| { | |
| "best_metric": 1.9631069898605347, | |
| "best_model_checkpoint": "/gpfs/space/home/sirts/EstRoBERTa/XLM-RoBERTa/output/checkpoint-20000", | |
| "epoch": 0.7784143477332575, | |
| "global_step": 700000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1e-09, | |
| "loss": 2.4605, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.93e-07, | |
| "loss": 3.0353, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 2.1905031204223633, | |
| "eval_runtime": 1291.547, | |
| "eval_samples_per_second": 60.963, | |
| "eval_steps_per_second": 1.905, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9930000000000002e-06, | |
| "loss": 2.693, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 2.1410903930664062, | |
| "eval_runtime": 1316.0761, | |
| "eval_samples_per_second": 59.827, | |
| "eval_steps_per_second": 1.87, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.9920000000000003e-06, | |
| "loss": 2.609, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 2.112772226333618, | |
| "eval_runtime": 1272.1468, | |
| "eval_samples_per_second": 61.893, | |
| "eval_steps_per_second": 1.935, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.992e-06, | |
| "loss": 2.5452, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 2.0833613872528076, | |
| "eval_runtime": 1295.6928, | |
| "eval_samples_per_second": 60.768, | |
| "eval_steps_per_second": 1.899, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.992e-06, | |
| "loss": 2.5094, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.071711778640747, | |
| "eval_runtime": 1246.6676, | |
| "eval_samples_per_second": 63.158, | |
| "eval_steps_per_second": 1.974, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9918305882352945e-06, | |
| "loss": 2.4723, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.058234691619873, | |
| "eval_runtime": 1244.8428, | |
| "eval_samples_per_second": 63.251, | |
| "eval_steps_per_second": 1.977, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.983595294117648e-06, | |
| "loss": 2.4497, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.049036741256714, | |
| "eval_runtime": 1246.1771, | |
| "eval_samples_per_second": 63.183, | |
| "eval_steps_per_second": 1.975, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.97536e-06, | |
| "loss": 2.4303, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.0401854515075684, | |
| "eval_runtime": 1272.8059, | |
| "eval_samples_per_second": 61.861, | |
| "eval_steps_per_second": 1.934, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.967124705882354e-06, | |
| "loss": 2.4146, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.030539035797119, | |
| "eval_runtime": 1305.6435, | |
| "eval_samples_per_second": 60.305, | |
| "eval_steps_per_second": 1.885, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.958889411764706e-06, | |
| "loss": 2.3796, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.0135810375213623, | |
| "eval_runtime": 1294.4476, | |
| "eval_samples_per_second": 60.827, | |
| "eval_steps_per_second": 1.901, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.950654117647059e-06, | |
| "loss": 2.3635, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.0098395347595215, | |
| "eval_runtime": 1304.5932, | |
| "eval_samples_per_second": 60.354, | |
| "eval_steps_per_second": 1.886, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9424270588235295e-06, | |
| "loss": 2.3659, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.0018415451049805, | |
| "eval_runtime": 1309.723, | |
| "eval_samples_per_second": 60.117, | |
| "eval_steps_per_second": 1.879, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.934191764705883e-06, | |
| "loss": 2.3621, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 1.9982237815856934, | |
| "eval_runtime": 1297.8423, | |
| "eval_samples_per_second": 60.668, | |
| "eval_steps_per_second": 1.896, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.925956470588235e-06, | |
| "loss": 2.3457, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.9903459548950195, | |
| "eval_runtime": 1245.2796, | |
| "eval_samples_per_second": 63.228, | |
| "eval_steps_per_second": 1.976, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.917721176470589e-06, | |
| "loss": 2.32, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.9873878955841064, | |
| "eval_runtime": 1279.3162, | |
| "eval_samples_per_second": 61.546, | |
| "eval_steps_per_second": 1.924, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.909502352941177e-06, | |
| "loss": 2.3196, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.9738166332244873, | |
| "eval_runtime": 1324.3821, | |
| "eval_samples_per_second": 59.452, | |
| "eval_steps_per_second": 1.858, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.901275294117647e-06, | |
| "loss": 2.307, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.9697579145431519, | |
| "eval_runtime": 1331.6669, | |
| "eval_samples_per_second": 59.127, | |
| "eval_steps_per_second": 1.848, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.893040000000001e-06, | |
| "loss": 2.3063, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.9780616760253906, | |
| "eval_runtime": 1379.3292, | |
| "eval_samples_per_second": 57.084, | |
| "eval_steps_per_second": 1.784, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.884804705882353e-06, | |
| "loss": 2.2927, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.9647581577301025, | |
| "eval_runtime": 1273.2021, | |
| "eval_samples_per_second": 61.842, | |
| "eval_steps_per_second": 1.933, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.8765694117647066e-06, | |
| "loss": 2.2862, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.9631069898605347, | |
| "eval_runtime": 1305.0876, | |
| "eval_samples_per_second": 60.331, | |
| "eval_steps_per_second": 1.886, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.868334117647059e-06, | |
| "loss": 2.2755, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.9493948221206665, | |
| "eval_runtime": 1273.9786, | |
| "eval_samples_per_second": 61.804, | |
| "eval_steps_per_second": 1.932, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.86010705882353e-06, | |
| "loss": 2.271, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.951810598373413, | |
| "eval_runtime": 1303.7209, | |
| "eval_samples_per_second": 60.394, | |
| "eval_steps_per_second": 1.888, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.85188e-06, | |
| "loss": 2.2652, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.9497112035751343, | |
| "eval_runtime": 1301.1007, | |
| "eval_samples_per_second": 60.516, | |
| "eval_steps_per_second": 1.891, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.843644705882353e-06, | |
| "loss": 2.2598, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.940477967262268, | |
| "eval_runtime": 1324.2392, | |
| "eval_samples_per_second": 59.458, | |
| "eval_steps_per_second": 1.858, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.835409411764706e-06, | |
| "loss": 2.2463, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.9413543939590454, | |
| "eval_runtime": 1243.8574, | |
| "eval_samples_per_second": 63.301, | |
| "eval_steps_per_second": 1.979, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.827174117647059e-06, | |
| "loss": 2.2484, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.9489567279815674, | |
| "eval_runtime": 1267.5954, | |
| "eval_samples_per_second": 62.115, | |
| "eval_steps_per_second": 1.941, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.8189470588235294e-06, | |
| "loss": 2.2345, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.9309957027435303, | |
| "eval_runtime": 1305.12, | |
| "eval_samples_per_second": 60.329, | |
| "eval_steps_per_second": 1.886, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.81072e-06, | |
| "loss": 2.2502, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.935508370399475, | |
| "eval_runtime": 1269.8199, | |
| "eval_samples_per_second": 62.006, | |
| "eval_steps_per_second": 1.938, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.8024847058823534e-06, | |
| "loss": 2.2279, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.9275970458984375, | |
| "eval_runtime": 1298.8069, | |
| "eval_samples_per_second": 60.623, | |
| "eval_steps_per_second": 1.895, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.794249411764706e-06, | |
| "loss": 2.2275, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.9117810726165771, | |
| "eval_runtime": 1334.2691, | |
| "eval_samples_per_second": 59.011, | |
| "eval_steps_per_second": 1.844, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.786014117647059e-06, | |
| "loss": 2.2233, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.9150503873825073, | |
| "eval_runtime": 1324.9615, | |
| "eval_samples_per_second": 59.426, | |
| "eval_steps_per_second": 1.857, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.777778823529412e-06, | |
| "loss": 2.2199, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.9108450412750244, | |
| "eval_runtime": 1324.574, | |
| "eval_samples_per_second": 59.443, | |
| "eval_steps_per_second": 1.858, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.769543529411765e-06, | |
| "loss": 2.2113, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.9146023988723755, | |
| "eval_runtime": 1239.9621, | |
| "eval_samples_per_second": 63.5, | |
| "eval_steps_per_second": 1.985, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.761308235294118e-06, | |
| "loss": 2.2216, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.9067528247833252, | |
| "eval_runtime": 1283.5053, | |
| "eval_samples_per_second": 61.345, | |
| "eval_steps_per_second": 1.917, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.753072941176471e-06, | |
| "loss": 2.2054, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.92031729221344, | |
| "eval_runtime": 1316.0539, | |
| "eval_samples_per_second": 59.828, | |
| "eval_steps_per_second": 1.87, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.744845882352942e-06, | |
| "loss": 2.2046, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.9086993932724, | |
| "eval_runtime": 1326.5645, | |
| "eval_samples_per_second": 59.354, | |
| "eval_steps_per_second": 1.855, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.736610588235294e-06, | |
| "loss": 2.2004, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.8981074094772339, | |
| "eval_runtime": 1240.1179, | |
| "eval_samples_per_second": 63.492, | |
| "eval_steps_per_second": 1.984, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.728383529411765e-06, | |
| "loss": 2.1925, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.8917450904846191, | |
| "eval_runtime": 1289.2602, | |
| "eval_samples_per_second": 61.071, | |
| "eval_steps_per_second": 1.909, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.720148235294118e-06, | |
| "loss": 2.1815, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.8893914222717285, | |
| "eval_runtime": 1347.7408, | |
| "eval_samples_per_second": 58.421, | |
| "eval_steps_per_second": 1.826, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.711912941176471e-06, | |
| "loss": 2.1826, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.8931858539581299, | |
| "eval_runtime": 1295.4191, | |
| "eval_samples_per_second": 60.781, | |
| "eval_steps_per_second": 1.9, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.7036858823529415e-06, | |
| "loss": 2.1763, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.8918838500976562, | |
| "eval_runtime": 1343.6015, | |
| "eval_samples_per_second": 58.601, | |
| "eval_steps_per_second": 1.832, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.695450588235294e-06, | |
| "loss": 2.1732, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.8779336214065552, | |
| "eval_runtime": 1265.8686, | |
| "eval_samples_per_second": 62.2, | |
| "eval_steps_per_second": 1.944, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.687215294117647e-06, | |
| "loss": 2.175, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.8825352191925049, | |
| "eval_runtime": 1349.6143, | |
| "eval_samples_per_second": 58.34, | |
| "eval_steps_per_second": 1.823, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.67898e-06, | |
| "loss": 2.1715, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.8862870931625366, | |
| "eval_runtime": 1289.9064, | |
| "eval_samples_per_second": 61.041, | |
| "eval_steps_per_second": 1.908, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.670761176470589e-06, | |
| "loss": 2.1676, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.877558946609497, | |
| "eval_runtime": 1339.6904, | |
| "eval_samples_per_second": 58.773, | |
| "eval_steps_per_second": 1.837, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.662525882352941e-06, | |
| "loss": 2.162, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.8775289058685303, | |
| "eval_runtime": 1237.9112, | |
| "eval_samples_per_second": 63.605, | |
| "eval_steps_per_second": 1.988, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.6542905882352945e-06, | |
| "loss": 2.1655, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.882572889328003, | |
| "eval_runtime": 1257.7653, | |
| "eval_samples_per_second": 62.601, | |
| "eval_steps_per_second": 1.957, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.646063529411765e-06, | |
| "loss": 2.1515, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.8675343990325928, | |
| "eval_runtime": 1295.0697, | |
| "eval_samples_per_second": 60.797, | |
| "eval_steps_per_second": 1.9, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.637828235294118e-06, | |
| "loss": 2.1521, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.8788520097732544, | |
| "eval_runtime": 1368.5815, | |
| "eval_samples_per_second": 57.532, | |
| "eval_steps_per_second": 1.798, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.629592941176471e-06, | |
| "loss": 2.1553, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.878118634223938, | |
| "eval_runtime": 1257.5481, | |
| "eval_samples_per_second": 62.612, | |
| "eval_steps_per_second": 1.957, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.621357647058824e-06, | |
| "loss": 2.1468, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.8591060638427734, | |
| "eval_runtime": 1301.9687, | |
| "eval_samples_per_second": 60.475, | |
| "eval_steps_per_second": 1.89, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.613138823529412e-06, | |
| "loss": 2.1498, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.8617653846740723, | |
| "eval_runtime": 1324.559, | |
| "eval_samples_per_second": 59.444, | |
| "eval_steps_per_second": 1.858, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.604903529411765e-06, | |
| "loss": 2.1424, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.8556735515594482, | |
| "eval_runtime": 1332.3018, | |
| "eval_samples_per_second": 59.098, | |
| "eval_steps_per_second": 1.847, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.596684705882353e-06, | |
| "loss": 2.1317, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.8501012325286865, | |
| "eval_runtime": 1335.1091, | |
| "eval_samples_per_second": 58.974, | |
| "eval_steps_per_second": 1.843, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.588449411764706e-06, | |
| "loss": 2.1481, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.8472974300384521, | |
| "eval_runtime": 1253.9865, | |
| "eval_samples_per_second": 62.789, | |
| "eval_steps_per_second": 1.963, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.580214117647059e-06, | |
| "loss": 2.138, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.8578077554702759, | |
| "eval_runtime": 1310.9382, | |
| "eval_samples_per_second": 60.062, | |
| "eval_steps_per_second": 1.877, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.571978823529412e-06, | |
| "loss": 2.1348, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.8515490293502808, | |
| "eval_runtime": 1273.8828, | |
| "eval_samples_per_second": 61.809, | |
| "eval_steps_per_second": 1.932, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.563743529411765e-06, | |
| "loss": 2.1254, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.851358413696289, | |
| "eval_runtime": 1272.3623, | |
| "eval_samples_per_second": 61.883, | |
| "eval_steps_per_second": 1.934, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.555508235294118e-06, | |
| "loss": 2.1193, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.8436750173568726, | |
| "eval_runtime": 1350.7689, | |
| "eval_samples_per_second": 58.291, | |
| "eval_steps_per_second": 1.822, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.547281176470589e-06, | |
| "loss": 2.1238, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.8456168174743652, | |
| "eval_runtime": 1276.1478, | |
| "eval_samples_per_second": 61.699, | |
| "eval_steps_per_second": 1.928, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.5390623529411765e-06, | |
| "loss": 2.1201, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.8359283208847046, | |
| "eval_runtime": 1296.4213, | |
| "eval_samples_per_second": 60.734, | |
| "eval_steps_per_second": 1.898, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.53082705882353e-06, | |
| "loss": 2.1216, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.8420335054397583, | |
| "eval_runtime": 1366.2934, | |
| "eval_samples_per_second": 57.628, | |
| "eval_steps_per_second": 1.801, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.522591764705882e-06, | |
| "loss": 2.1078, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.8367574214935303, | |
| "eval_runtime": 1274.6745, | |
| "eval_samples_per_second": 61.77, | |
| "eval_steps_per_second": 1.931, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.514356470588236e-06, | |
| "loss": 2.1124, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.831612467765808, | |
| "eval_runtime": 1350.1025, | |
| "eval_samples_per_second": 58.319, | |
| "eval_steps_per_second": 1.823, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.506121176470588e-06, | |
| "loss": 2.0956, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.8431429862976074, | |
| "eval_runtime": 1286.0027, | |
| "eval_samples_per_second": 61.226, | |
| "eval_steps_per_second": 1.914, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.497894117647059e-06, | |
| "loss": 2.1189, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.8319342136383057, | |
| "eval_runtime": 1368.0474, | |
| "eval_samples_per_second": 57.554, | |
| "eval_steps_per_second": 1.799, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.489658823529412e-06, | |
| "loss": 2.099, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.8349796533584595, | |
| "eval_runtime": 1270.3602, | |
| "eval_samples_per_second": 61.98, | |
| "eval_steps_per_second": 1.937, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.481423529411765e-06, | |
| "loss": 2.0924, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.835334062576294, | |
| "eval_runtime": 1307.6688, | |
| "eval_samples_per_second": 60.212, | |
| "eval_steps_per_second": 1.882, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.473188235294118e-06, | |
| "loss": 2.1088, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.8290066719055176, | |
| "eval_runtime": 1334.2905, | |
| "eval_samples_per_second": 59.01, | |
| "eval_steps_per_second": 1.844, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.464952941176472e-06, | |
| "loss": 2.1005, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.827639102935791, | |
| "eval_runtime": 1340.3121, | |
| "eval_samples_per_second": 58.745, | |
| "eval_steps_per_second": 1.836, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.456725882352942e-06, | |
| "loss": 2.0974, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.82291841506958, | |
| "eval_runtime": 1333.5213, | |
| "eval_samples_per_second": 59.044, | |
| "eval_steps_per_second": 1.845, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.448490588235294e-06, | |
| "loss": 2.0993, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.8226332664489746, | |
| "eval_runtime": 1277.2243, | |
| "eval_samples_per_second": 61.647, | |
| "eval_steps_per_second": 1.927, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.440255294117647e-06, | |
| "loss": 2.0923, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.826454520225525, | |
| "eval_runtime": 1282.1547, | |
| "eval_samples_per_second": 61.41, | |
| "eval_steps_per_second": 1.919, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.43202e-06, | |
| "loss": 2.0866, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.81631338596344, | |
| "eval_runtime": 1302.8545, | |
| "eval_samples_per_second": 60.434, | |
| "eval_steps_per_second": 1.889, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.4238011764705886e-06, | |
| "loss": 2.0837, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.8213496208190918, | |
| "eval_runtime": 1316.2489, | |
| "eval_samples_per_second": 59.819, | |
| "eval_steps_per_second": 1.87, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.415565882352941e-06, | |
| "loss": 2.0865, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.8240435123443604, | |
| "eval_runtime": 1333.9994, | |
| "eval_samples_per_second": 59.023, | |
| "eval_steps_per_second": 1.845, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.407338823529412e-06, | |
| "loss": 2.0923, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.809515357017517, | |
| "eval_runtime": 1362.5256, | |
| "eval_samples_per_second": 57.788, | |
| "eval_steps_per_second": 1.806, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.399103529411765e-06, | |
| "loss": 2.0789, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.8183976411819458, | |
| "eval_runtime": 1274.3396, | |
| "eval_samples_per_second": 61.787, | |
| "eval_steps_per_second": 1.931, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.390868235294118e-06, | |
| "loss": 2.0855, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.810996413230896, | |
| "eval_runtime": 1322.4479, | |
| "eval_samples_per_second": 59.539, | |
| "eval_steps_per_second": 1.861, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.382641176470588e-06, | |
| "loss": 2.0832, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.8153365850448608, | |
| "eval_runtime": 1343.5102, | |
| "eval_samples_per_second": 58.605, | |
| "eval_steps_per_second": 1.832, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.374405882352942e-06, | |
| "loss": 2.0825, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.808205485343933, | |
| "eval_runtime": 1313.381, | |
| "eval_samples_per_second": 59.95, | |
| "eval_steps_per_second": 1.874, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.366170588235295e-06, | |
| "loss": 2.0752, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.8093898296356201, | |
| "eval_runtime": 1349.7533, | |
| "eval_samples_per_second": 58.334, | |
| "eval_steps_per_second": 1.823, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.3579352941176475e-06, | |
| "loss": 2.0784, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.8149974346160889, | |
| "eval_runtime": 1295.5666, | |
| "eval_samples_per_second": 60.774, | |
| "eval_steps_per_second": 1.9, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.349700000000001e-06, | |
| "loss": 2.0732, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.8028277158737183, | |
| "eval_runtime": 1304.8774, | |
| "eval_samples_per_second": 60.341, | |
| "eval_steps_per_second": 1.886, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.341481176470588e-06, | |
| "loss": 2.0766, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.803389549255371, | |
| "eval_runtime": 1325.2979, | |
| "eval_samples_per_second": 59.411, | |
| "eval_steps_per_second": 1.857, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.333245882352941e-06, | |
| "loss": 2.0655, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.8071125745773315, | |
| "eval_runtime": 1308.7884, | |
| "eval_samples_per_second": 60.16, | |
| "eval_steps_per_second": 1.88, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.325010588235294e-06, | |
| "loss": 2.0627, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.8011773824691772, | |
| "eval_runtime": 1298.6527, | |
| "eval_samples_per_second": 60.63, | |
| "eval_steps_per_second": 1.895, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.316775294117647e-06, | |
| "loss": 2.0689, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.80793297290802, | |
| "eval_runtime": 1375.2481, | |
| "eval_samples_per_second": 57.253, | |
| "eval_steps_per_second": 1.789, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.308548235294118e-06, | |
| "loss": 2.0594, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.7938480377197266, | |
| "eval_runtime": 1361.5038, | |
| "eval_samples_per_second": 57.831, | |
| "eval_steps_per_second": 1.808, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.30031294117647e-06, | |
| "loss": 2.069, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.7888888120651245, | |
| "eval_runtime": 1395.2585, | |
| "eval_samples_per_second": 56.432, | |
| "eval_steps_per_second": 1.764, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.292085882352941e-06, | |
| "loss": 2.0629, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.7948452234268188, | |
| "eval_runtime": 1306.9601, | |
| "eval_samples_per_second": 60.244, | |
| "eval_steps_per_second": 1.883, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.283850588235294e-06, | |
| "loss": 2.0659, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.7888908386230469, | |
| "eval_runtime": 1295.0247, | |
| "eval_samples_per_second": 60.8, | |
| "eval_steps_per_second": 1.9, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.275623529411765e-06, | |
| "loss": 2.0499, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.7932168245315552, | |
| "eval_runtime": 1346.4053, | |
| "eval_samples_per_second": 58.479, | |
| "eval_steps_per_second": 1.828, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.267388235294118e-06, | |
| "loss": 2.0577, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.78506338596344, | |
| "eval_runtime": 1367.5039, | |
| "eval_samples_per_second": 57.577, | |
| "eval_steps_per_second": 1.8, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.259152941176471e-06, | |
| "loss": 2.0567, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.7812087535858154, | |
| "eval_runtime": 1317.2032, | |
| "eval_samples_per_second": 59.776, | |
| "eval_steps_per_second": 1.868, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.250917647058824e-06, | |
| "loss": 2.066, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.7878668308258057, | |
| "eval_runtime": 1334.3015, | |
| "eval_samples_per_second": 59.01, | |
| "eval_steps_per_second": 1.844, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.242682352941177e-06, | |
| "loss": 2.0503, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.7862142324447632, | |
| "eval_runtime": 1360.5455, | |
| "eval_samples_per_second": 57.872, | |
| "eval_steps_per_second": 1.809, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.2344552941176475e-06, | |
| "loss": 2.0524, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.7882963418960571, | |
| "eval_runtime": 1312.4549, | |
| "eval_samples_per_second": 59.992, | |
| "eval_steps_per_second": 1.875, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.226220000000001e-06, | |
| "loss": 2.0484, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.7941440343856812, | |
| "eval_runtime": 1330.4245, | |
| "eval_samples_per_second": 59.182, | |
| "eval_steps_per_second": 1.85, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.2179929411764715e-06, | |
| "loss": 2.0468, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.7767722606658936, | |
| "eval_runtime": 1352.4496, | |
| "eval_samples_per_second": 58.218, | |
| "eval_steps_per_second": 1.82, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.209765882352942e-06, | |
| "loss": 2.048, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.777193546295166, | |
| "eval_runtime": 1392.9228, | |
| "eval_samples_per_second": 56.526, | |
| "eval_steps_per_second": 1.767, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.201530588235295e-06, | |
| "loss": 2.0421, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.7795777320861816, | |
| "eval_runtime": 1353.8569, | |
| "eval_samples_per_second": 58.158, | |
| "eval_steps_per_second": 1.818, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.193295294117647e-06, | |
| "loss": 2.0394, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.7759983539581299, | |
| "eval_runtime": 1337.236, | |
| "eval_samples_per_second": 58.88, | |
| "eval_steps_per_second": 1.84, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.185076470588235e-06, | |
| "loss": 2.039, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.7742137908935547, | |
| "eval_runtime": 1341.9424, | |
| "eval_samples_per_second": 58.674, | |
| "eval_steps_per_second": 1.834, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.1768411764705885e-06, | |
| "loss": 2.0365, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.7747963666915894, | |
| "eval_runtime": 1380.5697, | |
| "eval_samples_per_second": 57.032, | |
| "eval_steps_per_second": 1.783, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.168605882352942e-06, | |
| "loss": 2.0326, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.7771369218826294, | |
| "eval_runtime": 1279.0938, | |
| "eval_samples_per_second": 61.557, | |
| "eval_steps_per_second": 1.924, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.160378823529412e-06, | |
| "loss": 2.0369, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.7755202054977417, | |
| "eval_runtime": 1277.1355, | |
| "eval_samples_per_second": 61.651, | |
| "eval_steps_per_second": 1.927, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.152143529411765e-06, | |
| "loss": 2.0404, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.782023549079895, | |
| "eval_runtime": 1332.026, | |
| "eval_samples_per_second": 59.111, | |
| "eval_steps_per_second": 1.848, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.143908235294118e-06, | |
| "loss": 2.0295, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.7722965478897095, | |
| "eval_runtime": 1302.5963, | |
| "eval_samples_per_second": 60.446, | |
| "eval_steps_per_second": 1.889, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.135672941176471e-06, | |
| "loss": 2.0329, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.772587776184082, | |
| "eval_runtime": 1317.5586, | |
| "eval_samples_per_second": 59.76, | |
| "eval_steps_per_second": 1.868, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.127437647058824e-06, | |
| "loss": 2.0249, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.764708161354065, | |
| "eval_runtime": 1344.7146, | |
| "eval_samples_per_second": 58.553, | |
| "eval_steps_per_second": 1.83, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.119210588235295e-06, | |
| "loss": 2.0372, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.7661118507385254, | |
| "eval_runtime": 1264.9153, | |
| "eval_samples_per_second": 62.247, | |
| "eval_steps_per_second": 1.946, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.1109752941176474e-06, | |
| "loss": 2.0287, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.7656384706497192, | |
| "eval_runtime": 1301.1054, | |
| "eval_samples_per_second": 60.515, | |
| "eval_steps_per_second": 1.891, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.102740000000001e-06, | |
| "loss": 2.0134, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.7664334774017334, | |
| "eval_runtime": 1345.5823, | |
| "eval_samples_per_second": 58.515, | |
| "eval_steps_per_second": 1.829, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.094504705882353e-06, | |
| "loss": 2.0164, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.763651967048645, | |
| "eval_runtime": 1262.0498, | |
| "eval_samples_per_second": 62.388, | |
| "eval_steps_per_second": 1.95, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.086277647058824e-06, | |
| "loss": 2.0248, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.7580262422561646, | |
| "eval_runtime": 1266.7103, | |
| "eval_samples_per_second": 62.159, | |
| "eval_steps_per_second": 1.943, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.0780423529411765e-06, | |
| "loss": 2.0172, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.7685062885284424, | |
| "eval_runtime": 1289.7069, | |
| "eval_samples_per_second": 61.05, | |
| "eval_steps_per_second": 1.908, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.06980705882353e-06, | |
| "loss": 2.019, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.7675044536590576, | |
| "eval_runtime": 1320.0327, | |
| "eval_samples_per_second": 59.648, | |
| "eval_steps_per_second": 1.864, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.061571764705882e-06, | |
| "loss": 2.0237, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.7597997188568115, | |
| "eval_runtime": 1298.1829, | |
| "eval_samples_per_second": 60.652, | |
| "eval_steps_per_second": 1.896, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.053352941176471e-06, | |
| "loss": 2.0096, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.7642709016799927, | |
| "eval_runtime": 1299.3688, | |
| "eval_samples_per_second": 60.596, | |
| "eval_steps_per_second": 1.894, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.045117647058824e-06, | |
| "loss": 2.0137, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.7602267265319824, | |
| "eval_runtime": 1297.1878, | |
| "eval_samples_per_second": 60.698, | |
| "eval_steps_per_second": 1.897, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.036882352941177e-06, | |
| "loss": 2.0142, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.7619584798812866, | |
| "eval_runtime": 1294.7741, | |
| "eval_samples_per_second": 60.811, | |
| "eval_steps_per_second": 1.901, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.028655294117648e-06, | |
| "loss": 2.0154, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.757212519645691, | |
| "eval_runtime": 1312.6161, | |
| "eval_samples_per_second": 59.985, | |
| "eval_steps_per_second": 1.875, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.02042e-06, | |
| "loss": 2.0131, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.7483080625534058, | |
| "eval_runtime": 1260.0115, | |
| "eval_samples_per_second": 62.489, | |
| "eval_steps_per_second": 1.953, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.012192941176471e-06, | |
| "loss": 2.0062, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.7526593208312988, | |
| "eval_runtime": 1267.5051, | |
| "eval_samples_per_second": 62.12, | |
| "eval_steps_per_second": 1.942, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.003957647058824e-06, | |
| "loss": 2.0056, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.7664062976837158, | |
| "eval_runtime": 1298.3162, | |
| "eval_samples_per_second": 60.645, | |
| "eval_steps_per_second": 1.896, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 3.995722352941177e-06, | |
| "loss": 2.0136, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.7430987358093262, | |
| "eval_runtime": 1363.753, | |
| "eval_samples_per_second": 57.736, | |
| "eval_steps_per_second": 1.805, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 3.98748705882353e-06, | |
| "loss": 2.0094, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.7556384801864624, | |
| "eval_runtime": 1283.1923, | |
| "eval_samples_per_second": 61.36, | |
| "eval_steps_per_second": 1.918, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 3.979251764705883e-06, | |
| "loss": 2.0018, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.7488545179367065, | |
| "eval_runtime": 1318.7895, | |
| "eval_samples_per_second": 59.704, | |
| "eval_steps_per_second": 1.866, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 3.971016470588236e-06, | |
| "loss": 2.012, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.7493007183074951, | |
| "eval_runtime": 1351.8311, | |
| "eval_samples_per_second": 58.245, | |
| "eval_steps_per_second": 1.82, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3.962789411764707e-06, | |
| "loss": 2.0038, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.7452046871185303, | |
| "eval_runtime": 1297.9368, | |
| "eval_samples_per_second": 60.663, | |
| "eval_steps_per_second": 1.896, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3.954554117647059e-06, | |
| "loss": 2.0036, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.743809700012207, | |
| "eval_runtime": 1345.0863, | |
| "eval_samples_per_second": 58.537, | |
| "eval_steps_per_second": 1.83, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3.94632705882353e-06, | |
| "loss": 2.0069, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.7406339645385742, | |
| "eval_runtime": 1336.5153, | |
| "eval_samples_per_second": 58.912, | |
| "eval_steps_per_second": 1.841, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3.938091764705882e-06, | |
| "loss": 2.0023, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.7494807243347168, | |
| "eval_runtime": 1324.0204, | |
| "eval_samples_per_second": 59.468, | |
| "eval_steps_per_second": 1.859, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3.929864705882353e-06, | |
| "loss": 2.0032, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.7454729080200195, | |
| "eval_runtime": 1272.2315, | |
| "eval_samples_per_second": 61.889, | |
| "eval_steps_per_second": 1.934, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3.921645882352942e-06, | |
| "loss": 1.9948, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.7327392101287842, | |
| "eval_runtime": 1260.2656, | |
| "eval_samples_per_second": 62.477, | |
| "eval_steps_per_second": 1.953, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3.913410588235294e-06, | |
| "loss": 2.0008, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.741957426071167, | |
| "eval_runtime": 1292.2259, | |
| "eval_samples_per_second": 60.931, | |
| "eval_steps_per_second": 1.904, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3.905175294117648e-06, | |
| "loss": 1.9927, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.7473654747009277, | |
| "eval_runtime": 1318.8071, | |
| "eval_samples_per_second": 59.703, | |
| "eval_steps_per_second": 1.866, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3.89694e-06, | |
| "loss": 1.987, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.7441741228103638, | |
| "eval_runtime": 1308.7801, | |
| "eval_samples_per_second": 60.161, | |
| "eval_steps_per_second": 1.88, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.8887047058823535e-06, | |
| "loss": 1.9987, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.7342219352722168, | |
| "eval_runtime": 1310.0491, | |
| "eval_samples_per_second": 60.102, | |
| "eval_steps_per_second": 1.879, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.880469411764706e-06, | |
| "loss": 1.9866, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.7366760969161987, | |
| "eval_runtime": 1338.3757, | |
| "eval_samples_per_second": 58.83, | |
| "eval_steps_per_second": 1.839, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.8722341176470594e-06, | |
| "loss": 1.9922, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.733156442642212, | |
| "eval_runtime": 1379.7672, | |
| "eval_samples_per_second": 57.065, | |
| "eval_steps_per_second": 1.784, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.86400705882353e-06, | |
| "loss": 1.9954, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.7350982427597046, | |
| "eval_runtime": 1276.6064, | |
| "eval_samples_per_second": 61.677, | |
| "eval_steps_per_second": 1.928, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.8557717647058834e-06, | |
| "loss": 1.9912, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.7301350831985474, | |
| "eval_runtime": 1290.7008, | |
| "eval_samples_per_second": 61.003, | |
| "eval_steps_per_second": 1.907, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.8475529411764705e-06, | |
| "loss": 1.9852, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.7331594228744507, | |
| "eval_runtime": 1303.6593, | |
| "eval_samples_per_second": 60.397, | |
| "eval_steps_per_second": 1.888, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.839317647058824e-06, | |
| "loss": 1.9878, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.7405369281768799, | |
| "eval_runtime": 1337.4986, | |
| "eval_samples_per_second": 58.869, | |
| "eval_steps_per_second": 1.84, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.831082352941176e-06, | |
| "loss": 1.9873, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.7377097606658936, | |
| "eval_runtime": 1338.3307, | |
| "eval_samples_per_second": 58.832, | |
| "eval_steps_per_second": 1.839, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.82284705882353e-06, | |
| "loss": 1.9896, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.733717441558838, | |
| "eval_runtime": 1270.765, | |
| "eval_samples_per_second": 61.96, | |
| "eval_steps_per_second": 1.937, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.8146117647058823e-06, | |
| "loss": 1.9998, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.7400872707366943, | |
| "eval_runtime": 1374.6506, | |
| "eval_samples_per_second": 57.278, | |
| "eval_steps_per_second": 1.79, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.806384705882353e-06, | |
| "loss": 1.9923, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.7128148078918457, | |
| "eval_runtime": 1269.3048, | |
| "eval_samples_per_second": 62.032, | |
| "eval_steps_per_second": 1.939, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.798149411764706e-06, | |
| "loss": 1.9877, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.7390938997268677, | |
| "eval_runtime": 1305.2056, | |
| "eval_samples_per_second": 60.325, | |
| "eval_steps_per_second": 1.886, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.7899223529411765e-06, | |
| "loss": 1.9802, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.7243410348892212, | |
| "eval_runtime": 1310.1732, | |
| "eval_samples_per_second": 60.097, | |
| "eval_steps_per_second": 1.878, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.7816870588235295e-06, | |
| "loss": 1.9828, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.7285162210464478, | |
| "eval_runtime": 1307.3997, | |
| "eval_samples_per_second": 60.224, | |
| "eval_steps_per_second": 1.882, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.7734599999999997e-06, | |
| "loss": 1.981, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.735887885093689, | |
| "eval_runtime": 1309.4529, | |
| "eval_samples_per_second": 60.13, | |
| "eval_steps_per_second": 1.879, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.765232941176471e-06, | |
| "loss": 1.9692, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.7372865676879883, | |
| "eval_runtime": 1335.6217, | |
| "eval_samples_per_second": 58.952, | |
| "eval_steps_per_second": 1.843, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.7569976470588237e-06, | |
| "loss": 1.9799, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.7367862462997437, | |
| "eval_runtime": 1363.2422, | |
| "eval_samples_per_second": 57.757, | |
| "eval_steps_per_second": 1.805, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.7487623529411767e-06, | |
| "loss": 1.9753, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.7180030345916748, | |
| "eval_runtime": 1369.9985, | |
| "eval_samples_per_second": 57.472, | |
| "eval_steps_per_second": 1.796, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.74052705882353e-06, | |
| "loss": 1.9783, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.728384256362915, | |
| "eval_runtime": 1283.0397, | |
| "eval_samples_per_second": 61.368, | |
| "eval_steps_per_second": 1.918, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.732291764705883e-06, | |
| "loss": 1.9754, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.7158981561660767, | |
| "eval_runtime": 1309.3703, | |
| "eval_samples_per_second": 60.133, | |
| "eval_steps_per_second": 1.88, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.724056470588236e-06, | |
| "loss": 1.9871, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.7252790927886963, | |
| "eval_runtime": 1292.6928, | |
| "eval_samples_per_second": 60.909, | |
| "eval_steps_per_second": 1.904, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.7158294117647066e-06, | |
| "loss": 1.9716, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.7210992574691772, | |
| "eval_runtime": 257.0246, | |
| "eval_samples_per_second": 306.34, | |
| "eval_steps_per_second": 9.575, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.707610588235295e-06, | |
| "loss": 1.9745, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.7264364957809448, | |
| "eval_runtime": 290.1187, | |
| "eval_samples_per_second": 271.396, | |
| "eval_steps_per_second": 8.483, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.699375294117648e-06, | |
| "loss": 1.9709, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.7170484066009521, | |
| "eval_runtime": 278.2177, | |
| "eval_samples_per_second": 283.005, | |
| "eval_steps_per_second": 8.846, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.6911482352941185e-06, | |
| "loss": 1.9783, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.720254898071289, | |
| "eval_runtime": 295.7088, | |
| "eval_samples_per_second": 266.265, | |
| "eval_steps_per_second": 8.322, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.6829129411764706e-06, | |
| "loss": 1.9717, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.723580002784729, | |
| "eval_runtime": 285.5463, | |
| "eval_samples_per_second": 275.742, | |
| "eval_steps_per_second": 8.619, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.6746776470588235e-06, | |
| "loss": 1.9621, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.7218551635742188, | |
| "eval_runtime": 289.3233, | |
| "eval_samples_per_second": 272.142, | |
| "eval_steps_per_second": 8.506, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.6664423529411765e-06, | |
| "loss": 1.9615, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.7153804302215576, | |
| "eval_runtime": 304.7383, | |
| "eval_samples_per_second": 258.376, | |
| "eval_steps_per_second": 8.076, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.65820705882353e-06, | |
| "loss": 1.9686, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.7157891988754272, | |
| "eval_runtime": 296.2947, | |
| "eval_samples_per_second": 265.739, | |
| "eval_steps_per_second": 8.306, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.64998e-06, | |
| "loss": 1.967, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.7255160808563232, | |
| "eval_runtime": 270.3222, | |
| "eval_samples_per_second": 291.271, | |
| "eval_steps_per_second": 9.104, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.6417447058823534e-06, | |
| "loss": 1.9701, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.718467116355896, | |
| "eval_runtime": 288.4423, | |
| "eval_samples_per_second": 272.973, | |
| "eval_steps_per_second": 8.532, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.6335094117647064e-06, | |
| "loss": 1.9541, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.7223858833312988, | |
| "eval_runtime": 301.9716, | |
| "eval_samples_per_second": 260.743, | |
| "eval_steps_per_second": 8.15, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.6252741176470598e-06, | |
| "loss": 1.9704, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.7094881534576416, | |
| "eval_runtime": 296.3843, | |
| "eval_samples_per_second": 265.658, | |
| "eval_steps_per_second": 8.303, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.617047058823529e-06, | |
| "loss": 1.9644, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.7200572490692139, | |
| "eval_runtime": 280.0116, | |
| "eval_samples_per_second": 281.192, | |
| "eval_steps_per_second": 8.789, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.6088117647058825e-06, | |
| "loss": 1.9701, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.7085354328155518, | |
| "eval_runtime": 270.4782, | |
| "eval_samples_per_second": 291.103, | |
| "eval_steps_per_second": 9.099, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.6005847058823527e-06, | |
| "loss": 1.963, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.6980141401290894, | |
| "eval_runtime": 262.3974, | |
| "eval_samples_per_second": 300.068, | |
| "eval_steps_per_second": 9.379, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.5923576470588234e-06, | |
| "loss": 1.9656, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.7150171995162964, | |
| "eval_runtime": 290.7308, | |
| "eval_samples_per_second": 270.824, | |
| "eval_steps_per_second": 8.465, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.5841223529411763e-06, | |
| "loss": 1.9572, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.718950867652893, | |
| "eval_runtime": 302.7947, | |
| "eval_samples_per_second": 260.034, | |
| "eval_steps_per_second": 8.128, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.5758952941176465e-06, | |
| "loss": 1.9579, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.7136762142181396, | |
| "eval_runtime": 293.5678, | |
| "eval_samples_per_second": 268.207, | |
| "eval_steps_per_second": 8.383, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.56766e-06, | |
| "loss": 1.9511, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.7204865217208862, | |
| "eval_runtime": 276.1567, | |
| "eval_samples_per_second": 285.117, | |
| "eval_steps_per_second": 8.912, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.559424705882353e-06, | |
| "loss": 1.9567, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.7064766883850098, | |
| "eval_runtime": 284.9959, | |
| "eval_samples_per_second": 276.274, | |
| "eval_steps_per_second": 8.635, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.5511976470588235e-06, | |
| "loss": 1.9517, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.7071802616119385, | |
| "eval_runtime": 302.7195, | |
| "eval_samples_per_second": 260.099, | |
| "eval_steps_per_second": 8.13, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.5429623529411764e-06, | |
| "loss": 1.9577, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.7056118249893188, | |
| "eval_runtime": 279.2944, | |
| "eval_samples_per_second": 281.914, | |
| "eval_steps_per_second": 8.811, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.534735294117647e-06, | |
| "loss": 1.9521, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.7090562582015991, | |
| "eval_runtime": 304.8754, | |
| "eval_samples_per_second": 258.26, | |
| "eval_steps_per_second": 8.072, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.5265000000000005e-06, | |
| "loss": 1.9541, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.7047358751296997, | |
| "eval_runtime": 287.5185, | |
| "eval_samples_per_second": 273.85, | |
| "eval_steps_per_second": 8.559, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.5182647058823534e-06, | |
| "loss": 1.9505, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.708825945854187, | |
| "eval_runtime": 282.3838, | |
| "eval_samples_per_second": 278.83, | |
| "eval_steps_per_second": 8.715, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.5100376470588236e-06, | |
| "loss": 1.9559, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.7142888307571411, | |
| "eval_runtime": 296.6697, | |
| "eval_samples_per_second": 265.403, | |
| "eval_steps_per_second": 8.295, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.501802352941177e-06, | |
| "loss": 1.9531, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.7113577127456665, | |
| "eval_runtime": 297.8189, | |
| "eval_samples_per_second": 264.379, | |
| "eval_steps_per_second": 8.263, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.4935752941176476e-06, | |
| "loss": 1.9627, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.7047557830810547, | |
| "eval_runtime": 303.2883, | |
| "eval_samples_per_second": 259.611, | |
| "eval_steps_per_second": 8.114, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.4853400000000006e-06, | |
| "loss": 1.9617, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.7064669132232666, | |
| "eval_runtime": 285.7888, | |
| "eval_samples_per_second": 275.508, | |
| "eval_steps_per_second": 8.611, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.4771047058823535e-06, | |
| "loss": 1.9468, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.6990549564361572, | |
| "eval_runtime": 283.1785, | |
| "eval_samples_per_second": 278.047, | |
| "eval_steps_per_second": 8.691, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.4688694117647065e-06, | |
| "loss": 1.9475, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.7063584327697754, | |
| "eval_runtime": 314.7643, | |
| "eval_samples_per_second": 250.146, | |
| "eval_steps_per_second": 7.819, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.4606341176470594e-06, | |
| "loss": 1.9569, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.7076828479766846, | |
| "eval_runtime": 303.2807, | |
| "eval_samples_per_second": 259.618, | |
| "eval_steps_per_second": 8.115, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.4523988235294128e-06, | |
| "loss": 1.9624, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.706101894378662, | |
| "eval_runtime": 292.0709, | |
| "eval_samples_per_second": 269.582, | |
| "eval_steps_per_second": 8.426, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.444171764705883e-06, | |
| "loss": 1.9575, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.704559326171875, | |
| "eval_runtime": 295.1202, | |
| "eval_samples_per_second": 266.796, | |
| "eval_steps_per_second": 8.339, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.4359447058823537e-06, | |
| "loss": 1.9522, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.6992961168289185, | |
| "eval_runtime": 297.5252, | |
| "eval_samples_per_second": 264.64, | |
| "eval_steps_per_second": 8.272, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.4277094117647066e-06, | |
| "loss": 1.9451, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.708154320716858, | |
| "eval_runtime": 296.8626, | |
| "eval_samples_per_second": 265.23, | |
| "eval_steps_per_second": 8.29, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.419474117647059e-06, | |
| "loss": 1.9398, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.694187879562378, | |
| "eval_runtime": 285.2559, | |
| "eval_samples_per_second": 276.022, | |
| "eval_steps_per_second": 8.627, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.411238823529412e-06, | |
| "loss": 1.9487, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.697739839553833, | |
| "eval_runtime": 271.0859, | |
| "eval_samples_per_second": 290.45, | |
| "eval_steps_per_second": 9.078, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.4030117647058823e-06, | |
| "loss": 1.9505, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.6950899362564087, | |
| "eval_runtime": 296.9518, | |
| "eval_samples_per_second": 265.151, | |
| "eval_steps_per_second": 8.288, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.3947847058823534e-06, | |
| "loss": 1.9444, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.6965278387069702, | |
| "eval_runtime": 298.5122, | |
| "eval_samples_per_second": 263.765, | |
| "eval_steps_per_second": 8.244, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.3865494117647063e-06, | |
| "loss": 1.9542, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.6953821182250977, | |
| "eval_runtime": 855.4125, | |
| "eval_samples_per_second": 92.046, | |
| "eval_steps_per_second": 2.877, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.3783141176470592e-06, | |
| "loss": 1.9352, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.6955593824386597, | |
| "eval_runtime": 825.3854, | |
| "eval_samples_per_second": 95.394, | |
| "eval_steps_per_second": 2.982, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.370078823529412e-06, | |
| "loss": 1.9335, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.6933975219726562, | |
| "eval_runtime": 832.1739, | |
| "eval_samples_per_second": 94.616, | |
| "eval_steps_per_second": 2.957, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.3618435294117647e-06, | |
| "loss": 1.9396, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.7037544250488281, | |
| "eval_runtime": 899.1013, | |
| "eval_samples_per_second": 87.573, | |
| "eval_steps_per_second": 2.737, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.3536082352941172e-06, | |
| "loss": 1.9393, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.6980476379394531, | |
| "eval_runtime": 890.1765, | |
| "eval_samples_per_second": 88.451, | |
| "eval_steps_per_second": 2.765, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.3453811764705883e-06, | |
| "loss": 1.9318, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.690232753753662, | |
| "eval_runtime": 893.2562, | |
| "eval_samples_per_second": 88.146, | |
| "eval_steps_per_second": 2.755, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.3371623529411767e-06, | |
| "loss": 1.9394, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.6947176456451416, | |
| "eval_runtime": 845.3897, | |
| "eval_samples_per_second": 93.137, | |
| "eval_steps_per_second": 2.911, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.3289270588235296e-06, | |
| "loss": 1.9349, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.6847898960113525, | |
| "eval_runtime": 840.3632, | |
| "eval_samples_per_second": 93.694, | |
| "eval_steps_per_second": 2.928, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.320691764705882e-06, | |
| "loss": 1.9437, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.6911025047302246, | |
| "eval_runtime": 829.0742, | |
| "eval_samples_per_second": 94.97, | |
| "eval_steps_per_second": 2.968, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.3124564705882355e-06, | |
| "loss": 1.9325, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.6867425441741943, | |
| "eval_runtime": 876.4729, | |
| "eval_samples_per_second": 89.834, | |
| "eval_steps_per_second": 2.808, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.3042211764705884e-06, | |
| "loss": 1.9189, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.6835554838180542, | |
| "eval_runtime": 863.7905, | |
| "eval_samples_per_second": 91.153, | |
| "eval_steps_per_second": 2.849, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.295985882352941e-06, | |
| "loss": 1.9392, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.6935853958129883, | |
| "eval_runtime": 885.5489, | |
| "eval_samples_per_second": 88.913, | |
| "eval_steps_per_second": 2.779, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.2877505882352943e-06, | |
| "loss": 1.9362, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.6833049058914185, | |
| "eval_runtime": 817.314, | |
| "eval_samples_per_second": 96.336, | |
| "eval_steps_per_second": 3.011, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.2795152941176473e-06, | |
| "loss": 1.9389, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.6875420808792114, | |
| "eval_runtime": 831.6008, | |
| "eval_samples_per_second": 94.681, | |
| "eval_steps_per_second": 2.959, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.2712800000000002e-06, | |
| "loss": 1.9332, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.6895575523376465, | |
| "eval_runtime": 785.6485, | |
| "eval_samples_per_second": 100.219, | |
| "eval_steps_per_second": 3.132, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.263061176470588e-06, | |
| "loss": 1.9182, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.6885087490081787, | |
| "eval_runtime": 827.3753, | |
| "eval_samples_per_second": 95.165, | |
| "eval_steps_per_second": 2.974, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.2548258823529415e-06, | |
| "loss": 1.9347, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.681879997253418, | |
| "eval_runtime": 900.142, | |
| "eval_samples_per_second": 87.472, | |
| "eval_steps_per_second": 2.734, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.2465905882352944e-06, | |
| "loss": 1.9381, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.6881948709487915, | |
| "eval_runtime": 834.4334, | |
| "eval_samples_per_second": 94.36, | |
| "eval_steps_per_second": 2.949, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.238363529411765e-06, | |
| "loss": 1.938, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.6861393451690674, | |
| "eval_runtime": 822.7924, | |
| "eval_samples_per_second": 95.695, | |
| "eval_steps_per_second": 2.991, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.230136470588236e-06, | |
| "loss": 1.9387, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.686549186706543, | |
| "eval_runtime": 760.0348, | |
| "eval_samples_per_second": 103.597, | |
| "eval_steps_per_second": 3.238, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.2219011764705887e-06, | |
| "loss": 1.9331, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.6894826889038086, | |
| "eval_runtime": 828.4061, | |
| "eval_samples_per_second": 95.046, | |
| "eval_steps_per_second": 2.971, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.2136658823529416e-06, | |
| "loss": 1.9277, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.6776493787765503, | |
| "eval_runtime": 788.589, | |
| "eval_samples_per_second": 99.845, | |
| "eval_steps_per_second": 3.121, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.205438823529412e-06, | |
| "loss": 1.93, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.6794580221176147, | |
| "eval_runtime": 847.1105, | |
| "eval_samples_per_second": 92.948, | |
| "eval_steps_per_second": 2.905, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.1972035294117652e-06, | |
| "loss": 1.9395, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.6972289085388184, | |
| "eval_runtime": 811.3504, | |
| "eval_samples_per_second": 97.044, | |
| "eval_steps_per_second": 3.033, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.188968235294118e-06, | |
| "loss": 1.937, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.684800148010254, | |
| "eval_runtime": 831.3474, | |
| "eval_samples_per_second": 94.71, | |
| "eval_steps_per_second": 2.96, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.180732941176471e-06, | |
| "loss": 1.9272, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.689572811126709, | |
| "eval_runtime": 858.3647, | |
| "eval_samples_per_second": 91.729, | |
| "eval_steps_per_second": 2.867, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.1724976470588236e-06, | |
| "loss": 1.9299, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.685671329498291, | |
| "eval_runtime": 855.5516, | |
| "eval_samples_per_second": 92.031, | |
| "eval_steps_per_second": 2.877, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.1642623529411766e-06, | |
| "loss": 1.9278, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.6928762197494507, | |
| "eval_runtime": 776.3726, | |
| "eval_samples_per_second": 101.417, | |
| "eval_steps_per_second": 3.17, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.156035294117647e-06, | |
| "loss": 1.9193, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.6825348138809204, | |
| "eval_runtime": 809.4317, | |
| "eval_samples_per_second": 97.274, | |
| "eval_steps_per_second": 3.04, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.1478e-06, | |
| "loss": 1.9247, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.676526427268982, | |
| "eval_runtime": 823.829, | |
| "eval_samples_per_second": 95.574, | |
| "eval_steps_per_second": 2.987, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.139572941176471e-06, | |
| "loss": 1.9233, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.6889564990997314, | |
| "eval_runtime": 781.5255, | |
| "eval_samples_per_second": 100.748, | |
| "eval_steps_per_second": 3.149, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.1313376470588238e-06, | |
| "loss": 1.9276, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.6908719539642334, | |
| "eval_runtime": 786.5253, | |
| "eval_samples_per_second": 100.107, | |
| "eval_steps_per_second": 3.129, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.123110588235295e-06, | |
| "loss": 1.9183, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.6757584810256958, | |
| "eval_runtime": 900.4138, | |
| "eval_samples_per_second": 87.445, | |
| "eval_steps_per_second": 2.733, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.114875294117647e-06, | |
| "loss": 1.9263, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.6813621520996094, | |
| "eval_runtime": 800.9151, | |
| "eval_samples_per_second": 98.309, | |
| "eval_steps_per_second": 3.073, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.1066399999999994e-06, | |
| "loss": 1.9132, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.6753489971160889, | |
| "eval_runtime": 841.1528, | |
| "eval_samples_per_second": 93.606, | |
| "eval_steps_per_second": 2.926, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.0984211764705886e-06, | |
| "loss": 1.9243, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.682147741317749, | |
| "eval_runtime": 876.3921, | |
| "eval_samples_per_second": 89.842, | |
| "eval_steps_per_second": 2.808, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.090185882352941e-06, | |
| "loss": 1.9132, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.6810792684555054, | |
| "eval_runtime": 800.804, | |
| "eval_samples_per_second": 98.322, | |
| "eval_steps_per_second": 3.073, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.081950588235294e-06, | |
| "loss": 1.918, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.686233639717102, | |
| "eval_runtime": 862.163, | |
| "eval_samples_per_second": 91.325, | |
| "eval_steps_per_second": 2.854, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.0737152941176466e-06, | |
| "loss": 1.9131, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.6782478094100952, | |
| "eval_runtime": 807.9469, | |
| "eval_samples_per_second": 97.453, | |
| "eval_steps_per_second": 3.046, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.06548e-06, | |
| "loss": 1.9292, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.6781325340270996, | |
| "eval_runtime": 808.511, | |
| "eval_samples_per_second": 97.385, | |
| "eval_steps_per_second": 3.044, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.057244705882353e-06, | |
| "loss": 1.9274, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.6813188791275024, | |
| "eval_runtime": 710.823, | |
| "eval_samples_per_second": 110.769, | |
| "eval_steps_per_second": 3.462, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.0490176470588236e-06, | |
| "loss": 1.9217, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.6681177616119385, | |
| "eval_runtime": 701.1999, | |
| "eval_samples_per_second": 112.289, | |
| "eval_steps_per_second": 3.51, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.0407823529411765e-06, | |
| "loss": 1.9136, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.6671432256698608, | |
| "eval_runtime": 639.7881, | |
| "eval_samples_per_second": 123.067, | |
| "eval_steps_per_second": 3.847, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.0325470588235295e-06, | |
| "loss": 1.9225, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.6838454008102417, | |
| "eval_runtime": 617.2221, | |
| "eval_samples_per_second": 127.567, | |
| "eval_steps_per_second": 3.987, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.0243117647058824e-06, | |
| "loss": 1.9202, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.67597234249115, | |
| "eval_runtime": 668.9084, | |
| "eval_samples_per_second": 117.71, | |
| "eval_steps_per_second": 3.679, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.0160847058823526e-06, | |
| "loss": 1.9216, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.6799976825714111, | |
| "eval_runtime": 679.9535, | |
| "eval_samples_per_second": 115.798, | |
| "eval_steps_per_second": 3.619, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.0078576470588237e-06, | |
| "loss": 1.9217, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.6781527996063232, | |
| "eval_runtime": 722.93, | |
| "eval_samples_per_second": 108.914, | |
| "eval_steps_per_second": 3.404, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.9996223529411767e-06, | |
| "loss": 1.9152, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.6670936346054077, | |
| "eval_runtime": 706.8606, | |
| "eval_samples_per_second": 111.39, | |
| "eval_steps_per_second": 3.482, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.9913952941176473e-06, | |
| "loss": 1.911, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.6739472150802612, | |
| "eval_runtime": 639.4338, | |
| "eval_samples_per_second": 123.136, | |
| "eval_steps_per_second": 3.849, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.9831600000000007e-06, | |
| "loss": 1.924, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.6732276678085327, | |
| "eval_runtime": 599.699, | |
| "eval_samples_per_second": 131.294, | |
| "eval_steps_per_second": 4.104, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.974924705882353e-06, | |
| "loss": 1.9087, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.6759378910064697, | |
| "eval_runtime": 603.5409, | |
| "eval_samples_per_second": 130.458, | |
| "eval_steps_per_second": 4.078, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.966689411764706e-06, | |
| "loss": 1.9133, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.6749118566513062, | |
| "eval_runtime": 671.1294, | |
| "eval_samples_per_second": 117.32, | |
| "eval_steps_per_second": 3.667, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.9584623529411764e-06, | |
| "loss": 1.9125, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.6708778142929077, | |
| "eval_runtime": 641.754, | |
| "eval_samples_per_second": 122.69, | |
| "eval_steps_per_second": 3.835, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.9502352941176474e-06, | |
| "loss": 1.9154, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.672595739364624, | |
| "eval_runtime": 665.3613, | |
| "eval_samples_per_second": 118.337, | |
| "eval_steps_per_second": 3.699, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.9420000000000004e-06, | |
| "loss": 1.9094, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.6622326374053955, | |
| "eval_runtime": 598.1523, | |
| "eval_samples_per_second": 131.634, | |
| "eval_steps_per_second": 4.114, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.9337647058823533e-06, | |
| "loss": 1.9101, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.6699204444885254, | |
| "eval_runtime": 592.06, | |
| "eval_samples_per_second": 132.988, | |
| "eval_steps_per_second": 4.157, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.9255376470588235e-06, | |
| "loss": 1.9173, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.6692543029785156, | |
| "eval_runtime": 602.9832, | |
| "eval_samples_per_second": 130.579, | |
| "eval_steps_per_second": 4.081, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.9173023529411765e-06, | |
| "loss": 1.9179, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.6609896421432495, | |
| "eval_runtime": 605.196, | |
| "eval_samples_per_second": 130.102, | |
| "eval_steps_per_second": 4.066, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.9090670588235294e-06, | |
| "loss": 1.925, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.6624456644058228, | |
| "eval_runtime": 662.6702, | |
| "eval_samples_per_second": 118.818, | |
| "eval_steps_per_second": 3.714, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.9008317647058824e-06, | |
| "loss": 1.9054, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.671242594718933, | |
| "eval_runtime": 656.7662, | |
| "eval_samples_per_second": 119.886, | |
| "eval_steps_per_second": 3.747, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.8925964705882353e-06, | |
| "loss": 1.9035, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.6635082960128784, | |
| "eval_runtime": 586.3995, | |
| "eval_samples_per_second": 134.272, | |
| "eval_steps_per_second": 4.197, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.884369411764706e-06, | |
| "loss": 1.8994, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.663743495941162, | |
| "eval_runtime": 636.0923, | |
| "eval_samples_per_second": 123.782, | |
| "eval_steps_per_second": 3.869, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.8761341176470593e-06, | |
| "loss": 1.9091, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.6615914106369019, | |
| "eval_runtime": 634.3745, | |
| "eval_samples_per_second": 124.118, | |
| "eval_steps_per_second": 3.879, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.8679070588235296e-06, | |
| "loss": 1.9121, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.6662075519561768, | |
| "eval_runtime": 633.787, | |
| "eval_samples_per_second": 124.233, | |
| "eval_steps_per_second": 3.883, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.859671764705882e-06, | |
| "loss": 1.8999, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.665105938911438, | |
| "eval_runtime": 695.9342, | |
| "eval_samples_per_second": 113.139, | |
| "eval_steps_per_second": 3.536, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.8514364705882355e-06, | |
| "loss": 1.8987, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.659078598022461, | |
| "eval_runtime": 593.4035, | |
| "eval_samples_per_second": 132.687, | |
| "eval_steps_per_second": 4.147, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.843201176470588e-06, | |
| "loss": 1.9075, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.6652796268463135, | |
| "eval_runtime": 675.3349, | |
| "eval_samples_per_second": 116.59, | |
| "eval_steps_per_second": 3.644, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.8349741176470586e-06, | |
| "loss": 1.9122, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.6633714437484741, | |
| "eval_runtime": 677.0834, | |
| "eval_samples_per_second": 116.288, | |
| "eval_steps_per_second": 3.635, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.8267470588235293e-06, | |
| "loss": 1.9027, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.6583502292633057, | |
| "eval_runtime": 635.279, | |
| "eval_samples_per_second": 123.941, | |
| "eval_steps_per_second": 3.874, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.818511764705882e-06, | |
| "loss": 1.9106, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.657875895500183, | |
| "eval_runtime": 579.2726, | |
| "eval_samples_per_second": 135.924, | |
| "eval_steps_per_second": 4.248, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.810284705882353e-06, | |
| "loss": 1.9031, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.6537038087844849, | |
| "eval_runtime": 636.8, | |
| "eval_samples_per_second": 123.645, | |
| "eval_steps_per_second": 3.865, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.802049411764706e-06, | |
| "loss": 1.9132, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.6636656522750854, | |
| "eval_runtime": 698.4216, | |
| "eval_samples_per_second": 112.736, | |
| "eval_steps_per_second": 3.524, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.793822352941176e-06, | |
| "loss": 1.896, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.6606979370117188, | |
| "eval_runtime": 702.9311, | |
| "eval_samples_per_second": 112.012, | |
| "eval_steps_per_second": 3.501, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.7855870588235294e-06, | |
| "loss": 1.8999, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.6614608764648438, | |
| "eval_runtime": 653.7097, | |
| "eval_samples_per_second": 120.446, | |
| "eval_steps_per_second": 3.765, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.77736e-06, | |
| "loss": 1.911, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.6599065065383911, | |
| "eval_runtime": 629.3127, | |
| "eval_samples_per_second": 125.116, | |
| "eval_steps_per_second": 3.911, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.769124705882353e-06, | |
| "loss": 1.9031, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.6615227460861206, | |
| "eval_runtime": 690.0639, | |
| "eval_samples_per_second": 114.101, | |
| "eval_steps_per_second": 3.566, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.7608894117647063e-06, | |
| "loss": 1.9023, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.6454137563705444, | |
| "eval_runtime": 592.223, | |
| "eval_samples_per_second": 132.952, | |
| "eval_steps_per_second": 4.156, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.752654117647059e-06, | |
| "loss": 1.9141, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.6627545356750488, | |
| "eval_runtime": 663.9405, | |
| "eval_samples_per_second": 118.59, | |
| "eval_steps_per_second": 3.707, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.7444188235294122e-06, | |
| "loss": 1.9003, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.6632248163223267, | |
| "eval_runtime": 631.893, | |
| "eval_samples_per_second": 124.605, | |
| "eval_steps_per_second": 3.895, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.736191764705882e-06, | |
| "loss": 1.8972, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.6637376546859741, | |
| "eval_runtime": 634.1872, | |
| "eval_samples_per_second": 124.154, | |
| "eval_steps_per_second": 3.881, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.727964705882353e-06, | |
| "loss": 1.8967, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.6564476490020752, | |
| "eval_runtime": 615.9047, | |
| "eval_samples_per_second": 127.84, | |
| "eval_steps_per_second": 3.996, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.7197294117647065e-06, | |
| "loss": 1.9001, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.6534888744354248, | |
| "eval_runtime": 648.5154, | |
| "eval_samples_per_second": 121.411, | |
| "eval_steps_per_second": 3.795, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.7114941176470594e-06, | |
| "loss": 1.8986, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.6570912599563599, | |
| "eval_runtime": 657.4951, | |
| "eval_samples_per_second": 119.753, | |
| "eval_steps_per_second": 3.743, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.7032588235294124e-06, | |
| "loss": 1.9137, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.6614021062850952, | |
| "eval_runtime": 628.005, | |
| "eval_samples_per_second": 125.376, | |
| "eval_steps_per_second": 3.919, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.6950235294117653e-06, | |
| "loss": 1.9016, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.6537100076675415, | |
| "eval_runtime": 641.9482, | |
| "eval_samples_per_second": 122.653, | |
| "eval_steps_per_second": 3.834, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.686796470588236e-06, | |
| "loss": 1.8957, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.659902572631836, | |
| "eval_runtime": 604.7038, | |
| "eval_samples_per_second": 130.208, | |
| "eval_steps_per_second": 4.07, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.678561176470589e-06, | |
| "loss": 1.9046, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.6513235569000244, | |
| "eval_runtime": 699.652, | |
| "eval_samples_per_second": 112.537, | |
| "eval_steps_per_second": 3.517, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.670325882352941e-06, | |
| "loss": 1.8932, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.6544750928878784, | |
| "eval_runtime": 629.6124, | |
| "eval_samples_per_second": 125.056, | |
| "eval_steps_per_second": 3.909, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.6620988235294116e-06, | |
| "loss": 1.8964, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.6519490480422974, | |
| "eval_runtime": 654.5444, | |
| "eval_samples_per_second": 120.293, | |
| "eval_steps_per_second": 3.76, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.653863529411765e-06, | |
| "loss": 1.8987, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.6551364660263062, | |
| "eval_runtime": 705.5195, | |
| "eval_samples_per_second": 111.601, | |
| "eval_steps_per_second": 3.488, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.645628235294118e-06, | |
| "loss": 1.8841, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.6510001420974731, | |
| "eval_runtime": 642.966, | |
| "eval_samples_per_second": 122.459, | |
| "eval_steps_per_second": 3.828, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.6374011764705886e-06, | |
| "loss": 1.9098, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.662022590637207, | |
| "eval_runtime": 655.201, | |
| "eval_samples_per_second": 120.172, | |
| "eval_steps_per_second": 3.756, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.6291658823529416e-06, | |
| "loss": 1.8923, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.664062261581421, | |
| "eval_runtime": 596.0888, | |
| "eval_samples_per_second": 132.089, | |
| "eval_steps_per_second": 4.129, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.6209388235294118e-06, | |
| "loss": 1.8923, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.6515814065933228, | |
| "eval_runtime": 644.2159, | |
| "eval_samples_per_second": 122.221, | |
| "eval_steps_per_second": 3.82, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.612703529411765e-06, | |
| "loss": 1.9038, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.6637661457061768, | |
| "eval_runtime": 633.5547, | |
| "eval_samples_per_second": 124.278, | |
| "eval_steps_per_second": 3.884, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.6044764705882345e-06, | |
| "loss": 1.8825, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.6578197479248047, | |
| "eval_runtime": 694.0675, | |
| "eval_samples_per_second": 113.443, | |
| "eval_steps_per_second": 3.546, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.596241176470588e-06, | |
| "loss": 1.8956, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.649842381477356, | |
| "eval_runtime": 657.1133, | |
| "eval_samples_per_second": 119.823, | |
| "eval_steps_per_second": 3.745, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.5880141176470585e-06, | |
| "loss": 1.8972, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.644415259361267, | |
| "eval_runtime": 707.7425, | |
| "eval_samples_per_second": 111.251, | |
| "eval_steps_per_second": 3.477, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.5797788235294115e-06, | |
| "loss": 1.8887, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.6474778652191162, | |
| "eval_runtime": 625.3496, | |
| "eval_samples_per_second": 125.909, | |
| "eval_steps_per_second": 3.935, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.571543529411765e-06, | |
| "loss": 1.8792, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.6593352556228638, | |
| "eval_runtime": 700.7863, | |
| "eval_samples_per_second": 112.355, | |
| "eval_steps_per_second": 3.512, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.563308235294118e-06, | |
| "loss": 1.8947, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.6596338748931885, | |
| "eval_runtime": 689.3715, | |
| "eval_samples_per_second": 114.216, | |
| "eval_steps_per_second": 3.57, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.5550729411764707e-06, | |
| "loss": 1.8862, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.6665337085723877, | |
| "eval_runtime": 636.7484, | |
| "eval_samples_per_second": 123.655, | |
| "eval_steps_per_second": 3.865, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.5468458823529414e-06, | |
| "loss": 1.8911, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.648636817932129, | |
| "eval_runtime": 627.8839, | |
| "eval_samples_per_second": 125.401, | |
| "eval_steps_per_second": 3.92, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.538610588235294e-06, | |
| "loss": 1.8993, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.6460869312286377, | |
| "eval_runtime": 742.579, | |
| "eval_samples_per_second": 106.032, | |
| "eval_steps_per_second": 3.314, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.5303752941176473e-06, | |
| "loss": 1.8947, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.6531628370285034, | |
| "eval_runtime": 686.6543, | |
| "eval_samples_per_second": 114.668, | |
| "eval_steps_per_second": 3.584, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.5221564705882356e-06, | |
| "loss": 1.8877, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.6493592262268066, | |
| "eval_runtime": 674.6189, | |
| "eval_samples_per_second": 116.713, | |
| "eval_steps_per_second": 3.648, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.5139211764705886e-06, | |
| "loss": 1.889, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.6436575651168823, | |
| "eval_runtime": 660.9898, | |
| "eval_samples_per_second": 119.12, | |
| "eval_steps_per_second": 3.723, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.505685882352942e-06, | |
| "loss": 1.8789, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.6456811428070068, | |
| "eval_runtime": 682.5583, | |
| "eval_samples_per_second": 115.356, | |
| "eval_steps_per_second": 3.606, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.4974505882352945e-06, | |
| "loss": 1.8818, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.6493545770645142, | |
| "eval_runtime": 656.6455, | |
| "eval_samples_per_second": 119.908, | |
| "eval_steps_per_second": 3.748, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.4892152941176474e-06, | |
| "loss": 1.8896, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.654678225517273, | |
| "eval_runtime": 696.7768, | |
| "eval_samples_per_second": 113.002, | |
| "eval_steps_per_second": 3.532, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.480988235294118e-06, | |
| "loss": 1.8835, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.649330496788025, | |
| "eval_runtime": 614.7903, | |
| "eval_samples_per_second": 128.071, | |
| "eval_steps_per_second": 4.003, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.472752941176471e-06, | |
| "loss": 1.8993, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.6418979167938232, | |
| "eval_runtime": 643.8384, | |
| "eval_samples_per_second": 122.293, | |
| "eval_steps_per_second": 3.822, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.464517647058824e-06, | |
| "loss": 1.8897, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.6511067152023315, | |
| "eval_runtime": 685.4246, | |
| "eval_samples_per_second": 114.873, | |
| "eval_steps_per_second": 3.59, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.456282352941177e-06, | |
| "loss": 1.883, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.6433333158493042, | |
| "eval_runtime": 690.9078, | |
| "eval_samples_per_second": 113.962, | |
| "eval_steps_per_second": 3.562, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.448055294117647e-06, | |
| "loss": 1.8812, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.6498456001281738, | |
| "eval_runtime": 721.7278, | |
| "eval_samples_per_second": 109.095, | |
| "eval_steps_per_second": 3.41, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.4398282352941177e-06, | |
| "loss": 1.8898, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.6489810943603516, | |
| "eval_runtime": 615.5981, | |
| "eval_samples_per_second": 127.903, | |
| "eval_steps_per_second": 3.998, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.4315929411764707e-06, | |
| "loss": 1.8841, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.6423102617263794, | |
| "eval_runtime": 619.1731, | |
| "eval_samples_per_second": 127.165, | |
| "eval_steps_per_second": 3.975, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.4233576470588236e-06, | |
| "loss": 1.8929, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.6477515697479248, | |
| "eval_runtime": 698.3602, | |
| "eval_samples_per_second": 112.746, | |
| "eval_steps_per_second": 3.524, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.4151223529411766e-06, | |
| "loss": 1.8769, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.6441521644592285, | |
| "eval_runtime": 741.7014, | |
| "eval_samples_per_second": 106.157, | |
| "eval_steps_per_second": 3.318, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.4068952941176472e-06, | |
| "loss": 1.88, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.6422946453094482, | |
| "eval_runtime": 616.4599, | |
| "eval_samples_per_second": 127.724, | |
| "eval_steps_per_second": 3.992, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.39866e-06, | |
| "loss": 1.8892, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.6453232765197754, | |
| "eval_runtime": 598.18, | |
| "eval_samples_per_second": 131.628, | |
| "eval_steps_per_second": 4.114, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.3904411764705885e-06, | |
| "loss": 1.8867, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.6516659259796143, | |
| "eval_runtime": 643.3214, | |
| "eval_samples_per_second": 122.391, | |
| "eval_steps_per_second": 3.825, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.3822058823529415e-06, | |
| "loss": 1.8788, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.6312636137008667, | |
| "eval_runtime": 714.2232, | |
| "eval_samples_per_second": 110.241, | |
| "eval_steps_per_second": 3.446, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.3739705882352944e-06, | |
| "loss": 1.885, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.6397331953048706, | |
| "eval_runtime": 660.6056, | |
| "eval_samples_per_second": 119.189, | |
| "eval_steps_per_second": 3.725, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.3657352941176474e-06, | |
| "loss": 1.8786, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.6381564140319824, | |
| "eval_runtime": 600.1409, | |
| "eval_samples_per_second": 131.198, | |
| "eval_steps_per_second": 4.101, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.357508235294118e-06, | |
| "loss": 1.8799, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.6406282186508179, | |
| "eval_runtime": 638.1975, | |
| "eval_samples_per_second": 123.374, | |
| "eval_steps_per_second": 3.856, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.349272941176471e-06, | |
| "loss": 1.8897, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.6376131772994995, | |
| "eval_runtime": 691.1499, | |
| "eval_samples_per_second": 113.922, | |
| "eval_steps_per_second": 3.561, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.3410541176470593e-06, | |
| "loss": 1.8819, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.6377204656600952, | |
| "eval_runtime": 639.4459, | |
| "eval_samples_per_second": 123.133, | |
| "eval_steps_per_second": 3.849, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.332818823529412e-06, | |
| "loss": 1.8685, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.6423110961914062, | |
| "eval_runtime": 692.3687, | |
| "eval_samples_per_second": 113.721, | |
| "eval_steps_per_second": 3.554, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.3245835294117648e-06, | |
| "loss": 1.8904, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.6445286273956299, | |
| "eval_runtime": 695.1818, | |
| "eval_samples_per_second": 113.261, | |
| "eval_steps_per_second": 3.54, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.3163482352941177e-06, | |
| "loss": 1.8826, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.6447981595993042, | |
| "eval_runtime": 717.5664, | |
| "eval_samples_per_second": 109.728, | |
| "eval_steps_per_second": 3.43, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.3081129411764706e-06, | |
| "loss": 1.8784, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.6407545804977417, | |
| "eval_runtime": 676.9456, | |
| "eval_samples_per_second": 116.312, | |
| "eval_steps_per_second": 3.635, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.2998776470588236e-06, | |
| "loss": 1.8876, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.6438355445861816, | |
| "eval_runtime": 673.2486, | |
| "eval_samples_per_second": 116.951, | |
| "eval_steps_per_second": 3.655, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.2916423529411765e-06, | |
| "loss": 1.8746, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.6389583349227905, | |
| "eval_runtime": 648.594, | |
| "eval_samples_per_second": 121.396, | |
| "eval_steps_per_second": 3.794, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.283415294117647e-06, | |
| "loss": 1.8719, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.6385319232940674, | |
| "eval_runtime": 708.8894, | |
| "eval_samples_per_second": 111.071, | |
| "eval_steps_per_second": 3.472, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.27518e-06, | |
| "loss": 1.881, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.6474238634109497, | |
| "eval_runtime": 686.9218, | |
| "eval_samples_per_second": 114.623, | |
| "eval_steps_per_second": 3.583, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.2669611764705885e-06, | |
| "loss": 1.8909, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.6290351152420044, | |
| "eval_runtime": 598.6713, | |
| "eval_samples_per_second": 131.52, | |
| "eval_steps_per_second": 4.111, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.2587258823529414e-06, | |
| "loss": 1.8788, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.646666407585144, | |
| "eval_runtime": 604.8994, | |
| "eval_samples_per_second": 130.165, | |
| "eval_steps_per_second": 4.068, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.2504905882352944e-06, | |
| "loss": 1.8878, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.6379634141921997, | |
| "eval_runtime": 666.7018, | |
| "eval_samples_per_second": 118.099, | |
| "eval_steps_per_second": 3.691, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.242263529411765e-06, | |
| "loss": 1.8879, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.636752724647522, | |
| "eval_runtime": 655.8918, | |
| "eval_samples_per_second": 120.046, | |
| "eval_steps_per_second": 3.752, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.234028235294118e-06, | |
| "loss": 1.8853, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.6320216655731201, | |
| "eval_runtime": 598.9547, | |
| "eval_samples_per_second": 131.457, | |
| "eval_steps_per_second": 4.109, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.2258011764705886e-06, | |
| "loss": 1.878, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.6368935108184814, | |
| "eval_runtime": 671.7937, | |
| "eval_samples_per_second": 117.204, | |
| "eval_steps_per_second": 3.663, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.2175658823529415e-06, | |
| "loss": 1.8724, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.6372097730636597, | |
| "eval_runtime": 649.2117, | |
| "eval_samples_per_second": 121.281, | |
| "eval_steps_per_second": 3.791, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.2093305882352945e-06, | |
| "loss": 1.8853, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.6407856941223145, | |
| "eval_runtime": 687.7581, | |
| "eval_samples_per_second": 114.484, | |
| "eval_steps_per_second": 3.578, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.2011035294117647e-06, | |
| "loss": 1.8826, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.6369657516479492, | |
| "eval_runtime": 653.073, | |
| "eval_samples_per_second": 120.564, | |
| "eval_steps_per_second": 3.768, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.1928682352941177e-06, | |
| "loss": 1.8766, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.6378271579742432, | |
| "eval_runtime": 595.8545, | |
| "eval_samples_per_second": 132.141, | |
| "eval_steps_per_second": 4.13, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.1846411764705883e-06, | |
| "loss": 1.8725, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.6308584213256836, | |
| "eval_runtime": 613.2861, | |
| "eval_samples_per_second": 128.385, | |
| "eval_steps_per_second": 4.013, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.1764058823529412e-06, | |
| "loss": 1.8823, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.6472721099853516, | |
| "eval_runtime": 614.538, | |
| "eval_samples_per_second": 128.124, | |
| "eval_steps_per_second": 4.005, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.168170588235294e-06, | |
| "loss": 1.8754, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.634007215499878, | |
| "eval_runtime": 680.3949, | |
| "eval_samples_per_second": 115.723, | |
| "eval_steps_per_second": 3.617, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.159935294117647e-06, | |
| "loss": 1.8871, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.6386611461639404, | |
| "eval_runtime": 681.8742, | |
| "eval_samples_per_second": 115.471, | |
| "eval_steps_per_second": 3.609, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.1517082352941178e-06, | |
| "loss": 1.8682, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.6339727640151978, | |
| "eval_runtime": 632.124, | |
| "eval_samples_per_second": 124.559, | |
| "eval_steps_per_second": 3.893, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.1434811764705884e-06, | |
| "loss": 1.8703, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.6315019130706787, | |
| "eval_runtime": 595.3007, | |
| "eval_samples_per_second": 132.264, | |
| "eval_steps_per_second": 4.134, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.135254117647059e-06, | |
| "loss": 1.8858, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.6289024353027344, | |
| "eval_runtime": 637.5934, | |
| "eval_samples_per_second": 123.491, | |
| "eval_steps_per_second": 3.86, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.127018823529412e-06, | |
| "loss": 1.8727, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.6371269226074219, | |
| "eval_runtime": 671.6032, | |
| "eval_samples_per_second": 117.237, | |
| "eval_steps_per_second": 3.664, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.118783529411765e-06, | |
| "loss": 1.8729, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.6401563882827759, | |
| "eval_runtime": 639.6628, | |
| "eval_samples_per_second": 123.091, | |
| "eval_steps_per_second": 3.847, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.1105564705882356e-06, | |
| "loss": 1.8767, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.6311676502227783, | |
| "eval_runtime": 600.697, | |
| "eval_samples_per_second": 131.076, | |
| "eval_steps_per_second": 4.097, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.1023211764705886e-06, | |
| "loss": 1.8751, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.6302475929260254, | |
| "eval_runtime": 596.162, | |
| "eval_samples_per_second": 132.073, | |
| "eval_steps_per_second": 4.128, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.0940858823529415e-06, | |
| "loss": 1.8778, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.6412676572799683, | |
| "eval_runtime": 620.8121, | |
| "eval_samples_per_second": 126.829, | |
| "eval_steps_per_second": 3.964, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.0858505882352944e-06, | |
| "loss": 1.8709, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.6188048124313354, | |
| "eval_runtime": 599.8506, | |
| "eval_samples_per_second": 131.261, | |
| "eval_steps_per_second": 4.103, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.0776235294117647e-06, | |
| "loss": 1.8763, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.6331790685653687, | |
| "eval_runtime": 650.4909, | |
| "eval_samples_per_second": 121.042, | |
| "eval_steps_per_second": 3.783, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.0693964705882353e-06, | |
| "loss": 1.8881, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.6275856494903564, | |
| "eval_runtime": 595.8254, | |
| "eval_samples_per_second": 132.148, | |
| "eval_steps_per_second": 4.13, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.0611611764705883e-06, | |
| "loss": 1.8805, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.6381438970565796, | |
| "eval_runtime": 627.6658, | |
| "eval_samples_per_second": 125.444, | |
| "eval_steps_per_second": 3.921, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.052925882352941e-06, | |
| "loss": 1.8802, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.6350407600402832, | |
| "eval_runtime": 594.3681, | |
| "eval_samples_per_second": 132.472, | |
| "eval_steps_per_second": 4.141, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.044690588235294e-06, | |
| "loss": 1.8781, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.6267595291137695, | |
| "eval_runtime": 667.2785, | |
| "eval_samples_per_second": 117.997, | |
| "eval_steps_per_second": 3.688, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.036455294117647e-06, | |
| "loss": 1.8637, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.6291269063949585, | |
| "eval_runtime": 595.964, | |
| "eval_samples_per_second": 132.117, | |
| "eval_steps_per_second": 4.129, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.02822e-06, | |
| "loss": 1.8729, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.6322344541549683, | |
| "eval_runtime": 667.1453, | |
| "eval_samples_per_second": 118.021, | |
| "eval_steps_per_second": 3.689, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.0199929411764707e-06, | |
| "loss": 1.8638, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.6420254707336426, | |
| "eval_runtime": 642.8047, | |
| "eval_samples_per_second": 122.49, | |
| "eval_steps_per_second": 3.829, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.0117576470588236e-06, | |
| "loss": 1.8692, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.6281312704086304, | |
| "eval_runtime": 662.9634, | |
| "eval_samples_per_second": 118.765, | |
| "eval_steps_per_second": 3.712, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.0035305882352943e-06, | |
| "loss": 1.8645, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.6313811540603638, | |
| "eval_runtime": 714.0456, | |
| "eval_samples_per_second": 110.269, | |
| "eval_steps_per_second": 3.447, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.9952952941176472e-06, | |
| "loss": 1.8684, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.6184828281402588, | |
| "eval_runtime": 685.5984, | |
| "eval_samples_per_second": 114.844, | |
| "eval_steps_per_second": 3.59, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.987068235294118e-06, | |
| "loss": 1.8681, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.628950595855713, | |
| "eval_runtime": 628.2882, | |
| "eval_samples_per_second": 125.32, | |
| "eval_steps_per_second": 3.917, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.978832941176471e-06, | |
| "loss": 1.8704, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.6387931108474731, | |
| "eval_runtime": 678.8489, | |
| "eval_samples_per_second": 115.986, | |
| "eval_steps_per_second": 3.625, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.9706058823529415e-06, | |
| "loss": 1.8639, | |
| "step": 373000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.6350470781326294, | |
| "eval_runtime": 729.0473, | |
| "eval_samples_per_second": 108.0, | |
| "eval_steps_per_second": 3.376, | |
| "step": 373000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.9623705882352944e-06, | |
| "loss": 1.8632, | |
| "step": 374000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.6308817863464355, | |
| "eval_runtime": 631.0976, | |
| "eval_samples_per_second": 124.762, | |
| "eval_steps_per_second": 3.9, | |
| "step": 374000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.954135294117647e-06, | |
| "loss": 1.8631, | |
| "step": 375000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.6306254863739014, | |
| "eval_runtime": 681.9362, | |
| "eval_samples_per_second": 115.461, | |
| "eval_steps_per_second": 3.609, | |
| "step": 375000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.9459e-06, | |
| "loss": 1.8727, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.6303691864013672, | |
| "eval_runtime": 714.3006, | |
| "eval_samples_per_second": 110.229, | |
| "eval_steps_per_second": 3.445, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.9376729411764705e-06, | |
| "loss": 1.8786, | |
| "step": 377000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.625319480895996, | |
| "eval_runtime": 677.4584, | |
| "eval_samples_per_second": 116.224, | |
| "eval_steps_per_second": 3.633, | |
| "step": 377000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.9294376470588235e-06, | |
| "loss": 1.8619, | |
| "step": 378000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.6231558322906494, | |
| "eval_runtime": 710.8825, | |
| "eval_samples_per_second": 110.76, | |
| "eval_steps_per_second": 3.462, | |
| "step": 378000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.9212023529411764e-06, | |
| "loss": 1.8635, | |
| "step": 379000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.6391326189041138, | |
| "eval_runtime": 635.1822, | |
| "eval_samples_per_second": 123.96, | |
| "eval_steps_per_second": 3.874, | |
| "step": 379000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.912975294117647e-06, | |
| "loss": 1.8639, | |
| "step": 380000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.6201550960540771, | |
| "eval_runtime": 652.0366, | |
| "eval_samples_per_second": 120.755, | |
| "eval_steps_per_second": 3.774, | |
| "step": 380000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.9047482352941177e-06, | |
| "loss": 1.8671, | |
| "step": 381000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.6272953748703003, | |
| "eval_runtime": 628.1118, | |
| "eval_samples_per_second": 125.355, | |
| "eval_steps_per_second": 3.918, | |
| "step": 381000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.8965129411764706e-06, | |
| "loss": 1.8646, | |
| "step": 382000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.6334937810897827, | |
| "eval_runtime": 600.8225, | |
| "eval_samples_per_second": 131.049, | |
| "eval_steps_per_second": 4.096, | |
| "step": 382000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.8882858823529413e-06, | |
| "loss": 1.8641, | |
| "step": 383000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.6256176233291626, | |
| "eval_runtime": 623.5899, | |
| "eval_samples_per_second": 126.264, | |
| "eval_steps_per_second": 3.947, | |
| "step": 383000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.8800505882352942e-06, | |
| "loss": 1.8641, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.6278165578842163, | |
| "eval_runtime": 634.1163, | |
| "eval_samples_per_second": 124.168, | |
| "eval_steps_per_second": 3.881, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.871815294117647e-06, | |
| "loss": 1.8696, | |
| "step": 385000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.6159448623657227, | |
| "eval_runtime": 688.2826, | |
| "eval_samples_per_second": 114.396, | |
| "eval_steps_per_second": 3.576, | |
| "step": 385000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.8635882352941178e-06, | |
| "loss": 1.8754, | |
| "step": 386000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.6252976655960083, | |
| "eval_runtime": 635.7586, | |
| "eval_samples_per_second": 123.847, | |
| "eval_steps_per_second": 3.871, | |
| "step": 386000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.8553529411764706e-06, | |
| "loss": 1.8652, | |
| "step": 387000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.6262269020080566, | |
| "eval_runtime": 660.6971, | |
| "eval_samples_per_second": 119.173, | |
| "eval_steps_per_second": 3.725, | |
| "step": 387000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.8471176470588237e-06, | |
| "loss": 1.8728, | |
| "step": 388000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.622817873954773, | |
| "eval_runtime": 613.1794, | |
| "eval_samples_per_second": 128.408, | |
| "eval_steps_per_second": 4.014, | |
| "step": 388000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.838882352941177e-06, | |
| "loss": 1.8573, | |
| "step": 389000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.6240416765213013, | |
| "eval_runtime": 658.1977, | |
| "eval_samples_per_second": 119.625, | |
| "eval_steps_per_second": 3.739, | |
| "step": 389000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.8306552941176469e-06, | |
| "loss": 1.867, | |
| "step": 390000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.6374046802520752, | |
| "eval_runtime": 659.4878, | |
| "eval_samples_per_second": 119.391, | |
| "eval_steps_per_second": 3.732, | |
| "step": 390000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.8224199999999998e-06, | |
| "loss": 1.8604, | |
| "step": 391000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.625261902809143, | |
| "eval_runtime": 660.1821, | |
| "eval_samples_per_second": 119.266, | |
| "eval_steps_per_second": 3.728, | |
| "step": 391000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.8141847058823528e-06, | |
| "loss": 1.867, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.620868444442749, | |
| "eval_runtime": 646.1503, | |
| "eval_samples_per_second": 121.856, | |
| "eval_steps_per_second": 3.809, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.805949411764706e-06, | |
| "loss": 1.8616, | |
| "step": 393000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.6343539953231812, | |
| "eval_runtime": 589.1258, | |
| "eval_samples_per_second": 133.651, | |
| "eval_steps_per_second": 4.177, | |
| "step": 393000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.7977223529411764e-06, | |
| "loss": 1.8695, | |
| "step": 394000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.6252588033676147, | |
| "eval_runtime": 652.0329, | |
| "eval_samples_per_second": 120.756, | |
| "eval_steps_per_second": 3.774, | |
| "step": 394000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.7894870588235293e-06, | |
| "loss": 1.8637, | |
| "step": 395000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.6274361610412598, | |
| "eval_runtime": 656.356, | |
| "eval_samples_per_second": 119.961, | |
| "eval_steps_per_second": 3.749, | |
| "step": 395000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.78126e-06, | |
| "loss": 1.8544, | |
| "step": 396000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.6243598461151123, | |
| "eval_runtime": 613.6606, | |
| "eval_samples_per_second": 128.307, | |
| "eval_steps_per_second": 4.01, | |
| "step": 396000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.773024705882353e-06, | |
| "loss": 1.8652, | |
| "step": 397000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.626272201538086, | |
| "eval_runtime": 627.4053, | |
| "eval_samples_per_second": 125.496, | |
| "eval_steps_per_second": 3.923, | |
| "step": 397000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.7647976470588235e-06, | |
| "loss": 1.8707, | |
| "step": 398000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.6186515092849731, | |
| "eval_runtime": 651.665, | |
| "eval_samples_per_second": 120.824, | |
| "eval_steps_per_second": 3.776, | |
| "step": 398000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.756562352941177e-06, | |
| "loss": 1.8607, | |
| "step": 399000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.6232746839523315, | |
| "eval_runtime": 721.7173, | |
| "eval_samples_per_second": 109.097, | |
| "eval_steps_per_second": 3.41, | |
| "step": 399000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.7483270588235299e-06, | |
| "loss": 1.8778, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.6159837245941162, | |
| "eval_runtime": 709.9821, | |
| "eval_samples_per_second": 110.9, | |
| "eval_steps_per_second": 3.466, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.740091764705883e-06, | |
| "loss": 1.8651, | |
| "step": 401000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.621022343635559, | |
| "eval_runtime": 609.3721, | |
| "eval_samples_per_second": 129.21, | |
| "eval_steps_per_second": 4.039, | |
| "step": 401000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.7318729411764711e-06, | |
| "loss": 1.8601, | |
| "step": 402000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.620976209640503, | |
| "eval_runtime": 640.963, | |
| "eval_samples_per_second": 122.842, | |
| "eval_steps_per_second": 3.84, | |
| "step": 402000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.7236376470588239e-06, | |
| "loss": 1.8634, | |
| "step": 403000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.6287916898727417, | |
| "eval_runtime": 722.8242, | |
| "eval_samples_per_second": 108.93, | |
| "eval_steps_per_second": 3.405, | |
| "step": 403000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.7154105882352947e-06, | |
| "loss": 1.8692, | |
| "step": 404000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.6240730285644531, | |
| "eval_runtime": 638.1242, | |
| "eval_samples_per_second": 123.388, | |
| "eval_steps_per_second": 3.857, | |
| "step": 404000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.7071752941176466e-06, | |
| "loss": 1.854, | |
| "step": 405000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.6287106275558472, | |
| "eval_runtime": 652.4874, | |
| "eval_samples_per_second": 120.672, | |
| "eval_steps_per_second": 3.772, | |
| "step": 405000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.6989399999999998e-06, | |
| "loss": 1.8628, | |
| "step": 406000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.6285154819488525, | |
| "eval_runtime": 674.6082, | |
| "eval_samples_per_second": 116.715, | |
| "eval_steps_per_second": 3.648, | |
| "step": 406000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.6907047058823527e-06, | |
| "loss": 1.8588, | |
| "step": 407000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.6281447410583496, | |
| "eval_runtime": 702.8676, | |
| "eval_samples_per_second": 112.023, | |
| "eval_steps_per_second": 3.501, | |
| "step": 407000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.6824776470588234e-06, | |
| "loss": 1.8613, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.6213467121124268, | |
| "eval_runtime": 658.5951, | |
| "eval_samples_per_second": 119.553, | |
| "eval_steps_per_second": 3.737, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.6742423529411763e-06, | |
| "loss": 1.8494, | |
| "step": 409000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.6278510093688965, | |
| "eval_runtime": 644.797, | |
| "eval_samples_per_second": 122.111, | |
| "eval_steps_per_second": 3.817, | |
| "step": 409000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.6660070588235297e-06, | |
| "loss": 1.8584, | |
| "step": 410000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.6307947635650635, | |
| "eval_runtime": 622.8216, | |
| "eval_samples_per_second": 126.42, | |
| "eval_steps_per_second": 3.951, | |
| "step": 410000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.6577882352941176e-06, | |
| "loss": 1.8642, | |
| "step": 411000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.6242249011993408, | |
| "eval_runtime": 659.8518, | |
| "eval_samples_per_second": 119.325, | |
| "eval_steps_per_second": 3.73, | |
| "step": 411000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.6495529411764706e-06, | |
| "loss": 1.8699, | |
| "step": 412000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.6131978034973145, | |
| "eval_runtime": 633.5288, | |
| "eval_samples_per_second": 124.283, | |
| "eval_steps_per_second": 3.885, | |
| "step": 412000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.6413176470588237e-06, | |
| "loss": 1.8609, | |
| "step": 413000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.6228089332580566, | |
| "eval_runtime": 663.4595, | |
| "eval_samples_per_second": 118.676, | |
| "eval_steps_per_second": 3.709, | |
| "step": 413000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.6330823529411769e-06, | |
| "loss": 1.8601, | |
| "step": 414000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.6239029169082642, | |
| "eval_runtime": 687.3212, | |
| "eval_samples_per_second": 114.556, | |
| "eval_steps_per_second": 3.581, | |
| "step": 414000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.6248552941176477e-06, | |
| "loss": 1.8534, | |
| "step": 415000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.6289734840393066, | |
| "eval_runtime": 626.344, | |
| "eval_samples_per_second": 125.709, | |
| "eval_steps_per_second": 3.929, | |
| "step": 415000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.6166200000000005e-06, | |
| "loss": 1.8473, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.6148146390914917, | |
| "eval_runtime": 596.927, | |
| "eval_samples_per_second": 131.904, | |
| "eval_steps_per_second": 4.123, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.6083847058823534e-06, | |
| "loss": 1.8564, | |
| "step": 417000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.6277542114257812, | |
| "eval_runtime": 670.7002, | |
| "eval_samples_per_second": 117.395, | |
| "eval_steps_per_second": 3.669, | |
| "step": 417000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.600157647058824e-06, | |
| "loss": 1.8491, | |
| "step": 418000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.619775414466858, | |
| "eval_runtime": 706.5202, | |
| "eval_samples_per_second": 111.443, | |
| "eval_steps_per_second": 3.483, | |
| "step": 418000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.5919305882352947e-06, | |
| "loss": 1.8539, | |
| "step": 419000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.6218732595443726, | |
| "eval_runtime": 648.1903, | |
| "eval_samples_per_second": 121.472, | |
| "eval_steps_per_second": 3.797, | |
| "step": 419000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.5836952941176468e-06, | |
| "loss": 1.8544, | |
| "step": 420000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.6217312812805176, | |
| "eval_runtime": 700.6655, | |
| "eval_samples_per_second": 112.375, | |
| "eval_steps_per_second": 3.512, | |
| "step": 420000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.5754599999999997e-06, | |
| "loss": 1.8524, | |
| "step": 421000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.6175516843795776, | |
| "eval_runtime": 646.3871, | |
| "eval_samples_per_second": 121.811, | |
| "eval_steps_per_second": 3.807, | |
| "step": 421000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.567224705882353e-06, | |
| "loss": 1.8586, | |
| "step": 422000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.6136716604232788, | |
| "eval_runtime": 637.3755, | |
| "eval_samples_per_second": 123.533, | |
| "eval_steps_per_second": 3.861, | |
| "step": 422000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.558989411764706e-06, | |
| "loss": 1.8564, | |
| "step": 423000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.6192333698272705, | |
| "eval_runtime": 593.2957, | |
| "eval_samples_per_second": 132.711, | |
| "eval_steps_per_second": 4.148, | |
| "step": 423000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.5507788235294117e-06, | |
| "loss": 1.8578, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.621081829071045, | |
| "eval_runtime": 596.6533, | |
| "eval_samples_per_second": 131.964, | |
| "eval_steps_per_second": 4.125, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.5425435294117646e-06, | |
| "loss": 1.8593, | |
| "step": 425000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.623468279838562, | |
| "eval_runtime": 694.5364, | |
| "eval_samples_per_second": 113.366, | |
| "eval_steps_per_second": 3.543, | |
| "step": 425000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.5343082352941174e-06, | |
| "loss": 1.8499, | |
| "step": 426000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.6201629638671875, | |
| "eval_runtime": 620.0591, | |
| "eval_samples_per_second": 126.983, | |
| "eval_steps_per_second": 3.969, | |
| "step": 426000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.526072941176471e-06, | |
| "loss": 1.8553, | |
| "step": 427000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.6244655847549438, | |
| "eval_runtime": 701.0162, | |
| "eval_samples_per_second": 112.318, | |
| "eval_steps_per_second": 3.511, | |
| "step": 427000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.5178376470588239e-06, | |
| "loss": 1.8612, | |
| "step": 428000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.6230287551879883, | |
| "eval_runtime": 637.0294, | |
| "eval_samples_per_second": 123.6, | |
| "eval_steps_per_second": 3.863, | |
| "step": 428000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.5096105882352945e-06, | |
| "loss": 1.8539, | |
| "step": 429000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.6243265867233276, | |
| "eval_runtime": 643.6788, | |
| "eval_samples_per_second": 122.323, | |
| "eval_steps_per_second": 3.823, | |
| "step": 429000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.5013752941176475e-06, | |
| "loss": 1.8552, | |
| "step": 430000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.623043417930603, | |
| "eval_runtime": 604.9319, | |
| "eval_samples_per_second": 130.158, | |
| "eval_steps_per_second": 4.068, | |
| "step": 430000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.4931400000000004e-06, | |
| "loss": 1.8608, | |
| "step": 431000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.6242647171020508, | |
| "eval_runtime": 645.9074, | |
| "eval_samples_per_second": 121.901, | |
| "eval_steps_per_second": 3.81, | |
| "step": 431000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.4849047058823536e-06, | |
| "loss": 1.8541, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.6212998628616333, | |
| "eval_runtime": 593.5841, | |
| "eval_samples_per_second": 132.647, | |
| "eval_steps_per_second": 4.146, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.4766858823529417e-06, | |
| "loss": 1.8471, | |
| "step": 433000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.6204901933670044, | |
| "eval_runtime": 632.0978, | |
| "eval_samples_per_second": 124.565, | |
| "eval_steps_per_second": 3.893, | |
| "step": 433000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.4684505882352944e-06, | |
| "loss": 1.8505, | |
| "step": 434000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.6168400049209595, | |
| "eval_runtime": 634.5582, | |
| "eval_samples_per_second": 124.082, | |
| "eval_steps_per_second": 3.878, | |
| "step": 434000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.4602152941176467e-06, | |
| "loss": 1.858, | |
| "step": 435000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.6155096292495728, | |
| "eval_runtime": 627.6321, | |
| "eval_samples_per_second": 125.451, | |
| "eval_steps_per_second": 3.921, | |
| "step": 435000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.4519800000000001e-06, | |
| "loss": 1.8523, | |
| "step": 436000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.6156325340270996, | |
| "eval_runtime": 610.2358, | |
| "eval_samples_per_second": 129.027, | |
| "eval_steps_per_second": 4.033, | |
| "step": 436000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.4437529411764703e-06, | |
| "loss": 1.853, | |
| "step": 437000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.612059235572815, | |
| "eval_runtime": 710.5317, | |
| "eval_samples_per_second": 110.814, | |
| "eval_steps_per_second": 3.464, | |
| "step": 437000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.4355176470588237e-06, | |
| "loss": 1.8495, | |
| "step": 438000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.6132701635360718, | |
| "eval_runtime": 627.4106, | |
| "eval_samples_per_second": 125.495, | |
| "eval_steps_per_second": 3.922, | |
| "step": 438000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.4272823529411767e-06, | |
| "loss": 1.845, | |
| "step": 439000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.6237196922302246, | |
| "eval_runtime": 618.6027, | |
| "eval_samples_per_second": 127.282, | |
| "eval_steps_per_second": 3.978, | |
| "step": 439000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.4190552941176473e-06, | |
| "loss": 1.8467, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.6179585456848145, | |
| "eval_runtime": 625.0402, | |
| "eval_samples_per_second": 125.971, | |
| "eval_steps_per_second": 3.937, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.410828235294118e-06, | |
| "loss": 1.8532, | |
| "step": 441000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.6177033185958862, | |
| "eval_runtime": 701.2169, | |
| "eval_samples_per_second": 112.286, | |
| "eval_steps_per_second": 3.51, | |
| "step": 441000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.4025929411764707e-06, | |
| "loss": 1.8516, | |
| "step": 442000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.6135560274124146, | |
| "eval_runtime": 670.6381, | |
| "eval_samples_per_second": 117.406, | |
| "eval_steps_per_second": 3.67, | |
| "step": 442000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.3943576470588238e-06, | |
| "loss": 1.8464, | |
| "step": 443000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.6133610010147095, | |
| "eval_runtime": 632.607, | |
| "eval_samples_per_second": 124.464, | |
| "eval_steps_per_second": 3.89, | |
| "step": 443000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.3861223529411768e-06, | |
| "loss": 1.8418, | |
| "step": 444000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.6199904680252075, | |
| "eval_runtime": 676.6467, | |
| "eval_samples_per_second": 116.364, | |
| "eval_steps_per_second": 3.637, | |
| "step": 444000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.3778870588235297e-06, | |
| "loss": 1.8538, | |
| "step": 445000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.620301365852356, | |
| "eval_runtime": 711.6514, | |
| "eval_samples_per_second": 110.64, | |
| "eval_steps_per_second": 3.458, | |
| "step": 445000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.3696517647058827e-06, | |
| "loss": 1.8517, | |
| "step": 446000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.6171836853027344, | |
| "eval_runtime": 617.9803, | |
| "eval_samples_per_second": 127.41, | |
| "eval_steps_per_second": 3.982, | |
| "step": 446000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.361424705882353e-06, | |
| "loss": 1.8612, | |
| "step": 447000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.6206892728805542, | |
| "eval_runtime": 639.5461, | |
| "eval_samples_per_second": 123.114, | |
| "eval_steps_per_second": 3.848, | |
| "step": 447000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.353197647058824e-06, | |
| "loss": 1.8535, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.6004185676574707, | |
| "eval_runtime": 591.7421, | |
| "eval_samples_per_second": 133.06, | |
| "eval_steps_per_second": 4.159, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.3449623529411767e-06, | |
| "loss": 1.8437, | |
| "step": 449000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.6153193712234497, | |
| "eval_runtime": 659.566, | |
| "eval_samples_per_second": 119.377, | |
| "eval_steps_per_second": 3.731, | |
| "step": 449000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.3367270588235298e-06, | |
| "loss": 1.8561, | |
| "step": 450000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.6150519847869873, | |
| "eval_runtime": 658.2097, | |
| "eval_samples_per_second": 119.623, | |
| "eval_steps_per_second": 3.739, | |
| "step": 450000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.3284917647058824e-06, | |
| "loss": 1.8512, | |
| "step": 451000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.6145780086517334, | |
| "eval_runtime": 596.1799, | |
| "eval_samples_per_second": 132.069, | |
| "eval_steps_per_second": 4.128, | |
| "step": 451000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.320264705882353e-06, | |
| "loss": 1.8492, | |
| "step": 452000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.6190379858016968, | |
| "eval_runtime": 599.0501, | |
| "eval_samples_per_second": 131.436, | |
| "eval_steps_per_second": 4.108, | |
| "step": 452000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.3120376470588237e-06, | |
| "loss": 1.8539, | |
| "step": 453000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.6064990758895874, | |
| "eval_runtime": 627.6701, | |
| "eval_samples_per_second": 125.443, | |
| "eval_steps_per_second": 3.921, | |
| "step": 453000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.3038023529411766e-06, | |
| "loss": 1.8406, | |
| "step": 454000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.61311674118042, | |
| "eval_runtime": 661.9232, | |
| "eval_samples_per_second": 118.952, | |
| "eval_steps_per_second": 3.718, | |
| "step": 454000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.2955670588235296e-06, | |
| "loss": 1.8343, | |
| "step": 455000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.6140803098678589, | |
| "eval_runtime": 594.958, | |
| "eval_samples_per_second": 132.34, | |
| "eval_steps_per_second": 4.136, | |
| "step": 455000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.2873317647058825e-06, | |
| "loss": 1.8447, | |
| "step": 456000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.607283592224121, | |
| "eval_runtime": 589.0492, | |
| "eval_samples_per_second": 133.668, | |
| "eval_steps_per_second": 4.178, | |
| "step": 456000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.2790964705882357e-06, | |
| "loss": 1.8476, | |
| "step": 457000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.623671293258667, | |
| "eval_runtime": 590.9271, | |
| "eval_samples_per_second": 133.243, | |
| "eval_steps_per_second": 4.165, | |
| "step": 457000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.270869411764706e-06, | |
| "loss": 1.8511, | |
| "step": 458000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.6194998025894165, | |
| "eval_runtime": 610.8052, | |
| "eval_samples_per_second": 128.907, | |
| "eval_steps_per_second": 4.029, | |
| "step": 458000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.262634117647059e-06, | |
| "loss": 1.8502, | |
| "step": 459000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.614992380142212, | |
| "eval_runtime": 669.6472, | |
| "eval_samples_per_second": 117.58, | |
| "eval_steps_per_second": 3.675, | |
| "step": 459000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.254398823529412e-06, | |
| "loss": 1.8485, | |
| "step": 460000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.6185976266860962, | |
| "eval_runtime": 593.1091, | |
| "eval_samples_per_second": 132.753, | |
| "eval_steps_per_second": 4.149, | |
| "step": 460000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.2461717647058826e-06, | |
| "loss": 1.8486, | |
| "step": 461000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.6242183446884155, | |
| "eval_runtime": 619.9316, | |
| "eval_samples_per_second": 127.009, | |
| "eval_steps_per_second": 3.97, | |
| "step": 461000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.2379447058823533e-06, | |
| "loss": 1.8508, | |
| "step": 462000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.6094743013381958, | |
| "eval_runtime": 682.5864, | |
| "eval_samples_per_second": 115.351, | |
| "eval_steps_per_second": 3.605, | |
| "step": 462000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.2297094117647062e-06, | |
| "loss": 1.8509, | |
| "step": 463000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.6169160604476929, | |
| "eval_runtime": 650.0935, | |
| "eval_samples_per_second": 121.116, | |
| "eval_steps_per_second": 3.786, | |
| "step": 463000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.2214741176470592e-06, | |
| "loss": 1.8449, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.62052583694458, | |
| "eval_runtime": 649.3412, | |
| "eval_samples_per_second": 121.257, | |
| "eval_steps_per_second": 3.79, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.213238823529412e-06, | |
| "loss": 1.8673, | |
| "step": 465000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.6155439615249634, | |
| "eval_runtime": 637.256, | |
| "eval_samples_per_second": 123.556, | |
| "eval_steps_per_second": 3.862, | |
| "step": 465000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.2050035294117646e-06, | |
| "loss": 1.8482, | |
| "step": 466000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.6143635511398315, | |
| "eval_runtime": 663.142, | |
| "eval_samples_per_second": 118.733, | |
| "eval_steps_per_second": 3.711, | |
| "step": 466000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.1967764705882353e-06, | |
| "loss": 1.8522, | |
| "step": 467000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.6124098300933838, | |
| "eval_runtime": 610.7893, | |
| "eval_samples_per_second": 128.91, | |
| "eval_steps_per_second": 4.029, | |
| "step": 467000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.1885411764705882e-06, | |
| "loss": 1.844, | |
| "step": 468000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.6135690212249756, | |
| "eval_runtime": 634.195, | |
| "eval_samples_per_second": 124.153, | |
| "eval_steps_per_second": 3.881, | |
| "step": 468000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.1803141176470589e-06, | |
| "loss": 1.8462, | |
| "step": 469000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.6144988536834717, | |
| "eval_runtime": 636.9429, | |
| "eval_samples_per_second": 123.617, | |
| "eval_steps_per_second": 3.864, | |
| "step": 469000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.1720788235294118e-06, | |
| "loss": 1.8593, | |
| "step": 470000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.6172668933868408, | |
| "eval_runtime": 705.616, | |
| "eval_samples_per_second": 111.586, | |
| "eval_steps_per_second": 3.488, | |
| "step": 470000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.1638435294117648e-06, | |
| "loss": 1.8493, | |
| "step": 471000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.6117665767669678, | |
| "eval_runtime": 676.055, | |
| "eval_samples_per_second": 116.465, | |
| "eval_steps_per_second": 3.64, | |
| "step": 471000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.1556082352941177e-06, | |
| "loss": 1.849, | |
| "step": 472000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.6118968725204468, | |
| "eval_runtime": 593.9987, | |
| "eval_samples_per_second": 132.554, | |
| "eval_steps_per_second": 4.143, | |
| "step": 472000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.1473811764705883e-06, | |
| "loss": 1.8478, | |
| "step": 473000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.6105737686157227, | |
| "eval_runtime": 691.8219, | |
| "eval_samples_per_second": 113.811, | |
| "eval_steps_per_second": 3.557, | |
| "step": 473000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.1391458823529413e-06, | |
| "loss": 1.8539, | |
| "step": 474000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.6143759489059448, | |
| "eval_runtime": 679.8256, | |
| "eval_samples_per_second": 115.819, | |
| "eval_steps_per_second": 3.62, | |
| "step": 474000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.1309105882352942e-06, | |
| "loss": 1.8547, | |
| "step": 475000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.616089105606079, | |
| "eval_runtime": 631.7324, | |
| "eval_samples_per_second": 124.637, | |
| "eval_steps_per_second": 3.896, | |
| "step": 475000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.1226835294117649e-06, | |
| "loss": 1.8483, | |
| "step": 476000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.6217153072357178, | |
| "eval_runtime": 634.5839, | |
| "eval_samples_per_second": 124.077, | |
| "eval_steps_per_second": 3.878, | |
| "step": 476000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.1144564705882355e-06, | |
| "loss": 1.8545, | |
| "step": 477000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.6165567636489868, | |
| "eval_runtime": 636.4723, | |
| "eval_samples_per_second": 123.708, | |
| "eval_steps_per_second": 3.867, | |
| "step": 477000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.1062211764705885e-06, | |
| "loss": 1.8458, | |
| "step": 478000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.601502776145935, | |
| "eval_runtime": 619.423, | |
| "eval_samples_per_second": 127.113, | |
| "eval_steps_per_second": 3.973, | |
| "step": 478000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.0979858823529414e-06, | |
| "loss": 1.8473, | |
| "step": 479000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.6162437200546265, | |
| "eval_runtime": 596.2973, | |
| "eval_samples_per_second": 132.043, | |
| "eval_steps_per_second": 4.127, | |
| "step": 479000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.089758823529412e-06, | |
| "loss": 1.8534, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.6076633930206299, | |
| "eval_runtime": 608.3431, | |
| "eval_samples_per_second": 129.429, | |
| "eval_steps_per_second": 4.045, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.0815235294117646e-06, | |
| "loss": 1.8486, | |
| "step": 481000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.607995629310608, | |
| "eval_runtime": 729.0011, | |
| "eval_samples_per_second": 108.007, | |
| "eval_steps_per_second": 3.376, | |
| "step": 481000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.0732882352941175e-06, | |
| "loss": 1.8526, | |
| "step": 482000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.6202946901321411, | |
| "eval_runtime": 755.7769, | |
| "eval_samples_per_second": 104.18, | |
| "eval_steps_per_second": 3.256, | |
| "step": 482000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.0650529411764705e-06, | |
| "loss": 1.8449, | |
| "step": 483000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.6120697259902954, | |
| "eval_runtime": 657.2602, | |
| "eval_samples_per_second": 119.796, | |
| "eval_steps_per_second": 3.744, | |
| "step": 483000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.0568258823529411e-06, | |
| "loss": 1.8369, | |
| "step": 484000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.6107741594314575, | |
| "eval_runtime": 614.6669, | |
| "eval_samples_per_second": 128.097, | |
| "eval_steps_per_second": 4.004, | |
| "step": 484000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.048590588235294e-06, | |
| "loss": 1.8493, | |
| "step": 485000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.6112476587295532, | |
| "eval_runtime": 637.5284, | |
| "eval_samples_per_second": 123.504, | |
| "eval_steps_per_second": 3.86, | |
| "step": 485000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.040355294117647e-06, | |
| "loss": 1.849, | |
| "step": 486000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.613427996635437, | |
| "eval_runtime": 690.4812, | |
| "eval_samples_per_second": 114.032, | |
| "eval_steps_per_second": 3.564, | |
| "step": 486000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.0321364705882354e-06, | |
| "loss": 1.8559, | |
| "step": 487000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.6105836629867554, | |
| "eval_runtime": 644.5734, | |
| "eval_samples_per_second": 122.154, | |
| "eval_steps_per_second": 3.818, | |
| "step": 487000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.0239011764705883e-06, | |
| "loss": 1.8505, | |
| "step": 488000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.6063605546951294, | |
| "eval_runtime": 611.8049, | |
| "eval_samples_per_second": 128.696, | |
| "eval_steps_per_second": 4.023, | |
| "step": 488000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.0156658823529412e-06, | |
| "loss": 1.859, | |
| "step": 489000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.6112093925476074, | |
| "eval_runtime": 596.3432, | |
| "eval_samples_per_second": 132.033, | |
| "eval_steps_per_second": 4.127, | |
| "step": 489000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.0074305882352942e-06, | |
| "loss": 1.8403, | |
| "step": 490000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.6082416772842407, | |
| "eval_runtime": 636.8445, | |
| "eval_samples_per_second": 123.636, | |
| "eval_steps_per_second": 3.864, | |
| "step": 490000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.992035294117648e-07, | |
| "loss": 1.837, | |
| "step": 491000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.6034836769104004, | |
| "eval_runtime": 721.1232, | |
| "eval_samples_per_second": 109.187, | |
| "eval_steps_per_second": 3.413, | |
| "step": 491000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.909682352941178e-07, | |
| "loss": 1.8472, | |
| "step": 492000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.6123322248458862, | |
| "eval_runtime": 598.9191, | |
| "eval_samples_per_second": 131.465, | |
| "eval_steps_per_second": 4.109, | |
| "step": 492000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.827329411764707e-07, | |
| "loss": 1.8381, | |
| "step": 493000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.6135793924331665, | |
| "eval_runtime": 636.3102, | |
| "eval_samples_per_second": 123.74, | |
| "eval_steps_per_second": 3.868, | |
| "step": 493000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.74514117647059e-07, | |
| "loss": 1.8451, | |
| "step": 494000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.6103402376174927, | |
| "eval_runtime": 643.5154, | |
| "eval_samples_per_second": 122.355, | |
| "eval_steps_per_second": 3.824, | |
| "step": 494000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.66278823529412e-07, | |
| "loss": 1.8472, | |
| "step": 495000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.6103589534759521, | |
| "eval_runtime": 713.2659, | |
| "eval_samples_per_second": 110.389, | |
| "eval_steps_per_second": 3.45, | |
| "step": 495000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.580517647058822e-07, | |
| "loss": 1.8456, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.6119657754898071, | |
| "eval_runtime": 661.2469, | |
| "eval_samples_per_second": 119.074, | |
| "eval_steps_per_second": 3.722, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.498164705882351e-07, | |
| "loss": 1.8472, | |
| "step": 497000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.6195623874664307, | |
| "eval_runtime": 721.1961, | |
| "eval_samples_per_second": 109.176, | |
| "eval_steps_per_second": 3.412, | |
| "step": 497000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.415811764705881e-07, | |
| "loss": 1.8463, | |
| "step": 498000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.6081604957580566, | |
| "eval_runtime": 653.4788, | |
| "eval_samples_per_second": 120.489, | |
| "eval_steps_per_second": 3.766, | |
| "step": 498000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.333458823529411e-07, | |
| "loss": 1.8361, | |
| "step": 499000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.6095768213272095, | |
| "eval_runtime": 717.3607, | |
| "eval_samples_per_second": 109.759, | |
| "eval_steps_per_second": 3.431, | |
| "step": 499000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.25110588235294e-07, | |
| "loss": 1.8419, | |
| "step": 500000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.604457974433899, | |
| "eval_runtime": 633.7813, | |
| "eval_samples_per_second": 124.234, | |
| "eval_steps_per_second": 3.883, | |
| "step": 500000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.168835294117647e-07, | |
| "loss": 1.8476, | |
| "step": 501000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.6114977598190308, | |
| "eval_runtime": 648.4133, | |
| "eval_samples_per_second": 121.43, | |
| "eval_steps_per_second": 3.795, | |
| "step": 501000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.086482352941177e-07, | |
| "loss": 1.842, | |
| "step": 502000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.6074268817901611, | |
| "eval_runtime": 658.9063, | |
| "eval_samples_per_second": 119.496, | |
| "eval_steps_per_second": 3.735, | |
| "step": 502000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.004129411764706e-07, | |
| "loss": 1.8483, | |
| "step": 503000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.6014885902404785, | |
| "eval_runtime": 714.2685, | |
| "eval_samples_per_second": 110.234, | |
| "eval_steps_per_second": 3.445, | |
| "step": 503000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.921858823529413e-07, | |
| "loss": 1.841, | |
| "step": 504000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.6082409620285034, | |
| "eval_runtime": 686.6491, | |
| "eval_samples_per_second": 114.668, | |
| "eval_steps_per_second": 3.584, | |
| "step": 504000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.839505882352944e-07, | |
| "loss": 1.8388, | |
| "step": 505000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.5999279022216797, | |
| "eval_runtime": 635.3059, | |
| "eval_samples_per_second": 123.936, | |
| "eval_steps_per_second": 3.874, | |
| "step": 505000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.757235294117648e-07, | |
| "loss": 1.8489, | |
| "step": 506000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.612676978111267, | |
| "eval_runtime": 643.6962, | |
| "eval_samples_per_second": 122.32, | |
| "eval_steps_per_second": 3.823, | |
| "step": 506000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.674882352941178e-07, | |
| "loss": 1.836, | |
| "step": 507000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.6081751585006714, | |
| "eval_runtime": 632.1897, | |
| "eval_samples_per_second": 124.546, | |
| "eval_steps_per_second": 3.893, | |
| "step": 507000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.592611764705886e-07, | |
| "loss": 1.8375, | |
| "step": 508000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.6010805368423462, | |
| "eval_runtime": 656.7973, | |
| "eval_samples_per_second": 119.88, | |
| "eval_steps_per_second": 3.747, | |
| "step": 508000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.510258823529414e-07, | |
| "loss": 1.8406, | |
| "step": 509000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.5963528156280518, | |
| "eval_runtime": 647.0602, | |
| "eval_samples_per_second": 121.684, | |
| "eval_steps_per_second": 3.803, | |
| "step": 509000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.427988235294121e-07, | |
| "loss": 1.8475, | |
| "step": 510000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.6051133871078491, | |
| "eval_runtime": 614.1278, | |
| "eval_samples_per_second": 128.209, | |
| "eval_steps_per_second": 4.007, | |
| "step": 510000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.345717647058822e-07, | |
| "loss": 1.8439, | |
| "step": 511000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.6119394302368164, | |
| "eval_runtime": 680.4122, | |
| "eval_samples_per_second": 115.72, | |
| "eval_steps_per_second": 3.617, | |
| "step": 511000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.263364705882351e-07, | |
| "loss": 1.8425, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.603615641593933, | |
| "eval_runtime": 582.1286, | |
| "eval_samples_per_second": 135.257, | |
| "eval_steps_per_second": 4.228, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.181011764705881e-07, | |
| "loss": 1.8376, | |
| "step": 513000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.5999643802642822, | |
| "eval_runtime": 637.8704, | |
| "eval_samples_per_second": 123.437, | |
| "eval_steps_per_second": 3.858, | |
| "step": 513000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.098658823529411e-07, | |
| "loss": 1.8362, | |
| "step": 514000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.6083329916000366, | |
| "eval_runtime": 645.3739, | |
| "eval_samples_per_second": 122.002, | |
| "eval_steps_per_second": 3.813, | |
| "step": 514000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.016388235294116e-07, | |
| "loss": 1.8531, | |
| "step": 515000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.6102386713027954, | |
| "eval_runtime": 641.5128, | |
| "eval_samples_per_second": 122.736, | |
| "eval_steps_per_second": 3.836, | |
| "step": 515000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 7.934035294117648e-07, | |
| "loss": 1.8377, | |
| "step": 516000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.6046222448349, | |
| "eval_runtime": 613.188, | |
| "eval_samples_per_second": 128.406, | |
| "eval_steps_per_second": 4.013, | |
| "step": 516000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 7.851764705882353e-07, | |
| "loss": 1.8382, | |
| "step": 517000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.6014589071273804, | |
| "eval_runtime": 670.3738, | |
| "eval_samples_per_second": 117.452, | |
| "eval_steps_per_second": 3.671, | |
| "step": 517000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.76949411764706e-07, | |
| "loss": 1.8428, | |
| "step": 518000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.5967994928359985, | |
| "eval_runtime": 603.4298, | |
| "eval_samples_per_second": 130.482, | |
| "eval_steps_per_second": 4.078, | |
| "step": 518000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.687141176470591e-07, | |
| "loss": 1.8425, | |
| "step": 519000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.6028351783752441, | |
| "eval_runtime": 653.6448, | |
| "eval_samples_per_second": 120.458, | |
| "eval_steps_per_second": 3.765, | |
| "step": 519000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.604788235294119e-07, | |
| "loss": 1.8387, | |
| "step": 520000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.6120455265045166, | |
| "eval_runtime": 592.1502, | |
| "eval_samples_per_second": 132.968, | |
| "eval_steps_per_second": 4.156, | |
| "step": 520000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.522435294117649e-07, | |
| "loss": 1.8395, | |
| "step": 521000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.595177173614502, | |
| "eval_runtime": 632.9138, | |
| "eval_samples_per_second": 124.404, | |
| "eval_steps_per_second": 3.888, | |
| "step": 521000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.440082352941178e-07, | |
| "loss": 1.8505, | |
| "step": 522000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.6045807600021362, | |
| "eval_runtime": 656.1512, | |
| "eval_samples_per_second": 119.998, | |
| "eval_steps_per_second": 3.751, | |
| "step": 522000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.357894117647061e-07, | |
| "loss": 1.8452, | |
| "step": 523000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.6030842065811157, | |
| "eval_runtime": 628.9711, | |
| "eval_samples_per_second": 125.184, | |
| "eval_steps_per_second": 3.913, | |
| "step": 523000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.275541176470591e-07, | |
| "loss": 1.8469, | |
| "step": 524000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.608011245727539, | |
| "eval_runtime": 706.4291, | |
| "eval_samples_per_second": 111.458, | |
| "eval_steps_per_second": 3.484, | |
| "step": 524000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.19318823529412e-07, | |
| "loss": 1.8323, | |
| "step": 525000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.6070075035095215, | |
| "eval_runtime": 612.8785, | |
| "eval_samples_per_second": 128.471, | |
| "eval_steps_per_second": 4.015, | |
| "step": 525000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.110835294117644e-07, | |
| "loss": 1.8438, | |
| "step": 526000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.612598180770874, | |
| "eval_runtime": 651.7595, | |
| "eval_samples_per_second": 120.807, | |
| "eval_steps_per_second": 3.776, | |
| "step": 526000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.028482352941175e-07, | |
| "loss": 1.8445, | |
| "step": 527000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.6047810316085815, | |
| "eval_runtime": 628.6369, | |
| "eval_samples_per_second": 125.25, | |
| "eval_steps_per_second": 3.915, | |
| "step": 527000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 6.946294117647058e-07, | |
| "loss": 1.8534, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.6085864305496216, | |
| "eval_runtime": 583.8466, | |
| "eval_samples_per_second": 134.859, | |
| "eval_steps_per_second": 4.215, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 6.863941176470587e-07, | |
| "loss": 1.8422, | |
| "step": 529000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.6161532402038574, | |
| "eval_runtime": 640.5762, | |
| "eval_samples_per_second": 122.916, | |
| "eval_steps_per_second": 3.842, | |
| "step": 529000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 6.781588235294117e-07, | |
| "loss": 1.8346, | |
| "step": 530000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.608655571937561, | |
| "eval_runtime": 602.4702, | |
| "eval_samples_per_second": 130.69, | |
| "eval_steps_per_second": 4.085, | |
| "step": 530000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 6.699235294117647e-07, | |
| "loss": 1.8323, | |
| "step": 531000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.6097711324691772, | |
| "eval_runtime": 631.9053, | |
| "eval_samples_per_second": 124.603, | |
| "eval_steps_per_second": 3.895, | |
| "step": 531000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 6.617047058823529e-07, | |
| "loss": 1.8431, | |
| "step": 532000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.6174230575561523, | |
| "eval_runtime": 690.1823, | |
| "eval_samples_per_second": 114.081, | |
| "eval_steps_per_second": 3.566, | |
| "step": 532000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 6.53469411764706e-07, | |
| "loss": 1.8356, | |
| "step": 533000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.6107144355773926, | |
| "eval_runtime": 614.0509, | |
| "eval_samples_per_second": 128.226, | |
| "eval_steps_per_second": 4.008, | |
| "step": 533000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 6.452341176470589e-07, | |
| "loss": 1.8445, | |
| "step": 534000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.6077425479888916, | |
| "eval_runtime": 602.2466, | |
| "eval_samples_per_second": 130.739, | |
| "eval_steps_per_second": 4.086, | |
| "step": 534000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 6.369988235294118e-07, | |
| "loss": 1.841, | |
| "step": 535000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.600361704826355, | |
| "eval_runtime": 594.6743, | |
| "eval_samples_per_second": 132.404, | |
| "eval_steps_per_second": 4.138, | |
| "step": 535000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 6.287717647058825e-07, | |
| "loss": 1.8499, | |
| "step": 536000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.6131929159164429, | |
| "eval_runtime": 631.7613, | |
| "eval_samples_per_second": 124.631, | |
| "eval_steps_per_second": 3.895, | |
| "step": 536000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 6.205447058823532e-07, | |
| "loss": 1.8418, | |
| "step": 537000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.6085360050201416, | |
| "eval_runtime": 645.6432, | |
| "eval_samples_per_second": 121.951, | |
| "eval_steps_per_second": 3.812, | |
| "step": 537000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 6.123094117647061e-07, | |
| "loss": 1.8293, | |
| "step": 538000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.6009540557861328, | |
| "eval_runtime": 646.7415, | |
| "eval_samples_per_second": 121.744, | |
| "eval_steps_per_second": 3.805, | |
| "step": 538000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 6.04074117647059e-07, | |
| "loss": 1.8343, | |
| "step": 539000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.6065633296966553, | |
| "eval_runtime": 661.4898, | |
| "eval_samples_per_second": 119.03, | |
| "eval_steps_per_second": 3.72, | |
| "step": 539000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5.958388235294121e-07, | |
| "loss": 1.8332, | |
| "step": 540000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.6017389297485352, | |
| "eval_runtime": 606.6913, | |
| "eval_samples_per_second": 129.781, | |
| "eval_steps_per_second": 4.056, | |
| "step": 540000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5.876117647058821e-07, | |
| "loss": 1.8292, | |
| "step": 541000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.6000785827636719, | |
| "eval_runtime": 633.3979, | |
| "eval_samples_per_second": 124.309, | |
| "eval_steps_per_second": 3.885, | |
| "step": 541000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5.793764705882352e-07, | |
| "loss": 1.836, | |
| "step": 542000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.6023591756820679, | |
| "eval_runtime": 657.5131, | |
| "eval_samples_per_second": 119.75, | |
| "eval_steps_per_second": 3.743, | |
| "step": 542000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5.711494117647057e-07, | |
| "loss": 1.8399, | |
| "step": 543000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.5998636484146118, | |
| "eval_runtime": 660.5514, | |
| "eval_samples_per_second": 119.199, | |
| "eval_steps_per_second": 3.726, | |
| "step": 543000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5.629141176470587e-07, | |
| "loss": 1.8474, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.6036168336868286, | |
| "eval_runtime": 632.9235, | |
| "eval_samples_per_second": 124.402, | |
| "eval_steps_per_second": 3.888, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 5.546870588235293e-07, | |
| "loss": 1.8332, | |
| "step": 545000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.5995994806289673, | |
| "eval_runtime": 655.1294, | |
| "eval_samples_per_second": 120.185, | |
| "eval_steps_per_second": 3.757, | |
| "step": 545000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 5.464517647058823e-07, | |
| "loss": 1.8409, | |
| "step": 546000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.6112017631530762, | |
| "eval_runtime": 703.7737, | |
| "eval_samples_per_second": 111.878, | |
| "eval_steps_per_second": 3.497, | |
| "step": 546000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 5.382164705882353e-07, | |
| "loss": 1.8445, | |
| "step": 547000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.6046810150146484, | |
| "eval_runtime": 585.0127, | |
| "eval_samples_per_second": 134.59, | |
| "eval_steps_per_second": 4.207, | |
| "step": 547000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 5.299894117647059e-07, | |
| "loss": 1.8394, | |
| "step": 548000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.6096245050430298, | |
| "eval_runtime": 618.7198, | |
| "eval_samples_per_second": 127.258, | |
| "eval_steps_per_second": 3.978, | |
| "step": 548000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 5.217541176470589e-07, | |
| "loss": 1.844, | |
| "step": 549000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.5993245840072632, | |
| "eval_runtime": 595.419, | |
| "eval_samples_per_second": 132.238, | |
| "eval_steps_per_second": 4.133, | |
| "step": 549000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 5.135270588235295e-07, | |
| "loss": 1.8311, | |
| "step": 550000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.6198428869247437, | |
| "eval_runtime": 630.0269, | |
| "eval_samples_per_second": 124.974, | |
| "eval_steps_per_second": 3.906, | |
| "step": 550000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 5.052917647058826e-07, | |
| "loss": 1.8387, | |
| "step": 551000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.6028835773468018, | |
| "eval_runtime": 645.501, | |
| "eval_samples_per_second": 121.978, | |
| "eval_steps_per_second": 3.813, | |
| "step": 551000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.970564705882355e-07, | |
| "loss": 1.8366, | |
| "step": 552000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.6106973886489868, | |
| "eval_runtime": 600.5839, | |
| "eval_samples_per_second": 131.101, | |
| "eval_steps_per_second": 4.098, | |
| "step": 552000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.888294117647062e-07, | |
| "loss": 1.8402, | |
| "step": 553000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.608701467514038, | |
| "eval_runtime": 657.3776, | |
| "eval_samples_per_second": 119.774, | |
| "eval_steps_per_second": 3.744, | |
| "step": 553000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.806023529411768e-07, | |
| "loss": 1.8369, | |
| "step": 554000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.6089677810668945, | |
| "eval_runtime": 618.0145, | |
| "eval_samples_per_second": 127.403, | |
| "eval_steps_per_second": 3.982, | |
| "step": 554000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.723670588235297e-07, | |
| "loss": 1.8392, | |
| "step": 555000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.6029914617538452, | |
| "eval_runtime": 655.4895, | |
| "eval_samples_per_second": 120.119, | |
| "eval_steps_per_second": 3.754, | |
| "step": 555000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.641317647058821e-07, | |
| "loss": 1.8462, | |
| "step": 556000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.6060106754302979, | |
| "eval_runtime": 665.1863, | |
| "eval_samples_per_second": 118.368, | |
| "eval_steps_per_second": 3.7, | |
| "step": 556000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.558964705882351e-07, | |
| "loss": 1.8292, | |
| "step": 557000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.6043024063110352, | |
| "eval_runtime": 621.9745, | |
| "eval_samples_per_second": 126.592, | |
| "eval_steps_per_second": 3.957, | |
| "step": 557000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.4766117647058806e-07, | |
| "loss": 1.8376, | |
| "step": 558000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.6115914583206177, | |
| "eval_runtime": 629.9877, | |
| "eval_samples_per_second": 124.982, | |
| "eval_steps_per_second": 3.906, | |
| "step": 558000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.3943411764705876e-07, | |
| "loss": 1.8418, | |
| "step": 559000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.609912633895874, | |
| "eval_runtime": 671.4315, | |
| "eval_samples_per_second": 117.267, | |
| "eval_steps_per_second": 3.665, | |
| "step": 559000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.311988235294117e-07, | |
| "loss": 1.8454, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.5986706018447876, | |
| "eval_runtime": 632.0091, | |
| "eval_samples_per_second": 124.582, | |
| "eval_steps_per_second": 3.894, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.2629831155778895e-06, | |
| "loss": 1.8358, | |
| "step": 561000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.6113981008529663, | |
| "eval_runtime": 1373.4808, | |
| "eval_samples_per_second": 57.327, | |
| "eval_steps_per_second": 1.792, | |
| "step": 561000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.2580584924623117e-06, | |
| "loss": 1.8424, | |
| "step": 562000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.608789086341858, | |
| "eval_runtime": 1317.8964, | |
| "eval_samples_per_second": 59.744, | |
| "eval_steps_per_second": 1.867, | |
| "step": 562000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.2531387939698494e-06, | |
| "loss": 1.8396, | |
| "step": 563000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.602584719657898, | |
| "eval_runtime": 1403.3018, | |
| "eval_samples_per_second": 56.108, | |
| "eval_steps_per_second": 1.754, | |
| "step": 563000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.248219095477387e-06, | |
| "loss": 1.8367, | |
| "step": 564000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.6060080528259277, | |
| "eval_runtime": 1432.9745, | |
| "eval_samples_per_second": 54.947, | |
| "eval_steps_per_second": 1.717, | |
| "step": 564000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.2432944723618093e-06, | |
| "loss": 1.8533, | |
| "step": 565000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.6123038530349731, | |
| "eval_runtime": 1298.3906, | |
| "eval_samples_per_second": 60.642, | |
| "eval_steps_per_second": 1.895, | |
| "step": 565000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.2383698492462315e-06, | |
| "loss": 1.8436, | |
| "step": 566000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.612805724143982, | |
| "eval_runtime": 1365.4257, | |
| "eval_samples_per_second": 57.665, | |
| "eval_steps_per_second": 1.802, | |
| "step": 566000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.2334501507537692e-06, | |
| "loss": 1.8483, | |
| "step": 567000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.610816478729248, | |
| "eval_runtime": 1332.0876, | |
| "eval_samples_per_second": 59.108, | |
| "eval_steps_per_second": 1.847, | |
| "step": 567000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.228530452261307e-06, | |
| "loss": 1.8398, | |
| "step": 568000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.5979838371276855, | |
| "eval_runtime": 1364.0972, | |
| "eval_samples_per_second": 57.721, | |
| "eval_steps_per_second": 1.804, | |
| "step": 568000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.2236058291457287e-06, | |
| "loss": 1.8463, | |
| "step": 569000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.6000773906707764, | |
| "eval_runtime": 1360.1908, | |
| "eval_samples_per_second": 57.887, | |
| "eval_steps_per_second": 1.809, | |
| "step": 569000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.2186861306532664e-06, | |
| "loss": 1.8359, | |
| "step": 570000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.6006139516830444, | |
| "eval_runtime": 1317.5401, | |
| "eval_samples_per_second": 59.761, | |
| "eval_steps_per_second": 1.868, | |
| "step": 570000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.2137615075376886e-06, | |
| "loss": 1.84, | |
| "step": 571000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.5974223613739014, | |
| "eval_runtime": 1313.3637, | |
| "eval_samples_per_second": 59.951, | |
| "eval_steps_per_second": 1.874, | |
| "step": 571000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.2088368844221107e-06, | |
| "loss": 1.8376, | |
| "step": 572000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.6001969575881958, | |
| "eval_runtime": 1469.4741, | |
| "eval_samples_per_second": 53.582, | |
| "eval_steps_per_second": 1.675, | |
| "step": 572000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.2039171859296485e-06, | |
| "loss": 1.8449, | |
| "step": 573000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.607892394065857, | |
| "eval_runtime": 1422.4124, | |
| "eval_samples_per_second": 55.355, | |
| "eval_steps_per_second": 1.73, | |
| "step": 573000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.19899256281407e-06, | |
| "loss": 1.8446, | |
| "step": 574000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.6081199645996094, | |
| "eval_runtime": 1373.6037, | |
| "eval_samples_per_second": 57.321, | |
| "eval_steps_per_second": 1.792, | |
| "step": 574000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.1940679396984923e-06, | |
| "loss": 1.8439, | |
| "step": 575000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.608659267425537, | |
| "eval_runtime": 1439.9758, | |
| "eval_samples_per_second": 54.679, | |
| "eval_steps_per_second": 1.709, | |
| "step": 575000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.189143316582915e-06, | |
| "loss": 1.8482, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.6077545881271362, | |
| "eval_runtime": 1319.2178, | |
| "eval_samples_per_second": 59.685, | |
| "eval_steps_per_second": 1.865, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.1842236180904522e-06, | |
| "loss": 1.8439, | |
| "step": 577000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.6032804250717163, | |
| "eval_runtime": 1317.0887, | |
| "eval_samples_per_second": 59.781, | |
| "eval_steps_per_second": 1.869, | |
| "step": 577000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.1792989949748748e-06, | |
| "loss": 1.8321, | |
| "step": 578000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.6043972969055176, | |
| "eval_runtime": 1470.5701, | |
| "eval_samples_per_second": 53.542, | |
| "eval_steps_per_second": 1.674, | |
| "step": 578000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.1743743718592965e-06, | |
| "loss": 1.8419, | |
| "step": 579000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.605370283126831, | |
| "eval_runtime": 1314.2922, | |
| "eval_samples_per_second": 59.908, | |
| "eval_steps_per_second": 1.872, | |
| "step": 579000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.1694497487437186e-06, | |
| "loss": 1.8476, | |
| "step": 580000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.6129260063171387, | |
| "eval_runtime": 1361.9015, | |
| "eval_samples_per_second": 57.814, | |
| "eval_steps_per_second": 1.807, | |
| "step": 580000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.1645300502512564e-06, | |
| "loss": 1.8451, | |
| "step": 581000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.6105306148529053, | |
| "eval_runtime": 1364.3506, | |
| "eval_samples_per_second": 57.71, | |
| "eval_steps_per_second": 1.804, | |
| "step": 581000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.1596054271356785e-06, | |
| "loss": 1.8428, | |
| "step": 582000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.6004083156585693, | |
| "eval_runtime": 1425.3385, | |
| "eval_samples_per_second": 55.241, | |
| "eval_steps_per_second": 1.727, | |
| "step": 582000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.1546808040201002e-06, | |
| "loss": 1.8428, | |
| "step": 583000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.5961782932281494, | |
| "eval_runtime": 1316.8053, | |
| "eval_samples_per_second": 59.794, | |
| "eval_steps_per_second": 1.869, | |
| "step": 583000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.149761105527638e-06, | |
| "loss": 1.8397, | |
| "step": 584000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.614754319190979, | |
| "eval_runtime": 1364.4836, | |
| "eval_samples_per_second": 57.705, | |
| "eval_steps_per_second": 1.804, | |
| "step": 584000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.14483648241206e-06, | |
| "loss": 1.8391, | |
| "step": 585000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.611263632774353, | |
| "eval_runtime": 1427.9009, | |
| "eval_samples_per_second": 55.142, | |
| "eval_steps_per_second": 1.724, | |
| "step": 585000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.139916783919598e-06, | |
| "loss": 1.8429, | |
| "step": 586000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.5951673984527588, | |
| "eval_runtime": 1415.1329, | |
| "eval_samples_per_second": 55.639, | |
| "eval_steps_per_second": 1.739, | |
| "step": 586000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.13499216080402e-06, | |
| "loss": 1.8367, | |
| "step": 587000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.6043238639831543, | |
| "eval_runtime": 1472.8356, | |
| "eval_samples_per_second": 53.459, | |
| "eval_steps_per_second": 1.671, | |
| "step": 587000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.1300724623115578e-06, | |
| "loss": 1.8346, | |
| "step": 588000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.6021771430969238, | |
| "eval_runtime": 1366.1283, | |
| "eval_samples_per_second": 57.635, | |
| "eval_steps_per_second": 1.801, | |
| "step": 588000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.1251478391959803e-06, | |
| "loss": 1.8367, | |
| "step": 589000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.6067354679107666, | |
| "eval_runtime": 1371.6575, | |
| "eval_samples_per_second": 57.403, | |
| "eval_steps_per_second": 1.794, | |
| "step": 589000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.1202281407035177e-06, | |
| "loss": 1.8272, | |
| "step": 590000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.610526442527771, | |
| "eval_runtime": 1417.1973, | |
| "eval_samples_per_second": 55.558, | |
| "eval_steps_per_second": 1.737, | |
| "step": 590000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.1153035175879402e-06, | |
| "loss": 1.8354, | |
| "step": 591000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.6014180183410645, | |
| "eval_runtime": 1484.2434, | |
| "eval_samples_per_second": 53.049, | |
| "eval_steps_per_second": 1.658, | |
| "step": 591000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.110378894472362e-06, | |
| "loss": 1.8425, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.6036982536315918, | |
| "eval_runtime": 1357.7515, | |
| "eval_samples_per_second": 57.991, | |
| "eval_steps_per_second": 1.813, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.105464120603015e-06, | |
| "loss": 1.8375, | |
| "step": 593000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.601694941520691, | |
| "eval_runtime": 1426.4682, | |
| "eval_samples_per_second": 55.197, | |
| "eval_steps_per_second": 1.725, | |
| "step": 593000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.100539497487437e-06, | |
| "loss": 1.8217, | |
| "step": 594000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.605579137802124, | |
| "eval_runtime": 1363.4095, | |
| "eval_samples_per_second": 57.75, | |
| "eval_steps_per_second": 1.805, | |
| "step": 594000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.0956148743718596e-06, | |
| "loss": 1.8363, | |
| "step": 595000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.602707028388977, | |
| "eval_runtime": 1465.2017, | |
| "eval_samples_per_second": 53.738, | |
| "eval_steps_per_second": 1.68, | |
| "step": 595000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.0906902512562817e-06, | |
| "loss": 1.8389, | |
| "step": 596000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.6052539348602295, | |
| "eval_runtime": 1364.7712, | |
| "eval_samples_per_second": 57.692, | |
| "eval_steps_per_second": 1.803, | |
| "step": 596000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.0857656281407034e-06, | |
| "loss": 1.8345, | |
| "step": 597000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.6135693788528442, | |
| "eval_runtime": 1319.0075, | |
| "eval_samples_per_second": 59.694, | |
| "eval_steps_per_second": 1.866, | |
| "step": 597000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.0808410050251256e-06, | |
| "loss": 1.8364, | |
| "step": 598000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.595258116722107, | |
| "eval_runtime": 1370.9372, | |
| "eval_samples_per_second": 57.433, | |
| "eval_steps_per_second": 1.795, | |
| "step": 598000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.0759213065326633e-06, | |
| "loss": 1.839, | |
| "step": 599000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.6040674448013306, | |
| "eval_runtime": 1411.8985, | |
| "eval_samples_per_second": 55.767, | |
| "eval_steps_per_second": 1.743, | |
| "step": 599000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.0709966834170855e-06, | |
| "loss": 1.8401, | |
| "step": 600000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.5981929302215576, | |
| "eval_runtime": 1370.3726, | |
| "eval_samples_per_second": 57.457, | |
| "eval_steps_per_second": 1.796, | |
| "step": 600000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.066072060301508e-06, | |
| "loss": 1.8327, | |
| "step": 601000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.607890009880066, | |
| "eval_runtime": 1378.4994, | |
| "eval_samples_per_second": 57.118, | |
| "eval_steps_per_second": 1.785, | |
| "step": 601000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.061152361809045e-06, | |
| "loss": 1.8361, | |
| "step": 602000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.606207013130188, | |
| "eval_runtime": 1418.921, | |
| "eval_samples_per_second": 55.491, | |
| "eval_steps_per_second": 1.734, | |
| "step": 602000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.0562277386934675e-06, | |
| "loss": 1.8387, | |
| "step": 603000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.5986562967300415, | |
| "eval_runtime": 1440.6978, | |
| "eval_samples_per_second": 54.652, | |
| "eval_steps_per_second": 1.708, | |
| "step": 603000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.0513031155778896e-06, | |
| "loss": 1.8336, | |
| "step": 604000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.599565863609314, | |
| "eval_runtime": 1366.4669, | |
| "eval_samples_per_second": 57.621, | |
| "eval_steps_per_second": 1.801, | |
| "step": 604000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.0463784924623118e-06, | |
| "loss": 1.8457, | |
| "step": 605000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.6037099361419678, | |
| "eval_runtime": 1374.6709, | |
| "eval_samples_per_second": 57.277, | |
| "eval_steps_per_second": 1.79, | |
| "step": 605000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.0414587939698495e-06, | |
| "loss": 1.8418, | |
| "step": 606000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.596120834350586, | |
| "eval_runtime": 1313.4049, | |
| "eval_samples_per_second": 59.949, | |
| "eval_steps_per_second": 1.874, | |
| "step": 606000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.0365390954773873e-06, | |
| "loss": 1.8334, | |
| "step": 607000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.598099946975708, | |
| "eval_runtime": 1348.2663, | |
| "eval_samples_per_second": 58.399, | |
| "eval_steps_per_second": 1.825, | |
| "step": 607000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.031614472361809e-06, | |
| "loss": 1.8376, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.6052206754684448, | |
| "eval_runtime": 1454.3089, | |
| "eval_samples_per_second": 54.14, | |
| "eval_steps_per_second": 1.692, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.026689849246231e-06, | |
| "loss": 1.8387, | |
| "step": 609000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.5904994010925293, | |
| "eval_runtime": 1429.466, | |
| "eval_samples_per_second": 55.081, | |
| "eval_steps_per_second": 1.722, | |
| "step": 609000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.0217652261306533e-06, | |
| "loss": 1.829, | |
| "step": 610000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.6081486940383911, | |
| "eval_runtime": 1346.6097, | |
| "eval_samples_per_second": 58.471, | |
| "eval_steps_per_second": 1.828, | |
| "step": 610000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.016840603015076e-06, | |
| "loss": 1.8329, | |
| "step": 611000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.6047282218933105, | |
| "eval_runtime": 1326.3086, | |
| "eval_samples_per_second": 59.366, | |
| "eval_steps_per_second": 1.856, | |
| "step": 611000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.0119159798994975e-06, | |
| "loss": 1.8415, | |
| "step": 612000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.6007598638534546, | |
| "eval_runtime": 1302.4192, | |
| "eval_samples_per_second": 60.454, | |
| "eval_steps_per_second": 1.89, | |
| "step": 612000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.0069962814070357e-06, | |
| "loss": 1.8287, | |
| "step": 613000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.6105679273605347, | |
| "eval_runtime": 1347.332, | |
| "eval_samples_per_second": 58.439, | |
| "eval_steps_per_second": 1.827, | |
| "step": 613000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.0020716582914574e-06, | |
| "loss": 1.8327, | |
| "step": 614000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.607060194015503, | |
| "eval_runtime": 1305.8265, | |
| "eval_samples_per_second": 60.297, | |
| "eval_steps_per_second": 1.885, | |
| "step": 614000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.9971470351758796e-06, | |
| "loss": 1.8366, | |
| "step": 615000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.6026506423950195, | |
| "eval_runtime": 1335.1184, | |
| "eval_samples_per_second": 58.974, | |
| "eval_steps_per_second": 1.843, | |
| "step": 615000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.9922322613065325e-06, | |
| "loss": 1.8467, | |
| "step": 616000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.6091498136520386, | |
| "eval_runtime": 1322.5487, | |
| "eval_samples_per_second": 59.534, | |
| "eval_steps_per_second": 1.861, | |
| "step": 616000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.9873125628140703e-06, | |
| "loss": 1.8222, | |
| "step": 617000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.6029044389724731, | |
| "eval_runtime": 1467.5465, | |
| "eval_samples_per_second": 53.652, | |
| "eval_steps_per_second": 1.677, | |
| "step": 617000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.982387939698493e-06, | |
| "loss": 1.833, | |
| "step": 618000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.6027536392211914, | |
| "eval_runtime": 1350.4841, | |
| "eval_samples_per_second": 58.303, | |
| "eval_steps_per_second": 1.822, | |
| "step": 618000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.977463316582915e-06, | |
| "loss": 1.8324, | |
| "step": 619000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.5961847305297852, | |
| "eval_runtime": 1301.7193, | |
| "eval_samples_per_second": 60.487, | |
| "eval_steps_per_second": 1.891, | |
| "step": 619000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.9725386934673367e-06, | |
| "loss": 1.8227, | |
| "step": 620000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.5996179580688477, | |
| "eval_runtime": 1340.0152, | |
| "eval_samples_per_second": 58.758, | |
| "eval_steps_per_second": 1.837, | |
| "step": 620000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.967614070351759e-06, | |
| "loss": 1.8286, | |
| "step": 621000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.598938226699829, | |
| "eval_runtime": 1445.9352, | |
| "eval_samples_per_second": 54.454, | |
| "eval_steps_per_second": 1.702, | |
| "step": 621000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.962689447236181e-06, | |
| "loss": 1.8252, | |
| "step": 622000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.6006757020950317, | |
| "eval_runtime": 1407.7995, | |
| "eval_samples_per_second": 55.929, | |
| "eval_steps_per_second": 1.748, | |
| "step": 622000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.9577648241206035e-06, | |
| "loss": 1.8317, | |
| "step": 623000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.5989092588424683, | |
| "eval_runtime": 1327.983, | |
| "eval_samples_per_second": 59.291, | |
| "eval_steps_per_second": 1.853, | |
| "step": 623000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.952854974874372e-06, | |
| "loss": 1.8389, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.602870225906372, | |
| "eval_runtime": 1383.3273, | |
| "eval_samples_per_second": 56.919, | |
| "eval_steps_per_second": 1.779, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.9479303517587942e-06, | |
| "loss": 1.8345, | |
| "step": 625000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.6017168760299683, | |
| "eval_runtime": 1446.0375, | |
| "eval_samples_per_second": 54.45, | |
| "eval_steps_per_second": 1.702, | |
| "step": 625000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.9430057286432164e-06, | |
| "loss": 1.8345, | |
| "step": 626000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.5972059965133667, | |
| "eval_runtime": 1349.1112, | |
| "eval_samples_per_second": 58.362, | |
| "eval_steps_per_second": 1.824, | |
| "step": 626000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.938081105527638e-06, | |
| "loss": 1.8314, | |
| "step": 627000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.59882390499115, | |
| "eval_runtime": 1362.0292, | |
| "eval_samples_per_second": 57.809, | |
| "eval_steps_per_second": 1.807, | |
| "step": 627000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.9331564824120606e-06, | |
| "loss": 1.8314, | |
| "step": 628000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.5979121923446655, | |
| "eval_runtime": 1463.5496, | |
| "eval_samples_per_second": 53.799, | |
| "eval_steps_per_second": 1.682, | |
| "step": 628000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.9282318592964828e-06, | |
| "loss": 1.8395, | |
| "step": 629000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.601837158203125, | |
| "eval_runtime": 1388.4972, | |
| "eval_samples_per_second": 56.707, | |
| "eval_steps_per_second": 1.772, | |
| "step": 629000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.9233121608040205e-06, | |
| "loss": 1.8279, | |
| "step": 630000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.5932117700576782, | |
| "eval_runtime": 1304.0965, | |
| "eval_samples_per_second": 60.377, | |
| "eval_steps_per_second": 1.887, | |
| "step": 630000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.9183875376884427e-06, | |
| "loss": 1.8349, | |
| "step": 631000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.60895574092865, | |
| "eval_runtime": 1312.317, | |
| "eval_samples_per_second": 59.998, | |
| "eval_steps_per_second": 1.875, | |
| "step": 631000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.9134629145728644e-06, | |
| "loss": 1.838, | |
| "step": 632000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.6004664897918701, | |
| "eval_runtime": 1437.6414, | |
| "eval_samples_per_second": 54.768, | |
| "eval_steps_per_second": 1.712, | |
| "step": 632000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.9085382914572865e-06, | |
| "loss": 1.8316, | |
| "step": 633000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.599939227104187, | |
| "eval_runtime": 1452.9057, | |
| "eval_samples_per_second": 54.193, | |
| "eval_steps_per_second": 1.694, | |
| "step": 633000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.90362351758794e-06, | |
| "loss": 1.832, | |
| "step": 634000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.5970202684402466, | |
| "eval_runtime": 1303.8096, | |
| "eval_samples_per_second": 60.39, | |
| "eval_steps_per_second": 1.888, | |
| "step": 634000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.898698894472362e-06, | |
| "loss": 1.8472, | |
| "step": 635000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.5940812826156616, | |
| "eval_runtime": 1337.4473, | |
| "eval_samples_per_second": 58.871, | |
| "eval_steps_per_second": 1.84, | |
| "step": 635000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.8937742713567842e-06, | |
| "loss": 1.8398, | |
| "step": 636000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.5929611921310425, | |
| "eval_runtime": 1328.097, | |
| "eval_samples_per_second": 59.286, | |
| "eval_steps_per_second": 1.853, | |
| "step": 636000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.8888496482412059e-06, | |
| "loss": 1.8337, | |
| "step": 637000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.5947929620742798, | |
| "eval_runtime": 1389.3994, | |
| "eval_samples_per_second": 56.67, | |
| "eval_steps_per_second": 1.771, | |
| "step": 637000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.8839299497487437e-06, | |
| "loss": 1.8344, | |
| "step": 638000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.593649983406067, | |
| "eval_runtime": 1395.5343, | |
| "eval_samples_per_second": 56.421, | |
| "eval_steps_per_second": 1.763, | |
| "step": 638000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.8790053266331656e-06, | |
| "loss": 1.8294, | |
| "step": 639000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.5959663391113281, | |
| "eval_runtime": 1347.3949, | |
| "eval_samples_per_second": 58.436, | |
| "eval_steps_per_second": 1.826, | |
| "step": 639000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.8740807035175883e-06, | |
| "loss": 1.8142, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.5931050777435303, | |
| "eval_runtime": 1396.136, | |
| "eval_samples_per_second": 56.396, | |
| "eval_steps_per_second": 1.763, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.8691560804020103e-06, | |
| "loss": 1.8267, | |
| "step": 641000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.5900132656097412, | |
| "eval_runtime": 1363.8371, | |
| "eval_samples_per_second": 57.732, | |
| "eval_steps_per_second": 1.804, | |
| "step": 641000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.8642314572864322e-06, | |
| "loss": 1.8277, | |
| "step": 642000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.598568320274353, | |
| "eval_runtime": 1470.956, | |
| "eval_samples_per_second": 53.528, | |
| "eval_steps_per_second": 1.673, | |
| "step": 642000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.85931175879397e-06, | |
| "loss": 1.817, | |
| "step": 643000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.5886738300323486, | |
| "eval_runtime": 1396.8317, | |
| "eval_samples_per_second": 56.368, | |
| "eval_steps_per_second": 1.762, | |
| "step": 643000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.854387135678392e-06, | |
| "loss": 1.8217, | |
| "step": 644000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.5907179117202759, | |
| "eval_runtime": 1416.7398, | |
| "eval_samples_per_second": 55.576, | |
| "eval_steps_per_second": 1.737, | |
| "step": 644000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.8494674371859298e-06, | |
| "loss": 1.8254, | |
| "step": 645000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.6016545295715332, | |
| "eval_runtime": 1459.5293, | |
| "eval_samples_per_second": 53.947, | |
| "eval_steps_per_second": 1.686, | |
| "step": 645000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.844542814070352e-06, | |
| "loss": 1.8257, | |
| "step": 646000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.6024249792099, | |
| "eval_runtime": 1378.9773, | |
| "eval_samples_per_second": 57.098, | |
| "eval_steps_per_second": 1.785, | |
| "step": 646000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.83962311557789e-06, | |
| "loss": 1.83, | |
| "step": 647000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.6028681993484497, | |
| "eval_runtime": 1452.3606, | |
| "eval_samples_per_second": 54.213, | |
| "eval_steps_per_second": 1.694, | |
| "step": 647000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.8347034170854275e-06, | |
| "loss": 1.8204, | |
| "step": 648000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.599324345588684, | |
| "eval_runtime": 1463.7748, | |
| "eval_samples_per_second": 53.79, | |
| "eval_steps_per_second": 1.681, | |
| "step": 648000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.8297787939698492e-06, | |
| "loss": 1.8234, | |
| "step": 649000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.5928692817687988, | |
| "eval_runtime": 1330.8025, | |
| "eval_samples_per_second": 59.165, | |
| "eval_steps_per_second": 1.849, | |
| "step": 649000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.8248590954773874e-06, | |
| "loss": 1.834, | |
| "step": 650000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.5874714851379395, | |
| "eval_runtime": 1348.2089, | |
| "eval_samples_per_second": 58.401, | |
| "eval_steps_per_second": 1.825, | |
| "step": 650000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.8199344723618089e-06, | |
| "loss": 1.8159, | |
| "step": 651000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.5897165536880493, | |
| "eval_runtime": 1380.8115, | |
| "eval_samples_per_second": 57.022, | |
| "eval_steps_per_second": 1.782, | |
| "step": 651000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.8150098492462312e-06, | |
| "loss": 1.8282, | |
| "step": 652000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.5937752723693848, | |
| "eval_runtime": 1430.1609, | |
| "eval_samples_per_second": 55.055, | |
| "eval_steps_per_second": 1.721, | |
| "step": 652000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.8100852261306536e-06, | |
| "loss": 1.8179, | |
| "step": 653000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.5979640483856201, | |
| "eval_runtime": 1317.4556, | |
| "eval_samples_per_second": 59.764, | |
| "eval_steps_per_second": 1.868, | |
| "step": 653000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.805165527638191e-06, | |
| "loss": 1.8235, | |
| "step": 654000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.596608281135559, | |
| "eval_runtime": 1413.1903, | |
| "eval_samples_per_second": 55.716, | |
| "eval_steps_per_second": 1.741, | |
| "step": 654000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.8002409045226133e-06, | |
| "loss": 1.8264, | |
| "step": 655000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.5875301361083984, | |
| "eval_runtime": 1474.9742, | |
| "eval_samples_per_second": 53.382, | |
| "eval_steps_per_second": 1.669, | |
| "step": 655000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.7953212060301506e-06, | |
| "loss": 1.8279, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.5822259187698364, | |
| "eval_runtime": 1434.0813, | |
| "eval_samples_per_second": 54.904, | |
| "eval_steps_per_second": 1.716, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.7903965829145732e-06, | |
| "loss": 1.8275, | |
| "step": 657000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.5921976566314697, | |
| "eval_runtime": 1303.7483, | |
| "eval_samples_per_second": 60.393, | |
| "eval_steps_per_second": 1.888, | |
| "step": 657000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.7854719597989953e-06, | |
| "loss": 1.8201, | |
| "step": 658000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.5922507047653198, | |
| "eval_runtime": 1451.3783, | |
| "eval_samples_per_second": 54.25, | |
| "eval_steps_per_second": 1.696, | |
| "step": 658000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.7805522613065333e-06, | |
| "loss": 1.8343, | |
| "step": 659000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.5992974042892456, | |
| "eval_runtime": 1312.6672, | |
| "eval_samples_per_second": 59.982, | |
| "eval_steps_per_second": 1.875, | |
| "step": 659000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.7756276381909552e-06, | |
| "loss": 1.8252, | |
| "step": 660000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.5954718589782715, | |
| "eval_runtime": 1329.4403, | |
| "eval_samples_per_second": 59.226, | |
| "eval_steps_per_second": 1.851, | |
| "step": 660000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.7707030150753767e-06, | |
| "loss": 1.8247, | |
| "step": 661000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.5888080596923828, | |
| "eval_runtime": 1470.1668, | |
| "eval_samples_per_second": 53.557, | |
| "eval_steps_per_second": 1.674, | |
| "step": 661000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.765778391959799e-06, | |
| "loss": 1.8241, | |
| "step": 662000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.5860859155654907, | |
| "eval_runtime": 1332.2427, | |
| "eval_samples_per_second": 59.101, | |
| "eval_steps_per_second": 1.847, | |
| "step": 662000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.7608537688442214e-06, | |
| "loss": 1.8299, | |
| "step": 663000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.592593789100647, | |
| "eval_runtime": 1407.4541, | |
| "eval_samples_per_second": 55.943, | |
| "eval_steps_per_second": 1.749, | |
| "step": 663000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.755934070351759e-06, | |
| "loss": 1.8337, | |
| "step": 664000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.5933688879013062, | |
| "eval_runtime": 1320.4107, | |
| "eval_samples_per_second": 59.631, | |
| "eval_steps_per_second": 1.864, | |
| "step": 664000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.751009447236181e-06, | |
| "loss": 1.8244, | |
| "step": 665000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.599759817123413, | |
| "eval_runtime": 1322.9928, | |
| "eval_samples_per_second": 59.514, | |
| "eval_steps_per_second": 1.86, | |
| "step": 665000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.7460897487437184e-06, | |
| "loss": 1.8275, | |
| "step": 666000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.5976141691207886, | |
| "eval_runtime": 1363.02, | |
| "eval_samples_per_second": 57.767, | |
| "eval_steps_per_second": 1.806, | |
| "step": 666000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.7411700502512564e-06, | |
| "loss": 1.8287, | |
| "step": 667000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.579295039176941, | |
| "eval_runtime": 1381.0984, | |
| "eval_samples_per_second": 57.01, | |
| "eval_steps_per_second": 1.782, | |
| "step": 667000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.7362454271356783e-06, | |
| "loss": 1.8293, | |
| "step": 668000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.5919257402420044, | |
| "eval_runtime": 1393.4561, | |
| "eval_samples_per_second": 56.505, | |
| "eval_steps_per_second": 1.766, | |
| "step": 668000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.7313208040201006e-06, | |
| "loss": 1.8171, | |
| "step": 669000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.5862181186676025, | |
| "eval_runtime": 1394.7193, | |
| "eval_samples_per_second": 56.454, | |
| "eval_steps_per_second": 1.765, | |
| "step": 669000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.726396180904523e-06, | |
| "loss": 1.8196, | |
| "step": 670000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.6017342805862427, | |
| "eval_runtime": 1385.2253, | |
| "eval_samples_per_second": 56.841, | |
| "eval_steps_per_second": 1.777, | |
| "step": 670000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.7214715577889445e-06, | |
| "loss": 1.8256, | |
| "step": 671000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.6013214588165283, | |
| "eval_runtime": 1435.0073, | |
| "eval_samples_per_second": 54.869, | |
| "eval_steps_per_second": 1.715, | |
| "step": 671000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.7165567839195985e-06, | |
| "loss": 1.8294, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.5915107727050781, | |
| "eval_runtime": 1381.2373, | |
| "eval_samples_per_second": 57.005, | |
| "eval_steps_per_second": 1.782, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.71163216080402e-06, | |
| "loss": 1.8299, | |
| "step": 673000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.5885646343231201, | |
| "eval_runtime": 1495.9255, | |
| "eval_samples_per_second": 52.634, | |
| "eval_steps_per_second": 1.645, | |
| "step": 673000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.7067075376884424e-06, | |
| "loss": 1.8264, | |
| "step": 674000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.5896543264389038, | |
| "eval_runtime": 1438.4722, | |
| "eval_samples_per_second": 54.737, | |
| "eval_steps_per_second": 1.711, | |
| "step": 674000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.7017878391959803e-06, | |
| "loss": 1.8256, | |
| "step": 675000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.5811702013015747, | |
| "eval_runtime": 1475.0011, | |
| "eval_samples_per_second": 53.381, | |
| "eval_steps_per_second": 1.668, | |
| "step": 675000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.6968632160804023e-06, | |
| "loss": 1.8179, | |
| "step": 676000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.5885577201843262, | |
| "eval_runtime": 1330.732, | |
| "eval_samples_per_second": 59.168, | |
| "eval_steps_per_second": 1.849, | |
| "step": 676000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.6919385929648242e-06, | |
| "loss": 1.8288, | |
| "step": 677000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.57944917678833, | |
| "eval_runtime": 1356.8541, | |
| "eval_samples_per_second": 58.029, | |
| "eval_steps_per_second": 1.814, | |
| "step": 677000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.6870139698492465e-06, | |
| "loss": 1.8225, | |
| "step": 678000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.5852633714675903, | |
| "eval_runtime": 1411.1498, | |
| "eval_samples_per_second": 55.796, | |
| "eval_steps_per_second": 1.744, | |
| "step": 678000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.6820893467336684e-06, | |
| "loss": 1.8151, | |
| "step": 679000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.6006282567977905, | |
| "eval_runtime": 1433.5991, | |
| "eval_samples_per_second": 54.923, | |
| "eval_steps_per_second": 1.717, | |
| "step": 679000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.6771696482412064e-06, | |
| "loss": 1.8326, | |
| "step": 680000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.5857617855072021, | |
| "eval_runtime": 1370.4186, | |
| "eval_samples_per_second": 57.455, | |
| "eval_steps_per_second": 1.796, | |
| "step": 680000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.6722450251256286e-06, | |
| "loss": 1.8248, | |
| "step": 681000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.5932334661483765, | |
| "eval_runtime": 1475.8822, | |
| "eval_samples_per_second": 53.349, | |
| "eval_steps_per_second": 1.667, | |
| "step": 681000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.6673204020100503e-06, | |
| "loss": 1.8206, | |
| "step": 682000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.5989573001861572, | |
| "eval_runtime": 1449.7957, | |
| "eval_samples_per_second": 54.309, | |
| "eval_steps_per_second": 1.697, | |
| "step": 682000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.662400703517588e-06, | |
| "loss": 1.8309, | |
| "step": 683000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.59175705909729, | |
| "eval_runtime": 1380.8863, | |
| "eval_samples_per_second": 57.019, | |
| "eval_steps_per_second": 1.782, | |
| "step": 683000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.6574760804020102e-06, | |
| "loss": 1.8219, | |
| "step": 684000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.5923930406570435, | |
| "eval_runtime": 1358.5234, | |
| "eval_samples_per_second": 57.958, | |
| "eval_steps_per_second": 1.812, | |
| "step": 684000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.6525563819095481e-06, | |
| "loss": 1.8155, | |
| "step": 685000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.5951777696609497, | |
| "eval_runtime": 1366.1742, | |
| "eval_samples_per_second": 57.633, | |
| "eval_steps_per_second": 1.801, | |
| "step": 685000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.64763175879397e-06, | |
| "loss": 1.8192, | |
| "step": 686000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.5806286334991455, | |
| "eval_runtime": 1380.6238, | |
| "eval_samples_per_second": 57.03, | |
| "eval_steps_per_second": 1.783, | |
| "step": 686000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.6427071356783916e-06, | |
| "loss": 1.8175, | |
| "step": 687000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.587588906288147, | |
| "eval_runtime": 1441.4618, | |
| "eval_samples_per_second": 54.623, | |
| "eval_steps_per_second": 1.707, | |
| "step": 687000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.6377825125628143e-06, | |
| "loss": 1.8198, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.5877431631088257, | |
| "eval_runtime": 1325.2917, | |
| "eval_samples_per_second": 59.411, | |
| "eval_steps_per_second": 1.857, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.6328578894472362e-06, | |
| "loss": 1.8172, | |
| "step": 689000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.5791815519332886, | |
| "eval_runtime": 1344.8655, | |
| "eval_samples_per_second": 58.546, | |
| "eval_steps_per_second": 1.83, | |
| "step": 689000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.6279381909547742e-06, | |
| "loss": 1.8135, | |
| "step": 690000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.591376543045044, | |
| "eval_runtime": 1410.6096, | |
| "eval_samples_per_second": 55.818, | |
| "eval_steps_per_second": 1.745, | |
| "step": 690000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.6230135678391964e-06, | |
| "loss": 1.824, | |
| "step": 691000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.584437370300293, | |
| "eval_runtime": 1318.433, | |
| "eval_samples_per_second": 59.72, | |
| "eval_steps_per_second": 1.867, | |
| "step": 691000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.6180938693467341e-06, | |
| "loss": 1.8146, | |
| "step": 692000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.5931404829025269, | |
| "eval_runtime": 1360.7166, | |
| "eval_samples_per_second": 57.864, | |
| "eval_steps_per_second": 1.809, | |
| "step": 692000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.6131692462311558e-06, | |
| "loss": 1.8215, | |
| "step": 693000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.5878210067749023, | |
| "eval_runtime": 1361.6065, | |
| "eval_samples_per_second": 57.827, | |
| "eval_steps_per_second": 1.807, | |
| "step": 693000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.608244623115578e-06, | |
| "loss": 1.8125, | |
| "step": 694000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.5885907411575317, | |
| "eval_runtime": 1346.9108, | |
| "eval_samples_per_second": 58.457, | |
| "eval_steps_per_second": 1.827, | |
| "step": 694000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.603324924623116e-06, | |
| "loss": 1.8284, | |
| "step": 695000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.579284906387329, | |
| "eval_runtime": 1419.5492, | |
| "eval_samples_per_second": 55.466, | |
| "eval_steps_per_second": 1.734, | |
| "step": 695000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.5984003015075379e-06, | |
| "loss": 1.8155, | |
| "step": 696000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.590699553489685, | |
| "eval_runtime": 1311.3869, | |
| "eval_samples_per_second": 60.041, | |
| "eval_steps_per_second": 1.877, | |
| "step": 696000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.5934855276381908e-06, | |
| "loss": 1.8215, | |
| "step": 697000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 1.5784730911254883, | |
| "eval_runtime": 1345.5637, | |
| "eval_samples_per_second": 58.516, | |
| "eval_steps_per_second": 1.829, | |
| "step": 697000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.5885609045226134e-06, | |
| "loss": 1.8356, | |
| "step": 698000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 1.5905190706253052, | |
| "eval_runtime": 1329.0593, | |
| "eval_samples_per_second": 59.243, | |
| "eval_steps_per_second": 1.852, | |
| "step": 698000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.5836362814070355e-06, | |
| "loss": 1.8121, | |
| "step": 699000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 1.5879490375518799, | |
| "eval_runtime": 1353.1981, | |
| "eval_samples_per_second": 58.186, | |
| "eval_steps_per_second": 1.819, | |
| "step": 699000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.5787116582914572e-06, | |
| "loss": 1.8282, | |
| "step": 700000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 1.589970350265503, | |
| "eval_runtime": 1320.5704, | |
| "eval_samples_per_second": 59.623, | |
| "eval_steps_per_second": 1.864, | |
| "step": 700000 | |
| } | |
| ], | |
| "max_steps": 1000000, | |
| "num_train_epochs": 2, | |
| "total_flos": 1.6795290993650842e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |