Run 11. Outer Step 78. Inner Step 9.
Browse files- config.json +40 -40
- gradients.pt +1 -1
- inner_optimizer.pt +1 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -16,33 +16,33 @@
|
|
| 16 |
"109": "SUCCESS",
|
| 17 |
"11": "NOT_ALIVE",
|
| 18 |
"110": "NOT_ALIVE",
|
| 19 |
-
"111": "
|
| 20 |
"112": "NOT_ALIVE",
|
| 21 |
-
"113": "
|
| 22 |
"114": "NOT_ALIVE",
|
| 23 |
"115": "SUCCESS",
|
| 24 |
-
"116": "
|
| 25 |
"117": "NON_PARTICIPATING",
|
| 26 |
"118": "SUCCESS",
|
| 27 |
"119": "NOT_ALIVE",
|
| 28 |
"12": "NOT_ALIVE",
|
| 29 |
-
"120": "
|
| 30 |
"121": "NOT_ALIVE",
|
| 31 |
"122": "NOT_ALIVE",
|
| 32 |
"123": "NON_PARTICIPATING",
|
| 33 |
"124": "SUCCESS",
|
| 34 |
-
"125": "
|
| 35 |
"126": "NON_PARTICIPATING",
|
| 36 |
"127": "NOT_ALIVE",
|
| 37 |
"128": "NOT_ALIVE",
|
| 38 |
"129": "NOT_ALIVE",
|
| 39 |
-
"13": "
|
| 40 |
"130": "SUCCESS",
|
| 41 |
"131": "NOT_ALIVE",
|
| 42 |
"132": "NOT_ALIVE",
|
| 43 |
-
"133": "
|
| 44 |
"134": "SUCCESS",
|
| 45 |
-
"135": "
|
| 46 |
"136": "NOT_ALIVE",
|
| 47 |
"137": "SUCCESS",
|
| 48 |
"138": "NOT_ALIVE",
|
|
@@ -53,7 +53,7 @@
|
|
| 53 |
"142": "SUCCESS",
|
| 54 |
"143": "SUCCESS",
|
| 55 |
"144": "NOT_ALIVE",
|
| 56 |
-
"145": "
|
| 57 |
"146": "NOT_ALIVE",
|
| 58 |
"147": "NOT_ALIVE",
|
| 59 |
"148": "NOT_ALIVE",
|
|
@@ -71,21 +71,21 @@
|
|
| 71 |
"159": "SUCCESS",
|
| 72 |
"16": "NOT_ALIVE",
|
| 73 |
"160": "NON_PARTICIPATING",
|
| 74 |
-
"161": "
|
| 75 |
-
"162": "
|
| 76 |
"163": "NON_PARTICIPATING",
|
| 77 |
"164": "NOT_ALIVE",
|
| 78 |
-
"165": "
|
| 79 |
"166": "SUCCESS",
|
| 80 |
"167": "NOT_ALIVE",
|
| 81 |
"168": "SUCCESS",
|
| 82 |
"169": "SUCCESS",
|
| 83 |
"17": "NOT_ALIVE",
|
| 84 |
-
"170": "
|
| 85 |
"171": "NOT_ALIVE",
|
| 86 |
"172": "NOT_ALIVE",
|
| 87 |
"173": "NON_PARTICIPATING",
|
| 88 |
-
"174": "
|
| 89 |
"175": "SUCCESS",
|
| 90 |
"176": "NOT_ALIVE",
|
| 91 |
"177": "NON_PARTICIPATING",
|
|
@@ -101,14 +101,14 @@
|
|
| 101 |
"186": "SUCCESS",
|
| 102 |
"187": "NOT_ALIVE",
|
| 103 |
"188": "NON_PARTICIPATING",
|
| 104 |
-
"189": "
|
| 105 |
-
"19": "
|
| 106 |
-
"190": "
|
| 107 |
"191": "NOT_ALIVE",
|
| 108 |
"192": "NOT_ALIVE",
|
| 109 |
"193": "NOT_ALIVE",
|
| 110 |
"194": "NON_PARTICIPATING",
|
| 111 |
-
"195": "
|
| 112 |
"196": "NON_PARTICIPATING",
|
| 113 |
"197": "NON_PARTICIPATING",
|
| 114 |
"198": "NON_PARTICIPATING",
|
|
@@ -130,20 +130,20 @@
|
|
| 130 |
"211": "NOT_ALIVE",
|
| 131 |
"212": "NOT_ALIVE",
|
| 132 |
"213": "NON_PARTICIPATING",
|
| 133 |
-
"214": "
|
| 134 |
"215": "NOT_ALIVE",
|
| 135 |
"216": "NON_PARTICIPATING",
|
| 136 |
-
"217": "
|
| 137 |
"218": "NOT_ALIVE",
|
| 138 |
"219": "NON_PARTICIPATING",
|
| 139 |
"22": "NOT_ALIVE",
|
| 140 |
-
"220": "
|
| 141 |
"221": "NON_PARTICIPATING",
|
| 142 |
"222": "NOT_ALIVE",
|
| 143 |
"223": "SUCCESS",
|
| 144 |
"224": "NOT_ALIVE",
|
| 145 |
"225": "NON_PARTICIPATING",
|
| 146 |
-
"226": "
|
| 147 |
"227": "NOT_ALIVE",
|
| 148 |
"228": "NOT_ALIVE",
|
| 149 |
"229": "NON_PARTICIPATING",
|
|
@@ -156,9 +156,9 @@
|
|
| 156 |
"235": "NON_PARTICIPATING",
|
| 157 |
"236": "NON_PARTICIPATING",
|
| 158 |
"237": "SUCCESS",
|
| 159 |
-
"238": "
|
| 160 |
"239": "NOT_ALIVE",
|
| 161 |
-
"24": "
|
| 162 |
"240": "NOT_ALIVE",
|
| 163 |
"241": "NON_PARTICIPATING",
|
| 164 |
"242": "NOT_ALIVE",
|
|
@@ -166,13 +166,13 @@
|
|
| 166 |
"244": "NON_PARTICIPATING",
|
| 167 |
"245": "NON_PARTICIPATING",
|
| 168 |
"246": "NON_PARTICIPATING",
|
| 169 |
-
"247": "
|
| 170 |
"248": "SUCCESS",
|
| 171 |
"249": "NOT_ALIVE",
|
| 172 |
"25": "SUCCESS",
|
| 173 |
"250": "NON_PARTICIPATING",
|
| 174 |
"251": "NON_PARTICIPATING",
|
| 175 |
-
"252": "
|
| 176 |
"253": "NON_PARTICIPATING",
|
| 177 |
"254": "NOT_ALIVE",
|
| 178 |
"255": "NOT_ALIVE",
|
|
@@ -185,15 +185,15 @@
|
|
| 185 |
"31": "SUCCESS",
|
| 186 |
"32": "NOT_ALIVE",
|
| 187 |
"33": "NOT_ALIVE",
|
| 188 |
-
"34": "
|
| 189 |
-
"35": "
|
| 190 |
"36": "NON_PARTICIPATING",
|
| 191 |
"37": "NOT_ALIVE",
|
| 192 |
"38": "NON_PARTICIPATING",
|
| 193 |
"39": "NON_PARTICIPATING",
|
| 194 |
"4": "NOT_ALIVE",
|
| 195 |
"40": "NOT_ALIVE",
|
| 196 |
-
"41": "
|
| 197 |
"42": "NOT_ALIVE",
|
| 198 |
"43": "NON_PARTICIPATING",
|
| 199 |
"44": "NON_PARTICIPATING",
|
|
@@ -205,9 +205,9 @@
|
|
| 205 |
"5": "NOT_ALIVE",
|
| 206 |
"50": "NOT_ALIVE",
|
| 207 |
"51": "NON_PARTICIPATING",
|
| 208 |
-
"52": "
|
| 209 |
"53": "SUCCESS",
|
| 210 |
-
"54": "
|
| 211 |
"55": "NOT_ALIVE",
|
| 212 |
"56": "NOT_ALIVE",
|
| 213 |
"57": "SUCCESS",
|
|
@@ -215,7 +215,7 @@
|
|
| 215 |
"59": "NON_PARTICIPATING",
|
| 216 |
"6": "NOT_ALIVE",
|
| 217 |
"60": "NON_PARTICIPATING",
|
| 218 |
-
"61": "
|
| 219 |
"62": "NOT_ALIVE",
|
| 220 |
"63": "NON_PARTICIPATING",
|
| 221 |
"64": "SUCCESS",
|
|
@@ -230,9 +230,9 @@
|
|
| 230 |
"72": "NOT_ALIVE",
|
| 231 |
"73": "SUCCESS",
|
| 232 |
"74": "NOT_ALIVE",
|
| 233 |
-
"75": "
|
| 234 |
"76": "SUCCESS",
|
| 235 |
-
"77": "
|
| 236 |
"78": "NON_PARTICIPATING",
|
| 237 |
"79": "NON_PARTICIPATING",
|
| 238 |
"8": "SUCCESS",
|
|
@@ -241,8 +241,8 @@
|
|
| 241 |
"82": "NOT_ALIVE",
|
| 242 |
"83": "SUCCESS",
|
| 243 |
"84": "NON_PARTICIPATING",
|
| 244 |
-
"85": "
|
| 245 |
-
"86": "
|
| 246 |
"87": "SUCCESS",
|
| 247 |
"88": "NON_PARTICIPATING",
|
| 248 |
"89": "NOT_ALIVE",
|
|
@@ -264,17 +264,17 @@
|
|
| 264 |
"attention_bias": false,
|
| 265 |
"attention_dropout": 0.0,
|
| 266 |
"block_list": [
|
| 267 |
-
|
| 268 |
-
|
| 269 |
],
|
| 270 |
"bos_token_id": 1,
|
| 271 |
"eos_token_id": 2,
|
| 272 |
"hidden_act": "silu",
|
| 273 |
"hidden_size": 2048,
|
| 274 |
"initializer_range": 0.02,
|
| 275 |
-
"inner_step":
|
| 276 |
"intermediate_size": 5632,
|
| 277 |
-
"last_allreduce_block":
|
| 278 |
"max_position_embeddings": 2048,
|
| 279 |
"mlp_bias": false,
|
| 280 |
"model_type": "llama",
|
|
|
|
| 16 |
"109": "SUCCESS",
|
| 17 |
"11": "NOT_ALIVE",
|
| 18 |
"110": "NOT_ALIVE",
|
| 19 |
+
"111": "NON_PARTICIPATING",
|
| 20 |
"112": "NOT_ALIVE",
|
| 21 |
+
"113": "NON_PARTICIPATING",
|
| 22 |
"114": "NOT_ALIVE",
|
| 23 |
"115": "SUCCESS",
|
| 24 |
+
"116": "NON_PARTICIPATING",
|
| 25 |
"117": "NON_PARTICIPATING",
|
| 26 |
"118": "SUCCESS",
|
| 27 |
"119": "NOT_ALIVE",
|
| 28 |
"12": "NOT_ALIVE",
|
| 29 |
+
"120": "NOT_ALIVE",
|
| 30 |
"121": "NOT_ALIVE",
|
| 31 |
"122": "NOT_ALIVE",
|
| 32 |
"123": "NON_PARTICIPATING",
|
| 33 |
"124": "SUCCESS",
|
| 34 |
+
"125": "NON_PARTICIPATING",
|
| 35 |
"126": "NON_PARTICIPATING",
|
| 36 |
"127": "NOT_ALIVE",
|
| 37 |
"128": "NOT_ALIVE",
|
| 38 |
"129": "NOT_ALIVE",
|
| 39 |
+
"13": "SUCCESS",
|
| 40 |
"130": "SUCCESS",
|
| 41 |
"131": "NOT_ALIVE",
|
| 42 |
"132": "NOT_ALIVE",
|
| 43 |
+
"133": "NOT_ALIVE",
|
| 44 |
"134": "SUCCESS",
|
| 45 |
+
"135": "SUCCESS",
|
| 46 |
"136": "NOT_ALIVE",
|
| 47 |
"137": "SUCCESS",
|
| 48 |
"138": "NOT_ALIVE",
|
|
|
|
| 53 |
"142": "SUCCESS",
|
| 54 |
"143": "SUCCESS",
|
| 55 |
"144": "NOT_ALIVE",
|
| 56 |
+
"145": "NOT_ALIVE",
|
| 57 |
"146": "NOT_ALIVE",
|
| 58 |
"147": "NOT_ALIVE",
|
| 59 |
"148": "NOT_ALIVE",
|
|
|
|
| 71 |
"159": "SUCCESS",
|
| 72 |
"16": "NOT_ALIVE",
|
| 73 |
"160": "NON_PARTICIPATING",
|
| 74 |
+
"161": "NOT_ALIVE",
|
| 75 |
+
"162": "NOT_ALIVE",
|
| 76 |
"163": "NON_PARTICIPATING",
|
| 77 |
"164": "NOT_ALIVE",
|
| 78 |
+
"165": "SUCCESS",
|
| 79 |
"166": "SUCCESS",
|
| 80 |
"167": "NOT_ALIVE",
|
| 81 |
"168": "SUCCESS",
|
| 82 |
"169": "SUCCESS",
|
| 83 |
"17": "NOT_ALIVE",
|
| 84 |
+
"170": "NOT_ALIVE",
|
| 85 |
"171": "NOT_ALIVE",
|
| 86 |
"172": "NOT_ALIVE",
|
| 87 |
"173": "NON_PARTICIPATING",
|
| 88 |
+
"174": "NON_PARTICIPATING",
|
| 89 |
"175": "SUCCESS",
|
| 90 |
"176": "NOT_ALIVE",
|
| 91 |
"177": "NON_PARTICIPATING",
|
|
|
|
| 101 |
"186": "SUCCESS",
|
| 102 |
"187": "NOT_ALIVE",
|
| 103 |
"188": "NON_PARTICIPATING",
|
| 104 |
+
"189": "NON_PARTICIPATING",
|
| 105 |
+
"19": "NOT_ALIVE",
|
| 106 |
+
"190": "SUCCESS",
|
| 107 |
"191": "NOT_ALIVE",
|
| 108 |
"192": "NOT_ALIVE",
|
| 109 |
"193": "NOT_ALIVE",
|
| 110 |
"194": "NON_PARTICIPATING",
|
| 111 |
+
"195": "NOT_ALIVE",
|
| 112 |
"196": "NON_PARTICIPATING",
|
| 113 |
"197": "NON_PARTICIPATING",
|
| 114 |
"198": "NON_PARTICIPATING",
|
|
|
|
| 130 |
"211": "NOT_ALIVE",
|
| 131 |
"212": "NOT_ALIVE",
|
| 132 |
"213": "NON_PARTICIPATING",
|
| 133 |
+
"214": "NOT_ALIVE",
|
| 134 |
"215": "NOT_ALIVE",
|
| 135 |
"216": "NON_PARTICIPATING",
|
| 136 |
+
"217": "NON_PARTICIPATING",
|
| 137 |
"218": "NOT_ALIVE",
|
| 138 |
"219": "NON_PARTICIPATING",
|
| 139 |
"22": "NOT_ALIVE",
|
| 140 |
+
"220": "NOT_ALIVE",
|
| 141 |
"221": "NON_PARTICIPATING",
|
| 142 |
"222": "NOT_ALIVE",
|
| 143 |
"223": "SUCCESS",
|
| 144 |
"224": "NOT_ALIVE",
|
| 145 |
"225": "NON_PARTICIPATING",
|
| 146 |
+
"226": "NOT_ALIVE",
|
| 147 |
"227": "NOT_ALIVE",
|
| 148 |
"228": "NOT_ALIVE",
|
| 149 |
"229": "NON_PARTICIPATING",
|
|
|
|
| 156 |
"235": "NON_PARTICIPATING",
|
| 157 |
"236": "NON_PARTICIPATING",
|
| 158 |
"237": "SUCCESS",
|
| 159 |
+
"238": "SUCCESS",
|
| 160 |
"239": "NOT_ALIVE",
|
| 161 |
+
"24": "NOT_ALIVE",
|
| 162 |
"240": "NOT_ALIVE",
|
| 163 |
"241": "NON_PARTICIPATING",
|
| 164 |
"242": "NOT_ALIVE",
|
|
|
|
| 166 |
"244": "NON_PARTICIPATING",
|
| 167 |
"245": "NON_PARTICIPATING",
|
| 168 |
"246": "NON_PARTICIPATING",
|
| 169 |
+
"247": "NOT_ALIVE",
|
| 170 |
"248": "SUCCESS",
|
| 171 |
"249": "NOT_ALIVE",
|
| 172 |
"25": "SUCCESS",
|
| 173 |
"250": "NON_PARTICIPATING",
|
| 174 |
"251": "NON_PARTICIPATING",
|
| 175 |
+
"252": "SUCCESS",
|
| 176 |
"253": "NON_PARTICIPATING",
|
| 177 |
"254": "NOT_ALIVE",
|
| 178 |
"255": "NOT_ALIVE",
|
|
|
|
| 185 |
"31": "SUCCESS",
|
| 186 |
"32": "NOT_ALIVE",
|
| 187 |
"33": "NOT_ALIVE",
|
| 188 |
+
"34": "NON_PARTICIPATING",
|
| 189 |
+
"35": "NON_PARTICIPATING",
|
| 190 |
"36": "NON_PARTICIPATING",
|
| 191 |
"37": "NOT_ALIVE",
|
| 192 |
"38": "NON_PARTICIPATING",
|
| 193 |
"39": "NON_PARTICIPATING",
|
| 194 |
"4": "NOT_ALIVE",
|
| 195 |
"40": "NOT_ALIVE",
|
| 196 |
+
"41": "NON_PARTICIPATING",
|
| 197 |
"42": "NOT_ALIVE",
|
| 198 |
"43": "NON_PARTICIPATING",
|
| 199 |
"44": "NON_PARTICIPATING",
|
|
|
|
| 205 |
"5": "NOT_ALIVE",
|
| 206 |
"50": "NOT_ALIVE",
|
| 207 |
"51": "NON_PARTICIPATING",
|
| 208 |
+
"52": "NON_PARTICIPATING",
|
| 209 |
"53": "SUCCESS",
|
| 210 |
+
"54": "SUCCESS",
|
| 211 |
"55": "NOT_ALIVE",
|
| 212 |
"56": "NOT_ALIVE",
|
| 213 |
"57": "SUCCESS",
|
|
|
|
| 215 |
"59": "NON_PARTICIPATING",
|
| 216 |
"6": "NOT_ALIVE",
|
| 217 |
"60": "NON_PARTICIPATING",
|
| 218 |
+
"61": "SUCCESS",
|
| 219 |
"62": "NOT_ALIVE",
|
| 220 |
"63": "NON_PARTICIPATING",
|
| 221 |
"64": "SUCCESS",
|
|
|
|
| 230 |
"72": "NOT_ALIVE",
|
| 231 |
"73": "SUCCESS",
|
| 232 |
"74": "NOT_ALIVE",
|
| 233 |
+
"75": "NON_PARTICIPATING",
|
| 234 |
"76": "SUCCESS",
|
| 235 |
+
"77": "NON_PARTICIPATING",
|
| 236 |
"78": "NON_PARTICIPATING",
|
| 237 |
"79": "NON_PARTICIPATING",
|
| 238 |
"8": "SUCCESS",
|
|
|
|
| 241 |
"82": "NOT_ALIVE",
|
| 242 |
"83": "SUCCESS",
|
| 243 |
"84": "NON_PARTICIPATING",
|
| 244 |
+
"85": "NON_PARTICIPATING",
|
| 245 |
+
"86": "NOT_ALIVE",
|
| 246 |
"87": "SUCCESS",
|
| 247 |
"88": "NON_PARTICIPATING",
|
| 248 |
"89": "NOT_ALIVE",
|
|
|
|
| 264 |
"attention_bias": false,
|
| 265 |
"attention_dropout": 0.0,
|
| 266 |
"block_list": [
|
| 267 |
+
6583511,
|
| 268 |
+
6583540
|
| 269 |
],
|
| 270 |
"bos_token_id": 1,
|
| 271 |
"eos_token_id": 2,
|
| 272 |
"hidden_act": "silu",
|
| 273 |
"hidden_size": 2048,
|
| 274 |
"initializer_range": 0.02,
|
| 275 |
+
"inner_step": 9,
|
| 276 |
"intermediate_size": 5632,
|
| 277 |
+
"last_allreduce_block": 6583488,
|
| 278 |
"max_position_embeddings": 2048,
|
| 279 |
"mlp_bias": false,
|
| 280 |
"model_type": "llama",
|
gradients.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 88390091
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec979699f4652ccb82e1cf003a5f6d4272b4d597377d3f6cbcf5d14be9ff9019
|
| 3 |
size 88390091
|
inner_optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4924928047
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3adfa1c899c295097849a8f1251df1e97b13acf8c613f9f4300ea0af9dc303a
|
| 3 |
size 4924928047
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4400216536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3ef25a7731bc350def4ffed12bfefe00798d511fe37ded4ab7de5036c7045ad
|
| 3 |
size 4400216536
|