| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 372000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3.125e-05, | |
| "loss": 6.2338, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 6.25e-05, | |
| "loss": 5.0105, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.375e-05, | |
| "loss": 4.6777, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.000125, | |
| "loss": 4.4581, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00015625, | |
| "loss": 4.2898, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001875, | |
| "loss": 4.1756, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00021875, | |
| "loss": 4.0724, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00025, | |
| "loss": 3.9803, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00028125000000000003, | |
| "loss": 3.9012, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0003125, | |
| "loss": 3.843, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00034368749999999997, | |
| "loss": 3.7953, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0003749375, | |
| "loss": 3.7587, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00040615625, | |
| "loss": 3.7178, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00043740625, | |
| "loss": 3.6927, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.000468625, | |
| "loss": 3.6634, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.000499875, | |
| "loss": 3.6388, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00053109375, | |
| "loss": 3.6183, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00056234375, | |
| "loss": 3.6013, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.3598086413059763, | |
| "eval_loss": 3.7572503089904785, | |
| "eval_runtime": 152.1013, | |
| "eval_samples_per_second": 380.786, | |
| "eval_steps_per_second": 5.95, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0005935625, | |
| "loss": 3.5663, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0006248125, | |
| "loss": 3.5444, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0006560625, | |
| "loss": 3.5357, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00068728125, | |
| "loss": 3.5202, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00071853125, | |
| "loss": 3.5085, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00074978125, | |
| "loss": 3.4996, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.000781, | |
| "loss": 3.4913, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00081225, | |
| "loss": 3.4877, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00084346875, | |
| "loss": 3.471, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0008746874999999999, | |
| "loss": 3.4621, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0009059375, | |
| "loss": 3.4592, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0009371875, | |
| "loss": 3.4485, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0009684062500000001, | |
| "loss": 3.4352, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0009996562500000001, | |
| "loss": 3.4331, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0009970911764705882, | |
| "loss": 3.4186, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0009941529411764706, | |
| "loss": 3.4146, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0009912117647058825, | |
| "loss": 3.3994, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.000988270588235294, | |
| "loss": 3.3879, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0009853323529411765, | |
| "loss": 3.3813, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.38050911371678975, | |
| "eval_loss": 3.568835973739624, | |
| "eval_runtime": 153.3703, | |
| "eval_samples_per_second": 377.635, | |
| "eval_steps_per_second": 5.901, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0009823911764705884, | |
| "loss": 3.333, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00097945, | |
| "loss": 3.3214, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0009765088235294118, | |
| "loss": 3.3175, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0009735705882352941, | |
| "loss": 3.3143, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0009706294117647059, | |
| "loss": 3.3106, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.0009676911764705883, | |
| "loss": 3.3026, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.00096475, | |
| "loss": 3.3039, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.0009618088235294117, | |
| "loss": 3.2946, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.0009588705882352941, | |
| "loss": 3.2936, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0009559294117647059, | |
| "loss": 3.2887, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0009529911764705883, | |
| "loss": 3.2852, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.0009500499999999999, | |
| "loss": 3.2788, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0009471088235294118, | |
| "loss": 3.272, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.0009441676470588235, | |
| "loss": 3.2677, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0009412294117647059, | |
| "loss": 3.2678, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0009382882352941176, | |
| "loss": 3.2596, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.0009353470588235295, | |
| "loss": 3.2587, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.0009324088235294118, | |
| "loss": 3.2541, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3921681572350444, | |
| "eval_loss": 3.4489290714263916, | |
| "eval_runtime": 153.3343, | |
| "eval_samples_per_second": 377.724, | |
| "eval_steps_per_second": 5.902, | |
| "step": 55800 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.0009294676470588236, | |
| "loss": 3.2395, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.0009265294117647059, | |
| "loss": 3.1852, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.0009235882352941177, | |
| "loss": 3.1889, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.00092065, | |
| "loss": 3.1939, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.0009177088235294118, | |
| "loss": 3.1919, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.0009147676470588235, | |
| "loss": 3.1922, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.000911829411764706, | |
| "loss": 3.1904, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.0009088882352941177, | |
| "loss": 3.1884, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.0009059470588235294, | |
| "loss": 3.1901, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.0009030088235294118, | |
| "loss": 3.1882, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 0.0009000676470588236, | |
| "loss": 3.1883, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.0008971294117647059, | |
| "loss": 3.1849, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 0.0008941882352941176, | |
| "loss": 3.1812, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.0008912470588235294, | |
| "loss": 3.1793, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.0008883088235294117, | |
| "loss": 3.1826, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.0008853676470588236, | |
| "loss": 3.1801, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.0008824294117647059, | |
| "loss": 3.1776, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 0.0008794882352941177, | |
| "loss": 3.1748, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.00087655, | |
| "loss": 3.174, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3980487373601992, | |
| "eval_loss": 3.4157938957214355, | |
| "eval_runtime": 153.3125, | |
| "eval_samples_per_second": 377.777, | |
| "eval_steps_per_second": 5.903, | |
| "step": 74400 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.0008736117647058823, | |
| "loss": 3.1295, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.0008706705882352941, | |
| "loss": 3.105, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.0008677294117647059, | |
| "loss": 3.1165, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 0.0008647911764705882, | |
| "loss": 3.1173, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 0.00086185, | |
| "loss": 3.1218, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.0008589088235294118, | |
| "loss": 3.1184, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 0.0008559705882352942, | |
| "loss": 3.1184, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.0008530294117647059, | |
| "loss": 3.1218, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 0.0008500882352941177, | |
| "loss": 3.1196, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 0.0008471470588235294, | |
| "loss": 3.1223, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.0008442088235294117, | |
| "loss": 3.1211, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.0008412676470588235, | |
| "loss": 3.1229, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.0008383294117647058, | |
| "loss": 3.1174, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.0008353882352941177, | |
| "loss": 3.1202, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 0.0008324470588235294, | |
| "loss": 3.119, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 0.0008295058823529413, | |
| "loss": 3.1187, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.000826564705882353, | |
| "loss": 3.1212, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.0008236235294117648, | |
| "loss": 3.1204, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0008206882352941176, | |
| "loss": 3.1166, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.40280018859348043, | |
| "eval_loss": 3.376669406890869, | |
| "eval_runtime": 153.1553, | |
| "eval_samples_per_second": 378.165, | |
| "eval_steps_per_second": 5.909, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.0008177470588235295, | |
| "loss": 3.0425, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.0008148058823529412, | |
| "loss": 3.0587, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 0.0008118676470588236, | |
| "loss": 3.0598, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.0008089264705882353, | |
| "loss": 3.0659, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 0.0008059852941176471, | |
| "loss": 3.0633, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 0.0008030441176470589, | |
| "loss": 3.0673, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 0.0008001058823529412, | |
| "loss": 3.0679, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.000797164705882353, | |
| "loss": 3.0717, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 0.0007942264705882352, | |
| "loss": 3.0709, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 0.0007912852941176471, | |
| "loss": 3.0727, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 0.0007883470588235294, | |
| "loss": 3.075, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 0.0007854058823529412, | |
| "loss": 3.075, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.0007824676470588235, | |
| "loss": 3.0717, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 0.0007795264705882354, | |
| "loss": 3.0765, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 0.0007765882352941177, | |
| "loss": 3.0704, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 0.0007736470588235295, | |
| "loss": 3.0737, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 0.0007707058823529411, | |
| "loss": 3.075, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 0.0007677676470588236, | |
| "loss": 3.0777, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.40363969562226915, | |
| "eval_loss": 3.3729135990142822, | |
| "eval_runtime": 153.3723, | |
| "eval_samples_per_second": 377.63, | |
| "eval_steps_per_second": 5.901, | |
| "step": 111600 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 0.0007648264705882353, | |
| "loss": 3.047, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 0.0007618882352941177, | |
| "loss": 3.0073, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 0.0007589470588235294, | |
| "loss": 3.0136, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 0.0007560058823529412, | |
| "loss": 3.0185, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 0.000753064705882353, | |
| "loss": 3.0199, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 0.000750129411764706, | |
| "loss": 3.0238, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 0.0007471882352941176, | |
| "loss": 3.0277, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.0007442470588235293, | |
| "loss": 3.0306, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 0.0007413058823529412, | |
| "loss": 3.0287, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 0.0007383647058823529, | |
| "loss": 3.0362, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 0.0007354235294117647, | |
| "loss": 3.0349, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 0.0007324852941176471, | |
| "loss": 3.033, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.0007295441176470588, | |
| "loss": 3.0312, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 0.0007266029411764707, | |
| "loss": 3.0349, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 0.000723664705882353, | |
| "loss": 3.0387, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 0.0007207235294117647, | |
| "loss": 3.0442, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 0.0007177823529411764, | |
| "loss": 3.0378, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 0.0007148441176470588, | |
| "loss": 3.0379, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 0.0007119029411764706, | |
| "loss": 3.0372, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.4071418964393911, | |
| "eval_loss": 3.346435308456421, | |
| "eval_runtime": 153.3224, | |
| "eval_samples_per_second": 377.753, | |
| "eval_steps_per_second": 5.903, | |
| "step": 130200 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 0.000708964705882353, | |
| "loss": 2.9848, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 0.0007060235294117647, | |
| "loss": 2.9689, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 0.0007030823529411766, | |
| "loss": 2.9787, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 0.0007001411764705883, | |
| "loss": 2.9855, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 0.0006972029411764707, | |
| "loss": 2.9867, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 0.0006942647058823529, | |
| "loss": 2.9893, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 0.0006913235294117647, | |
| "loss": 2.9943, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 0.0006883823529411765, | |
| "loss": 2.995, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 0.0006854470588235294, | |
| "loss": 3.001, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 0.0006825058823529412, | |
| "loss": 3.0026, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 0.000679564705882353, | |
| "loss": 2.9996, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 0.0006766235294117648, | |
| "loss": 3.0003, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.0006736823529411765, | |
| "loss": 3.0031, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 0.0006707441176470588, | |
| "loss": 3.0056, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 0.0006678058823529412, | |
| "loss": 3.0048, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 0.0006648647058823529, | |
| "loss": 3.0047, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 0.0006619235294117647, | |
| "loss": 3.0095, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 0.0006589823529411765, | |
| "loss": 3.0083, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4081011890821627, | |
| "eval_loss": 3.350280523300171, | |
| "eval_runtime": 153.4302, | |
| "eval_samples_per_second": 377.488, | |
| "eval_steps_per_second": 5.898, | |
| "step": 148800 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.0006560441176470588, | |
| "loss": 2.9882, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 0.0006531029411764707, | |
| "loss": 2.9395, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 0.000650164705882353, | |
| "loss": 2.9446, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "learning_rate": 0.0006472235294117648, | |
| "loss": 2.9537, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 0.0006442823529411764, | |
| "loss": 2.9581, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 0.0006413441176470588, | |
| "loss": 2.9604, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 0.0006384029411764706, | |
| "loss": 2.9627, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 0.0006354617647058823, | |
| "loss": 2.9662, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 0.0006325235294117647, | |
| "loss": 2.9658, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 0.0006295823529411765, | |
| "loss": 2.9663, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 0.0006266441176470589, | |
| "loss": 2.9685, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 0.0006237029411764706, | |
| "loss": 2.9764, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 0.000620764705882353, | |
| "loss": 2.9716, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 0.0006178235294117646, | |
| "loss": 2.9724, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 0.000614885294117647, | |
| "loss": 2.9742, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 0.0006119470588235294, | |
| "loss": 2.9805, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 0.0006090058823529412, | |
| "loss": 2.981, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 0.0006060647058823529, | |
| "loss": 2.9788, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 0.0006031235294117648, | |
| "loss": 2.9762, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.4097836294248289, | |
| "eval_loss": 3.3317084312438965, | |
| "eval_runtime": 153.4112, | |
| "eval_samples_per_second": 377.534, | |
| "eval_steps_per_second": 5.899, | |
| "step": 167400 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 0.0006001823529411765, | |
| "loss": 2.9357, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 0.0005972411764705882, | |
| "loss": 2.9207, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 0.0005943029411764705, | |
| "loss": 2.9201, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 0.0005913617647058823, | |
| "loss": 2.9297, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 0.0005884205882352941, | |
| "loss": 2.9281, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 0.0005854823529411765, | |
| "loss": 2.934, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 0.0005825411764705883, | |
| "loss": 2.937, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 0.0005796, | |
| "loss": 2.9399, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 0.0005766617647058824, | |
| "loss": 2.9399, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 0.0005737235294117648, | |
| "loss": 2.9457, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 0.0005707823529411765, | |
| "loss": 2.9457, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.0005678411764705882, | |
| "loss": 2.944, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 0.0005649029411764706, | |
| "loss": 2.9477, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 0.0005619617647058823, | |
| "loss": 2.9473, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 0.0005590205882352942, | |
| "loss": 2.9526, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 0.0005560794117647059, | |
| "loss": 2.9494, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 0.0005531382352941176, | |
| "loss": 2.9512, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 0.0005502, | |
| "loss": 2.9513, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0005472617647058824, | |
| "loss": 2.9515, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.40877818270645083, | |
| "eval_loss": 3.34344220161438, | |
| "eval_runtime": 153.6569, | |
| "eval_samples_per_second": 376.931, | |
| "eval_steps_per_second": 5.89, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 0.0005443205882352942, | |
| "loss": 2.8912, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 0.0005413794117647058, | |
| "loss": 2.8929, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 0.0005384382352941177, | |
| "loss": 2.8995, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 0.0005355, | |
| "loss": 2.9022, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 0.0005325617647058824, | |
| "loss": 2.9064, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 0.0005296205882352941, | |
| "loss": 2.9114, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 0.0005266794117647059, | |
| "loss": 2.9089, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 0.0005237382352941177, | |
| "loss": 2.9157, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 0.0005207970588235294, | |
| "loss": 2.9171, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 10.54, | |
| "learning_rate": 0.0005178588235294118, | |
| "loss": 2.9189, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 10.59, | |
| "learning_rate": 0.0005149176470588234, | |
| "loss": 2.9211, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 0.0005119764705882353, | |
| "loss": 2.9244, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 0.0005090382352941176, | |
| "loss": 2.9241, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 0.0005060970588235294, | |
| "loss": 2.9272, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 0.0005031588235294117, | |
| "loss": 2.9262, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 0.0005002176470588236, | |
| "loss": 2.9245, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 0.0004972794117647059, | |
| "loss": 2.9301, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 0.0004943382352941176, | |
| "loss": 2.9338, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.4101543400350126, | |
| "eval_loss": 3.352632999420166, | |
| "eval_runtime": 153.2552, | |
| "eval_samples_per_second": 377.919, | |
| "eval_steps_per_second": 5.905, | |
| "step": 204600 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 0.0004914, | |
| "loss": 2.9052, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "learning_rate": 0.0004884617647058824, | |
| "loss": 2.8729, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 0.0004855205882352941, | |
| "loss": 2.8713, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 11.18, | |
| "learning_rate": 0.0004825794117647059, | |
| "loss": 2.8818, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 0.00047963823529411764, | |
| "loss": 2.8817, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 0.0004767029411764706, | |
| "loss": 2.8858, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 11.34, | |
| "learning_rate": 0.00047376176470588234, | |
| "loss": 2.8868, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 0.00047082058823529413, | |
| "loss": 2.8926, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 0.00046787941176470587, | |
| "loss": 2.8954, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 0.00046494117647058827, | |
| "loss": 2.8962, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 0.000462, | |
| "loss": 2.9008, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 0.00045906176470588236, | |
| "loss": 2.8967, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 11.67, | |
| "learning_rate": 0.0004561205882352941, | |
| "loss": 2.9005, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 0.0004531794117647059, | |
| "loss": 2.9019, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 11.77, | |
| "learning_rate": 0.00045024411764705885, | |
| "loss": 2.9035, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 11.83, | |
| "learning_rate": 0.0004473029411764706, | |
| "loss": 2.9052, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "learning_rate": 0.0004443617647058824, | |
| "loss": 2.9025, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 0.0004414205882352941, | |
| "loss": 2.9048, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 0.0004384794117647059, | |
| "loss": 2.9063, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4095115420795508, | |
| "eval_loss": 3.3577072620391846, | |
| "eval_runtime": 153.429, | |
| "eval_samples_per_second": 377.491, | |
| "eval_steps_per_second": 5.898, | |
| "step": 223200 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 0.0004355411764705882, | |
| "loss": 2.8611, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 0.0004326029411764706, | |
| "loss": 2.848, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 0.00042966176470588235, | |
| "loss": 2.8595, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 0.00042672058823529414, | |
| "loss": 2.8575, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 0.00042377941176470593, | |
| "loss": 2.8666, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 0.00042084117647058823, | |
| "loss": 2.8673, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 12.37, | |
| "learning_rate": 0.0004179, | |
| "loss": 2.8672, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 0.00041496176470588237, | |
| "loss": 2.8726, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 12.47, | |
| "learning_rate": 0.0004120235294117647, | |
| "loss": 2.8747, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "learning_rate": 0.00040908235294117646, | |
| "loss": 2.8704, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 0.00040614117647058825, | |
| "loss": 2.8813, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 0.0004032, | |
| "loss": 2.8766, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "learning_rate": 0.0004002617647058824, | |
| "loss": 2.8794, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 12.74, | |
| "learning_rate": 0.0003973205882352941, | |
| "loss": 2.8787, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 0.00039437941176470587, | |
| "loss": 2.8828, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 12.85, | |
| "learning_rate": 0.0003914411764705882, | |
| "loss": 2.8818, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 0.0003885, | |
| "loss": 2.8882, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 0.00038556176470588236, | |
| "loss": 2.8871, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.41012236137418484, | |
| "eval_loss": 3.349349021911621, | |
| "eval_runtime": 153.8141, | |
| "eval_samples_per_second": 376.545, | |
| "eval_steps_per_second": 5.884, | |
| "step": 241800 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 0.0003826205882352941, | |
| "loss": 2.8739, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 0.0003796823529411765, | |
| "loss": 2.8261, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 0.00037674117647058824, | |
| "loss": 2.8331, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 13.17, | |
| "learning_rate": 0.00037380294117647065, | |
| "loss": 2.8387, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 0.00037086176470588233, | |
| "loss": 2.8441, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 0.00036792352941176473, | |
| "loss": 2.8441, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 0.00036498235294117647, | |
| "loss": 2.8482, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "learning_rate": 0.00036204117647058826, | |
| "loss": 2.8523, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 0.00035910294117647056, | |
| "loss": 2.8522, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 13.49, | |
| "learning_rate": 0.00035616176470588235, | |
| "loss": 2.856, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "learning_rate": 0.00035322058823529414, | |
| "loss": 2.8598, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 0.0003502794117647059, | |
| "loss": 2.8586, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 0.00034734117647058823, | |
| "loss": 2.8579, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 0.00034439999999999997, | |
| "loss": 2.8572, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 0.00034145882352941176, | |
| "loss": 2.861, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 0.00033851764705882355, | |
| "loss": 2.8622, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "learning_rate": 0.0003355794117647059, | |
| "loss": 2.8644, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 0.00033263823529411764, | |
| "loss": 2.8637, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "learning_rate": 0.0003297, | |
| "loss": 2.8654, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.41062555500779785, | |
| "eval_loss": 3.364118814468384, | |
| "eval_runtime": 153.4801, | |
| "eval_samples_per_second": 377.365, | |
| "eval_steps_per_second": 5.897, | |
| "step": 260400 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 0.0003267588235294118, | |
| "loss": 2.83, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 0.0003238176470588236, | |
| "loss": 2.8131, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 0.00032087941176470587, | |
| "loss": 2.8176, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 0.00031793823529411766, | |
| "loss": 2.8218, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 0.000315, | |
| "loss": 2.8223, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 0.0003120588235294118, | |
| "loss": 2.8292, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 14.35, | |
| "learning_rate": 0.00030911764705882354, | |
| "loss": 2.8295, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 0.0003061794117647059, | |
| "loss": 2.8308, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 14.46, | |
| "learning_rate": 0.00030323823529411763, | |
| "loss": 2.8285, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 0.0003002970588235294, | |
| "loss": 2.8353, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 0.0002973588235294118, | |
| "loss": 2.8333, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 0.0002944176470588235, | |
| "loss": 2.84, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 0.00029147941176470586, | |
| "loss": 2.8404, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 0.00028853823529411765, | |
| "loss": 2.8432, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 14.78, | |
| "learning_rate": 0.00028559705882352945, | |
| "loss": 2.8454, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 0.0002826558823529412, | |
| "loss": 2.8454, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 0.00027971764705882353, | |
| "loss": 2.8452, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 0.00027677647058823527, | |
| "loss": 2.8457, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 0.0002738382352941177, | |
| "loss": 2.8465, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.41153869357496303, | |
| "eval_loss": 3.3597159385681152, | |
| "eval_runtime": 153.3032, | |
| "eval_samples_per_second": 377.8, | |
| "eval_steps_per_second": 5.903, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 0.00027089705882352947, | |
| "loss": 2.7933, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 0.00026795882352941176, | |
| "loss": 2.7996, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 0.00026501764705882356, | |
| "loss": 2.8057, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 0.0002620794117647059, | |
| "loss": 2.8073, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 0.0002591382352941177, | |
| "loss": 2.8103, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 15.32, | |
| "learning_rate": 0.0002561970588235294, | |
| "loss": 2.8119, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 0.0002532558823529412, | |
| "loss": 2.8127, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 15.43, | |
| "learning_rate": 0.0002503176470588235, | |
| "loss": 2.812, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 15.48, | |
| "learning_rate": 0.00024737647058823526, | |
| "loss": 2.8125, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 0.00024443529411764705, | |
| "loss": 2.814, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 0.0002414970588235294, | |
| "loss": 2.8221, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 15.65, | |
| "learning_rate": 0.00023855588235294117, | |
| "loss": 2.82, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "learning_rate": 0.00023561764705882355, | |
| "loss": 2.8229, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "learning_rate": 0.0002326794117647059, | |
| "loss": 2.8214, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 15.81, | |
| "learning_rate": 0.00022973823529411766, | |
| "loss": 2.8212, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 0.00022679705882352943, | |
| "loss": 2.8257, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "learning_rate": 0.0002238558823529412, | |
| "loss": 2.8235, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 0.00022092058823529413, | |
| "loss": 2.8233, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.41061084213653465, | |
| "eval_loss": 3.374824285507202, | |
| "eval_runtime": 153.5576, | |
| "eval_samples_per_second": 377.174, | |
| "eval_steps_per_second": 5.894, | |
| "step": 297600 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 0.0002179794117647059, | |
| "loss": 2.8099, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 16.08, | |
| "learning_rate": 0.00021503823529411766, | |
| "loss": 2.7833, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 16.13, | |
| "learning_rate": 0.00021209705882352942, | |
| "loss": 2.7849, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 0.00020915588235294116, | |
| "loss": 2.7882, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 16.24, | |
| "learning_rate": 0.00020621764705882354, | |
| "loss": 2.7944, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 16.29, | |
| "learning_rate": 0.00020327647058823527, | |
| "loss": 2.7924, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "learning_rate": 0.00020033529411764707, | |
| "loss": 2.7938, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "learning_rate": 0.00019739705882352944, | |
| "loss": 2.7968, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 16.45, | |
| "learning_rate": 0.00019445588235294118, | |
| "loss": 2.7968, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "learning_rate": 0.00019151764705882356, | |
| "loss": 2.7986, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 16.56, | |
| "learning_rate": 0.0001885764705882353, | |
| "loss": 2.7984, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 16.61, | |
| "learning_rate": 0.00018563529411764706, | |
| "loss": 2.7991, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 0.0001826970588235294, | |
| "loss": 2.7993, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "learning_rate": 0.00017975588235294118, | |
| "loss": 2.7993, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 16.77, | |
| "learning_rate": 0.00017681470588235294, | |
| "loss": 2.8052, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 0.0001738794117647059, | |
| "loss": 2.8066, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 16.88, | |
| "learning_rate": 0.00017093823529411764, | |
| "loss": 2.8064, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "learning_rate": 0.00016799705882352943, | |
| "loss": 2.8063, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "learning_rate": 0.00016505588235294117, | |
| "loss": 2.8071, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.4113243828017687, | |
| "eval_loss": 3.3753533363342285, | |
| "eval_runtime": 153.6573, | |
| "eval_samples_per_second": 376.93, | |
| "eval_steps_per_second": 5.89, | |
| "step": 316200 | |
| }, | |
| { | |
| "epoch": 17.04, | |
| "learning_rate": 0.00016211470588235294, | |
| "loss": 2.7774, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 0.00015917647058823529, | |
| "loss": 2.769, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 17.15, | |
| "learning_rate": 0.00015623823529411766, | |
| "loss": 2.77, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 17.2, | |
| "learning_rate": 0.00015329705882352943, | |
| "loss": 2.7725, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 17.26, | |
| "learning_rate": 0.00015035588235294117, | |
| "loss": 2.7753, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 17.31, | |
| "learning_rate": 0.00014741470588235296, | |
| "loss": 2.7769, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 17.37, | |
| "learning_rate": 0.0001444735294117647, | |
| "loss": 2.7774, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 17.42, | |
| "learning_rate": 0.00014153235294117646, | |
| "loss": 2.7804, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 17.47, | |
| "learning_rate": 0.0001385941176470588, | |
| "loss": 2.7809, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 0.0001356529411764706, | |
| "loss": 2.7838, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 17.58, | |
| "learning_rate": 0.00013271470588235293, | |
| "loss": 2.7843, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.00012977352941176472, | |
| "loss": 2.7811, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 17.69, | |
| "learning_rate": 0.00012683529411764704, | |
| "loss": 2.786, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 17.74, | |
| "learning_rate": 0.00012389411764705883, | |
| "loss": 2.783, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 0.00012095294117647058, | |
| "loss": 2.788, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 17.85, | |
| "learning_rate": 0.00011801470588235293, | |
| "loss": 2.7863, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 17.9, | |
| "learning_rate": 0.0001150735294117647, | |
| "loss": 2.7812, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 17.96, | |
| "learning_rate": 0.00011213529411764706, | |
| "loss": 2.7899, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.4111288158234713, | |
| "eval_loss": 3.3832848072052, | |
| "eval_runtime": 153.4169, | |
| "eval_samples_per_second": 377.52, | |
| "eval_steps_per_second": 5.899, | |
| "step": 334800 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 0.00010919411764705883, | |
| "loss": 2.7852, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "learning_rate": 0.00010625294117647059, | |
| "loss": 2.7586, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 18.12, | |
| "learning_rate": 0.00010331470588235294, | |
| "loss": 2.7622, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 18.17, | |
| "learning_rate": 0.00010037352941176471, | |
| "loss": 2.7606, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 18.23, | |
| "learning_rate": 9.743235294117647e-05, | |
| "loss": 2.7597, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 18.28, | |
| "learning_rate": 9.449411764705882e-05, | |
| "loss": 2.7611, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 18.33, | |
| "learning_rate": 9.155294117647059e-05, | |
| "loss": 2.7621, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 18.39, | |
| "learning_rate": 8.861176470588235e-05, | |
| "loss": 2.7574, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 18.44, | |
| "learning_rate": 8.567058823529413e-05, | |
| "loss": 2.7634, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 18.49, | |
| "learning_rate": 8.273235294117647e-05, | |
| "loss": 2.7695, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 18.55, | |
| "learning_rate": 7.979411764705882e-05, | |
| "loss": 2.7641, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 18.6, | |
| "learning_rate": 7.685294117647058e-05, | |
| "loss": 2.768, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 7.391176470588236e-05, | |
| "loss": 2.7652, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 18.71, | |
| "learning_rate": 7.09735294117647e-05, | |
| "loss": 2.7697, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 18.76, | |
| "learning_rate": 6.803235294117648e-05, | |
| "loss": 2.7651, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 18.82, | |
| "learning_rate": 6.509117647058824e-05, | |
| "loss": 2.7693, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 18.87, | |
| "learning_rate": 6.215294117647059e-05, | |
| "loss": 2.7705, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "learning_rate": 5.9211764705882356e-05, | |
| "loss": 2.7659, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "learning_rate": 5.6273529411764707e-05, | |
| "loss": 2.7669, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.41123140282995024, | |
| "eval_loss": 3.3913280963897705, | |
| "eval_runtime": 153.735, | |
| "eval_samples_per_second": 376.739, | |
| "eval_steps_per_second": 5.887, | |
| "step": 353400 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 5.333235294117647e-05, | |
| "loss": 2.7561, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 19.09, | |
| "learning_rate": 5.039411764705883e-05, | |
| "loss": 2.7467, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 19.14, | |
| "learning_rate": 4.7452941176470587e-05, | |
| "loss": 2.745, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 19.19, | |
| "learning_rate": 4.451470588235294e-05, | |
| "loss": 2.7506, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 19.25, | |
| "learning_rate": 4.15735294117647e-05, | |
| "loss": 2.7487, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 19.3, | |
| "learning_rate": 3.863235294117647e-05, | |
| "loss": 2.7512, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "learning_rate": 3.5697058823529415e-05, | |
| "loss": 2.749, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 19.41, | |
| "learning_rate": 3.275588235294118e-05, | |
| "loss": 2.7506, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 19.46, | |
| "learning_rate": 2.981764705882353e-05, | |
| "loss": 2.7527, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 2.6876470588235295e-05, | |
| "loss": 2.7497, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 2.393529411764706e-05, | |
| "loss": 2.7504, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 19.62, | |
| "learning_rate": 2.0994117647058822e-05, | |
| "loss": 2.7494, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 1.8052941176470587e-05, | |
| "loss": 2.7493, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 19.73, | |
| "learning_rate": 1.5114705882352942e-05, | |
| "loss": 2.7522, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 19.78, | |
| "learning_rate": 1.2173529411764707e-05, | |
| "loss": 2.7499, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 9.232352941176472e-06, | |
| "loss": 2.7512, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 19.89, | |
| "learning_rate": 6.291176470588235e-06, | |
| "loss": 2.751, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "learning_rate": 3.3558823529411767e-06, | |
| "loss": 2.7553, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.147058823529412e-07, | |
| "loss": 2.7513, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.41096838506284816, | |
| "eval_loss": 3.400571823120117, | |
| "eval_runtime": 153.2719, | |
| "eval_samples_per_second": 377.877, | |
| "eval_steps_per_second": 5.905, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 372000, | |
| "total_flos": 1.56732865394688e+18, | |
| "train_loss": 3.0213956810735887, | |
| "train_runtime": 80911.1288, | |
| "train_samples_per_second": 147.121, | |
| "train_steps_per_second": 4.598 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 372000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 5000, | |
| "total_flos": 1.56732865394688e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |