MHC-A1 durable progress index
Browse files
experiments/MHC_REAL_A1/progress.json
CHANGED
|
@@ -1,7 +1,18 @@
|
|
| 1 |
{
|
| 2 |
"contract_source_sha": "498fa31f672759981d3039c03705cb720cd0ac799f78fd78e33acbcc71e5ee18",
|
| 3 |
"steps": 64,
|
| 4 |
-
"results": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"history": [
|
| 6 |
{
|
| 7 |
"seed": 17,
|
|
@@ -9,7 +20,7 @@
|
|
| 9 |
"step": 0,
|
| 10 |
"loss_train": 0.09119217842817307,
|
| 11 |
"grad_norm": 0.013730722479522228,
|
| 12 |
-
"head_grad_norm": 1.
|
| 13 |
"q0_trials": [
|
| 14 |
{
|
| 15 |
"radius": 0.0003,
|
|
@@ -43,7 +54,7 @@
|
|
| 43 |
"loss_train": 0.08606645464897156,
|
| 44 |
"W3_MSE": 0.1147225337723891,
|
| 45 |
"W4_MSE": 0.11396808549761772,
|
| 46 |
-
"ctrl_max_rms": 0.
|
| 47 |
},
|
| 48 |
{
|
| 49 |
"seed": 17,
|
|
@@ -52,7 +63,7 @@
|
|
| 52 |
"loss_train": 0.1242414116859436,
|
| 53 |
"W3_MSE": 0.11465953538815181,
|
| 54 |
"W4_MSE": 0.11387925470868747,
|
| 55 |
-
"ctrl_max_rms": 0.
|
| 56 |
},
|
| 57 |
{
|
| 58 |
"seed": 17,
|
|
@@ -60,8 +71,8 @@
|
|
| 60 |
"step": 24,
|
| 61 |
"loss_train": 0.09662917256355286,
|
| 62 |
"W3_MSE": 0.11453648408253987,
|
| 63 |
-
"W4_MSE": 0.
|
| 64 |
-
"ctrl_max_rms": 0.
|
| 65 |
},
|
| 66 |
{
|
| 67 |
"seed": 17,
|
|
@@ -70,7 +81,7 @@
|
|
| 70 |
"loss_train": 0.1582513302564621,
|
| 71 |
"W3_MSE": 0.1143090259283781,
|
| 72 |
"W4_MSE": 0.11331315711140633,
|
| 73 |
-
"ctrl_max_rms": 0.
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"seed": 17,
|
|
@@ -87,17 +98,26 @@
|
|
| 87 |
"step": 48,
|
| 88 |
"loss_train": 0.10963404178619385,
|
| 89 |
"W3_MSE": 0.1130196029941241,
|
| 90 |
-
"W4_MSE": 0.
|
| 91 |
-
"ctrl_max_rms": 0.
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"seed": 17,
|
| 95 |
"arm": "stateless",
|
| 96 |
"step": 56,
|
| 97 |
"loss_train": 0.10562591254711151,
|
| 98 |
-
"W3_MSE": 0.
|
| 99 |
"W4_MSE": 0.10920579296847184,
|
| 100 |
"ctrl_max_rms": 0.004299115234365066
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
}
|
| 102 |
],
|
| 103 |
"checkpoints": [
|
|
@@ -107,39 +127,44 @@
|
|
| 107 |
"bytes": 93186
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"sha256": "
|
| 111 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0008.pt",
|
| 112 |
"bytes": 268976
|
| 113 |
},
|
| 114 |
{
|
| 115 |
-
"sha256": "
|
| 116 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0016.pt",
|
| 117 |
"bytes": 268976
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"sha256": "
|
| 121 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0024.pt",
|
| 122 |
"bytes": 268976
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"sha256": "
|
| 126 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0032.pt",
|
| 127 |
"bytes": 268976
|
| 128 |
},
|
| 129 |
{
|
| 130 |
-
"sha256": "
|
| 131 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0040.pt",
|
| 132 |
"bytes": 268976
|
| 133 |
},
|
| 134 |
{
|
| 135 |
-
"sha256": "
|
| 136 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0048.pt",
|
| 137 |
"bytes": 268976
|
| 138 |
},
|
| 139 |
{
|
| 140 |
-
"sha256": "
|
| 141 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0056.pt",
|
| 142 |
"bytes": 268976
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 143 |
}
|
| 144 |
]
|
| 145 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"contract_source_sha": "498fa31f672759981d3039c03705cb720cd0ac799f78fd78e33acbcc71e5ee18",
|
| 3 |
"steps": 64,
|
| 4 |
+
"results": [
|
| 5 |
+
{
|
| 6 |
+
"seed": 17,
|
| 7 |
+
"arm": "stateless",
|
| 8 |
+
"validation": {
|
| 9 |
+
"W3_MSE": 0.11103641552229722,
|
| 10 |
+
"W4_MSE": 0.10791260376572609,
|
| 11 |
+
"ctrl_max_rms": 0.005281291048352917
|
| 12 |
+
},
|
| 13 |
+
"checkpoint_step": 64
|
| 14 |
+
}
|
| 15 |
+
],
|
| 16 |
"history": [
|
| 17 |
{
|
| 18 |
"seed": 17,
|
|
|
|
| 20 |
"step": 0,
|
| 21 |
"loss_train": 0.09119217842817307,
|
| 22 |
"grad_norm": 0.013730722479522228,
|
| 23 |
+
"head_grad_norm": 1.4221209312381689e-06,
|
| 24 |
"q0_trials": [
|
| 25 |
{
|
| 26 |
"radius": 0.0003,
|
|
|
|
| 54 |
"loss_train": 0.08606645464897156,
|
| 55 |
"W3_MSE": 0.1147225337723891,
|
| 56 |
"W4_MSE": 0.11396808549761772,
|
| 57 |
+
"ctrl_max_rms": 0.00018752604106945606
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"seed": 17,
|
|
|
|
| 63 |
"loss_train": 0.1242414116859436,
|
| 64 |
"W3_MSE": 0.11465953538815181,
|
| 65 |
"W4_MSE": 0.11387925470868747,
|
| 66 |
+
"ctrl_max_rms": 0.00030438662361120805
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"seed": 17,
|
|
|
|
| 71 |
"step": 24,
|
| 72 |
"loss_train": 0.09662917256355286,
|
| 73 |
"W3_MSE": 0.11453648408253987,
|
| 74 |
+
"W4_MSE": 0.11368757858872414,
|
| 75 |
+
"ctrl_max_rms": 0.0003923155866990176
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"seed": 17,
|
|
|
|
| 81 |
"loss_train": 0.1582513302564621,
|
| 82 |
"W3_MSE": 0.1143090259283781,
|
| 83 |
"W4_MSE": 0.11331315711140633,
|
| 84 |
+
"ctrl_max_rms": 0.0005296767437054465
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"seed": 17,
|
|
|
|
| 98 |
"step": 48,
|
| 99 |
"loss_train": 0.10963404178619385,
|
| 100 |
"W3_MSE": 0.1130196029941241,
|
| 101 |
+
"W4_MSE": 0.1111137376477321,
|
| 102 |
+
"ctrl_max_rms": 0.002058053525009503
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"seed": 17,
|
| 106 |
"arm": "stateless",
|
| 107 |
"step": 56,
|
| 108 |
"loss_train": 0.10562591254711151,
|
| 109 |
+
"W3_MSE": 0.1119188629090786,
|
| 110 |
"W4_MSE": 0.10920579296847184,
|
| 111 |
"ctrl_max_rms": 0.004299115234365066
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"seed": 17,
|
| 115 |
+
"arm": "stateless",
|
| 116 |
+
"step": 64,
|
| 117 |
+
"loss_train": 0.1330445259809494,
|
| 118 |
+
"W3_MSE": 0.11103641552229722,
|
| 119 |
+
"W4_MSE": 0.10791260376572609,
|
| 120 |
+
"ctrl_max_rms": 0.005281291048352917
|
| 121 |
}
|
| 122 |
],
|
| 123 |
"checkpoints": [
|
|
|
|
| 127 |
"bytes": 93186
|
| 128 |
},
|
| 129 |
{
|
| 130 |
+
"sha256": "a13078dc643df7c8d28691c0174a8dd32d54f090f1bf45b927ff39b8651a156f",
|
| 131 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0008.pt",
|
| 132 |
"bytes": 268976
|
| 133 |
},
|
| 134 |
{
|
| 135 |
+
"sha256": "931cf4a39db5a1dc51cd106afc874d157c15e0d61d775ab5d0cce63ac6638724",
|
| 136 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0016.pt",
|
| 137 |
"bytes": 268976
|
| 138 |
},
|
| 139 |
{
|
| 140 |
+
"sha256": "e682bcc3339512ea4c8b6ca78b772ba77b523052f88d030f8205b3052a8b4e19",
|
| 141 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0024.pt",
|
| 142 |
"bytes": 268976
|
| 143 |
},
|
| 144 |
{
|
| 145 |
+
"sha256": "f872e196b3e38155833df2fb4fab642093aa25f0ccff31ec6fe7f9001f3bed72",
|
| 146 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0032.pt",
|
| 147 |
"bytes": 268976
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"sha256": "a1f47b6860f76d86c226ee6b40207f80bda831c96079d9e8ed7e9df0785b320c",
|
| 151 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0040.pt",
|
| 152 |
"bytes": 268976
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"sha256": "5faa3709c19c3c8f5bf46b20a968d9edfe5379f02ffc4ff845bdc26f3f885e8c",
|
| 156 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0048.pt",
|
| 157 |
"bytes": 268976
|
| 158 |
},
|
| 159 |
{
|
| 160 |
+
"sha256": "bd2526fced8e5ec09ad957fec56eb5138505edaacfd40c8ffc0335f0748051c6",
|
| 161 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0056.pt",
|
| 162 |
"bytes": 268976
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"sha256": "bcbf846ee11028b6446dd47f735a4eee5539c646622d22c71909db9fb5e156ec",
|
| 166 |
+
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0064.pt",
|
| 167 |
+
"bytes": 268976
|
| 168 |
}
|
| 169 |
]
|
| 170 |
}
|