| { | |
| "best_metric": 0.8559175133705139, | |
| "best_model_checkpoint": "data/Gemma-2-2B_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": 0.44557425379753113, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 1.2887, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.46409451961517334, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 1.3351, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.5389336943626404, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 1.3366, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 0.6690118908882141, | |
| "learning_rate": 7.058823529411765e-06, | |
| "loss": 1.349, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.4524342715740204, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 1.3157, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.4505831003189087, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 1.2825, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.40734270215034485, | |
| "learning_rate": 1.411764705882353e-05, | |
| "loss": 1.2674, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 0.507776141166687, | |
| "learning_rate": 1.647058823529412e-05, | |
| "loss": 1.2858, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.3996591866016388, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 1.2757, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.2557902336120605, | |
| "eval_runtime": 14.3237, | |
| "eval_samples_per_second": 2.513, | |
| "eval_steps_per_second": 2.513, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 0.38115519285202026, | |
| "learning_rate": 2.1176470588235296e-05, | |
| "loss": 1.3028, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.33201029896736145, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 1.2415, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 0.3179093599319458, | |
| "learning_rate": 2.5882352941176475e-05, | |
| "loss": 1.213, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.29493674635887146, | |
| "learning_rate": 2.823529411764706e-05, | |
| "loss": 1.1568, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5294117647058822, | |
| "grad_norm": 0.2580755650997162, | |
| "learning_rate": 3.058823529411765e-05, | |
| "loss": 1.1347, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.2519474923610687, | |
| "learning_rate": 3.294117647058824e-05, | |
| "loss": 1.1551, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.28838059306144714, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 1.1194, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.2726597785949707, | |
| "learning_rate": 3.7647058823529415e-05, | |
| "loss": 1.0802, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.27081483602523804, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0993, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.0768206119537354, | |
| "eval_runtime": 14.3153, | |
| "eval_samples_per_second": 2.515, | |
| "eval_steps_per_second": 2.515, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.2724240720272064, | |
| "learning_rate": 4.235294117647059e-05, | |
| "loss": 1.0529, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.2476433962583542, | |
| "learning_rate": 4.470588235294118e-05, | |
| "loss": 1.0052, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.244949072599411, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 1.0106, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.2707188129425049, | |
| "learning_rate": 4.9411764705882355e-05, | |
| "loss": 1.0266, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 0.28227752447128296, | |
| "learning_rate": 5.176470588235295e-05, | |
| "loss": 0.9574, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.3808193802833557, | |
| "learning_rate": 5.411764705882353e-05, | |
| "loss": 0.9719, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 0.23235781490802765, | |
| "learning_rate": 5.647058823529412e-05, | |
| "loss": 0.9431, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.23546043038368225, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 0.9179, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.9359103441238403, | |
| "eval_runtime": 14.3183, | |
| "eval_samples_per_second": 2.514, | |
| "eval_steps_per_second": 2.514, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0588235294117645, | |
| "grad_norm": 0.20412394404411316, | |
| "learning_rate": 6.11764705882353e-05, | |
| "loss": 0.8754, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.176470588235294, | |
| "grad_norm": 0.1845676749944687, | |
| "learning_rate": 6.352941176470588e-05, | |
| "loss": 0.8557, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.2941176470588234, | |
| "grad_norm": 0.1963583528995514, | |
| "learning_rate": 6.588235294117648e-05, | |
| "loss": 0.9079, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.411764705882353, | |
| "grad_norm": 0.24228143692016602, | |
| "learning_rate": 6.823529411764707e-05, | |
| "loss": 0.922, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 0.1979658007621765, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.8162, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.6470588235294117, | |
| "grad_norm": 0.17711713910102844, | |
| "learning_rate": 7.294117647058823e-05, | |
| "loss": 0.9042, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.764705882352941, | |
| "grad_norm": 0.24821941554546356, | |
| "learning_rate": 7.529411764705883e-05, | |
| "loss": 0.8467, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.8823529411764706, | |
| "grad_norm": 0.20329095423221588, | |
| "learning_rate": 7.764705882352942e-05, | |
| "loss": 0.8063, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.1967359036207199, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8135, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.8880578875541687, | |
| "eval_runtime": 14.3227, | |
| "eval_samples_per_second": 2.513, | |
| "eval_steps_per_second": 2.513, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.117647058823529, | |
| "grad_norm": 0.2104751318693161, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 0.9141, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.235294117647059, | |
| "grad_norm": 0.19950838387012482, | |
| "learning_rate": 8.470588235294118e-05, | |
| "loss": 0.7671, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.352941176470588, | |
| "grad_norm": 0.17338353395462036, | |
| "learning_rate": 8.705882352941177e-05, | |
| "loss": 0.8438, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.470588235294118, | |
| "grad_norm": 0.1931561678647995, | |
| "learning_rate": 8.941176470588236e-05, | |
| "loss": 0.7856, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.588235294117647, | |
| "grad_norm": 0.204703226685524, | |
| "learning_rate": 9.176470588235295e-05, | |
| "loss": 0.806, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.18646745383739471, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 0.826, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.823529411764706, | |
| "grad_norm": 0.24499262869358063, | |
| "learning_rate": 9.647058823529412e-05, | |
| "loss": 0.7958, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.9411764705882355, | |
| "grad_norm": 0.5254810452461243, | |
| "learning_rate": 9.882352941176471e-05, | |
| "loss": 0.7851, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.8659862875938416, | |
| "eval_runtime": 14.3219, | |
| "eval_samples_per_second": 2.514, | |
| "eval_steps_per_second": 2.514, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.0588235294117645, | |
| "grad_norm": 0.2184593379497528, | |
| "learning_rate": 9.99995783847866e-05, | |
| "loss": 0.7489, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.176470588235294, | |
| "grad_norm": 0.22517095506191254, | |
| "learning_rate": 9.999620550574153e-05, | |
| "loss": 0.7633, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.294117647058823, | |
| "grad_norm": 0.22111377120018005, | |
| "learning_rate": 9.998945997517956e-05, | |
| "loss": 0.7976, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.411764705882353, | |
| "grad_norm": 0.22816969454288483, | |
| "learning_rate": 9.997934224814173e-05, | |
| "loss": 0.7986, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.529411764705882, | |
| "grad_norm": 0.23081211745738983, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 0.757, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 5.647058823529412, | |
| "grad_norm": 0.2289036512374878, | |
| "learning_rate": 9.994899316216708e-05, | |
| "loss": 0.7629, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 5.764705882352941, | |
| "grad_norm": 0.2328266054391861, | |
| "learning_rate": 9.992876385052345e-05, | |
| "loss": 0.7835, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 0.2813725173473358, | |
| "learning_rate": 9.990516643685222e-05, | |
| "loss": 0.8117, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.2496640831232071, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.7461, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.8559175133705139, | |
| "eval_runtime": 14.3167, | |
| "eval_samples_per_second": 2.515, | |
| "eval_steps_per_second": 2.515, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.117647058823529, | |
| "grad_norm": 0.2345692366361618, | |
| "learning_rate": 9.984787389787688e-05, | |
| "loss": 0.7141, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 6.235294117647059, | |
| "grad_norm": 0.25992751121520996, | |
| "learning_rate": 9.981418263742148e-05, | |
| "loss": 0.7454, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 6.352941176470588, | |
| "grad_norm": 0.2537041902542114, | |
| "learning_rate": 9.977713100437509e-05, | |
| "loss": 0.687, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 6.470588235294118, | |
| "grad_norm": 0.2825081944465637, | |
| "learning_rate": 9.973672149817232e-05, | |
| "loss": 0.7441, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.588235294117647, | |
| "grad_norm": 0.2681923508644104, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 0.7096, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 6.705882352941177, | |
| "grad_norm": 0.3162495195865631, | |
| "learning_rate": 9.964583999643174e-05, | |
| "loss": 0.7805, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.823529411764706, | |
| "grad_norm": 0.297635018825531, | |
| "learning_rate": 9.95953741315919e-05, | |
| "loss": 0.7623, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 6.9411764705882355, | |
| "grad_norm": 0.3174566924571991, | |
| "learning_rate": 9.954156265457801e-05, | |
| "loss": 0.7244, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.8580873608589172, | |
| "eval_runtime": 14.3169, | |
| "eval_samples_per_second": 2.515, | |
| "eval_steps_per_second": 2.515, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 0.2805008590221405, | |
| "learning_rate": 9.948440919541278e-05, | |
| "loss": 0.7486, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.176470588235294, | |
| "grad_norm": 0.29953888058662415, | |
| "learning_rate": 9.942391760956277e-05, | |
| "loss": 0.6948, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 7.294117647058823, | |
| "grad_norm": 0.3195772171020508, | |
| "learning_rate": 9.936009197767845e-05, | |
| "loss": 0.6806, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 7.411764705882353, | |
| "grad_norm": 0.35064831376075745, | |
| "learning_rate": 9.929293660531888e-05, | |
| "loss": 0.6591, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 7.529411764705882, | |
| "grad_norm": 0.3541794419288635, | |
| "learning_rate": 9.922245602266118e-05, | |
| "loss": 0.6771, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 7.647058823529412, | |
| "grad_norm": 0.37810057401657104, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 0.6934, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.764705882352941, | |
| "grad_norm": 0.38405174016952515, | |
| "learning_rate": 9.90715384684021e-05, | |
| "loss": 0.6319, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 7.882352941176471, | |
| "grad_norm": 0.4086880087852478, | |
| "learning_rate": 9.899111167741966e-05, | |
| "loss": 0.7391, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.40427207946777344, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.6484, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.8743382692337036, | |
| "eval_runtime": 14.3209, | |
| "eval_samples_per_second": 2.514, | |
| "eval_steps_per_second": 2.514, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.117647058823529, | |
| "grad_norm": 0.4126022756099701, | |
| "learning_rate": 9.882034919459555e-05, | |
| "loss": 0.6391, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 8.235294117647058, | |
| "grad_norm": 0.45940935611724854, | |
| "learning_rate": 9.873002502207503e-05, | |
| "loss": 0.603, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.352941176470589, | |
| "grad_norm": 0.43467313051223755, | |
| "learning_rate": 9.863641361223024e-05, | |
| "loss": 0.6566, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 8.470588235294118, | |
| "grad_norm": 0.45064640045166016, | |
| "learning_rate": 9.853952127991372e-05, | |
| "loss": 0.6532, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 8.588235294117647, | |
| "grad_norm": 0.4794512689113617, | |
| "learning_rate": 9.843935456130295e-05, | |
| "loss": 0.6684, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 8.705882352941176, | |
| "grad_norm": 0.4778634309768677, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 0.6499, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 8.823529411764707, | |
| "grad_norm": 0.46291792392730713, | |
| "learning_rate": 9.822922521387276e-05, | |
| "loss": 0.6073, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.941176470588236, | |
| "grad_norm": 0.5143027901649475, | |
| "learning_rate": 9.811927675999036e-05, | |
| "loss": 0.5865, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.9081636071205139, | |
| "eval_runtime": 14.323, | |
| "eval_samples_per_second": 2.513, | |
| "eval_steps_per_second": 2.513, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.058823529411764, | |
| "grad_norm": 0.4815616309642792, | |
| "learning_rate": 9.800608226873142e-05, | |
| "loss": 0.6145, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 9.176470588235293, | |
| "grad_norm": 0.5296688675880432, | |
| "learning_rate": 9.788964937598689e-05, | |
| "loss": 0.5744, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 9.294117647058824, | |
| "grad_norm": 0.6967027187347412, | |
| "learning_rate": 9.776998593610428e-05, | |
| "loss": 0.5867, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 0.565801739692688, | |
| "learning_rate": 9.764710002135784e-05, | |
| "loss": 0.5875, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.529411764705882, | |
| "grad_norm": 0.5451968312263489, | |
| "learning_rate": 9.752099992140399e-05, | |
| "loss": 0.5591, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 9.647058823529411, | |
| "grad_norm": 0.6253576874732971, | |
| "learning_rate": 9.739169414272217e-05, | |
| "loss": 0.5909, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 9.764705882352942, | |
| "grad_norm": 0.5514420866966248, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 0.6062, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 9.882352941176471, | |
| "grad_norm": 0.6496943831443787, | |
| "learning_rate": 9.71235006557497e-05, | |
| "loss": 0.5106, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.6828575134277344, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.5719, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.9505001902580261, | |
| "eval_runtime": 14.3178, | |
| "eval_samples_per_second": 2.514, | |
| "eval_steps_per_second": 2.514, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.117647058823529, | |
| "grad_norm": 0.672283947467804, | |
| "learning_rate": 9.684259192656553e-05, | |
| "loss": 0.4832, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 10.235294117647058, | |
| "grad_norm": 1.21843683719635, | |
| "learning_rate": 9.669739289925577e-05, | |
| "loss": 0.5134, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 10.352941176470589, | |
| "grad_norm": 0.709522008895874, | |
| "learning_rate": 9.654904375222385e-05, | |
| "loss": 0.5445, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 10.470588235294118, | |
| "grad_norm": 0.7210734486579895, | |
| "learning_rate": 9.639755449282875e-05, | |
| "loss": 0.4752, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 10.588235294117647, | |
| "grad_norm": 0.8929433226585388, | |
| "learning_rate": 9.62429353402556e-05, | |
| "loss": 0.5363, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 10.705882352941176, | |
| "grad_norm": 0.7936208248138428, | |
| "learning_rate": 9.608519672482636e-05, | |
| "loss": 0.493, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 10.823529411764707, | |
| "grad_norm": 0.8169009685516357, | |
| "learning_rate": 9.592434928729616e-05, | |
| "loss": 0.5175, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 10.941176470588236, | |
| "grad_norm": 0.8355841040611267, | |
| "learning_rate": 9.576040387813552e-05, | |
| "loss": 0.5453, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.0114682912826538, | |
| "eval_runtime": 14.331, | |
| "eval_samples_per_second": 2.512, | |
| "eval_steps_per_second": 2.512, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.058823529411764, | |
| "grad_norm": 0.6956731677055359, | |
| "learning_rate": 9.559337155679842e-05, | |
| "loss": 0.5278, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 11.176470588235293, | |
| "grad_norm": 0.7138647437095642, | |
| "learning_rate": 9.542326359097619e-05, | |
| "loss": 0.4621, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.294117647058824, | |
| "grad_norm": 1.1661685705184937, | |
| "learning_rate": 9.525009145583745e-05, | |
| "loss": 0.5186, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 11.411764705882353, | |
| "grad_norm": 0.8066191673278809, | |
| "learning_rate": 9.507386683325404e-05, | |
| "loss": 0.3402, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 11.529411764705882, | |
| "grad_norm": 0.8090474009513855, | |
| "learning_rate": 9.489460161101291e-05, | |
| "loss": 0.4998, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 11.647058823529411, | |
| "grad_norm": 0.8497116565704346, | |
| "learning_rate": 9.471230788201429e-05, | |
| "loss": 0.4663, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 0.9977283477783203, | |
| "learning_rate": 9.452699794345581e-05, | |
| "loss": 0.461, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.882352941176471, | |
| "grad_norm": 0.8664698004722595, | |
| "learning_rate": 9.43386842960031e-05, | |
| "loss": 0.4452, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.9439713954925537, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.4079, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.1288411617279053, | |
| "eval_runtime": 14.3202, | |
| "eval_samples_per_second": 2.514, | |
| "eval_steps_per_second": 2.514, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.117647058823529, | |
| "grad_norm": 0.8019619584083557, | |
| "learning_rate": 9.395309688934351e-05, | |
| "loss": 0.4145, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 12.235294117647058, | |
| "grad_norm": 1.0398062467575073, | |
| "learning_rate": 9.375584914114963e-05, | |
| "loss": 0.3651, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 12.352941176470589, | |
| "grad_norm": 0.8522201776504517, | |
| "learning_rate": 9.355564970433288e-05, | |
| "loss": 0.3983, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.470588235294118, | |
| "grad_norm": 0.9897236227989197, | |
| "learning_rate": 9.335251208397684e-05, | |
| "loss": 0.3603, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 12.588235294117647, | |
| "grad_norm": 1.1317540407180786, | |
| "learning_rate": 9.314644998336949e-05, | |
| "loss": 0.4367, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 12.705882352941176, | |
| "grad_norm": 0.9567973613739014, | |
| "learning_rate": 9.293747730307889e-05, | |
| "loss": 0.3602, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 12.823529411764707, | |
| "grad_norm": 0.9444957375526428, | |
| "learning_rate": 9.272560814001539e-05, | |
| "loss": 0.3903, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 12.941176470588236, | |
| "grad_norm": 0.9697360396385193, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.4321, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.149044156074524, | |
| "eval_runtime": 14.3168, | |
| "eval_samples_per_second": 2.515, | |
| "eval_steps_per_second": 2.515, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 221, | |
| "total_flos": 5.957299251393331e+16, | |
| "train_loss": 0.7600922224478485, | |
| "train_runtime": 2534.5033, | |
| "train_samples_per_second": 2.683, | |
| "train_steps_per_second": 0.335 | |
| } | |
| ], | |
| "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": 5.957299251393331e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |