| { | |
| "best_metric": 0.7140286564826965, | |
| "best_model_checkpoint": "data/Llama-31-8B_task-2_180-samples_config-3/checkpoint-323", | |
| "epoch": 26.0, | |
| "eval_steps": 500, | |
| "global_step": 442, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 0.7734732031822205, | |
| "learning_rate": 3.9215686274509804e-08, | |
| "loss": 1.1412, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.6782335638999939, | |
| "learning_rate": 7.843137254901961e-08, | |
| "loss": 1.1733, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.8408952951431274, | |
| "learning_rate": 1.5686274509803921e-07, | |
| "loss": 1.1666, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 0.7287867069244385, | |
| "learning_rate": 2.3529411764705883e-07, | |
| "loss": 1.1801, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.7565770745277405, | |
| "learning_rate": 3.1372549019607843e-07, | |
| "loss": 1.1116, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.6836811304092407, | |
| "learning_rate": 3.921568627450981e-07, | |
| "loss": 1.1475, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.6788910627365112, | |
| "learning_rate": 4.7058823529411767e-07, | |
| "loss": 1.0752, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 0.6463932991027832, | |
| "learning_rate": 5.490196078431373e-07, | |
| "loss": 1.1428, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.7503110766410828, | |
| "learning_rate": 6.274509803921569e-07, | |
| "loss": 1.0365, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.131649374961853, | |
| "eval_runtime": 37.0173, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 0.7130016088485718, | |
| "learning_rate": 7.058823529411766e-07, | |
| "loss": 1.1439, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.69338458776474, | |
| "learning_rate": 7.843137254901962e-07, | |
| "loss": 1.1374, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 0.6517343521118164, | |
| "learning_rate": 8.627450980392157e-07, | |
| "loss": 1.1213, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.685614287853241, | |
| "learning_rate": 9.411764705882353e-07, | |
| "loss": 1.1182, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5294117647058822, | |
| "grad_norm": 0.6998293995857239, | |
| "learning_rate": 1.019607843137255e-06, | |
| "loss": 1.0508, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.6757376194000244, | |
| "learning_rate": 1.0980392156862745e-06, | |
| "loss": 1.0773, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.7003068327903748, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 1.1765, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.75652676820755, | |
| "learning_rate": 1.2549019607843137e-06, | |
| "loss": 1.0897, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.8910195231437683, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 1.1746, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.119631290435791, | |
| "eval_runtime": 37.0058, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.6963354349136353, | |
| "learning_rate": 1.4117647058823531e-06, | |
| "loss": 1.0914, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.6639174818992615, | |
| "learning_rate": 1.4901960784313726e-06, | |
| "loss": 1.1038, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.7396222949028015, | |
| "learning_rate": 1.5686274509803923e-06, | |
| "loss": 1.0596, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.7213342189788818, | |
| "learning_rate": 1.6470588235294118e-06, | |
| "loss": 1.0962, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 0.7507779002189636, | |
| "learning_rate": 1.7254901960784315e-06, | |
| "loss": 1.0945, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.803626298904419, | |
| "learning_rate": 1.8039215686274512e-06, | |
| "loss": 1.1417, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 0.8166558742523193, | |
| "learning_rate": 1.8823529411764707e-06, | |
| "loss": 1.1391, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.7504469752311707, | |
| "learning_rate": 1.96078431372549e-06, | |
| "loss": 1.0933, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.0957257747650146, | |
| "eval_runtime": 37.0081, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0588235294117645, | |
| "grad_norm": 0.7341092228889465, | |
| "learning_rate": 2.03921568627451e-06, | |
| "loss": 1.0645, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.176470588235294, | |
| "grad_norm": 0.7262235283851624, | |
| "learning_rate": 2.1176470588235296e-06, | |
| "loss": 1.1047, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.2941176470588234, | |
| "grad_norm": 0.6933767795562744, | |
| "learning_rate": 2.196078431372549e-06, | |
| "loss": 1.0305, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.411764705882353, | |
| "grad_norm": 0.8481059670448303, | |
| "learning_rate": 2.274509803921569e-06, | |
| "loss": 1.1403, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 0.7597863078117371, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 1.0537, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.6470588235294117, | |
| "grad_norm": 0.7542691826820374, | |
| "learning_rate": 2.431372549019608e-06, | |
| "loss": 1.0815, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.764705882352941, | |
| "grad_norm": 0.7457835674285889, | |
| "learning_rate": 2.5098039215686274e-06, | |
| "loss": 1.0747, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.8823529411764706, | |
| "grad_norm": 0.6987655758857727, | |
| "learning_rate": 2.5882352941176473e-06, | |
| "loss": 1.1015, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.7653221487998962, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 0.985, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.0540263652801514, | |
| "eval_runtime": 37.0036, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.117647058823529, | |
| "grad_norm": 0.6138588190078735, | |
| "learning_rate": 2.7450980392156867e-06, | |
| "loss": 1.0818, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.235294117647059, | |
| "grad_norm": 0.7161767482757568, | |
| "learning_rate": 2.8235294117647062e-06, | |
| "loss": 1.0233, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.352941176470588, | |
| "grad_norm": 0.5691388845443726, | |
| "learning_rate": 2.901960784313726e-06, | |
| "loss": 1.0152, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.470588235294118, | |
| "grad_norm": 0.6562293171882629, | |
| "learning_rate": 2.980392156862745e-06, | |
| "loss": 1.0299, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.588235294117647, | |
| "grad_norm": 0.6522495150566101, | |
| "learning_rate": 3.058823529411765e-06, | |
| "loss": 1.0341, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.6249567270278931, | |
| "learning_rate": 3.1372549019607846e-06, | |
| "loss": 0.9573, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.823529411764706, | |
| "grad_norm": 0.6513485312461853, | |
| "learning_rate": 3.2156862745098045e-06, | |
| "loss": 1.0373, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.9411764705882355, | |
| "grad_norm": 0.6425153613090515, | |
| "learning_rate": 3.2941176470588236e-06, | |
| "loss": 0.9741, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.99503093957901, | |
| "eval_runtime": 37.0007, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.0588235294117645, | |
| "grad_norm": 0.645844042301178, | |
| "learning_rate": 3.3725490196078435e-06, | |
| "loss": 0.9862, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.176470588235294, | |
| "grad_norm": 0.6497894525527954, | |
| "learning_rate": 3.450980392156863e-06, | |
| "loss": 0.9873, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.294117647058823, | |
| "grad_norm": 0.5283099412918091, | |
| "learning_rate": 3.529411764705883e-06, | |
| "loss": 0.9488, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.411764705882353, | |
| "grad_norm": 0.4905494451522827, | |
| "learning_rate": 3.6078431372549024e-06, | |
| "loss": 0.9606, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.529411764705882, | |
| "grad_norm": 0.5407238602638245, | |
| "learning_rate": 3.6862745098039223e-06, | |
| "loss": 0.888, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 5.647058823529412, | |
| "grad_norm": 0.5735270977020264, | |
| "learning_rate": 3.7647058823529414e-06, | |
| "loss": 0.916, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 5.764705882352941, | |
| "grad_norm": 0.5201605558395386, | |
| "learning_rate": 3.843137254901962e-06, | |
| "loss": 0.982, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 0.4470115303993225, | |
| "learning_rate": 3.92156862745098e-06, | |
| "loss": 0.9389, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.3844221532344818, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.0008, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.937701940536499, | |
| "eval_runtime": 37.0036, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.117647058823529, | |
| "grad_norm": 0.4652542173862457, | |
| "learning_rate": 4.07843137254902e-06, | |
| "loss": 0.915, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 6.235294117647059, | |
| "grad_norm": 0.4144337773323059, | |
| "learning_rate": 4.15686274509804e-06, | |
| "loss": 0.8833, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 6.352941176470588, | |
| "grad_norm": 0.4218851327896118, | |
| "learning_rate": 4.235294117647059e-06, | |
| "loss": 0.8672, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 6.470588235294118, | |
| "grad_norm": 0.4070567786693573, | |
| "learning_rate": 4.313725490196079e-06, | |
| "loss": 0.9036, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.588235294117647, | |
| "grad_norm": 0.36765947937965393, | |
| "learning_rate": 4.392156862745098e-06, | |
| "loss": 0.9384, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 6.705882352941177, | |
| "grad_norm": 0.3613109886646271, | |
| "learning_rate": 4.4705882352941184e-06, | |
| "loss": 0.904, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.823529411764706, | |
| "grad_norm": 0.36222243309020996, | |
| "learning_rate": 4.549019607843138e-06, | |
| "loss": 0.8641, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 6.9411764705882355, | |
| "grad_norm": 0.42111915349960327, | |
| "learning_rate": 4.627450980392157e-06, | |
| "loss": 0.8935, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.8938563466072083, | |
| "eval_runtime": 37.0541, | |
| "eval_samples_per_second": 0.972, | |
| "eval_steps_per_second": 0.972, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 0.35050034523010254, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 0.9626, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.176470588235294, | |
| "grad_norm": 0.37680429220199585, | |
| "learning_rate": 4.784313725490196e-06, | |
| "loss": 0.8818, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 7.294117647058823, | |
| "grad_norm": 0.3310965895652771, | |
| "learning_rate": 4.862745098039216e-06, | |
| "loss": 0.8631, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 7.411764705882353, | |
| "grad_norm": 0.3843957781791687, | |
| "learning_rate": 4.941176470588236e-06, | |
| "loss": 0.8506, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 7.529411764705882, | |
| "grad_norm": 0.3577839732170105, | |
| "learning_rate": 5.019607843137255e-06, | |
| "loss": 0.841, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 7.647058823529412, | |
| "grad_norm": 0.3117690682411194, | |
| "learning_rate": 5.098039215686274e-06, | |
| "loss": 0.8576, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.764705882352941, | |
| "grad_norm": 0.37441667914390564, | |
| "learning_rate": 5.176470588235295e-06, | |
| "loss": 0.8127, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 7.882352941176471, | |
| "grad_norm": 0.3178256154060364, | |
| "learning_rate": 5.254901960784314e-06, | |
| "loss": 0.8554, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.3216207027435303, | |
| "learning_rate": 5.333333333333334e-06, | |
| "loss": 0.8862, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.8579282760620117, | |
| "eval_runtime": 37.0044, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.117647058823529, | |
| "grad_norm": 0.341949462890625, | |
| "learning_rate": 5.411764705882353e-06, | |
| "loss": 0.8519, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 8.235294117647058, | |
| "grad_norm": 0.3150944113731384, | |
| "learning_rate": 5.4901960784313735e-06, | |
| "loss": 0.8338, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.352941176470589, | |
| "grad_norm": 0.3646303713321686, | |
| "learning_rate": 5.568627450980393e-06, | |
| "loss": 0.8381, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 8.470588235294118, | |
| "grad_norm": 0.334943950176239, | |
| "learning_rate": 5.6470588235294125e-06, | |
| "loss": 0.879, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 8.588235294117647, | |
| "grad_norm": 0.3029642403125763, | |
| "learning_rate": 5.725490196078431e-06, | |
| "loss": 0.7807, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 8.705882352941176, | |
| "grad_norm": 0.30906420946121216, | |
| "learning_rate": 5.803921568627452e-06, | |
| "loss": 0.7946, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 8.823529411764707, | |
| "grad_norm": 0.34527918696403503, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 0.8397, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.941176470588236, | |
| "grad_norm": 0.3913155794143677, | |
| "learning_rate": 5.96078431372549e-06, | |
| "loss": 0.8266, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.8293797969818115, | |
| "eval_runtime": 37.0023, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.058823529411764, | |
| "grad_norm": 0.3411412835121155, | |
| "learning_rate": 6.03921568627451e-06, | |
| "loss": 0.8249, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 9.176470588235293, | |
| "grad_norm": 0.28964897990226746, | |
| "learning_rate": 6.11764705882353e-06, | |
| "loss": 0.7887, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 9.294117647058824, | |
| "grad_norm": 0.36540400981903076, | |
| "learning_rate": 6.19607843137255e-06, | |
| "loss": 0.7434, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 0.3152979016304016, | |
| "learning_rate": 6.274509803921569e-06, | |
| "loss": 0.7864, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.529411764705882, | |
| "grad_norm": 0.28152012825012207, | |
| "learning_rate": 6.352941176470589e-06, | |
| "loss": 0.777, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 9.647058823529411, | |
| "grad_norm": 0.37814223766326904, | |
| "learning_rate": 6.431372549019609e-06, | |
| "loss": 0.8319, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 9.764705882352942, | |
| "grad_norm": 0.3085719645023346, | |
| "learning_rate": 6.5098039215686285e-06, | |
| "loss": 0.7986, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 9.882352941176471, | |
| "grad_norm": 0.29185226559638977, | |
| "learning_rate": 6.588235294117647e-06, | |
| "loss": 0.8292, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.30540931224823, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.7797, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.807489275932312, | |
| "eval_runtime": 37.0049, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.117647058823529, | |
| "grad_norm": 0.3091186285018921, | |
| "learning_rate": 6.745098039215687e-06, | |
| "loss": 0.7765, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 10.235294117647058, | |
| "grad_norm": 0.30727335810661316, | |
| "learning_rate": 6.8235294117647065e-06, | |
| "loss": 0.7505, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 10.352941176470589, | |
| "grad_norm": 0.2999902665615082, | |
| "learning_rate": 6.901960784313726e-06, | |
| "loss": 0.7233, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 10.470588235294118, | |
| "grad_norm": 0.2925303876399994, | |
| "learning_rate": 6.9803921568627454e-06, | |
| "loss": 0.7613, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 10.588235294117647, | |
| "grad_norm": 0.28137609362602234, | |
| "learning_rate": 7.058823529411766e-06, | |
| "loss": 0.7336, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 10.705882352941176, | |
| "grad_norm": 0.3438097834587097, | |
| "learning_rate": 7.137254901960785e-06, | |
| "loss": 0.822, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 10.823529411764707, | |
| "grad_norm": 0.3309740722179413, | |
| "learning_rate": 7.215686274509805e-06, | |
| "loss": 0.8488, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 10.941176470588236, | |
| "grad_norm": 0.33822691440582275, | |
| "learning_rate": 7.294117647058823e-06, | |
| "loss": 0.8158, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.790329098701477, | |
| "eval_runtime": 37.0086, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.058823529411764, | |
| "grad_norm": 0.3196800649166107, | |
| "learning_rate": 7.372549019607845e-06, | |
| "loss": 0.7996, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 11.176470588235293, | |
| "grad_norm": 0.2967463731765747, | |
| "learning_rate": 7.450980392156863e-06, | |
| "loss": 0.7102, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.294117647058824, | |
| "grad_norm": 0.32051464915275574, | |
| "learning_rate": 7.529411764705883e-06, | |
| "loss": 0.8008, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 11.411764705882353, | |
| "grad_norm": 0.399475634098053, | |
| "learning_rate": 7.607843137254902e-06, | |
| "loss": 0.8271, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 11.529411764705882, | |
| "grad_norm": 0.3100043535232544, | |
| "learning_rate": 7.686274509803923e-06, | |
| "loss": 0.7954, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 11.647058823529411, | |
| "grad_norm": 0.31522953510284424, | |
| "learning_rate": 7.764705882352941e-06, | |
| "loss": 0.712, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 0.3450244665145874, | |
| "learning_rate": 7.84313725490196e-06, | |
| "loss": 0.7329, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.882352941176471, | |
| "grad_norm": 0.3267311453819275, | |
| "learning_rate": 7.92156862745098e-06, | |
| "loss": 0.7275, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.42111936211586, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.6845, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.7741987705230713, | |
| "eval_runtime": 37.0028, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.117647058823529, | |
| "grad_norm": 0.33904674649238586, | |
| "learning_rate": 8.07843137254902e-06, | |
| "loss": 0.7635, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 12.235294117647058, | |
| "grad_norm": 0.33812686800956726, | |
| "learning_rate": 8.15686274509804e-06, | |
| "loss": 0.8239, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 12.352941176470589, | |
| "grad_norm": 0.34535664319992065, | |
| "learning_rate": 8.23529411764706e-06, | |
| "loss": 0.7084, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.470588235294118, | |
| "grad_norm": 0.330837219953537, | |
| "learning_rate": 8.31372549019608e-06, | |
| "loss": 0.6769, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 12.588235294117647, | |
| "grad_norm": 0.31368908286094666, | |
| "learning_rate": 8.392156862745099e-06, | |
| "loss": 0.7651, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 12.705882352941176, | |
| "grad_norm": 0.35061123967170715, | |
| "learning_rate": 8.470588235294118e-06, | |
| "loss": 0.7452, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 12.823529411764707, | |
| "grad_norm": 0.32111451029777527, | |
| "learning_rate": 8.549019607843138e-06, | |
| "loss": 0.718, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 12.941176470588236, | |
| "grad_norm": 0.3150181174278259, | |
| "learning_rate": 8.627450980392157e-06, | |
| "loss": 0.6819, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.7598351240158081, | |
| "eval_runtime": 37.0068, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 13.058823529411764, | |
| "grad_norm": 0.3078894019126892, | |
| "learning_rate": 8.705882352941177e-06, | |
| "loss": 0.7151, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 13.176470588235293, | |
| "grad_norm": 0.3273066282272339, | |
| "learning_rate": 8.784313725490196e-06, | |
| "loss": 0.6766, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 13.294117647058824, | |
| "grad_norm": 0.30240604281425476, | |
| "learning_rate": 8.862745098039216e-06, | |
| "loss": 0.665, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 13.411764705882353, | |
| "grad_norm": 0.3365361988544464, | |
| "learning_rate": 8.941176470588237e-06, | |
| "loss": 0.73, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 13.529411764705882, | |
| "grad_norm": 0.3776240646839142, | |
| "learning_rate": 9.019607843137256e-06, | |
| "loss": 0.7319, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 13.647058823529411, | |
| "grad_norm": 0.32826074957847595, | |
| "learning_rate": 9.098039215686276e-06, | |
| "loss": 0.7021, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 13.764705882352942, | |
| "grad_norm": 0.3192596435546875, | |
| "learning_rate": 9.176470588235294e-06, | |
| "loss": 0.7333, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 13.882352941176471, | |
| "grad_norm": 0.36111271381378174, | |
| "learning_rate": 9.254901960784315e-06, | |
| "loss": 0.7633, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 0.3694405257701874, | |
| "learning_rate": 9.333333333333334e-06, | |
| "loss": 0.7241, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.7471711039543152, | |
| "eval_runtime": 37.0047, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 14.117647058823529, | |
| "grad_norm": 0.3688935339450836, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 0.742, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 14.235294117647058, | |
| "grad_norm": 0.41638877987861633, | |
| "learning_rate": 9.490196078431373e-06, | |
| "loss": 0.7049, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 14.352941176470589, | |
| "grad_norm": 0.3489099442958832, | |
| "learning_rate": 9.568627450980393e-06, | |
| "loss": 0.6517, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 14.470588235294118, | |
| "grad_norm": 0.3671415448188782, | |
| "learning_rate": 9.647058823529412e-06, | |
| "loss": 0.7233, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 14.588235294117647, | |
| "grad_norm": 0.37552204728126526, | |
| "learning_rate": 9.725490196078432e-06, | |
| "loss": 0.701, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 14.705882352941176, | |
| "grad_norm": 0.43261757493019104, | |
| "learning_rate": 9.803921568627451e-06, | |
| "loss": 0.6979, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 14.823529411764707, | |
| "grad_norm": 0.37599849700927734, | |
| "learning_rate": 9.882352941176472e-06, | |
| "loss": 0.6462, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 14.941176470588236, | |
| "grad_norm": 0.3583243191242218, | |
| "learning_rate": 9.960784313725492e-06, | |
| "loss": 0.695, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.7365108132362366, | |
| "eval_runtime": 37.003, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 15.058823529411764, | |
| "grad_norm": 0.4206070005893707, | |
| "learning_rate": 9.999995315380667e-06, | |
| "loss": 0.6862, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 15.176470588235293, | |
| "grad_norm": 0.47259286046028137, | |
| "learning_rate": 9.99995783847866e-06, | |
| "loss": 0.6933, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 15.294117647058824, | |
| "grad_norm": 0.3962372839450836, | |
| "learning_rate": 9.999882884955554e-06, | |
| "loss": 0.6643, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 15.411764705882353, | |
| "grad_norm": 0.37228551506996155, | |
| "learning_rate": 9.99977045537315e-06, | |
| "loss": 0.6676, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 15.529411764705882, | |
| "grad_norm": 0.4293304979801178, | |
| "learning_rate": 9.999620550574155e-06, | |
| "loss": 0.6497, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 15.647058823529411, | |
| "grad_norm": 0.4316819906234741, | |
| "learning_rate": 9.999433171682158e-06, | |
| "loss": 0.6687, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 15.764705882352942, | |
| "grad_norm": 0.4474015533924103, | |
| "learning_rate": 9.999208320101643e-06, | |
| "loss": 0.6935, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 15.882352941176471, | |
| "grad_norm": 0.4514879584312439, | |
| "learning_rate": 9.998945997517957e-06, | |
| "loss": 0.6542, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 0.5015867948532104, | |
| "learning_rate": 9.99864620589731e-06, | |
| "loss": 0.6982, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.7271888256072998, | |
| "eval_runtime": 37.0158, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 16.11764705882353, | |
| "grad_norm": 0.5128858685493469, | |
| "learning_rate": 9.998308947486753e-06, | |
| "loss": 0.6414, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 16.235294117647058, | |
| "grad_norm": 0.40119990706443787, | |
| "learning_rate": 9.997934224814173e-06, | |
| "loss": 0.628, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 16.352941176470587, | |
| "grad_norm": 0.4133683145046234, | |
| "learning_rate": 9.997522040688258e-06, | |
| "loss": 0.7072, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 16.470588235294116, | |
| "grad_norm": 0.41614237427711487, | |
| "learning_rate": 9.997072398198492e-06, | |
| "loss": 0.6526, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 16.58823529411765, | |
| "grad_norm": 0.4795832931995392, | |
| "learning_rate": 9.996585300715117e-06, | |
| "loss": 0.6583, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 16.705882352941178, | |
| "grad_norm": 0.4348108470439911, | |
| "learning_rate": 9.996060751889114e-06, | |
| "loss": 0.6728, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 16.823529411764707, | |
| "grad_norm": 0.4476607143878937, | |
| "learning_rate": 9.995498755652186e-06, | |
| "loss": 0.626, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 16.941176470588236, | |
| "grad_norm": 0.4528913199901581, | |
| "learning_rate": 9.994899316216709e-06, | |
| "loss": 0.622, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.7215262055397034, | |
| "eval_runtime": 36.9993, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 17.058823529411764, | |
| "grad_norm": 0.5009466409683228, | |
| "learning_rate": 9.994262438075713e-06, | |
| "loss": 0.7081, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 17.176470588235293, | |
| "grad_norm": 0.475374698638916, | |
| "learning_rate": 9.993588126002848e-06, | |
| "loss": 0.6229, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 17.294117647058822, | |
| "grad_norm": 0.4642236828804016, | |
| "learning_rate": 9.992876385052346e-06, | |
| "loss": 0.5844, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 17.41176470588235, | |
| "grad_norm": 0.4536580741405487, | |
| "learning_rate": 9.992127220558976e-06, | |
| "loss": 0.6135, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 17.529411764705884, | |
| "grad_norm": 0.45987674593925476, | |
| "learning_rate": 9.991340638138022e-06, | |
| "loss": 0.6511, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 17.647058823529413, | |
| "grad_norm": 0.4978199899196625, | |
| "learning_rate": 9.990516643685222e-06, | |
| "loss": 0.6424, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 17.764705882352942, | |
| "grad_norm": 0.49036839604377747, | |
| "learning_rate": 9.98965524337673e-06, | |
| "loss": 0.6773, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 17.88235294117647, | |
| "grad_norm": 0.5300158858299255, | |
| "learning_rate": 9.988756443669081e-06, | |
| "loss": 0.6364, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "grad_norm": 0.4950679540634155, | |
| "learning_rate": 9.987820251299121e-06, | |
| "loss": 0.5905, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.7155699133872986, | |
| "eval_runtime": 37.0042, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 18.11764705882353, | |
| "grad_norm": 0.5069499611854553, | |
| "learning_rate": 9.98684667328398e-06, | |
| "loss": 0.6123, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 18.235294117647058, | |
| "grad_norm": 0.46550482511520386, | |
| "learning_rate": 9.985835716921e-06, | |
| "loss": 0.6102, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 18.352941176470587, | |
| "grad_norm": 0.7860422730445862, | |
| "learning_rate": 9.984787389787689e-06, | |
| "loss": 0.6273, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 18.470588235294116, | |
| "grad_norm": 0.49825742840766907, | |
| "learning_rate": 9.983701699741668e-06, | |
| "loss": 0.6297, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 18.58823529411765, | |
| "grad_norm": 0.5290573239326477, | |
| "learning_rate": 9.982578654920601e-06, | |
| "loss": 0.6238, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 18.705882352941178, | |
| "grad_norm": 0.5185476541519165, | |
| "learning_rate": 9.981418263742148e-06, | |
| "loss": 0.5702, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 18.823529411764707, | |
| "grad_norm": 0.5360794067382812, | |
| "learning_rate": 9.980220534903889e-06, | |
| "loss": 0.6082, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 18.941176470588236, | |
| "grad_norm": 0.5598728656768799, | |
| "learning_rate": 9.978985477383264e-06, | |
| "loss": 0.6121, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.7140286564826965, | |
| "eval_runtime": 36.9943, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 19.058823529411764, | |
| "grad_norm": 0.5005812048912048, | |
| "learning_rate": 9.97771310043751e-06, | |
| "loss": 0.5964, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 19.176470588235293, | |
| "grad_norm": 0.5243679881095886, | |
| "learning_rate": 9.97640341360358e-06, | |
| "loss": 0.643, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 19.294117647058822, | |
| "grad_norm": 0.5746588706970215, | |
| "learning_rate": 9.975056426698094e-06, | |
| "loss": 0.587, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 19.41176470588235, | |
| "grad_norm": 0.5213414430618286, | |
| "learning_rate": 9.973672149817232e-06, | |
| "loss": 0.5835, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 19.529411764705884, | |
| "grad_norm": 0.6261019706726074, | |
| "learning_rate": 9.972250593336689e-06, | |
| "loss": 0.5884, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 19.647058823529413, | |
| "grad_norm": 0.5905741453170776, | |
| "learning_rate": 9.970791767911581e-06, | |
| "loss": 0.588, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 19.764705882352942, | |
| "grad_norm": 0.5681843757629395, | |
| "learning_rate": 9.96929568447637e-06, | |
| "loss": 0.554, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 19.88235294117647, | |
| "grad_norm": 0.6130782961845398, | |
| "learning_rate": 9.967762354244778e-06, | |
| "loss": 0.6003, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.6039074659347534, | |
| "learning_rate": 9.966191788709716e-06, | |
| "loss": 0.567, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.7166150808334351, | |
| "eval_runtime": 36.9981, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 20.11764705882353, | |
| "grad_norm": 0.661340594291687, | |
| "learning_rate": 9.964583999643174e-06, | |
| "loss": 0.5771, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 20.235294117647058, | |
| "grad_norm": 0.6773268580436707, | |
| "learning_rate": 9.962938999096159e-06, | |
| "loss": 0.5611, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 20.352941176470587, | |
| "grad_norm": 0.6907221674919128, | |
| "learning_rate": 9.961256799398584e-06, | |
| "loss": 0.5961, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 20.470588235294116, | |
| "grad_norm": 0.6799242496490479, | |
| "learning_rate": 9.95953741315919e-06, | |
| "loss": 0.605, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 20.58823529411765, | |
| "grad_norm": 0.6507272720336914, | |
| "learning_rate": 9.957780853265441e-06, | |
| "loss": 0.5564, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 20.705882352941178, | |
| "grad_norm": 0.7043225765228271, | |
| "learning_rate": 9.955987132883435e-06, | |
| "loss": 0.5069, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 20.823529411764707, | |
| "grad_norm": 0.7170704007148743, | |
| "learning_rate": 9.954156265457801e-06, | |
| "loss": 0.5671, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 20.941176470588236, | |
| "grad_norm": 0.6098182797431946, | |
| "learning_rate": 9.952288264711601e-06, | |
| "loss": 0.5471, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.7171775698661804, | |
| "eval_runtime": 36.9995, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 21.058823529411764, | |
| "grad_norm": 0.7199786305427551, | |
| "learning_rate": 9.950383144646221e-06, | |
| "loss": 0.5856, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 21.176470588235293, | |
| "grad_norm": 0.748616635799408, | |
| "learning_rate": 9.948440919541277e-06, | |
| "loss": 0.5347, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 21.294117647058822, | |
| "grad_norm": 0.7035663723945618, | |
| "learning_rate": 9.946461603954499e-06, | |
| "loss": 0.5433, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 21.41176470588235, | |
| "grad_norm": 0.7293503880500793, | |
| "learning_rate": 9.944445212721619e-06, | |
| "loss": 0.5473, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 21.529411764705884, | |
| "grad_norm": 0.7407766580581665, | |
| "learning_rate": 9.942391760956277e-06, | |
| "loss": 0.527, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 21.647058823529413, | |
| "grad_norm": 0.7856358289718628, | |
| "learning_rate": 9.940301264049885e-06, | |
| "loss": 0.5372, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 21.764705882352942, | |
| "grad_norm": 0.7008533477783203, | |
| "learning_rate": 9.938173737671531e-06, | |
| "loss": 0.5375, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 21.88235294117647, | |
| "grad_norm": 0.7586143612861633, | |
| "learning_rate": 9.936009197767847e-06, | |
| "loss": 0.5467, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "grad_norm": 0.8423267602920532, | |
| "learning_rate": 9.933807660562898e-06, | |
| "loss": 0.4761, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.7233606576919556, | |
| "eval_runtime": 37.0054, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 22.11764705882353, | |
| "grad_norm": 0.882168710231781, | |
| "learning_rate": 9.931569142558057e-06, | |
| "loss": 0.562, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 22.235294117647058, | |
| "grad_norm": 0.8616783618927002, | |
| "learning_rate": 9.929293660531889e-06, | |
| "loss": 0.5039, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 22.352941176470587, | |
| "grad_norm": 0.9095832705497742, | |
| "learning_rate": 9.926981231540007e-06, | |
| "loss": 0.4744, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 22.470588235294116, | |
| "grad_norm": 0.8473853468894958, | |
| "learning_rate": 9.924631872914967e-06, | |
| "loss": 0.4976, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 22.58823529411765, | |
| "grad_norm": 0.844835102558136, | |
| "learning_rate": 9.922245602266119e-06, | |
| "loss": 0.4721, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 22.705882352941178, | |
| "grad_norm": 0.820750892162323, | |
| "learning_rate": 9.919822437479488e-06, | |
| "loss": 0.4995, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 22.823529411764707, | |
| "grad_norm": 0.823648989200592, | |
| "learning_rate": 9.91736239671763e-06, | |
| "loss": 0.5061, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 22.941176470588236, | |
| "grad_norm": 0.8103899359703064, | |
| "learning_rate": 9.91486549841951e-06, | |
| "loss": 0.4967, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.7357540726661682, | |
| "eval_runtime": 37.0101, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 23.058823529411764, | |
| "grad_norm": 0.7696477174758911, | |
| "learning_rate": 9.912331761300341e-06, | |
| "loss": 0.5004, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 23.176470588235293, | |
| "grad_norm": 0.7803938984870911, | |
| "learning_rate": 9.909761204351469e-06, | |
| "loss": 0.4903, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 23.294117647058822, | |
| "grad_norm": 0.9065766930580139, | |
| "learning_rate": 9.90715384684021e-06, | |
| "loss": 0.505, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 23.41176470588235, | |
| "grad_norm": 1.1152830123901367, | |
| "learning_rate": 9.904509708309723e-06, | |
| "loss": 0.4312, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 23.529411764705884, | |
| "grad_norm": 1.0776093006134033, | |
| "learning_rate": 9.901828808578846e-06, | |
| "loss": 0.4503, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 23.647058823529413, | |
| "grad_norm": 1.0322400331497192, | |
| "learning_rate": 9.899111167741966e-06, | |
| "loss": 0.4685, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 23.764705882352942, | |
| "grad_norm": 0.9414217472076416, | |
| "learning_rate": 9.896356806168851e-06, | |
| "loss": 0.4757, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 23.88235294117647, | |
| "grad_norm": 1.1830779314041138, | |
| "learning_rate": 9.89356574450451e-06, | |
| "loss": 0.4408, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 0.9795882105827332, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 0.4833, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.7643568515777588, | |
| "eval_runtime": 37.0004, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 24.11764705882353, | |
| "grad_norm": 1.2952356338500977, | |
| "learning_rate": 9.887873604857424e-06, | |
| "loss": 0.4299, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 24.235294117647058, | |
| "grad_norm": 1.2539509534835815, | |
| "learning_rate": 9.884972569539471e-06, | |
| "loss": 0.4488, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 24.352941176470587, | |
| "grad_norm": 1.0663094520568848, | |
| "learning_rate": 9.882034919459556e-06, | |
| "loss": 0.4152, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 24.470588235294116, | |
| "grad_norm": 1.03883957862854, | |
| "learning_rate": 9.879060676636502e-06, | |
| "loss": 0.4435, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 24.58823529411765, | |
| "grad_norm": 0.9475598931312561, | |
| "learning_rate": 9.876049863363415e-06, | |
| "loss": 0.4408, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 24.705882352941178, | |
| "grad_norm": 0.9946249723434448, | |
| "learning_rate": 9.873002502207502e-06, | |
| "loss": 0.4292, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 24.823529411764707, | |
| "grad_norm": 1.135332465171814, | |
| "learning_rate": 9.86991861600992e-06, | |
| "loss": 0.4057, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 24.941176470588236, | |
| "grad_norm": 1.7003220319747925, | |
| "learning_rate": 9.866798227885588e-06, | |
| "loss": 0.4071, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.8012258410453796, | |
| "eval_runtime": 37.0059, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 25.058823529411764, | |
| "grad_norm": 1.124939203262329, | |
| "learning_rate": 9.863641361223025e-06, | |
| "loss": 0.3795, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 25.176470588235293, | |
| "grad_norm": 1.2946455478668213, | |
| "learning_rate": 9.860448039684169e-06, | |
| "loss": 0.3631, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 25.294117647058822, | |
| "grad_norm": 1.2063255310058594, | |
| "learning_rate": 9.857218287204204e-06, | |
| "loss": 0.3786, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 25.41176470588235, | |
| "grad_norm": 1.1833475828170776, | |
| "learning_rate": 9.853952127991374e-06, | |
| "loss": 0.403, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 25.529411764705884, | |
| "grad_norm": 1.2458750009536743, | |
| "learning_rate": 9.850649586526808e-06, | |
| "loss": 0.3626, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 25.647058823529413, | |
| "grad_norm": 1.2201582193374634, | |
| "learning_rate": 9.847310687564335e-06, | |
| "loss": 0.3774, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 25.764705882352942, | |
| "grad_norm": 1.2703592777252197, | |
| "learning_rate": 9.843935456130295e-06, | |
| "loss": 0.4078, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 25.88235294117647, | |
| "grad_norm": 1.8023614883422852, | |
| "learning_rate": 9.840523917523354e-06, | |
| "loss": 0.406, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "grad_norm": 1.3355423212051392, | |
| "learning_rate": 9.83707609731432e-06, | |
| "loss": 0.3567, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.8288628458976746, | |
| "eval_runtime": 37.0058, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "step": 442, | |
| "total_flos": 3.38458179962667e+17, | |
| "train_loss": 0.7497456199173475, | |
| "train_runtime": 12081.7026, | |
| "train_samples_per_second": 1.689, | |
| "train_steps_per_second": 0.211 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 2550, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 150, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 7, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.38458179962667e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |