{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 0, "global_step": 340, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0029411764705882353, "grad_norm": 1.4588830471038818, "learning_rate": 1e-05, "loss": 2.2815, "step": 1 }, { "epoch": 0.0058823529411764705, "grad_norm": 1.471093773841858, "learning_rate": 9.970588235294119e-06, "loss": 2.2693, "step": 2 }, { "epoch": 0.008823529411764706, "grad_norm": 1.3569601774215698, "learning_rate": 9.941176470588236e-06, "loss": 2.2162, "step": 3 }, { "epoch": 0.011764705882352941, "grad_norm": 1.218796730041504, "learning_rate": 9.911764705882354e-06, "loss": 2.1471, "step": 4 }, { "epoch": 0.014705882352941176, "grad_norm": 1.0461595058441162, "learning_rate": 9.882352941176472e-06, "loss": 2.1782, "step": 5 }, { "epoch": 0.01764705882352941, "grad_norm": 0.7329587340354919, "learning_rate": 9.852941176470589e-06, "loss": 2.1145, "step": 6 }, { "epoch": 0.020588235294117647, "grad_norm": 0.598797619342804, "learning_rate": 9.823529411764706e-06, "loss": 2.0937, "step": 7 }, { "epoch": 0.023529411764705882, "grad_norm": 0.5003849267959595, "learning_rate": 9.794117647058824e-06, "loss": 2.0904, "step": 8 }, { "epoch": 0.026470588235294117, "grad_norm": 0.46593984961509705, "learning_rate": 9.764705882352942e-06, "loss": 2.0499, "step": 9 }, { "epoch": 0.029411764705882353, "grad_norm": 0.4855063557624817, "learning_rate": 9.735294117647059e-06, "loss": 2.036, "step": 10 }, { "epoch": 0.03235294117647059, "grad_norm": 0.47671785950660706, "learning_rate": 9.705882352941177e-06, "loss": 2.0764, "step": 11 }, { "epoch": 0.03529411764705882, "grad_norm": 0.43939489126205444, "learning_rate": 9.676470588235296e-06, "loss": 1.9735, "step": 12 }, { "epoch": 0.03823529411764706, "grad_norm": 0.46610742807388306, "learning_rate": 9.647058823529412e-06, "loss": 1.9306, "step": 13 }, { "epoch": 0.041176470588235294, "grad_norm": 0.4459688067436218, "learning_rate": 9.61764705882353e-06, "loss": 1.9308, "step": 14 }, { "epoch": 0.04411764705882353, "grad_norm": 0.4437696039676666, "learning_rate": 9.588235294117649e-06, "loss": 1.9268, "step": 15 }, { "epoch": 0.047058823529411764, "grad_norm": 0.43988853693008423, "learning_rate": 9.558823529411766e-06, "loss": 1.9884, "step": 16 }, { "epoch": 0.05, "grad_norm": 0.4177871346473694, "learning_rate": 9.529411764705882e-06, "loss": 1.8756, "step": 17 }, { "epoch": 0.052941176470588235, "grad_norm": 0.4325030744075775, "learning_rate": 9.5e-06, "loss": 1.9104, "step": 18 }, { "epoch": 0.05588235294117647, "grad_norm": 0.4101027250289917, "learning_rate": 9.470588235294119e-06, "loss": 1.7968, "step": 19 }, { "epoch": 0.058823529411764705, "grad_norm": 0.4248889982700348, "learning_rate": 9.441176470588235e-06, "loss": 1.8519, "step": 20 }, { "epoch": 0.061764705882352944, "grad_norm": 0.41984012722969055, "learning_rate": 9.411764705882354e-06, "loss": 1.8169, "step": 21 }, { "epoch": 0.06470588235294118, "grad_norm": 0.44382062554359436, "learning_rate": 9.382352941176472e-06, "loss": 1.7935, "step": 22 }, { "epoch": 0.06764705882352941, "grad_norm": 0.4285382032394409, "learning_rate": 9.352941176470589e-06, "loss": 1.7796, "step": 23 }, { "epoch": 0.07058823529411765, "grad_norm": 0.41278114914894104, "learning_rate": 9.323529411764707e-06, "loss": 1.7602, "step": 24 }, { "epoch": 0.07352941176470588, "grad_norm": 0.3789098560810089, "learning_rate": 9.294117647058824e-06, "loss": 1.7267, "step": 25 }, { "epoch": 0.07647058823529412, "grad_norm": 0.3891398012638092, "learning_rate": 9.264705882352942e-06, "loss": 1.7524, "step": 26 }, { "epoch": 0.07941176470588235, "grad_norm": 0.3455236852169037, "learning_rate": 9.23529411764706e-06, "loss": 1.6852, "step": 27 }, { "epoch": 0.08235294117647059, "grad_norm": 0.3453163504600525, "learning_rate": 9.205882352941177e-06, "loss": 1.6711, "step": 28 }, { "epoch": 0.08529411764705883, "grad_norm": 0.36744871735572815, "learning_rate": 9.176470588235294e-06, "loss": 1.6939, "step": 29 }, { "epoch": 0.08823529411764706, "grad_norm": 0.32585012912750244, "learning_rate": 9.147058823529412e-06, "loss": 1.6565, "step": 30 }, { "epoch": 0.09117647058823529, "grad_norm": 0.3447589576244354, "learning_rate": 9.11764705882353e-06, "loss": 1.6604, "step": 31 }, { "epoch": 0.09411764705882353, "grad_norm": 0.3437487781047821, "learning_rate": 9.088235294117647e-06, "loss": 1.6219, "step": 32 }, { "epoch": 0.09705882352941177, "grad_norm": 0.3249136507511139, "learning_rate": 9.058823529411765e-06, "loss": 1.5504, "step": 33 }, { "epoch": 0.1, "grad_norm": 0.3307740092277527, "learning_rate": 9.029411764705884e-06, "loss": 1.5859, "step": 34 }, { "epoch": 0.10294117647058823, "grad_norm": 0.3171888589859009, "learning_rate": 9e-06, "loss": 1.5263, "step": 35 }, { "epoch": 0.10588235294117647, "grad_norm": 0.3062046766281128, "learning_rate": 8.970588235294119e-06, "loss": 1.5303, "step": 36 }, { "epoch": 0.10882352941176471, "grad_norm": 0.29522180557250977, "learning_rate": 8.941176470588237e-06, "loss": 1.5458, "step": 37 }, { "epoch": 0.11176470588235295, "grad_norm": 0.30089306831359863, "learning_rate": 8.911764705882354e-06, "loss": 1.5185, "step": 38 }, { "epoch": 0.11470588235294117, "grad_norm": 0.29232335090637207, "learning_rate": 8.88235294117647e-06, "loss": 1.502, "step": 39 }, { "epoch": 0.11764705882352941, "grad_norm": 0.27594244480133057, "learning_rate": 8.852941176470588e-06, "loss": 1.4367, "step": 40 }, { "epoch": 0.12058823529411765, "grad_norm": 0.2704189419746399, "learning_rate": 8.823529411764707e-06, "loss": 1.4339, "step": 41 }, { "epoch": 0.12352941176470589, "grad_norm": 0.26492875814437866, "learning_rate": 8.794117647058823e-06, "loss": 1.459, "step": 42 }, { "epoch": 0.1264705882352941, "grad_norm": 0.28606313467025757, "learning_rate": 8.764705882352942e-06, "loss": 1.4691, "step": 43 }, { "epoch": 0.12941176470588237, "grad_norm": 0.28363236784935, "learning_rate": 8.73529411764706e-06, "loss": 1.4443, "step": 44 }, { "epoch": 0.1323529411764706, "grad_norm": 0.2818906009197235, "learning_rate": 8.705882352941177e-06, "loss": 1.4286, "step": 45 }, { "epoch": 0.13529411764705881, "grad_norm": 0.26159507036209106, "learning_rate": 8.676470588235295e-06, "loss": 1.3945, "step": 46 }, { "epoch": 0.13823529411764707, "grad_norm": 0.26535022258758545, "learning_rate": 8.647058823529413e-06, "loss": 1.4587, "step": 47 }, { "epoch": 0.1411764705882353, "grad_norm": 0.2538270056247711, "learning_rate": 8.61764705882353e-06, "loss": 1.4064, "step": 48 }, { "epoch": 0.14411764705882352, "grad_norm": 0.2544410228729248, "learning_rate": 8.588235294117647e-06, "loss": 1.411, "step": 49 }, { "epoch": 0.14705882352941177, "grad_norm": 0.2816343605518341, "learning_rate": 8.558823529411765e-06, "loss": 1.4139, "step": 50 }, { "epoch": 0.15, "grad_norm": 0.2536643445491791, "learning_rate": 8.529411764705883e-06, "loss": 1.3882, "step": 51 }, { "epoch": 0.15294117647058825, "grad_norm": 0.26011887192726135, "learning_rate": 8.5e-06, "loss": 1.3709, "step": 52 }, { "epoch": 0.15588235294117647, "grad_norm": 0.2549336552619934, "learning_rate": 8.470588235294118e-06, "loss": 1.398, "step": 53 }, { "epoch": 0.1588235294117647, "grad_norm": 0.22624710202217102, "learning_rate": 8.441176470588237e-06, "loss": 1.3423, "step": 54 }, { "epoch": 0.16176470588235295, "grad_norm": 0.25475260615348816, "learning_rate": 8.411764705882353e-06, "loss": 1.356, "step": 55 }, { "epoch": 0.16470588235294117, "grad_norm": 0.25191032886505127, "learning_rate": 8.382352941176472e-06, "loss": 1.3847, "step": 56 }, { "epoch": 0.1676470588235294, "grad_norm": 0.2320636808872223, "learning_rate": 8.35294117647059e-06, "loss": 1.3318, "step": 57 }, { "epoch": 0.17058823529411765, "grad_norm": 0.276131808757782, "learning_rate": 8.323529411764707e-06, "loss": 1.2964, "step": 58 }, { "epoch": 0.17352941176470588, "grad_norm": 0.2447700798511505, "learning_rate": 8.294117647058825e-06, "loss": 1.3262, "step": 59 }, { "epoch": 0.17647058823529413, "grad_norm": 0.26056042313575745, "learning_rate": 8.264705882352941e-06, "loss": 1.3793, "step": 60 }, { "epoch": 0.17941176470588235, "grad_norm": 0.21680042147636414, "learning_rate": 8.23529411764706e-06, "loss": 1.301, "step": 61 }, { "epoch": 0.18235294117647058, "grad_norm": 0.21796001493930817, "learning_rate": 8.205882352941176e-06, "loss": 1.3339, "step": 62 }, { "epoch": 0.18529411764705883, "grad_norm": 0.218816876411438, "learning_rate": 8.176470588235295e-06, "loss": 1.2843, "step": 63 }, { "epoch": 0.18823529411764706, "grad_norm": 0.1997959166765213, "learning_rate": 8.147058823529413e-06, "loss": 1.2712, "step": 64 }, { "epoch": 0.19117647058823528, "grad_norm": 0.20165401697158813, "learning_rate": 8.11764705882353e-06, "loss": 1.2902, "step": 65 }, { "epoch": 0.19411764705882353, "grad_norm": 0.20525865256786346, "learning_rate": 8.088235294117648e-06, "loss": 1.2632, "step": 66 }, { "epoch": 0.19705882352941176, "grad_norm": 0.24750295281410217, "learning_rate": 8.058823529411766e-06, "loss": 1.2622, "step": 67 }, { "epoch": 0.2, "grad_norm": 0.20822177827358246, "learning_rate": 8.029411764705883e-06, "loss": 1.2762, "step": 68 }, { "epoch": 0.20294117647058824, "grad_norm": 0.20200103521347046, "learning_rate": 8.000000000000001e-06, "loss": 1.2593, "step": 69 }, { "epoch": 0.20588235294117646, "grad_norm": 0.20765094459056854, "learning_rate": 7.97058823529412e-06, "loss": 1.2962, "step": 70 }, { "epoch": 0.2088235294117647, "grad_norm": 0.19960962235927582, "learning_rate": 7.941176470588236e-06, "loss": 1.2768, "step": 71 }, { "epoch": 0.21176470588235294, "grad_norm": 0.20074956119060516, "learning_rate": 7.911764705882353e-06, "loss": 1.2417, "step": 72 }, { "epoch": 0.21470588235294116, "grad_norm": 0.1980939656496048, "learning_rate": 7.882352941176471e-06, "loss": 1.2606, "step": 73 }, { "epoch": 0.21764705882352942, "grad_norm": 0.2036397010087967, "learning_rate": 7.85294117647059e-06, "loss": 1.2412, "step": 74 }, { "epoch": 0.22058823529411764, "grad_norm": 0.19486106932163239, "learning_rate": 7.823529411764706e-06, "loss": 1.2154, "step": 75 }, { "epoch": 0.2235294117647059, "grad_norm": 0.19677641987800598, "learning_rate": 7.794117647058825e-06, "loss": 1.2178, "step": 76 }, { "epoch": 0.22647058823529412, "grad_norm": 0.18516194820404053, "learning_rate": 7.764705882352941e-06, "loss": 1.2198, "step": 77 }, { "epoch": 0.22941176470588234, "grad_norm": 0.2153574824333191, "learning_rate": 7.73529411764706e-06, "loss": 1.2526, "step": 78 }, { "epoch": 0.2323529411764706, "grad_norm": 0.19904084503650665, "learning_rate": 7.705882352941178e-06, "loss": 1.2524, "step": 79 }, { "epoch": 0.23529411764705882, "grad_norm": 0.19030578434467316, "learning_rate": 7.676470588235294e-06, "loss": 1.2112, "step": 80 }, { "epoch": 0.23823529411764705, "grad_norm": 0.19393247365951538, "learning_rate": 7.647058823529411e-06, "loss": 1.2088, "step": 81 }, { "epoch": 0.2411764705882353, "grad_norm": 0.1918642818927765, "learning_rate": 7.617647058823529e-06, "loss": 1.1991, "step": 82 }, { "epoch": 0.24411764705882352, "grad_norm": 0.1984645426273346, "learning_rate": 7.588235294117648e-06, "loss": 1.1831, "step": 83 }, { "epoch": 0.24705882352941178, "grad_norm": 0.18611128628253937, "learning_rate": 7.558823529411765e-06, "loss": 1.1878, "step": 84 }, { "epoch": 0.25, "grad_norm": 0.23308077454566956, "learning_rate": 7.529411764705883e-06, "loss": 1.256, "step": 85 }, { "epoch": 0.2529411764705882, "grad_norm": 0.21278584003448486, "learning_rate": 7.500000000000001e-06, "loss": 1.2132, "step": 86 }, { "epoch": 0.25588235294117645, "grad_norm": 0.1996898353099823, "learning_rate": 7.4705882352941185e-06, "loss": 1.2179, "step": 87 }, { "epoch": 0.25882352941176473, "grad_norm": 0.1844678670167923, "learning_rate": 7.441176470588236e-06, "loss": 1.2023, "step": 88 }, { "epoch": 0.26176470588235295, "grad_norm": 0.18834266066551208, "learning_rate": 7.4117647058823535e-06, "loss": 1.1773, "step": 89 }, { "epoch": 0.2647058823529412, "grad_norm": 0.1843290776014328, "learning_rate": 7.382352941176472e-06, "loss": 1.1989, "step": 90 }, { "epoch": 0.2676470588235294, "grad_norm": 0.19822850823402405, "learning_rate": 7.352941176470589e-06, "loss": 1.2012, "step": 91 }, { "epoch": 0.27058823529411763, "grad_norm": 0.224341481924057, "learning_rate": 7.323529411764706e-06, "loss": 1.2019, "step": 92 }, { "epoch": 0.2735294117647059, "grad_norm": 0.1946311742067337, "learning_rate": 7.294117647058823e-06, "loss": 1.1963, "step": 93 }, { "epoch": 0.27647058823529413, "grad_norm": 0.19121474027633667, "learning_rate": 7.264705882352942e-06, "loss": 1.1697, "step": 94 }, { "epoch": 0.27941176470588236, "grad_norm": 0.40967074036598206, "learning_rate": 7.235294117647059e-06, "loss": 1.1968, "step": 95 }, { "epoch": 0.2823529411764706, "grad_norm": 0.19602446258068085, "learning_rate": 7.205882352941177e-06, "loss": 1.1593, "step": 96 }, { "epoch": 0.2852941176470588, "grad_norm": 0.1895453929901123, "learning_rate": 7.176470588235295e-06, "loss": 1.1737, "step": 97 }, { "epoch": 0.28823529411764703, "grad_norm": 0.1971290111541748, "learning_rate": 7.1470588235294125e-06, "loss": 1.1937, "step": 98 }, { "epoch": 0.2911764705882353, "grad_norm": 0.183615580201149, "learning_rate": 7.11764705882353e-06, "loss": 1.1823, "step": 99 }, { "epoch": 0.29411764705882354, "grad_norm": 0.20080818235874176, "learning_rate": 7.088235294117648e-06, "loss": 1.1882, "step": 100 }, { "epoch": 0.29705882352941176, "grad_norm": 0.20981959998607635, "learning_rate": 7.058823529411766e-06, "loss": 1.1916, "step": 101 }, { "epoch": 0.3, "grad_norm": 0.19891297817230225, "learning_rate": 7.029411764705882e-06, "loss": 1.168, "step": 102 }, { "epoch": 0.3029411764705882, "grad_norm": 0.19170914590358734, "learning_rate": 7e-06, "loss": 1.1672, "step": 103 }, { "epoch": 0.3058823529411765, "grad_norm": 0.19901618361473083, "learning_rate": 6.970588235294118e-06, "loss": 1.172, "step": 104 }, { "epoch": 0.3088235294117647, "grad_norm": 0.20435598492622375, "learning_rate": 6.941176470588236e-06, "loss": 1.1596, "step": 105 }, { "epoch": 0.31176470588235294, "grad_norm": 0.19358821213245392, "learning_rate": 6.911764705882353e-06, "loss": 1.1541, "step": 106 }, { "epoch": 0.31470588235294117, "grad_norm": 0.22525909543037415, "learning_rate": 6.8823529411764715e-06, "loss": 1.1385, "step": 107 }, { "epoch": 0.3176470588235294, "grad_norm": 0.22417089343070984, "learning_rate": 6.852941176470589e-06, "loss": 1.204, "step": 108 }, { "epoch": 0.3205882352941177, "grad_norm": 0.20851701498031616, "learning_rate": 6.8235294117647065e-06, "loss": 1.1874, "step": 109 }, { "epoch": 0.3235294117647059, "grad_norm": 0.19366827607154846, "learning_rate": 6.794117647058824e-06, "loss": 1.1461, "step": 110 }, { "epoch": 0.3264705882352941, "grad_norm": 0.1981084942817688, "learning_rate": 6.764705882352942e-06, "loss": 1.1369, "step": 111 }, { "epoch": 0.32941176470588235, "grad_norm": 0.21598248183727264, "learning_rate": 6.73529411764706e-06, "loss": 1.1471, "step": 112 }, { "epoch": 0.3323529411764706, "grad_norm": 0.2313269078731537, "learning_rate": 6.705882352941176e-06, "loss": 1.17, "step": 113 }, { "epoch": 0.3352941176470588, "grad_norm": 0.2236504703760147, "learning_rate": 6.676470588235294e-06, "loss": 1.1372, "step": 114 }, { "epoch": 0.3382352941176471, "grad_norm": 0.20379534363746643, "learning_rate": 6.647058823529412e-06, "loss": 1.1667, "step": 115 }, { "epoch": 0.3411764705882353, "grad_norm": 0.21076861023902893, "learning_rate": 6.61764705882353e-06, "loss": 1.1847, "step": 116 }, { "epoch": 0.34411764705882353, "grad_norm": 0.21549032628536224, "learning_rate": 6.588235294117647e-06, "loss": 1.1241, "step": 117 }, { "epoch": 0.34705882352941175, "grad_norm": 0.20546089112758636, "learning_rate": 6.5588235294117655e-06, "loss": 1.1105, "step": 118 }, { "epoch": 0.35, "grad_norm": 0.22100862860679626, "learning_rate": 6.529411764705883e-06, "loss": 1.1139, "step": 119 }, { "epoch": 0.35294117647058826, "grad_norm": 0.22141504287719727, "learning_rate": 6.5000000000000004e-06, "loss": 1.1616, "step": 120 }, { "epoch": 0.3558823529411765, "grad_norm": 0.20799893140792847, "learning_rate": 6.470588235294119e-06, "loss": 1.0986, "step": 121 }, { "epoch": 0.3588235294117647, "grad_norm": 0.1906932294368744, "learning_rate": 6.441176470588236e-06, "loss": 1.1263, "step": 122 }, { "epoch": 0.36176470588235293, "grad_norm": 0.2036122828722, "learning_rate": 6.411764705882354e-06, "loss": 1.1189, "step": 123 }, { "epoch": 0.36470588235294116, "grad_norm": 0.21240055561065674, "learning_rate": 6.38235294117647e-06, "loss": 1.156, "step": 124 }, { "epoch": 0.36764705882352944, "grad_norm": 0.21339499950408936, "learning_rate": 6.352941176470589e-06, "loss": 1.1046, "step": 125 }, { "epoch": 0.37058823529411766, "grad_norm": 0.20749010145664215, "learning_rate": 6.323529411764706e-06, "loss": 1.1369, "step": 126 }, { "epoch": 0.3735294117647059, "grad_norm": 0.25060978531837463, "learning_rate": 6.294117647058824e-06, "loss": 1.1424, "step": 127 }, { "epoch": 0.3764705882352941, "grad_norm": 0.22475501894950867, "learning_rate": 6.264705882352942e-06, "loss": 1.1346, "step": 128 }, { "epoch": 0.37941176470588234, "grad_norm": 0.26187384128570557, "learning_rate": 6.2352941176470595e-06, "loss": 1.0951, "step": 129 }, { "epoch": 0.38235294117647056, "grad_norm": 0.21285903453826904, "learning_rate": 6.205882352941177e-06, "loss": 1.1309, "step": 130 }, { "epoch": 0.38529411764705884, "grad_norm": 0.2294841706752777, "learning_rate": 6.176470588235295e-06, "loss": 1.133, "step": 131 }, { "epoch": 0.38823529411764707, "grad_norm": 0.21611462533473969, "learning_rate": 6.147058823529413e-06, "loss": 1.1325, "step": 132 }, { "epoch": 0.3911764705882353, "grad_norm": 0.22627894580364227, "learning_rate": 6.11764705882353e-06, "loss": 1.1467, "step": 133 }, { "epoch": 0.3941176470588235, "grad_norm": 0.2144460827112198, "learning_rate": 6.088235294117647e-06, "loss": 1.1093, "step": 134 }, { "epoch": 0.39705882352941174, "grad_norm": 0.20621620118618011, "learning_rate": 6.058823529411765e-06, "loss": 1.1538, "step": 135 }, { "epoch": 0.4, "grad_norm": 0.19962570071220398, "learning_rate": 6.029411764705883e-06, "loss": 1.1032, "step": 136 }, { "epoch": 0.40294117647058825, "grad_norm": 0.2382269650697708, "learning_rate": 6e-06, "loss": 1.1381, "step": 137 }, { "epoch": 0.40588235294117647, "grad_norm": 0.20725472271442413, "learning_rate": 5.970588235294118e-06, "loss": 1.1153, "step": 138 }, { "epoch": 0.4088235294117647, "grad_norm": 0.21083097159862518, "learning_rate": 5.941176470588236e-06, "loss": 1.102, "step": 139 }, { "epoch": 0.4117647058823529, "grad_norm": 0.22206459939479828, "learning_rate": 5.9117647058823534e-06, "loss": 1.1309, "step": 140 }, { "epoch": 0.4147058823529412, "grad_norm": 0.22022652626037598, "learning_rate": 5.882352941176471e-06, "loss": 1.1515, "step": 141 }, { "epoch": 0.4176470588235294, "grad_norm": 0.2197543978691101, "learning_rate": 5.852941176470589e-06, "loss": 1.1402, "step": 142 }, { "epoch": 0.42058823529411765, "grad_norm": 0.22253328561782837, "learning_rate": 5.823529411764707e-06, "loss": 1.1038, "step": 143 }, { "epoch": 0.4235294117647059, "grad_norm": 0.21993358433246613, "learning_rate": 5.794117647058824e-06, "loss": 1.1258, "step": 144 }, { "epoch": 0.4264705882352941, "grad_norm": 0.24475879967212677, "learning_rate": 5.764705882352941e-06, "loss": 1.0968, "step": 145 }, { "epoch": 0.4294117647058823, "grad_norm": 0.2095886617898941, "learning_rate": 5.735294117647059e-06, "loss": 1.1428, "step": 146 }, { "epoch": 0.4323529411764706, "grad_norm": 0.21642598509788513, "learning_rate": 5.705882352941177e-06, "loss": 1.1131, "step": 147 }, { "epoch": 0.43529411764705883, "grad_norm": 0.2527022659778595, "learning_rate": 5.676470588235294e-06, "loss": 1.1412, "step": 148 }, { "epoch": 0.43823529411764706, "grad_norm": 0.2121608853340149, "learning_rate": 5.6470588235294125e-06, "loss": 1.1005, "step": 149 }, { "epoch": 0.4411764705882353, "grad_norm": 0.23695634305477142, "learning_rate": 5.61764705882353e-06, "loss": 1.1315, "step": 150 }, { "epoch": 0.4441176470588235, "grad_norm": 0.22872112691402435, "learning_rate": 5.588235294117647e-06, "loss": 1.0705, "step": 151 }, { "epoch": 0.4470588235294118, "grad_norm": 0.2091210037469864, "learning_rate": 5.558823529411766e-06, "loss": 1.1232, "step": 152 }, { "epoch": 0.45, "grad_norm": 0.2245001345872879, "learning_rate": 5.529411764705883e-06, "loss": 1.1113, "step": 153 }, { "epoch": 0.45294117647058824, "grad_norm": 0.2469629943370819, "learning_rate": 5.500000000000001e-06, "loss": 1.1097, "step": 154 }, { "epoch": 0.45588235294117646, "grad_norm": 0.24886055290699005, "learning_rate": 5.470588235294119e-06, "loss": 1.1161, "step": 155 }, { "epoch": 0.4588235294117647, "grad_norm": 0.230917289853096, "learning_rate": 5.441176470588236e-06, "loss": 1.0882, "step": 156 }, { "epoch": 0.46176470588235297, "grad_norm": 0.315561443567276, "learning_rate": 5.411764705882353e-06, "loss": 1.0864, "step": 157 }, { "epoch": 0.4647058823529412, "grad_norm": 0.2106507569551468, "learning_rate": 5.382352941176471e-06, "loss": 1.091, "step": 158 }, { "epoch": 0.4676470588235294, "grad_norm": 0.22026994824409485, "learning_rate": 5.352941176470589e-06, "loss": 1.0655, "step": 159 }, { "epoch": 0.47058823529411764, "grad_norm": 0.23006486892700195, "learning_rate": 5.3235294117647064e-06, "loss": 1.0913, "step": 160 }, { "epoch": 0.47352941176470587, "grad_norm": 0.2270439714193344, "learning_rate": 5.294117647058824e-06, "loss": 1.076, "step": 161 }, { "epoch": 0.4764705882352941, "grad_norm": 0.25586023926734924, "learning_rate": 5.264705882352941e-06, "loss": 1.134, "step": 162 }, { "epoch": 0.47941176470588237, "grad_norm": 0.22336019575595856, "learning_rate": 5.23529411764706e-06, "loss": 1.1006, "step": 163 }, { "epoch": 0.4823529411764706, "grad_norm": 0.22112180292606354, "learning_rate": 5.205882352941177e-06, "loss": 1.0788, "step": 164 }, { "epoch": 0.4852941176470588, "grad_norm": 0.21939323842525482, "learning_rate": 5.176470588235295e-06, "loss": 1.0916, "step": 165 }, { "epoch": 0.48823529411764705, "grad_norm": 0.21641314029693604, "learning_rate": 5.147058823529411e-06, "loss": 1.0845, "step": 166 }, { "epoch": 0.49117647058823527, "grad_norm": 0.20961056649684906, "learning_rate": 5.11764705882353e-06, "loss": 1.0925, "step": 167 }, { "epoch": 0.49411764705882355, "grad_norm": 0.2464180290699005, "learning_rate": 5.088235294117647e-06, "loss": 1.0962, "step": 168 }, { "epoch": 0.4970588235294118, "grad_norm": 0.2157599776983261, "learning_rate": 5.058823529411765e-06, "loss": 1.0519, "step": 169 }, { "epoch": 0.5, "grad_norm": 0.22428640723228455, "learning_rate": 5.029411764705883e-06, "loss": 1.0584, "step": 170 }, { "epoch": 0.5029411764705882, "grad_norm": 0.21695849299430847, "learning_rate": 5e-06, "loss": 1.0702, "step": 171 }, { "epoch": 0.5058823529411764, "grad_norm": 0.22800521552562714, "learning_rate": 4.970588235294118e-06, "loss": 1.0781, "step": 172 }, { "epoch": 0.5088235294117647, "grad_norm": 0.21697255969047546, "learning_rate": 4.941176470588236e-06, "loss": 1.0828, "step": 173 }, { "epoch": 0.5117647058823529, "grad_norm": 0.22448962926864624, "learning_rate": 4.911764705882353e-06, "loss": 1.0685, "step": 174 }, { "epoch": 0.5147058823529411, "grad_norm": 0.24604758620262146, "learning_rate": 4.882352941176471e-06, "loss": 1.0435, "step": 175 }, { "epoch": 0.5176470588235295, "grad_norm": 0.23682597279548645, "learning_rate": 4.852941176470589e-06, "loss": 1.0897, "step": 176 }, { "epoch": 0.5205882352941177, "grad_norm": 0.23220428824424744, "learning_rate": 4.823529411764706e-06, "loss": 1.0848, "step": 177 }, { "epoch": 0.5235294117647059, "grad_norm": 0.21729770302772522, "learning_rate": 4.7941176470588245e-06, "loss": 1.1027, "step": 178 }, { "epoch": 0.5264705882352941, "grad_norm": 0.36938586831092834, "learning_rate": 4.764705882352941e-06, "loss": 1.0855, "step": 179 }, { "epoch": 0.5294117647058824, "grad_norm": 0.22503703832626343, "learning_rate": 4.7352941176470594e-06, "loss": 1.0892, "step": 180 }, { "epoch": 0.5323529411764706, "grad_norm": 0.22622622549533844, "learning_rate": 4.705882352941177e-06, "loss": 1.0941, "step": 181 }, { "epoch": 0.5352941176470588, "grad_norm": 0.27123570442199707, "learning_rate": 4.676470588235294e-06, "loss": 1.0792, "step": 182 }, { "epoch": 0.538235294117647, "grad_norm": 0.23995374143123627, "learning_rate": 4.647058823529412e-06, "loss": 1.0669, "step": 183 }, { "epoch": 0.5411764705882353, "grad_norm": 0.2274896800518036, "learning_rate": 4.61764705882353e-06, "loss": 1.0665, "step": 184 }, { "epoch": 0.5441176470588235, "grad_norm": 0.2378711700439453, "learning_rate": 4.588235294117647e-06, "loss": 1.0748, "step": 185 }, { "epoch": 0.5470588235294118, "grad_norm": 0.2415841519832611, "learning_rate": 4.558823529411765e-06, "loss": 1.0837, "step": 186 }, { "epoch": 0.55, "grad_norm": 0.21746912598609924, "learning_rate": 4.529411764705883e-06, "loss": 1.079, "step": 187 }, { "epoch": 0.5529411764705883, "grad_norm": 0.353338360786438, "learning_rate": 4.5e-06, "loss": 1.05, "step": 188 }, { "epoch": 0.5558823529411765, "grad_norm": 0.23014746606349945, "learning_rate": 4.4705882352941184e-06, "loss": 1.092, "step": 189 }, { "epoch": 0.5588235294117647, "grad_norm": 0.23989826440811157, "learning_rate": 4.441176470588235e-06, "loss": 1.0795, "step": 190 }, { "epoch": 0.5617647058823529, "grad_norm": 0.2372935563325882, "learning_rate": 4.411764705882353e-06, "loss": 1.0599, "step": 191 }, { "epoch": 0.5647058823529412, "grad_norm": 0.22507061064243317, "learning_rate": 4.382352941176471e-06, "loss": 1.0746, "step": 192 }, { "epoch": 0.5676470588235294, "grad_norm": 0.2515420913696289, "learning_rate": 4.352941176470588e-06, "loss": 1.0765, "step": 193 }, { "epoch": 0.5705882352941176, "grad_norm": 0.23316609859466553, "learning_rate": 4.323529411764707e-06, "loss": 1.1088, "step": 194 }, { "epoch": 0.5735294117647058, "grad_norm": 0.24043501913547516, "learning_rate": 4.294117647058823e-06, "loss": 1.1, "step": 195 }, { "epoch": 0.5764705882352941, "grad_norm": 0.22288966178894043, "learning_rate": 4.264705882352942e-06, "loss": 1.0924, "step": 196 }, { "epoch": 0.5794117647058824, "grad_norm": 0.23474599421024323, "learning_rate": 4.235294117647059e-06, "loss": 1.0658, "step": 197 }, { "epoch": 0.5823529411764706, "grad_norm": 0.2446664720773697, "learning_rate": 4.205882352941177e-06, "loss": 1.0773, "step": 198 }, { "epoch": 0.5852941176470589, "grad_norm": 0.247602179646492, "learning_rate": 4.176470588235295e-06, "loss": 1.0627, "step": 199 }, { "epoch": 0.5882352941176471, "grad_norm": 0.2503092586994171, "learning_rate": 4.147058823529412e-06, "loss": 1.0938, "step": 200 }, { "epoch": 0.5911764705882353, "grad_norm": 0.23191429674625397, "learning_rate": 4.11764705882353e-06, "loss": 1.0668, "step": 201 }, { "epoch": 0.5941176470588235, "grad_norm": 0.23563452064990997, "learning_rate": 4.088235294117647e-06, "loss": 1.0328, "step": 202 }, { "epoch": 0.5970588235294118, "grad_norm": 0.27292484045028687, "learning_rate": 4.058823529411765e-06, "loss": 1.0473, "step": 203 }, { "epoch": 0.6, "grad_norm": 0.21903876960277557, "learning_rate": 4.029411764705883e-06, "loss": 1.0523, "step": 204 }, { "epoch": 0.6029411764705882, "grad_norm": 0.3081904351711273, "learning_rate": 4.000000000000001e-06, "loss": 1.0887, "step": 205 }, { "epoch": 0.6058823529411764, "grad_norm": 0.31239840388298035, "learning_rate": 3.970588235294118e-06, "loss": 1.0981, "step": 206 }, { "epoch": 0.6088235294117647, "grad_norm": 0.23030546307563782, "learning_rate": 3.941176470588236e-06, "loss": 1.0273, "step": 207 }, { "epoch": 0.611764705882353, "grad_norm": 0.24007487297058105, "learning_rate": 3.911764705882353e-06, "loss": 1.0981, "step": 208 }, { "epoch": 0.6147058823529412, "grad_norm": 0.2520597577095032, "learning_rate": 3.882352941176471e-06, "loss": 1.0742, "step": 209 }, { "epoch": 0.6176470588235294, "grad_norm": 0.24418134987354279, "learning_rate": 3.852941176470589e-06, "loss": 1.0769, "step": 210 }, { "epoch": 0.6205882352941177, "grad_norm": 0.24392227828502655, "learning_rate": 3.8235294117647055e-06, "loss": 1.0591, "step": 211 }, { "epoch": 0.6235294117647059, "grad_norm": 0.25623035430908203, "learning_rate": 3.794117647058824e-06, "loss": 1.0524, "step": 212 }, { "epoch": 0.6264705882352941, "grad_norm": 0.25523054599761963, "learning_rate": 3.7647058823529414e-06, "loss": 1.0785, "step": 213 }, { "epoch": 0.6294117647058823, "grad_norm": 0.2477787584066391, "learning_rate": 3.7352941176470593e-06, "loss": 1.084, "step": 214 }, { "epoch": 0.6323529411764706, "grad_norm": 0.22725874185562134, "learning_rate": 3.7058823529411767e-06, "loss": 1.0784, "step": 215 }, { "epoch": 0.6352941176470588, "grad_norm": 0.25304916501045227, "learning_rate": 3.6764705882352946e-06, "loss": 1.067, "step": 216 }, { "epoch": 0.638235294117647, "grad_norm": 0.23904795944690704, "learning_rate": 3.6470588235294117e-06, "loss": 1.0671, "step": 217 }, { "epoch": 0.6411764705882353, "grad_norm": 0.35910505056381226, "learning_rate": 3.6176470588235296e-06, "loss": 1.1031, "step": 218 }, { "epoch": 0.6441176470588236, "grad_norm": 0.2860150933265686, "learning_rate": 3.5882352941176475e-06, "loss": 1.0789, "step": 219 }, { "epoch": 0.6470588235294118, "grad_norm": 0.25603345036506653, "learning_rate": 3.558823529411765e-06, "loss": 1.0452, "step": 220 }, { "epoch": 0.65, "grad_norm": 0.24726077914237976, "learning_rate": 3.529411764705883e-06, "loss": 1.0663, "step": 221 }, { "epoch": 0.6529411764705882, "grad_norm": 0.24604010581970215, "learning_rate": 3.5e-06, "loss": 1.0638, "step": 222 }, { "epoch": 0.6558823529411765, "grad_norm": 0.25741252303123474, "learning_rate": 3.470588235294118e-06, "loss": 1.0516, "step": 223 }, { "epoch": 0.6588235294117647, "grad_norm": 0.2364550083875656, "learning_rate": 3.4411764705882358e-06, "loss": 1.066, "step": 224 }, { "epoch": 0.6617647058823529, "grad_norm": 0.25125953555107117, "learning_rate": 3.4117647058823532e-06, "loss": 1.0247, "step": 225 }, { "epoch": 0.6647058823529411, "grad_norm": 0.3127348721027374, "learning_rate": 3.382352941176471e-06, "loss": 1.0668, "step": 226 }, { "epoch": 0.6676470588235294, "grad_norm": 0.233737975358963, "learning_rate": 3.352941176470588e-06, "loss": 1.0794, "step": 227 }, { "epoch": 0.6705882352941176, "grad_norm": 0.25699761509895325, "learning_rate": 3.323529411764706e-06, "loss": 1.0511, "step": 228 }, { "epoch": 0.6735294117647059, "grad_norm": 0.24534179270267487, "learning_rate": 3.2941176470588236e-06, "loss": 1.0707, "step": 229 }, { "epoch": 0.6764705882352942, "grad_norm": 0.2518172264099121, "learning_rate": 3.2647058823529415e-06, "loss": 1.0856, "step": 230 }, { "epoch": 0.6794117647058824, "grad_norm": 0.2618185877799988, "learning_rate": 3.2352941176470594e-06, "loss": 1.0624, "step": 231 }, { "epoch": 0.6823529411764706, "grad_norm": 0.24736982583999634, "learning_rate": 3.205882352941177e-06, "loss": 1.0648, "step": 232 }, { "epoch": 0.6852941176470588, "grad_norm": 0.25377774238586426, "learning_rate": 3.1764705882352943e-06, "loss": 1.0563, "step": 233 }, { "epoch": 0.6882352941176471, "grad_norm": 0.264789342880249, "learning_rate": 3.147058823529412e-06, "loss": 1.0609, "step": 234 }, { "epoch": 0.6911764705882353, "grad_norm": 0.23524682223796844, "learning_rate": 3.1176470588235297e-06, "loss": 1.0513, "step": 235 }, { "epoch": 0.6941176470588235, "grad_norm": 0.2972707748413086, "learning_rate": 3.0882352941176476e-06, "loss": 1.0712, "step": 236 }, { "epoch": 0.6970588235294117, "grad_norm": 0.2425236701965332, "learning_rate": 3.058823529411765e-06, "loss": 1.0636, "step": 237 }, { "epoch": 0.7, "grad_norm": 0.23967207968235016, "learning_rate": 3.0294117647058826e-06, "loss": 1.0506, "step": 238 }, { "epoch": 0.7029411764705882, "grad_norm": 0.25000911951065063, "learning_rate": 3e-06, "loss": 1.0225, "step": 239 }, { "epoch": 0.7058823529411765, "grad_norm": 0.27761110663414, "learning_rate": 2.970588235294118e-06, "loss": 1.0557, "step": 240 }, { "epoch": 0.7088235294117647, "grad_norm": 0.23988835513591766, "learning_rate": 2.9411764705882355e-06, "loss": 1.039, "step": 241 }, { "epoch": 0.711764705882353, "grad_norm": 0.2365685999393463, "learning_rate": 2.9117647058823534e-06, "loss": 1.0524, "step": 242 }, { "epoch": 0.7147058823529412, "grad_norm": 0.2913731038570404, "learning_rate": 2.8823529411764704e-06, "loss": 1.0733, "step": 243 }, { "epoch": 0.7176470588235294, "grad_norm": 0.3353981375694275, "learning_rate": 2.8529411764705883e-06, "loss": 1.0579, "step": 244 }, { "epoch": 0.7205882352941176, "grad_norm": 0.3488647937774658, "learning_rate": 2.8235294117647062e-06, "loss": 1.0766, "step": 245 }, { "epoch": 0.7235294117647059, "grad_norm": 0.2559491693973541, "learning_rate": 2.7941176470588237e-06, "loss": 1.0751, "step": 246 }, { "epoch": 0.7264705882352941, "grad_norm": 0.24440276622772217, "learning_rate": 2.7647058823529416e-06, "loss": 1.0735, "step": 247 }, { "epoch": 0.7294117647058823, "grad_norm": 0.237368643283844, "learning_rate": 2.7352941176470595e-06, "loss": 1.0442, "step": 248 }, { "epoch": 0.7323529411764705, "grad_norm": 0.29413533210754395, "learning_rate": 2.7058823529411766e-06, "loss": 1.0496, "step": 249 }, { "epoch": 0.7352941176470589, "grad_norm": 0.23831024765968323, "learning_rate": 2.6764705882352945e-06, "loss": 1.0522, "step": 250 }, { "epoch": 0.7382352941176471, "grad_norm": 0.2576645612716675, "learning_rate": 2.647058823529412e-06, "loss": 1.0257, "step": 251 }, { "epoch": 0.7411764705882353, "grad_norm": 0.2468797266483307, "learning_rate": 2.61764705882353e-06, "loss": 1.0742, "step": 252 }, { "epoch": 0.7441176470588236, "grad_norm": 0.2345353364944458, "learning_rate": 2.5882352941176473e-06, "loss": 1.0615, "step": 253 }, { "epoch": 0.7470588235294118, "grad_norm": 0.2569163143634796, "learning_rate": 2.558823529411765e-06, "loss": 1.0656, "step": 254 }, { "epoch": 0.75, "grad_norm": 0.2634453773498535, "learning_rate": 2.5294117647058823e-06, "loss": 1.0498, "step": 255 }, { "epoch": 0.7529411764705882, "grad_norm": 0.3457936644554138, "learning_rate": 2.5e-06, "loss": 1.04, "step": 256 }, { "epoch": 0.7558823529411764, "grad_norm": 0.24360963702201843, "learning_rate": 2.470588235294118e-06, "loss": 1.0357, "step": 257 }, { "epoch": 0.7588235294117647, "grad_norm": 0.23760569095611572, "learning_rate": 2.4411764705882356e-06, "loss": 1.0592, "step": 258 }, { "epoch": 0.7617647058823529, "grad_norm": 0.24314503371715546, "learning_rate": 2.411764705882353e-06, "loss": 1.0389, "step": 259 }, { "epoch": 0.7647058823529411, "grad_norm": 0.24598494172096252, "learning_rate": 2.3823529411764705e-06, "loss": 1.0223, "step": 260 }, { "epoch": 0.7676470588235295, "grad_norm": 0.2521425783634186, "learning_rate": 2.3529411764705885e-06, "loss": 1.0707, "step": 261 }, { "epoch": 0.7705882352941177, "grad_norm": 0.34780582785606384, "learning_rate": 2.323529411764706e-06, "loss": 1.0389, "step": 262 }, { "epoch": 0.7735294117647059, "grad_norm": 0.25080588459968567, "learning_rate": 2.2941176470588234e-06, "loss": 1.0546, "step": 263 }, { "epoch": 0.7764705882352941, "grad_norm": 0.2575359344482422, "learning_rate": 2.2647058823529413e-06, "loss": 1.0652, "step": 264 }, { "epoch": 0.7794117647058824, "grad_norm": 0.307264119386673, "learning_rate": 2.2352941176470592e-06, "loss": 1.0675, "step": 265 }, { "epoch": 0.7823529411764706, "grad_norm": 0.24160020053386688, "learning_rate": 2.2058823529411767e-06, "loss": 1.0452, "step": 266 }, { "epoch": 0.7852941176470588, "grad_norm": 0.24322670698165894, "learning_rate": 2.176470588235294e-06, "loss": 1.0553, "step": 267 }, { "epoch": 0.788235294117647, "grad_norm": 0.24782130122184753, "learning_rate": 2.1470588235294117e-06, "loss": 1.0724, "step": 268 }, { "epoch": 0.7911764705882353, "grad_norm": 0.27055615186691284, "learning_rate": 2.1176470588235296e-06, "loss": 1.0247, "step": 269 }, { "epoch": 0.7941176470588235, "grad_norm": 0.2918650805950165, "learning_rate": 2.0882352941176475e-06, "loss": 1.0021, "step": 270 }, { "epoch": 0.7970588235294118, "grad_norm": 0.27240893244743347, "learning_rate": 2.058823529411765e-06, "loss": 1.0386, "step": 271 }, { "epoch": 0.8, "grad_norm": 0.26854994893074036, "learning_rate": 2.0294117647058824e-06, "loss": 1.0705, "step": 272 }, { "epoch": 0.8029411764705883, "grad_norm": 0.2381146103143692, "learning_rate": 2.0000000000000003e-06, "loss": 1.0533, "step": 273 }, { "epoch": 0.8058823529411765, "grad_norm": 0.2356519252061844, "learning_rate": 1.970588235294118e-06, "loss": 1.0368, "step": 274 }, { "epoch": 0.8088235294117647, "grad_norm": 0.2659197747707367, "learning_rate": 1.9411764705882353e-06, "loss": 1.0609, "step": 275 }, { "epoch": 0.8117647058823529, "grad_norm": 0.24807916581630707, "learning_rate": 1.9117647058823528e-06, "loss": 1.0314, "step": 276 }, { "epoch": 0.8147058823529412, "grad_norm": 0.2560952603816986, "learning_rate": 1.8823529411764707e-06, "loss": 1.0362, "step": 277 }, { "epoch": 0.8176470588235294, "grad_norm": 0.23093286156654358, "learning_rate": 1.8529411764705884e-06, "loss": 1.0337, "step": 278 }, { "epoch": 0.8205882352941176, "grad_norm": 0.24520130455493927, "learning_rate": 1.8235294117647058e-06, "loss": 1.0255, "step": 279 }, { "epoch": 0.8235294117647058, "grad_norm": 0.24421636760234833, "learning_rate": 1.7941176470588238e-06, "loss": 1.0533, "step": 280 }, { "epoch": 0.8264705882352941, "grad_norm": 0.24678398668766022, "learning_rate": 1.7647058823529414e-06, "loss": 1.0597, "step": 281 }, { "epoch": 0.8294117647058824, "grad_norm": 0.27443745732307434, "learning_rate": 1.735294117647059e-06, "loss": 1.0489, "step": 282 }, { "epoch": 0.8323529411764706, "grad_norm": 0.24420900642871857, "learning_rate": 1.7058823529411766e-06, "loss": 1.0453, "step": 283 }, { "epoch": 0.8352941176470589, "grad_norm": 0.2628645598888397, "learning_rate": 1.676470588235294e-06, "loss": 1.0557, "step": 284 }, { "epoch": 0.8382352941176471, "grad_norm": 0.2697880268096924, "learning_rate": 1.6470588235294118e-06, "loss": 0.987, "step": 285 }, { "epoch": 0.8411764705882353, "grad_norm": 0.2665739357471466, "learning_rate": 1.6176470588235297e-06, "loss": 1.0502, "step": 286 }, { "epoch": 0.8441176470588235, "grad_norm": 0.2457929402589798, "learning_rate": 1.5882352941176472e-06, "loss": 1.0461, "step": 287 }, { "epoch": 0.8470588235294118, "grad_norm": 0.2716211676597595, "learning_rate": 1.5588235294117649e-06, "loss": 1.0517, "step": 288 }, { "epoch": 0.85, "grad_norm": 0.2448592483997345, "learning_rate": 1.5294117647058826e-06, "loss": 1.012, "step": 289 }, { "epoch": 0.8529411764705882, "grad_norm": 0.24840906262397766, "learning_rate": 1.5e-06, "loss": 1.057, "step": 290 }, { "epoch": 0.8558823529411764, "grad_norm": 0.3201400935649872, "learning_rate": 1.4705882352941177e-06, "loss": 1.0132, "step": 291 }, { "epoch": 0.8588235294117647, "grad_norm": 0.24024993181228638, "learning_rate": 1.4411764705882352e-06, "loss": 1.0422, "step": 292 }, { "epoch": 0.861764705882353, "grad_norm": 0.2523883283138275, "learning_rate": 1.4117647058823531e-06, "loss": 1.0431, "step": 293 }, { "epoch": 0.8647058823529412, "grad_norm": 0.23962493240833282, "learning_rate": 1.3823529411764708e-06, "loss": 1.0499, "step": 294 }, { "epoch": 0.8676470588235294, "grad_norm": 0.23773916065692902, "learning_rate": 1.3529411764705883e-06, "loss": 1.0031, "step": 295 }, { "epoch": 0.8705882352941177, "grad_norm": 0.24341008067131042, "learning_rate": 1.323529411764706e-06, "loss": 1.0457, "step": 296 }, { "epoch": 0.8735294117647059, "grad_norm": 0.27544376254081726, "learning_rate": 1.2941176470588237e-06, "loss": 1.0574, "step": 297 }, { "epoch": 0.8764705882352941, "grad_norm": 0.2580159604549408, "learning_rate": 1.2647058823529412e-06, "loss": 1.0042, "step": 298 }, { "epoch": 0.8794117647058823, "grad_norm": 0.2834937274456024, "learning_rate": 1.235294117647059e-06, "loss": 1.04, "step": 299 }, { "epoch": 0.8823529411764706, "grad_norm": 0.2423858493566513, "learning_rate": 1.2058823529411765e-06, "loss": 1.043, "step": 300 }, { "epoch": 0.8852941176470588, "grad_norm": 0.24057364463806152, "learning_rate": 1.1764705882352942e-06, "loss": 1.0464, "step": 301 }, { "epoch": 0.888235294117647, "grad_norm": 0.25729063153266907, "learning_rate": 1.1470588235294117e-06, "loss": 1.0825, "step": 302 }, { "epoch": 0.8911764705882353, "grad_norm": 0.24446231126785278, "learning_rate": 1.1176470588235296e-06, "loss": 1.0542, "step": 303 }, { "epoch": 0.8941176470588236, "grad_norm": 0.2583821415901184, "learning_rate": 1.088235294117647e-06, "loss": 1.015, "step": 304 }, { "epoch": 0.8970588235294118, "grad_norm": 0.23999781906604767, "learning_rate": 1.0588235294117648e-06, "loss": 1.032, "step": 305 }, { "epoch": 0.9, "grad_norm": 0.25951138138771057, "learning_rate": 1.0294117647058825e-06, "loss": 1.0619, "step": 306 }, { "epoch": 0.9029411764705882, "grad_norm": 0.24357210099697113, "learning_rate": 1.0000000000000002e-06, "loss": 1.0349, "step": 307 }, { "epoch": 0.9058823529411765, "grad_norm": 0.2540913224220276, "learning_rate": 9.705882352941176e-07, "loss": 1.0651, "step": 308 }, { "epoch": 0.9088235294117647, "grad_norm": 0.2388201504945755, "learning_rate": 9.411764705882353e-07, "loss": 1.0361, "step": 309 }, { "epoch": 0.9117647058823529, "grad_norm": 0.26510342955589294, "learning_rate": 9.117647058823529e-07, "loss": 1.0545, "step": 310 }, { "epoch": 0.9147058823529411, "grad_norm": 0.26220619678497314, "learning_rate": 8.823529411764707e-07, "loss": 1.0607, "step": 311 }, { "epoch": 0.9176470588235294, "grad_norm": 0.24358054995536804, "learning_rate": 8.529411764705883e-07, "loss": 1.0315, "step": 312 }, { "epoch": 0.9205882352941176, "grad_norm": 0.2402532547712326, "learning_rate": 8.235294117647059e-07, "loss": 1.0482, "step": 313 }, { "epoch": 0.9235294117647059, "grad_norm": 0.2409527748823166, "learning_rate": 7.941176470588236e-07, "loss": 1.0179, "step": 314 }, { "epoch": 0.9264705882352942, "grad_norm": 0.23844361305236816, "learning_rate": 7.647058823529413e-07, "loss": 1.0343, "step": 315 }, { "epoch": 0.9294117647058824, "grad_norm": 0.2569085955619812, "learning_rate": 7.352941176470589e-07, "loss": 1.0672, "step": 316 }, { "epoch": 0.9323529411764706, "grad_norm": 0.2910473048686981, "learning_rate": 7.058823529411766e-07, "loss": 1.0306, "step": 317 }, { "epoch": 0.9352941176470588, "grad_norm": 0.24089165031909943, "learning_rate": 6.764705882352941e-07, "loss": 1.0184, "step": 318 }, { "epoch": 0.9382352941176471, "grad_norm": 0.25330087542533875, "learning_rate": 6.470588235294118e-07, "loss": 1.0566, "step": 319 }, { "epoch": 0.9411764705882353, "grad_norm": 0.25225237011909485, "learning_rate": 6.176470588235295e-07, "loss": 1.0303, "step": 320 }, { "epoch": 0.9441176470588235, "grad_norm": 0.24123378098011017, "learning_rate": 5.882352941176471e-07, "loss": 1.021, "step": 321 }, { "epoch": 0.9470588235294117, "grad_norm": 0.2519339323043823, "learning_rate": 5.588235294117648e-07, "loss": 1.0472, "step": 322 }, { "epoch": 0.95, "grad_norm": 0.25272488594055176, "learning_rate": 5.294117647058824e-07, "loss": 1.0592, "step": 323 }, { "epoch": 0.9529411764705882, "grad_norm": 0.24109138548374176, "learning_rate": 5.000000000000001e-07, "loss": 1.0241, "step": 324 }, { "epoch": 0.9558823529411765, "grad_norm": 0.2700742483139038, "learning_rate": 4.7058823529411767e-07, "loss": 1.0378, "step": 325 }, { "epoch": 0.9588235294117647, "grad_norm": 0.24684427678585052, "learning_rate": 4.4117647058823536e-07, "loss": 1.0328, "step": 326 }, { "epoch": 0.961764705882353, "grad_norm": 0.36805665493011475, "learning_rate": 4.1176470588235295e-07, "loss": 1.0588, "step": 327 }, { "epoch": 0.9647058823529412, "grad_norm": 0.24640294909477234, "learning_rate": 3.8235294117647064e-07, "loss": 1.0281, "step": 328 }, { "epoch": 0.9676470588235294, "grad_norm": 0.2545859217643738, "learning_rate": 3.529411764705883e-07, "loss": 1.0663, "step": 329 }, { "epoch": 0.9705882352941176, "grad_norm": 0.256657212972641, "learning_rate": 3.235294117647059e-07, "loss": 1.0219, "step": 330 }, { "epoch": 0.9735294117647059, "grad_norm": 0.23593604564666748, "learning_rate": 2.9411764705882356e-07, "loss": 1.0273, "step": 331 }, { "epoch": 0.9764705882352941, "grad_norm": 0.25067442655563354, "learning_rate": 2.647058823529412e-07, "loss": 1.0298, "step": 332 }, { "epoch": 0.9794117647058823, "grad_norm": 0.23615114390850067, "learning_rate": 2.3529411764705883e-07, "loss": 1.0325, "step": 333 }, { "epoch": 0.9823529411764705, "grad_norm": 0.24917052686214447, "learning_rate": 2.0588235294117647e-07, "loss": 1.0646, "step": 334 }, { "epoch": 0.9852941176470589, "grad_norm": 0.2560918629169464, "learning_rate": 1.7647058823529414e-07, "loss": 1.0233, "step": 335 }, { "epoch": 0.9882352941176471, "grad_norm": 0.25138577818870544, "learning_rate": 1.4705882352941178e-07, "loss": 1.0614, "step": 336 }, { "epoch": 0.9911764705882353, "grad_norm": 0.23887692391872406, "learning_rate": 1.1764705882352942e-07, "loss": 1.019, "step": 337 }, { "epoch": 0.9941176470588236, "grad_norm": 0.2688574492931366, "learning_rate": 8.823529411764707e-08, "loss": 1.0471, "step": 338 }, { "epoch": 0.9970588235294118, "grad_norm": 0.5432394742965698, "learning_rate": 5.882352941176471e-08, "loss": 1.0482, "step": 339 }, { "epoch": 1.0, "grad_norm": 0.2513401210308075, "learning_rate": 2.9411764705882354e-08, "loss": 1.0161, "step": 340 } ], "logging_steps": 1.0, "max_steps": 340, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 0, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.128366044583297e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }