| { | |
| "best_metric": 0.9984785914421082, | |
| "best_model_checkpoint": "data/Llama-31-8B_task-2_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": 0.4825083911418915, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 1.5, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.5180450677871704, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 1.5563, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.5447845458984375, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 1.5401, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 0.46300044655799866, | |
| "learning_rate": 7.058823529411765e-06, | |
| "loss": 1.524, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.4108465611934662, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 1.522, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.3941603899002075, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 1.4886, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.44514769315719604, | |
| "learning_rate": 1.411764705882353e-05, | |
| "loss": 1.4726, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 0.4823445975780487, | |
| "learning_rate": 1.647058823529412e-05, | |
| "loss": 1.4653, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.35265323519706726, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 1.4597, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.4483990669250488, | |
| "eval_runtime": 38.0063, | |
| "eval_samples_per_second": 0.947, | |
| "eval_steps_per_second": 0.947, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 0.35966965556144714, | |
| "learning_rate": 2.1176470588235296e-05, | |
| "loss": 1.4391, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.32761916518211365, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 1.4201, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 0.2901964783668518, | |
| "learning_rate": 2.5882352941176475e-05, | |
| "loss": 1.3959, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.3420025408267975, | |
| "learning_rate": 2.823529411764706e-05, | |
| "loss": 1.3511, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5294117647058822, | |
| "grad_norm": 0.21471835672855377, | |
| "learning_rate": 3.058823529411765e-05, | |
| "loss": 1.3394, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.23242667317390442, | |
| "learning_rate": 3.294117647058824e-05, | |
| "loss": 1.3306, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.27259019017219543, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 1.3032, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.252906858921051, | |
| "learning_rate": 3.7647058823529415e-05, | |
| "loss": 1.274, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.24995239078998566, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2836, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.2670295238494873, | |
| "eval_runtime": 38.0017, | |
| "eval_samples_per_second": 0.947, | |
| "eval_steps_per_second": 0.947, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.25231388211250305, | |
| "learning_rate": 4.235294117647059e-05, | |
| "loss": 1.2229, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.22629840672016144, | |
| "learning_rate": 4.470588235294118e-05, | |
| "loss": 1.1843, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.2289404720067978, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 1.169, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.25495997071266174, | |
| "learning_rate": 4.9411764705882355e-05, | |
| "loss": 1.144, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 0.30859699845314026, | |
| "learning_rate": 5.176470588235295e-05, | |
| "loss": 1.0932, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.31817567348480225, | |
| "learning_rate": 5.411764705882353e-05, | |
| "loss": 1.1034, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 0.25908929109573364, | |
| "learning_rate": 5.647058823529412e-05, | |
| "loss": 1.0719, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.3229236304759979, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 1.0573, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.0739870071411133, | |
| "eval_runtime": 38.0074, | |
| "eval_samples_per_second": 0.947, | |
| "eval_steps_per_second": 0.947, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0588235294117645, | |
| "grad_norm": 0.17172937095165253, | |
| "learning_rate": 6.11764705882353e-05, | |
| "loss": 1.0135, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.176470588235294, | |
| "grad_norm": 0.15758301317691803, | |
| "learning_rate": 6.352941176470588e-05, | |
| "loss": 0.9897, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.2941176470588234, | |
| "grad_norm": 0.15762178599834442, | |
| "learning_rate": 6.588235294117648e-05, | |
| "loss": 1.0567, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.411764705882353, | |
| "grad_norm": 0.17562586069107056, | |
| "learning_rate": 6.823529411764707e-05, | |
| "loss": 1.0081, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 0.17557750642299652, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.9553, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.6470588235294117, | |
| "grad_norm": 0.15448470413684845, | |
| "learning_rate": 7.294117647058823e-05, | |
| "loss": 1.0557, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.764705882352941, | |
| "grad_norm": 0.2150467485189438, | |
| "learning_rate": 7.529411764705883e-05, | |
| "loss": 0.9791, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.8823529411764706, | |
| "grad_norm": 0.17866112291812897, | |
| "learning_rate": 7.764705882352942e-05, | |
| "loss": 0.9376, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.17645590007305145, | |
| "learning_rate": 8e-05, | |
| "loss": 0.9449, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.0340993404388428, | |
| "eval_runtime": 38.0061, | |
| "eval_samples_per_second": 0.947, | |
| "eval_steps_per_second": 0.947, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.117647058823529, | |
| "grad_norm": 0.17610642313957214, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 1.0303, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.235294117647059, | |
| "grad_norm": 0.1893858015537262, | |
| "learning_rate": 8.470588235294118e-05, | |
| "loss": 0.8961, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.352941176470588, | |
| "grad_norm": 0.1767551451921463, | |
| "learning_rate": 8.705882352941177e-05, | |
| "loss": 0.9827, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.470588235294118, | |
| "grad_norm": 0.18365183472633362, | |
| "learning_rate": 8.941176470588236e-05, | |
| "loss": 0.9234, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.588235294117647, | |
| "grad_norm": 0.19456446170806885, | |
| "learning_rate": 9.176470588235295e-05, | |
| "loss": 0.9427, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.17445731163024902, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 0.9792, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.823529411764706, | |
| "grad_norm": 0.1859886646270752, | |
| "learning_rate": 9.647058823529412e-05, | |
| "loss": 0.9385, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.9411764705882355, | |
| "grad_norm": 0.1941513866186142, | |
| "learning_rate": 9.882352941176471e-05, | |
| "loss": 0.9261, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.0129356384277344, | |
| "eval_runtime": 37.9987, | |
| "eval_samples_per_second": 0.947, | |
| "eval_steps_per_second": 0.947, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.0588235294117645, | |
| "grad_norm": 0.22550666332244873, | |
| "learning_rate": 9.99995783847866e-05, | |
| "loss": 0.8715, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.176470588235294, | |
| "grad_norm": 0.2172684222459793, | |
| "learning_rate": 9.999620550574153e-05, | |
| "loss": 0.8998, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.294117647058823, | |
| "grad_norm": 0.265871524810791, | |
| "learning_rate": 9.998945997517956e-05, | |
| "loss": 0.9391, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.411764705882353, | |
| "grad_norm": 0.20749951899051666, | |
| "learning_rate": 9.997934224814173e-05, | |
| "loss": 0.9401, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.529411764705882, | |
| "grad_norm": 0.23640455305576324, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 0.9023, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 5.647058823529412, | |
| "grad_norm": 0.26980534195899963, | |
| "learning_rate": 9.994899316216708e-05, | |
| "loss": 0.9029, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 5.764705882352941, | |
| "grad_norm": 0.22679144144058228, | |
| "learning_rate": 9.992876385052345e-05, | |
| "loss": 0.9274, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 0.24695728719234467, | |
| "learning_rate": 9.990516643685222e-05, | |
| "loss": 0.93, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.24241463840007782, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.8846, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.9984785914421082, | |
| "eval_runtime": 38.004, | |
| "eval_samples_per_second": 0.947, | |
| "eval_steps_per_second": 0.947, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.117647058823529, | |
| "grad_norm": 0.22544971108436584, | |
| "learning_rate": 9.984787389787688e-05, | |
| "loss": 0.8528, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 6.235294117647059, | |
| "grad_norm": 0.25677189230918884, | |
| "learning_rate": 9.981418263742148e-05, | |
| "loss": 0.86, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 6.352941176470588, | |
| "grad_norm": 0.23866721987724304, | |
| "learning_rate": 9.977713100437509e-05, | |
| "loss": 0.8158, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 6.470588235294118, | |
| "grad_norm": 0.2694612145423889, | |
| "learning_rate": 9.973672149817232e-05, | |
| "loss": 0.8858, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.588235294117647, | |
| "grad_norm": 0.2675221264362335, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 0.8379, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 6.705882352941177, | |
| "grad_norm": 0.2968759834766388, | |
| "learning_rate": 9.964583999643174e-05, | |
| "loss": 0.9166, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.823529411764706, | |
| "grad_norm": 0.25507184863090515, | |
| "learning_rate": 9.95953741315919e-05, | |
| "loss": 0.9124, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 6.9411764705882355, | |
| "grad_norm": 0.2768806219100952, | |
| "learning_rate": 9.954156265457801e-05, | |
| "loss": 0.8643, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.9998984932899475, | |
| "eval_runtime": 38.0087, | |
| "eval_samples_per_second": 0.947, | |
| "eval_steps_per_second": 0.947, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 0.25486838817596436, | |
| "learning_rate": 9.948440919541278e-05, | |
| "loss": 0.8655, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.176470588235294, | |
| "grad_norm": 0.26725322008132935, | |
| "learning_rate": 9.942391760956277e-05, | |
| "loss": 0.8282, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 7.294117647058823, | |
| "grad_norm": 0.3074885904788971, | |
| "learning_rate": 9.936009197767845e-05, | |
| "loss": 0.8062, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 7.411764705882353, | |
| "grad_norm": 0.33064115047454834, | |
| "learning_rate": 9.929293660531888e-05, | |
| "loss": 0.7761, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 7.529411764705882, | |
| "grad_norm": 0.3693828582763672, | |
| "learning_rate": 9.922245602266118e-05, | |
| "loss": 0.8012, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 7.647058823529412, | |
| "grad_norm": 0.3340955674648285, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 0.8275, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.764705882352941, | |
| "grad_norm": 0.3681499660015106, | |
| "learning_rate": 9.90715384684021e-05, | |
| "loss": 0.7529, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 7.882352941176471, | |
| "grad_norm": 0.34088456630706787, | |
| "learning_rate": 9.899111167741966e-05, | |
| "loss": 0.8636, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.37362542748451233, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.7576, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.0170567035675049, | |
| "eval_runtime": 38.0014, | |
| "eval_samples_per_second": 0.947, | |
| "eval_steps_per_second": 0.947, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.117647058823529, | |
| "grad_norm": 0.41248711943626404, | |
| "learning_rate": 9.882034919459555e-05, | |
| "loss": 0.746, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 8.235294117647058, | |
| "grad_norm": 0.510824978351593, | |
| "learning_rate": 9.873002502207503e-05, | |
| "loss": 0.7089, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.352941176470589, | |
| "grad_norm": 0.4643978476524353, | |
| "learning_rate": 9.863641361223024e-05, | |
| "loss": 0.7757, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 8.470588235294118, | |
| "grad_norm": 0.4337863028049469, | |
| "learning_rate": 9.853952127991372e-05, | |
| "loss": 0.7567, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 8.588235294117647, | |
| "grad_norm": 0.45920026302337646, | |
| "learning_rate": 9.843935456130295e-05, | |
| "loss": 0.7669, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 8.705882352941176, | |
| "grad_norm": 0.4424627125263214, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 0.7526, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 8.823529411764707, | |
| "grad_norm": 0.45860111713409424, | |
| "learning_rate": 9.822922521387276e-05, | |
| "loss": 0.6996, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.941176470588236, | |
| "grad_norm": 0.5122858285903931, | |
| "learning_rate": 9.811927675999036e-05, | |
| "loss": 0.6809, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.0483341217041016, | |
| "eval_runtime": 38.0081, | |
| "eval_samples_per_second": 0.947, | |
| "eval_steps_per_second": 0.947, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.058823529411764, | |
| "grad_norm": 0.5136114954948425, | |
| "learning_rate": 9.800608226873142e-05, | |
| "loss": 0.71, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 9.176470588235293, | |
| "grad_norm": 0.6347455382347107, | |
| "learning_rate": 9.788964937598689e-05, | |
| "loss": 0.6533, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 9.294117647058824, | |
| "grad_norm": 0.5639290809631348, | |
| "learning_rate": 9.776998593610428e-05, | |
| "loss": 0.6705, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 0.5048836469650269, | |
| "learning_rate": 9.764710002135784e-05, | |
| "loss": 0.6655, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.529411764705882, | |
| "grad_norm": 0.5414577126502991, | |
| "learning_rate": 9.752099992140399e-05, | |
| "loss": 0.6378, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 9.647058823529411, | |
| "grad_norm": 0.6064717769622803, | |
| "learning_rate": 9.739169414272217e-05, | |
| "loss": 0.6629, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 9.764705882352942, | |
| "grad_norm": 0.5832774639129639, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 0.6795, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 9.882352941176471, | |
| "grad_norm": 0.6321535110473633, | |
| "learning_rate": 9.71235006557497e-05, | |
| "loss": 0.5703, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.5615116357803345, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.6404, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.095086693763733, | |
| "eval_runtime": 37.9992, | |
| "eval_samples_per_second": 0.947, | |
| "eval_steps_per_second": 0.947, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.117647058823529, | |
| "grad_norm": 0.6006438732147217, | |
| "learning_rate": 9.684259192656553e-05, | |
| "loss": 0.5289, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 10.235294117647058, | |
| "grad_norm": 0.7408490180969238, | |
| "learning_rate": 9.669739289925577e-05, | |
| "loss": 0.5612, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 10.352941176470589, | |
| "grad_norm": 0.7145248055458069, | |
| "learning_rate": 9.654904375222385e-05, | |
| "loss": 0.6012, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 10.470588235294118, | |
| "grad_norm": 0.9708057641983032, | |
| "learning_rate": 9.639755449282875e-05, | |
| "loss": 0.5171, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 10.588235294117647, | |
| "grad_norm": 0.6955903172492981, | |
| "learning_rate": 9.62429353402556e-05, | |
| "loss": 0.573, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 10.705882352941176, | |
| "grad_norm": 0.6297414302825928, | |
| "learning_rate": 9.608519672482636e-05, | |
| "loss": 0.5448, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 10.823529411764707, | |
| "grad_norm": 0.7149149775505066, | |
| "learning_rate": 9.592434928729616e-05, | |
| "loss": 0.5685, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 10.941176470588236, | |
| "grad_norm": 0.73154217004776, | |
| "learning_rate": 9.576040387813552e-05, | |
| "loss": 0.5943, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.137541651725769, | |
| "eval_runtime": 38.0008, | |
| "eval_samples_per_second": 0.947, | |
| "eval_steps_per_second": 0.947, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.058823529411764, | |
| "grad_norm": 0.635881781578064, | |
| "learning_rate": 9.559337155679842e-05, | |
| "loss": 0.5701, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 11.176470588235293, | |
| "grad_norm": 0.822847843170166, | |
| "learning_rate": 9.542326359097619e-05, | |
| "loss": 0.4971, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.294117647058824, | |
| "grad_norm": 0.8416553735733032, | |
| "learning_rate": 9.525009145583745e-05, | |
| "loss": 0.5472, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 11.411764705882353, | |
| "grad_norm": 0.7461684346199036, | |
| "learning_rate": 9.507386683325404e-05, | |
| "loss": 0.3399, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 11.529411764705882, | |
| "grad_norm": 1.0195852518081665, | |
| "learning_rate": 9.489460161101291e-05, | |
| "loss": 0.5238, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 11.647058823529411, | |
| "grad_norm": 0.8228163123130798, | |
| "learning_rate": 9.471230788201429e-05, | |
| "loss": 0.4945, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 0.8025856614112854, | |
| "learning_rate": 9.452699794345581e-05, | |
| "loss": 0.4842, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.882352941176471, | |
| "grad_norm": 0.7643564343452454, | |
| "learning_rate": 9.43386842960031e-05, | |
| "loss": 0.4817, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.7619509696960449, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.4267, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.2362412214279175, | |
| "eval_runtime": 38.0041, | |
| "eval_samples_per_second": 0.947, | |
| "eval_steps_per_second": 0.947, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.117647058823529, | |
| "grad_norm": 0.7823988199234009, | |
| "learning_rate": 9.395309688934351e-05, | |
| "loss": 0.4205, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 12.235294117647058, | |
| "grad_norm": 0.919938862323761, | |
| "learning_rate": 9.375584914114963e-05, | |
| "loss": 0.3754, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 12.352941176470589, | |
| "grad_norm": 0.7952852845191956, | |
| "learning_rate": 9.355564970433288e-05, | |
| "loss": 0.4087, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.470588235294118, | |
| "grad_norm": 0.8951109051704407, | |
| "learning_rate": 9.335251208397684e-05, | |
| "loss": 0.363, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 12.588235294117647, | |
| "grad_norm": 0.8961105942726135, | |
| "learning_rate": 9.314644998336949e-05, | |
| "loss": 0.4405, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 12.705882352941176, | |
| "grad_norm": 0.8086352348327637, | |
| "learning_rate": 9.293747730307889e-05, | |
| "loss": 0.365, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 12.823529411764707, | |
| "grad_norm": 1.0718464851379395, | |
| "learning_rate": 9.272560814001539e-05, | |
| "loss": 0.3986, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 12.941176470588236, | |
| "grad_norm": 0.8437643647193909, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.446, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.2402316331863403, | |
| "eval_runtime": 38.0048, | |
| "eval_samples_per_second": 0.947, | |
| "eval_steps_per_second": 0.947, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 221, | |
| "total_flos": 1.755282942029988e+17, | |
| "train_loss": 0.8710994886327114, | |
| "train_runtime": 6239.7757, | |
| "train_samples_per_second": 1.09, | |
| "train_steps_per_second": 0.136 | |
| } | |
| ], | |
| "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": 1.755282942029988e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |