Run 11. Outer Step 227. 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
|
@@ -13,14 +13,14 @@
|
|
| 13 |
"106": "SUCCESS",
|
| 14 |
"107": "NON_PARTICIPATING",
|
| 15 |
"108": "SUCCESS",
|
| 16 |
-
"109": "
|
| 17 |
"11": "NOT_ALIVE",
|
| 18 |
"110": "NON_PARTICIPATING",
|
| 19 |
-
"111": "
|
| 20 |
"112": "NOT_ALIVE",
|
| 21 |
"113": "NON_PARTICIPATING",
|
| 22 |
"114": "NOT_ALIVE",
|
| 23 |
-
"115": "
|
| 24 |
"116": "NON_PARTICIPATING",
|
| 25 |
"117": "NOT_ALIVE",
|
| 26 |
"118": "NOT_ALIVE",
|
|
@@ -33,30 +33,30 @@
|
|
| 33 |
"124": "NOT_ALIVE",
|
| 34 |
"125": "NOT_ALIVE",
|
| 35 |
"126": "NOT_ALIVE",
|
| 36 |
-
"127": "
|
| 37 |
-
"128": "
|
| 38 |
"129": "NOT_ALIVE",
|
| 39 |
-
"13": "
|
| 40 |
-
"130": "
|
| 41 |
"131": "NOT_ALIVE",
|
| 42 |
"132": "NOT_ALIVE",
|
| 43 |
"133": "NOT_ALIVE",
|
| 44 |
"134": "SUCCESS",
|
| 45 |
-
"135": "
|
| 46 |
"136": "NOT_ALIVE",
|
| 47 |
"137": "NOT_ALIVE",
|
| 48 |
"138": "NOT_ALIVE",
|
| 49 |
"139": "NON_PARTICIPATING",
|
| 50 |
"14": "NON_PARTICIPATING",
|
| 51 |
"140": "SUCCESS",
|
| 52 |
-
"141": "
|
| 53 |
"142": "NOT_ALIVE",
|
| 54 |
"143": "NON_PARTICIPATING",
|
| 55 |
"144": "NOT_ALIVE",
|
| 56 |
"145": "NOT_ALIVE",
|
| 57 |
"146": "SUCCESS",
|
| 58 |
"147": "SUCCESS",
|
| 59 |
-
"148": "
|
| 60 |
"149": "NOT_ALIVE",
|
| 61 |
"15": "NOT_ALIVE",
|
| 62 |
"150": "NON_PARTICIPATING",
|
|
@@ -66,7 +66,7 @@
|
|
| 66 |
"154": "NOT_ALIVE",
|
| 67 |
"155": "NOT_ALIVE",
|
| 68 |
"156": "NOT_ALIVE",
|
| 69 |
-
"157": "
|
| 70 |
"158": "NOT_ALIVE",
|
| 71 |
"159": "NOT_ALIVE",
|
| 72 |
"16": "NOT_ALIVE",
|
|
@@ -75,11 +75,11 @@
|
|
| 75 |
"162": "SUCCESS",
|
| 76 |
"163": "NOT_ALIVE",
|
| 77 |
"164": "NOT_ALIVE",
|
| 78 |
-
"165": "
|
| 79 |
"166": "NOT_ALIVE",
|
| 80 |
"167": "NON_PARTICIPATING",
|
| 81 |
"168": "NOT_ALIVE",
|
| 82 |
-
"169": "
|
| 83 |
"17": "NOT_ALIVE",
|
| 84 |
"170": "NOT_ALIVE",
|
| 85 |
"171": "NON_PARTICIPATING",
|
|
@@ -94,12 +94,12 @@
|
|
| 94 |
"18": "NOT_ALIVE",
|
| 95 |
"180": "NOT_ALIVE",
|
| 96 |
"181": "NOT_ALIVE",
|
| 97 |
-
"182": "
|
| 98 |
"183": "NOT_ALIVE",
|
| 99 |
"184": "NON_PARTICIPATING",
|
| 100 |
"185": "SUCCESS",
|
| 101 |
"186": "SUCCESS",
|
| 102 |
-
"187": "
|
| 103 |
"188": "NOT_ALIVE",
|
| 104 |
"189": "NOT_ALIVE",
|
| 105 |
"19": "NOT_ALIVE",
|
|
@@ -121,38 +121,38 @@
|
|
| 121 |
"203": "NOT_ALIVE",
|
| 122 |
"204": "NOT_ALIVE",
|
| 123 |
"205": "NOT_ALIVE",
|
| 124 |
-
"206": "
|
| 125 |
"207": "NOT_ALIVE",
|
| 126 |
"208": "NOT_ALIVE",
|
| 127 |
"209": "NON_PARTICIPATING",
|
| 128 |
"21": "NOT_ALIVE",
|
| 129 |
-
"210": "
|
| 130 |
"211": "NOT_ALIVE",
|
| 131 |
"212": "NOT_ALIVE",
|
| 132 |
"213": "NON_PARTICIPATING",
|
| 133 |
-
"214": "
|
| 134 |
"215": "NOT_ALIVE",
|
| 135 |
-
"216": "
|
| 136 |
"217": "SUCCESS",
|
| 137 |
"218": "NOT_ALIVE",
|
| 138 |
"219": "NOT_ALIVE",
|
| 139 |
"22": "NOT_ALIVE",
|
| 140 |
-
"220": "
|
| 141 |
-
"221": "
|
| 142 |
"222": "NOT_ALIVE",
|
| 143 |
"223": "NON_PARTICIPATING",
|
| 144 |
"224": "NOT_ALIVE",
|
| 145 |
"225": "NOT_ALIVE",
|
| 146 |
"226": "SUCCESS",
|
| 147 |
-
"227": "
|
| 148 |
"228": "NOT_ALIVE",
|
| 149 |
"229": "NOT_ALIVE",
|
| 150 |
"23": "NON_PARTICIPATING",
|
| 151 |
"230": "SUCCESS",
|
| 152 |
-
"231": "
|
| 153 |
"232": "NOT_ALIVE",
|
| 154 |
-
"233": "
|
| 155 |
-
"234": "
|
| 156 |
"235": "NON_PARTICIPATING",
|
| 157 |
"236": "SUCCESS",
|
| 158 |
"237": "SUCCESS",
|
|
@@ -166,13 +166,13 @@
|
|
| 166 |
"244": "NOT_ALIVE",
|
| 167 |
"245": "SUCCESS",
|
| 168 |
"246": "NOT_ALIVE",
|
| 169 |
-
"247": "
|
| 170 |
"248": "NOT_ALIVE",
|
| 171 |
"249": "NOT_ALIVE",
|
| 172 |
"25": "SUCCESS",
|
| 173 |
"250": "NOT_ALIVE",
|
| 174 |
"251": "SUCCESS",
|
| 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": "
|
| 192 |
"38": "NON_PARTICIPATING",
|
| 193 |
"39": "NOT_ALIVE",
|
| 194 |
-
"4": "
|
| 195 |
"40": "NOT_ALIVE",
|
| 196 |
"41": "NON_PARTICIPATING",
|
| 197 |
"42": "NOT_ALIVE",
|
|
@@ -204,9 +204,9 @@
|
|
| 204 |
"49": "NOT_ALIVE",
|
| 205 |
"5": "NOT_ALIVE",
|
| 206 |
"50": "NOT_ALIVE",
|
| 207 |
-
"51": "
|
| 208 |
"52": "NOT_ALIVE",
|
| 209 |
-
"53": "
|
| 210 |
"54": "SUCCESS",
|
| 211 |
"55": "NON_PARTICIPATING",
|
| 212 |
"56": "NOT_ALIVE",
|
|
@@ -215,7 +215,7 @@
|
|
| 215 |
"59": "NOT_ALIVE",
|
| 216 |
"6": "NOT_ALIVE",
|
| 217 |
"60": "NON_PARTICIPATING",
|
| 218 |
-
"61": "
|
| 219 |
"62": "NON_PARTICIPATING",
|
| 220 |
"63": "NON_PARTICIPATING",
|
| 221 |
"64": "NOT_ALIVE",
|
|
@@ -226,12 +226,12 @@
|
|
| 226 |
"69": "NOT_ALIVE",
|
| 227 |
"7": "NOT_ALIVE",
|
| 228 |
"70": "NOT_ALIVE",
|
| 229 |
-
"71": "
|
| 230 |
"72": "NOT_ALIVE",
|
| 231 |
"73": "NOT_ALIVE",
|
| 232 |
"74": "NOT_ALIVE",
|
| 233 |
"75": "NOT_ALIVE",
|
| 234 |
-
"76": "
|
| 235 |
"77": "NOT_ALIVE",
|
| 236 |
"78": "NOT_ALIVE",
|
| 237 |
"79": "NON_PARTICIPATING",
|
|
@@ -254,7 +254,7 @@
|
|
| 254 |
"94": "NON_PARTICIPATING",
|
| 255 |
"95": "NOT_ALIVE",
|
| 256 |
"96": "NON_PARTICIPATING",
|
| 257 |
-
"97": "
|
| 258 |
"98": "SUCCESS",
|
| 259 |
"99": "SUCCESS"
|
| 260 |
},
|
|
@@ -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",
|
|
@@ -274,9 +274,9 @@
|
|
| 274 |
"hidden_act": "silu",
|
| 275 |
"hidden_size": 2048,
|
| 276 |
"initializer_range": 0.02,
|
| 277 |
-
"inner_step":
|
| 278 |
"intermediate_size": 5632,
|
| 279 |
-
"last_allreduce_block":
|
| 280 |
"max_position_embeddings": 2048,
|
| 281 |
"mlp_bias": false,
|
| 282 |
"model_type": "llama",
|
|
|
|
| 13 |
"106": "SUCCESS",
|
| 14 |
"107": "NON_PARTICIPATING",
|
| 15 |
"108": "SUCCESS",
|
| 16 |
+
"109": "NOT_ALIVE",
|
| 17 |
"11": "NOT_ALIVE",
|
| 18 |
"110": "NON_PARTICIPATING",
|
| 19 |
+
"111": "NON_PARTICIPATING",
|
| 20 |
"112": "NOT_ALIVE",
|
| 21 |
"113": "NON_PARTICIPATING",
|
| 22 |
"114": "NOT_ALIVE",
|
| 23 |
+
"115": "NON_PARTICIPATING",
|
| 24 |
"116": "NON_PARTICIPATING",
|
| 25 |
"117": "NOT_ALIVE",
|
| 26 |
"118": "NOT_ALIVE",
|
|
|
|
| 33 |
"124": "NOT_ALIVE",
|
| 34 |
"125": "NOT_ALIVE",
|
| 35 |
"126": "NOT_ALIVE",
|
| 36 |
+
"127": "NOT_ALIVE",
|
| 37 |
+
"128": "SUCCESS",
|
| 38 |
"129": "NOT_ALIVE",
|
| 39 |
+
"13": "NOT_ALIVE",
|
| 40 |
+
"130": "NOT_ALIVE",
|
| 41 |
"131": "NOT_ALIVE",
|
| 42 |
"132": "NOT_ALIVE",
|
| 43 |
"133": "NOT_ALIVE",
|
| 44 |
"134": "SUCCESS",
|
| 45 |
+
"135": "NON_PARTICIPATING",
|
| 46 |
"136": "NOT_ALIVE",
|
| 47 |
"137": "NOT_ALIVE",
|
| 48 |
"138": "NOT_ALIVE",
|
| 49 |
"139": "NON_PARTICIPATING",
|
| 50 |
"14": "NON_PARTICIPATING",
|
| 51 |
"140": "SUCCESS",
|
| 52 |
+
"141": "NOT_ALIVE",
|
| 53 |
"142": "NOT_ALIVE",
|
| 54 |
"143": "NON_PARTICIPATING",
|
| 55 |
"144": "NOT_ALIVE",
|
| 56 |
"145": "NOT_ALIVE",
|
| 57 |
"146": "SUCCESS",
|
| 58 |
"147": "SUCCESS",
|
| 59 |
+
"148": "NON_PARTICIPATING",
|
| 60 |
"149": "NOT_ALIVE",
|
| 61 |
"15": "NOT_ALIVE",
|
| 62 |
"150": "NON_PARTICIPATING",
|
|
|
|
| 66 |
"154": "NOT_ALIVE",
|
| 67 |
"155": "NOT_ALIVE",
|
| 68 |
"156": "NOT_ALIVE",
|
| 69 |
+
"157": "SUCCESS",
|
| 70 |
"158": "NOT_ALIVE",
|
| 71 |
"159": "NOT_ALIVE",
|
| 72 |
"16": "NOT_ALIVE",
|
|
|
|
| 75 |
"162": "SUCCESS",
|
| 76 |
"163": "NOT_ALIVE",
|
| 77 |
"164": "NOT_ALIVE",
|
| 78 |
+
"165": "NOT_ALIVE",
|
| 79 |
"166": "NOT_ALIVE",
|
| 80 |
"167": "NON_PARTICIPATING",
|
| 81 |
"168": "NOT_ALIVE",
|
| 82 |
+
"169": "NOT_ALIVE",
|
| 83 |
"17": "NOT_ALIVE",
|
| 84 |
"170": "NOT_ALIVE",
|
| 85 |
"171": "NON_PARTICIPATING",
|
|
|
|
| 94 |
"18": "NOT_ALIVE",
|
| 95 |
"180": "NOT_ALIVE",
|
| 96 |
"181": "NOT_ALIVE",
|
| 97 |
+
"182": "NOT_ALIVE",
|
| 98 |
"183": "NOT_ALIVE",
|
| 99 |
"184": "NON_PARTICIPATING",
|
| 100 |
"185": "SUCCESS",
|
| 101 |
"186": "SUCCESS",
|
| 102 |
+
"187": "SUCCESS",
|
| 103 |
"188": "NOT_ALIVE",
|
| 104 |
"189": "NOT_ALIVE",
|
| 105 |
"19": "NOT_ALIVE",
|
|
|
|
| 121 |
"203": "NOT_ALIVE",
|
| 122 |
"204": "NOT_ALIVE",
|
| 123 |
"205": "NOT_ALIVE",
|
| 124 |
+
"206": "NON_PARTICIPATING",
|
| 125 |
"207": "NOT_ALIVE",
|
| 126 |
"208": "NOT_ALIVE",
|
| 127 |
"209": "NON_PARTICIPATING",
|
| 128 |
"21": "NOT_ALIVE",
|
| 129 |
+
"210": "NOT_ALIVE",
|
| 130 |
"211": "NOT_ALIVE",
|
| 131 |
"212": "NOT_ALIVE",
|
| 132 |
"213": "NON_PARTICIPATING",
|
| 133 |
+
"214": "SUCCESS",
|
| 134 |
"215": "NOT_ALIVE",
|
| 135 |
+
"216": "NON_PARTICIPATING",
|
| 136 |
"217": "SUCCESS",
|
| 137 |
"218": "NOT_ALIVE",
|
| 138 |
"219": "NOT_ALIVE",
|
| 139 |
"22": "NOT_ALIVE",
|
| 140 |
+
"220": "NON_PARTICIPATING",
|
| 141 |
+
"221": "NON_PARTICIPATING",
|
| 142 |
"222": "NOT_ALIVE",
|
| 143 |
"223": "NON_PARTICIPATING",
|
| 144 |
"224": "NOT_ALIVE",
|
| 145 |
"225": "NOT_ALIVE",
|
| 146 |
"226": "SUCCESS",
|
| 147 |
+
"227": "NOT_ALIVE",
|
| 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": "NON_PARTICIPATING",
|
| 157 |
"236": "SUCCESS",
|
| 158 |
"237": "SUCCESS",
|
|
|
|
| 166 |
"244": "NOT_ALIVE",
|
| 167 |
"245": "SUCCESS",
|
| 168 |
"246": "NOT_ALIVE",
|
| 169 |
+
"247": "NOT_ALIVE",
|
| 170 |
"248": "NOT_ALIVE",
|
| 171 |
"249": "NOT_ALIVE",
|
| 172 |
"25": "SUCCESS",
|
| 173 |
"250": "NOT_ALIVE",
|
| 174 |
"251": "SUCCESS",
|
| 175 |
+
"252": "NOT_ALIVE",
|
| 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": "NON_PARTICIPATING",
|
| 189 |
"35": "NOT_ALIVE",
|
| 190 |
"36": "NOT_ALIVE",
|
| 191 |
+
"37": "NOT_ALIVE",
|
| 192 |
"38": "NON_PARTICIPATING",
|
| 193 |
"39": "NOT_ALIVE",
|
| 194 |
+
"4": "NON_PARTICIPATING",
|
| 195 |
"40": "NOT_ALIVE",
|
| 196 |
"41": "NON_PARTICIPATING",
|
| 197 |
"42": "NOT_ALIVE",
|
|
|
|
| 204 |
"49": "NOT_ALIVE",
|
| 205 |
"5": "NOT_ALIVE",
|
| 206 |
"50": "NOT_ALIVE",
|
| 207 |
+
"51": "NOT_ALIVE",
|
| 208 |
"52": "NOT_ALIVE",
|
| 209 |
+
"53": "NON_PARTICIPATING",
|
| 210 |
"54": "SUCCESS",
|
| 211 |
"55": "NON_PARTICIPATING",
|
| 212 |
"56": "NOT_ALIVE",
|
|
|
|
| 215 |
"59": "NOT_ALIVE",
|
| 216 |
"6": "NOT_ALIVE",
|
| 217 |
"60": "NON_PARTICIPATING",
|
| 218 |
+
"61": "SUCCESS",
|
| 219 |
"62": "NON_PARTICIPATING",
|
| 220 |
"63": "NON_PARTICIPATING",
|
| 221 |
"64": "NOT_ALIVE",
|
|
|
|
| 226 |
"69": "NOT_ALIVE",
|
| 227 |
"7": "NOT_ALIVE",
|
| 228 |
"70": "NOT_ALIVE",
|
| 229 |
+
"71": "NOT_ALIVE",
|
| 230 |
"72": "NOT_ALIVE",
|
| 231 |
"73": "NOT_ALIVE",
|
| 232 |
"74": "NOT_ALIVE",
|
| 233 |
"75": "NOT_ALIVE",
|
| 234 |
+
"76": "SUCCESS",
|
| 235 |
"77": "NOT_ALIVE",
|
| 236 |
"78": "NOT_ALIVE",
|
| 237 |
"79": "NON_PARTICIPATING",
|
|
|
|
| 254 |
"94": "NON_PARTICIPATING",
|
| 255 |
"95": "NOT_ALIVE",
|
| 256 |
"96": "NON_PARTICIPATING",
|
| 257 |
+
"97": "SUCCESS",
|
| 258 |
"98": "SUCCESS",
|
| 259 |
"99": "SUCCESS"
|
| 260 |
},
|
|
|
|
| 264 |
"attention_bias": false,
|
| 265 |
"attention_dropout": 0.0,
|
| 266 |
"block_list": [
|
| 267 |
+
6669712,
|
| 268 |
+
6669740
|
| 269 |
],
|
| 270 |
"bos_token_id": 1,
|
| 271 |
"dtype": "float32",
|
|
|
|
| 274 |
"hidden_act": "silu",
|
| 275 |
"hidden_size": 2048,
|
| 276 |
"initializer_range": 0.02,
|
| 277 |
+
"inner_step": 9,
|
| 278 |
"intermediate_size": 5632,
|
| 279 |
+
"last_allreduce_block": 6669670,
|
| 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:d7d0625dc6b698fed72dbebb142beaa1a1f8b4332d85736c5eb03f1a34749544
|
| 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 sha256:4928067e707da1d1015b90ac74f183b4d48a476cefb6fb379eca31f9967054af
|
| 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 sha256:46a7c43df5d1225b5b0f5784448037f9b5dc1270c44c440aa308a22904fd2645
|
| 3 |
size 4400216536
|