| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.5042194092827, | |
| "eval_steps": 30, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016877637130801686, | |
| "grad_norm": 0.08447265625, | |
| "learning_rate": 3e-06, | |
| "loss": 1.1751, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016877637130801686, | |
| "eval_loss": 1.185997486114502, | |
| "eval_runtime": 72.8223, | |
| "eval_samples_per_second": 14.144, | |
| "eval_steps_per_second": 14.144, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03375527426160337, | |
| "grad_norm": 0.08544921875, | |
| "learning_rate": 6e-06, | |
| "loss": 1.1683, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05063291139240506, | |
| "grad_norm": 0.0830078125, | |
| "learning_rate": 9e-06, | |
| "loss": 1.1737, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06751054852320675, | |
| "grad_norm": 0.08544921875, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.1889, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08438818565400844, | |
| "grad_norm": 0.0849609375, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.1619, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10126582278481013, | |
| "grad_norm": 0.0869140625, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.1815, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11814345991561181, | |
| "grad_norm": 0.08447265625, | |
| "learning_rate": 2.1e-05, | |
| "loss": 1.1726, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1350210970464135, | |
| "grad_norm": 0.08740234375, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.1701, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1518987341772152, | |
| "grad_norm": 0.08642578125, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 1.1818, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16877637130801687, | |
| "grad_norm": 0.08935546875, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1896, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18565400843881857, | |
| "grad_norm": 0.0888671875, | |
| "learning_rate": 2.999855077059572e-05, | |
| "loss": 1.1873, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.20253164556962025, | |
| "grad_norm": 0.08984375, | |
| "learning_rate": 2.9994203362418313e-05, | |
| "loss": 1.1838, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21940928270042195, | |
| "grad_norm": 0.0859375, | |
| "learning_rate": 2.998695861552002e-05, | |
| "loss": 1.1569, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.23628691983122363, | |
| "grad_norm": 0.08642578125, | |
| "learning_rate": 2.9976817929807542e-05, | |
| "loss": 1.1595, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.25316455696202533, | |
| "grad_norm": 0.078125, | |
| "learning_rate": 2.996378326477153e-05, | |
| "loss": 1.1348, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.270042194092827, | |
| "grad_norm": 0.07470703125, | |
| "learning_rate": 2.9947857139107964e-05, | |
| "loss": 1.1434, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2869198312236287, | |
| "grad_norm": 0.140625, | |
| "learning_rate": 2.992904263023146e-05, | |
| "loss": 1.8213, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3037974683544304, | |
| "grad_norm": 0.06787109375, | |
| "learning_rate": 2.990734337368062e-05, | |
| "loss": 1.1289, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3206751054852321, | |
| "grad_norm": 0.0654296875, | |
| "learning_rate": 2.9882763562415518e-05, | |
| "loss": 1.1106, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.33755274261603374, | |
| "grad_norm": 0.06640625, | |
| "learning_rate": 2.9855307946007532e-05, | |
| "loss": 1.1381, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.35443037974683544, | |
| "grad_norm": 0.064453125, | |
| "learning_rate": 2.982498182972154e-05, | |
| "loss": 1.1192, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.37130801687763715, | |
| "grad_norm": 0.0615234375, | |
| "learning_rate": 2.9791791073490795e-05, | |
| "loss": 1.1105, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3881856540084388, | |
| "grad_norm": 0.061767578125, | |
| "learning_rate": 2.9755742090784617e-05, | |
| "loss": 1.1207, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4050632911392405, | |
| "grad_norm": 0.0634765625, | |
| "learning_rate": 2.9716841847369106e-05, | |
| "loss": 1.1083, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4219409282700422, | |
| "grad_norm": 0.058349609375, | |
| "learning_rate": 2.967509785996114e-05, | |
| "loss": 1.1007, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4388185654008439, | |
| "grad_norm": 0.0615234375, | |
| "learning_rate": 2.963051819477592e-05, | |
| "loss": 1.0842, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.45569620253164556, | |
| "grad_norm": 0.0625, | |
| "learning_rate": 2.958311146596833e-05, | |
| "loss": 1.0961, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.47257383966244726, | |
| "grad_norm": 0.05908203125, | |
| "learning_rate": 2.953288683396841e-05, | |
| "loss": 1.109, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.48945147679324896, | |
| "grad_norm": 0.061767578125, | |
| "learning_rate": 2.9479854003711298e-05, | |
| "loss": 1.0789, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5063291139240507, | |
| "grad_norm": 0.06103515625, | |
| "learning_rate": 2.9424023222761938e-05, | |
| "loss": 1.1007, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5063291139240507, | |
| "eval_loss": 1.091182827949524, | |
| "eval_runtime": 74.0135, | |
| "eval_samples_per_second": 13.916, | |
| "eval_steps_per_second": 13.916, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5232067510548524, | |
| "grad_norm": 0.059814453125, | |
| "learning_rate": 2.9365405279334904e-05, | |
| "loss": 1.0756, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.540084388185654, | |
| "grad_norm": 0.056396484375, | |
| "learning_rate": 2.930401150020983e-05, | |
| "loss": 1.0939, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5569620253164557, | |
| "grad_norm": 0.05712890625, | |
| "learning_rate": 2.9239853748542717e-05, | |
| "loss": 1.0901, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5738396624472574, | |
| "grad_norm": 0.054931640625, | |
| "learning_rate": 2.9172944421573587e-05, | |
| "loss": 1.0873, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5907172995780591, | |
| "grad_norm": 0.0546875, | |
| "learning_rate": 2.9103296448230986e-05, | |
| "loss": 1.0584, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6075949367088608, | |
| "grad_norm": 0.0556640625, | |
| "learning_rate": 2.9030923286633703e-05, | |
| "loss": 1.0692, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6244725738396625, | |
| "grad_norm": 0.16015625, | |
| "learning_rate": 2.8955838921490252e-05, | |
| "loss": 1.782, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6413502109704642, | |
| "grad_norm": 0.052001953125, | |
| "learning_rate": 2.8878057861396606e-05, | |
| "loss": 1.0667, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6582278481012658, | |
| "grad_norm": 0.052001953125, | |
| "learning_rate": 2.8797595136032675e-05, | |
| "loss": 1.0656, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6751054852320675, | |
| "grad_norm": 0.052734375, | |
| "learning_rate": 2.8714466293258142e-05, | |
| "loss": 1.0736, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6919831223628692, | |
| "grad_norm": 0.053955078125, | |
| "learning_rate": 2.8628687396108107e-05, | |
| "loss": 1.0638, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7088607594936709, | |
| "grad_norm": 0.05224609375, | |
| "learning_rate": 2.8540275019689237e-05, | |
| "loss": 1.0746, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7257383966244726, | |
| "grad_norm": 0.051513671875, | |
| "learning_rate": 2.8449246247976947e-05, | |
| "loss": 1.0608, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7426160337552743, | |
| "grad_norm": 0.052001953125, | |
| "learning_rate": 2.835561867051426e-05, | |
| "loss": 1.0619, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.759493670886076, | |
| "grad_norm": 0.051025390625, | |
| "learning_rate": 2.825941037901294e-05, | |
| "loss": 1.048, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7763713080168776, | |
| "grad_norm": 0.05078125, | |
| "learning_rate": 2.816063996385765e-05, | |
| "loss": 1.0761, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7932489451476793, | |
| "grad_norm": 0.0498046875, | |
| "learning_rate": 2.805932651051372e-05, | |
| "loss": 1.0443, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.810126582278481, | |
| "grad_norm": 0.051025390625, | |
| "learning_rate": 2.7955489595839228e-05, | |
| "loss": 1.0527, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8270042194092827, | |
| "grad_norm": 0.052734375, | |
| "learning_rate": 2.784914928430218e-05, | |
| "loss": 1.0498, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8438818565400844, | |
| "grad_norm": 0.049560546875, | |
| "learning_rate": 2.7740326124103416e-05, | |
| "loss": 1.0537, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8607594936708861, | |
| "grad_norm": 0.053466796875, | |
| "learning_rate": 2.762904114320609e-05, | |
| "loss": 1.0326, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.8776371308016878, | |
| "grad_norm": 0.04931640625, | |
| "learning_rate": 2.751531584527241e-05, | |
| "loss": 1.043, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.8945147679324894, | |
| "grad_norm": 0.05126953125, | |
| "learning_rate": 2.7399172205508476e-05, | |
| "loss": 1.0463, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.9113924050632911, | |
| "grad_norm": 0.0517578125, | |
| "learning_rate": 2.7280632666418013e-05, | |
| "loss": 1.0476, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9282700421940928, | |
| "grad_norm": 0.053466796875, | |
| "learning_rate": 2.715972013346576e-05, | |
| "loss": 1.0467, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.9451476793248945, | |
| "grad_norm": 0.0498046875, | |
| "learning_rate": 2.703645797065147e-05, | |
| "loss": 1.0467, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.9620253164556962, | |
| "grad_norm": 0.05078125, | |
| "learning_rate": 2.6910869995995247e-05, | |
| "loss": 1.05, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.9789029535864979, | |
| "grad_norm": 0.053955078125, | |
| "learning_rate": 2.678298047693518e-05, | |
| "loss": 1.0453, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.9957805907172996, | |
| "grad_norm": 0.050048828125, | |
| "learning_rate": 2.6652814125638142e-05, | |
| "loss": 1.0348, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.0126582278481013, | |
| "grad_norm": 0.052490234375, | |
| "learning_rate": 2.652039609422463e-05, | |
| "loss": 1.0418, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0126582278481013, | |
| "eval_loss": 1.0428293943405151, | |
| "eval_runtime": 74.0734, | |
| "eval_samples_per_second": 13.905, | |
| "eval_steps_per_second": 13.905, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0147679324894514, | |
| "grad_norm": 0.0732421875, | |
| "learning_rate": 2.638575196990862e-05, | |
| "loss": 1.0194, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.0316455696202531, | |
| "grad_norm": 0.049560546875, | |
| "learning_rate": 2.624890777005332e-05, | |
| "loss": 1.0365, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.0485232067510548, | |
| "grad_norm": 0.05126953125, | |
| "learning_rate": 2.6109889937143828e-05, | |
| "loss": 1.0426, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.0654008438818565, | |
| "grad_norm": 0.05126953125, | |
| "learning_rate": 2.5968725333677628e-05, | |
| "loss": 1.043, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.0822784810126582, | |
| "grad_norm": 0.051513671875, | |
| "learning_rate": 2.582544123697395e-05, | |
| "loss": 1.0243, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.09915611814346, | |
| "grad_norm": 0.0517578125, | |
| "learning_rate": 2.568006533390295e-05, | |
| "loss": 1.0258, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.1160337552742616, | |
| "grad_norm": 0.050537109375, | |
| "learning_rate": 2.5532625715535733e-05, | |
| "loss": 1.0248, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.1329113924050633, | |
| "grad_norm": 0.0498046875, | |
| "learning_rate": 2.5383150871716342e-05, | |
| "loss": 1.0083, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.149789029535865, | |
| "grad_norm": 0.05224609375, | |
| "learning_rate": 2.5231669685556636e-05, | |
| "loss": 1.0207, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.1666666666666667, | |
| "grad_norm": 0.051513671875, | |
| "learning_rate": 2.507821142785516e-05, | |
| "loss": 1.0435, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1835443037974684, | |
| "grad_norm": 0.05224609375, | |
| "learning_rate": 2.4922805751441174e-05, | |
| "loss": 1.0354, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.20042194092827, | |
| "grad_norm": 0.054443359375, | |
| "learning_rate": 2.4765482685444786e-05, | |
| "loss": 1.0266, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.2172995780590719, | |
| "grad_norm": 0.05126953125, | |
| "learning_rate": 2.460627262949443e-05, | |
| "loss": 1.0411, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.2341772151898733, | |
| "grad_norm": 0.05126953125, | |
| "learning_rate": 2.4445206347842714e-05, | |
| "loss": 1.0224, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.251054852320675, | |
| "grad_norm": 0.052978515625, | |
| "learning_rate": 2.428231496342181e-05, | |
| "loss": 1.0253, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.2679324894514767, | |
| "grad_norm": 0.05322265625, | |
| "learning_rate": 2.4117629951829602e-05, | |
| "loss": 1.0298, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.2848101265822784, | |
| "grad_norm": 0.052490234375, | |
| "learning_rate": 2.395118313524758e-05, | |
| "loss": 1.0239, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.3016877637130801, | |
| "grad_norm": 0.0537109375, | |
| "learning_rate": 2.3783006676291866e-05, | |
| "loss": 1.0212, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.3185654008438819, | |
| "grad_norm": 0.052734375, | |
| "learning_rate": 2.361313307179837e-05, | |
| "loss": 1.0371, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.3354430379746836, | |
| "grad_norm": 0.05126953125, | |
| "learning_rate": 2.3441595146543458e-05, | |
| "loss": 1.0314, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3523206751054853, | |
| "grad_norm": 0.052001953125, | |
| "learning_rate": 2.3268426046901153e-05, | |
| "loss": 1.0195, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.369198312236287, | |
| "grad_norm": 0.052978515625, | |
| "learning_rate": 2.3093659234438266e-05, | |
| "loss": 1.0219, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.3860759493670887, | |
| "grad_norm": 0.054931640625, | |
| "learning_rate": 2.291732847944861e-05, | |
| "loss": 1.0293, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.4029535864978904, | |
| "grad_norm": 0.052734375, | |
| "learning_rate": 2.2739467854427512e-05, | |
| "loss": 0.9992, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.4198312236286919, | |
| "grad_norm": 0.05224609375, | |
| "learning_rate": 2.2560111727488e-05, | |
| "loss": 1.0254, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.4367088607594938, | |
| "grad_norm": 0.0546875, | |
| "learning_rate": 2.237929475571979e-05, | |
| "loss": 1.0148, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.4535864978902953, | |
| "grad_norm": 0.055419921875, | |
| "learning_rate": 2.219705187849254e-05, | |
| "loss": 1.0228, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.4704641350210972, | |
| "grad_norm": 0.05810546875, | |
| "learning_rate": 2.2013418310704422e-05, | |
| "loss": 1.021, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.4873417721518987, | |
| "grad_norm": 0.0537109375, | |
| "learning_rate": 2.1828429535977585e-05, | |
| "loss": 1.0352, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.5042194092827004, | |
| "grad_norm": 0.054931640625, | |
| "learning_rate": 2.1642121299801594e-05, | |
| "loss": 1.0105, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.5042194092827004, | |
| "eval_loss": 1.0232045650482178, | |
| "eval_runtime": 74.0589, | |
| "eval_samples_per_second": 13.908, | |
| "eval_steps_per_second": 13.908, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.521097046413502, | |
| "grad_norm": 0.054931640625, | |
| "learning_rate": 2.1454529602626336e-05, | |
| "loss": 1.0051, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.5379746835443038, | |
| "grad_norm": 0.0546875, | |
| "learning_rate": 2.126569069290562e-05, | |
| "loss": 1.023, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.5548523206751055, | |
| "grad_norm": 0.0546875, | |
| "learning_rate": 2.107564106009286e-05, | |
| "loss": 1.012, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.5717299578059072, | |
| "grad_norm": 0.0546875, | |
| "learning_rate": 2.0884417427590217e-05, | |
| "loss": 1.0136, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.5886075949367089, | |
| "grad_norm": 0.0546875, | |
| "learning_rate": 2.0692056745652483e-05, | |
| "loss": 1.0194, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.6054852320675106, | |
| "grad_norm": 0.0556640625, | |
| "learning_rate": 2.0498596184247196e-05, | |
| "loss": 1.0089, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.6223628691983123, | |
| "grad_norm": 0.054931640625, | |
| "learning_rate": 2.030407312587224e-05, | |
| "loss": 1.0226, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.6392405063291138, | |
| "grad_norm": 0.058349609375, | |
| "learning_rate": 2.010852515833242e-05, | |
| "loss": 1.0219, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.6561181434599157, | |
| "grad_norm": 0.0556640625, | |
| "learning_rate": 1.9911990067476336e-05, | |
| "loss": 1.0035, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.6729957805907172, | |
| "grad_norm": 0.055908203125, | |
| "learning_rate": 1.9714505829895004e-05, | |
| "loss": 1.0052, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.689873417721519, | |
| "grad_norm": 0.05712890625, | |
| "learning_rate": 1.951611060558363e-05, | |
| "loss": 1.0175, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.7067510548523206, | |
| "grad_norm": 0.056396484375, | |
| "learning_rate": 1.9316842730567902e-05, | |
| "loss": 1.0099, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.7236286919831225, | |
| "grad_norm": 0.05615234375, | |
| "learning_rate": 1.9116740709496334e-05, | |
| "loss": 0.998, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.740506329113924, | |
| "grad_norm": 0.05615234375, | |
| "learning_rate": 1.8915843208199967e-05, | |
| "loss": 0.996, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.7573839662447257, | |
| "grad_norm": 0.058837890625, | |
| "learning_rate": 1.8714189046220946e-05, | |
| "loss": 1.009, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.7742616033755274, | |
| "grad_norm": 0.059326171875, | |
| "learning_rate": 1.851181718931141e-05, | |
| "loss": 1.0127, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.7911392405063291, | |
| "grad_norm": 0.0556640625, | |
| "learning_rate": 1.830876674190411e-05, | |
| "loss": 1.0107, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.8080168776371308, | |
| "grad_norm": 0.06201171875, | |
| "learning_rate": 1.8105076939556238e-05, | |
| "loss": 1.0264, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.8248945147679325, | |
| "grad_norm": 0.056884765625, | |
| "learning_rate": 1.790078714136792e-05, | |
| "loss": 1.0068, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.8417721518987342, | |
| "grad_norm": 0.056640625, | |
| "learning_rate": 1.769593682237682e-05, | |
| "loss": 1.0094, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.8586497890295357, | |
| "grad_norm": 0.057861328125, | |
| "learning_rate": 1.7490565565930382e-05, | |
| "loss": 1.0135, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.8755274261603376, | |
| "grad_norm": 0.05859375, | |
| "learning_rate": 1.7284713056037074e-05, | |
| "loss": 0.993, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.8924050632911391, | |
| "grad_norm": 0.056884765625, | |
| "learning_rate": 1.7078419069698283e-05, | |
| "loss": 1.015, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.909282700421941, | |
| "grad_norm": 0.055908203125, | |
| "learning_rate": 1.687172346922213e-05, | |
| "loss": 1.0043, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.9261603375527425, | |
| "grad_norm": 0.05859375, | |
| "learning_rate": 1.6664666194520873e-05, | |
| "loss": 0.9959, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.9430379746835444, | |
| "grad_norm": 0.0625, | |
| "learning_rate": 1.645728725539329e-05, | |
| "loss": 1.0177, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.959915611814346, | |
| "grad_norm": 0.05810546875, | |
| "learning_rate": 1.6249626723793572e-05, | |
| "loss": 1.033, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.9767932489451476, | |
| "grad_norm": 0.059326171875, | |
| "learning_rate": 1.6041724726088187e-05, | |
| "loss": 1.0155, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.9936708860759493, | |
| "grad_norm": 0.060791015625, | |
| "learning_rate": 1.5833621435302247e-05, | |
| "loss": 1.0167, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 2.010548523206751, | |
| "grad_norm": 0.0595703125, | |
| "learning_rate": 1.5625357063356825e-05, | |
| "loss": 1.0082, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.010548523206751, | |
| "eval_loss": 1.0127062797546387, | |
| "eval_runtime": 74.0711, | |
| "eval_samples_per_second": 13.906, | |
| "eval_steps_per_second": 13.906, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0147679324894514, | |
| "grad_norm": 0.1865234375, | |
| "learning_rate": 1.541697185329881e-05, | |
| "loss": 1.6592, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 2.0316455696202533, | |
| "grad_norm": 0.0595703125, | |
| "learning_rate": 1.5208506071524727e-05, | |
| "loss": 1.0041, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.048523206751055, | |
| "grad_norm": 0.059326171875, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.0116, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.0654008438818567, | |
| "grad_norm": 0.05859375, | |
| "learning_rate": 1.4791493928475275e-05, | |
| "loss": 1.0026, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.0822784810126582, | |
| "grad_norm": 0.05810546875, | |
| "learning_rate": 1.4583028146701191e-05, | |
| "loss": 1.0122, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.0991561181434597, | |
| "grad_norm": 0.06005859375, | |
| "learning_rate": 1.437464293664318e-05, | |
| "loss": 1.0024, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.1160337552742616, | |
| "grad_norm": 0.060546875, | |
| "learning_rate": 1.4166378564697757e-05, | |
| "loss": 1.0092, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 2.132911392405063, | |
| "grad_norm": 0.05908203125, | |
| "learning_rate": 1.3958275273911812e-05, | |
| "loss": 1.0048, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.149789029535865, | |
| "grad_norm": 0.058837890625, | |
| "learning_rate": 1.375037327620643e-05, | |
| "loss": 0.9921, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.1666666666666665, | |
| "grad_norm": 0.06005859375, | |
| "learning_rate": 1.3542712744606712e-05, | |
| "loss": 1.0117, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.1835443037974684, | |
| "grad_norm": 0.05859375, | |
| "learning_rate": 1.3335333805479126e-05, | |
| "loss": 0.9965, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 2.20042194092827, | |
| "grad_norm": 0.059814453125, | |
| "learning_rate": 1.3128276530777874e-05, | |
| "loss": 1.0108, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.217299578059072, | |
| "grad_norm": 0.060791015625, | |
| "learning_rate": 1.292158093030172e-05, | |
| "loss": 1.0029, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 2.2341772151898733, | |
| "grad_norm": 0.058349609375, | |
| "learning_rate": 1.2715286943962925e-05, | |
| "loss": 0.9958, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.2510548523206753, | |
| "grad_norm": 0.05908203125, | |
| "learning_rate": 1.2509434434069625e-05, | |
| "loss": 1.0054, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.2679324894514767, | |
| "grad_norm": 0.0576171875, | |
| "learning_rate": 1.2304063177623182e-05, | |
| "loss": 0.9837, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.2848101265822787, | |
| "grad_norm": 0.060302734375, | |
| "learning_rate": 1.2099212858632083e-05, | |
| "loss": 1.0014, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 2.30168776371308, | |
| "grad_norm": 0.0595703125, | |
| "learning_rate": 1.1894923060443763e-05, | |
| "loss": 0.9816, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.318565400843882, | |
| "grad_norm": 0.0595703125, | |
| "learning_rate": 1.169123325809589e-05, | |
| "loss": 1.0021, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 2.3354430379746836, | |
| "grad_norm": 0.05859375, | |
| "learning_rate": 1.1488182810688593e-05, | |
| "loss": 1.0005, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.352320675105485, | |
| "grad_norm": 0.06103515625, | |
| "learning_rate": 1.1285810953779057e-05, | |
| "loss": 1.0167, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.369198312236287, | |
| "grad_norm": 0.059814453125, | |
| "learning_rate": 1.1084156791800036e-05, | |
| "loss": 1.0146, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.3860759493670884, | |
| "grad_norm": 0.05859375, | |
| "learning_rate": 1.0883259290503665e-05, | |
| "loss": 1.0024, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 2.4029535864978904, | |
| "grad_norm": 0.0576171875, | |
| "learning_rate": 1.0683157269432097e-05, | |
| "loss": 0.9959, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.419831223628692, | |
| "grad_norm": 0.060546875, | |
| "learning_rate": 1.0483889394416373e-05, | |
| "loss": 1.0059, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.4367088607594938, | |
| "grad_norm": 0.06396484375, | |
| "learning_rate": 1.0285494170104996e-05, | |
| "loss": 0.983, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.4535864978902953, | |
| "grad_norm": 0.06005859375, | |
| "learning_rate": 1.0088009932523664e-05, | |
| "loss": 1.0116, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.470464135021097, | |
| "grad_norm": 0.061279296875, | |
| "learning_rate": 9.891474841667585e-06, | |
| "loss": 1.0136, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.4873417721518987, | |
| "grad_norm": 0.057861328125, | |
| "learning_rate": 9.695926874127765e-06, | |
| "loss": 0.9937, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 2.5042194092827, | |
| "grad_norm": 0.0595703125, | |
| "learning_rate": 9.501403815752813e-06, | |
| "loss": 0.9946, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.5042194092827, | |
| "eval_loss": 1.0074498653411865, | |
| "eval_runtime": 74.0482, | |
| "eval_samples_per_second": 13.91, | |
| "eval_steps_per_second": 13.91, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 236, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 30, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.218043458650112e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |