| { | |
| "best_metric": 1.1360936164855957, | |
| "best_model_checkpoint": "data/Llama-31-8B_task-3_180-samples_config-1_full/checkpoint-102", | |
| "epoch": 13.0, | |
| "eval_steps": 500, | |
| "global_step": 221, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 0.5528482794761658, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 1.6924, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.5329808592796326, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 1.7338, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.5967728495597839, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 1.7281, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 0.49345582723617554, | |
| "learning_rate": 7.058823529411765e-06, | |
| "loss": 1.7366, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.4737401306629181, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 1.7026, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.4043700695037842, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 1.6686, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.44782882928848267, | |
| "learning_rate": 1.411764705882353e-05, | |
| "loss": 1.6423, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 0.5165250897407532, | |
| "learning_rate": 1.647058823529412e-05, | |
| "loss": 1.6869, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.359055757522583, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 1.6392, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.6279072761535645, | |
| "eval_runtime": 31.9058, | |
| "eval_samples_per_second": 1.128, | |
| "eval_steps_per_second": 1.128, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 0.40160268545150757, | |
| "learning_rate": 2.1176470588235296e-05, | |
| "loss": 1.6323, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.3287017345428467, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 1.6342, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 0.40547311305999756, | |
| "learning_rate": 2.5882352941176475e-05, | |
| "loss": 1.5666, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.34866002202033997, | |
| "learning_rate": 2.823529411764706e-05, | |
| "loss": 1.5357, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5294117647058822, | |
| "grad_norm": 0.23447023332118988, | |
| "learning_rate": 3.058823529411765e-05, | |
| "loss": 1.5156, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.25884920358657837, | |
| "learning_rate": 3.294117647058824e-05, | |
| "loss": 1.4992, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.2869214117527008, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 1.4898, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.26174890995025635, | |
| "learning_rate": 3.7647058823529415e-05, | |
| "loss": 1.4608, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.26974084973335266, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4618, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.434288501739502, | |
| "eval_runtime": 31.9061, | |
| "eval_samples_per_second": 1.128, | |
| "eval_steps_per_second": 1.128, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.2725391983985901, | |
| "learning_rate": 4.235294117647059e-05, | |
| "loss": 1.3898, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.2956322729587555, | |
| "learning_rate": 4.470588235294118e-05, | |
| "loss": 1.3601, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.2611425518989563, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 1.329, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.3174993097782135, | |
| "learning_rate": 4.9411764705882355e-05, | |
| "loss": 1.3026, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 0.4165894687175751, | |
| "learning_rate": 5.176470588235295e-05, | |
| "loss": 1.2414, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.31013932824134827, | |
| "learning_rate": 5.411764705882353e-05, | |
| "loss": 1.2527, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 0.24389834702014923, | |
| "learning_rate": 5.647058823529412e-05, | |
| "loss": 1.2176, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.3046438992023468, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 1.2006, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.224098801612854, | |
| "eval_runtime": 31.8632, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0588235294117645, | |
| "grad_norm": 0.20166687667369843, | |
| "learning_rate": 6.11764705882353e-05, | |
| "loss": 1.1704, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.176470588235294, | |
| "grad_norm": 0.17880035936832428, | |
| "learning_rate": 6.352941176470588e-05, | |
| "loss": 1.1347, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.2941176470588234, | |
| "grad_norm": 0.19436635076999664, | |
| "learning_rate": 6.588235294117648e-05, | |
| "loss": 1.2011, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.411764705882353, | |
| "grad_norm": 0.21855325996875763, | |
| "learning_rate": 6.823529411764707e-05, | |
| "loss": 1.1406, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 0.20831391215324402, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 1.0812, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.6470588235294117, | |
| "grad_norm": 0.17739257216453552, | |
| "learning_rate": 7.294117647058823e-05, | |
| "loss": 1.1997, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.764705882352941, | |
| "grad_norm": 0.3042898178100586, | |
| "learning_rate": 7.529411764705883e-05, | |
| "loss": 1.1212, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.8823529411764706, | |
| "grad_norm": 0.21835383772850037, | |
| "learning_rate": 7.764705882352942e-05, | |
| "loss": 1.0866, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.2302902638912201, | |
| "learning_rate": 8e-05, | |
| "loss": 1.0799, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.176115870475769, | |
| "eval_runtime": 31.8551, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.117647058823529, | |
| "grad_norm": 0.18710270524024963, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 1.1674, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.235294117647059, | |
| "grad_norm": 0.19638200104236603, | |
| "learning_rate": 8.470588235294118e-05, | |
| "loss": 1.0292, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.352941176470588, | |
| "grad_norm": 0.34665539860725403, | |
| "learning_rate": 8.705882352941177e-05, | |
| "loss": 1.1262, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.470588235294118, | |
| "grad_norm": 0.209116131067276, | |
| "learning_rate": 8.941176470588236e-05, | |
| "loss": 1.046, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.588235294117647, | |
| "grad_norm": 0.23588423430919647, | |
| "learning_rate": 9.176470588235295e-05, | |
| "loss": 1.0824, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.19609621167182922, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 1.1144, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.823529411764706, | |
| "grad_norm": 0.23131436109542847, | |
| "learning_rate": 9.647058823529412e-05, | |
| "loss": 1.0587, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.9411764705882355, | |
| "grad_norm": 0.24030965566635132, | |
| "learning_rate": 9.882352941176471e-05, | |
| "loss": 1.0615, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.152439832687378, | |
| "eval_runtime": 31.8505, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.0588235294117645, | |
| "grad_norm": 0.2504451274871826, | |
| "learning_rate": 9.99995783847866e-05, | |
| "loss": 1.0025, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.176470588235294, | |
| "grad_norm": 0.2802024781703949, | |
| "learning_rate": 9.999620550574153e-05, | |
| "loss": 1.0199, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.294117647058823, | |
| "grad_norm": 0.2964102327823639, | |
| "learning_rate": 9.998945997517956e-05, | |
| "loss": 1.0687, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.411764705882353, | |
| "grad_norm": 0.25978174805641174, | |
| "learning_rate": 9.997934224814173e-05, | |
| "loss": 1.0788, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.529411764705882, | |
| "grad_norm": 0.2862597405910492, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 1.0386, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 5.647058823529412, | |
| "grad_norm": 0.324344277381897, | |
| "learning_rate": 9.994899316216708e-05, | |
| "loss": 1.0285, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 5.764705882352941, | |
| "grad_norm": 0.268693208694458, | |
| "learning_rate": 9.992876385052345e-05, | |
| "loss": 1.0574, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 0.27559933066368103, | |
| "learning_rate": 9.990516643685222e-05, | |
| "loss": 1.0658, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.24688442051410675, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.0045, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.1360936164855957, | |
| "eval_runtime": 31.8501, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.117647058823529, | |
| "grad_norm": 0.24914266169071198, | |
| "learning_rate": 9.984787389787688e-05, | |
| "loss": 0.9713, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 6.235294117647059, | |
| "grad_norm": 0.27919214963912964, | |
| "learning_rate": 9.981418263742148e-05, | |
| "loss": 0.984, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 6.352941176470588, | |
| "grad_norm": 0.28271570801734924, | |
| "learning_rate": 9.977713100437509e-05, | |
| "loss": 0.9364, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 6.470588235294118, | |
| "grad_norm": 0.3078059256076813, | |
| "learning_rate": 9.973672149817232e-05, | |
| "loss": 1.0203, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.588235294117647, | |
| "grad_norm": 0.3157869875431061, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 0.9561, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 6.705882352941177, | |
| "grad_norm": 0.33077776432037354, | |
| "learning_rate": 9.964583999643174e-05, | |
| "loss": 1.0549, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.823529411764706, | |
| "grad_norm": 0.27845317125320435, | |
| "learning_rate": 9.95953741315919e-05, | |
| "loss": 1.0329, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 6.9411764705882355, | |
| "grad_norm": 0.3240528702735901, | |
| "learning_rate": 9.954156265457801e-05, | |
| "loss": 0.9831, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.1391760110855103, | |
| "eval_runtime": 31.8528, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 0.2748457193374634, | |
| "learning_rate": 9.948440919541278e-05, | |
| "loss": 0.9727, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.176470588235294, | |
| "grad_norm": 0.39954397082328796, | |
| "learning_rate": 9.942391760956277e-05, | |
| "loss": 0.9451, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 7.294117647058823, | |
| "grad_norm": 0.40366628766059875, | |
| "learning_rate": 9.936009197767845e-05, | |
| "loss": 0.9226, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 7.411764705882353, | |
| "grad_norm": 0.39687567949295044, | |
| "learning_rate": 9.929293660531888e-05, | |
| "loss": 0.8883, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 7.529411764705882, | |
| "grad_norm": 0.40977299213409424, | |
| "learning_rate": 9.922245602266118e-05, | |
| "loss": 0.9214, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 7.647058823529412, | |
| "grad_norm": 0.4080333709716797, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 0.937, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.764705882352941, | |
| "grad_norm": 0.4549306631088257, | |
| "learning_rate": 9.90715384684021e-05, | |
| "loss": 0.8678, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 7.882352941176471, | |
| "grad_norm": 0.4073057174682617, | |
| "learning_rate": 9.899111167741966e-05, | |
| "loss": 0.985, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.4704064726829529, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.8698, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.1567057371139526, | |
| "eval_runtime": 31.8584, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.117647058823529, | |
| "grad_norm": 0.5016499757766724, | |
| "learning_rate": 9.882034919459555e-05, | |
| "loss": 0.8543, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 8.235294117647058, | |
| "grad_norm": 0.4757508337497711, | |
| "learning_rate": 9.873002502207503e-05, | |
| "loss": 0.8096, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.352941176470589, | |
| "grad_norm": 0.5401610136032104, | |
| "learning_rate": 9.863641361223024e-05, | |
| "loss": 0.8839, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 8.470588235294118, | |
| "grad_norm": 0.5351719260215759, | |
| "learning_rate": 9.853952127991372e-05, | |
| "loss": 0.8609, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 8.588235294117647, | |
| "grad_norm": 0.5949414372444153, | |
| "learning_rate": 9.843935456130295e-05, | |
| "loss": 0.8766, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 8.705882352941176, | |
| "grad_norm": 0.5695145130157471, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 0.8563, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 8.823529411764707, | |
| "grad_norm": 0.5231143832206726, | |
| "learning_rate": 9.822922521387276e-05, | |
| "loss": 0.7935, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.941176470588236, | |
| "grad_norm": 0.6562063694000244, | |
| "learning_rate": 9.811927675999036e-05, | |
| "loss": 0.7759, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.1918365955352783, | |
| "eval_runtime": 31.8636, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.058823529411764, | |
| "grad_norm": 0.6664929986000061, | |
| "learning_rate": 9.800608226873142e-05, | |
| "loss": 0.8143, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 9.176470588235293, | |
| "grad_norm": 0.697819709777832, | |
| "learning_rate": 9.788964937598689e-05, | |
| "loss": 0.7413, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 9.294117647058824, | |
| "grad_norm": 0.7139567136764526, | |
| "learning_rate": 9.776998593610428e-05, | |
| "loss": 0.7634, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 0.691534698009491, | |
| "learning_rate": 9.764710002135784e-05, | |
| "loss": 0.7556, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.529411764705882, | |
| "grad_norm": 0.6350474953651428, | |
| "learning_rate": 9.752099992140399e-05, | |
| "loss": 0.7312, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 9.647058823529411, | |
| "grad_norm": 0.6918034553527832, | |
| "learning_rate": 9.739169414272217e-05, | |
| "loss": 0.7499, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 9.764705882352942, | |
| "grad_norm": 0.71235191822052, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 0.7801, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 9.882352941176471, | |
| "grad_norm": 0.7917525768280029, | |
| "learning_rate": 9.71235006557497e-05, | |
| "loss": 0.6504, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.8137404322624207, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.7296, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.253719687461853, | |
| "eval_runtime": 31.864, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.117647058823529, | |
| "grad_norm": 0.722001314163208, | |
| "learning_rate": 9.684259192656553e-05, | |
| "loss": 0.5957, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 10.235294117647058, | |
| "grad_norm": 1.1950467824935913, | |
| "learning_rate": 9.669739289925577e-05, | |
| "loss": 0.6398, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 10.352941176470589, | |
| "grad_norm": 0.8718464970588684, | |
| "learning_rate": 9.654904375222385e-05, | |
| "loss": 0.6747, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 10.470588235294118, | |
| "grad_norm": 1.0716255903244019, | |
| "learning_rate": 9.639755449282875e-05, | |
| "loss": 0.5795, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 10.588235294117647, | |
| "grad_norm": 0.8144655823707581, | |
| "learning_rate": 9.62429353402556e-05, | |
| "loss": 0.6561, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 10.705882352941176, | |
| "grad_norm": 0.7325339913368225, | |
| "learning_rate": 9.608519672482636e-05, | |
| "loss": 0.6126, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 10.823529411764707, | |
| "grad_norm": 0.8531737327575684, | |
| "learning_rate": 9.592434928729616e-05, | |
| "loss": 0.634, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 10.941176470588236, | |
| "grad_norm": 0.9125006794929504, | |
| "learning_rate": 9.576040387813552e-05, | |
| "loss": 0.6747, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.2851899862289429, | |
| "eval_runtime": 31.864, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.058823529411764, | |
| "grad_norm": 0.7676507234573364, | |
| "learning_rate": 9.559337155679842e-05, | |
| "loss": 0.6426, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 11.176470588235293, | |
| "grad_norm": 1.0699644088745117, | |
| "learning_rate": 9.542326359097619e-05, | |
| "loss": 0.5464, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.294117647058824, | |
| "grad_norm": 1.1215331554412842, | |
| "learning_rate": 9.525009145583745e-05, | |
| "loss": 0.62, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 11.411764705882353, | |
| "grad_norm": 0.900759220123291, | |
| "learning_rate": 9.507386683325404e-05, | |
| "loss": 0.3819, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 11.529411764705882, | |
| "grad_norm": 1.1087801456451416, | |
| "learning_rate": 9.489460161101291e-05, | |
| "loss": 0.5873, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 11.647058823529411, | |
| "grad_norm": 1.0627771615982056, | |
| "learning_rate": 9.471230788201429e-05, | |
| "loss": 0.5488, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 0.8630377054214478, | |
| "learning_rate": 9.452699794345581e-05, | |
| "loss": 0.5419, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.882352941176471, | |
| "grad_norm": 0.9275286793708801, | |
| "learning_rate": 9.43386842960031e-05, | |
| "loss": 0.535, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 1.0373382568359375, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.4777, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.3876960277557373, | |
| "eval_runtime": 31.8598, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.117647058823529, | |
| "grad_norm": 0.8839051723480225, | |
| "learning_rate": 9.395309688934351e-05, | |
| "loss": 0.4635, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 12.235294117647058, | |
| "grad_norm": 1.4167739152908325, | |
| "learning_rate": 9.375584914114963e-05, | |
| "loss": 0.4182, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 12.352941176470589, | |
| "grad_norm": 0.9632711410522461, | |
| "learning_rate": 9.355564970433288e-05, | |
| "loss": 0.4579, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.470588235294118, | |
| "grad_norm": 1.0840599536895752, | |
| "learning_rate": 9.335251208397684e-05, | |
| "loss": 0.4057, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 12.588235294117647, | |
| "grad_norm": 1.2447075843811035, | |
| "learning_rate": 9.314644998336949e-05, | |
| "loss": 0.496, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 12.705882352941176, | |
| "grad_norm": 1.0373592376708984, | |
| "learning_rate": 9.293747730307889e-05, | |
| "loss": 0.4091, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 12.823529411764707, | |
| "grad_norm": 1.1981492042541504, | |
| "learning_rate": 9.272560814001539e-05, | |
| "loss": 0.444, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 12.941176470588236, | |
| "grad_norm": 1.128504753112793, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.5052, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.4002447128295898, | |
| "eval_runtime": 31.8634, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 221, | |
| "total_flos": 1.386613776014377e+17, | |
| "train_loss": 0.9896936357291036, | |
| "train_runtime": 5091.6658, | |
| "train_samples_per_second": 1.336, | |
| "train_steps_per_second": 0.167 | |
| } | |
| ], | |
| "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": 1.386613776014377e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |