| { | |
| "best_metric": 0.7769492864608765, | |
| "best_model_checkpoint": "data/Llama-31-8B_task-1_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": 1.6523724794387817, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 2.1691, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 1.6836340427398682, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 2.1842, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 1.5566470623016357, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 2.1145, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 1.2963809967041016, | |
| "learning_rate": 7.058823529411765e-06, | |
| "loss": 2.1306, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 1.4403284788131714, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 2.132, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 1.295866847038269, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 2.052, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 1.614176630973816, | |
| "learning_rate": 1.411764705882353e-05, | |
| "loss": 2.1225, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 1.2672216892242432, | |
| "learning_rate": 1.647058823529412e-05, | |
| "loss": 2.062, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.9760181903839111, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 1.9328, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.88367760181427, | |
| "eval_runtime": 14.8645, | |
| "eval_samples_per_second": 2.422, | |
| "eval_steps_per_second": 2.422, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 1.17051100730896, | |
| "learning_rate": 2.1176470588235296e-05, | |
| "loss": 1.8863, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 1.5599249601364136, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 1.8024, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 1.5132921934127808, | |
| "learning_rate": 2.5882352941176475e-05, | |
| "loss": 1.7803, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.6918522715568542, | |
| "learning_rate": 2.823529411764706e-05, | |
| "loss": 1.679, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5294117647058822, | |
| "grad_norm": 0.6983150243759155, | |
| "learning_rate": 3.058823529411765e-05, | |
| "loss": 1.6667, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.7761859893798828, | |
| "learning_rate": 3.294117647058824e-05, | |
| "loss": 1.539, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.8353598117828369, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 1.5206, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.9407578706741333, | |
| "learning_rate": 3.7647058823529415e-05, | |
| "loss": 1.376, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.949256956577301, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3207, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.2487163543701172, | |
| "eval_runtime": 14.8453, | |
| "eval_samples_per_second": 2.425, | |
| "eval_steps_per_second": 2.425, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.9521347284317017, | |
| "learning_rate": 4.235294117647059e-05, | |
| "loss": 1.2211, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.7206575274467468, | |
| "learning_rate": 4.470588235294118e-05, | |
| "loss": 1.1197, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.6541872024536133, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 1.0114, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.5366835594177246, | |
| "learning_rate": 4.9411764705882355e-05, | |
| "loss": 0.9836, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 0.511836051940918, | |
| "learning_rate": 5.176470588235295e-05, | |
| "loss": 0.9295, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.445992648601532, | |
| "learning_rate": 5.411764705882353e-05, | |
| "loss": 0.9802, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 0.5018168687820435, | |
| "learning_rate": 5.647058823529412e-05, | |
| "loss": 0.931, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.4126249849796295, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 0.8894, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.9027308225631714, | |
| "eval_runtime": 14.8851, | |
| "eval_samples_per_second": 2.419, | |
| "eval_steps_per_second": 2.419, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0588235294117645, | |
| "grad_norm": 0.4266379773616791, | |
| "learning_rate": 6.11764705882353e-05, | |
| "loss": 0.8278, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.176470588235294, | |
| "grad_norm": 0.3853524923324585, | |
| "learning_rate": 6.352941176470588e-05, | |
| "loss": 0.9039, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.2941176470588234, | |
| "grad_norm": 0.4155946969985962, | |
| "learning_rate": 6.588235294117648e-05, | |
| "loss": 0.8751, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.411764705882353, | |
| "grad_norm": 0.39866942167282104, | |
| "learning_rate": 6.823529411764707e-05, | |
| "loss": 0.9078, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 0.381352037191391, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.8152, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.6470588235294117, | |
| "grad_norm": 0.5366601347923279, | |
| "learning_rate": 7.294117647058823e-05, | |
| "loss": 0.8364, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.764705882352941, | |
| "grad_norm": 0.3933020234107971, | |
| "learning_rate": 7.529411764705883e-05, | |
| "loss": 0.8334, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.8823529411764706, | |
| "grad_norm": 0.40245521068573, | |
| "learning_rate": 7.764705882352942e-05, | |
| "loss": 0.8088, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.45432624220848083, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8023, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.8472109436988831, | |
| "eval_runtime": 14.8552, | |
| "eval_samples_per_second": 2.423, | |
| "eval_steps_per_second": 2.423, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.117647058823529, | |
| "grad_norm": 0.45503902435302734, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 0.7973, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.235294117647059, | |
| "grad_norm": 0.5366276502609253, | |
| "learning_rate": 8.470588235294118e-05, | |
| "loss": 0.7703, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.352941176470588, | |
| "grad_norm": 0.5137152671813965, | |
| "learning_rate": 8.705882352941177e-05, | |
| "loss": 0.7816, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.470588235294118, | |
| "grad_norm": 0.5894597172737122, | |
| "learning_rate": 8.941176470588236e-05, | |
| "loss": 0.7567, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.588235294117647, | |
| "grad_norm": 0.6147476434707642, | |
| "learning_rate": 9.176470588235295e-05, | |
| "loss": 0.8077, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.6426551342010498, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 0.7512, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.823529411764706, | |
| "grad_norm": 0.7501271367073059, | |
| "learning_rate": 9.647058823529412e-05, | |
| "loss": 0.7698, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.9411764705882355, | |
| "grad_norm": 0.6803474426269531, | |
| "learning_rate": 9.882352941176471e-05, | |
| "loss": 0.7382, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.8033356070518494, | |
| "eval_runtime": 14.848, | |
| "eval_samples_per_second": 2.425, | |
| "eval_steps_per_second": 2.425, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.0588235294117645, | |
| "grad_norm": 0.5934538245201111, | |
| "learning_rate": 9.99995783847866e-05, | |
| "loss": 0.6922, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.176470588235294, | |
| "grad_norm": 0.46946585178375244, | |
| "learning_rate": 9.999620550574153e-05, | |
| "loss": 0.729, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.294117647058823, | |
| "grad_norm": 0.47429749369621277, | |
| "learning_rate": 9.998945997517956e-05, | |
| "loss": 0.6776, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.411764705882353, | |
| "grad_norm": 0.5794419050216675, | |
| "learning_rate": 9.997934224814173e-05, | |
| "loss": 0.6623, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.529411764705882, | |
| "grad_norm": 0.6016111969947815, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 0.6451, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 5.647058823529412, | |
| "grad_norm": 0.54630446434021, | |
| "learning_rate": 9.994899316216708e-05, | |
| "loss": 0.617, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 5.764705882352941, | |
| "grad_norm": 0.5690641403198242, | |
| "learning_rate": 9.992876385052345e-05, | |
| "loss": 0.6952, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 0.656909704208374, | |
| "learning_rate": 9.990516643685222e-05, | |
| "loss": 0.6869, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.6280810832977295, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.6937, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.7769492864608765, | |
| "eval_runtime": 14.8716, | |
| "eval_samples_per_second": 2.421, | |
| "eval_steps_per_second": 2.421, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.117647058823529, | |
| "grad_norm": 0.6893706321716309, | |
| "learning_rate": 9.984787389787688e-05, | |
| "loss": 0.5477, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 6.235294117647059, | |
| "grad_norm": 0.6587519645690918, | |
| "learning_rate": 9.981418263742148e-05, | |
| "loss": 0.6074, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 6.352941176470588, | |
| "grad_norm": 0.6921840310096741, | |
| "learning_rate": 9.977713100437509e-05, | |
| "loss": 0.5796, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 6.470588235294118, | |
| "grad_norm": 0.6617905497550964, | |
| "learning_rate": 9.973672149817232e-05, | |
| "loss": 0.5966, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.588235294117647, | |
| "grad_norm": 0.6643382906913757, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 0.5631, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 6.705882352941177, | |
| "grad_norm": 0.8007850646972656, | |
| "learning_rate": 9.964583999643174e-05, | |
| "loss": 0.5944, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.823529411764706, | |
| "grad_norm": 0.7560325860977173, | |
| "learning_rate": 9.95953741315919e-05, | |
| "loss": 0.5503, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 6.9411764705882355, | |
| "grad_norm": 0.7627629637718201, | |
| "learning_rate": 9.954156265457801e-05, | |
| "loss": 0.6042, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.794569194316864, | |
| "eval_runtime": 14.8548, | |
| "eval_samples_per_second": 2.423, | |
| "eval_steps_per_second": 2.423, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 0.6710206270217896, | |
| "learning_rate": 9.948440919541278e-05, | |
| "loss": 0.5629, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.176470588235294, | |
| "grad_norm": 0.720169723033905, | |
| "learning_rate": 9.942391760956277e-05, | |
| "loss": 0.4882, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 7.294117647058823, | |
| "grad_norm": 0.7802786827087402, | |
| "learning_rate": 9.936009197767845e-05, | |
| "loss": 0.47, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 7.411764705882353, | |
| "grad_norm": 0.9922766089439392, | |
| "learning_rate": 9.929293660531888e-05, | |
| "loss": 0.4643, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 7.529411764705882, | |
| "grad_norm": 0.9673358201980591, | |
| "learning_rate": 9.922245602266118e-05, | |
| "loss": 0.4587, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 7.647058823529412, | |
| "grad_norm": 0.8364777565002441, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 0.4661, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.764705882352941, | |
| "grad_norm": 0.9660435318946838, | |
| "learning_rate": 9.90715384684021e-05, | |
| "loss": 0.4597, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 7.882352941176471, | |
| "grad_norm": 0.855879545211792, | |
| "learning_rate": 9.899111167741966e-05, | |
| "loss": 0.5083, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.8621300458908081, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.4994, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.8584206700325012, | |
| "eval_runtime": 14.8559, | |
| "eval_samples_per_second": 2.423, | |
| "eval_steps_per_second": 2.423, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.117647058823529, | |
| "grad_norm": 0.8841436505317688, | |
| "learning_rate": 9.882034919459555e-05, | |
| "loss": 0.3538, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 8.235294117647058, | |
| "grad_norm": 0.9180885553359985, | |
| "learning_rate": 9.873002502207503e-05, | |
| "loss": 0.3524, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.352941176470589, | |
| "grad_norm": 1.4361402988433838, | |
| "learning_rate": 9.863641361223024e-05, | |
| "loss": 0.3367, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 8.470588235294118, | |
| "grad_norm": 1.1419262886047363, | |
| "learning_rate": 9.853952127991372e-05, | |
| "loss": 0.4098, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 8.588235294117647, | |
| "grad_norm": 0.9227531552314758, | |
| "learning_rate": 9.843935456130295e-05, | |
| "loss": 0.3554, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 8.705882352941176, | |
| "grad_norm": 0.9173327684402466, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 0.3181, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 8.823529411764707, | |
| "grad_norm": 0.941938579082489, | |
| "learning_rate": 9.822922521387276e-05, | |
| "loss": 0.3863, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.941176470588236, | |
| "grad_norm": 1.236094355583191, | |
| "learning_rate": 9.811927675999036e-05, | |
| "loss": 0.3568, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.9740625023841858, | |
| "eval_runtime": 14.8524, | |
| "eval_samples_per_second": 2.424, | |
| "eval_steps_per_second": 2.424, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.058823529411764, | |
| "grad_norm": 0.9866283535957336, | |
| "learning_rate": 9.800608226873142e-05, | |
| "loss": 0.2949, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 9.176470588235293, | |
| "grad_norm": 1.017112374305725, | |
| "learning_rate": 9.788964937598689e-05, | |
| "loss": 0.2554, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 9.294117647058824, | |
| "grad_norm": 1.4848501682281494, | |
| "learning_rate": 9.776998593610428e-05, | |
| "loss": 0.2178, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 1.5629372596740723, | |
| "learning_rate": 9.764710002135784e-05, | |
| "loss": 0.2582, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.529411764705882, | |
| "grad_norm": 1.040290117263794, | |
| "learning_rate": 9.752099992140399e-05, | |
| "loss": 0.2465, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 9.647058823529411, | |
| "grad_norm": 1.0305852890014648, | |
| "learning_rate": 9.739169414272217e-05, | |
| "loss": 0.2581, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 9.764705882352942, | |
| "grad_norm": 0.9678947925567627, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 0.2686, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 9.882352941176471, | |
| "grad_norm": 1.1301528215408325, | |
| "learning_rate": 9.71235006557497e-05, | |
| "loss": 0.2563, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.0202564001083374, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.2463, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.0730422735214233, | |
| "eval_runtime": 14.8529, | |
| "eval_samples_per_second": 2.424, | |
| "eval_steps_per_second": 2.424, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.117647058823529, | |
| "grad_norm": 0.8738579154014587, | |
| "learning_rate": 9.684259192656553e-05, | |
| "loss": 0.1708, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 10.235294117647058, | |
| "grad_norm": 1.2385995388031006, | |
| "learning_rate": 9.669739289925577e-05, | |
| "loss": 0.1605, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 10.352941176470589, | |
| "grad_norm": 1.486833930015564, | |
| "learning_rate": 9.654904375222385e-05, | |
| "loss": 0.1762, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 10.470588235294118, | |
| "grad_norm": 1.0552796125411987, | |
| "learning_rate": 9.639755449282875e-05, | |
| "loss": 0.1627, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 10.588235294117647, | |
| "grad_norm": 0.9729524254798889, | |
| "learning_rate": 9.62429353402556e-05, | |
| "loss": 0.1652, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 10.705882352941176, | |
| "grad_norm": 1.1173099279403687, | |
| "learning_rate": 9.608519672482636e-05, | |
| "loss": 0.207, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 10.823529411764707, | |
| "grad_norm": 1.094077467918396, | |
| "learning_rate": 9.592434928729616e-05, | |
| "loss": 0.1874, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 10.941176470588236, | |
| "grad_norm": 1.0079216957092285, | |
| "learning_rate": 9.576040387813552e-05, | |
| "loss": 0.1823, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.1565437316894531, | |
| "eval_runtime": 14.8518, | |
| "eval_samples_per_second": 2.424, | |
| "eval_steps_per_second": 2.424, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.058823529411764, | |
| "grad_norm": 0.8162212371826172, | |
| "learning_rate": 9.559337155679842e-05, | |
| "loss": 0.1429, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 11.176470588235293, | |
| "grad_norm": 0.9778859615325928, | |
| "learning_rate": 9.542326359097619e-05, | |
| "loss": 0.1296, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.294117647058824, | |
| "grad_norm": 0.8713005781173706, | |
| "learning_rate": 9.525009145583745e-05, | |
| "loss": 0.1189, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 11.411764705882353, | |
| "grad_norm": 1.829667329788208, | |
| "learning_rate": 9.507386683325404e-05, | |
| "loss": 0.1384, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 11.529411764705882, | |
| "grad_norm": 1.2394943237304688, | |
| "learning_rate": 9.489460161101291e-05, | |
| "loss": 0.13, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 11.647058823529411, | |
| "grad_norm": 1.0086442232131958, | |
| "learning_rate": 9.471230788201429e-05, | |
| "loss": 0.1187, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 0.9524409174919128, | |
| "learning_rate": 9.452699794345581e-05, | |
| "loss": 0.1342, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.882352941176471, | |
| "grad_norm": 1.0471522808074951, | |
| "learning_rate": 9.43386842960031e-05, | |
| "loss": 0.1194, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 1.002863883972168, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.1229, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.2556722164154053, | |
| "eval_runtime": 14.8677, | |
| "eval_samples_per_second": 2.421, | |
| "eval_steps_per_second": 2.421, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.117647058823529, | |
| "grad_norm": 0.6466752886772156, | |
| "learning_rate": 9.395309688934351e-05, | |
| "loss": 0.0892, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 12.235294117647058, | |
| "grad_norm": 0.6629582643508911, | |
| "learning_rate": 9.375584914114963e-05, | |
| "loss": 0.1036, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 12.352941176470589, | |
| "grad_norm": 0.9311277270317078, | |
| "learning_rate": 9.355564970433288e-05, | |
| "loss": 0.1041, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.470588235294118, | |
| "grad_norm": 1.2726823091506958, | |
| "learning_rate": 9.335251208397684e-05, | |
| "loss": 0.096, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 12.588235294117647, | |
| "grad_norm": 1.180190086364746, | |
| "learning_rate": 9.314644998336949e-05, | |
| "loss": 0.0928, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 12.705882352941176, | |
| "grad_norm": 1.1233559846878052, | |
| "learning_rate": 9.293747730307889e-05, | |
| "loss": 0.0982, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 12.823529411764707, | |
| "grad_norm": 0.8981254696846008, | |
| "learning_rate": 9.272560814001539e-05, | |
| "loss": 0.0948, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 12.941176470588236, | |
| "grad_norm": 0.9729477167129517, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.1015, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.330010175704956, | |
| "eval_runtime": 14.8631, | |
| "eval_samples_per_second": 2.422, | |
| "eval_steps_per_second": 2.422, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 221, | |
| "total_flos": 3.000024813063373e+16, | |
| "train_loss": 0.6953470619960068, | |
| "train_runtime": 2134.7301, | |
| "train_samples_per_second": 3.185, | |
| "train_steps_per_second": 0.398 | |
| } | |
| ], | |
| "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": 3.000024813063373e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |