Copy files from models/jayasriii/57M_10B
Browse files
warmup_500steps_450M_stabilitycheck.csv
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
step,train_loss,val_loss,tok_per_sec,grad_norm,dt_ms,lr,elapsed_min,muon_lr
|
| 2 |
+
0,11.066354,11.053152,47869.571040,20.915958,10952.427369,0.000012,0.220719,0.000012
|
| 3 |
+
1,11.039084,11.053152,48939.976001,19.531719,10712.878159,0.000024,0.400921,0.000024
|
| 4 |
+
2,10.965948,11.053152,49191.938017,22.626043,10658.006599,0.000036,0.579732,0.000036
|
| 5 |
+
3,10.841732,11.053152,49563.593026,18.648500,10578.087019,0.000048,0.756040,0.000048
|
| 6 |
+
4,10.679325,11.053152,49575.484577,17.998524,10575.549679,0.000060,0.932304,0.000060
|
| 7 |
+
5,10.454514,11.053152,49557.482345,17.396326,10579.391349,0.000072,1.108633,0.000072
|
| 8 |
+
6,10.236917,11.053152,49578.498605,16.793922,10574.906759,0.000084,1.284887,0.000084
|
| 9 |
+
7,9.932341,11.053152,49575.012244,16.149319,10575.650439,0.000096,1.461153,0.000096
|
| 10 |
+
8,9.608929,11.053152,49569.968558,15.087049,10576.726499,0.000108,1.637437,0.000108
|
| 11 |
+
9,9.402693,11.053152,49569.638335,11.044486,10576.796959,0.000120,1.813722,0.000120
|
| 12 |
+
10,9.144703,11.053152,49588.245794,9.094260,10572.828129,0.000132,1.989941,0.000132
|
| 13 |
+
11,8.913101,11.053152,49565.742591,7.504558,10577.628269,0.000144,2.166240,0.000144
|
| 14 |
+
12,8.672513,11.053152,49613.869923,7.107585,10567.367569,0.000156,2.342368,0.000156
|
| 15 |
+
13,8.483335,11.053152,49634.985453,9.226773,10562.872039,0.000168,2.518421,0.000168
|
| 16 |
+
14,8.252608,11.053152,49632.331456,14.784000,10563.436869,0.000180,2.694484,0.000180
|
| 17 |
+
15,8.130715,11.053152,49628.829064,7.936351,10564.182349,0.000192,2.870559,0.000192
|
| 18 |
+
16,7.937550,11.053152,49598.436790,13.716204,10570.655729,0.000204,3.046741,0.000204
|
| 19 |
+
17,7.767540,11.053152,49618.239341,10.516768,10566.436999,0.000216,3.222854,0.000216
|
| 20 |
+
18,7.583117,11.053152,49614.083876,12.901004,10567.321999,0.000228,3.398982,0.000228
|
| 21 |
+
19,7.454672,11.053152,49589.015930,8.319250,10572.663929,0.000240,3.575198,0.000240
|
| 22 |
+
20,7.411219,11.053152,49619.680863,11.866556,10566.130029,0.000252,3.751306,0.000252
|
| 23 |
+
21,7.321939,11.053152,49624.997990,14.476563,10564.997909,0.000264,3.927395,0.000264
|
| 24 |
+
22,7.302217,11.053152,49583.151726,10.151662,10573.914359,0.000276,4.103632,0.000276
|
| 25 |
+
23,7.164737,11.053152,49605.202200,8.859375,10569.214049,0.000288,4.279791,0.000288
|
| 26 |
+
24,7.126419,11.053152,49596.615764,11.680076,10571.043849,0.000300,4.455980,0.000300
|
| 27 |
+
25,7.067708,11.053152,49593.881426,7.528028,10571.626679,0.000312,4.632180,0.000312
|
| 28 |
+
26,7.015353,11.053152,49596.985804,10.043826,10570.964979,0.000324,4.808368,0.000324
|
| 29 |
+
27,6.852988,11.053152,49596.762850,6.868258,10571.012499,0.000336,4.984557,0.000336
|
| 30 |
+
28,6.902584,11.053152,49588.528472,7.821333,10572.767859,0.000348,5.160775,0.000348
|
| 31 |
+
29,6.869988,11.053152,49592.976130,6.645007,10571.819659,0.000360,5.336977,0.000360
|
| 32 |
+
30,6.856277,11.053152,49598.236673,7.197589,10570.698379,0.000372,5.513161,0.000372
|
| 33 |
+
31,6.744816,11.053152,49589.390829,7.317073,10572.583999,0.000384,5.689376,0.000384
|
| 34 |
+
32,6.774980,11.053152,49597.919446,10.769730,10570.765989,0.000396,5.865560,0.000396
|
| 35 |
+
33,6.591572,11.053152,49557.606808,5.061138,10579.364779,0.000408,6.041888,0.000408
|
| 36 |
+
34,6.687301,11.053152,49567.131109,5.027588,10577.331959,0.000420,6.218183,0.000420
|
| 37 |
+
35,6.623246,11.053152,49592.414805,3.979075,10571.939319,0.000432,6.394387,0.000432
|
| 38 |
+
36,6.533303,11.053152,49598.776264,3.760327,10570.583379,0.000444,6.570569,0.000444
|
| 39 |
+
37,6.461662,11.053152,49580.348402,3.202894,10574.512219,0.000456,6.746816,0.000456
|
| 40 |
+
38,6.435514,11.053152,49587.125247,3.873983,10573.067049,0.000468,6.923039,0.000468
|
| 41 |
+
39,6.406319,11.053152,49423.410734,4.155348,10608.090219,0.000480,7.099846,0.000480
|
| 42 |
+
40,6.332901,11.053152,49586.376273,3.211956,10573.226749,0.000492,7.276073,0.000492
|
| 43 |
+
41,6.350723,11.053152,49619.187636,3.838921,10566.235059,0.000504,7.452182,0.000504
|
| 44 |
+
42,6.312028,11.053152,49636.248155,2.763764,10562.603329,0.000516,7.628231,0.000516
|
| 45 |
+
43,6.270370,11.053152,49596.691864,1.819132,10571.027629,0.000528,7.804421,0.000528
|
| 46 |
+
44,6.214734,11.053152,49605.830228,2.296805,10569.080239,0.000540,7.980578,0.000540
|
| 47 |
+
45,6.326629,11.053152,49589.002938,2.772758,10572.666699,0.000552,8.156794,0.000552
|
| 48 |
+
46,6.287328,11.053152,49609.005246,2.680347,10568.403809,0.000564,8.332939,0.000564
|
| 49 |
+
47,6.192577,11.053152,49587.317301,2.079368,10573.026099,0.000576,8.509162,0.000576
|
| 50 |
+
48,6.226033,11.053152,49595.889962,1.886525,10571.198549,0.000588,8.685354,0.000588
|
| 51 |
+
49,6.106044,11.053152,49594.653708,1.557534,10571.462059,0.000600,8.861550,0.000600
|
| 52 |
+
50,6.148938,11.053152,49593.660142,1.826329,10571.673849,0.000612,9.037751,0.000612
|
| 53 |
+
51,6.140829,11.053152,49564.667480,1.854200,10577.857709,0.000624,9.214054,0.000624
|
| 54 |
+
52,6.174147,11.053152,49629.657683,1.689617,10564.005969,0.000636,9.390126,0.000636
|
| 55 |
+
53,6.064402,11.053152,49574.516342,1.283487,10575.756229,0.000648,9.566394,0.000648
|
| 56 |
+
54,5.965606,11.053152,49570.715864,1.631016,10576.567049,0.000660,9.742676,0.000660
|
| 57 |
+
55,6.007326,11.053152,49552.174946,1.211783,10580.524479,0.000672,9.919025,0.000672
|
| 58 |
+
56,5.993603,11.053152,49549.917487,1.391411,10581.006520,0.000684,10.095380,0.000684
|
| 59 |
+
57,6.031452,11.053152,49558.882956,1.344216,10579.092359,0.000696,10.271704,0.000696
|
| 60 |
+
58,5.971352,11.053152,49570.993233,1.414309,10576.507869,0.000708,10.447984,0.000708
|
| 61 |
+
59,6.065826,11.053152,49567.774341,1.179538,10577.194699,0.000720,10.624277,0.000720
|
| 62 |
+
60,6.043016,11.053152,49563.963792,1.655416,10578.007889,0.000732,10.800582,0.000732
|
| 63 |
+
61,6.091240,11.053152,49574.081808,2.151548,10575.848929,0.000744,10.976852,0.000744
|
| 64 |
+
62,5.908826,11.053152,49588.679403,1.180661,10572.735679,0.000756,11.153070,0.000756
|
| 65 |
+
63,6.031398,11.053152,49608.179382,1.453465,10568.579749,0.000768,11.329219,0.000768
|
| 66 |
+
64,5.983883,11.053152,49636.638665,1.454411,10562.520229,0.000780,11.505266,0.000780
|
| 67 |
+
65,5.860258,11.053152,49611.602151,1.245832,10567.850609,0.000792,11.681402,0.000792
|
| 68 |
+
66,5.974788,11.053152,49645.660504,1.039740,10560.600759,0.000804,11.857418,0.000804
|
| 69 |
+
67,5.991943,11.053152,49601.203915,1.075205,10570.066019,0.000816,12.033591,0.000816
|
| 70 |
+
68,5.876173,11.053152,49615.596103,1.190325,10566.999919,0.000828,12.209713,0.000828
|
| 71 |
+
69,5.886452,11.053152,49634.959139,1.065102,10562.877639,0.000840,12.385767,0.000840
|
| 72 |
+
70,5.904429,11.053152,49582.489996,1.064583,10574.055479,0.000852,12.562006,0.000852
|
| 73 |
+
71,5.951005,11.053152,49622.444958,1.435709,10565.541469,0.000864,12.738105,0.000864
|
| 74 |
+
72,5.829657,11.053152,49638.291940,0.728720,10562.168429,0.000876,12.914146,0.000876
|
| 75 |
+
73,5.846940,11.053152,49687.227763,0.762499,10551.765989,0.000888,13.090015,0.000888
|
| 76 |
+
74,5.832050,11.053152,49633.790290,1.110062,10563.126389,0.000900,13.266072,0.000900
|
| 77 |
+
75,5.916031,11.053152,49593.181599,1.062879,10571.775859,0.000912,13.442275,0.000912
|
| 78 |
+
76,5.707827,11.053152,49633.754157,0.923749,10563.134079,0.000924,13.618333,0.000924
|
| 79 |
+
77,5.839659,11.053152,49636.559576,0.876042,10562.537059,0.000936,13.794380,0.000936
|
| 80 |
+
78,5.790799,11.053152,49611.849697,0.838342,10567.797879,0.000948,13.970516,0.000948
|
| 81 |
+
79,5.778706,11.053152,49468.679181,0.920156,10598.382829,0.000960,14.147161,0.000960
|
| 82 |
+
80,5.815504,11.053152,49596.390420,0.822215,10571.091879,0.000972,14.323351,0.000972
|
| 83 |
+
81,5.793572,11.053152,49593.328947,0.811579,10571.744449,0.000984,14.499552,0.000984
|
| 84 |
+
82,5.840338,11.053152,49581.566219,0.833245,10574.252489,0.000996,14.675796,0.000996
|
| 85 |
+
83,5.748702,11.053152,49563.772996,0.640050,10578.048609,0.001008,14.852102,0.001008
|
| 86 |
+
84,5.735820,11.053152,49545.664369,0.809441,10581.914819,0.001020,15.028473,0.001020
|
| 87 |
+
85,5.757621,11.053152,49553.465098,0.850338,10580.249009,0.001032,15.204816,0.001032
|
| 88 |
+
86,5.785703,11.053152,49550.364902,0.766300,10580.910979,0.001044,15.381171,0.001044
|
| 89 |
+
87,5.705674,11.053152,49544.166842,0.730916,10582.234669,0.001056,15.557547,0.001056
|
| 90 |
+
88,5.774658,11.053152,49553.669772,0.919683,10580.205309,0.001068,15.733889,0.001068
|
| 91 |
+
89,5.701285,11.053152,49559.009113,0.770642,10579.065429,0.001080,15.910212,0.001080
|
| 92 |
+
90,5.697346,11.053152,49548.940750,0.683401,10581.215099,0.001092,16.086572,0.001092
|
| 93 |
+
91,5.858577,11.053152,49543.828255,2.207645,10582.306989,0.001104,16.262949,0.001104
|
| 94 |
+
92,5.687789,11.053152,49551.146881,0.454596,10580.743999,0.001116,16.439300,0.001116
|
| 95 |
+
93,5.687775,11.053152,49549.883588,0.627020,10581.013759,0.001128,16.615655,0.001128
|
| 96 |
+
94,5.627503,11.053152,49608.800209,0.753515,10568.447489,0.001140,16.791801,0.001140
|
| 97 |
+
95,5.666321,11.053152,49558.583986,0.729421,10579.156179,0.001152,16.968126,0.001152
|
| 98 |
+
96,5.620394,11.053152,49579.275190,0.756517,10574.741119,0.001164,17.144377,0.001164
|
| 99 |
+
97,5.657304,11.053152,49576.417174,0.708672,10575.350739,0.001176,17.320639,0.001176
|
| 100 |
+
98,5.650695,11.053152,49532.920048,0.527068,10584.637439,0.001188,17.497055,0.001188
|
| 101 |
+
99,5.618207,11.053152,49545.105846,0.760557,10582.034109,0.001200,17.673428,0.001200
|
| 102 |
+
100,5.697881,11.053152,49531.785200,0.961033,10584.879949,0.001212,17.849848,0.001212
|
| 103 |
+
101,5.620191,11.053152,49551.846177,0.983466,10580.594679,0.001224,18.026196,0.001224
|
| 104 |
+
102,5.584038,11.053152,49565.534584,0.564846,10577.672659,0.001236,18.202496,0.001236
|