Upload training_logs/it_tsae_paper_k20__seed42.json with huggingface_hub
Browse files
training_logs/it_tsae_paper_k20__seed42.json
ADDED
|
@@ -0,0 +1,190 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"loss": [
|
| 3 |
+
185893.8125,
|
| 4 |
+
43409.96484375,
|
| 5 |
+
19474.39453125,
|
| 6 |
+
13977.06640625,
|
| 7 |
+
12460.4560546875,
|
| 8 |
+
11605.5146484375,
|
| 9 |
+
11384.26953125,
|
| 10 |
+
11045.8359375,
|
| 11 |
+
10638.7548828125,
|
| 12 |
+
10600.4482421875,
|
| 13 |
+
10439.8671875,
|
| 14 |
+
10340.474609375,
|
| 15 |
+
10392.740234375,
|
| 16 |
+
10191.560546875,
|
| 17 |
+
9968.5400390625,
|
| 18 |
+
10038.353515625,
|
| 19 |
+
10102.6025390625,
|
| 20 |
+
9992.2275390625,
|
| 21 |
+
9869.166015625,
|
| 22 |
+
9724.1201171875,
|
| 23 |
+
9648.580078125,
|
| 24 |
+
9769.30859375,
|
| 25 |
+
9696.89453125,
|
| 26 |
+
9642.62890625,
|
| 27 |
+
9678.5146484375,
|
| 28 |
+
9546.8828125,
|
| 29 |
+
9543.2626953125
|
| 30 |
+
],
|
| 31 |
+
"l0": [
|
| 32 |
+
20.0,
|
| 33 |
+
20.0,
|
| 34 |
+
20.0,
|
| 35 |
+
20.0,
|
| 36 |
+
20.0,
|
| 37 |
+
20.0,
|
| 38 |
+
20.0,
|
| 39 |
+
20.0,
|
| 40 |
+
20.0,
|
| 41 |
+
20.0,
|
| 42 |
+
20.0,
|
| 43 |
+
20.0,
|
| 44 |
+
20.0,
|
| 45 |
+
20.0,
|
| 46 |
+
20.0,
|
| 47 |
+
20.0,
|
| 48 |
+
20.0,
|
| 49 |
+
20.0,
|
| 50 |
+
20.0,
|
| 51 |
+
20.0,
|
| 52 |
+
20.0,
|
| 53 |
+
20.0,
|
| 54 |
+
20.0,
|
| 55 |
+
20.0,
|
| 56 |
+
20.0,
|
| 57 |
+
20.0,
|
| 58 |
+
20.0
|
| 59 |
+
],
|
| 60 |
+
"auxk": [
|
| 61 |
+
0.0,
|
| 62 |
+
0.0,
|
| 63 |
+
0.0,
|
| 64 |
+
0.0,
|
| 65 |
+
0.0,
|
| 66 |
+
0.0,
|
| 67 |
+
0.0,
|
| 68 |
+
0.0,
|
| 69 |
+
0.0,
|
| 70 |
+
0.0,
|
| 71 |
+
0.0,
|
| 72 |
+
0.0,
|
| 73 |
+
0.0,
|
| 74 |
+
0.0,
|
| 75 |
+
0.0,
|
| 76 |
+
0.0,
|
| 77 |
+
0.0,
|
| 78 |
+
1.0001938343048096,
|
| 79 |
+
0.9997935891151428,
|
| 80 |
+
0.9977656006813049,
|
| 81 |
+
0.9959306716918945,
|
| 82 |
+
0.9857977628707886,
|
| 83 |
+
0.9760985374450684,
|
| 84 |
+
0.9644298553466797,
|
| 85 |
+
0.9572041034698486,
|
| 86 |
+
0.958156168460846,
|
| 87 |
+
0.9474268555641174
|
| 88 |
+
],
|
| 89 |
+
"dead": [
|
| 90 |
+
0,
|
| 91 |
+
0,
|
| 92 |
+
0,
|
| 93 |
+
0,
|
| 94 |
+
0,
|
| 95 |
+
0,
|
| 96 |
+
0,
|
| 97 |
+
0,
|
| 98 |
+
0,
|
| 99 |
+
0,
|
| 100 |
+
0,
|
| 101 |
+
0,
|
| 102 |
+
0,
|
| 103 |
+
0,
|
| 104 |
+
0,
|
| 105 |
+
0,
|
| 106 |
+
0,
|
| 107 |
+
4,
|
| 108 |
+
31,
|
| 109 |
+
82,
|
| 110 |
+
183,
|
| 111 |
+
294,
|
| 112 |
+
470,
|
| 113 |
+
651,
|
| 114 |
+
834,
|
| 115 |
+
1030,
|
| 116 |
+
1214
|
| 117 |
+
],
|
| 118 |
+
"steps_logged": [
|
| 119 |
+
0,
|
| 120 |
+
200,
|
| 121 |
+
400,
|
| 122 |
+
600,
|
| 123 |
+
800,
|
| 124 |
+
1000,
|
| 125 |
+
1200,
|
| 126 |
+
1400,
|
| 127 |
+
1600,
|
| 128 |
+
1800,
|
| 129 |
+
2000,
|
| 130 |
+
2200,
|
| 131 |
+
2400,
|
| 132 |
+
2600,
|
| 133 |
+
2800,
|
| 134 |
+
3000,
|
| 135 |
+
3200,
|
| 136 |
+
3400,
|
| 137 |
+
3600,
|
| 138 |
+
3800,
|
| 139 |
+
4000,
|
| 140 |
+
4200,
|
| 141 |
+
4400,
|
| 142 |
+
4600,
|
| 143 |
+
4800,
|
| 144 |
+
5000,
|
| 145 |
+
5200
|
| 146 |
+
],
|
| 147 |
+
"final_step": 5200,
|
| 148 |
+
"converged": true,
|
| 149 |
+
"plateau_last": 0.01826850192401348,
|
| 150 |
+
"elapsed_s": 1381.2595372200012,
|
| 151 |
+
"group_sizes": [
|
| 152 |
+
3686,
|
| 153 |
+
14746
|
| 154 |
+
],
|
| 155 |
+
"group_weights": [
|
| 156 |
+
0.5,
|
| 157 |
+
0.5
|
| 158 |
+
],
|
| 159 |
+
"lr_used": 0.0001885618083164127,
|
| 160 |
+
"row": 3,
|
| 161 |
+
"arch_id": "tsae_paper_k20",
|
| 162 |
+
"arch": "tsae_paper_k20",
|
| 163 |
+
"group": 1,
|
| 164 |
+
"src_class": "TemporalMatryoshkaBatchTopKSAE",
|
| 165 |
+
"src_module": "src.architectures.tsae_paper",
|
| 166 |
+
"T": 1,
|
| 167 |
+
"T_max": null,
|
| 168 |
+
"t_sample": null,
|
| 169 |
+
"n_layers": null,
|
| 170 |
+
"k_win": 20,
|
| 171 |
+
"k_pos": 20,
|
| 172 |
+
"shifts": null,
|
| 173 |
+
"alpha": null,
|
| 174 |
+
"gamma": null,
|
| 175 |
+
"n_scales": null,
|
| 176 |
+
"seed": 42,
|
| 177 |
+
"d_in": 2304,
|
| 178 |
+
"d_sae": 18432,
|
| 179 |
+
"subject_model": "google/gemma-2-2b-it",
|
| 180 |
+
"anchor_layer": 13,
|
| 181 |
+
"mlc_layers": [
|
| 182 |
+
11,
|
| 183 |
+
12,
|
| 184 |
+
13,
|
| 185 |
+
14,
|
| 186 |
+
15
|
| 187 |
+
],
|
| 188 |
+
"phase": "phase7_unification",
|
| 189 |
+
"run_id": "it_tsae_paper_k20__seed42"
|
| 190 |
+
}
|