |
| "loss": 48.6808, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00015979091274628067, | |
| "loss": 48.6235, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 50.51723098754883, | |
| "eval_runtime": 0.4899, | |
| "eval_samples_per_second": 102.054, | |
| "eval_steps_per_second": 4.082, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00015811553411070902, | |
| "loss": 48.5341, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0001564401554751374, | |
| "loss": 48.5, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 50.48223114013672, | |
| "eval_runtime": 0.4899, | |
| "eval_samples_per_second": 102.056, | |
| "eval_steps_per_second": 4.082, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00015476477683956574, | |
| "loss": 48.4708, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0001530893982039941, | |
| "loss": 48.4386, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 50.327213287353516, | |
| "eval_runtime": 0.4814, | |
| "eval_samples_per_second": 103.863, | |
| "eval_steps_per_second": 4.155, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00015141401956842248, | |
| "loss": 48.4488, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00014973864093285083, | |
| "loss": 48.3875, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 50.33498001098633, | |
| "eval_runtime": 0.5229, | |
| "eval_samples_per_second": 95.612, | |
| "eval_steps_per_second": 3.824, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00014806326229727917, | |
| "loss": 48.3842, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00014638788366170755, | |
| "loss": 48.3353, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 50.22550964355469, | |
| "eval_runtime": 0.5249, | |
| "eval_samples_per_second": 95.248, | |
| "eval_steps_per_second": 3.81, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00014471250502613592, | |
| "loss": 48.3718, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00014303712639056427, | |
| "loss": 48.3404, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 50.19435501098633, | |
| "eval_runtime": 0.5549, | |
| "eval_samples_per_second": 90.105, | |
| "eval_steps_per_second": 3.604, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00014136174775499264, | |
| "loss": 48.2976, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.000139686369119421, | |
| "loss": 48.2946, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 50.1772346496582, | |
| "eval_runtime": 0.6058, | |
| "eval_samples_per_second": 82.531, | |
| "eval_steps_per_second": 3.301, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00013801099048384936, | |
| "loss": 48.2515, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00013633561184827773, | |
| "loss": 48.2941, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 50.101707458496094, | |
| "eval_runtime": 0.55, | |
| "eval_samples_per_second": 90.916, | |
| "eval_steps_per_second": 3.637, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00013466023321270608, | |
| "loss": 48.1908, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00013298485457713443, | |
| "loss": 48.1547, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 50.0978889465332, | |
| "eval_runtime": 0.4898, | |
| "eval_samples_per_second": 102.081, | |
| "eval_steps_per_second": 4.083, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001313094759415628, | |
| "loss": 47.9981, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00012963409730599117, | |
| "loss": 48.0147, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 50.161685943603516, | |
| "eval_runtime": 0.4871, | |
| "eval_samples_per_second": 102.644, | |
| "eval_steps_per_second": 4.106, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00012795871867041952, | |
| "loss": 47.9851, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00012628334003484786, | |
| "loss": 47.936, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 50.107810974121094, | |
| "eval_runtime": 0.4846, | |
| "eval_samples_per_second": 103.186, | |
| "eval_steps_per_second": 4.127, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00012460796139927624, | |
| "loss": 48.0228, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0001229325827637046, | |
| "loss": 47.9642, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 50.060237884521484, | |
| "eval_runtime": 0.4856, | |
| "eval_samples_per_second": 102.961, | |
| "eval_steps_per_second": 4.118, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00012125720412813297, | |
| "loss": 47.9917, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00011958182549256132, | |
| "loss": 47.9531, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 50.01976013183594, | |
| "eval_runtime": 0.483, | |
| "eval_samples_per_second": 103.524, | |
| "eval_steps_per_second": 4.141, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00011790644685698968, | |
| "loss": 47.9594, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00011623106822141805, | |
| "loss": 47.9126, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 50.01350021362305, | |
| "eval_runtime": 0.4811, | |
| "eval_samples_per_second": 103.929, | |
| "eval_steps_per_second": 4.157, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00011455568958584641, | |
| "loss": 47.9141, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00011288031095027476, | |
| "loss": 47.9471, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 49.97874450683594, | |
| "eval_runtime": 0.5117, | |
| "eval_samples_per_second": 97.707, | |
| "eval_steps_per_second": 3.908, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00011120493231470313, | |
| "loss": 47.9071, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00010952955367913149, | |
| "loss": 47.9708, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 49.936649322509766, | |
| "eval_runtime": 0.4804, | |
| "eval_samples_per_second": 104.085, | |
| "eval_steps_per_second": 4.163, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00010785417504355986, | |
| "loss": 47.9294, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00010617879640798821, | |
| "loss": 47.8889, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 49.88063049316406, | |
| "eval_runtime": 0.5134, | |
| "eval_samples_per_second": 97.396, | |
| "eval_steps_per_second": 3.896, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00010450341777241657, | |
| "loss": 47.9306, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00010282803913684493, | |
| "loss": 47.909, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 49.8420524597168, | |
| "eval_runtime": 0.556, | |
| "eval_samples_per_second": 89.932, | |
| "eval_steps_per_second": 3.597, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0001011526605012733, | |
| "loss": 47.9044, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 9.947728186570166e-05, | |
| "loss": 47.8723, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 49.780277252197266, | |
| "eval_runtime": 0.4985, | |
| "eval_samples_per_second": 100.306, | |
| "eval_steps_per_second": 4.012, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.780190323013e-05, | |
| "loss": 47.8765, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.612652459455838e-05, | |
| "loss": 47.865, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 49.72420883178711, | |
| "eval_runtime": 0.5031, | |
| "eval_samples_per_second": 99.377, | |
| "eval_steps_per_second": 3.975, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.445114595898673e-05, | |
| "loss": 47.8886, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.27757673234151e-05, | |
| "loss": 47.8624, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 49.74140548706055, | |
| "eval_runtime": 0.5052, | |
| "eval_samples_per_second": 98.962, | |
| "eval_steps_per_second": 3.958, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.110038868784345e-05, | |
| "loss": 47.8765, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.942501005227182e-05, | |
| "loss": 47.8475, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 49.755550384521484, | |
| "eval_runtime": 0.5482, | |
| "eval_samples_per_second": 91.209, | |
| "eval_steps_per_second": 3.648, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8.774963141670018e-05, | |
| "loss": 47.8899, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 8.607425278112854e-05, | |
| "loss": 47.8309, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 49.78474044799805, | |
| "eval_runtime": 0.511, | |
| "eval_samples_per_second": 97.843, | |
| "eval_steps_per_second": 3.914, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 8.439887414555691e-05, | |
| "loss": 47.8192, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 8.272349550998526e-05, | |
| "loss": 47.8468, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 49.781124114990234, | |
| "eval_runtime": 0.5263, | |
| "eval_samples_per_second": 95.0, | |
| "eval_steps_per_second": 3.8, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.104811687441363e-05, | |
| "loss": 47.7881, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 7.937273823884198e-05, | |
| "loss": 47.85, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 49.724666595458984, | |
| "eval_runtime": 0.5014, | |
| "eval_samples_per_second": 99.722, | |
| "eval_steps_per_second": 3.989, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.769735960327035e-05, | |
| "loss": 47.7805, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 7.60219809676987e-05, | |
| "loss": 47.7769, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 49.74330139160156, | |
| "eval_runtime": 0.5536, | |
| "eval_samples_per_second": 90.316, | |
| "eval_steps_per_second": 3.613, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 7.434660233212707e-05, | |
| "loss": 47.8081, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 7.267122369655543e-05, | |
| "loss": 47.8395, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 49.658382415771484, | |
| "eval_runtime": 0.5279, | |
| "eval_samples_per_second": 94.711, | |
| "eval_steps_per_second": 3.788, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.099584506098379e-05, | |
| "loss": 47.8198, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 6.932046642541215e-05, | |
| "loss": 47.7978, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 49.645263671875, | |
| "eval_runtime": 0.4826, | |
| "eval_samples_per_second": 103.596, | |
| "eval_steps_per_second": 4.144, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 6.764508778984051e-05, | |
| "loss": 47.8224, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 6.596970915426887e-05, | |
| "loss": 47.7541, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 49.628944396972656, | |
| "eval_runtime": 0.484, | |
| "eval_samples_per_second": 103.305, | |
| "eval_steps_per_second": 4.132, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 6.429433051869723e-05, | |
| "loss": 47.6855, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 6.261895188312559e-05, | |
| "loss": 47.6644, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 49.626243591308594, | |
| "eval_runtime": 0.5063, | |
| "eval_samples_per_second": 98.747, | |
| "eval_steps_per_second": 3.95, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 6.0943573247553954e-05, | |
| "loss": 47.6146, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 5.926819461198231e-05, | |
| "loss": 47.6472, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 49.61125183105469, | |
| "eval_runtime": 0.483, | |
| "eval_samples_per_second": 103.514, | |
| "eval_steps_per_second": 4.141, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 5.7592815976410674e-05, | |
| "loss": 47.6434, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 5.5917437340839026e-05, | |
| "loss": 47.6436, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 49.59366226196289, | |
| "eval_runtime": 0.4865, | |
| "eval_samples_per_second": 102.777, | |
| "eval_steps_per_second": 4.111, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 5.424205870526739e-05, | |
| "loss": 47.6443, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 5.256668006969575e-05, | |
| "loss": 47.6082, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 49.62874984741211, | |
| "eval_runtime": 0.4801, | |
| "eval_samples_per_second": 104.141, | |
| "eval_steps_per_second": 4.166, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 5.089130143412412e-05, | |
| "loss": 47.6407, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 4.921592279855248e-05, | |
| "loss": 47.63, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 49.61036682128906, | |
| "eval_runtime": 0.4794, | |
| "eval_samples_per_second": 104.297, | |
| "eval_steps_per_second": 4.172, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 4.754054416298084e-05, | |
| "loss": 47.6592, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 4.58651655274092e-05, | |
| "loss": 47.6281, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 49.57414245605469, | |
| "eval_runtime": 0.4781, | |
| "eval_samples_per_second": 104.584, | |
| "eval_steps_per_second": 4.183, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.418978689183756e-05, | |
| "loss": 47.6234, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 4.251440825626592e-05, | |
| "loss": 47.661, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 49.538631439208984, | |
| "eval_runtime": 0.4811, | |
| "eval_samples_per_second": 103.938, | |
| "eval_steps_per_second": 4.158, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 4.083902962069428e-05, | |
| "loss": 47.6321, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 3.9163650985122644e-05, | |
| "loss": 47.5848, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 49.5694580078125, | |
| "eval_runtime": 0.4826, | |
| "eval_samples_per_second": 103.601, | |
| "eval_steps_per_second": 4.144, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 3.7488272349551004e-05, | |
| "loss": 47.6428, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 3.581289371397936e-05, | |
| "loss": 47.6209, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 49.554813385009766, | |
| "eval_runtime": 0.4889, | |
| "eval_samples_per_second": 102.277, | |
| "eval_steps_per_second": 4.091, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 3.413751507840772e-05, | |
| "loss": 47.6301, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 3.246213644283608e-05, | |
| "loss": 47.637, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_loss": 49.56814956665039, | |
| "eval_runtime": 0.483, | |
| "eval_samples_per_second": 103.514, | |
| "eval_steps_per_second": 4.141, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 3.078675780726444e-05, | |
| "loss": 47.6194, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.9111379171692806e-05, | |
| "loss": 47.6155, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 49.561641693115234, | |
| "eval_runtime": 0.4803, | |
| "eval_samples_per_second": 104.094, | |
| "eval_steps_per_second": 4.164, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2.7436000536121165e-05, | |
| "loss": 47.5766, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 2.5760621900549525e-05, | |
| "loss": 47.605, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_loss": 49.548133850097656, | |
| "eval_runtime": 0.4783, | |
| "eval_samples_per_second": 104.528, | |
| "eval_steps_per_second": 4.181, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 2.4085243264977885e-05, | |
| "loss": 47.5708, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 2.2409864629406248e-05, | |
| "loss": 47.6354, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_loss": 49.530643463134766, | |
| "eval_runtime": 0.4813, | |
| "eval_samples_per_second": 103.878, | |
| "eval_steps_per_second": 4.155, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.0734485993834608e-05, | |
| "loss": 47.5549, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 1.9059107358262967e-05, | |
| "loss": 47.6402, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_loss": 49.539710998535156, | |
| "eval_runtime": 0.4791, | |
| "eval_samples_per_second": 104.352, | |
| "eval_steps_per_second": 4.174, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.7383728722691327e-05, | |
| "loss": 47.5883, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.570835008711969e-05, | |
| "loss": 47.607, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 49.52818298339844, | |
| "eval_runtime": 0.5295, | |
| "eval_samples_per_second": 94.423, | |
| "eval_steps_per_second": 3.777, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.403297145154805e-05, | |
| "loss": 47.5659, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.2357592815976411e-05, | |
| "loss": 47.577, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_loss": 49.54225540161133, | |
| "eval_runtime": 0.478, | |
| "eval_samples_per_second": 104.606, | |
| "eval_steps_per_second": 4.184, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.0682214180404771e-05, | |
| "loss": 47.5713, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 9.006835544833132e-06, | |
| "loss": 47.5776, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 49.539093017578125, | |
| "eval_runtime": 0.5132, | |
| "eval_samples_per_second": 97.431, | |
| "eval_steps_per_second": 3.897, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.331456909261493e-06, | |
| "loss": 47.5852, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 5.656078273689854e-06, | |
| "loss": 47.6098, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_loss": 49.5291748046875, | |
| "eval_runtime": 0.5718, | |
| "eval_samples_per_second": 87.44, | |
| "eval_steps_per_second": 3.498, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 3.980699638118215e-06, | |
| "loss": 47.5699, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.3053210025465755e-06, | |
| "loss": 47.596, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_loss": 49.524417877197266, | |
| "eval_runtime": 0.5058, | |
| "eval_samples_per_second": 98.86, | |
| "eval_steps_per_second": 3.954, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 6.299423669749365e-07, | |
| "loss": 47.5627, | |
| "step": 59500 | |
| } | |
| ], | |
| "max_steps": 59688, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.0794540774520259e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |