| { | |
| "best_metric": 0.8448383808135986, | |
| "best_model_checkpoint": "Geofin2/checkpoint-189", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 189, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.031746031746031744, | |
| "grad_norm": 7.465758323669434, | |
| "learning_rate": 1.3157894736842106e-06, | |
| "loss": 1.3772, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06349206349206349, | |
| "grad_norm": 8.092686653137207, | |
| "learning_rate": 2.631578947368421e-06, | |
| "loss": 1.3957, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 7.4101128578186035, | |
| "learning_rate": 3.9473684210526315e-06, | |
| "loss": 1.4296, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12698412698412698, | |
| "grad_norm": 8.683792114257812, | |
| "learning_rate": 5.263157894736842e-06, | |
| "loss": 1.3899, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15873015873015872, | |
| "grad_norm": 6.577025890350342, | |
| "learning_rate": 5.921052631578948e-06, | |
| "loss": 1.2476, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 5.01353120803833, | |
| "learning_rate": 7.236842105263158e-06, | |
| "loss": 1.251, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 5.670907020568848, | |
| "learning_rate": 8.552631578947368e-06, | |
| "loss": 1.1302, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.25396825396825395, | |
| "grad_norm": 5.124192237854004, | |
| "learning_rate": 9.868421052631579e-06, | |
| "loss": 1.0868, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 5.516786575317383, | |
| "learning_rate": 1.118421052631579e-05, | |
| "loss": 1.1253, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.31746031746031744, | |
| "grad_norm": 3.85540509223938, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.2439, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3492063492063492, | |
| "grad_norm": 3.8742074966430664, | |
| "learning_rate": 1.3815789473684213e-05, | |
| "loss": 1.1262, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 2.986392021179199, | |
| "learning_rate": 1.5131578947368422e-05, | |
| "loss": 1.0517, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4126984126984127, | |
| "grad_norm": 5.179540634155273, | |
| "learning_rate": 1.6447368421052635e-05, | |
| "loss": 1.2095, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 6.125196933746338, | |
| "learning_rate": 1.7763157894736842e-05, | |
| "loss": 0.9101, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 2.7059922218322754, | |
| "learning_rate": 1.9078947368421056e-05, | |
| "loss": 1.007, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5079365079365079, | |
| "grad_norm": 4.918309688568115, | |
| "learning_rate": 2.0394736842105264e-05, | |
| "loss": 0.9643, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5396825396825397, | |
| "grad_norm": 4.556388854980469, | |
| "learning_rate": 2.1710526315789474e-05, | |
| "loss": 1.1077, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 4.733363151550293, | |
| "learning_rate": 2.3026315789473685e-05, | |
| "loss": 0.7966, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6031746031746031, | |
| "grad_norm": 3.822625160217285, | |
| "learning_rate": 2.4342105263157896e-05, | |
| "loss": 1.0073, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6349206349206349, | |
| "grad_norm": 5.641210556030273, | |
| "learning_rate": 2.565789473684211e-05, | |
| "loss": 1.1397, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 9.277029037475586, | |
| "learning_rate": 2.6973684210526317e-05, | |
| "loss": 1.0713, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6984126984126984, | |
| "grad_norm": 4.467797756195068, | |
| "learning_rate": 2.8289473684210528e-05, | |
| "loss": 1.0723, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7301587301587301, | |
| "grad_norm": 4.384549617767334, | |
| "learning_rate": 2.9605263157894735e-05, | |
| "loss": 0.8307, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 8.216472625732422, | |
| "learning_rate": 3.092105263157895e-05, | |
| "loss": 0.8728, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7936507936507936, | |
| "grad_norm": 9.079232215881348, | |
| "learning_rate": 3.223684210526316e-05, | |
| "loss": 1.0659, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8253968253968254, | |
| "grad_norm": 3.665755271911621, | |
| "learning_rate": 3.355263157894737e-05, | |
| "loss": 0.8979, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 5.41543436050415, | |
| "learning_rate": 3.4868421052631575e-05, | |
| "loss": 1.0802, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 7.024143695831299, | |
| "learning_rate": 3.618421052631579e-05, | |
| "loss": 1.0002, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.9206349206349206, | |
| "grad_norm": 3.5612032413482666, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.9603, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 3.873774528503418, | |
| "learning_rate": 3.8815789473684214e-05, | |
| "loss": 0.9288, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9841269841269841, | |
| "grad_norm": 4.467899322509766, | |
| "learning_rate": 4.0131578947368425e-05, | |
| "loss": 0.8583, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.600418410041841, | |
| "eval_f1_macro": 0.3606594342605176, | |
| "eval_f1_micro": 0.600418410041841, | |
| "eval_f1_weighted": 0.5394691319097269, | |
| "eval_loss": 0.9678400754928589, | |
| "eval_precision_macro": 0.5016447368421053, | |
| "eval_precision_micro": 0.600418410041841, | |
| "eval_precision_weighted": 0.5647709755560449, | |
| "eval_recall_macro": 0.36994897475386573, | |
| "eval_recall_micro": 0.600418410041841, | |
| "eval_recall_weighted": 0.600418410041841, | |
| "eval_runtime": 0.6589, | |
| "eval_samples_per_second": 725.401, | |
| "eval_steps_per_second": 12.141, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.0158730158730158, | |
| "grad_norm": 6.57659912109375, | |
| "learning_rate": 4.1447368421052636e-05, | |
| "loss": 1.2212, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.0476190476190477, | |
| "grad_norm": 4.848594665527344, | |
| "learning_rate": 4.2763157894736847e-05, | |
| "loss": 0.8313, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.0793650793650793, | |
| "grad_norm": 11.077583312988281, | |
| "learning_rate": 4.407894736842105e-05, | |
| "loss": 0.8718, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 7.393773555755615, | |
| "learning_rate": 4.539473684210527e-05, | |
| "loss": 0.8306, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 7.678964614868164, | |
| "learning_rate": 4.671052631578948e-05, | |
| "loss": 0.7947, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.1746031746031746, | |
| "grad_norm": 5.603248596191406, | |
| "learning_rate": 4.802631578947368e-05, | |
| "loss": 0.8215, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.2063492063492063, | |
| "grad_norm": 9.599581718444824, | |
| "learning_rate": 4.9342105263157894e-05, | |
| "loss": 0.7965, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.2380952380952381, | |
| "grad_norm": 8.484407424926758, | |
| "learning_rate": 4.99264705882353e-05, | |
| "loss": 0.927, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.2698412698412698, | |
| "grad_norm": 5.3073039054870605, | |
| "learning_rate": 4.977941176470589e-05, | |
| "loss": 0.8808, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3015873015873016, | |
| "grad_norm": 9.473642349243164, | |
| "learning_rate": 4.9632352941176476e-05, | |
| "loss": 0.7203, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 11.76883316040039, | |
| "learning_rate": 4.9485294117647065e-05, | |
| "loss": 0.8228, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.3650793650793651, | |
| "grad_norm": 5.096563816070557, | |
| "learning_rate": 4.933823529411765e-05, | |
| "loss": 0.6165, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.3968253968253967, | |
| "grad_norm": 11.677984237670898, | |
| "learning_rate": 4.9191176470588234e-05, | |
| "loss": 0.7567, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 5.166780948638916, | |
| "learning_rate": 4.904411764705882e-05, | |
| "loss": 0.6387, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.4603174603174602, | |
| "grad_norm": 12.531747817993164, | |
| "learning_rate": 4.889705882352941e-05, | |
| "loss": 0.7438, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.492063492063492, | |
| "grad_norm": 7.940852165222168, | |
| "learning_rate": 4.875e-05, | |
| "loss": 0.6612, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 7.54194450378418, | |
| "learning_rate": 4.860294117647059e-05, | |
| "loss": 0.7491, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.5555555555555556, | |
| "grad_norm": 11.355642318725586, | |
| "learning_rate": 4.8455882352941176e-05, | |
| "loss": 0.6706, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.5873015873015874, | |
| "grad_norm": 9.662281036376953, | |
| "learning_rate": 4.830882352941177e-05, | |
| "loss": 0.7006, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.619047619047619, | |
| "grad_norm": 23.622243881225586, | |
| "learning_rate": 4.823529411764706e-05, | |
| "loss": 0.9295, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.6507936507936507, | |
| "grad_norm": 17.682966232299805, | |
| "learning_rate": 4.808823529411765e-05, | |
| "loss": 0.7496, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.6825396825396826, | |
| "grad_norm": 12.16619873046875, | |
| "learning_rate": 4.794117647058824e-05, | |
| "loss": 0.7494, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 13.556631088256836, | |
| "learning_rate": 4.7794117647058826e-05, | |
| "loss": 0.7712, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.746031746031746, | |
| "grad_norm": 6.017486572265625, | |
| "learning_rate": 4.7647058823529414e-05, | |
| "loss": 0.7188, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 11.243678092956543, | |
| "learning_rate": 4.75e-05, | |
| "loss": 0.6643, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.8095238095238095, | |
| "grad_norm": 10.802536010742188, | |
| "learning_rate": 4.735294117647059e-05, | |
| "loss": 0.8871, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.8412698412698414, | |
| "grad_norm": 7.732793807983398, | |
| "learning_rate": 4.720588235294118e-05, | |
| "loss": 0.6364, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.873015873015873, | |
| "grad_norm": 6.510237693786621, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 0.7261, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 12.734888076782227, | |
| "learning_rate": 4.6911764705882356e-05, | |
| "loss": 0.6648, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.9365079365079365, | |
| "grad_norm": 7.841517448425293, | |
| "learning_rate": 4.6764705882352944e-05, | |
| "loss": 0.7823, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.9682539682539684, | |
| "grad_norm": 5.880507946014404, | |
| "learning_rate": 4.661764705882353e-05, | |
| "loss": 0.5976, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 25.059062957763672, | |
| "learning_rate": 4.647058823529412e-05, | |
| "loss": 0.7921, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6548117154811716, | |
| "eval_f1_macro": 0.5746828539107951, | |
| "eval_f1_micro": 0.6548117154811716, | |
| "eval_f1_weighted": 0.6512875563807756, | |
| "eval_loss": 0.8622708320617676, | |
| "eval_precision_macro": 0.6126744388528891, | |
| "eval_precision_micro": 0.6548117154811716, | |
| "eval_precision_weighted": 0.6571633638241423, | |
| "eval_recall_macro": 0.5589115976575145, | |
| "eval_recall_micro": 0.6548117154811716, | |
| "eval_recall_weighted": 0.6548117154811716, | |
| "eval_runtime": 0.659, | |
| "eval_samples_per_second": 725.381, | |
| "eval_steps_per_second": 12.14, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.0317460317460316, | |
| "grad_norm": 10.687665939331055, | |
| "learning_rate": 4.632352941176471e-05, | |
| "loss": 0.5602, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.0634920634920633, | |
| "grad_norm": 10.464973449707031, | |
| "learning_rate": 4.61764705882353e-05, | |
| "loss": 0.7192, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.0952380952380953, | |
| "grad_norm": 12.922086715698242, | |
| "learning_rate": 4.6029411764705885e-05, | |
| "loss": 0.5306, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.126984126984127, | |
| "grad_norm": 6.641724109649658, | |
| "learning_rate": 4.588235294117647e-05, | |
| "loss": 0.5492, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.1587301587301586, | |
| "grad_norm": 12.109314918518066, | |
| "learning_rate": 4.573529411764706e-05, | |
| "loss": 0.4188, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.1904761904761907, | |
| "grad_norm": 9.922542572021484, | |
| "learning_rate": 4.558823529411765e-05, | |
| "loss": 0.8148, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 13.446711540222168, | |
| "learning_rate": 4.544117647058824e-05, | |
| "loss": 0.427, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.253968253968254, | |
| "grad_norm": 8.166778564453125, | |
| "learning_rate": 4.5294117647058826e-05, | |
| "loss": 0.5399, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 9.932488441467285, | |
| "learning_rate": 4.5147058823529415e-05, | |
| "loss": 0.4946, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.317460317460317, | |
| "grad_norm": 10.837618827819824, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.4638, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.3492063492063493, | |
| "grad_norm": 13.24123764038086, | |
| "learning_rate": 4.485294117647059e-05, | |
| "loss": 0.6378, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 9.553241729736328, | |
| "learning_rate": 4.470588235294118e-05, | |
| "loss": 0.4446, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.4126984126984126, | |
| "grad_norm": 8.025355339050293, | |
| "learning_rate": 4.455882352941177e-05, | |
| "loss": 0.4382, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 2.4444444444444446, | |
| "grad_norm": 21.713151931762695, | |
| "learning_rate": 4.4411764705882356e-05, | |
| "loss": 0.483, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 2.4761904761904763, | |
| "grad_norm": 8.21530818939209, | |
| "learning_rate": 4.4264705882352944e-05, | |
| "loss": 0.6038, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.507936507936508, | |
| "grad_norm": 13.48081111907959, | |
| "learning_rate": 4.411764705882353e-05, | |
| "loss": 0.5339, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 2.5396825396825395, | |
| "grad_norm": 10.05782699584961, | |
| "learning_rate": 4.397058823529412e-05, | |
| "loss": 0.3154, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 7.361288070678711, | |
| "learning_rate": 4.382352941176471e-05, | |
| "loss": 0.4124, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.6031746031746033, | |
| "grad_norm": 9.82521915435791, | |
| "learning_rate": 4.36764705882353e-05, | |
| "loss": 0.4079, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 2.634920634920635, | |
| "grad_norm": 7.5020599365234375, | |
| "learning_rate": 4.3529411764705885e-05, | |
| "loss": 0.355, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 18.065765380859375, | |
| "learning_rate": 4.3382352941176474e-05, | |
| "loss": 0.3729, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.6984126984126986, | |
| "grad_norm": 10.793977737426758, | |
| "learning_rate": 4.323529411764706e-05, | |
| "loss": 0.5139, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.7301587301587302, | |
| "grad_norm": 15.099814414978027, | |
| "learning_rate": 4.308823529411765e-05, | |
| "loss": 0.6046, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "grad_norm": 12.796354293823242, | |
| "learning_rate": 4.294117647058823e-05, | |
| "loss": 0.5686, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.7936507936507935, | |
| "grad_norm": 13.530609130859375, | |
| "learning_rate": 4.2794117647058827e-05, | |
| "loss": 0.6008, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 2.825396825396825, | |
| "grad_norm": 15.42242431640625, | |
| "learning_rate": 4.2647058823529415e-05, | |
| "loss": 0.5564, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 11.694255828857422, | |
| "learning_rate": 4.25e-05, | |
| "loss": 0.3813, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.888888888888889, | |
| "grad_norm": 11.016369819641113, | |
| "learning_rate": 4.235294117647059e-05, | |
| "loss": 0.5223, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 2.9206349206349205, | |
| "grad_norm": 11.818913459777832, | |
| "learning_rate": 4.220588235294118e-05, | |
| "loss": 0.5471, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 2.9523809523809526, | |
| "grad_norm": 12.641321182250977, | |
| "learning_rate": 4.205882352941177e-05, | |
| "loss": 0.3342, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 2.984126984126984, | |
| "grad_norm": 10.896586418151855, | |
| "learning_rate": 4.1911764705882356e-05, | |
| "loss": 0.4335, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6903765690376569, | |
| "eval_f1_macro": 0.6157720421369062, | |
| "eval_f1_micro": 0.6903765690376569, | |
| "eval_f1_weighted": 0.6859027993316449, | |
| "eval_loss": 0.8448383808135986, | |
| "eval_precision_macro": 0.6455502935971685, | |
| "eval_precision_micro": 0.6903765690376569, | |
| "eval_precision_weighted": 0.686461837753025, | |
| "eval_recall_macro": 0.5960579394741132, | |
| "eval_recall_micro": 0.6903765690376569, | |
| "eval_recall_weighted": 0.6903765690376569, | |
| "eval_runtime": 0.6555, | |
| "eval_samples_per_second": 729.214, | |
| "eval_steps_per_second": 12.204, | |
| "step": 189 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 756, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 397217661990912.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |