MHC-A1 durable progress index
Browse files
experiments/MHC_REAL_A1/progress.json
CHANGED
|
@@ -1,18 +1,7 @@
|
|
| 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,
|
|
@@ -20,7 +9,7 @@
|
|
| 20 |
"step": 0,
|
| 21 |
"loss_train": 0.09119217842817307,
|
| 22 |
"grad_norm": 0.013730722479522228,
|
| 23 |
-
"head_grad_norm": 1.
|
| 24 |
"q0_trials": [
|
| 25 |
{
|
| 26 |
"radius": 0.0003,
|
|
@@ -54,7 +43,7 @@
|
|
| 54 |
"loss_train": 0.08606645464897156,
|
| 55 |
"W3_MSE": 0.1147225337723891,
|
| 56 |
"W4_MSE": 0.11396808549761772,
|
| 57 |
-
"ctrl_max_rms": 0.
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"seed": 17,
|
|
@@ -63,7 +52,7 @@
|
|
| 63 |
"loss_train": 0.1242414116859436,
|
| 64 |
"W3_MSE": 0.11465953538815181,
|
| 65 |
"W4_MSE": 0.11387925470868747,
|
| 66 |
-
"ctrl_max_rms": 0.
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"seed": 17,
|
|
@@ -71,8 +60,8 @@
|
|
| 71 |
"step": 24,
|
| 72 |
"loss_train": 0.09662917256355286,
|
| 73 |
"W3_MSE": 0.11453648408253987,
|
| 74 |
-
"W4_MSE": 0.
|
| 75 |
-
"ctrl_max_rms": 0.
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"seed": 17,
|
|
@@ -81,7 +70,7 @@
|
|
| 81 |
"loss_train": 0.1582513302564621,
|
| 82 |
"W3_MSE": 0.1143090259283781,
|
| 83 |
"W4_MSE": 0.11331315711140633,
|
| 84 |
-
"ctrl_max_rms": 0.
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"seed": 17,
|
|
@@ -98,15 +87,15 @@
|
|
| 98 |
"step": 48,
|
| 99 |
"loss_train": 0.10963404178619385,
|
| 100 |
"W3_MSE": 0.1130196029941241,
|
| 101 |
-
"W4_MSE": 0.
|
| 102 |
-
"ctrl_max_rms": 0.
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"seed": 17,
|
| 106 |
"arm": "stateless",
|
| 107 |
"step": 56,
|
| 108 |
"loss_train": 0.10562591254711151,
|
| 109 |
-
"W3_MSE": 0.
|
| 110 |
"W4_MSE": 0.10920579296847184,
|
| 111 |
"ctrl_max_rms": 0.004299115234365066
|
| 112 |
},
|
|
@@ -116,8 +105,8 @@
|
|
| 116 |
"step": 64,
|
| 117 |
"loss_train": 0.1330445259809494,
|
| 118 |
"W3_MSE": 0.11103641552229722,
|
| 119 |
-
"W4_MSE": 0.
|
| 120 |
-
"ctrl_max_rms": 0.
|
| 121 |
}
|
| 122 |
],
|
| 123 |
"checkpoints": [
|
|
@@ -127,42 +116,42 @@
|
|
| 127 |
"bytes": 93186
|
| 128 |
},
|
| 129 |
{
|
| 130 |
-
"sha256": "
|
| 131 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0008.pt",
|
| 132 |
"bytes": 268976
|
| 133 |
},
|
| 134 |
{
|
| 135 |
-
"sha256": "
|
| 136 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0016.pt",
|
| 137 |
"bytes": 268976
|
| 138 |
},
|
| 139 |
{
|
| 140 |
-
"sha256": "
|
| 141 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0024.pt",
|
| 142 |
"bytes": 268976
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"sha256": "
|
| 146 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0032.pt",
|
| 147 |
"bytes": 268976
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"sha256": "
|
| 151 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0040.pt",
|
| 152 |
"bytes": 268976
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"sha256": "
|
| 156 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0048.pt",
|
| 157 |
"bytes": 268976
|
| 158 |
},
|
| 159 |
{
|
| 160 |
-
"sha256": "
|
| 161 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0056.pt",
|
| 162 |
"bytes": 268976
|
| 163 |
},
|
| 164 |
{
|
| 165 |
-
"sha256": "
|
| 166 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0064.pt",
|
| 167 |
"bytes": 268976
|
| 168 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"contract_source_sha": "498fa31f672759981d3039c03705cb720cd0ac799f78fd78e33acbcc71e5ee18",
|
| 3 |
"steps": 64,
|
| 4 |
+
"results": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"history": [
|
| 6 |
{
|
| 7 |
"seed": 17,
|
|
|
|
| 9 |
"step": 0,
|
| 10 |
"loss_train": 0.09119217842817307,
|
| 11 |
"grad_norm": 0.013730722479522228,
|
| 12 |
+
"head_grad_norm": 1.4221210449250066e-06,
|
| 13 |
"q0_trials": [
|
| 14 |
{
|
| 15 |
"radius": 0.0003,
|
|
|
|
| 43 |
"loss_train": 0.08606645464897156,
|
| 44 |
"W3_MSE": 0.1147225337723891,
|
| 45 |
"W4_MSE": 0.11396808549761772,
|
| 46 |
+
"ctrl_max_rms": 0.00018752604228211567
|
| 47 |
},
|
| 48 |
{
|
| 49 |
"seed": 17,
|
|
|
|
| 52 |
"loss_train": 0.1242414116859436,
|
| 53 |
"W3_MSE": 0.11465953538815181,
|
| 54 |
"W4_MSE": 0.11387925470868747,
|
| 55 |
+
"ctrl_max_rms": 0.00030438662846184644
|
| 56 |
},
|
| 57 |
{
|
| 58 |
"seed": 17,
|
|
|
|
| 60 |
"step": 24,
|
| 61 |
"loss_train": 0.09662917256355286,
|
| 62 |
"W3_MSE": 0.11453648408253987,
|
| 63 |
+
"W4_MSE": 0.11368757920960586,
|
| 64 |
+
"ctrl_max_rms": 0.0003923155600205064
|
| 65 |
},
|
| 66 |
{
|
| 67 |
"seed": 17,
|
|
|
|
| 70 |
"loss_train": 0.1582513302564621,
|
| 71 |
"W3_MSE": 0.1143090259283781,
|
| 72 |
"W4_MSE": 0.11331315711140633,
|
| 73 |
+
"ctrl_max_rms": 0.0005296767340041697
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"seed": 17,
|
|
|
|
| 87 |
"step": 48,
|
| 88 |
"loss_train": 0.10963404178619385,
|
| 89 |
"W3_MSE": 0.1130196029941241,
|
| 90 |
+
"W4_MSE": 0.11111373826861382,
|
| 91 |
+
"ctrl_max_rms": 0.00205805353471078
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"seed": 17,
|
| 95 |
"arm": "stateless",
|
| 96 |
"step": 56,
|
| 97 |
"loss_train": 0.10562591254711151,
|
| 98 |
+
"W3_MSE": 0.11191886352996032,
|
| 99 |
"W4_MSE": 0.10920579296847184,
|
| 100 |
"ctrl_max_rms": 0.004299115234365066
|
| 101 |
},
|
|
|
|
| 105 |
"step": 64,
|
| 106 |
"loss_train": 0.1330445259809494,
|
| 107 |
"W3_MSE": 0.11103641552229722,
|
| 108 |
+
"W4_MSE": 0.10791260438660781,
|
| 109 |
+
"ctrl_max_rms": 0.00528129100954781
|
| 110 |
}
|
| 111 |
],
|
| 112 |
"checkpoints": [
|
|
|
|
| 116 |
"bytes": 93186
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"sha256": "8564fa6b02b9004df33b139b15888e345f27bc9392db5b1bdd36918417abb5d3",
|
| 120 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0008.pt",
|
| 121 |
"bytes": 268976
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"sha256": "42792020756dbc501ab231c407134a90b13db10de7d9dca0192c4da6eabafbae",
|
| 125 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0016.pt",
|
| 126 |
"bytes": 268976
|
| 127 |
},
|
| 128 |
{
|
| 129 |
+
"sha256": "c1297071cf2cd8ef2da147b116cd01823b41f9af63bc2a603e075a72ec9936ca",
|
| 130 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0024.pt",
|
| 131 |
"bytes": 268976
|
| 132 |
},
|
| 133 |
{
|
| 134 |
+
"sha256": "c95fcb3a196dfed881e2a01f5b54b8dea25fbfe13f5eae71336af1c671f71d14",
|
| 135 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0032.pt",
|
| 136 |
"bytes": 268976
|
| 137 |
},
|
| 138 |
{
|
| 139 |
+
"sha256": "84d1bb51dafe0dc9ab687d2bfaa6f2e590a6a257a72053a9d05610754a27e554",
|
| 140 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0040.pt",
|
| 141 |
"bytes": 268976
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"sha256": "a2a4ffa22bf4208049e3b06accfb87699cb28b0987592bbbbdada6aea7410750",
|
| 145 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0048.pt",
|
| 146 |
"bytes": 268976
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"sha256": "99d7cae2f26351d8183ceb0b2c152adf512324e147ffbce0c8b0a5fd4c34163a",
|
| 150 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0056.pt",
|
| 151 |
"bytes": 268976
|
| 152 |
},
|
| 153 |
{
|
| 154 |
+
"sha256": "e2a449c3025fe0223022be26a6a9c1ee8e6a60e46f146208f6a7a532f9dba37e",
|
| 155 |
"hf_path": "experiments/MHC_REAL_A1/pilot_seed17_stateless_step0064.pt",
|
| 156 |
"bytes": 268976
|
| 157 |
}
|