| { | |
| "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": 6.2154, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 6.25e-05, | |
| "loss": 5.0023, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.375e-05, | |
| "loss": 4.6739, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.000125, | |
| "loss": 4.4488, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00015625, | |
| "loss": 4.2953, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001875, | |
| "loss": 4.1702, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00021875, | |
| "loss": 4.0706, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00025, | |
| "loss": 3.9833, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00028121875, | |
| "loss": 3.9089, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0003124375, | |
| "loss": 3.8494, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00034368749999999997, | |
| "loss": 3.7982, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0003749375, | |
| "loss": 3.7586, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00040615625, | |
| "loss": 3.7205, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00043740625, | |
| "loss": 3.6922, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.000468625, | |
| "loss": 3.6653, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.000499875, | |
| "loss": 3.6439, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.000531125, | |
| "loss": 3.6156, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00056234375, | |
| "loss": 3.5998, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.35954542199269246, | |
| "eval_loss": 3.7955493927001953, | |
| "eval_runtime": 152.7997, | |
| "eval_samples_per_second": 379.045, | |
| "eval_steps_per_second": 5.923, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00059359375, | |
| "loss": 3.5649, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0006248125, | |
| "loss": 3.545, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0006560625, | |
| "loss": 3.5367, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0006873125, | |
| "loss": 3.5224, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0007185000000000001, | |
| "loss": 3.5073, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0007497500000000001, | |
| "loss": 3.5, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.000781, | |
| "loss": 3.4919, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00081225, | |
| "loss": 3.4773, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00084346875, | |
| "loss": 3.4669, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00087471875, | |
| "loss": 3.4613, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0009059375, | |
| "loss": 3.4528, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0009371875, | |
| "loss": 3.4462, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0009684375, | |
| "loss": 3.4366, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0009996875, | |
| "loss": 3.4323, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0009970941176470588, | |
| "loss": 3.4186, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0009941529411764706, | |
| "loss": 3.4067, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.000991214705882353, | |
| "loss": 3.3964, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0009882735294117647, | |
| "loss": 3.3851, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0009853323529411765, | |
| "loss": 3.3776, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.38045328542446233, | |
| "eval_loss": 3.5874266624450684, | |
| "eval_runtime": 155.4692, | |
| "eval_samples_per_second": 372.537, | |
| "eval_steps_per_second": 5.821, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0009823911764705884, | |
| "loss": 3.326, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00097945, | |
| "loss": 3.3184, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0009765117647058823, | |
| "loss": 3.3162, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0009735705882352941, | |
| "loss": 3.3123, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0009706323529411764, | |
| "loss": 3.3072, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.0009676941176470588, | |
| "loss": 3.3018, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0009647529411764706, | |
| "loss": 3.2918, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.000961814705882353, | |
| "loss": 3.2907, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.0009588735294117647, | |
| "loss": 3.2896, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0009559323529411766, | |
| "loss": 3.2864, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0009529941176470587, | |
| "loss": 3.2805, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.0009500529411764706, | |
| "loss": 3.2719, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0009471117647058823, | |
| "loss": 3.2722, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.0009441705882352942, | |
| "loss": 3.2672, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0009412294117647059, | |
| "loss": 3.2614, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0009382911764705883, | |
| "loss": 3.2574, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.00093535, | |
| "loss": 3.2526, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.0009324088235294118, | |
| "loss": 3.245, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.392286599207816, | |
| "eval_loss": 3.4956088066101074, | |
| "eval_runtime": 154.66, | |
| "eval_samples_per_second": 374.486, | |
| "eval_steps_per_second": 5.852, | |
| "step": 55800 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.0009294705882352942, | |
| "loss": 3.2315, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.0009265323529411765, | |
| "loss": 3.1807, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.0009235911764705882, | |
| "loss": 3.1819, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.00092065, | |
| "loss": 3.1812, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.0009177117647058824, | |
| "loss": 3.189, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.0009147705882352941, | |
| "loss": 3.181, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.000911829411764706, | |
| "loss": 3.1879, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.0009088882352941177, | |
| "loss": 3.1835, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.0009059500000000001, | |
| "loss": 3.18, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.0009030088235294118, | |
| "loss": 3.1831, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 0.0009000705882352941, | |
| "loss": 3.1791, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.0008971323529411764, | |
| "loss": 3.1821, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 0.0008941911764705883, | |
| "loss": 3.1778, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.00089125, | |
| "loss": 3.1752, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.0008883088235294117, | |
| "loss": 3.1732, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.0008853705882352941, | |
| "loss": 3.1736, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.0008824294117647059, | |
| "loss": 3.1737, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 0.0008794882352941177, | |
| "loss": 3.169, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.00087655, | |
| "loss": 3.1698, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3991002037900625, | |
| "eval_loss": 3.430137872695923, | |
| "eval_runtime": 154.5458, | |
| "eval_samples_per_second": 374.763, | |
| "eval_steps_per_second": 5.856, | |
| "step": 74400 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.0008736088235294118, | |
| "loss": 3.1234, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.0008706676470588235, | |
| "loss": 3.0984, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.0008677264705882352, | |
| "loss": 3.1061, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 0.0008647911764705882, | |
| "loss": 3.1072, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 0.00086185, | |
| "loss": 3.107, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.0008589117647058823, | |
| "loss": 3.1159, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 0.0008559705882352942, | |
| "loss": 3.1125, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.0008530294117647059, | |
| "loss": 3.1107, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 0.0008500882352941177, | |
| "loss": 3.1106, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 0.00084715, | |
| "loss": 3.1144, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.0008442088235294117, | |
| "loss": 3.1112, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.0008412705882352941, | |
| "loss": 3.113, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.0008383294117647058, | |
| "loss": 3.1116, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.0008353882352941177, | |
| "loss": 3.1179, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 0.0008324470588235294, | |
| "loss": 3.1197, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 0.0008295058823529413, | |
| "loss": 3.1122, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.0008265676470588236, | |
| "loss": 3.1156, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.0008236294117647059, | |
| "loss": 3.1107, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0008206882352941176, | |
| "loss": 3.1095, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.40172641771951034, | |
| "eval_loss": 3.4079980850219727, | |
| "eval_runtime": 154.469, | |
| "eval_samples_per_second": 374.949, | |
| "eval_steps_per_second": 5.859, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.0008177470588235295, | |
| "loss": 3.0393, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.0008148088235294117, | |
| "loss": 3.0451, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 0.0008118676470588236, | |
| "loss": 3.0493, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.0008089264705882353, | |
| "loss": 3.0574, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 0.0008059882352941177, | |
| "loss": 3.0549, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 0.0008030470588235295, | |
| "loss": 3.0565, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 0.0008001058823529412, | |
| "loss": 3.0629, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.0007971676470588235, | |
| "loss": 3.064, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 0.0007942264705882352, | |
| "loss": 3.0659, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 0.0007912852941176471, | |
| "loss": 3.0616, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 0.0007883441176470588, | |
| "loss": 3.0659, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 0.0007854058823529412, | |
| "loss": 3.0657, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.000782464705882353, | |
| "loss": 3.0672, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 0.0007795264705882354, | |
| "loss": 3.0646, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 0.0007765852941176471, | |
| "loss": 3.0602, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 0.0007736470588235295, | |
| "loss": 3.0654, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 0.0007707058823529411, | |
| "loss": 3.069, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 0.0007677647058823529, | |
| "loss": 3.0618, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.40467026843129755, | |
| "eval_loss": 3.3783042430877686, | |
| "eval_runtime": 153.5335, | |
| "eval_samples_per_second": 377.234, | |
| "eval_steps_per_second": 5.894, | |
| "step": 111600 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 0.0007648264705882353, | |
| "loss": 3.037, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 0.0007618882352941177, | |
| "loss": 2.9966, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 0.0007589470588235294, | |
| "loss": 2.9999, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 0.0007560058823529412, | |
| "loss": 3.0101, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 0.0007530676470588236, | |
| "loss": 3.0134, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 0.0007501264705882353, | |
| "loss": 3.0171, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 0.0007471852941176472, | |
| "loss": 3.0178, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.0007442441176470588, | |
| "loss": 3.0199, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 0.0007413029411764705, | |
| "loss": 3.0203, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 0.0007383647058823529, | |
| "loss": 3.0196, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 0.0007354235294117647, | |
| "loss": 3.018, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 0.0007324823529411765, | |
| "loss": 3.02, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.0007295441176470588, | |
| "loss": 3.0304, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 0.0007266058823529412, | |
| "loss": 3.0253, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 0.000723664705882353, | |
| "loss": 3.0284, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 0.0007207235294117647, | |
| "loss": 3.0287, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 0.0007177823529411764, | |
| "loss": 3.0282, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 0.0007148411764705882, | |
| "loss": 3.0303, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 0.0007119029411764706, | |
| "loss": 3.0262, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.4062741057631056, | |
| "eval_loss": 3.365633964538574, | |
| "eval_runtime": 153.1084, | |
| "eval_samples_per_second": 378.281, | |
| "eval_steps_per_second": 5.911, | |
| "step": 130200 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 0.000708964705882353, | |
| "loss": 2.9723, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 0.0007060235294117647, | |
| "loss": 2.9655, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 0.0007030823529411766, | |
| "loss": 2.9658, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 0.0007001411764705883, | |
| "loss": 2.9749, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 0.0006972, | |
| "loss": 2.9813, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 0.0006942617647058823, | |
| "loss": 2.9773, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 0.0006913235294117647, | |
| "loss": 2.9775, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 0.0006883823529411765, | |
| "loss": 2.9839, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 0.0006854411764705882, | |
| "loss": 2.9863, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 0.0006825000000000001, | |
| "loss": 2.9888, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 0.0006795588235294118, | |
| "loss": 2.9899, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 0.0006766205882352942, | |
| "loss": 2.9932, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.0006736794117647059, | |
| "loss": 2.9915, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 0.0006707382352941177, | |
| "loss": 2.9934, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 0.0006678, | |
| "loss": 2.992, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 0.0006648588235294117, | |
| "loss": 2.9929, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 0.0006619176470588236, | |
| "loss": 2.9975, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 0.0006589794117647058, | |
| "loss": 2.9992, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4087943064009858, | |
| "eval_loss": 3.3349857330322266, | |
| "eval_runtime": 153.3102, | |
| "eval_samples_per_second": 377.783, | |
| "eval_steps_per_second": 5.903, | |
| "step": 148800 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.0006560411764705883, | |
| "loss": 2.984, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 0.0006531, | |
| "loss": 2.9284, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 0.0006501588235294118, | |
| "loss": 2.9398, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "learning_rate": 0.0006472176470588236, | |
| "loss": 2.9419, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 0.000644279411764706, | |
| "loss": 2.9454, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 0.0006413411764705882, | |
| "loss": 2.9433, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 0.0006384, | |
| "loss": 2.9512, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 0.0006354588235294118, | |
| "loss": 2.9516, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 0.0006325205882352942, | |
| "loss": 2.9533, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 0.0006295794117647059, | |
| "loss": 2.9566, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 0.0006266382352941176, | |
| "loss": 2.9596, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 0.0006236970588235295, | |
| "loss": 2.958, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 0.0006207558823529412, | |
| "loss": 2.96, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 0.0006178176470588236, | |
| "loss": 2.9595, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 0.0006148764705882352, | |
| "loss": 2.962, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 0.0006119382352941177, | |
| "loss": 2.9631, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 0.0006089970588235294, | |
| "loss": 2.9653, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 0.0006060588235294118, | |
| "loss": 2.9669, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 0.0006031176470588235, | |
| "loss": 2.9653, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.4102860168737151, | |
| "eval_loss": 3.35310435295105, | |
| "eval_runtime": 153.3713, | |
| "eval_samples_per_second": 377.633, | |
| "eval_steps_per_second": 5.901, | |
| "step": 167400 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 0.0006001764705882353, | |
| "loss": 2.9306, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 0.0005972352941176471, | |
| "loss": 2.9031, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 0.0005942941176470589, | |
| "loss": 2.909, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 0.0005913529411764707, | |
| "loss": 2.9187, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 0.0005884147058823529, | |
| "loss": 2.9128, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 0.0005854764705882353, | |
| "loss": 2.9235, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 0.000582535294117647, | |
| "loss": 2.9253, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 0.0005795941176470589, | |
| "loss": 2.9269, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 0.0005766529411764706, | |
| "loss": 2.9271, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 0.000573714705882353, | |
| "loss": 2.9316, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 0.0005707735294117648, | |
| "loss": 2.9318, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.0005678352941176472, | |
| "loss": 2.9354, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 0.0005648941176470588, | |
| "loss": 2.9352, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 0.0005619529411764705, | |
| "loss": 2.9342, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 0.0005590147058823529, | |
| "loss": 2.9369, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 0.0005560735294117647, | |
| "loss": 2.9383, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 0.0005531352941176471, | |
| "loss": 2.9375, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 0.0005501941176470588, | |
| "loss": 2.9363, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0005472529411764707, | |
| "loss": 2.9376, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.41102911764559663, | |
| "eval_loss": 3.352627754211426, | |
| "eval_runtime": 153.4087, | |
| "eval_samples_per_second": 377.541, | |
| "eval_steps_per_second": 5.899, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 0.000544314705882353, | |
| "loss": 2.8724, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 0.0005413735294117648, | |
| "loss": 2.8806, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 0.000538435294117647, | |
| "loss": 2.8845, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 0.0005354941176470588, | |
| "loss": 2.8894, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 0.0005325529411764706, | |
| "loss": 2.891, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 0.0005296176470588235, | |
| "loss": 2.8999, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 0.0005266764705882353, | |
| "loss": 2.9032, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 0.0005237352941176471, | |
| "loss": 2.9028, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 0.0005207941176470589, | |
| "loss": 2.9044, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 10.54, | |
| "learning_rate": 0.0005178529411764706, | |
| "loss": 2.904, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 10.59, | |
| "learning_rate": 0.000514914705882353, | |
| "loss": 2.9046, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 0.0005119735294117646, | |
| "loss": 2.914, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 0.0005090323529411765, | |
| "loss": 2.9142, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 0.0005060911764705882, | |
| "loss": 2.9131, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 0.0005031529411764706, | |
| "loss": 2.9088, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 0.0005002117647058824, | |
| "loss": 2.9135, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 0.0004972735294117648, | |
| "loss": 2.9141, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 0.0004943323529411765, | |
| "loss": 2.9136, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.4098210498325621, | |
| "eval_loss": 3.3538424968719482, | |
| "eval_runtime": 153.3952, | |
| "eval_samples_per_second": 377.574, | |
| "eval_steps_per_second": 5.9, | |
| "step": 204600 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 0.0004913941176470588, | |
| "loss": 2.8874, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "learning_rate": 0.0004884529411764706, | |
| "loss": 2.8549, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 0.0004855117647058824, | |
| "loss": 2.8607, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 11.18, | |
| "learning_rate": 0.0004825764705882353, | |
| "loss": 2.8626, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 0.0004796352941176471, | |
| "loss": 2.8704, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 0.0004766941176470588, | |
| "loss": 2.8691, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 11.34, | |
| "learning_rate": 0.0004737529411764706, | |
| "loss": 2.8752, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 0.0004708117647058824, | |
| "loss": 2.8756, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 0.0004678735294117647, | |
| "loss": 2.8781, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 0.0004649323529411765, | |
| "loss": 2.8795, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 0.0004619911764705882, | |
| "loss": 2.8855, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 0.00045905, | |
| "loss": 2.8841, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 11.67, | |
| "learning_rate": 0.0004561147058823529, | |
| "loss": 2.8852, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 0.0004531735294117647, | |
| "loss": 2.8896, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 11.77, | |
| "learning_rate": 0.00045023235294117646, | |
| "loss": 2.8897, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 11.83, | |
| "learning_rate": 0.00044729705882352947, | |
| "loss": 2.8911, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "learning_rate": 0.00044435588235294116, | |
| "loss": 2.8946, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 0.00044141470588235295, | |
| "loss": 2.8931, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 0.00043847352941176474, | |
| "loss": 2.8922, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4120207248594988, | |
| "eval_loss": 3.342489242553711, | |
| "eval_runtime": 153.6659, | |
| "eval_samples_per_second": 376.909, | |
| "eval_steps_per_second": 5.889, | |
| "step": 223200 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 0.0004355323529411765, | |
| "loss": 2.8448, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 0.0004325941176470589, | |
| "loss": 2.8354, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 0.00042965294117647057, | |
| "loss": 2.8436, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 0.00042671176470588236, | |
| "loss": 2.8461, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 0.0004237735294117647, | |
| "loss": 2.8485, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 0.0004208323529411765, | |
| "loss": 2.8509, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 12.37, | |
| "learning_rate": 0.0004178941176470588, | |
| "loss": 2.8533, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 0.0004149529411764706, | |
| "loss": 2.851, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 12.47, | |
| "learning_rate": 0.00041201470588235294, | |
| "loss": 2.8564, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "learning_rate": 0.00040907352941176473, | |
| "loss": 2.8575, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 0.00040613235294117647, | |
| "loss": 2.8597, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 0.0004031941176470588, | |
| "loss": 2.862, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "learning_rate": 0.0004002529411764706, | |
| "loss": 2.8681, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 12.74, | |
| "learning_rate": 0.00039731176470588235, | |
| "loss": 2.8676, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 0.00039437058823529414, | |
| "loss": 2.8679, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 12.85, | |
| "learning_rate": 0.00039143235294117644, | |
| "loss": 2.8722, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 0.00038849117647058823, | |
| "loss": 2.8704, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 0.00038555294117647063, | |
| "loss": 2.8698, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4124001019554951, | |
| "eval_loss": 3.334566593170166, | |
| "eval_runtime": 153.4386, | |
| "eval_samples_per_second": 377.467, | |
| "eval_steps_per_second": 5.898, | |
| "step": 241800 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 0.00038261176470588237, | |
| "loss": 2.8591, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 0.0003796735294117647, | |
| "loss": 2.8145, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 0.00037673235294117646, | |
| "loss": 2.8202, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 13.17, | |
| "learning_rate": 0.00037379117647058825, | |
| "loss": 2.8253, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 0.0003708529411764706, | |
| "loss": 2.8266, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 0.00036791176470588234, | |
| "loss": 2.828, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 0.00036497058823529413, | |
| "loss": 2.8293, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "learning_rate": 0.00036202941176470587, | |
| "loss": 2.8366, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 0.00035909411764705883, | |
| "loss": 2.833, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 13.49, | |
| "learning_rate": 0.00035615294117647057, | |
| "loss": 2.8374, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "learning_rate": 0.00035321176470588236, | |
| "loss": 2.8412, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 0.0003502735294117647, | |
| "loss": 2.8395, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 0.0003473323529411765, | |
| "loss": 2.8447, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 0.00034439117647058824, | |
| "loss": 2.8452, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 0.00034145, | |
| "loss": 2.8468, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 0.00033850882352941177, | |
| "loss": 2.8423, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "learning_rate": 0.00033557352941176473, | |
| "loss": 2.8491, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 0.0003326352941176471, | |
| "loss": 2.8509, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "learning_rate": 0.0003296941176470588, | |
| "loss": 2.8466, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.41103603739783456, | |
| "eval_loss": 3.3659889698028564, | |
| "eval_runtime": 153.5876, | |
| "eval_samples_per_second": 377.101, | |
| "eval_steps_per_second": 5.892, | |
| "step": 260400 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 0.0003267529411764706, | |
| "loss": 2.8134, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 0.00032381176470588235, | |
| "loss": 2.7979, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 0.00032087352941176475, | |
| "loss": 2.8031, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 0.00031793235294117644, | |
| "loss": 2.8053, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 0.00031499117647058823, | |
| "loss": 2.8064, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 0.00031205, | |
| "loss": 2.8108, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 14.35, | |
| "learning_rate": 0.000309114705882353, | |
| "loss": 2.813, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 0.0003061764705882353, | |
| "loss": 2.8169, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 14.46, | |
| "learning_rate": 0.0003032352941176471, | |
| "loss": 2.8133, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 0.0003002941176470588, | |
| "loss": 2.8175, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 0.0002973529411764706, | |
| "loss": 2.8211, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 0.0002944117647058824, | |
| "loss": 2.8244, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 0.0002914705882352941, | |
| "loss": 2.824, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 0.00028852941176470587, | |
| "loss": 2.8284, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 14.78, | |
| "learning_rate": 0.00028558823529411766, | |
| "loss": 2.8244, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 0.00028265, | |
| "loss": 2.8288, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 0.0002797088235294118, | |
| "loss": 2.8286, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 0.0002767705882352941, | |
| "loss": 2.8313, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 0.0002738294117647059, | |
| "loss": 2.8253, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4127363481686103, | |
| "eval_loss": 3.3566222190856934, | |
| "eval_runtime": 154.4389, | |
| "eval_samples_per_second": 375.022, | |
| "eval_steps_per_second": 5.86, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 0.00027088823529411763, | |
| "loss": 2.7791, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 0.00026795000000000003, | |
| "loss": 2.7812, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 0.00026500882352941177, | |
| "loss": 2.7858, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 0.0002620705882352941, | |
| "loss": 2.7945, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 0.0002591294117647059, | |
| "loss": 2.7885, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 15.32, | |
| "learning_rate": 0.00025619117647058827, | |
| "loss": 2.7939, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 0.00025325, | |
| "loss": 2.7941, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 15.43, | |
| "learning_rate": 0.00025031176470588235, | |
| "loss": 2.8015, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 15.48, | |
| "learning_rate": 0.00024737058823529415, | |
| "loss": 2.8007, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 0.0002444294117647059, | |
| "loss": 2.8006, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 0.00024148823529411765, | |
| "loss": 2.8011, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 15.65, | |
| "learning_rate": 0.00023855000000000003, | |
| "loss": 2.8047, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "learning_rate": 0.00023560882352941176, | |
| "loss": 2.8052, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "learning_rate": 0.00023267058823529414, | |
| "loss": 2.8025, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 15.81, | |
| "learning_rate": 0.00022972941176470588, | |
| "loss": 2.8028, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 0.00022679117647058826, | |
| "loss": 2.8107, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "learning_rate": 0.00022385, | |
| "loss": 2.8037, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 0.00022091176470588237, | |
| "loss": 2.8058, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.41131376803619984, | |
| "eval_loss": 3.378085136413574, | |
| "eval_runtime": 153.1864, | |
| "eval_samples_per_second": 378.088, | |
| "eval_steps_per_second": 5.908, | |
| "step": 297600 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 0.0002179705882352941, | |
| "loss": 2.7912, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 16.08, | |
| "learning_rate": 0.0002150294117647059, | |
| "loss": 2.7613, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 16.13, | |
| "learning_rate": 0.00021208823529411767, | |
| "loss": 2.7684, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 0.00020915000000000002, | |
| "loss": 2.769, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 16.24, | |
| "learning_rate": 0.00020621176470588234, | |
| "loss": 2.7768, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 16.29, | |
| "learning_rate": 0.00020327058823529413, | |
| "loss": 2.7762, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "learning_rate": 0.0002003294117647059, | |
| "loss": 2.7738, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "learning_rate": 0.00019739117647058825, | |
| "loss": 2.7754, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 16.45, | |
| "learning_rate": 0.00019445, | |
| "loss": 2.7823, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "learning_rate": 0.00019151176470588236, | |
| "loss": 2.7826, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 16.56, | |
| "learning_rate": 0.00018857058823529413, | |
| "loss": 2.7848, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 16.61, | |
| "learning_rate": 0.0001856294117647059, | |
| "loss": 2.7803, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 0.00018268823529411766, | |
| "loss": 2.7872, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "learning_rate": 0.0001797470588235294, | |
| "loss": 2.787, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 16.77, | |
| "learning_rate": 0.00017680882352941177, | |
| "loss": 2.785, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 0.0001738676470588235, | |
| "loss": 2.7892, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 16.88, | |
| "learning_rate": 0.0001709264705882353, | |
| "loss": 2.7841, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "learning_rate": 0.00016798529411764707, | |
| "loss": 2.7881, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "learning_rate": 0.00016504705882352942, | |
| "loss": 2.7908, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.41194850414439416, | |
| "eval_loss": 3.385124444961548, | |
| "eval_runtime": 153.7223, | |
| "eval_samples_per_second": 376.77, | |
| "eval_steps_per_second": 5.887, | |
| "step": 316200 | |
| }, | |
| { | |
| "epoch": 17.04, | |
| "learning_rate": 0.00016211176470588235, | |
| "loss": 2.7549, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 0.00015917058823529412, | |
| "loss": 2.7526, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 17.15, | |
| "learning_rate": 0.0001562294117647059, | |
| "loss": 2.7539, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 17.2, | |
| "learning_rate": 0.00015329117647058823, | |
| "loss": 2.7572, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 17.26, | |
| "learning_rate": 0.00015035000000000002, | |
| "loss": 2.7556, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 17.31, | |
| "learning_rate": 0.00014740882352941176, | |
| "loss": 2.7586, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 17.37, | |
| "learning_rate": 0.00014446764705882353, | |
| "loss": 2.7568, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 17.42, | |
| "learning_rate": 0.0001415264705882353, | |
| "loss": 2.7627, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 17.47, | |
| "learning_rate": 0.00013858823529411764, | |
| "loss": 2.7655, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 0.0001356470588235294, | |
| "loss": 2.7653, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 17.58, | |
| "learning_rate": 0.00013270588235294117, | |
| "loss": 2.7651, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.00012976764705882355, | |
| "loss": 2.7704, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 17.69, | |
| "learning_rate": 0.00012682647058823529, | |
| "loss": 2.7669, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 17.74, | |
| "learning_rate": 0.00012388823529411764, | |
| "loss": 2.7659, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 0.00012094705882352941, | |
| "loss": 2.7658, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 17.85, | |
| "learning_rate": 0.00011800588235294118, | |
| "loss": 2.7708, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 17.9, | |
| "learning_rate": 0.00011506764705882353, | |
| "loss": 2.7669, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 17.96, | |
| "learning_rate": 0.00011212647058823531, | |
| "loss": 2.7701, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.41275025485514677, | |
| "eval_loss": 3.3872385025024414, | |
| "eval_runtime": 153.0517, | |
| "eval_samples_per_second": 378.421, | |
| "eval_steps_per_second": 5.913, | |
| "step": 334800 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 0.00010918529411764706, | |
| "loss": 2.7633, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "learning_rate": 0.00010624411764705882, | |
| "loss": 2.7371, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 18.12, | |
| "learning_rate": 0.00010330588235294117, | |
| "loss": 2.7362, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 18.17, | |
| "learning_rate": 0.00010036470588235294, | |
| "loss": 2.7389, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 18.23, | |
| "learning_rate": 9.74264705882353e-05, | |
| "loss": 2.7427, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 18.28, | |
| "learning_rate": 9.448529411764705e-05, | |
| "loss": 2.7458, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 18.33, | |
| "learning_rate": 9.154411764705882e-05, | |
| "loss": 2.7439, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 18.39, | |
| "learning_rate": 8.860588235294117e-05, | |
| "loss": 2.7465, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 18.44, | |
| "learning_rate": 8.566470588235293e-05, | |
| "loss": 2.7453, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 18.49, | |
| "learning_rate": 8.27264705882353e-05, | |
| "loss": 2.7531, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 18.55, | |
| "learning_rate": 7.978529411764706e-05, | |
| "loss": 2.7479, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 18.6, | |
| "learning_rate": 7.684411764705883e-05, | |
| "loss": 2.7496, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 7.390294117647059e-05, | |
| "loss": 2.7496, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 18.71, | |
| "learning_rate": 7.096470588235294e-05, | |
| "loss": 2.7498, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 18.76, | |
| "learning_rate": 6.80264705882353e-05, | |
| "loss": 2.7499, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 18.82, | |
| "learning_rate": 6.508529411764706e-05, | |
| "loss": 2.7466, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 18.87, | |
| "learning_rate": 6.214411764705882e-05, | |
| "loss": 2.7539, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "learning_rate": 5.920588235294118e-05, | |
| "loss": 2.7515, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "learning_rate": 5.626470588235294e-05, | |
| "loss": 2.7511, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.41200177951842015, | |
| "eval_loss": 3.403754472732544, | |
| "eval_runtime": 153.7263, | |
| "eval_samples_per_second": 376.76, | |
| "eval_steps_per_second": 5.887, | |
| "step": 353400 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 5.332352941176471e-05, | |
| "loss": 2.7378, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 19.09, | |
| "learning_rate": 5.038529411764706e-05, | |
| "loss": 2.7307, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 19.14, | |
| "learning_rate": 4.7444117647058824e-05, | |
| "loss": 2.7299, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 19.19, | |
| "learning_rate": 4.450294117647059e-05, | |
| "loss": 2.7367, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 19.25, | |
| "learning_rate": 4.156470588235294e-05, | |
| "loss": 2.731, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 19.3, | |
| "learning_rate": 3.862352941176471e-05, | |
| "loss": 2.7302, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "learning_rate": 3.568529411764706e-05, | |
| "loss": 2.7275, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 19.41, | |
| "learning_rate": 3.2744117647058826e-05, | |
| "loss": 2.7326, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 19.46, | |
| "learning_rate": 2.9805882352941176e-05, | |
| "loss": 2.7306, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 2.686470588235294e-05, | |
| "loss": 2.731, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 2.3923529411764706e-05, | |
| "loss": 2.7339, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 19.62, | |
| "learning_rate": 2.098235294117647e-05, | |
| "loss": 2.7355, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 1.8041176470588236e-05, | |
| "loss": 2.7329, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 19.73, | |
| "learning_rate": 1.5100000000000001e-05, | |
| "loss": 2.731, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 19.78, | |
| "learning_rate": 1.2161764705882353e-05, | |
| "loss": 2.7359, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 9.223529411764705e-06, | |
| "loss": 2.7291, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 19.89, | |
| "learning_rate": 6.2823529411764705e-06, | |
| "loss": 2.731, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "learning_rate": 3.3411764705882354e-06, | |
| "loss": 2.7347, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 2.7292, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.4118896526593414, | |
| "eval_loss": 3.411447286605835, | |
| "eval_runtime": 153.7365, | |
| "eval_samples_per_second": 376.736, | |
| "eval_steps_per_second": 5.887, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 372000, | |
| "total_flos": 1.56732865394688e+18, | |
| "train_loss": 3.009390573809224, | |
| "train_runtime": 81008.6007, | |
| "train_samples_per_second": 146.944, | |
| "train_steps_per_second": 4.592 | |
| } | |
| ], | |
| "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 | |
| } | |