| step,lambda,train_loss,val_loss,perplexity,grad_norm,lr | |
| 1,5.0,4.439182,4.401433,81.57,1.8206,5e-05 | |
| 2,5.0,4.425845,4.499078,89.93,1.9943,5e-05 | |
| 3,5.0,4.413262,4.638323,103.37,1.2868,5e-05 | |
| 4,5.0,4.324896,4.516158,91.48,1.9661,5e-05 | |
| 5,5.0,4.38296,4.388484,80.52,1.9368,5e-05 | |
| 6,5.0,4.396439,4.592255,98.72,1.5608,5e-05 | |
| 7,5.0,4.320875,4.489231,89.05,1.2136,5e-05 | |
| 8,5.0,4.225918,4.501476,90.15,1.7529,5e-05 | |
| 9,5.0,4.31143,4.275868,71.94,1.7723,5e-05 | |
| 10,5.0,4.259973,4.321823,75.33,1.9027,5e-05 | |
| 11,5.0,4.319943,4.411529,82.4,2.0002,5e-05 | |
| 12,5.0,4.204026,4.204776,67.01,1.8041,5e-05 | |
| 13,5.0,4.179761,4.117256,61.39,1.4147,5e-05 | |
| 14,5.0,4.124375,4.171768,64.83,1.707,5e-05 | |
| 15,5.0,4.093269,4.170282,64.73,1.7566,5e-05 | |
| 16,5.0,4.086002,4.188016,65.89,1.7025,5e-05 | |
| 17,5.0,4.047834,4.023562,55.9,1.5458,5e-05 | |
| 18,5.0,4.046859,4.112727,61.11,1.7028,5e-05 | |
| 19,5.0,4.019934,4.251786,70.23,1.4874,5e-05 | |
| 20,5.0,3.907715,4.072797,58.72,1.6932,5e-05 | |
| 21,5.0,3.922146,3.951205,52.0,1.3106,5e-05 | |
| 22,5.0,3.996865,4.111187,61.02,1.4928,5e-05 | |
| 23,5.0,3.973646,4.114249,61.21,1.4506,5e-05 | |
| 24,5.0,3.937268,4.0433,57.01,1.4038,5e-05 | |
| 25,5.0,3.923605,3.913486,50.07,1.6098,5e-05 | |
| 26,5.0,3.939859,4.02104,55.76,1.3642,5e-05 | |
| 27,5.0,3.756066,3.729621,41.66,1.0119,5e-05 | |
| 28,5.0,3.808359,4.02817,56.16,1.705,5e-05 | |
| 29,5.0,3.767406,3.816133,45.43,1.2281,5e-05 | |
| 30,5.0,3.806492,3.928285,50.82,1.1661,5e-05 | |
| 31,5.0,3.673875,3.84967,46.98,1.1798,5e-05 | |
| 32,5.0,3.72545,3.90244,49.52,1.0798,5e-05 | |
| 33,5.0,3.624605,3.845745,46.79,1.1157,5e-05 | |
| 34,5.0,3.590695,3.706007,40.69,1.3562,5e-05 | |
| 35,5.0,3.692491,3.710188,40.86,1.0549,5e-05 | |
| 36,5.0,3.664012,3.774854,43.59,0.9572,5e-05 | |
| 37,5.0,3.651831,3.711326,40.91,1.0075,5e-05 | |
| 38,5.0,3.61477,3.594546,36.4,1.1342,5e-05 | |
| 39,5.0,3.481596,3.533321,34.24,0.9792,5e-05 | |
| 40,5.0,3.477439,3.61574,37.18,0.8806,5e-05 | |
| 41,5.0,3.362945,3.506306,33.32,1.1565,5e-05 | |
| 42,5.0,3.540449,3.683561,39.79,1.0024,5e-05 | |
| 43,5.0,3.374159,3.497862,33.04,1.1957,5e-05 | |
| 44,5.0,3.436776,3.583323,35.99,0.9301,5e-05 | |
| 45,5.0,3.42309,3.459788,31.81,0.7372,5e-05 | |
| 46,5.0,3.360055,3.478199,32.4,0.8849,5e-05 | |
| 47,5.0,3.403229,3.414177,30.39,0.8943,5e-05 | |
| 48,5.0,3.257649,3.371495,29.12,0.6532,5e-05 | |
| 49,5.0,3.353027,3.357166,28.71,0.682,5e-05 | |
| 50,5.0,3.17747,3.218861,25.0,0.8191,5e-05 | |
| 51,5.0,3.341124,3.358755,28.75,0.7439,5e-05 | |
| 52,5.0,3.214482,3.328915,27.91,0.6319,5e-05 | |
| 53,5.0,3.144758,3.368717,29.04,0.7391,5e-05 | |
| 54,5.0,3.152316,3.232011,25.33,0.6103,5e-05 | |
| 55,5.0,3.173858,3.304188,27.23,0.7127,5e-05 | |
| 56,5.0,3.114145,3.302456,27.18,0.564,5e-05 | |
| 57,5.0,3.199964,3.259384,26.03,0.5695,5e-05 | |
| 58,5.0,3.022734,3.062363,21.38,0.6301,5e-05 | |
| 59,5.0,3.013718,3.127346,22.81,0.5143,5e-05 | |
| 60,5.0,3.004478,3.069394,21.53,0.5347,5e-05 | |