| { | |
| "best_metric": 1.0345184803009033, | |
| "best_model_checkpoint": "data/Llama-31-8B_task-2_180-samples_config-1_full/checkpoint-119", | |
| "epoch": 14.0, | |
| "eval_steps": 500, | |
| "global_step": 238, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 0.5214345455169678, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 1.5724, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.5508020520210266, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 1.6207, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.5937786102294922, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 1.6106, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 0.5013459324836731, | |
| "learning_rate": 7.058823529411765e-06, | |
| "loss": 1.6182, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.4731301963329315, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 1.5894, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.4294460713863373, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 1.5504, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.4912262260913849, | |
| "learning_rate": 1.411764705882353e-05, | |
| "loss": 1.5279, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 0.5266876220703125, | |
| "learning_rate": 1.647058823529412e-05, | |
| "loss": 1.5391, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.391021728515625, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 1.504, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.5035704374313354, | |
| "eval_runtime": 37.0347, | |
| "eval_samples_per_second": 0.972, | |
| "eval_steps_per_second": 0.972, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 0.3921213746070862, | |
| "learning_rate": 2.1176470588235296e-05, | |
| "loss": 1.5014, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.38555383682250977, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 1.4873, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 0.2951497733592987, | |
| "learning_rate": 2.5882352941176475e-05, | |
| "loss": 1.4459, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.31671950221061707, | |
| "learning_rate": 2.823529411764706e-05, | |
| "loss": 1.4021, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5294117647058822, | |
| "grad_norm": 0.2338249385356903, | |
| "learning_rate": 3.058823529411765e-05, | |
| "loss": 1.3717, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.2480524629354477, | |
| "learning_rate": 3.294117647058824e-05, | |
| "loss": 1.364, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.29380786418914795, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 1.3607, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.26109302043914795, | |
| "learning_rate": 3.7647058823529415e-05, | |
| "loss": 1.3166, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.2589414417743683, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3344, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.3100626468658447, | |
| "eval_runtime": 37.0282, | |
| "eval_samples_per_second": 0.972, | |
| "eval_steps_per_second": 0.972, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.2652131915092468, | |
| "learning_rate": 4.235294117647059e-05, | |
| "loss": 1.2648, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.2305995672941208, | |
| "learning_rate": 4.470588235294118e-05, | |
| "loss": 1.2315, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.22336632013320923, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 1.208, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.25589871406555176, | |
| "learning_rate": 4.9411764705882355e-05, | |
| "loss": 1.1869, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 0.3676718771457672, | |
| "learning_rate": 5.176470588235295e-05, | |
| "loss": 1.1343, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.308319628238678, | |
| "learning_rate": 5.411764705882353e-05, | |
| "loss": 1.1467, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 0.2406923770904541, | |
| "learning_rate": 5.647058823529412e-05, | |
| "loss": 1.1131, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.3291592299938202, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 1.0895, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.1146036386489868, | |
| "eval_runtime": 36.9993, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0588235294117645, | |
| "grad_norm": 0.16729487478733063, | |
| "learning_rate": 6.11764705882353e-05, | |
| "loss": 1.0574, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.176470588235294, | |
| "grad_norm": 0.15566912293434143, | |
| "learning_rate": 6.352941176470588e-05, | |
| "loss": 1.0398, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.2941176470588234, | |
| "grad_norm": 0.15833047032356262, | |
| "learning_rate": 6.588235294117648e-05, | |
| "loss": 1.0902, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.411764705882353, | |
| "grad_norm": 0.16289210319519043, | |
| "learning_rate": 6.823529411764707e-05, | |
| "loss": 1.0512, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 0.16850221157073975, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.9916, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.6470588235294117, | |
| "grad_norm": 0.15705695748329163, | |
| "learning_rate": 7.294117647058823e-05, | |
| "loss": 1.0991, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.764705882352941, | |
| "grad_norm": 0.192249596118927, | |
| "learning_rate": 7.529411764705883e-05, | |
| "loss": 1.022, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.8823529411764706, | |
| "grad_norm": 0.18115530908107758, | |
| "learning_rate": 7.764705882352942e-05, | |
| "loss": 0.9873, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.17344814538955688, | |
| "learning_rate": 8e-05, | |
| "loss": 0.9755, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.0741065740585327, | |
| "eval_runtime": 36.9986, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.117647058823529, | |
| "grad_norm": 0.16507934033870697, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 1.0732, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.235294117647059, | |
| "grad_norm": 0.17189058661460876, | |
| "learning_rate": 8.470588235294118e-05, | |
| "loss": 0.9364, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.352941176470588, | |
| "grad_norm": 0.2030569314956665, | |
| "learning_rate": 8.705882352941177e-05, | |
| "loss": 1.0275, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.470588235294118, | |
| "grad_norm": 0.1766645312309265, | |
| "learning_rate": 8.941176470588236e-05, | |
| "loss": 0.9621, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.588235294117647, | |
| "grad_norm": 0.19495844841003418, | |
| "learning_rate": 9.176470588235295e-05, | |
| "loss": 0.9856, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.17263540625572205, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 1.012, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.823529411764706, | |
| "grad_norm": 0.19147881865501404, | |
| "learning_rate": 9.647058823529412e-05, | |
| "loss": 0.9723, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.9411764705882355, | |
| "grad_norm": 0.19374307990074158, | |
| "learning_rate": 9.882352941176471e-05, | |
| "loss": 0.9637, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.052433967590332, | |
| "eval_runtime": 37.0057, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.0588235294117645, | |
| "grad_norm": 0.2304454743862152, | |
| "learning_rate": 9.99995783847866e-05, | |
| "loss": 0.9125, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.176470588235294, | |
| "grad_norm": 0.2263410985469818, | |
| "learning_rate": 9.999620550574153e-05, | |
| "loss": 0.942, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.294117647058823, | |
| "grad_norm": 0.2422245293855667, | |
| "learning_rate": 9.998945997517956e-05, | |
| "loss": 0.9778, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.411764705882353, | |
| "grad_norm": 0.20600196719169617, | |
| "learning_rate": 9.997934224814173e-05, | |
| "loss": 0.9842, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.529411764705882, | |
| "grad_norm": 0.23495109379291534, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 0.9389, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 5.647058823529412, | |
| "grad_norm": 0.27190443873405457, | |
| "learning_rate": 9.994899316216708e-05, | |
| "loss": 0.9416, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 5.764705882352941, | |
| "grad_norm": 0.24846382439136505, | |
| "learning_rate": 9.992876385052345e-05, | |
| "loss": 0.9654, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 0.23965619504451752, | |
| "learning_rate": 9.990516643685222e-05, | |
| "loss": 0.9653, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.23243875801563263, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.9215, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.0348577499389648, | |
| "eval_runtime": 36.9988, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.117647058823529, | |
| "grad_norm": 0.2187218964099884, | |
| "learning_rate": 9.984787389787688e-05, | |
| "loss": 0.886, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 6.235294117647059, | |
| "grad_norm": 0.24537856876850128, | |
| "learning_rate": 9.981418263742148e-05, | |
| "loss": 0.8928, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 6.352941176470588, | |
| "grad_norm": 0.25448307394981384, | |
| "learning_rate": 9.977713100437509e-05, | |
| "loss": 0.8498, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 6.470588235294118, | |
| "grad_norm": 0.2609221339225769, | |
| "learning_rate": 9.973672149817232e-05, | |
| "loss": 0.926, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.588235294117647, | |
| "grad_norm": 0.27997028827667236, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 0.8778, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 6.705882352941177, | |
| "grad_norm": 0.29801490902900696, | |
| "learning_rate": 9.964583999643174e-05, | |
| "loss": 0.9633, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.823529411764706, | |
| "grad_norm": 0.25596335530281067, | |
| "learning_rate": 9.95953741315919e-05, | |
| "loss": 0.9494, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 6.9411764705882355, | |
| "grad_norm": 0.2853046655654907, | |
| "learning_rate": 9.954156265457801e-05, | |
| "loss": 0.8984, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.0345184803009033, | |
| "eval_runtime": 36.9963, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 0.31706833839416504, | |
| "learning_rate": 9.948440919541278e-05, | |
| "loss": 0.8992, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.176470588235294, | |
| "grad_norm": 0.2826850712299347, | |
| "learning_rate": 9.942391760956277e-05, | |
| "loss": 0.8611, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 7.294117647058823, | |
| "grad_norm": 0.33343079686164856, | |
| "learning_rate": 9.936009197767845e-05, | |
| "loss": 0.8488, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 7.411764705882353, | |
| "grad_norm": 0.33269575238227844, | |
| "learning_rate": 9.929293660531888e-05, | |
| "loss": 0.809, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 7.529411764705882, | |
| "grad_norm": 0.3902694582939148, | |
| "learning_rate": 9.922245602266118e-05, | |
| "loss": 0.8352, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 7.647058823529412, | |
| "grad_norm": 0.34491705894470215, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 0.8561, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.764705882352941, | |
| "grad_norm": 0.3838919401168823, | |
| "learning_rate": 9.90715384684021e-05, | |
| "loss": 0.7896, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 7.882352941176471, | |
| "grad_norm": 0.3754192590713501, | |
| "learning_rate": 9.899111167741966e-05, | |
| "loss": 0.9033, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.3832869529724121, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.7983, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.0459100008010864, | |
| "eval_runtime": 37.0077, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.117647058823529, | |
| "grad_norm": 0.4289301633834839, | |
| "learning_rate": 9.882034919459555e-05, | |
| "loss": 0.7896, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 8.235294117647058, | |
| "grad_norm": 0.5225833058357239, | |
| "learning_rate": 9.873002502207503e-05, | |
| "loss": 0.7458, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.352941176470589, | |
| "grad_norm": 0.47407665848731995, | |
| "learning_rate": 9.863641361223024e-05, | |
| "loss": 0.8066, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 8.470588235294118, | |
| "grad_norm": 0.46604663133621216, | |
| "learning_rate": 9.853952127991372e-05, | |
| "loss": 0.7907, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 8.588235294117647, | |
| "grad_norm": 0.4920913577079773, | |
| "learning_rate": 9.843935456130295e-05, | |
| "loss": 0.8002, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 8.705882352941176, | |
| "grad_norm": 0.4699203670024872, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 0.7876, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 8.823529411764707, | |
| "grad_norm": 0.4708077907562256, | |
| "learning_rate": 9.822922521387276e-05, | |
| "loss": 0.7274, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.941176470588236, | |
| "grad_norm": 0.6590410470962524, | |
| "learning_rate": 9.811927675999036e-05, | |
| "loss": 0.711, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.0750151872634888, | |
| "eval_runtime": 37.003, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.058823529411764, | |
| "grad_norm": 0.6144815683364868, | |
| "learning_rate": 9.800608226873142e-05, | |
| "loss": 0.7504, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 9.176470588235293, | |
| "grad_norm": 0.5911457538604736, | |
| "learning_rate": 9.788964937598689e-05, | |
| "loss": 0.6873, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 9.294117647058824, | |
| "grad_norm": 0.6449252963066101, | |
| "learning_rate": 9.776998593610428e-05, | |
| "loss": 0.7058, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 0.5975269079208374, | |
| "learning_rate": 9.764710002135784e-05, | |
| "loss": 0.7004, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.529411764705882, | |
| "grad_norm": 0.5621377825737, | |
| "learning_rate": 9.752099992140399e-05, | |
| "loss": 0.672, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 9.647058823529411, | |
| "grad_norm": 0.6631340980529785, | |
| "learning_rate": 9.739169414272217e-05, | |
| "loss": 0.6917, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 9.764705882352942, | |
| "grad_norm": 0.6114043593406677, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 0.7236, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 9.882352941176471, | |
| "grad_norm": 0.6280692219734192, | |
| "learning_rate": 9.71235006557497e-05, | |
| "loss": 0.602, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.6364344358444214, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.6725, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.134390950202942, | |
| "eval_runtime": 37.0, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.117647058823529, | |
| "grad_norm": 0.6386916041374207, | |
| "learning_rate": 9.684259192656553e-05, | |
| "loss": 0.561, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 10.235294117647058, | |
| "grad_norm": 0.9274471402168274, | |
| "learning_rate": 9.669739289925577e-05, | |
| "loss": 0.5975, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 10.352941176470589, | |
| "grad_norm": 0.758702278137207, | |
| "learning_rate": 9.654904375222385e-05, | |
| "loss": 0.621, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 10.470588235294118, | |
| "grad_norm": 0.949181854724884, | |
| "learning_rate": 9.639755449282875e-05, | |
| "loss": 0.5464, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 10.588235294117647, | |
| "grad_norm": 0.7223683595657349, | |
| "learning_rate": 9.62429353402556e-05, | |
| "loss": 0.6089, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 10.705882352941176, | |
| "grad_norm": 0.6299746632575989, | |
| "learning_rate": 9.608519672482636e-05, | |
| "loss": 0.5711, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 10.823529411764707, | |
| "grad_norm": 0.7116110920906067, | |
| "learning_rate": 9.592434928729616e-05, | |
| "loss": 0.5963, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 10.941176470588236, | |
| "grad_norm": 0.6831782460212708, | |
| "learning_rate": 9.576040387813552e-05, | |
| "loss": 0.629, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.1629810333251953, | |
| "eval_runtime": 37.0044, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.058823529411764, | |
| "grad_norm": 0.6914322972297668, | |
| "learning_rate": 9.559337155679842e-05, | |
| "loss": 0.6061, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 11.176470588235293, | |
| "grad_norm": 0.8476060628890991, | |
| "learning_rate": 9.542326359097619e-05, | |
| "loss": 0.513, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.294117647058824, | |
| "grad_norm": 0.9703707098960876, | |
| "learning_rate": 9.525009145583745e-05, | |
| "loss": 0.5803, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 11.411764705882353, | |
| "grad_norm": 0.8944510221481323, | |
| "learning_rate": 9.507386683325404e-05, | |
| "loss": 0.3622, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 11.529411764705882, | |
| "grad_norm": 1.0056551694869995, | |
| "learning_rate": 9.489460161101291e-05, | |
| "loss": 0.5537, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 11.647058823529411, | |
| "grad_norm": 0.9109512567520142, | |
| "learning_rate": 9.471230788201429e-05, | |
| "loss": 0.519, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 0.82012540102005, | |
| "learning_rate": 9.452699794345581e-05, | |
| "loss": 0.5082, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.882352941176471, | |
| "grad_norm": 0.7492274641990662, | |
| "learning_rate": 9.43386842960031e-05, | |
| "loss": 0.5116, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.8394200801849365, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.4573, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.2680054903030396, | |
| "eval_runtime": 37.0068, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.117647058823529, | |
| "grad_norm": 0.8289351463317871, | |
| "learning_rate": 9.395309688934351e-05, | |
| "loss": 0.4454, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 12.235294117647058, | |
| "grad_norm": 0.97170090675354, | |
| "learning_rate": 9.375584914114963e-05, | |
| "loss": 0.3926, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 12.352941176470589, | |
| "grad_norm": 0.8402796983718872, | |
| "learning_rate": 9.355564970433288e-05, | |
| "loss": 0.4302, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.470588235294118, | |
| "grad_norm": 0.8999544978141785, | |
| "learning_rate": 9.335251208397684e-05, | |
| "loss": 0.3877, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 12.588235294117647, | |
| "grad_norm": 1.080120325088501, | |
| "learning_rate": 9.314644998336949e-05, | |
| "loss": 0.4688, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 12.705882352941176, | |
| "grad_norm": 0.8625339269638062, | |
| "learning_rate": 9.293747730307889e-05, | |
| "loss": 0.3901, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 12.823529411764707, | |
| "grad_norm": 1.0037257671356201, | |
| "learning_rate": 9.272560814001539e-05, | |
| "loss": 0.4283, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 12.941176470588236, | |
| "grad_norm": 0.8916875720024109, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.4754, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.2756708860397339, | |
| "eval_runtime": 37.001, | |
| "eval_samples_per_second": 0.973, | |
| "eval_steps_per_second": 0.973, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 13.058823529411764, | |
| "grad_norm": 0.9820285439491272, | |
| "learning_rate": 9.229323772920381e-05, | |
| "loss": 0.4135, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 13.176470588235293, | |
| "grad_norm": 1.5194408893585205, | |
| "learning_rate": 9.207276564836366e-05, | |
| "loss": 0.3795, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 13.294117647058824, | |
| "grad_norm": 0.8674440383911133, | |
| "learning_rate": 9.184945541659889e-05, | |
| "loss": 0.3577, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 13.411764705882353, | |
| "grad_norm": 1.037719488143921, | |
| "learning_rate": 9.162332209800455e-05, | |
| "loss": 0.292, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 13.529411764705882, | |
| "grad_norm": 1.3491851091384888, | |
| "learning_rate": 9.139438094711589e-05, | |
| "loss": 0.3822, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 13.647058823529411, | |
| "grad_norm": 1.114529013633728, | |
| "learning_rate": 9.116264740787936e-05, | |
| "loss": 0.3377, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 13.764705882352942, | |
| "grad_norm": 0.971333920955658, | |
| "learning_rate": 9.092813711261074e-05, | |
| "loss": 0.4037, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 13.882352941176471, | |
| "grad_norm": 1.0582764148712158, | |
| "learning_rate": 9.069086588094067e-05, | |
| "loss": 0.3383, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 0.9523320198059082, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.4236, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.337109923362732, | |
| "eval_runtime": 37.033, | |
| "eval_samples_per_second": 0.972, | |
| "eval_steps_per_second": 0.972, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "step": 238, | |
| "total_flos": 1.8224671283478528e+17, | |
| "train_loss": 0.8704949083949337, | |
| "train_runtime": 6511.5654, | |
| "train_samples_per_second": 1.044, | |
| "train_steps_per_second": 0.131 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 850, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "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": 1.8224671283478528e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |