| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.779220779220779, | |
| "eval_steps": 100000, | |
| "global_step": 368, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012987012987012988, | |
| "grad_norm": 2.8171603240352896, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5466, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025974025974025976, | |
| "grad_norm": 2.8001921525321785, | |
| "learning_rate": 9.973958333333335e-06, | |
| "loss": 0.547, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03896103896103896, | |
| "grad_norm": 1.5392157012941012, | |
| "learning_rate": 9.947916666666667e-06, | |
| "loss": 0.459, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05194805194805195, | |
| "grad_norm": 1.1573857414234903, | |
| "learning_rate": 9.921875e-06, | |
| "loss": 0.4574, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06493506493506493, | |
| "grad_norm": 0.8995358249149084, | |
| "learning_rate": 9.895833333333334e-06, | |
| "loss": 0.421, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07792207792207792, | |
| "grad_norm": 0.9904798146163455, | |
| "learning_rate": 9.869791666666667e-06, | |
| "loss": 0.3695, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 0.9283957441209373, | |
| "learning_rate": 9.84375e-06, | |
| "loss": 0.3627, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1038961038961039, | |
| "grad_norm": 0.7771365268975639, | |
| "learning_rate": 9.817708333333334e-06, | |
| "loss": 0.3576, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11688311688311688, | |
| "grad_norm": 0.8022346587811421, | |
| "learning_rate": 9.791666666666666e-06, | |
| "loss": 0.3191, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12987012987012986, | |
| "grad_norm": 0.819398725227865, | |
| "learning_rate": 9.765625e-06, | |
| "loss": 0.3287, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.6805869638028169, | |
| "learning_rate": 9.739583333333334e-06, | |
| "loss": 0.3184, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15584415584415584, | |
| "grad_norm": 0.5977289690207203, | |
| "learning_rate": 9.713541666666668e-06, | |
| "loss": 0.3123, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16883116883116883, | |
| "grad_norm": 0.6566097354029716, | |
| "learning_rate": 9.6875e-06, | |
| "loss": 0.3023, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 0.6239198357102247, | |
| "learning_rate": 9.661458333333334e-06, | |
| "loss": 0.2982, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19480519480519481, | |
| "grad_norm": 0.5689846226409981, | |
| "learning_rate": 9.635416666666668e-06, | |
| "loss": 0.3, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2077922077922078, | |
| "grad_norm": 0.5003921754161651, | |
| "learning_rate": 9.609375000000001e-06, | |
| "loss": 0.2806, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22077922077922077, | |
| "grad_norm": 0.4669430776472446, | |
| "learning_rate": 9.583333333333335e-06, | |
| "loss": 0.2712, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23376623376623376, | |
| "grad_norm": 0.4464962776593643, | |
| "learning_rate": 9.557291666666667e-06, | |
| "loss": 0.2649, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24675324675324675, | |
| "grad_norm": 0.4429858692736543, | |
| "learning_rate": 9.531250000000001e-06, | |
| "loss": 0.2709, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "grad_norm": 0.4534349349480874, | |
| "learning_rate": 9.505208333333335e-06, | |
| "loss": 0.2659, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 0.45604692611068276, | |
| "learning_rate": 9.479166666666667e-06, | |
| "loss": 0.274, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 0.42386666170861903, | |
| "learning_rate": 9.453125000000001e-06, | |
| "loss": 0.2432, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2987012987012987, | |
| "grad_norm": 0.4539418581699697, | |
| "learning_rate": 9.427083333333335e-06, | |
| "loss": 0.2479, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3116883116883117, | |
| "grad_norm": 0.36873765590858, | |
| "learning_rate": 9.401041666666667e-06, | |
| "loss": 0.2533, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3246753246753247, | |
| "grad_norm": 0.3597660839493326, | |
| "learning_rate": 9.375000000000001e-06, | |
| "loss": 0.2427, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33766233766233766, | |
| "grad_norm": 0.43380755500127693, | |
| "learning_rate": 9.348958333333335e-06, | |
| "loss": 0.2629, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.35064935064935066, | |
| "grad_norm": 0.4124812851086015, | |
| "learning_rate": 9.322916666666667e-06, | |
| "loss": 0.2555, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 0.3899208758432942, | |
| "learning_rate": 9.296875e-06, | |
| "loss": 0.2385, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.37662337662337664, | |
| "grad_norm": 0.4307637034312358, | |
| "learning_rate": 9.270833333333334e-06, | |
| "loss": 0.2676, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.38961038961038963, | |
| "grad_norm": 0.381920816609879, | |
| "learning_rate": 9.244791666666667e-06, | |
| "loss": 0.2366, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4025974025974026, | |
| "grad_norm": 0.3816394656089062, | |
| "learning_rate": 9.21875e-06, | |
| "loss": 0.2321, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4155844155844156, | |
| "grad_norm": 0.42534009456351374, | |
| "learning_rate": 9.192708333333334e-06, | |
| "loss": 0.265, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 0.37160388698301566, | |
| "learning_rate": 9.166666666666666e-06, | |
| "loss": 0.2373, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.44155844155844154, | |
| "grad_norm": 0.3801489729504126, | |
| "learning_rate": 9.140625e-06, | |
| "loss": 0.2414, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 0.3913349306860418, | |
| "learning_rate": 9.114583333333334e-06, | |
| "loss": 0.2206, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4675324675324675, | |
| "grad_norm": 0.3943320977947317, | |
| "learning_rate": 9.088541666666666e-06, | |
| "loss": 0.223, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4805194805194805, | |
| "grad_norm": 0.3702281679651669, | |
| "learning_rate": 9.0625e-06, | |
| "loss": 0.2147, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4935064935064935, | |
| "grad_norm": 0.422823856947034, | |
| "learning_rate": 9.036458333333334e-06, | |
| "loss": 0.2493, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5064935064935064, | |
| "grad_norm": 0.38040718111635613, | |
| "learning_rate": 9.010416666666668e-06, | |
| "loss": 0.2245, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5194805194805194, | |
| "grad_norm": 0.3440649156844092, | |
| "learning_rate": 8.984375000000002e-06, | |
| "loss": 0.2216, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5324675324675324, | |
| "grad_norm": 0.3646349376051012, | |
| "learning_rate": 8.958333333333334e-06, | |
| "loss": 0.2127, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 0.34399756355860645, | |
| "learning_rate": 8.932291666666668e-06, | |
| "loss": 0.2148, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5584415584415584, | |
| "grad_norm": 0.3823461645884333, | |
| "learning_rate": 8.906250000000001e-06, | |
| "loss": 0.2367, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.3396475181827773, | |
| "learning_rate": 8.880208333333335e-06, | |
| "loss": 0.2097, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5844155844155844, | |
| "grad_norm": 0.40580965210317627, | |
| "learning_rate": 8.854166666666667e-06, | |
| "loss": 0.2539, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5974025974025974, | |
| "grad_norm": 0.3720924077531135, | |
| "learning_rate": 8.828125000000001e-06, | |
| "loss": 0.2416, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6103896103896104, | |
| "grad_norm": 0.36386894867601904, | |
| "learning_rate": 8.802083333333335e-06, | |
| "loss": 0.2159, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6233766233766234, | |
| "grad_norm": 0.39963494878899575, | |
| "learning_rate": 8.776041666666667e-06, | |
| "loss": 0.2155, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": 0.41491580966165253, | |
| "learning_rate": 8.750000000000001e-06, | |
| "loss": 0.2441, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6493506493506493, | |
| "grad_norm": 0.413722874540919, | |
| "learning_rate": 8.723958333333335e-06, | |
| "loss": 0.2411, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6623376623376623, | |
| "grad_norm": 0.3627710473819897, | |
| "learning_rate": 8.697916666666667e-06, | |
| "loss": 0.2032, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.6753246753246753, | |
| "grad_norm": 0.37183990680520124, | |
| "learning_rate": 8.671875e-06, | |
| "loss": 0.2297, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.6883116883116883, | |
| "grad_norm": 0.3447910113593886, | |
| "learning_rate": 8.645833333333335e-06, | |
| "loss": 0.2152, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.7012987012987013, | |
| "grad_norm": 0.3746990091470779, | |
| "learning_rate": 8.619791666666667e-06, | |
| "loss": 0.2196, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.38360093812511664, | |
| "learning_rate": 8.59375e-06, | |
| "loss": 0.2351, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.3401850780087419, | |
| "learning_rate": 8.567708333333334e-06, | |
| "loss": 0.1948, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.7402597402597403, | |
| "grad_norm": 0.3341353144174157, | |
| "learning_rate": 8.541666666666666e-06, | |
| "loss": 0.1985, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.7532467532467533, | |
| "grad_norm": 0.3317473111284822, | |
| "learning_rate": 8.515625e-06, | |
| "loss": 0.2019, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.7662337662337663, | |
| "grad_norm": 0.37322280586801393, | |
| "learning_rate": 8.489583333333334e-06, | |
| "loss": 0.2258, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.7792207792207793, | |
| "grad_norm": 0.36560124214432044, | |
| "learning_rate": 8.463541666666666e-06, | |
| "loss": 0.2188, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7922077922077922, | |
| "grad_norm": 0.3372344746230244, | |
| "learning_rate": 8.4375e-06, | |
| "loss": 0.2157, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.8051948051948052, | |
| "grad_norm": 0.3486634994045839, | |
| "learning_rate": 8.411458333333334e-06, | |
| "loss": 0.202, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.8181818181818182, | |
| "grad_norm": 0.39190266385589323, | |
| "learning_rate": 8.385416666666668e-06, | |
| "loss": 0.2148, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.8311688311688312, | |
| "grad_norm": 0.36845516731632094, | |
| "learning_rate": 8.359375e-06, | |
| "loss": 0.2184, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.8441558441558441, | |
| "grad_norm": 0.35457910296524253, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.2149, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.3603241548710575, | |
| "learning_rate": 8.307291666666668e-06, | |
| "loss": 0.2155, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.8701298701298701, | |
| "grad_norm": 0.36738480430355874, | |
| "learning_rate": 8.281250000000001e-06, | |
| "loss": 0.2262, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.8831168831168831, | |
| "grad_norm": 0.3994418788798323, | |
| "learning_rate": 8.255208333333335e-06, | |
| "loss": 0.2237, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.8961038961038961, | |
| "grad_norm": 0.3818265307209604, | |
| "learning_rate": 8.229166666666667e-06, | |
| "loss": 0.2134, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.3498820594838212, | |
| "learning_rate": 8.203125000000001e-06, | |
| "loss": 0.2069, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.922077922077922, | |
| "grad_norm": 0.385917668930501, | |
| "learning_rate": 8.177083333333335e-06, | |
| "loss": 0.2123, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.935064935064935, | |
| "grad_norm": 0.39236894265571665, | |
| "learning_rate": 8.151041666666667e-06, | |
| "loss": 0.2234, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.948051948051948, | |
| "grad_norm": 0.3725234037920641, | |
| "learning_rate": 8.125000000000001e-06, | |
| "loss": 0.2066, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.961038961038961, | |
| "grad_norm": 0.35880219297664784, | |
| "learning_rate": 8.098958333333335e-06, | |
| "loss": 0.1897, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.974025974025974, | |
| "grad_norm": 0.3907765260625405, | |
| "learning_rate": 8.072916666666667e-06, | |
| "loss": 0.2294, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.987012987012987, | |
| "grad_norm": 0.36488776593694006, | |
| "learning_rate": 8.046875e-06, | |
| "loss": 0.1958, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.3787789187575852, | |
| "learning_rate": 8.020833333333335e-06, | |
| "loss": 0.2067, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.0129870129870129, | |
| "grad_norm": 0.448465153413621, | |
| "learning_rate": 7.994791666666667e-06, | |
| "loss": 0.1244, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.025974025974026, | |
| "grad_norm": 0.3915974513800719, | |
| "learning_rate": 7.96875e-06, | |
| "loss": 0.1243, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.0389610389610389, | |
| "grad_norm": 0.3963769912247312, | |
| "learning_rate": 7.942708333333334e-06, | |
| "loss": 0.1172, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.051948051948052, | |
| "grad_norm": 0.6014772610010978, | |
| "learning_rate": 7.916666666666667e-06, | |
| "loss": 0.1342, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.0649350649350648, | |
| "grad_norm": 0.36513022825436714, | |
| "learning_rate": 7.890625e-06, | |
| "loss": 0.1155, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.077922077922078, | |
| "grad_norm": 0.36495385435491967, | |
| "learning_rate": 7.864583333333334e-06, | |
| "loss": 0.1278, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 0.3817117188167101, | |
| "learning_rate": 7.838541666666666e-06, | |
| "loss": 0.1294, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.103896103896104, | |
| "grad_norm": 0.3466875502600336, | |
| "learning_rate": 7.8125e-06, | |
| "loss": 0.1187, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.1168831168831168, | |
| "grad_norm": 0.38224176701280815, | |
| "learning_rate": 7.786458333333334e-06, | |
| "loss": 0.1163, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.12987012987013, | |
| "grad_norm": 0.387717741867272, | |
| "learning_rate": 7.760416666666666e-06, | |
| "loss": 0.1229, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.33922354465727605, | |
| "learning_rate": 7.734375e-06, | |
| "loss": 0.1026, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.155844155844156, | |
| "grad_norm": 0.35409301762559464, | |
| "learning_rate": 7.708333333333334e-06, | |
| "loss": 0.1208, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.1688311688311688, | |
| "grad_norm": 0.4114669310411066, | |
| "learning_rate": 7.682291666666668e-06, | |
| "loss": 0.138, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.1818181818181819, | |
| "grad_norm": 0.3522471695287209, | |
| "learning_rate": 7.656250000000001e-06, | |
| "loss": 0.1268, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.1948051948051948, | |
| "grad_norm": 0.3494758184949061, | |
| "learning_rate": 7.630208333333334e-06, | |
| "loss": 0.1118, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.2077922077922079, | |
| "grad_norm": 0.35673580541279293, | |
| "learning_rate": 7.6041666666666666e-06, | |
| "loss": 0.111, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.2207792207792207, | |
| "grad_norm": 0.2877699742066818, | |
| "learning_rate": 7.578125e-06, | |
| "loss": 0.1024, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.2337662337662338, | |
| "grad_norm": 0.36809061483198696, | |
| "learning_rate": 7.552083333333334e-06, | |
| "loss": 0.125, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.2467532467532467, | |
| "grad_norm": 0.3326924572780158, | |
| "learning_rate": 7.526041666666667e-06, | |
| "loss": 0.1165, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.2597402597402598, | |
| "grad_norm": 0.3381064907954975, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.1242, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.2727272727272727, | |
| "grad_norm": 0.31808537453343166, | |
| "learning_rate": 7.473958333333334e-06, | |
| "loss": 0.1194, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": 0.3338293488215449, | |
| "learning_rate": 7.447916666666667e-06, | |
| "loss": 0.1045, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.2987012987012987, | |
| "grad_norm": 0.32638382374328245, | |
| "learning_rate": 7.421875000000001e-06, | |
| "loss": 0.1274, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.3116883116883118, | |
| "grad_norm": 0.3798687835449094, | |
| "learning_rate": 7.395833333333335e-06, | |
| "loss": 0.1216, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.3246753246753247, | |
| "grad_norm": 0.42118782006430655, | |
| "learning_rate": 7.369791666666667e-06, | |
| "loss": 0.1116, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.3376623376623376, | |
| "grad_norm": 0.31491431320109803, | |
| "learning_rate": 7.343750000000001e-06, | |
| "loss": 0.123, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.3506493506493507, | |
| "grad_norm": 0.31006216567911504, | |
| "learning_rate": 7.3177083333333345e-06, | |
| "loss": 0.1186, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 0.32515923422393395, | |
| "learning_rate": 7.291666666666667e-06, | |
| "loss": 0.1069, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.3766233766233766, | |
| "grad_norm": 0.3258624400110308, | |
| "learning_rate": 7.265625e-06, | |
| "loss": 0.0925, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.3896103896103895, | |
| "grad_norm": 0.3147044898639944, | |
| "learning_rate": 7.239583333333334e-06, | |
| "loss": 0.1114, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.4025974025974026, | |
| "grad_norm": 0.3155522217588101, | |
| "learning_rate": 7.213541666666667e-06, | |
| "loss": 0.1237, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.4155844155844157, | |
| "grad_norm": 0.3144003636320752, | |
| "learning_rate": 7.1875e-06, | |
| "loss": 0.1159, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.32254719268793725, | |
| "learning_rate": 7.161458333333334e-06, | |
| "loss": 0.1196, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.4415584415584415, | |
| "grad_norm": 0.315615751768773, | |
| "learning_rate": 7.135416666666667e-06, | |
| "loss": 0.1121, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 0.2995055345846169, | |
| "learning_rate": 7.109375000000001e-06, | |
| "loss": 0.1199, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.4675324675324675, | |
| "grad_norm": 0.3457518743206924, | |
| "learning_rate": 7.083333333333335e-06, | |
| "loss": 0.1262, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.4805194805194806, | |
| "grad_norm": 0.34216271471145815, | |
| "learning_rate": 7.057291666666667e-06, | |
| "loss": 0.1067, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.4935064935064934, | |
| "grad_norm": 0.3178295536529888, | |
| "learning_rate": 7.031250000000001e-06, | |
| "loss": 0.1202, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.5064935064935066, | |
| "grad_norm": 0.2819573454273538, | |
| "learning_rate": 7.0052083333333345e-06, | |
| "loss": 0.1033, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.5194805194805194, | |
| "grad_norm": 0.32378485295884113, | |
| "learning_rate": 6.979166666666667e-06, | |
| "loss": 0.117, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.5324675324675323, | |
| "grad_norm": 0.3154734102111175, | |
| "learning_rate": 6.9531250000000004e-06, | |
| "loss": 0.1089, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.5454545454545454, | |
| "grad_norm": 0.3112595772562475, | |
| "learning_rate": 6.927083333333334e-06, | |
| "loss": 0.1131, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.5584415584415585, | |
| "grad_norm": 0.308567184284047, | |
| "learning_rate": 6.901041666666667e-06, | |
| "loss": 0.0981, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.5714285714285714, | |
| "grad_norm": 0.2941894268668758, | |
| "learning_rate": 6.875e-06, | |
| "loss": 0.0992, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.5844155844155843, | |
| "grad_norm": 0.3244832758495866, | |
| "learning_rate": 6.848958333333334e-06, | |
| "loss": 0.1151, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.5974025974025974, | |
| "grad_norm": 0.3486204249378559, | |
| "learning_rate": 6.822916666666667e-06, | |
| "loss": 0.1144, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.6103896103896105, | |
| "grad_norm": 0.3108839874338576, | |
| "learning_rate": 6.796875000000001e-06, | |
| "loss": 0.1166, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.6233766233766234, | |
| "grad_norm": 0.3362850203366801, | |
| "learning_rate": 6.770833333333334e-06, | |
| "loss": 0.1166, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.6363636363636362, | |
| "grad_norm": 0.3001509180382928, | |
| "learning_rate": 6.744791666666667e-06, | |
| "loss": 0.1105, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.6493506493506493, | |
| "grad_norm": 0.2997092451007753, | |
| "learning_rate": 6.718750000000001e-06, | |
| "loss": 0.1086, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.6623376623376624, | |
| "grad_norm": 0.3427204611958163, | |
| "learning_rate": 6.6927083333333345e-06, | |
| "loss": 0.1054, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.6753246753246753, | |
| "grad_norm": 0.2994776086256174, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.1154, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.6883116883116882, | |
| "grad_norm": 0.31431249708262365, | |
| "learning_rate": 6.6406250000000005e-06, | |
| "loss": 0.1227, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.7012987012987013, | |
| "grad_norm": 0.311578248576694, | |
| "learning_rate": 6.614583333333334e-06, | |
| "loss": 0.1084, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.3316176770331044, | |
| "learning_rate": 6.5885416666666664e-06, | |
| "loss": 0.1104, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.7272727272727273, | |
| "grad_norm": 0.30426933433479547, | |
| "learning_rate": 6.5625e-06, | |
| "loss": 0.1125, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.7402597402597402, | |
| "grad_norm": 0.28043555053128094, | |
| "learning_rate": 6.536458333333334e-06, | |
| "loss": 0.0992, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.7532467532467533, | |
| "grad_norm": 0.30386469668813254, | |
| "learning_rate": 6.510416666666667e-06, | |
| "loss": 0.1091, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.7662337662337664, | |
| "grad_norm": 0.3224355180252757, | |
| "learning_rate": 6.484375000000001e-06, | |
| "loss": 0.1057, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.7792207792207793, | |
| "grad_norm": 0.33241428871080214, | |
| "learning_rate": 6.458333333333334e-06, | |
| "loss": 0.1059, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.7922077922077921, | |
| "grad_norm": 0.3147577283191284, | |
| "learning_rate": 6.432291666666667e-06, | |
| "loss": 0.1182, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.8051948051948052, | |
| "grad_norm": 0.3078113700946741, | |
| "learning_rate": 6.406250000000001e-06, | |
| "loss": 0.1041, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 0.29167494344756056, | |
| "learning_rate": 6.3802083333333345e-06, | |
| "loss": 0.1118, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.8311688311688312, | |
| "grad_norm": 0.3185841818138518, | |
| "learning_rate": 6.354166666666667e-06, | |
| "loss": 0.1086, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.844155844155844, | |
| "grad_norm": 0.32641774304326837, | |
| "learning_rate": 6.3281250000000005e-06, | |
| "loss": 0.1109, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.8571428571428572, | |
| "grad_norm": 0.3203734291459141, | |
| "learning_rate": 6.302083333333334e-06, | |
| "loss": 0.0955, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.87012987012987, | |
| "grad_norm": 0.2890498272171896, | |
| "learning_rate": 6.2760416666666665e-06, | |
| "loss": 0.101, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.883116883116883, | |
| "grad_norm": 0.29736342466973853, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.118, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.896103896103896, | |
| "grad_norm": 0.31984473875794944, | |
| "learning_rate": 6.223958333333334e-06, | |
| "loss": 0.1102, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.9090909090909092, | |
| "grad_norm": 0.3172704335356637, | |
| "learning_rate": 6.197916666666667e-06, | |
| "loss": 0.1082, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.922077922077922, | |
| "grad_norm": 0.2973111874066074, | |
| "learning_rate": 6.171875e-06, | |
| "loss": 0.1197, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.935064935064935, | |
| "grad_norm": 0.3095998340575272, | |
| "learning_rate": 6.145833333333334e-06, | |
| "loss": 0.1079, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.948051948051948, | |
| "grad_norm": 0.31787152770234606, | |
| "learning_rate": 6.119791666666667e-06, | |
| "loss": 0.0994, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.9610389610389611, | |
| "grad_norm": 0.28985366328378903, | |
| "learning_rate": 6.093750000000001e-06, | |
| "loss": 0.1202, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.974025974025974, | |
| "grad_norm": 0.3052098497087059, | |
| "learning_rate": 6.0677083333333346e-06, | |
| "loss": 0.1137, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.987012987012987, | |
| "grad_norm": 0.3066915552338606, | |
| "learning_rate": 6.041666666666667e-06, | |
| "loss": 0.1172, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.30629249293934785, | |
| "learning_rate": 6.0156250000000005e-06, | |
| "loss": 0.1032, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 2.012987012987013, | |
| "grad_norm": 0.35023782090844824, | |
| "learning_rate": 5.989583333333334e-06, | |
| "loss": 0.0557, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.0259740259740258, | |
| "grad_norm": 0.2862415000889261, | |
| "learning_rate": 5.9635416666666665e-06, | |
| "loss": 0.0656, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.038961038961039, | |
| "grad_norm": 0.25460716359572677, | |
| "learning_rate": 5.9375e-06, | |
| "loss": 0.0559, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 2.051948051948052, | |
| "grad_norm": 0.32189640709965023, | |
| "learning_rate": 5.911458333333334e-06, | |
| "loss": 0.0563, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 2.064935064935065, | |
| "grad_norm": 0.34761763544000046, | |
| "learning_rate": 5.885416666666667e-06, | |
| "loss": 0.0695, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 2.0779220779220777, | |
| "grad_norm": 0.2780054835792156, | |
| "learning_rate": 5.859375e-06, | |
| "loss": 0.0555, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.090909090909091, | |
| "grad_norm": 0.24032473108802174, | |
| "learning_rate": 5.833333333333334e-06, | |
| "loss": 0.0565, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 2.103896103896104, | |
| "grad_norm": 0.2950389512514924, | |
| "learning_rate": 5.807291666666667e-06, | |
| "loss": 0.0566, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.116883116883117, | |
| "grad_norm": 0.22432748520418566, | |
| "learning_rate": 5.781250000000001e-06, | |
| "loss": 0.056, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 2.1298701298701297, | |
| "grad_norm": 0.24784953484105113, | |
| "learning_rate": 5.755208333333335e-06, | |
| "loss": 0.0479, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 2.142857142857143, | |
| "grad_norm": 0.2702464812816263, | |
| "learning_rate": 5.729166666666667e-06, | |
| "loss": 0.0591, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.155844155844156, | |
| "grad_norm": 0.24201294320174244, | |
| "learning_rate": 5.7031250000000006e-06, | |
| "loss": 0.0599, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 2.168831168831169, | |
| "grad_norm": 0.27746964323966916, | |
| "learning_rate": 5.677083333333334e-06, | |
| "loss": 0.0533, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 2.1818181818181817, | |
| "grad_norm": 0.2897264068192118, | |
| "learning_rate": 5.6510416666666665e-06, | |
| "loss": 0.053, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.1948051948051948, | |
| "grad_norm": 0.27265023383714393, | |
| "learning_rate": 5.625e-06, | |
| "loss": 0.0663, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 2.207792207792208, | |
| "grad_norm": 0.23815823204180192, | |
| "learning_rate": 5.598958333333334e-06, | |
| "loss": 0.0553, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.220779220779221, | |
| "grad_norm": 0.27451200943828685, | |
| "learning_rate": 5.572916666666667e-06, | |
| "loss": 0.0628, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 2.2337662337662336, | |
| "grad_norm": 0.24756583000652174, | |
| "learning_rate": 5.546875e-06, | |
| "loss": 0.0556, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.2467532467532467, | |
| "grad_norm": 0.2544315370018155, | |
| "learning_rate": 5.520833333333334e-06, | |
| "loss": 0.0578, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 2.25974025974026, | |
| "grad_norm": 0.23275351662072738, | |
| "learning_rate": 5.494791666666667e-06, | |
| "loss": 0.0538, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 0.2618251778102254, | |
| "learning_rate": 5.468750000000001e-06, | |
| "loss": 0.0658, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.25188249686135555, | |
| "learning_rate": 5.442708333333334e-06, | |
| "loss": 0.0486, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 2.2987012987012987, | |
| "grad_norm": 0.28055649582376346, | |
| "learning_rate": 5.416666666666667e-06, | |
| "loss": 0.0626, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 2.311688311688312, | |
| "grad_norm": 0.24599632120103626, | |
| "learning_rate": 5.390625000000001e-06, | |
| "loss": 0.0583, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 2.324675324675325, | |
| "grad_norm": 0.27127338612129825, | |
| "learning_rate": 5.364583333333334e-06, | |
| "loss": 0.0586, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 2.3376623376623376, | |
| "grad_norm": 0.24409520592231887, | |
| "learning_rate": 5.3385416666666666e-06, | |
| "loss": 0.0546, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.3506493506493507, | |
| "grad_norm": 0.2730534578010532, | |
| "learning_rate": 5.3125e-06, | |
| "loss": 0.049, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 2.3636363636363638, | |
| "grad_norm": 0.3063550918757163, | |
| "learning_rate": 5.286458333333334e-06, | |
| "loss": 0.0626, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 2.3766233766233764, | |
| "grad_norm": 0.24974475183252906, | |
| "learning_rate": 5.260416666666666e-06, | |
| "loss": 0.0644, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 2.3896103896103895, | |
| "grad_norm": 0.27100592128125456, | |
| "learning_rate": 5.234375e-06, | |
| "loss": 0.0585, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 2.4025974025974026, | |
| "grad_norm": 0.2814186690984644, | |
| "learning_rate": 5.208333333333334e-06, | |
| "loss": 0.0582, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.4155844155844157, | |
| "grad_norm": 0.25261977006702085, | |
| "learning_rate": 5.182291666666667e-06, | |
| "loss": 0.0518, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 2.4285714285714284, | |
| "grad_norm": 0.2657725313570488, | |
| "learning_rate": 5.156250000000001e-06, | |
| "loss": 0.0578, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 2.4415584415584415, | |
| "grad_norm": 0.2546037193133823, | |
| "learning_rate": 5.130208333333334e-06, | |
| "loss": 0.0538, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 2.4545454545454546, | |
| "grad_norm": 0.281253389764468, | |
| "learning_rate": 5.104166666666667e-06, | |
| "loss": 0.0635, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 2.4675324675324677, | |
| "grad_norm": 0.26338794462461806, | |
| "learning_rate": 5.078125000000001e-06, | |
| "loss": 0.0562, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.4805194805194803, | |
| "grad_norm": 0.24941779389697705, | |
| "learning_rate": 5.0520833333333344e-06, | |
| "loss": 0.0556, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 2.4935064935064934, | |
| "grad_norm": 0.24447967903315854, | |
| "learning_rate": 5.026041666666667e-06, | |
| "loss": 0.0583, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 2.5064935064935066, | |
| "grad_norm": 0.23904209946561095, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0466, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 2.5194805194805197, | |
| "grad_norm": 0.2647184458213586, | |
| "learning_rate": 4.973958333333333e-06, | |
| "loss": 0.0631, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 2.5324675324675323, | |
| "grad_norm": 0.22821154672037003, | |
| "learning_rate": 4.947916666666667e-06, | |
| "loss": 0.0473, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.5454545454545454, | |
| "grad_norm": 0.2626904902801862, | |
| "learning_rate": 4.921875e-06, | |
| "loss": 0.0506, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 2.5584415584415585, | |
| "grad_norm": 0.24930087318211805, | |
| "learning_rate": 4.895833333333333e-06, | |
| "loss": 0.0572, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 0.2481390560509281, | |
| "learning_rate": 4.869791666666667e-06, | |
| "loss": 0.0555, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 2.5844155844155843, | |
| "grad_norm": 0.2877573573303393, | |
| "learning_rate": 4.84375e-06, | |
| "loss": 0.067, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 2.5974025974025974, | |
| "grad_norm": 0.25217308853248577, | |
| "learning_rate": 4.817708333333334e-06, | |
| "loss": 0.0471, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.6103896103896105, | |
| "grad_norm": 0.24328918721469303, | |
| "learning_rate": 4.791666666666668e-06, | |
| "loss": 0.0576, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 2.6233766233766236, | |
| "grad_norm": 0.2523930869041385, | |
| "learning_rate": 4.765625000000001e-06, | |
| "loss": 0.0545, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 2.6363636363636362, | |
| "grad_norm": 0.2535471838454832, | |
| "learning_rate": 4.739583333333334e-06, | |
| "loss": 0.0625, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 2.6493506493506493, | |
| "grad_norm": 0.2712254471205784, | |
| "learning_rate": 4.7135416666666675e-06, | |
| "loss": 0.061, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 2.6623376623376624, | |
| "grad_norm": 0.26161221717819355, | |
| "learning_rate": 4.6875000000000004e-06, | |
| "loss": 0.0567, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.675324675324675, | |
| "grad_norm": 0.24838669747413192, | |
| "learning_rate": 4.661458333333333e-06, | |
| "loss": 0.0518, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 2.688311688311688, | |
| "grad_norm": 0.23966177399361988, | |
| "learning_rate": 4.635416666666667e-06, | |
| "loss": 0.0542, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 2.7012987012987013, | |
| "grad_norm": 0.24657984039301706, | |
| "learning_rate": 4.609375e-06, | |
| "loss": 0.0666, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 2.7142857142857144, | |
| "grad_norm": 0.2583103237439079, | |
| "learning_rate": 4.583333333333333e-06, | |
| "loss": 0.0545, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 2.7272727272727275, | |
| "grad_norm": 0.2562617620737508, | |
| "learning_rate": 4.557291666666667e-06, | |
| "loss": 0.0558, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.74025974025974, | |
| "grad_norm": 0.23308521833875492, | |
| "learning_rate": 4.53125e-06, | |
| "loss": 0.0496, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 2.7532467532467533, | |
| "grad_norm": 0.24092047046705078, | |
| "learning_rate": 4.505208333333334e-06, | |
| "loss": 0.0596, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.7662337662337664, | |
| "grad_norm": 0.27349855814243884, | |
| "learning_rate": 4.479166666666667e-06, | |
| "loss": 0.0468, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 2.779220779220779, | |
| "grad_norm": 0.2275758123203626, | |
| "learning_rate": 4.453125000000001e-06, | |
| "loss": 0.056, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 2.792207792207792, | |
| "grad_norm": 0.266884630074945, | |
| "learning_rate": 4.427083333333334e-06, | |
| "loss": 0.0571, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.8051948051948052, | |
| "grad_norm": 0.25024069366637947, | |
| "learning_rate": 4.4010416666666675e-06, | |
| "loss": 0.0642, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.8181818181818183, | |
| "grad_norm": 0.24857662695800786, | |
| "learning_rate": 4.3750000000000005e-06, | |
| "loss": 0.0486, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 2.8311688311688314, | |
| "grad_norm": 0.25080858473278267, | |
| "learning_rate": 4.3489583333333334e-06, | |
| "loss": 0.0584, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 2.844155844155844, | |
| "grad_norm": 0.24530740860883163, | |
| "learning_rate": 4.322916666666667e-06, | |
| "loss": 0.0633, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.23913022308407994, | |
| "learning_rate": 4.296875e-06, | |
| "loss": 0.0549, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.87012987012987, | |
| "grad_norm": 0.24149083025156237, | |
| "learning_rate": 4.270833333333333e-06, | |
| "loss": 0.0467, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 2.883116883116883, | |
| "grad_norm": 0.26965528602346694, | |
| "learning_rate": 4.244791666666667e-06, | |
| "loss": 0.0606, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 2.896103896103896, | |
| "grad_norm": 0.25365858810429237, | |
| "learning_rate": 4.21875e-06, | |
| "loss": 0.0694, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "grad_norm": 0.24179541312218353, | |
| "learning_rate": 4.192708333333334e-06, | |
| "loss": 0.0616, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 2.9220779220779223, | |
| "grad_norm": 0.2361020434984871, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.0476, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.935064935064935, | |
| "grad_norm": 0.27226949918910437, | |
| "learning_rate": 4.140625000000001e-06, | |
| "loss": 0.0642, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 2.948051948051948, | |
| "grad_norm": 0.2527942476147371, | |
| "learning_rate": 4.114583333333334e-06, | |
| "loss": 0.0619, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 2.961038961038961, | |
| "grad_norm": 0.24251482806607963, | |
| "learning_rate": 4.0885416666666675e-06, | |
| "loss": 0.0525, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 2.974025974025974, | |
| "grad_norm": 0.23476269808521869, | |
| "learning_rate": 4.0625000000000005e-06, | |
| "loss": 0.062, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 2.987012987012987, | |
| "grad_norm": 0.2374808258403478, | |
| "learning_rate": 4.0364583333333335e-06, | |
| "loss": 0.0505, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.24928176045345568, | |
| "learning_rate": 4.010416666666667e-06, | |
| "loss": 0.0626, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 3.012987012987013, | |
| "grad_norm": 0.22194182328876036, | |
| "learning_rate": 3.984375e-06, | |
| "loss": 0.0344, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 3.0259740259740258, | |
| "grad_norm": 0.22872923006570003, | |
| "learning_rate": 3.958333333333333e-06, | |
| "loss": 0.0413, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 3.038961038961039, | |
| "grad_norm": 0.19665583235009848, | |
| "learning_rate": 3.932291666666667e-06, | |
| "loss": 0.0287, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 3.051948051948052, | |
| "grad_norm": 0.19667069366179346, | |
| "learning_rate": 3.90625e-06, | |
| "loss": 0.0352, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 3.064935064935065, | |
| "grad_norm": 0.215711200723706, | |
| "learning_rate": 3.880208333333333e-06, | |
| "loss": 0.0333, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 3.0779220779220777, | |
| "grad_norm": 0.2313666120277444, | |
| "learning_rate": 3.854166666666667e-06, | |
| "loss": 0.0284, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 3.090909090909091, | |
| "grad_norm": 0.23091064810625503, | |
| "learning_rate": 3.828125000000001e-06, | |
| "loss": 0.0328, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 3.103896103896104, | |
| "grad_norm": 0.20452236865758217, | |
| "learning_rate": 3.8020833333333333e-06, | |
| "loss": 0.0319, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 3.116883116883117, | |
| "grad_norm": 0.2130097271956879, | |
| "learning_rate": 3.776041666666667e-06, | |
| "loss": 0.0353, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.1298701298701297, | |
| "grad_norm": 0.17171823929322136, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.0259, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 3.142857142857143, | |
| "grad_norm": 0.18378369851335255, | |
| "learning_rate": 3.7239583333333335e-06, | |
| "loss": 0.0313, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 3.155844155844156, | |
| "grad_norm": 0.1828525728293844, | |
| "learning_rate": 3.6979166666666673e-06, | |
| "loss": 0.028, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 3.168831168831169, | |
| "grad_norm": 0.19380765006793751, | |
| "learning_rate": 3.6718750000000003e-06, | |
| "loss": 0.0289, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 3.1818181818181817, | |
| "grad_norm": 0.1990094351044486, | |
| "learning_rate": 3.6458333333333333e-06, | |
| "loss": 0.027, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 3.1948051948051948, | |
| "grad_norm": 0.18792815598678744, | |
| "learning_rate": 3.619791666666667e-06, | |
| "loss": 0.0291, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 3.207792207792208, | |
| "grad_norm": 0.18192941363864568, | |
| "learning_rate": 3.59375e-06, | |
| "loss": 0.0333, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 3.220779220779221, | |
| "grad_norm": 0.19920093771078823, | |
| "learning_rate": 3.5677083333333335e-06, | |
| "loss": 0.0359, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 3.2337662337662336, | |
| "grad_norm": 0.20752665916487095, | |
| "learning_rate": 3.5416666666666673e-06, | |
| "loss": 0.0346, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 3.2467532467532467, | |
| "grad_norm": 0.19735194752925486, | |
| "learning_rate": 3.5156250000000003e-06, | |
| "loss": 0.0286, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.25974025974026, | |
| "grad_norm": 0.21107169053286765, | |
| "learning_rate": 3.4895833333333333e-06, | |
| "loss": 0.0302, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 3.2727272727272725, | |
| "grad_norm": 0.19257404946331436, | |
| "learning_rate": 3.463541666666667e-06, | |
| "loss": 0.0266, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 3.2857142857142856, | |
| "grad_norm": 0.20416526855617004, | |
| "learning_rate": 3.4375e-06, | |
| "loss": 0.0338, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 3.2987012987012987, | |
| "grad_norm": 0.16009297749675383, | |
| "learning_rate": 3.4114583333333335e-06, | |
| "loss": 0.0298, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 3.311688311688312, | |
| "grad_norm": 0.1865805004238836, | |
| "learning_rate": 3.385416666666667e-06, | |
| "loss": 0.0381, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 3.324675324675325, | |
| "grad_norm": 0.1856518020717426, | |
| "learning_rate": 3.3593750000000003e-06, | |
| "loss": 0.032, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 3.3376623376623376, | |
| "grad_norm": 0.1643615680531049, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.0261, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 3.3506493506493507, | |
| "grad_norm": 0.20350173056124413, | |
| "learning_rate": 3.307291666666667e-06, | |
| "loss": 0.0289, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 3.3636363636363638, | |
| "grad_norm": 0.1851001849213331, | |
| "learning_rate": 3.28125e-06, | |
| "loss": 0.0303, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 3.3766233766233764, | |
| "grad_norm": 0.17486718674776422, | |
| "learning_rate": 3.2552083333333335e-06, | |
| "loss": 0.0341, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.3896103896103895, | |
| "grad_norm": 0.20208654835258116, | |
| "learning_rate": 3.229166666666667e-06, | |
| "loss": 0.0292, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 3.4025974025974026, | |
| "grad_norm": 0.1879927363412167, | |
| "learning_rate": 3.2031250000000004e-06, | |
| "loss": 0.029, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 3.4155844155844157, | |
| "grad_norm": 0.2092150414129076, | |
| "learning_rate": 3.1770833333333333e-06, | |
| "loss": 0.0335, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "grad_norm": 0.1828398699501031, | |
| "learning_rate": 3.151041666666667e-06, | |
| "loss": 0.0287, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 3.4415584415584415, | |
| "grad_norm": 0.1646440626911746, | |
| "learning_rate": 3.125e-06, | |
| "loss": 0.0249, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 3.4545454545454546, | |
| "grad_norm": 0.2213658118877642, | |
| "learning_rate": 3.0989583333333336e-06, | |
| "loss": 0.0313, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 3.4675324675324677, | |
| "grad_norm": 0.19833753553756947, | |
| "learning_rate": 3.072916666666667e-06, | |
| "loss": 0.0305, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 3.4805194805194803, | |
| "grad_norm": 0.18639002939061947, | |
| "learning_rate": 3.0468750000000004e-06, | |
| "loss": 0.0285, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 3.4935064935064934, | |
| "grad_norm": 0.2049138683286163, | |
| "learning_rate": 3.0208333333333334e-06, | |
| "loss": 0.0253, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 3.5064935064935066, | |
| "grad_norm": 0.17884962390491255, | |
| "learning_rate": 2.994791666666667e-06, | |
| "loss": 0.0307, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.5194805194805197, | |
| "grad_norm": 0.1982271960154676, | |
| "learning_rate": 2.96875e-06, | |
| "loss": 0.0269, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 3.5324675324675323, | |
| "grad_norm": 0.1802446997280461, | |
| "learning_rate": 2.9427083333333336e-06, | |
| "loss": 0.0289, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 3.5454545454545454, | |
| "grad_norm": 0.22296142453499057, | |
| "learning_rate": 2.916666666666667e-06, | |
| "loss": 0.0312, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 3.5584415584415585, | |
| "grad_norm": 0.20453986728427528, | |
| "learning_rate": 2.8906250000000004e-06, | |
| "loss": 0.0314, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 3.571428571428571, | |
| "grad_norm": 0.18470206760727637, | |
| "learning_rate": 2.8645833333333334e-06, | |
| "loss": 0.0224, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 3.5844155844155843, | |
| "grad_norm": 0.18999613246744235, | |
| "learning_rate": 2.838541666666667e-06, | |
| "loss": 0.0362, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 3.5974025974025974, | |
| "grad_norm": 0.1680826823967811, | |
| "learning_rate": 2.8125e-06, | |
| "loss": 0.0295, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 3.6103896103896105, | |
| "grad_norm": 0.1750343035924861, | |
| "learning_rate": 2.7864583333333336e-06, | |
| "loss": 0.0252, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 3.6233766233766236, | |
| "grad_norm": 0.1889879529926468, | |
| "learning_rate": 2.760416666666667e-06, | |
| "loss": 0.0251, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 3.6363636363636362, | |
| "grad_norm": 0.18898957778162337, | |
| "learning_rate": 2.7343750000000004e-06, | |
| "loss": 0.0289, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.6493506493506493, | |
| "grad_norm": 0.178208525512879, | |
| "learning_rate": 2.7083333333333334e-06, | |
| "loss": 0.0256, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 3.6623376623376624, | |
| "grad_norm": 0.18961129083755054, | |
| "learning_rate": 2.682291666666667e-06, | |
| "loss": 0.0338, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 3.675324675324675, | |
| "grad_norm": 0.19080605075919305, | |
| "learning_rate": 2.65625e-06, | |
| "loss": 0.0267, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 3.688311688311688, | |
| "grad_norm": 0.2147288655205537, | |
| "learning_rate": 2.630208333333333e-06, | |
| "loss": 0.0261, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 3.7012987012987013, | |
| "grad_norm": 0.17582709254045928, | |
| "learning_rate": 2.604166666666667e-06, | |
| "loss": 0.0223, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 3.7142857142857144, | |
| "grad_norm": 0.17094890369659926, | |
| "learning_rate": 2.5781250000000004e-06, | |
| "loss": 0.0292, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 3.7272727272727275, | |
| "grad_norm": 0.1998709196442666, | |
| "learning_rate": 2.5520833333333334e-06, | |
| "loss": 0.0304, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 3.74025974025974, | |
| "grad_norm": 0.17072439958723487, | |
| "learning_rate": 2.5260416666666672e-06, | |
| "loss": 0.0269, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 3.7532467532467533, | |
| "grad_norm": 0.1903923054426443, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0296, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 3.7662337662337664, | |
| "grad_norm": 0.18728539960718932, | |
| "learning_rate": 2.4739583333333336e-06, | |
| "loss": 0.0286, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.779220779220779, | |
| "grad_norm": 0.1747917940824676, | |
| "learning_rate": 2.4479166666666666e-06, | |
| "loss": 0.0349, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 3.792207792207792, | |
| "grad_norm": 0.17515549499079433, | |
| "learning_rate": 2.421875e-06, | |
| "loss": 0.027, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 3.8051948051948052, | |
| "grad_norm": 0.17289038920757535, | |
| "learning_rate": 2.395833333333334e-06, | |
| "loss": 0.0308, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 3.8181818181818183, | |
| "grad_norm": 0.1620641486147313, | |
| "learning_rate": 2.369791666666667e-06, | |
| "loss": 0.0235, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 3.8311688311688314, | |
| "grad_norm": 0.1800272114039067, | |
| "learning_rate": 2.3437500000000002e-06, | |
| "loss": 0.029, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 3.844155844155844, | |
| "grad_norm": 0.1714629421802426, | |
| "learning_rate": 2.3177083333333336e-06, | |
| "loss": 0.0325, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 3.857142857142857, | |
| "grad_norm": 0.19442415161637205, | |
| "learning_rate": 2.2916666666666666e-06, | |
| "loss": 0.0289, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 3.87012987012987, | |
| "grad_norm": 0.17365311658981006, | |
| "learning_rate": 2.265625e-06, | |
| "loss": 0.0264, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 3.883116883116883, | |
| "grad_norm": 0.1562256172576751, | |
| "learning_rate": 2.2395833333333334e-06, | |
| "loss": 0.0204, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 3.896103896103896, | |
| "grad_norm": 0.18527276756636948, | |
| "learning_rate": 2.213541666666667e-06, | |
| "loss": 0.038, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.909090909090909, | |
| "grad_norm": 0.185548190702714, | |
| "learning_rate": 2.1875000000000002e-06, | |
| "loss": 0.0274, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 3.9220779220779223, | |
| "grad_norm": 0.18710521272243544, | |
| "learning_rate": 2.1614583333333336e-06, | |
| "loss": 0.0282, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 3.935064935064935, | |
| "grad_norm": 0.19705254815926593, | |
| "learning_rate": 2.1354166666666666e-06, | |
| "loss": 0.029, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 3.948051948051948, | |
| "grad_norm": 0.18926365228746053, | |
| "learning_rate": 2.109375e-06, | |
| "loss": 0.031, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 3.961038961038961, | |
| "grad_norm": 0.20932783484563577, | |
| "learning_rate": 2.0833333333333334e-06, | |
| "loss": 0.0347, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 3.974025974025974, | |
| "grad_norm": 0.1844456439281899, | |
| "learning_rate": 2.057291666666667e-06, | |
| "loss": 0.0297, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 3.987012987012987, | |
| "grad_norm": 0.17809794425485584, | |
| "learning_rate": 2.0312500000000002e-06, | |
| "loss": 0.0286, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.20096357456266348, | |
| "learning_rate": 2.0052083333333337e-06, | |
| "loss": 0.0258, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 4.012987012987013, | |
| "grad_norm": 0.15779488457929053, | |
| "learning_rate": 1.9791666666666666e-06, | |
| "loss": 0.0197, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 4.025974025974026, | |
| "grad_norm": 0.17635189527472814, | |
| "learning_rate": 1.953125e-06, | |
| "loss": 0.0214, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.038961038961039, | |
| "grad_norm": 0.13517784425731946, | |
| "learning_rate": 1.9270833333333334e-06, | |
| "loss": 0.0226, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 4.0519480519480515, | |
| "grad_norm": 0.12354611702984837, | |
| "learning_rate": 1.9010416666666666e-06, | |
| "loss": 0.0211, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 4.064935064935065, | |
| "grad_norm": 0.12929184375596317, | |
| "learning_rate": 1.8750000000000003e-06, | |
| "loss": 0.0184, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 4.077922077922078, | |
| "grad_norm": 0.13540347091068558, | |
| "learning_rate": 1.8489583333333337e-06, | |
| "loss": 0.0216, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 4.090909090909091, | |
| "grad_norm": 0.16456545986510454, | |
| "learning_rate": 1.8229166666666666e-06, | |
| "loss": 0.0275, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 4.103896103896104, | |
| "grad_norm": 0.13103783773070332, | |
| "learning_rate": 1.796875e-06, | |
| "loss": 0.0167, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 4.116883116883117, | |
| "grad_norm": 0.15039425342491727, | |
| "learning_rate": 1.7708333333333337e-06, | |
| "loss": 0.0176, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 4.12987012987013, | |
| "grad_norm": 0.1528874968260015, | |
| "learning_rate": 1.7447916666666667e-06, | |
| "loss": 0.0228, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 4.142857142857143, | |
| "grad_norm": 0.1277979944302909, | |
| "learning_rate": 1.71875e-06, | |
| "loss": 0.0153, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 4.1558441558441555, | |
| "grad_norm": 0.10986972687139382, | |
| "learning_rate": 1.6927083333333335e-06, | |
| "loss": 0.0114, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.1688311688311686, | |
| "grad_norm": 0.12327195530898087, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.0247, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 4.181818181818182, | |
| "grad_norm": 0.1303364571800614, | |
| "learning_rate": 1.640625e-06, | |
| "loss": 0.0132, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 4.194805194805195, | |
| "grad_norm": 0.1129046695889519, | |
| "learning_rate": 1.6145833333333335e-06, | |
| "loss": 0.0137, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 4.207792207792208, | |
| "grad_norm": 0.12487716628769142, | |
| "learning_rate": 1.5885416666666667e-06, | |
| "loss": 0.0171, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 4.220779220779221, | |
| "grad_norm": 0.11121142713696242, | |
| "learning_rate": 1.5625e-06, | |
| "loss": 0.0119, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 4.233766233766234, | |
| "grad_norm": 0.12219540809008053, | |
| "learning_rate": 1.5364583333333335e-06, | |
| "loss": 0.02, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 4.246753246753247, | |
| "grad_norm": 0.1231988249512158, | |
| "learning_rate": 1.5104166666666667e-06, | |
| "loss": 0.0167, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 4.259740259740259, | |
| "grad_norm": 0.12591039931221573, | |
| "learning_rate": 1.484375e-06, | |
| "loss": 0.0145, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 4.2727272727272725, | |
| "grad_norm": 0.13528042945474514, | |
| "learning_rate": 1.4583333333333335e-06, | |
| "loss": 0.0164, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 4.285714285714286, | |
| "grad_norm": 0.13318619366466836, | |
| "learning_rate": 1.4322916666666667e-06, | |
| "loss": 0.0178, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.298701298701299, | |
| "grad_norm": 0.1147621867962911, | |
| "learning_rate": 1.40625e-06, | |
| "loss": 0.0146, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 4.311688311688312, | |
| "grad_norm": 0.1171420417701479, | |
| "learning_rate": 1.3802083333333335e-06, | |
| "loss": 0.0155, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 4.324675324675325, | |
| "grad_norm": 0.15069462003471634, | |
| "learning_rate": 1.3541666666666667e-06, | |
| "loss": 0.0169, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 4.337662337662338, | |
| "grad_norm": 0.13369044996596968, | |
| "learning_rate": 1.328125e-06, | |
| "loss": 0.02, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 4.35064935064935, | |
| "grad_norm": 0.1454995879584439, | |
| "learning_rate": 1.3020833333333335e-06, | |
| "loss": 0.0172, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 4.363636363636363, | |
| "grad_norm": 0.10957228964118756, | |
| "learning_rate": 1.2760416666666667e-06, | |
| "loss": 0.0146, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 4.376623376623376, | |
| "grad_norm": 0.13794250836423072, | |
| "learning_rate": 1.25e-06, | |
| "loss": 0.0186, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 4.3896103896103895, | |
| "grad_norm": 0.13155919219887055, | |
| "learning_rate": 1.2239583333333333e-06, | |
| "loss": 0.02, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 4.402597402597403, | |
| "grad_norm": 0.13527086701859414, | |
| "learning_rate": 1.197916666666667e-06, | |
| "loss": 0.0194, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 4.415584415584416, | |
| "grad_norm": 0.13783015873528512, | |
| "learning_rate": 1.1718750000000001e-06, | |
| "loss": 0.016, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.428571428571429, | |
| "grad_norm": 0.14817876036194735, | |
| "learning_rate": 1.1458333333333333e-06, | |
| "loss": 0.0202, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 4.441558441558442, | |
| "grad_norm": 0.13486669752884248, | |
| "learning_rate": 1.1197916666666667e-06, | |
| "loss": 0.0133, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 4.454545454545454, | |
| "grad_norm": 0.127193126169577, | |
| "learning_rate": 1.0937500000000001e-06, | |
| "loss": 0.0225, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 4.467532467532467, | |
| "grad_norm": 0.12716918562412002, | |
| "learning_rate": 1.0677083333333333e-06, | |
| "loss": 0.0161, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 4.48051948051948, | |
| "grad_norm": 0.12022862958417269, | |
| "learning_rate": 1.0416666666666667e-06, | |
| "loss": 0.0178, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 4.4935064935064934, | |
| "grad_norm": 0.11185223739581632, | |
| "learning_rate": 1.0156250000000001e-06, | |
| "loss": 0.0125, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 4.5064935064935066, | |
| "grad_norm": 0.12306589435982454, | |
| "learning_rate": 9.895833333333333e-07, | |
| "loss": 0.0177, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 4.51948051948052, | |
| "grad_norm": 0.1356833136264956, | |
| "learning_rate": 9.635416666666667e-07, | |
| "loss": 0.0225, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 4.532467532467533, | |
| "grad_norm": 0.12707329769968861, | |
| "learning_rate": 9.375000000000001e-07, | |
| "loss": 0.0144, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 4.545454545454545, | |
| "grad_norm": 0.13157923603380584, | |
| "learning_rate": 9.114583333333333e-07, | |
| "loss": 0.0246, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.558441558441558, | |
| "grad_norm": 0.11570507668897385, | |
| "learning_rate": 8.854166666666668e-07, | |
| "loss": 0.0136, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "grad_norm": 0.1133212555134258, | |
| "learning_rate": 8.59375e-07, | |
| "loss": 0.016, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 4.584415584415584, | |
| "grad_norm": 0.11403791282962417, | |
| "learning_rate": 8.333333333333333e-07, | |
| "loss": 0.0173, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 4.597402597402597, | |
| "grad_norm": 0.1261694785889651, | |
| "learning_rate": 8.072916666666667e-07, | |
| "loss": 0.0164, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 4.6103896103896105, | |
| "grad_norm": 0.1647802144483293, | |
| "learning_rate": 7.8125e-07, | |
| "loss": 0.0194, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 4.623376623376624, | |
| "grad_norm": 0.12321856169539074, | |
| "learning_rate": 7.552083333333333e-07, | |
| "loss": 0.0154, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 4.636363636363637, | |
| "grad_norm": 0.11947597399789361, | |
| "learning_rate": 7.291666666666667e-07, | |
| "loss": 0.0128, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 4.64935064935065, | |
| "grad_norm": 0.12412634751604261, | |
| "learning_rate": 7.03125e-07, | |
| "loss": 0.0216, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 4.662337662337662, | |
| "grad_norm": 0.10648985459552097, | |
| "learning_rate": 6.770833333333333e-07, | |
| "loss": 0.016, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 4.675324675324675, | |
| "grad_norm": 0.10795065481176093, | |
| "learning_rate": 6.510416666666668e-07, | |
| "loss": 0.0149, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.688311688311688, | |
| "grad_norm": 0.13861642312992048, | |
| "learning_rate": 6.25e-07, | |
| "loss": 0.0197, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 4.701298701298701, | |
| "grad_norm": 0.12770449682753193, | |
| "learning_rate": 5.989583333333335e-07, | |
| "loss": 0.0221, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 4.714285714285714, | |
| "grad_norm": 0.10430014511475291, | |
| "learning_rate": 5.729166666666667e-07, | |
| "loss": 0.0129, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 4.7272727272727275, | |
| "grad_norm": 0.11966755573044428, | |
| "learning_rate": 5.468750000000001e-07, | |
| "loss": 0.0206, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 4.740259740259741, | |
| "grad_norm": 0.1275756019900647, | |
| "learning_rate": 5.208333333333334e-07, | |
| "loss": 0.0171, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 4.753246753246753, | |
| "grad_norm": 0.12808966422886903, | |
| "learning_rate": 4.947916666666667e-07, | |
| "loss": 0.0192, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 4.766233766233766, | |
| "grad_norm": 0.12149697378823344, | |
| "learning_rate": 4.6875000000000006e-07, | |
| "loss": 0.0143, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 4.779220779220779, | |
| "grad_norm": 0.1120503286114493, | |
| "learning_rate": 4.427083333333334e-07, | |
| "loss": 0.013, | |
| "step": 368 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 385, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 16, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 552596339163136.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |