Run 11. Outer Step 246. Inner Step 9.
Browse files- config.json +44 -44
- gradients.pt +1 -1
- inner_optimizer.pt +1 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -3,28 +3,28 @@
|
|
| 3 |
"all_reduce_scores": {
|
| 4 |
"0": "NOT_ALIVE",
|
| 5 |
"1": "NOT_ALIVE",
|
| 6 |
-
"10": "
|
| 7 |
"100": "NOT_ALIVE",
|
| 8 |
"101": "SUCCESS",
|
| 9 |
"102": "NOT_ALIVE",
|
| 10 |
-
"103": "
|
| 11 |
"104": "SUCCESS",
|
| 12 |
"105": "NOT_ALIVE",
|
| 13 |
"106": "NOT_ALIVE",
|
| 14 |
-
"107": "
|
| 15 |
"108": "NON_PARTICIPATING",
|
| 16 |
"109": "SUCCESS",
|
| 17 |
"11": "NOT_ALIVE",
|
| 18 |
"110": "SUCCESS",
|
| 19 |
"111": "NON_PARTICIPATING",
|
| 20 |
-
"112": "
|
| 21 |
"113": "NOT_ALIVE",
|
| 22 |
-
"114": "
|
| 23 |
"115": "NOT_ALIVE",
|
| 24 |
-
"116": "
|
| 25 |
"117": "NOT_ALIVE",
|
| 26 |
"118": "NOT_ALIVE",
|
| 27 |
-
"119": "
|
| 28 |
"12": "NOT_ALIVE",
|
| 29 |
"120": "NOT_ALIVE",
|
| 30 |
"121": "SUCCESS",
|
|
@@ -34,28 +34,28 @@
|
|
| 34 |
"125": "NOT_ALIVE",
|
| 35 |
"126": "NOT_ALIVE",
|
| 36 |
"127": "SUCCESS",
|
| 37 |
-
"128": "
|
| 38 |
"129": "NOT_ALIVE",
|
| 39 |
"13": "SUCCESS",
|
| 40 |
-
"130": "
|
| 41 |
"131": "NOT_ALIVE",
|
| 42 |
"132": "NOT_ALIVE",
|
| 43 |
"133": "NOT_ALIVE",
|
| 44 |
-
"134": "
|
| 45 |
"135": "SUCCESS",
|
| 46 |
"136": "NOT_ALIVE",
|
| 47 |
"137": "NOT_ALIVE",
|
| 48 |
"138": "NOT_ALIVE",
|
| 49 |
"139": "NON_PARTICIPATING",
|
| 50 |
-
"14": "
|
| 51 |
"140": "SUCCESS",
|
| 52 |
-
"141": "
|
| 53 |
"142": "NOT_ALIVE",
|
| 54 |
"143": "NON_PARTICIPATING",
|
| 55 |
"144": "NOT_ALIVE",
|
| 56 |
"145": "NOT_ALIVE",
|
| 57 |
"146": "NOT_ALIVE",
|
| 58 |
-
"147": "
|
| 59 |
"148": "SUCCESS",
|
| 60 |
"149": "NOT_ALIVE",
|
| 61 |
"15": "NON_PARTICIPATING",
|
|
@@ -69,7 +69,7 @@
|
|
| 69 |
"157": "NON_PARTICIPATING",
|
| 70 |
"158": "NOT_ALIVE",
|
| 71 |
"159": "NOT_ALIVE",
|
| 72 |
-
"16": "
|
| 73 |
"160": "SUCCESS",
|
| 74 |
"161": "NOT_ALIVE",
|
| 75 |
"162": "SUCCESS",
|
|
@@ -79,7 +79,7 @@
|
|
| 79 |
"166": "NOT_ALIVE",
|
| 80 |
"167": "SUCCESS",
|
| 81 |
"168": "NOT_ALIVE",
|
| 82 |
-
"169": "
|
| 83 |
"17": "NOT_ALIVE",
|
| 84 |
"170": "NOT_ALIVE",
|
| 85 |
"171": "NOT_ALIVE",
|
|
@@ -89,7 +89,7 @@
|
|
| 89 |
"175": "NON_PARTICIPATING",
|
| 90 |
"176": "NOT_ALIVE",
|
| 91 |
"177": "NOT_ALIVE",
|
| 92 |
-
"178": "
|
| 93 |
"179": "SUCCESS",
|
| 94 |
"18": "NOT_ALIVE",
|
| 95 |
"180": "NOT_ALIVE",
|
|
@@ -98,8 +98,8 @@
|
|
| 98 |
"183": "NOT_ALIVE",
|
| 99 |
"184": "SUCCESS",
|
| 100 |
"185": "SUCCESS",
|
| 101 |
-
"186": "
|
| 102 |
-
"187": "
|
| 103 |
"188": "NOT_ALIVE",
|
| 104 |
"189": "NOT_ALIVE",
|
| 105 |
"19": "NOT_ALIVE",
|
|
@@ -108,13 +108,13 @@
|
|
| 108 |
"192": "NOT_ALIVE",
|
| 109 |
"193": "SUCCESS",
|
| 110 |
"194": "NOT_ALIVE",
|
| 111 |
-
"195": "
|
| 112 |
"196": "NOT_ALIVE",
|
| 113 |
"197": "SUCCESS",
|
| 114 |
"198": "NOT_ALIVE",
|
| 115 |
-
"199": "
|
| 116 |
"2": "NOT_ALIVE",
|
| 117 |
-
"20": "
|
| 118 |
"200": "SUCCESS",
|
| 119 |
"201": "NON_PARTICIPATING",
|
| 120 |
"202": "NOT_ALIVE",
|
|
@@ -127,52 +127,52 @@
|
|
| 127 |
"209": "SUCCESS",
|
| 128 |
"21": "NOT_ALIVE",
|
| 129 |
"210": "NOT_ALIVE",
|
| 130 |
-
"211": "
|
| 131 |
"212": "NOT_ALIVE",
|
| 132 |
"213": "NON_PARTICIPATING",
|
| 133 |
"214": "SUCCESS",
|
| 134 |
-
"215": "
|
| 135 |
"216": "NON_PARTICIPATING",
|
| 136 |
-
"217": "
|
| 137 |
"218": "NOT_ALIVE",
|
| 138 |
"219": "NOT_ALIVE",
|
| 139 |
"22": "NOT_ALIVE",
|
| 140 |
"220": "NOT_ALIVE",
|
| 141 |
-
"221": "
|
| 142 |
"222": "NOT_ALIVE",
|
| 143 |
"223": "NOT_ALIVE",
|
| 144 |
"224": "NOT_ALIVE",
|
| 145 |
"225": "NOT_ALIVE",
|
| 146 |
"226": "SUCCESS",
|
| 147 |
-
"227": "
|
| 148 |
"228": "NOT_ALIVE",
|
| 149 |
"229": "NOT_ALIVE",
|
| 150 |
-
"23": "
|
| 151 |
"230": "SUCCESS",
|
| 152 |
"231": "SUCCESS",
|
| 153 |
"232": "NOT_ALIVE",
|
| 154 |
"233": "SUCCESS",
|
| 155 |
"234": "NON_PARTICIPATING",
|
| 156 |
-
"235": "
|
| 157 |
"236": "NOT_ALIVE",
|
| 158 |
"237": "SUCCESS",
|
| 159 |
"238": "SUCCESS",
|
| 160 |
"239": "NOT_ALIVE",
|
| 161 |
-
"24": "
|
| 162 |
"240": "NOT_ALIVE",
|
| 163 |
"241": "SUCCESS",
|
| 164 |
"242": "NOT_ALIVE",
|
| 165 |
"243": "NOT_ALIVE",
|
| 166 |
"244": "NOT_ALIVE",
|
| 167 |
-
"245": "
|
| 168 |
"246": "NOT_ALIVE",
|
| 169 |
"247": "NON_PARTICIPATING",
|
| 170 |
"248": "NOT_ALIVE",
|
| 171 |
"249": "NOT_ALIVE",
|
| 172 |
"25": "SUCCESS",
|
| 173 |
"250": "NOT_ALIVE",
|
| 174 |
-
"251": "
|
| 175 |
-
"252": "
|
| 176 |
"253": "NOT_ALIVE",
|
| 177 |
"254": "NOT_ALIVE",
|
| 178 |
"255": "NOT_ALIVE",
|
|
@@ -185,13 +185,13 @@
|
|
| 185 |
"31": "NOT_ALIVE",
|
| 186 |
"32": "NOT_ALIVE",
|
| 187 |
"33": "NOT_ALIVE",
|
| 188 |
-
"34": "
|
| 189 |
"35": "NOT_ALIVE",
|
| 190 |
"36": "NOT_ALIVE",
|
| 191 |
"37": "NON_PARTICIPATING",
|
| 192 |
-
"38": "
|
| 193 |
"39": "NOT_ALIVE",
|
| 194 |
-
"4": "
|
| 195 |
"40": "NOT_ALIVE",
|
| 196 |
"41": "NON_PARTICIPATING",
|
| 197 |
"42": "NOT_ALIVE",
|
|
@@ -207,15 +207,15 @@
|
|
| 207 |
"51": "NON_PARTICIPATING",
|
| 208 |
"52": "NOT_ALIVE",
|
| 209 |
"53": "NON_PARTICIPATING",
|
| 210 |
-
"54": "
|
| 211 |
"55": "NOT_ALIVE",
|
| 212 |
"56": "NOT_ALIVE",
|
| 213 |
-
"57": "
|
| 214 |
"58": "NOT_ALIVE",
|
| 215 |
"59": "NOT_ALIVE",
|
| 216 |
"6": "NOT_ALIVE",
|
| 217 |
"60": "NON_PARTICIPATING",
|
| 218 |
-
"61": "
|
| 219 |
"62": "NON_PARTICIPATING",
|
| 220 |
"63": "NOT_ALIVE",
|
| 221 |
"64": "NOT_ALIVE",
|
|
@@ -234,16 +234,16 @@
|
|
| 234 |
"76": "SUCCESS",
|
| 235 |
"77": "NOT_ALIVE",
|
| 236 |
"78": "NOT_ALIVE",
|
| 237 |
-
"79": "
|
| 238 |
"8": "SUCCESS",
|
| 239 |
-
"80": "
|
| 240 |
"81": "NOT_ALIVE",
|
| 241 |
"82": "NOT_ALIVE",
|
| 242 |
"83": "NON_PARTICIPATING",
|
| 243 |
"84": "NON_PARTICIPATING",
|
| 244 |
"85": "NOT_ALIVE",
|
| 245 |
"86": "NON_PARTICIPATING",
|
| 246 |
-
"87": "
|
| 247 |
"88": "NON_PARTICIPATING",
|
| 248 |
"89": "NON_PARTICIPATING",
|
| 249 |
"9": "NOT_ALIVE",
|
|
@@ -264,8 +264,8 @@
|
|
| 264 |
"attention_bias": false,
|
| 265 |
"attention_dropout": 0.0,
|
| 266 |
"block_list": [
|
| 267 |
-
|
| 268 |
-
|
| 269 |
],
|
| 270 |
"bos_token_id": 1,
|
| 271 |
"dtype": "float32",
|
|
@@ -276,7 +276,7 @@
|
|
| 276 |
"initializer_range": 0.02,
|
| 277 |
"inner_step": 9,
|
| 278 |
"intermediate_size": 5632,
|
| 279 |
-
"last_allreduce_block":
|
| 280 |
"max_position_embeddings": 2048,
|
| 281 |
"mlp_bias": false,
|
| 282 |
"model_type": "llama",
|
|
|
|
| 3 |
"all_reduce_scores": {
|
| 4 |
"0": "NOT_ALIVE",
|
| 5 |
"1": "NOT_ALIVE",
|
| 6 |
+
"10": "NON_PARTICIPATING",
|
| 7 |
"100": "NOT_ALIVE",
|
| 8 |
"101": "SUCCESS",
|
| 9 |
"102": "NOT_ALIVE",
|
| 10 |
+
"103": "NON_PARTICIPATING",
|
| 11 |
"104": "SUCCESS",
|
| 12 |
"105": "NOT_ALIVE",
|
| 13 |
"106": "NOT_ALIVE",
|
| 14 |
+
"107": "SUCCESS",
|
| 15 |
"108": "NON_PARTICIPATING",
|
| 16 |
"109": "SUCCESS",
|
| 17 |
"11": "NOT_ALIVE",
|
| 18 |
"110": "SUCCESS",
|
| 19 |
"111": "NON_PARTICIPATING",
|
| 20 |
+
"112": "NON_PARTICIPATING",
|
| 21 |
"113": "NOT_ALIVE",
|
| 22 |
+
"114": "SUCCESS",
|
| 23 |
"115": "NOT_ALIVE",
|
| 24 |
+
"116": "NON_PARTICIPATING",
|
| 25 |
"117": "NOT_ALIVE",
|
| 26 |
"118": "NOT_ALIVE",
|
| 27 |
+
"119": "NON_PARTICIPATING",
|
| 28 |
"12": "NOT_ALIVE",
|
| 29 |
"120": "NOT_ALIVE",
|
| 30 |
"121": "SUCCESS",
|
|
|
|
| 34 |
"125": "NOT_ALIVE",
|
| 35 |
"126": "NOT_ALIVE",
|
| 36 |
"127": "SUCCESS",
|
| 37 |
+
"128": "NOT_ALIVE",
|
| 38 |
"129": "NOT_ALIVE",
|
| 39 |
"13": "SUCCESS",
|
| 40 |
+
"130": "NON_PARTICIPATING",
|
| 41 |
"131": "NOT_ALIVE",
|
| 42 |
"132": "NOT_ALIVE",
|
| 43 |
"133": "NOT_ALIVE",
|
| 44 |
+
"134": "NOT_ALIVE",
|
| 45 |
"135": "SUCCESS",
|
| 46 |
"136": "NOT_ALIVE",
|
| 47 |
"137": "NOT_ALIVE",
|
| 48 |
"138": "NOT_ALIVE",
|
| 49 |
"139": "NON_PARTICIPATING",
|
| 50 |
+
"14": "NOT_ALIVE",
|
| 51 |
"140": "SUCCESS",
|
| 52 |
+
"141": "SUCCESS",
|
| 53 |
"142": "NOT_ALIVE",
|
| 54 |
"143": "NON_PARTICIPATING",
|
| 55 |
"144": "NOT_ALIVE",
|
| 56 |
"145": "NOT_ALIVE",
|
| 57 |
"146": "NOT_ALIVE",
|
| 58 |
+
"147": "SUCCESS",
|
| 59 |
"148": "SUCCESS",
|
| 60 |
"149": "NOT_ALIVE",
|
| 61 |
"15": "NON_PARTICIPATING",
|
|
|
|
| 69 |
"157": "NON_PARTICIPATING",
|
| 70 |
"158": "NOT_ALIVE",
|
| 71 |
"159": "NOT_ALIVE",
|
| 72 |
+
"16": "NOT_ALIVE",
|
| 73 |
"160": "SUCCESS",
|
| 74 |
"161": "NOT_ALIVE",
|
| 75 |
"162": "SUCCESS",
|
|
|
|
| 79 |
"166": "NOT_ALIVE",
|
| 80 |
"167": "SUCCESS",
|
| 81 |
"168": "NOT_ALIVE",
|
| 82 |
+
"169": "NON_PARTICIPATING",
|
| 83 |
"17": "NOT_ALIVE",
|
| 84 |
"170": "NOT_ALIVE",
|
| 85 |
"171": "NOT_ALIVE",
|
|
|
|
| 89 |
"175": "NON_PARTICIPATING",
|
| 90 |
"176": "NOT_ALIVE",
|
| 91 |
"177": "NOT_ALIVE",
|
| 92 |
+
"178": "NON_PARTICIPATING",
|
| 93 |
"179": "SUCCESS",
|
| 94 |
"18": "NOT_ALIVE",
|
| 95 |
"180": "NOT_ALIVE",
|
|
|
|
| 98 |
"183": "NOT_ALIVE",
|
| 99 |
"184": "SUCCESS",
|
| 100 |
"185": "SUCCESS",
|
| 101 |
+
"186": "NON_PARTICIPATING",
|
| 102 |
+
"187": "SUCCESS",
|
| 103 |
"188": "NOT_ALIVE",
|
| 104 |
"189": "NOT_ALIVE",
|
| 105 |
"19": "NOT_ALIVE",
|
|
|
|
| 108 |
"192": "NOT_ALIVE",
|
| 109 |
"193": "SUCCESS",
|
| 110 |
"194": "NOT_ALIVE",
|
| 111 |
+
"195": "NOT_ALIVE",
|
| 112 |
"196": "NOT_ALIVE",
|
| 113 |
"197": "SUCCESS",
|
| 114 |
"198": "NOT_ALIVE",
|
| 115 |
+
"199": "NOT_ALIVE",
|
| 116 |
"2": "NOT_ALIVE",
|
| 117 |
+
"20": "SUCCESS",
|
| 118 |
"200": "SUCCESS",
|
| 119 |
"201": "NON_PARTICIPATING",
|
| 120 |
"202": "NOT_ALIVE",
|
|
|
|
| 127 |
"209": "SUCCESS",
|
| 128 |
"21": "NOT_ALIVE",
|
| 129 |
"210": "NOT_ALIVE",
|
| 130 |
+
"211": "SUCCESS",
|
| 131 |
"212": "NOT_ALIVE",
|
| 132 |
"213": "NON_PARTICIPATING",
|
| 133 |
"214": "SUCCESS",
|
| 134 |
+
"215": "NON_PARTICIPATING",
|
| 135 |
"216": "NON_PARTICIPATING",
|
| 136 |
+
"217": "NON_PARTICIPATING",
|
| 137 |
"218": "NOT_ALIVE",
|
| 138 |
"219": "NOT_ALIVE",
|
| 139 |
"22": "NOT_ALIVE",
|
| 140 |
"220": "NOT_ALIVE",
|
| 141 |
+
"221": "NON_PARTICIPATING",
|
| 142 |
"222": "NOT_ALIVE",
|
| 143 |
"223": "NOT_ALIVE",
|
| 144 |
"224": "NOT_ALIVE",
|
| 145 |
"225": "NOT_ALIVE",
|
| 146 |
"226": "SUCCESS",
|
| 147 |
+
"227": "NON_PARTICIPATING",
|
| 148 |
"228": "NOT_ALIVE",
|
| 149 |
"229": "NOT_ALIVE",
|
| 150 |
+
"23": "NON_PARTICIPATING",
|
| 151 |
"230": "SUCCESS",
|
| 152 |
"231": "SUCCESS",
|
| 153 |
"232": "NOT_ALIVE",
|
| 154 |
"233": "SUCCESS",
|
| 155 |
"234": "NON_PARTICIPATING",
|
| 156 |
+
"235": "NOT_ALIVE",
|
| 157 |
"236": "NOT_ALIVE",
|
| 158 |
"237": "SUCCESS",
|
| 159 |
"238": "SUCCESS",
|
| 160 |
"239": "NOT_ALIVE",
|
| 161 |
+
"24": "NON_PARTICIPATING",
|
| 162 |
"240": "NOT_ALIVE",
|
| 163 |
"241": "SUCCESS",
|
| 164 |
"242": "NOT_ALIVE",
|
| 165 |
"243": "NOT_ALIVE",
|
| 166 |
"244": "NOT_ALIVE",
|
| 167 |
+
"245": "SUCCESS",
|
| 168 |
"246": "NOT_ALIVE",
|
| 169 |
"247": "NON_PARTICIPATING",
|
| 170 |
"248": "NOT_ALIVE",
|
| 171 |
"249": "NOT_ALIVE",
|
| 172 |
"25": "SUCCESS",
|
| 173 |
"250": "NOT_ALIVE",
|
| 174 |
+
"251": "SUCCESS",
|
| 175 |
+
"252": "SUCCESS",
|
| 176 |
"253": "NOT_ALIVE",
|
| 177 |
"254": "NOT_ALIVE",
|
| 178 |
"255": "NOT_ALIVE",
|
|
|
|
| 185 |
"31": "NOT_ALIVE",
|
| 186 |
"32": "NOT_ALIVE",
|
| 187 |
"33": "NOT_ALIVE",
|
| 188 |
+
"34": "SUCCESS",
|
| 189 |
"35": "NOT_ALIVE",
|
| 190 |
"36": "NOT_ALIVE",
|
| 191 |
"37": "NON_PARTICIPATING",
|
| 192 |
+
"38": "NOT_ALIVE",
|
| 193 |
"39": "NOT_ALIVE",
|
| 194 |
+
"4": "SUCCESS",
|
| 195 |
"40": "NOT_ALIVE",
|
| 196 |
"41": "NON_PARTICIPATING",
|
| 197 |
"42": "NOT_ALIVE",
|
|
|
|
| 207 |
"51": "NON_PARTICIPATING",
|
| 208 |
"52": "NOT_ALIVE",
|
| 209 |
"53": "NON_PARTICIPATING",
|
| 210 |
+
"54": "NOT_ALIVE",
|
| 211 |
"55": "NOT_ALIVE",
|
| 212 |
"56": "NOT_ALIVE",
|
| 213 |
+
"57": "NON_PARTICIPATING",
|
| 214 |
"58": "NOT_ALIVE",
|
| 215 |
"59": "NOT_ALIVE",
|
| 216 |
"6": "NOT_ALIVE",
|
| 217 |
"60": "NON_PARTICIPATING",
|
| 218 |
+
"61": "NON_PARTICIPATING",
|
| 219 |
"62": "NON_PARTICIPATING",
|
| 220 |
"63": "NOT_ALIVE",
|
| 221 |
"64": "NOT_ALIVE",
|
|
|
|
| 234 |
"76": "SUCCESS",
|
| 235 |
"77": "NOT_ALIVE",
|
| 236 |
"78": "NOT_ALIVE",
|
| 237 |
+
"79": "NOT_ALIVE",
|
| 238 |
"8": "SUCCESS",
|
| 239 |
+
"80": "NON_PARTICIPATING",
|
| 240 |
"81": "NOT_ALIVE",
|
| 241 |
"82": "NOT_ALIVE",
|
| 242 |
"83": "NON_PARTICIPATING",
|
| 243 |
"84": "NON_PARTICIPATING",
|
| 244 |
"85": "NOT_ALIVE",
|
| 245 |
"86": "NON_PARTICIPATING",
|
| 246 |
+
"87": "NON_PARTICIPATING",
|
| 247 |
"88": "NON_PARTICIPATING",
|
| 248 |
"89": "NON_PARTICIPATING",
|
| 249 |
"9": "NOT_ALIVE",
|
|
|
|
| 264 |
"attention_bias": false,
|
| 265 |
"attention_dropout": 0.0,
|
| 266 |
"block_list": [
|
| 267 |
+
6677311,
|
| 268 |
+
6677357
|
| 269 |
],
|
| 270 |
"bos_token_id": 1,
|
| 271 |
"dtype": "float32",
|
|
|
|
| 276 |
"initializer_range": 0.02,
|
| 277 |
"inner_step": 9,
|
| 278 |
"intermediate_size": 5632,
|
| 279 |
+
"last_allreduce_block": 6677295,
|
| 280 |
"max_position_embeddings": 2048,
|
| 281 |
"mlp_bias": false,
|
| 282 |
"model_type": "llama",
|
gradients.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 88389626
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04e4180fabaa1aa1ee223b5c650e6a207707ef57554c2134e4c24df62abe9431
|
| 3 |
size 88389626
|
inner_optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4924926906
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c669687dc10153681228c7bc33d222ee820acede2ed28eda1df2ffb8b691f3f
|
| 3 |
size 4924926906
|
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 sha256:4af0283c2d35c73989ca7622d4b103d8d1d6cf982d2f2a7579a6113d3b042b8b
|
| 3 |
size 4400216536
|