| { | |
| "best_metric": 1.1245054006576538, | |
| "best_model_checkpoint": "data/Llama-31-8B_task-3_180-samples_config-1_full_auto/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": 0.5154790878295898, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 1.6773, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.5242067575454712, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 1.7016, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.5748609900474548, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 1.7066, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 0.4629555940628052, | |
| "learning_rate": 7.058823529411765e-06, | |
| "loss": 1.6941, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.45625194907188416, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 1.6861, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.40385475754737854, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 1.647, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.4409833550453186, | |
| "learning_rate": 1.411764705882353e-05, | |
| "loss": 1.6256, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 0.5124372243881226, | |
| "learning_rate": 1.647058823529412e-05, | |
| "loss": 1.6702, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.34378665685653687, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 1.6152, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.6113862991333008, | |
| "eval_runtime": 32.0253, | |
| "eval_samples_per_second": 1.124, | |
| "eval_steps_per_second": 1.124, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 0.37906378507614136, | |
| "learning_rate": 2.1176470588235296e-05, | |
| "loss": 1.609, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.33282193541526794, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 1.6161, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 0.40532830357551575, | |
| "learning_rate": 2.5882352941176475e-05, | |
| "loss": 1.5415, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.3349685072898865, | |
| "learning_rate": 2.823529411764706e-05, | |
| "loss": 1.531, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5294117647058822, | |
| "grad_norm": 0.22680427134037018, | |
| "learning_rate": 3.058823529411765e-05, | |
| "loss": 1.4992, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.26350638270378113, | |
| "learning_rate": 3.294117647058824e-05, | |
| "loss": 1.492, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.2858111262321472, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 1.4521, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.2600354254245758, | |
| "learning_rate": 3.7647058823529415e-05, | |
| "loss": 1.4463, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.2709079682826996, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4448, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.4188469648361206, | |
| "eval_runtime": 32.0245, | |
| "eval_samples_per_second": 1.124, | |
| "eval_steps_per_second": 1.124, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.25996771454811096, | |
| "learning_rate": 4.235294117647059e-05, | |
| "loss": 1.3693, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.3167082667350769, | |
| "learning_rate": 4.470588235294118e-05, | |
| "loss": 1.3456, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.2686874270439148, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 1.3121, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.32691195607185364, | |
| "learning_rate": 4.9411764705882355e-05, | |
| "loss": 1.2913, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 0.37983521819114685, | |
| "learning_rate": 5.176470588235295e-05, | |
| "loss": 1.2229, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.310078501701355, | |
| "learning_rate": 5.411764705882353e-05, | |
| "loss": 1.233, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 0.2612503468990326, | |
| "learning_rate": 5.647058823529412e-05, | |
| "loss": 1.2069, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.2700905203819275, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 1.1866, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.2108592987060547, | |
| "eval_runtime": 32.0391, | |
| "eval_samples_per_second": 1.124, | |
| "eval_steps_per_second": 1.124, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0588235294117645, | |
| "grad_norm": 0.19277745485305786, | |
| "learning_rate": 6.11764705882353e-05, | |
| "loss": 1.1612, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.176470588235294, | |
| "grad_norm": 0.17981261014938354, | |
| "learning_rate": 6.352941176470588e-05, | |
| "loss": 1.1087, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.2941176470588234, | |
| "grad_norm": 0.18927226960659027, | |
| "learning_rate": 6.588235294117648e-05, | |
| "loss": 1.185, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.411764705882353, | |
| "grad_norm": 0.20899620652198792, | |
| "learning_rate": 6.823529411764707e-05, | |
| "loss": 1.122, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 0.2021784782409668, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 1.0776, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.6470588235294117, | |
| "grad_norm": 0.19065357744693756, | |
| "learning_rate": 7.294117647058823e-05, | |
| "loss": 1.1868, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.764705882352941, | |
| "grad_norm": 0.28463226556777954, | |
| "learning_rate": 7.529411764705883e-05, | |
| "loss": 1.0977, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.8823529411764706, | |
| "grad_norm": 0.23024596273899078, | |
| "learning_rate": 7.764705882352942e-05, | |
| "loss": 1.0829, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.21433672308921814, | |
| "learning_rate": 8e-05, | |
| "loss": 1.071, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.161912202835083, | |
| "eval_runtime": 32.0243, | |
| "eval_samples_per_second": 1.124, | |
| "eval_steps_per_second": 1.124, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.117647058823529, | |
| "grad_norm": 0.19719600677490234, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 1.1566, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.235294117647059, | |
| "grad_norm": 0.20649372041225433, | |
| "learning_rate": 8.470588235294118e-05, | |
| "loss": 1.0155, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.352941176470588, | |
| "grad_norm": 0.211807981133461, | |
| "learning_rate": 8.705882352941177e-05, | |
| "loss": 1.0977, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.470588235294118, | |
| "grad_norm": 0.21025048196315765, | |
| "learning_rate": 8.941176470588236e-05, | |
| "loss": 1.0347, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.588235294117647, | |
| "grad_norm": 0.22808781266212463, | |
| "learning_rate": 9.176470588235295e-05, | |
| "loss": 1.0623, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.1917581707239151, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 1.104, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.823529411764706, | |
| "grad_norm": 0.21716080605983734, | |
| "learning_rate": 9.647058823529412e-05, | |
| "loss": 1.0512, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.9411764705882355, | |
| "grad_norm": 0.23685045540332794, | |
| "learning_rate": 9.882352941176471e-05, | |
| "loss": 1.0559, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.1390061378479004, | |
| "eval_runtime": 32.0277, | |
| "eval_samples_per_second": 1.124, | |
| "eval_steps_per_second": 1.124, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.0588235294117645, | |
| "grad_norm": 0.24202123284339905, | |
| "learning_rate": 9.99995783847866e-05, | |
| "loss": 0.9913, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.176470588235294, | |
| "grad_norm": 0.28112703561782837, | |
| "learning_rate": 9.999620550574153e-05, | |
| "loss": 1.0089, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.294117647058823, | |
| "grad_norm": 0.2965831458568573, | |
| "learning_rate": 9.998945997517956e-05, | |
| "loss": 1.0559, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.411764705882353, | |
| "grad_norm": 0.23468242585659027, | |
| "learning_rate": 9.997934224814173e-05, | |
| "loss": 1.0734, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.529411764705882, | |
| "grad_norm": 0.2855753004550934, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 1.0278, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 5.647058823529412, | |
| "grad_norm": 0.29968711733818054, | |
| "learning_rate": 9.994899316216708e-05, | |
| "loss": 1.023, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 5.764705882352941, | |
| "grad_norm": 0.25852108001708984, | |
| "learning_rate": 9.992876385052345e-05, | |
| "loss": 1.0435, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 0.2889048755168915, | |
| "learning_rate": 9.990516643685222e-05, | |
| "loss": 1.0497, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.234141007065773, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.9877, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.1245054006576538, | |
| "eval_runtime": 32.0333, | |
| "eval_samples_per_second": 1.124, | |
| "eval_steps_per_second": 1.124, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.117647058823529, | |
| "grad_norm": 0.24628965556621552, | |
| "learning_rate": 9.984787389787688e-05, | |
| "loss": 0.9644, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 6.235294117647059, | |
| "grad_norm": 0.26862069964408875, | |
| "learning_rate": 9.981418263742148e-05, | |
| "loss": 0.9701, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 6.352941176470588, | |
| "grad_norm": 0.2855232059955597, | |
| "learning_rate": 9.977713100437509e-05, | |
| "loss": 0.923, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 6.470588235294118, | |
| "grad_norm": 0.30253928899765015, | |
| "learning_rate": 9.973672149817232e-05, | |
| "loss": 1.0113, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.588235294117647, | |
| "grad_norm": 0.28570523858070374, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 0.9434, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 6.705882352941177, | |
| "grad_norm": 0.3323829472064972, | |
| "learning_rate": 9.964583999643174e-05, | |
| "loss": 1.0461, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.823529411764706, | |
| "grad_norm": 0.28602075576782227, | |
| "learning_rate": 9.95953741315919e-05, | |
| "loss": 1.0281, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 6.9411764705882355, | |
| "grad_norm": 0.317854106426239, | |
| "learning_rate": 9.954156265457801e-05, | |
| "loss": 0.9672, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.127182960510254, | |
| "eval_runtime": 32.0202, | |
| "eval_samples_per_second": 1.124, | |
| "eval_steps_per_second": 1.124, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 0.28219544887542725, | |
| "learning_rate": 9.948440919541278e-05, | |
| "loss": 0.9647, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.176470588235294, | |
| "grad_norm": 0.32057374715805054, | |
| "learning_rate": 9.942391760956277e-05, | |
| "loss": 0.9365, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 7.294117647058823, | |
| "grad_norm": 0.3677031695842743, | |
| "learning_rate": 9.936009197767845e-05, | |
| "loss": 0.9153, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 7.411764705882353, | |
| "grad_norm": 0.3779713213443756, | |
| "learning_rate": 9.929293660531888e-05, | |
| "loss": 0.8729, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 7.529411764705882, | |
| "grad_norm": 0.4241270124912262, | |
| "learning_rate": 9.922245602266118e-05, | |
| "loss": 0.9108, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 7.647058823529412, | |
| "grad_norm": 0.4075779318809509, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 0.9354, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.764705882352941, | |
| "grad_norm": 0.4593713879585266, | |
| "learning_rate": 9.90715384684021e-05, | |
| "loss": 0.8606, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 7.882352941176471, | |
| "grad_norm": 0.40737801790237427, | |
| "learning_rate": 9.899111167741966e-05, | |
| "loss": 0.9789, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.49215108156204224, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.8614, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.1424829959869385, | |
| "eval_runtime": 32.0201, | |
| "eval_samples_per_second": 1.124, | |
| "eval_steps_per_second": 1.124, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.117647058823529, | |
| "grad_norm": 0.49610352516174316, | |
| "learning_rate": 9.882034919459555e-05, | |
| "loss": 0.8508, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 8.235294117647058, | |
| "grad_norm": 0.5119228363037109, | |
| "learning_rate": 9.873002502207503e-05, | |
| "loss": 0.8054, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.352941176470589, | |
| "grad_norm": 0.5245838761329651, | |
| "learning_rate": 9.863641361223024e-05, | |
| "loss": 0.8711, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 8.470588235294118, | |
| "grad_norm": 0.4978489279747009, | |
| "learning_rate": 9.853952127991372e-05, | |
| "loss": 0.8615, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 8.588235294117647, | |
| "grad_norm": 0.5468574166297913, | |
| "learning_rate": 9.843935456130295e-05, | |
| "loss": 0.8643, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 8.705882352941176, | |
| "grad_norm": 0.5397177934646606, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 0.8533, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 8.823529411764707, | |
| "grad_norm": 0.5044189691543579, | |
| "learning_rate": 9.822922521387276e-05, | |
| "loss": 0.78, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.941176470588236, | |
| "grad_norm": 0.5977628827095032, | |
| "learning_rate": 9.811927675999036e-05, | |
| "loss": 0.7722, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.1850228309631348, | |
| "eval_runtime": 32.0138, | |
| "eval_samples_per_second": 1.125, | |
| "eval_steps_per_second": 1.125, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.058823529411764, | |
| "grad_norm": 0.5697214603424072, | |
| "learning_rate": 9.800608226873142e-05, | |
| "loss": 0.8054, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 9.176470588235293, | |
| "grad_norm": 0.6791819930076599, | |
| "learning_rate": 9.788964937598689e-05, | |
| "loss": 0.7329, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 9.294117647058824, | |
| "grad_norm": 0.6606687903404236, | |
| "learning_rate": 9.776998593610428e-05, | |
| "loss": 0.7566, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 0.6617732048034668, | |
| "learning_rate": 9.764710002135784e-05, | |
| "loss": 0.7464, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.529411764705882, | |
| "grad_norm": 0.6102858185768127, | |
| "learning_rate": 9.752099992140399e-05, | |
| "loss": 0.7203, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 9.647058823529411, | |
| "grad_norm": 0.7051090002059937, | |
| "learning_rate": 9.739169414272217e-05, | |
| "loss": 0.7464, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 9.764705882352942, | |
| "grad_norm": 0.6591344475746155, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 0.7706, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 9.882352941176471, | |
| "grad_norm": 0.7764294743537903, | |
| "learning_rate": 9.71235006557497e-05, | |
| "loss": 0.643, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.8501608967781067, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.7255, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.2317448854446411, | |
| "eval_runtime": 32.0219, | |
| "eval_samples_per_second": 1.124, | |
| "eval_steps_per_second": 1.124, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.117647058823529, | |
| "grad_norm": 0.7115060687065125, | |
| "learning_rate": 9.684259192656553e-05, | |
| "loss": 0.5894, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 10.235294117647058, | |
| "grad_norm": 1.1212257146835327, | |
| "learning_rate": 9.669739289925577e-05, | |
| "loss": 0.6349, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 10.352941176470589, | |
| "grad_norm": 0.8680469989776611, | |
| "learning_rate": 9.654904375222385e-05, | |
| "loss": 0.6664, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 10.470588235294118, | |
| "grad_norm": 1.0663613080978394, | |
| "learning_rate": 9.639755449282875e-05, | |
| "loss": 0.5743, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 10.588235294117647, | |
| "grad_norm": 0.8043115139007568, | |
| "learning_rate": 9.62429353402556e-05, | |
| "loss": 0.6482, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 10.705882352941176, | |
| "grad_norm": 0.7615100145339966, | |
| "learning_rate": 9.608519672482636e-05, | |
| "loss": 0.6081, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 10.823529411764707, | |
| "grad_norm": 0.7999354004859924, | |
| "learning_rate": 9.592434928729616e-05, | |
| "loss": 0.6301, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 10.941176470588236, | |
| "grad_norm": 0.8139082789421082, | |
| "learning_rate": 9.576040387813552e-05, | |
| "loss": 0.6638, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.275167465209961, | |
| "eval_runtime": 32.0158, | |
| "eval_samples_per_second": 1.124, | |
| "eval_steps_per_second": 1.124, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.058823529411764, | |
| "grad_norm": 0.7575787305831909, | |
| "learning_rate": 9.559337155679842e-05, | |
| "loss": 0.6337, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 11.176470588235293, | |
| "grad_norm": 0.9686254262924194, | |
| "learning_rate": 9.542326359097619e-05, | |
| "loss": 0.545, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.294117647058824, | |
| "grad_norm": 1.1185410022735596, | |
| "learning_rate": 9.525009145583745e-05, | |
| "loss": 0.6135, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 11.411764705882353, | |
| "grad_norm": 0.846567690372467, | |
| "learning_rate": 9.507386683325404e-05, | |
| "loss": 0.3796, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 11.529411764705882, | |
| "grad_norm": 1.2112523317337036, | |
| "learning_rate": 9.489460161101291e-05, | |
| "loss": 0.5887, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 11.647058823529411, | |
| "grad_norm": 1.1113760471343994, | |
| "learning_rate": 9.471230788201429e-05, | |
| "loss": 0.5442, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 0.9875977039337158, | |
| "learning_rate": 9.452699794345581e-05, | |
| "loss": 0.5352, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.882352941176471, | |
| "grad_norm": 0.9439451098442078, | |
| "learning_rate": 9.43386842960031e-05, | |
| "loss": 0.5317, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.9071803689002991, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.4688, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.3815627098083496, | |
| "eval_runtime": 32.0227, | |
| "eval_samples_per_second": 1.124, | |
| "eval_steps_per_second": 1.124, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.117647058823529, | |
| "grad_norm": 1.0820075273513794, | |
| "learning_rate": 9.395309688934351e-05, | |
| "loss": 0.4593, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 12.235294117647058, | |
| "grad_norm": 1.2419748306274414, | |
| "learning_rate": 9.375584914114963e-05, | |
| "loss": 0.4133, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 12.352941176470589, | |
| "grad_norm": 0.9341420531272888, | |
| "learning_rate": 9.355564970433288e-05, | |
| "loss": 0.4533, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.470588235294118, | |
| "grad_norm": 1.1270216703414917, | |
| "learning_rate": 9.335251208397684e-05, | |
| "loss": 0.401, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 12.588235294117647, | |
| "grad_norm": 1.1522716283798218, | |
| "learning_rate": 9.314644998336949e-05, | |
| "loss": 0.49, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 12.705882352941176, | |
| "grad_norm": 1.113818645477295, | |
| "learning_rate": 9.293747730307889e-05, | |
| "loss": 0.4059, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 12.823529411764707, | |
| "grad_norm": 1.3186521530151367, | |
| "learning_rate": 9.272560814001539e-05, | |
| "loss": 0.4369, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 12.941176470588236, | |
| "grad_norm": 1.1053836345672607, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.5007, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.3799538612365723, | |
| "eval_runtime": 32.0216, | |
| "eval_samples_per_second": 1.124, | |
| "eval_steps_per_second": 1.124, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 221, | |
| "total_flos": 1.3967739754800742e+17, | |
| "train_loss": 0.978654435587145, | |
| "train_runtime": 5121.3441, | |
| "train_samples_per_second": 1.328, | |
| "train_steps_per_second": 0.166 | |
| } | |
| ], | |
| "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": 1.3967739754800742e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |