| { | |
| "best_metric": 0.9348610639572144, | |
| "best_model_checkpoint": "data/Gemma-2-2B_task-3_180-samples_config-1_full_auto/checkpoint-102", | |
| "epoch": 13.0, | |
| "eval_steps": 500, | |
| "global_step": 221, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 0.44407349824905396, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 1.3731, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.44889241456985474, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 1.4033, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.5245712995529175, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 1.4017, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 0.5061965584754944, | |
| "learning_rate": 7.058823529411765e-06, | |
| "loss": 1.4219, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.45101216435432434, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 1.3868, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.3960080146789551, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 1.3448, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.4101226031780243, | |
| "learning_rate": 1.411764705882353e-05, | |
| "loss": 1.3375, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 0.45800548791885376, | |
| "learning_rate": 1.647058823529412e-05, | |
| "loss": 1.3901, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.38581979274749756, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 1.3445, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.327479362487793, | |
| "eval_runtime": 11.3476, | |
| "eval_samples_per_second": 3.172, | |
| "eval_steps_per_second": 3.172, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 0.36708876490592957, | |
| "learning_rate": 2.1176470588235296e-05, | |
| "loss": 1.3581, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.32376426458358765, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 1.3403, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 0.2978406846523285, | |
| "learning_rate": 2.5882352941176475e-05, | |
| "loss": 1.2701, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.28498387336730957, | |
| "learning_rate": 2.823529411764706e-05, | |
| "loss": 1.2397, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5294117647058822, | |
| "grad_norm": 0.24285344779491425, | |
| "learning_rate": 3.058823529411765e-05, | |
| "loss": 1.2122, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.2547561526298523, | |
| "learning_rate": 3.294117647058824e-05, | |
| "loss": 1.2196, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.2959032356739044, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 1.2051, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.2710707187652588, | |
| "learning_rate": 3.7647058823529415e-05, | |
| "loss": 1.1659, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.27771642804145813, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1845, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.1511038541793823, | |
| "eval_runtime": 11.3569, | |
| "eval_samples_per_second": 3.17, | |
| "eval_steps_per_second": 3.17, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.2791696786880493, | |
| "learning_rate": 4.235294117647059e-05, | |
| "loss": 1.121, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.26073259115219116, | |
| "learning_rate": 4.470588235294118e-05, | |
| "loss": 1.092, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.2581411302089691, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 1.0702, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.289313942193985, | |
| "learning_rate": 4.9411764705882355e-05, | |
| "loss": 1.084, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 0.41395315527915955, | |
| "learning_rate": 5.176470588235295e-05, | |
| "loss": 1.0148, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.3129213750362396, | |
| "learning_rate": 5.411764705882353e-05, | |
| "loss": 1.0395, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 0.24733658134937286, | |
| "learning_rate": 5.647058823529412e-05, | |
| "loss": 1.0164, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.24539409577846527, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 0.9848, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.0058537721633911, | |
| "eval_runtime": 11.3536, | |
| "eval_samples_per_second": 3.171, | |
| "eval_steps_per_second": 3.171, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0588235294117645, | |
| "grad_norm": 0.21120277047157288, | |
| "learning_rate": 6.11764705882353e-05, | |
| "loss": 0.9594, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.176470588235294, | |
| "grad_norm": 0.20411401987075806, | |
| "learning_rate": 6.352941176470588e-05, | |
| "loss": 0.9148, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.2941176470588234, | |
| "grad_norm": 0.19725768268108368, | |
| "learning_rate": 6.588235294117648e-05, | |
| "loss": 0.9785, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.411764705882353, | |
| "grad_norm": 0.22567933797836304, | |
| "learning_rate": 6.823529411764707e-05, | |
| "loss": 0.9532, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 0.21849629282951355, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.8852, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.6470588235294117, | |
| "grad_norm": 0.1872478574514389, | |
| "learning_rate": 7.294117647058823e-05, | |
| "loss": 0.9803, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.764705882352941, | |
| "grad_norm": 0.27072635293006897, | |
| "learning_rate": 7.529411764705883e-05, | |
| "loss": 0.9233, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.8823529411764706, | |
| "grad_norm": 0.21282005310058594, | |
| "learning_rate": 7.764705882352942e-05, | |
| "loss": 0.8947, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.21633774042129517, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8922, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.9610133767127991, | |
| "eval_runtime": 11.3681, | |
| "eval_samples_per_second": 3.167, | |
| "eval_steps_per_second": 3.167, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.117647058823529, | |
| "grad_norm": 0.18769878149032593, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 0.9583, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.235294117647059, | |
| "grad_norm": 0.21951356530189514, | |
| "learning_rate": 8.470588235294118e-05, | |
| "loss": 0.8397, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.352941176470588, | |
| "grad_norm": 0.18273769319057465, | |
| "learning_rate": 8.705882352941177e-05, | |
| "loss": 0.9128, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.470588235294118, | |
| "grad_norm": 0.21580995619297028, | |
| "learning_rate": 8.941176470588236e-05, | |
| "loss": 0.853, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.588235294117647, | |
| "grad_norm": 0.22421741485595703, | |
| "learning_rate": 9.176470588235295e-05, | |
| "loss": 0.8769, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.20292414724826813, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 0.9041, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.823529411764706, | |
| "grad_norm": 0.24162541329860687, | |
| "learning_rate": 9.647058823529412e-05, | |
| "loss": 0.8635, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.9411764705882355, | |
| "grad_norm": 0.22393815219402313, | |
| "learning_rate": 9.882352941176471e-05, | |
| "loss": 0.8603, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.9426808953285217, | |
| "eval_runtime": 11.3544, | |
| "eval_samples_per_second": 3.171, | |
| "eval_steps_per_second": 3.171, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.0588235294117645, | |
| "grad_norm": 0.25070905685424805, | |
| "learning_rate": 9.99995783847866e-05, | |
| "loss": 0.8169, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.176470588235294, | |
| "grad_norm": 0.2468973696231842, | |
| "learning_rate": 9.999620550574153e-05, | |
| "loss": 0.827, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.294117647058823, | |
| "grad_norm": 0.24047043919563293, | |
| "learning_rate": 9.998945997517956e-05, | |
| "loss": 0.8556, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.411764705882353, | |
| "grad_norm": 0.24731236696243286, | |
| "learning_rate": 9.997934224814173e-05, | |
| "loss": 0.8719, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.529411764705882, | |
| "grad_norm": 0.2597956955432892, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 0.8315, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 5.647058823529412, | |
| "grad_norm": 0.25839799642562866, | |
| "learning_rate": 9.994899316216708e-05, | |
| "loss": 0.8391, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 5.764705882352941, | |
| "grad_norm": 0.2606346607208252, | |
| "learning_rate": 9.992876385052345e-05, | |
| "loss": 0.8489, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 0.303012877702713, | |
| "learning_rate": 9.990516643685222e-05, | |
| "loss": 0.8779, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.26129570603370667, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.8088, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.9348610639572144, | |
| "eval_runtime": 11.355, | |
| "eval_samples_per_second": 3.17, | |
| "eval_steps_per_second": 3.17, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.117647058823529, | |
| "grad_norm": 0.2719724178314209, | |
| "learning_rate": 9.984787389787688e-05, | |
| "loss": 0.7766, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 6.235294117647059, | |
| "grad_norm": 0.2840684652328491, | |
| "learning_rate": 9.981418263742148e-05, | |
| "loss": 0.7936, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 6.352941176470588, | |
| "grad_norm": 0.29696789383888245, | |
| "learning_rate": 9.977713100437509e-05, | |
| "loss": 0.7484, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 6.470588235294118, | |
| "grad_norm": 0.3484632968902588, | |
| "learning_rate": 9.973672149817232e-05, | |
| "loss": 0.8151, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.588235294117647, | |
| "grad_norm": 2.68868350982666, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 0.7689, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 6.705882352941177, | |
| "grad_norm": 0.3818742334842682, | |
| "learning_rate": 9.964583999643174e-05, | |
| "loss": 0.8552, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.823529411764706, | |
| "grad_norm": 0.34056252241134644, | |
| "learning_rate": 9.95953741315919e-05, | |
| "loss": 0.83, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 6.9411764705882355, | |
| "grad_norm": 0.3711160719394684, | |
| "learning_rate": 9.954156265457801e-05, | |
| "loss": 0.7811, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.942317545413971, | |
| "eval_runtime": 11.3501, | |
| "eval_samples_per_second": 3.172, | |
| "eval_steps_per_second": 3.172, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 0.3215789794921875, | |
| "learning_rate": 9.948440919541278e-05, | |
| "loss": 0.8026, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.176470588235294, | |
| "grad_norm": 0.3400995135307312, | |
| "learning_rate": 9.942391760956277e-05, | |
| "loss": 0.7546, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 7.294117647058823, | |
| "grad_norm": 0.42271682620048523, | |
| "learning_rate": 9.936009197767845e-05, | |
| "loss": 0.7369, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 7.411764705882353, | |
| "grad_norm": 0.4162324368953705, | |
| "learning_rate": 9.929293660531888e-05, | |
| "loss": 0.7056, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 7.529411764705882, | |
| "grad_norm": 0.43582209944725037, | |
| "learning_rate": 9.922245602266118e-05, | |
| "loss": 0.7311, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 7.647058823529412, | |
| "grad_norm": 0.4621220827102661, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 0.7486, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.764705882352941, | |
| "grad_norm": 0.47560861706733704, | |
| "learning_rate": 9.90715384684021e-05, | |
| "loss": 0.6942, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 7.882352941176471, | |
| "grad_norm": 0.4656902253627777, | |
| "learning_rate": 9.899111167741966e-05, | |
| "loss": 0.7962, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.48444864153862, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.7022, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.9658232927322388, | |
| "eval_runtime": 11.3484, | |
| "eval_samples_per_second": 3.172, | |
| "eval_steps_per_second": 3.172, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.117647058823529, | |
| "grad_norm": 0.5267347693443298, | |
| "learning_rate": 9.882034919459555e-05, | |
| "loss": 0.6809, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 8.235294117647058, | |
| "grad_norm": 0.6218305826187134, | |
| "learning_rate": 9.873002502207503e-05, | |
| "loss": 0.6429, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.352941176470589, | |
| "grad_norm": 0.5625961422920227, | |
| "learning_rate": 9.863641361223024e-05, | |
| "loss": 0.6973, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 8.470588235294118, | |
| "grad_norm": 0.5714606642723083, | |
| "learning_rate": 9.853952127991372e-05, | |
| "loss": 0.6936, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 8.588235294117647, | |
| "grad_norm": 0.6646034121513367, | |
| "learning_rate": 9.843935456130295e-05, | |
| "loss": 0.713, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 8.705882352941176, | |
| "grad_norm": 0.611829936504364, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 0.6911, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 8.823529411764707, | |
| "grad_norm": 0.5963591933250427, | |
| "learning_rate": 9.822922521387276e-05, | |
| "loss": 0.6471, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.941176470588236, | |
| "grad_norm": 0.6600967645645142, | |
| "learning_rate": 9.811927675999036e-05, | |
| "loss": 0.6335, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.00136399269104, | |
| "eval_runtime": 11.3524, | |
| "eval_samples_per_second": 3.171, | |
| "eval_steps_per_second": 3.171, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.058823529411764, | |
| "grad_norm": 0.6069875955581665, | |
| "learning_rate": 9.800608226873142e-05, | |
| "loss": 0.6572, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 9.176470588235293, | |
| "grad_norm": 0.6122432351112366, | |
| "learning_rate": 9.788964937598689e-05, | |
| "loss": 0.6026, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 9.294117647058824, | |
| "grad_norm": 1.0427063703536987, | |
| "learning_rate": 9.776998593610428e-05, | |
| "loss": 0.628, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 0.7985001802444458, | |
| "learning_rate": 9.764710002135784e-05, | |
| "loss": 0.6199, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.529411764705882, | |
| "grad_norm": 0.6789429783821106, | |
| "learning_rate": 9.752099992140399e-05, | |
| "loss": 0.5939, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 9.647058823529411, | |
| "grad_norm": 0.7528170943260193, | |
| "learning_rate": 9.739169414272217e-05, | |
| "loss": 0.625, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 9.764705882352942, | |
| "grad_norm": 0.7215481400489807, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 0.6412, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 9.882352941176471, | |
| "grad_norm": 0.812872588634491, | |
| "learning_rate": 9.71235006557497e-05, | |
| "loss": 0.5429, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.9312589764595032, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.6005, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.0960454940795898, | |
| "eval_runtime": 11.3495, | |
| "eval_samples_per_second": 3.172, | |
| "eval_steps_per_second": 3.172, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.117647058823529, | |
| "grad_norm": 0.7775615453720093, | |
| "learning_rate": 9.684259192656553e-05, | |
| "loss": 0.5053, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 10.235294117647058, | |
| "grad_norm": 1.2666046619415283, | |
| "learning_rate": 9.669739289925577e-05, | |
| "loss": 0.5393, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 10.352941176470589, | |
| "grad_norm": 0.8414201736450195, | |
| "learning_rate": 9.654904375222385e-05, | |
| "loss": 0.5641, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 10.470588235294118, | |
| "grad_norm": 0.9468352198600769, | |
| "learning_rate": 9.639755449282875e-05, | |
| "loss": 0.4872, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 10.588235294117647, | |
| "grad_norm": 1.0405274629592896, | |
| "learning_rate": 9.62429353402556e-05, | |
| "loss": 0.5585, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 10.705882352941176, | |
| "grad_norm": 0.881247878074646, | |
| "learning_rate": 9.608519672482636e-05, | |
| "loss": 0.5156, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 10.823529411764707, | |
| "grad_norm": 0.8318790197372437, | |
| "learning_rate": 9.592434928729616e-05, | |
| "loss": 0.536, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 10.941176470588236, | |
| "grad_norm": 0.9478181600570679, | |
| "learning_rate": 9.576040387813552e-05, | |
| "loss": 0.5752, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.1256170272827148, | |
| "eval_runtime": 11.3486, | |
| "eval_samples_per_second": 3.172, | |
| "eval_steps_per_second": 3.172, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.058823529411764, | |
| "grad_norm": 0.7912821173667908, | |
| "learning_rate": 9.559337155679842e-05, | |
| "loss": 0.5468, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 11.176470588235293, | |
| "grad_norm": 0.8649311661720276, | |
| "learning_rate": 9.542326359097619e-05, | |
| "loss": 0.4652, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.294117647058824, | |
| "grad_norm": 1.516218662261963, | |
| "learning_rate": 9.525009145583745e-05, | |
| "loss": 0.5282, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 11.411764705882353, | |
| "grad_norm": 0.8936471343040466, | |
| "learning_rate": 9.507386683325404e-05, | |
| "loss": 0.344, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 11.529411764705882, | |
| "grad_norm": 0.9856701493263245, | |
| "learning_rate": 9.489460161101291e-05, | |
| "loss": 0.511, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 11.647058823529411, | |
| "grad_norm": 1.2524642944335938, | |
| "learning_rate": 9.471230788201429e-05, | |
| "loss": 0.4732, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 0.9999769330024719, | |
| "learning_rate": 9.452699794345581e-05, | |
| "loss": 0.4705, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.882352941176471, | |
| "grad_norm": 1.1060373783111572, | |
| "learning_rate": 9.43386842960031e-05, | |
| "loss": 0.4568, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 1.0465986728668213, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.4181, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.2757269144058228, | |
| "eval_runtime": 11.3525, | |
| "eval_samples_per_second": 3.171, | |
| "eval_steps_per_second": 3.171, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.117647058823529, | |
| "grad_norm": 0.9606939554214478, | |
| "learning_rate": 9.395309688934351e-05, | |
| "loss": 0.4175, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 12.235294117647058, | |
| "grad_norm": 1.1511764526367188, | |
| "learning_rate": 9.375584914114963e-05, | |
| "loss": 0.3664, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 12.352941176470589, | |
| "grad_norm": 1.3019860982894897, | |
| "learning_rate": 9.355564970433288e-05, | |
| "loss": 0.4045, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.470588235294118, | |
| "grad_norm": 1.1645996570587158, | |
| "learning_rate": 9.335251208397684e-05, | |
| "loss": 0.3536, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 12.588235294117647, | |
| "grad_norm": 1.29787015914917, | |
| "learning_rate": 9.314644998336949e-05, | |
| "loss": 0.442, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 12.705882352941176, | |
| "grad_norm": 1.1158279180526733, | |
| "learning_rate": 9.293747730307889e-05, | |
| "loss": 0.3554, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 12.823529411764707, | |
| "grad_norm": 1.1821708679199219, | |
| "learning_rate": 9.272560814001539e-05, | |
| "loss": 0.3921, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 12.941176470588236, | |
| "grad_norm": 1.1477068662643433, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.437, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.291459560394287, | |
| "eval_runtime": 11.3721, | |
| "eval_samples_per_second": 3.166, | |
| "eval_steps_per_second": 3.166, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 221, | |
| "total_flos": 4.79429356683264e+16, | |
| "train_loss": 0.810044450592671, | |
| "train_runtime": 2019.2323, | |
| "train_samples_per_second": 3.368, | |
| "train_steps_per_second": 0.421 | |
| } | |
| ], | |
| "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": 4.79429356683264e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |