| { | |
| "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": 6.2307, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 6.25e-05, | |
| "loss": 5.0106, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.375e-05, | |
| "loss": 4.68, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.000125, | |
| "loss": 4.4601, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00015625, | |
| "loss": 4.2904, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001875, | |
| "loss": 4.1762, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00021875, | |
| "loss": 4.0703, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00025, | |
| "loss": 3.977, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00028125000000000003, | |
| "loss": 3.9045, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00031246875000000003, | |
| "loss": 3.848, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00034371875, | |
| "loss": 3.8034, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0003749375, | |
| "loss": 3.7535, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0004061875, | |
| "loss": 3.7203, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0004374375, | |
| "loss": 3.6886, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00046865625, | |
| "loss": 3.6652, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00049990625, | |
| "loss": 3.6413, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.000531125, | |
| "loss": 3.6178, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0005623749999999999, | |
| "loss": 3.6017, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.35927561873656305, | |
| "eval_loss": 3.768275737762451, | |
| "eval_runtime": 151.987, | |
| "eval_samples_per_second": 381.092, | |
| "eval_steps_per_second": 5.961, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00059359375, | |
| "loss": 3.5665, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0006248437500000001, | |
| "loss": 3.5454, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0006560625, | |
| "loss": 3.5334, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00068728125, | |
| "loss": 3.5201, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00071853125, | |
| "loss": 3.5093, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00074978125, | |
| "loss": 3.5036, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0007810312499999999, | |
| "loss": 3.491, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00081228125, | |
| "loss": 3.4802, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0008435000000000001, | |
| "loss": 3.4787, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0008747500000000001, | |
| "loss": 3.463, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0009059375, | |
| "loss": 3.4564, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0009371875, | |
| "loss": 3.4457, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0009684375, | |
| "loss": 3.4381, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0009996875, | |
| "loss": 3.4322, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0009970911764705882, | |
| "loss": 3.4237, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00099415, | |
| "loss": 3.4082, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0009912117647058825, | |
| "loss": 3.4007, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.000988270588235294, | |
| "loss": 3.3875, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.000985329411764706, | |
| "loss": 3.3799, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.37902175491009926, | |
| "eval_loss": 3.593546152114868, | |
| "eval_runtime": 153.1239, | |
| "eval_samples_per_second": 378.262, | |
| "eval_steps_per_second": 5.917, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0009823911764705884, | |
| "loss": 3.3337, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00097945, | |
| "loss": 3.3265, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0009765088235294118, | |
| "loss": 3.3165, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0009735676470588235, | |
| "loss": 3.3161, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0009706294117647059, | |
| "loss": 3.312, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.0009676911764705883, | |
| "loss": 3.3036, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.00096475, | |
| "loss": 3.3006, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.0009618088235294117, | |
| "loss": 3.2951, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.0009588705882352941, | |
| "loss": 3.2917, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0009559294117647059, | |
| "loss": 3.282, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0009529882352941177, | |
| "loss": 3.2847, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.0009500470588235295, | |
| "loss": 3.2786, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0009471088235294118, | |
| "loss": 3.271, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.0009441676470588235, | |
| "loss": 3.2696, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0009412264705882353, | |
| "loss": 3.2677, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0009382882352941176, | |
| "loss": 3.2575, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.0009353470588235295, | |
| "loss": 3.2542, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.0009324058823529412, | |
| "loss": 3.2546, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.39154149113743214, | |
| "eval_loss": 3.482309103012085, | |
| "eval_runtime": 153.2699, | |
| "eval_samples_per_second": 377.902, | |
| "eval_steps_per_second": 5.911, | |
| "step": 55800 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.000929464705882353, | |
| "loss": 3.234, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.0009265264705882354, | |
| "loss": 3.1844, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.000923585294117647, | |
| "loss": 3.1895, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.0009206441176470588, | |
| "loss": 3.1899, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.0009177058823529411, | |
| "loss": 3.1897, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.000914764705882353, | |
| "loss": 3.1888, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.0009118264705882353, | |
| "loss": 3.19, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.0009088852941176471, | |
| "loss": 3.1929, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.0009059441176470589, | |
| "loss": 3.1901, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.0009030058823529413, | |
| "loss": 3.1868, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 0.000900064705882353, | |
| "loss": 3.1808, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.0008971264705882353, | |
| "loss": 3.1813, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 0.000894185294117647, | |
| "loss": 3.1815, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.0008912470588235294, | |
| "loss": 3.1778, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.0008883058823529412, | |
| "loss": 3.1842, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.0008853676470588236, | |
| "loss": 3.1788, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.0008824264705882353, | |
| "loss": 3.1787, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 0.0008794852941176471, | |
| "loss": 3.1714, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.0008765441176470589, | |
| "loss": 3.1737, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.39783632570245114, | |
| "eval_loss": 3.4548425674438477, | |
| "eval_runtime": 154.0942, | |
| "eval_samples_per_second": 375.88, | |
| "eval_steps_per_second": 5.88, | |
| "step": 74400 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.0008736058823529411, | |
| "loss": 3.1312, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.000870664705882353, | |
| "loss": 3.107, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.0008677264705882352, | |
| "loss": 3.1138, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 0.0008647852941176471, | |
| "loss": 3.1109, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 0.0008618441176470588, | |
| "loss": 3.1156, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.0008589029411764706, | |
| "loss": 3.1169, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 0.0008559676470588235, | |
| "loss": 3.1188, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.0008530264705882354, | |
| "loss": 3.1217, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 0.0008500882352941177, | |
| "loss": 3.1207, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 0.0008471470588235294, | |
| "loss": 3.1183, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.0008442058823529411, | |
| "loss": 3.1259, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.0008412676470588235, | |
| "loss": 3.1255, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.0008383264705882353, | |
| "loss": 3.12, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.000835385294117647, | |
| "loss": 3.1135, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 0.0008324470588235294, | |
| "loss": 3.1175, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 0.0008295058823529413, | |
| "loss": 3.1197, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.0008265676470588236, | |
| "loss": 3.1176, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.0008236264705882354, | |
| "loss": 3.1175, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0008206882352941176, | |
| "loss": 3.1178, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.40139941045420985, | |
| "eval_loss": 3.4163460731506348, | |
| "eval_runtime": 152.6757, | |
| "eval_samples_per_second": 379.373, | |
| "eval_steps_per_second": 5.934, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.0008177470588235295, | |
| "loss": 3.0456, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.0008148058823529412, | |
| "loss": 3.0573, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 0.0008118676470588236, | |
| "loss": 3.0613, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.0008089264705882353, | |
| "loss": 3.0623, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 0.0008059852941176471, | |
| "loss": 3.0653, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 0.0008030441176470589, | |
| "loss": 3.0626, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 0.0008001058823529412, | |
| "loss": 3.0658, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.000797164705882353, | |
| "loss": 3.0673, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 0.0007942264705882352, | |
| "loss": 3.0705, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 0.0007912852941176471, | |
| "loss": 3.067, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 0.0007883441176470588, | |
| "loss": 3.0735, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 0.0007854029411764706, | |
| "loss": 3.0763, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.0007824617647058824, | |
| "loss": 3.0734, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 0.0007795235294117647, | |
| "loss": 3.0735, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 0.0007765823529411766, | |
| "loss": 3.0735, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 0.0007736441176470589, | |
| "loss": 3.0709, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 0.0007707029411764706, | |
| "loss": 3.0737, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 0.0007677647058823529, | |
| "loss": 3.0736, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.4037599986080598, | |
| "eval_loss": 3.401655673980713, | |
| "eval_runtime": 153.1003, | |
| "eval_samples_per_second": 378.321, | |
| "eval_steps_per_second": 5.918, | |
| "step": 111600 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 0.0007648235294117647, | |
| "loss": 3.0433, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 0.0007618823529411765, | |
| "loss": 3.0037, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 0.0007589441176470589, | |
| "loss": 3.0114, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 0.0007560029411764706, | |
| "loss": 3.0155, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 0.000753064705882353, | |
| "loss": 3.0163, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 0.0007501235294117648, | |
| "loss": 3.0242, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 0.0007471823529411765, | |
| "loss": 3.0261, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.0007442411764705882, | |
| "loss": 3.0279, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 0.0007413029411764705, | |
| "loss": 3.0314, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 0.0007383617647058824, | |
| "loss": 3.0319, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 0.0007354205882352941, | |
| "loss": 3.03, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 0.0007324823529411765, | |
| "loss": 3.035, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.0007295411764705883, | |
| "loss": 3.0351, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 0.0007266029411764707, | |
| "loss": 3.0333, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 0.0007236617647058824, | |
| "loss": 3.0353, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 0.0007207235294117647, | |
| "loss": 3.0375, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 0.0007177823529411764, | |
| "loss": 3.0362, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 0.0007148441176470588, | |
| "loss": 3.0355, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 0.0007119029411764706, | |
| "loss": 3.0385, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.4057333022430861, | |
| "eval_loss": 3.3797543048858643, | |
| "eval_runtime": 152.5811, | |
| "eval_samples_per_second": 379.608, | |
| "eval_steps_per_second": 5.938, | |
| "step": 130200 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 0.0007089617647058824, | |
| "loss": 2.9799, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 0.0007060205882352942, | |
| "loss": 2.9734, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 0.0007030794117647059, | |
| "loss": 2.9787, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 0.0007001411764705883, | |
| "loss": 2.9844, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 0.0006972, | |
| "loss": 2.9858, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 0.0006942617647058823, | |
| "loss": 2.9909, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 0.0006913205882352941, | |
| "loss": 2.993, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 0.0006883794117647059, | |
| "loss": 2.9939, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 0.0006854411764705882, | |
| "loss": 2.9916, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 0.0006825000000000001, | |
| "loss": 2.9992, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 0.0006795617647058824, | |
| "loss": 2.9996, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 0.0006766205882352942, | |
| "loss": 2.9953, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.0006736823529411765, | |
| "loss": 3.0019, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 0.0006707411764705883, | |
| "loss": 3.0053, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 0.0006678, | |
| "loss": 3.0019, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 0.0006648588235294117, | |
| "loss": 3.0029, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 0.0006619205882352941, | |
| "loss": 3.0039, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 0.0006589794117647058, | |
| "loss": 3.0068, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4059920741366696, | |
| "eval_loss": 3.3987667560577393, | |
| "eval_runtime": 152.6066, | |
| "eval_samples_per_second": 379.545, | |
| "eval_steps_per_second": 5.937, | |
| "step": 148800 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.0006560411764705883, | |
| "loss": 2.9921, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 0.0006531029411764707, | |
| "loss": 2.9365, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 0.0006501617647058824, | |
| "loss": 2.9421, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "learning_rate": 0.0006472205882352941, | |
| "loss": 2.9522, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 0.000644279411764706, | |
| "loss": 2.9535, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 0.0006413382352941176, | |
| "loss": 2.9562, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 0.0006384, | |
| "loss": 2.9613, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 0.0006354588235294118, | |
| "loss": 2.9634, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 0.0006325176470588235, | |
| "loss": 2.9646, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 0.0006295794117647059, | |
| "loss": 2.9638, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 0.0006266382352941176, | |
| "loss": 2.9689, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 0.0006237, | |
| "loss": 2.9713, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 0.0006207588235294118, | |
| "loss": 2.9745, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 0.0006178176470588236, | |
| "loss": 2.9719, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 0.0006148794117647058, | |
| "loss": 2.9719, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 0.0006119411764705882, | |
| "loss": 2.9743, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 0.000609, | |
| "loss": 2.9776, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 0.0006060588235294118, | |
| "loss": 2.9772, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 0.0006031176470588235, | |
| "loss": 2.9774, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.4074036304783041, | |
| "eval_loss": 3.3728039264678955, | |
| "eval_runtime": 152.355, | |
| "eval_samples_per_second": 380.171, | |
| "eval_steps_per_second": 5.947, | |
| "step": 167400 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 0.0006001764705882353, | |
| "loss": 2.9356, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 0.0005972411764705882, | |
| "loss": 2.9158, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 0.0005943000000000001, | |
| "loss": 2.92, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 0.0005913588235294117, | |
| "loss": 2.9247, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 0.0005884205882352941, | |
| "loss": 2.9248, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 0.0005854794117647059, | |
| "loss": 2.9304, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 0.0005825382352941177, | |
| "loss": 2.93, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 0.0005795970588235294, | |
| "loss": 2.9384, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 0.0005766588235294118, | |
| "loss": 2.9418, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 0.0005737176470588236, | |
| "loss": 2.9438, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 0.000570779411764706, | |
| "loss": 2.9424, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.0005678411764705882, | |
| "loss": 2.9404, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 0.0005649, | |
| "loss": 2.9428, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 0.0005619588235294118, | |
| "loss": 2.9464, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 0.0005590176470588235, | |
| "loss": 2.9472, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 0.0005560764705882353, | |
| "loss": 2.9478, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 0.0005531382352941176, | |
| "loss": 2.9515, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 0.0005501970588235295, | |
| "loss": 2.9535, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0005472588235294118, | |
| "loss": 2.9558, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.4086515397968936, | |
| "eval_loss": 3.3694682121276855, | |
| "eval_runtime": 152.991, | |
| "eval_samples_per_second": 378.591, | |
| "eval_steps_per_second": 5.922, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 0.0005443176470588236, | |
| "loss": 2.8847, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 0.0005413764705882354, | |
| "loss": 2.8924, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 0.0005384382352941177, | |
| "loss": 2.8966, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 0.0005354970588235294, | |
| "loss": 2.903, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 0.0005325588235294118, | |
| "loss": 2.9012, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 0.0005296205882352941, | |
| "loss": 2.9059, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 0.0005266794117647059, | |
| "loss": 2.9088, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 0.0005237382352941177, | |
| "loss": 2.9133, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 0.0005207970588235294, | |
| "loss": 2.913, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 10.54, | |
| "learning_rate": 0.0005178558823529413, | |
| "loss": 2.919, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 10.59, | |
| "learning_rate": 0.0005149176470588234, | |
| "loss": 2.9168, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 0.0005119764705882353, | |
| "loss": 2.9204, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 0.0005090382352941176, | |
| "loss": 2.926, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 0.0005061, | |
| "loss": 2.9238, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 0.0005031588235294117, | |
| "loss": 2.9267, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 0.0005002176470588236, | |
| "loss": 2.9296, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 0.0004972764705882353, | |
| "loss": 2.9231, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 0.0004943382352941176, | |
| "loss": 2.9289, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.409351809324078, | |
| "eval_loss": 3.364856004714966, | |
| "eval_runtime": 153.2895, | |
| "eval_samples_per_second": 377.854, | |
| "eval_steps_per_second": 5.91, | |
| "step": 204600 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 0.0004913970588235295, | |
| "loss": 2.9004, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "learning_rate": 0.0004884588235294118, | |
| "loss": 2.8684, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 0.00048551764705882355, | |
| "loss": 2.8725, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 11.18, | |
| "learning_rate": 0.0004825794117647059, | |
| "loss": 2.8784, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 0.00047963823529411764, | |
| "loss": 2.8794, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 0.00047669705882352943, | |
| "loss": 2.8815, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 11.34, | |
| "learning_rate": 0.0004737558823529412, | |
| "loss": 2.8833, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 0.0004708176470588235, | |
| "loss": 2.8887, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 0.0004678764705882353, | |
| "loss": 2.8906, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 0.00046493529411764705, | |
| "loss": 2.8921, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 0.00046199411764705884, | |
| "loss": 2.8961, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 0.00045905882352941175, | |
| "loss": 2.8966, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 11.67, | |
| "learning_rate": 0.00045611764705882354, | |
| "loss": 2.899, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 0.0004531764705882353, | |
| "loss": 2.9001, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 11.77, | |
| "learning_rate": 0.0004502382352941177, | |
| "loss": 2.9036, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 11.83, | |
| "learning_rate": 0.00044729705882352947, | |
| "loss": 2.9021, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "learning_rate": 0.00044435588235294116, | |
| "loss": 2.9045, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 0.00044141470588235295, | |
| "loss": 2.9051, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 0.0004384764705882353, | |
| "loss": 2.9058, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4094906002721942, | |
| "eval_loss": 3.3603594303131104, | |
| "eval_runtime": 152.9212, | |
| "eval_samples_per_second": 378.764, | |
| "eval_steps_per_second": 5.925, | |
| "step": 223200 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 0.0004355382352941177, | |
| "loss": 2.854, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 0.0004325970588235294, | |
| "loss": 2.8436, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 0.0004296588235294118, | |
| "loss": 2.8549, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 0.00042671764705882353, | |
| "loss": 2.8551, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 0.0004237764705882353, | |
| "loss": 2.8579, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 0.0004208352941176471, | |
| "loss": 2.8663, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 12.37, | |
| "learning_rate": 0.0004178970588235294, | |
| "loss": 2.8652, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 0.0004149558823529412, | |
| "loss": 2.871, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 12.47, | |
| "learning_rate": 0.00041201470588235294, | |
| "loss": 2.8696, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "learning_rate": 0.00040907352941176473, | |
| "loss": 2.8723, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 0.00040613235294117647, | |
| "loss": 2.875, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 0.0004031911764705882, | |
| "loss": 2.8776, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "learning_rate": 0.0004002529411764706, | |
| "loss": 2.8773, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 12.74, | |
| "learning_rate": 0.00039731470588235296, | |
| "loss": 2.8808, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 0.0003943735294117647, | |
| "loss": 2.8819, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 12.85, | |
| "learning_rate": 0.00039143235294117644, | |
| "loss": 2.8865, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 0.00038849411764705884, | |
| "loss": 2.8811, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 0.0003855558823529412, | |
| "loss": 2.8805, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.40976489041796293, | |
| "eval_loss": 3.380065679550171, | |
| "eval_runtime": 152.8294, | |
| "eval_samples_per_second": 378.991, | |
| "eval_steps_per_second": 5.928, | |
| "step": 241800 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 0.000382614705882353, | |
| "loss": 2.8705, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 0.0003796735294117647, | |
| "loss": 2.8279, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 0.00037673235294117646, | |
| "loss": 2.8249, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 13.17, | |
| "learning_rate": 0.00037379117647058825, | |
| "loss": 2.8377, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 0.0003708529411764706, | |
| "loss": 2.8363, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 0.00036791176470588234, | |
| "loss": 2.8433, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 0.0003649735294117647, | |
| "loss": 2.8461, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "learning_rate": 0.0003620323529411765, | |
| "loss": 2.8522, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 0.00035909411764705883, | |
| "loss": 2.8426, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 13.49, | |
| "learning_rate": 0.00035615294117647057, | |
| "loss": 2.854, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "learning_rate": 0.00035321176470588236, | |
| "loss": 2.8533, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 0.0003502705882352941, | |
| "loss": 2.8515, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 0.0003473323529411765, | |
| "loss": 2.8585, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 0.00034439117647058824, | |
| "loss": 2.8567, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 0.00034145, | |
| "loss": 2.861, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 0.00033850882352941177, | |
| "loss": 2.8554, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "learning_rate": 0.0003355705882352941, | |
| "loss": 2.8636, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 0.0003326294117647059, | |
| "loss": 2.8648, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "learning_rate": 0.0003296882352941177, | |
| "loss": 2.8621, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.409478642484796, | |
| "eval_loss": 3.3870773315429688, | |
| "eval_runtime": 153.1211, | |
| "eval_samples_per_second": 378.269, | |
| "eval_steps_per_second": 5.917, | |
| "step": 260400 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 0.0003267529411764706, | |
| "loss": 2.8345, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 0.00032381176470588235, | |
| "loss": 2.809, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 0.00032087058823529414, | |
| "loss": 2.8165, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 0.00031792941176470593, | |
| "loss": 2.8175, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 0.0003149882352941176, | |
| "loss": 2.8223, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 0.00031205, | |
| "loss": 2.8244, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 14.35, | |
| "learning_rate": 0.00030910882352941176, | |
| "loss": 2.8286, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 0.00030616764705882355, | |
| "loss": 2.8291, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 14.46, | |
| "learning_rate": 0.00030322941176470585, | |
| "loss": 2.8318, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 0.00030028823529411764, | |
| "loss": 2.8312, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 0.00029734705882352943, | |
| "loss": 2.8348, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 0.0002944088235294118, | |
| "loss": 2.8378, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 0.0002914676470588236, | |
| "loss": 2.8368, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 0.00028852941176470587, | |
| "loss": 2.8375, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 14.78, | |
| "learning_rate": 0.00028558823529411766, | |
| "loss": 2.8374, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 0.0002826470588235294, | |
| "loss": 2.8398, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 0.0002797088235294118, | |
| "loss": 2.8405, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 0.0002767676470588235, | |
| "loss": 2.8394, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 0.0002738294117647059, | |
| "loss": 2.8423, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4095923758222406, | |
| "eval_loss": 3.3872194290161133, | |
| "eval_runtime": 152.5036, | |
| "eval_samples_per_second": 379.801, | |
| "eval_steps_per_second": 5.941, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 0.00027088823529411763, | |
| "loss": 2.7935, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 0.0002679470588235294, | |
| "loss": 2.8014, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 0.00026500882352941177, | |
| "loss": 2.7988, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 0.0002620676470588235, | |
| "loss": 2.8032, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 0.0002591294117647059, | |
| "loss": 2.8058, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 15.32, | |
| "learning_rate": 0.00025619117647058827, | |
| "loss": 2.8074, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 0.00025325, | |
| "loss": 2.8105, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 15.43, | |
| "learning_rate": 0.00025030882352941174, | |
| "loss": 2.8109, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 15.48, | |
| "learning_rate": 0.00024737058823529415, | |
| "loss": 2.8118, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 0.0002444294117647059, | |
| "loss": 2.814, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 0.00024148823529411765, | |
| "loss": 2.817, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 15.65, | |
| "learning_rate": 0.0002385470588235294, | |
| "loss": 2.8198, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "learning_rate": 0.00023560588235294118, | |
| "loss": 2.8158, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "learning_rate": 0.00023266764705882353, | |
| "loss": 2.8187, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 15.81, | |
| "learning_rate": 0.0002297264705882353, | |
| "loss": 2.8163, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 0.00022678529411764706, | |
| "loss": 2.8183, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "learning_rate": 0.00022385, | |
| "loss": 2.8204, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 0.00022090882352941179, | |
| "loss": 2.8216, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.40969267344350757, | |
| "eval_loss": 3.3996341228485107, | |
| "eval_runtime": 152.6929, | |
| "eval_samples_per_second": 379.33, | |
| "eval_steps_per_second": 5.933, | |
| "step": 297600 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 0.00021796764705882352, | |
| "loss": 2.8062, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 16.08, | |
| "learning_rate": 0.0002150294117647059, | |
| "loss": 2.7798, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 16.13, | |
| "learning_rate": 0.00021208823529411767, | |
| "loss": 2.7837, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 0.0002091470588235294, | |
| "loss": 2.7856, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 16.24, | |
| "learning_rate": 0.0002062058823529412, | |
| "loss": 2.7852, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 16.29, | |
| "learning_rate": 0.00020327058823529413, | |
| "loss": 2.7907, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "learning_rate": 0.0002003294117647059, | |
| "loss": 2.7915, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "learning_rate": 0.00019738823529411763, | |
| "loss": 2.7898, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 16.45, | |
| "learning_rate": 0.00019444705882352943, | |
| "loss": 2.7921, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "learning_rate": 0.00019150882352941178, | |
| "loss": 2.7969, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 16.56, | |
| "learning_rate": 0.00018856764705882354, | |
| "loss": 2.7974, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 16.61, | |
| "learning_rate": 0.0001856294117647059, | |
| "loss": 2.7936, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 0.00018268823529411766, | |
| "loss": 2.7995, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "learning_rate": 0.0001797470588235294, | |
| "loss": 2.7983, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 16.77, | |
| "learning_rate": 0.00017680882352941177, | |
| "loss": 2.7995, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 0.0001738676470588235, | |
| "loss": 2.7993, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 16.88, | |
| "learning_rate": 0.00017092941176470589, | |
| "loss": 2.8003, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "learning_rate": 0.00016798823529411768, | |
| "loss": 2.8086, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "learning_rate": 0.00016504705882352942, | |
| "loss": 2.8042, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.41008405585576546, | |
| "eval_loss": 3.398700714111328, | |
| "eval_runtime": 152.4781, | |
| "eval_samples_per_second": 379.864, | |
| "eval_steps_per_second": 5.942, | |
| "step": 316200 | |
| }, | |
| { | |
| "epoch": 17.04, | |
| "learning_rate": 0.00016210588235294118, | |
| "loss": 2.7702, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 0.00015916764705882353, | |
| "loss": 2.7625, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 17.15, | |
| "learning_rate": 0.0001562264705882353, | |
| "loss": 2.7737, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 17.2, | |
| "learning_rate": 0.00015328529411764706, | |
| "loss": 2.7706, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 17.26, | |
| "learning_rate": 0.0001503470588235294, | |
| "loss": 2.7714, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 17.31, | |
| "learning_rate": 0.00014740588235294118, | |
| "loss": 2.7705, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 17.37, | |
| "learning_rate": 0.00014446764705882353, | |
| "loss": 2.7761, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 17.42, | |
| "learning_rate": 0.0001415264705882353, | |
| "loss": 2.776, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 17.47, | |
| "learning_rate": 0.00013858529411764706, | |
| "loss": 2.7782, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 0.0001356470588235294, | |
| "loss": 2.7805, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 17.58, | |
| "learning_rate": 0.00013270588235294117, | |
| "loss": 2.7804, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.00012976470588235296, | |
| "loss": 2.7823, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 17.69, | |
| "learning_rate": 0.00012682647058823529, | |
| "loss": 2.7811, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 17.74, | |
| "learning_rate": 0.00012388529411764708, | |
| "loss": 2.7799, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 0.00012094411764705883, | |
| "loss": 2.7821, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 17.85, | |
| "learning_rate": 0.0001180029411764706, | |
| "loss": 2.7839, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 17.9, | |
| "learning_rate": 0.00011506176470588235, | |
| "loss": 2.7848, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 17.96, | |
| "learning_rate": 0.00011212058823529411, | |
| "loss": 2.7834, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.41014008279222663, | |
| "eval_loss": 3.4020495414733887, | |
| "eval_runtime": 152.7878, | |
| "eval_samples_per_second": 379.094, | |
| "eval_steps_per_second": 5.93, | |
| "step": 334800 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 0.00010918235294117647, | |
| "loss": 2.7783, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "learning_rate": 0.00010624117647058824, | |
| "loss": 2.7522, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 18.12, | |
| "learning_rate": 0.00010330294117647059, | |
| "loss": 2.7562, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 18.17, | |
| "learning_rate": 0.00010036176470588237, | |
| "loss": 2.7594, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 18.23, | |
| "learning_rate": 9.74235294117647e-05, | |
| "loss": 2.7523, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 18.28, | |
| "learning_rate": 9.448235294117648e-05, | |
| "loss": 2.7595, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 18.33, | |
| "learning_rate": 9.154411764705882e-05, | |
| "loss": 2.7656, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 18.39, | |
| "learning_rate": 8.86029411764706e-05, | |
| "loss": 2.7577, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 18.44, | |
| "learning_rate": 8.566176470588236e-05, | |
| "loss": 2.7624, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 18.49, | |
| "learning_rate": 8.272058823529411e-05, | |
| "loss": 2.7589, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 18.55, | |
| "learning_rate": 7.978235294117648e-05, | |
| "loss": 2.7612, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 18.6, | |
| "learning_rate": 7.684117647058823e-05, | |
| "loss": 2.7645, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 7.390294117647059e-05, | |
| "loss": 2.7634, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 18.71, | |
| "learning_rate": 7.096176470588236e-05, | |
| "loss": 2.761, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 18.76, | |
| "learning_rate": 6.802058823529412e-05, | |
| "loss": 2.7608, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 18.82, | |
| "learning_rate": 6.508235294117647e-05, | |
| "loss": 2.7627, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 18.87, | |
| "learning_rate": 6.214117647058824e-05, | |
| "loss": 2.767, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "learning_rate": 5.9202941176470594e-05, | |
| "loss": 2.7678, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "learning_rate": 5.626176470588235e-05, | |
| "loss": 2.7643, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.4096899191216911, | |
| "eval_loss": 3.419888973236084, | |
| "eval_runtime": 152.6752, | |
| "eval_samples_per_second": 379.374, | |
| "eval_steps_per_second": 5.934, | |
| "step": 353400 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 5.332058823529412e-05, | |
| "loss": 2.7504, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 19.09, | |
| "learning_rate": 5.037941176470588e-05, | |
| "loss": 2.7458, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 19.14, | |
| "learning_rate": 4.743823529411765e-05, | |
| "loss": 2.7466, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 19.19, | |
| "learning_rate": 4.449705882352941e-05, | |
| "loss": 2.7444, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 19.25, | |
| "learning_rate": 4.155882352941177e-05, | |
| "loss": 2.7448, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 19.3, | |
| "learning_rate": 3.862058823529411e-05, | |
| "loss": 2.7459, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "learning_rate": 3.5679411764705884e-05, | |
| "loss": 2.747, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 19.41, | |
| "learning_rate": 3.2741176470588234e-05, | |
| "loss": 2.7463, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 19.46, | |
| "learning_rate": 2.98e-05, | |
| "loss": 2.7457, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 2.6858823529411764e-05, | |
| "loss": 2.7479, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 2.391764705882353e-05, | |
| "loss": 2.7478, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 19.62, | |
| "learning_rate": 2.0979411764705883e-05, | |
| "loss": 2.7469, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 1.8038235294117648e-05, | |
| "loss": 2.7461, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 19.73, | |
| "learning_rate": 1.5097058823529411e-05, | |
| "loss": 2.7484, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 19.78, | |
| "learning_rate": 1.2158823529411766e-05, | |
| "loss": 2.7524, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 9.217647058823531e-06, | |
| "loss": 2.7469, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 19.89, | |
| "learning_rate": 6.2823529411764705e-06, | |
| "loss": 2.7463, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "learning_rate": 3.3411764705882354e-06, | |
| "loss": 2.746, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 2.7463, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.4096600918317765, | |
| "eval_loss": 3.425863742828369, | |
| "eval_runtime": 152.7802, | |
| "eval_samples_per_second": 379.113, | |
| "eval_steps_per_second": 5.93, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 372000, | |
| "total_flos": 1.56735498728448e+18, | |
| "train_loss": 3.0193379687237485, | |
| "train_runtime": 80852.2733, | |
| "train_samples_per_second": 147.231, | |
| "train_steps_per_second": 4.601 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 372000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 5000, | |
| "total_flos": 1.56735498728448e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |