| { | |
| "best_metric": 0.43765950202941895, | |
| "best_model_checkpoint": "data/Llama-31-8B_task-3_180-samples_config-1/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": 2.9806036949157715, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 2.6305, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 1.5811554193496704, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 2.0227, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 3.059112310409546, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 2.8006, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 1.5905879735946655, | |
| "learning_rate": 7.058823529411765e-06, | |
| "loss": 2.5659, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 2.937735080718994, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 2.3172, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 2.908135175704956, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 2.4708, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 2.5028913021087646, | |
| "learning_rate": 1.411764705882353e-05, | |
| "loss": 2.0215, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 3.3263680934906006, | |
| "learning_rate": 1.647058823529412e-05, | |
| "loss": 2.2979, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 1.5710484981536865, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 1.9354, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.7708439826965332, | |
| "eval_runtime": 31.8772, | |
| "eval_samples_per_second": 1.129, | |
| "eval_steps_per_second": 1.129, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 1.1524016857147217, | |
| "learning_rate": 2.1176470588235296e-05, | |
| "loss": 1.7289, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 2.096369981765747, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 1.6079, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 1.5421291589736938, | |
| "learning_rate": 2.5882352941176475e-05, | |
| "loss": 1.3783, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 2.0535740852355957, | |
| "learning_rate": 2.823529411764706e-05, | |
| "loss": 1.1007, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5294117647058822, | |
| "grad_norm": 1.7358132600784302, | |
| "learning_rate": 3.058823529411765e-05, | |
| "loss": 0.8679, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 1.2015416622161865, | |
| "learning_rate": 3.294117647058824e-05, | |
| "loss": 0.7215, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 1.3056217432022095, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 0.959, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 1.081710934638977, | |
| "learning_rate": 3.7647058823529415e-05, | |
| "loss": 0.4937, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.6709741353988647, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6268, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6220616102218628, | |
| "eval_runtime": 31.8809, | |
| "eval_samples_per_second": 1.129, | |
| "eval_steps_per_second": 1.129, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.6889598369598389, | |
| "learning_rate": 4.235294117647059e-05, | |
| "loss": 0.5838, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 1.135616421699524, | |
| "learning_rate": 4.470588235294118e-05, | |
| "loss": 0.6598, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 1.0939359664916992, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 0.554, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.9954046607017517, | |
| "learning_rate": 4.9411764705882355e-05, | |
| "loss": 0.4145, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 0.4152926802635193, | |
| "learning_rate": 5.176470588235295e-05, | |
| "loss": 0.4579, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.4777827560901642, | |
| "learning_rate": 5.411764705882353e-05, | |
| "loss": 0.5156, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 7.0992631912231445, | |
| "learning_rate": 5.647058823529412e-05, | |
| "loss": 0.5171, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.2415984869003296, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 0.3923, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.5086178183555603, | |
| "eval_runtime": 31.8697, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0588235294117645, | |
| "grad_norm": 0.3886338472366333, | |
| "learning_rate": 6.11764705882353e-05, | |
| "loss": 0.3796, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.176470588235294, | |
| "grad_norm": 0.5336315035820007, | |
| "learning_rate": 6.352941176470588e-05, | |
| "loss": 0.6383, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.2941176470588234, | |
| "grad_norm": 0.5669986009597778, | |
| "learning_rate": 6.588235294117648e-05, | |
| "loss": 0.4904, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.411764705882353, | |
| "grad_norm": 0.2478373944759369, | |
| "learning_rate": 6.823529411764707e-05, | |
| "loss": 0.536, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 0.16090020537376404, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.2108, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.6470588235294117, | |
| "grad_norm": 0.350099116563797, | |
| "learning_rate": 7.294117647058823e-05, | |
| "loss": 0.4021, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.764705882352941, | |
| "grad_norm": 1.6697726249694824, | |
| "learning_rate": 7.529411764705883e-05, | |
| "loss": 0.5626, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.8823529411764706, | |
| "grad_norm": 0.34072333574295044, | |
| "learning_rate": 7.764705882352942e-05, | |
| "loss": 0.2934, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.7432898283004761, | |
| "learning_rate": 8e-05, | |
| "loss": 0.2943, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.45811617374420166, | |
| "eval_runtime": 31.868, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.117647058823529, | |
| "grad_norm": 0.5389276742935181, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 0.3754, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.235294117647059, | |
| "grad_norm": 0.43829599022865295, | |
| "learning_rate": 8.470588235294118e-05, | |
| "loss": 0.3586, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.352941176470588, | |
| "grad_norm": 0.5614160895347595, | |
| "learning_rate": 8.705882352941177e-05, | |
| "loss": 0.5275, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.470588235294118, | |
| "grad_norm": 0.3643663823604584, | |
| "learning_rate": 8.941176470588236e-05, | |
| "loss": 0.342, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.588235294117647, | |
| "grad_norm": 0.3923664689064026, | |
| "learning_rate": 9.176470588235295e-05, | |
| "loss": 0.395, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.44436177611351013, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 0.2989, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.823529411764706, | |
| "grad_norm": 0.4928082227706909, | |
| "learning_rate": 9.647058823529412e-05, | |
| "loss": 0.3496, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.9411764705882355, | |
| "grad_norm": 0.5441502928733826, | |
| "learning_rate": 9.882352941176471e-05, | |
| "loss": 0.3006, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.4389885663986206, | |
| "eval_runtime": 31.8626, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.0588235294117645, | |
| "grad_norm": 0.4954172372817993, | |
| "learning_rate": 9.99995783847866e-05, | |
| "loss": 0.3281, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.176470588235294, | |
| "grad_norm": 0.4600774347782135, | |
| "learning_rate": 9.999620550574153e-05, | |
| "loss": 0.3747, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.294117647058823, | |
| "grad_norm": 0.510309100151062, | |
| "learning_rate": 9.998945997517956e-05, | |
| "loss": 0.2751, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.411764705882353, | |
| "grad_norm": 0.003833649680018425, | |
| "learning_rate": 9.997934224814173e-05, | |
| "loss": 0.11, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.529411764705882, | |
| "grad_norm": 0.9155761003494263, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 0.2909, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 5.647058823529412, | |
| "grad_norm": 0.5105080008506775, | |
| "learning_rate": 9.994899316216708e-05, | |
| "loss": 0.1964, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 5.764705882352941, | |
| "grad_norm": 0.6393014192581177, | |
| "learning_rate": 9.992876385052345e-05, | |
| "loss": 0.3017, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 0.4922525882720947, | |
| "learning_rate": 9.990516643685222e-05, | |
| "loss": 0.3364, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.7725474238395691, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.3831, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.43765950202941895, | |
| "eval_runtime": 31.8564, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.117647058823529, | |
| "grad_norm": 0.5879455208778381, | |
| "learning_rate": 9.984787389787688e-05, | |
| "loss": 0.1447, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 6.235294117647059, | |
| "grad_norm": 0.7769209742546082, | |
| "learning_rate": 9.981418263742148e-05, | |
| "loss": 0.2444, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 6.352941176470588, | |
| "grad_norm": 1.1724755764007568, | |
| "learning_rate": 9.977713100437509e-05, | |
| "loss": 0.2148, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 6.470588235294118, | |
| "grad_norm": 0.599888801574707, | |
| "learning_rate": 9.973672149817232e-05, | |
| "loss": 0.1624, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.588235294117647, | |
| "grad_norm": 0.8013498187065125, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 0.1627, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 6.705882352941177, | |
| "grad_norm": 0.6758402585983276, | |
| "learning_rate": 9.964583999643174e-05, | |
| "loss": 0.1462, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.823529411764706, | |
| "grad_norm": 0.6956180334091187, | |
| "learning_rate": 9.95953741315919e-05, | |
| "loss": 0.2132, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 6.9411764705882355, | |
| "grad_norm": 1.106181263923645, | |
| "learning_rate": 9.954156265457801e-05, | |
| "loss": 0.2878, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.49799612164497375, | |
| "eval_runtime": 31.8667, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 0.7827078104019165, | |
| "learning_rate": 9.948440919541278e-05, | |
| "loss": 0.2307, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.176470588235294, | |
| "grad_norm": 1.054808259010315, | |
| "learning_rate": 9.942391760956277e-05, | |
| "loss": 0.1359, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 7.294117647058823, | |
| "grad_norm": 2.5423500537872314, | |
| "learning_rate": 9.936009197767845e-05, | |
| "loss": 0.1569, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 7.411764705882353, | |
| "grad_norm": 1.2457938194274902, | |
| "learning_rate": 9.929293660531888e-05, | |
| "loss": 0.1147, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 7.529411764705882, | |
| "grad_norm": 0.7288180589675903, | |
| "learning_rate": 9.922245602266118e-05, | |
| "loss": 0.0994, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 7.647058823529412, | |
| "grad_norm": 0.4904559254646301, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 0.0794, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.764705882352941, | |
| "grad_norm": 0.8609570264816284, | |
| "learning_rate": 9.90715384684021e-05, | |
| "loss": 0.0841, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 7.882352941176471, | |
| "grad_norm": 0.5112635493278503, | |
| "learning_rate": 9.899111167741966e-05, | |
| "loss": 0.1191, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.8523367047309875, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.1028, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.6311503052711487, | |
| "eval_runtime": 31.8647, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.117647058823529, | |
| "grad_norm": 0.8957595229148865, | |
| "learning_rate": 9.882034919459555e-05, | |
| "loss": 0.0577, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 8.235294117647058, | |
| "grad_norm": 0.7346336841583252, | |
| "learning_rate": 9.873002502207503e-05, | |
| "loss": 0.0451, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.352941176470589, | |
| "grad_norm": 1.4324090480804443, | |
| "learning_rate": 9.863641361223024e-05, | |
| "loss": 0.0778, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 8.470588235294118, | |
| "grad_norm": 0.000629694142844528, | |
| "learning_rate": 9.853952127991372e-05, | |
| "loss": 0.0458, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 8.588235294117647, | |
| "grad_norm": 0.9645481705665588, | |
| "learning_rate": 9.843935456130295e-05, | |
| "loss": 0.0654, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 8.705882352941176, | |
| "grad_norm": 0.697653591632843, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 0.0259, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 8.823529411764707, | |
| "grad_norm": 1.007393479347229, | |
| "learning_rate": 9.822922521387276e-05, | |
| "loss": 0.0572, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.941176470588236, | |
| "grad_norm": 0.7456847429275513, | |
| "learning_rate": 9.811927675999036e-05, | |
| "loss": 0.0608, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.6598667502403259, | |
| "eval_runtime": 31.8676, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.058823529411764, | |
| "grad_norm": 0.5595569014549255, | |
| "learning_rate": 9.800608226873142e-05, | |
| "loss": 0.0279, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 9.176470588235293, | |
| "grad_norm": 0.6336766481399536, | |
| "learning_rate": 9.788964937598689e-05, | |
| "loss": 0.0309, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 9.294117647058824, | |
| "grad_norm": 0.7993122339248657, | |
| "learning_rate": 9.776998593610428e-05, | |
| "loss": 0.028, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 0.8022798895835876, | |
| "learning_rate": 9.764710002135784e-05, | |
| "loss": 0.0298, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.529411764705882, | |
| "grad_norm": 0.6976908445358276, | |
| "learning_rate": 9.752099992140399e-05, | |
| "loss": 0.0192, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 9.647058823529411, | |
| "grad_norm": 0.6124653220176697, | |
| "learning_rate": 9.739169414272217e-05, | |
| "loss": 0.0151, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 9.764705882352942, | |
| "grad_norm": 0.6153112053871155, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 0.0276, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 9.882352941176471, | |
| "grad_norm": 0.6241044402122498, | |
| "learning_rate": 9.71235006557497e-05, | |
| "loss": 0.0201, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.5975130200386047, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.0272, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.7521817088127136, | |
| "eval_runtime": 31.8729, | |
| "eval_samples_per_second": 1.129, | |
| "eval_steps_per_second": 1.129, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.117647058823529, | |
| "grad_norm": 0.6075451374053955, | |
| "learning_rate": 9.684259192656553e-05, | |
| "loss": 0.0109, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 10.235294117647058, | |
| "grad_norm": 0.40531089901924133, | |
| "learning_rate": 9.669739289925577e-05, | |
| "loss": 0.0129, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 10.352941176470589, | |
| "grad_norm": 0.3455725908279419, | |
| "learning_rate": 9.654904375222385e-05, | |
| "loss": 0.0067, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 10.470588235294118, | |
| "grad_norm": 0.8923009634017944, | |
| "learning_rate": 9.639755449282875e-05, | |
| "loss": 0.0185, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 10.588235294117647, | |
| "grad_norm": 0.3538866937160492, | |
| "learning_rate": 9.62429353402556e-05, | |
| "loss": 0.009, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 10.705882352941176, | |
| "grad_norm": 0.5075867772102356, | |
| "learning_rate": 9.608519672482636e-05, | |
| "loss": 0.0121, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 10.823529411764707, | |
| "grad_norm": 0.9656047224998474, | |
| "learning_rate": 9.592434928729616e-05, | |
| "loss": 0.0263, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 10.941176470588236, | |
| "grad_norm": 1.078016996383667, | |
| "learning_rate": 9.576040387813552e-05, | |
| "loss": 0.0172, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.8401343822479248, | |
| "eval_runtime": 31.8673, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.058823529411764, | |
| "grad_norm": 0.16839314997196198, | |
| "learning_rate": 9.559337155679842e-05, | |
| "loss": 0.0032, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 11.176470588235293, | |
| "grad_norm": 0.3535742461681366, | |
| "learning_rate": 9.542326359097619e-05, | |
| "loss": 0.0047, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.294117647058824, | |
| "grad_norm": 0.2792235314846039, | |
| "learning_rate": 9.525009145583745e-05, | |
| "loss": 0.0069, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 11.411764705882353, | |
| "grad_norm": 0.28880617022514343, | |
| "learning_rate": 9.507386683325404e-05, | |
| "loss": 0.0184, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 11.529411764705882, | |
| "grad_norm": 0.496808260679245, | |
| "learning_rate": 9.489460161101291e-05, | |
| "loss": 0.0105, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 11.647058823529411, | |
| "grad_norm": 0.29307544231414795, | |
| "learning_rate": 9.471230788201429e-05, | |
| "loss": 0.0049, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 0.2909545600414276, | |
| "learning_rate": 9.452699794345581e-05, | |
| "loss": 0.0077, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.882352941176471, | |
| "grad_norm": 0.2807806432247162, | |
| "learning_rate": 9.43386842960031e-05, | |
| "loss": 0.0026, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.15847039222717285, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.0086, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.8499218821525574, | |
| "eval_runtime": 31.8689, | |
| "eval_samples_per_second": 1.13, | |
| "eval_steps_per_second": 1.13, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.117647058823529, | |
| "grad_norm": 0.12410937249660492, | |
| "learning_rate": 9.395309688934351e-05, | |
| "loss": 0.0014, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 12.235294117647058, | |
| "grad_norm": 0.09352313727140427, | |
| "learning_rate": 9.375584914114963e-05, | |
| "loss": 0.0031, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 12.352941176470589, | |
| "grad_norm": 0.057727377861738205, | |
| "learning_rate": 9.355564970433288e-05, | |
| "loss": 0.0019, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.470588235294118, | |
| "grad_norm": 0.9200026392936707, | |
| "learning_rate": 9.335251208397684e-05, | |
| "loss": 0.0123, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 12.588235294117647, | |
| "grad_norm": 0.05677800625562668, | |
| "learning_rate": 9.314644998336949e-05, | |
| "loss": 0.0036, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 12.705882352941176, | |
| "grad_norm": 0.16251857578754425, | |
| "learning_rate": 9.293747730307889e-05, | |
| "loss": 0.0025, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 12.823529411764707, | |
| "grad_norm": 0.7199786305427551, | |
| "learning_rate": 9.272560814001539e-05, | |
| "loss": 0.0043, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 12.941176470588236, | |
| "grad_norm": 0.8885202407836914, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.0078, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.835817813873291, | |
| "eval_runtime": 31.8664, | |
| "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": 0.40950302978265374, | |
| "train_runtime": 5089.6281, | |
| "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 | |
| } | |