Run 8. Outer Step 57. Inner Step 5.
Browse files- config.json +113 -113
- gradients.pt +1 -1
- inner_optimizer.pt +1 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -2,29 +2,29 @@
|
|
| 2 |
"_name_or_path": "distributed/llama-1b",
|
| 3 |
"all_reduce_scores": {
|
| 4 |
"0": "NOT_ALIVE",
|
| 5 |
-
"1": "
|
| 6 |
-
"10": "
|
| 7 |
"100": "NOT_ALIVE",
|
| 8 |
"101": "SUCCESS",
|
| 9 |
-
"102": "
|
| 10 |
"103": "NON_PARTICIPATING",
|
| 11 |
"104": "NON_PARTICIPATING",
|
| 12 |
"105": "NOT_ALIVE",
|
| 13 |
"106": "SUCCESS",
|
| 14 |
-
"107": "
|
| 15 |
"108": "SUCCESS",
|
| 16 |
-
"109": "
|
| 17 |
"11": "SUCCESS",
|
| 18 |
-
"110": "
|
| 19 |
"111": "NOT_ALIVE",
|
| 20 |
"112": "SUCCESS",
|
| 21 |
"113": "NOT_ALIVE",
|
| 22 |
"114": "NOT_ALIVE",
|
| 23 |
"115": "NON_PARTICIPATING",
|
| 24 |
"116": "NON_PARTICIPATING",
|
| 25 |
-
"117": "
|
| 26 |
"118": "NOT_ALIVE",
|
| 27 |
-
"119": "
|
| 28 |
"12": "NOT_ALIVE",
|
| 29 |
"120": "NON_PARTICIPATING",
|
| 30 |
"121": "SUCCESS",
|
|
@@ -32,142 +32,142 @@
|
|
| 32 |
"123": "SUCCESS",
|
| 33 |
"124": "NOT_ALIVE",
|
| 34 |
"125": "NOT_ALIVE",
|
| 35 |
-
"126": "
|
| 36 |
-
"127": "
|
| 37 |
-
"128": "
|
| 38 |
"129": "FAIL",
|
| 39 |
"13": "NOT_ALIVE",
|
| 40 |
-
"130": "
|
| 41 |
"131": "NON_PARTICIPATING",
|
| 42 |
"132": "SUCCESS",
|
| 43 |
-
"133": "
|
| 44 |
"134": "NOT_ALIVE",
|
| 45 |
-
"135": "
|
| 46 |
"136": "SUCCESS",
|
| 47 |
"137": "SUCCESS",
|
| 48 |
-
"138": "
|
| 49 |
-
"139": "
|
| 50 |
"14": "NOT_ALIVE",
|
| 51 |
-
"140": "
|
| 52 |
"141": "NOT_ALIVE",
|
| 53 |
"142": "FAIL",
|
| 54 |
-
"143": "
|
| 55 |
"144": "NON_PARTICIPATING",
|
| 56 |
-
"145": "
|
| 57 |
"146": "NON_PARTICIPATING",
|
| 58 |
-
"147": "
|
| 59 |
"148": "NON_PARTICIPATING",
|
| 60 |
"149": "NOT_ALIVE",
|
| 61 |
-
"15": "
|
| 62 |
-
"150": "
|
| 63 |
"151": "NON_PARTICIPATING",
|
| 64 |
-
"152": "
|
| 65 |
"153": "SUCCESS",
|
| 66 |
"154": "NON_PARTICIPATING",
|
| 67 |
"155": "NON_PARTICIPATING",
|
| 68 |
"156": "NOT_ALIVE",
|
| 69 |
"157": "NON_PARTICIPATING",
|
| 70 |
-
"158": "
|
| 71 |
-
"159": "
|
| 72 |
"16": "NOT_ALIVE",
|
| 73 |
"160": "NON_PARTICIPATING",
|
| 74 |
-
"161": "
|
| 75 |
"162": "NON_PARTICIPATING",
|
| 76 |
-
"163": "
|
| 77 |
-
"164": "
|
| 78 |
"165": "SUCCESS",
|
| 79 |
"166": "NOT_ALIVE",
|
| 80 |
"167": "NON_PARTICIPATING",
|
| 81 |
"168": "SUCCESS",
|
| 82 |
-
"169": "
|
| 83 |
"17": "NOT_ALIVE",
|
| 84 |
"170": "SUCCESS",
|
| 85 |
-
"171": "
|
| 86 |
-
"172": "
|
| 87 |
-
"173": "
|
| 88 |
"174": "SUCCESS",
|
| 89 |
"175": "SUCCESS",
|
| 90 |
"176": "NOT_ALIVE",
|
| 91 |
-
"177": "
|
| 92 |
"178": "NON_PARTICIPATING",
|
| 93 |
"179": "SUCCESS",
|
| 94 |
"18": "NOT_ALIVE",
|
| 95 |
"180": "SUCCESS",
|
| 96 |
"181": "SUCCESS",
|
| 97 |
"182": "SUCCESS",
|
| 98 |
-
"183": "
|
| 99 |
-
"184": "
|
| 100 |
-
"185": "
|
| 101 |
-
"186": "
|
| 102 |
"187": "NOT_ALIVE",
|
| 103 |
"188": "SUCCESS",
|
| 104 |
-
"189": "
|
| 105 |
-
"19": "
|
| 106 |
"190": "NON_PARTICIPATING",
|
| 107 |
"191": "FAIL",
|
| 108 |
-
"192": "
|
| 109 |
-
"193": "
|
| 110 |
-
"194": "
|
| 111 |
-
"195": "
|
| 112 |
"196": "NON_PARTICIPATING",
|
| 113 |
-
"197": "
|
| 114 |
-
"198": "
|
| 115 |
"199": "SUCCESS",
|
| 116 |
"2": "NOT_ALIVE",
|
| 117 |
"20": "NOT_ALIVE",
|
| 118 |
"200": "SUCCESS",
|
| 119 |
"201": "NOT_ALIVE",
|
| 120 |
"202": "NON_PARTICIPATING",
|
| 121 |
-
"203": "
|
| 122 |
"204": "SUCCESS",
|
| 123 |
"205": "SUCCESS",
|
| 124 |
-
"206": "
|
| 125 |
"207": "NON_PARTICIPATING",
|
| 126 |
"208": "NON_PARTICIPATING",
|
| 127 |
-
"209": "
|
| 128 |
"21": "SUCCESS",
|
| 129 |
-
"210": "
|
| 130 |
-
"211": "
|
| 131 |
"212": "SUCCESS",
|
| 132 |
-
"213": "
|
| 133 |
"214": "SUCCESS",
|
| 134 |
"215": "SUCCESS",
|
| 135 |
"216": "SUCCESS",
|
| 136 |
-
"217": "
|
| 137 |
-
"218": "
|
| 138 |
"219": "SUCCESS",
|
| 139 |
-
"22": "
|
| 140 |
-
"220": "
|
| 141 |
-
"221": "
|
| 142 |
"222": "SUCCESS",
|
| 143 |
"223": "SUCCESS",
|
| 144 |
"224": "NON_PARTICIPATING",
|
| 145 |
-
"225": "
|
| 146 |
"226": "NOT_ALIVE",
|
| 147 |
"227": "NOT_ALIVE",
|
| 148 |
-
"228": "
|
| 149 |
"229": "NON_PARTICIPATING",
|
| 150 |
"23": "NOT_ALIVE",
|
| 151 |
-
"230": "
|
| 152 |
-
"231": "
|
| 153 |
-
"232": "
|
| 154 |
-
"233": "
|
| 155 |
"234": "SUCCESS",
|
| 156 |
"235": "SUCCESS",
|
| 157 |
"236": "SUCCESS",
|
| 158 |
-
"237": "
|
| 159 |
"238": "SUCCESS",
|
| 160 |
-
"239": "
|
| 161 |
-
"24": "
|
| 162 |
"240": "NON_PARTICIPATING",
|
| 163 |
-
"241": "
|
| 164 |
"242": "SUCCESS",
|
| 165 |
-
"243": "
|
| 166 |
-
"244": "
|
| 167 |
"245": "SUCCESS",
|
| 168 |
-
"246": "
|
| 169 |
-
"247": "
|
| 170 |
-
"248": "
|
| 171 |
"249": "NOT_ALIVE",
|
| 172 |
"25": "SUCCESS",
|
| 173 |
"250": "FAIL",
|
|
@@ -177,70 +177,70 @@
|
|
| 177 |
"254": "NOT_ALIVE",
|
| 178 |
"255": "NON_PARTICIPATING",
|
| 179 |
"26": "SUCCESS",
|
| 180 |
-
"27": "
|
| 181 |
"28": "SUCCESS",
|
| 182 |
-
"29": "
|
| 183 |
"3": "SUCCESS",
|
| 184 |
-
"30": "
|
| 185 |
-
"31": "
|
| 186 |
-
"32": "
|
| 187 |
"33": "NOT_ALIVE",
|
| 188 |
-
"34": "
|
| 189 |
"35": "FAIL",
|
| 190 |
-
"36": "
|
| 191 |
"37": "NOT_ALIVE",
|
| 192 |
"38": "NOT_ALIVE",
|
| 193 |
"39": "NON_PARTICIPATING",
|
| 194 |
-
"4": "
|
| 195 |
"40": "NON_PARTICIPATING",
|
| 196 |
-
"41": "
|
| 197 |
-
"42": "
|
| 198 |
"43": "NON_PARTICIPATING",
|
| 199 |
-
"44": "
|
| 200 |
-
"45": "
|
| 201 |
-
"46": "
|
| 202 |
-
"47": "
|
| 203 |
"48": "NOT_ALIVE",
|
| 204 |
-
"49": "
|
| 205 |
-
"5": "
|
| 206 |
-
"50": "
|
| 207 |
"51": "SUCCESS",
|
| 208 |
"52": "SUCCESS",
|
| 209 |
"53": "SUCCESS",
|
| 210 |
"54": "SUCCESS",
|
| 211 |
-
"55": "
|
| 212 |
"56": "NON_PARTICIPATING",
|
| 213 |
-
"57": "
|
| 214 |
"58": "SUCCESS",
|
| 215 |
-
"59": "
|
| 216 |
-
"6": "
|
| 217 |
"60": "SUCCESS",
|
| 218 |
"61": "NON_PARTICIPATING",
|
| 219 |
-
"62": "
|
| 220 |
"63": "SUCCESS",
|
| 221 |
"64": "SUCCESS",
|
| 222 |
-
"65": "
|
| 223 |
-
"66": "
|
| 224 |
-
"67": "
|
| 225 |
-
"68": "
|
| 226 |
"69": "NON_PARTICIPATING",
|
| 227 |
"7": "NOT_ALIVE",
|
| 228 |
-
"70": "
|
| 229 |
-
"71": "
|
| 230 |
"72": "NON_PARTICIPATING",
|
| 231 |
"73": "NON_PARTICIPATING",
|
| 232 |
-
"74": "
|
| 233 |
"75": "NON_PARTICIPATING",
|
| 234 |
-
"76": "
|
| 235 |
-
"77": "
|
| 236 |
"78": "SUCCESS",
|
| 237 |
"79": "SUCCESS",
|
| 238 |
"8": "NOT_ALIVE",
|
| 239 |
"80": "NON_PARTICIPATING",
|
| 240 |
-
"81": "
|
| 241 |
"82": "SUCCESS",
|
| 242 |
-
"83": "
|
| 243 |
-
"84": "
|
| 244 |
"85": "NON_PARTICIPATING",
|
| 245 |
"86": "NOT_ALIVE",
|
| 246 |
"87": "FAIL",
|
|
@@ -248,12 +248,12 @@
|
|
| 248 |
"89": "NON_PARTICIPATING",
|
| 249 |
"9": "NOT_ALIVE",
|
| 250 |
"90": "SUCCESS",
|
| 251 |
-
"91": "
|
| 252 |
"92": "NOT_ALIVE",
|
| 253 |
"93": "NON_PARTICIPATING",
|
| 254 |
"94": "NOT_ALIVE",
|
| 255 |
-
"95": "
|
| 256 |
-
"96": "
|
| 257 |
"97": "SUCCESS",
|
| 258 |
"98": "NON_PARTICIPATING",
|
| 259 |
"99": "NON_PARTICIPATING"
|
|
@@ -264,18 +264,18 @@
|
|
| 264 |
"attention_bias": false,
|
| 265 |
"attention_dropout": 0.0,
|
| 266 |
"block_list": [
|
| 267 |
-
|
| 268 |
-
|
| 269 |
-
|
| 270 |
],
|
| 271 |
"bos_token_id": 1,
|
| 272 |
"eos_token_id": 2,
|
| 273 |
"hidden_act": "silu",
|
| 274 |
"hidden_size": 2048,
|
| 275 |
"initializer_range": 0.02,
|
| 276 |
-
"inner_step":
|
| 277 |
"intermediate_size": 5632,
|
| 278 |
-
"last_allreduce_block":
|
| 279 |
"max_position_embeddings": 2048,
|
| 280 |
"mlp_bias": false,
|
| 281 |
"model_type": "llama",
|
|
|
|
| 2 |
"_name_or_path": "distributed/llama-1b",
|
| 3 |
"all_reduce_scores": {
|
| 4 |
"0": "NOT_ALIVE",
|
| 5 |
+
"1": "SUCCESS",
|
| 6 |
+
"10": "FAIL",
|
| 7 |
"100": "NOT_ALIVE",
|
| 8 |
"101": "SUCCESS",
|
| 9 |
+
"102": "NOT_ALIVE",
|
| 10 |
"103": "NON_PARTICIPATING",
|
| 11 |
"104": "NON_PARTICIPATING",
|
| 12 |
"105": "NOT_ALIVE",
|
| 13 |
"106": "SUCCESS",
|
| 14 |
+
"107": "SUCCESS",
|
| 15 |
"108": "SUCCESS",
|
| 16 |
+
"109": "NOT_ALIVE",
|
| 17 |
"11": "SUCCESS",
|
| 18 |
+
"110": "FAIL",
|
| 19 |
"111": "NOT_ALIVE",
|
| 20 |
"112": "SUCCESS",
|
| 21 |
"113": "NOT_ALIVE",
|
| 22 |
"114": "NOT_ALIVE",
|
| 23 |
"115": "NON_PARTICIPATING",
|
| 24 |
"116": "NON_PARTICIPATING",
|
| 25 |
+
"117": "SUCCESS",
|
| 26 |
"118": "NOT_ALIVE",
|
| 27 |
+
"119": "SUCCESS",
|
| 28 |
"12": "NOT_ALIVE",
|
| 29 |
"120": "NON_PARTICIPATING",
|
| 30 |
"121": "SUCCESS",
|
|
|
|
| 32 |
"123": "SUCCESS",
|
| 33 |
"124": "NOT_ALIVE",
|
| 34 |
"125": "NOT_ALIVE",
|
| 35 |
+
"126": "SUCCESS",
|
| 36 |
+
"127": "NON_PARTICIPATING",
|
| 37 |
+
"128": "SUCCESS",
|
| 38 |
"129": "FAIL",
|
| 39 |
"13": "NOT_ALIVE",
|
| 40 |
+
"130": "SUCCESS",
|
| 41 |
"131": "NON_PARTICIPATING",
|
| 42 |
"132": "SUCCESS",
|
| 43 |
+
"133": "SUCCESS",
|
| 44 |
"134": "NOT_ALIVE",
|
| 45 |
+
"135": "SUCCESS",
|
| 46 |
"136": "SUCCESS",
|
| 47 |
"137": "SUCCESS",
|
| 48 |
+
"138": "NON_PARTICIPATING",
|
| 49 |
+
"139": "SUCCESS",
|
| 50 |
"14": "NOT_ALIVE",
|
| 51 |
+
"140": "NON_PARTICIPATING",
|
| 52 |
"141": "NOT_ALIVE",
|
| 53 |
"142": "FAIL",
|
| 54 |
+
"143": "FAIL",
|
| 55 |
"144": "NON_PARTICIPATING",
|
| 56 |
+
"145": "SUCCESS",
|
| 57 |
"146": "NON_PARTICIPATING",
|
| 58 |
+
"147": "FAIL",
|
| 59 |
"148": "NON_PARTICIPATING",
|
| 60 |
"149": "NOT_ALIVE",
|
| 61 |
+
"15": "SUCCESS",
|
| 62 |
+
"150": "NOT_ALIVE",
|
| 63 |
"151": "NON_PARTICIPATING",
|
| 64 |
+
"152": "NOT_ALIVE",
|
| 65 |
"153": "SUCCESS",
|
| 66 |
"154": "NON_PARTICIPATING",
|
| 67 |
"155": "NON_PARTICIPATING",
|
| 68 |
"156": "NOT_ALIVE",
|
| 69 |
"157": "NON_PARTICIPATING",
|
| 70 |
+
"158": "NON_PARTICIPATING",
|
| 71 |
+
"159": "SUCCESS",
|
| 72 |
"16": "NOT_ALIVE",
|
| 73 |
"160": "NON_PARTICIPATING",
|
| 74 |
+
"161": "SUCCESS",
|
| 75 |
"162": "NON_PARTICIPATING",
|
| 76 |
+
"163": "SUCCESS",
|
| 77 |
+
"164": "NON_PARTICIPATING",
|
| 78 |
"165": "SUCCESS",
|
| 79 |
"166": "NOT_ALIVE",
|
| 80 |
"167": "NON_PARTICIPATING",
|
| 81 |
"168": "SUCCESS",
|
| 82 |
+
"169": "SUCCESS",
|
| 83 |
"17": "NOT_ALIVE",
|
| 84 |
"170": "SUCCESS",
|
| 85 |
+
"171": "SUCCESS",
|
| 86 |
+
"172": "SUCCESS",
|
| 87 |
+
"173": "SUCCESS",
|
| 88 |
"174": "SUCCESS",
|
| 89 |
"175": "SUCCESS",
|
| 90 |
"176": "NOT_ALIVE",
|
| 91 |
+
"177": "SUCCESS",
|
| 92 |
"178": "NON_PARTICIPATING",
|
| 93 |
"179": "SUCCESS",
|
| 94 |
"18": "NOT_ALIVE",
|
| 95 |
"180": "SUCCESS",
|
| 96 |
"181": "SUCCESS",
|
| 97 |
"182": "SUCCESS",
|
| 98 |
+
"183": "FAIL",
|
| 99 |
+
"184": "SUCCESS",
|
| 100 |
+
"185": "FAIL",
|
| 101 |
+
"186": "NON_PARTICIPATING",
|
| 102 |
"187": "NOT_ALIVE",
|
| 103 |
"188": "SUCCESS",
|
| 104 |
+
"189": "FAIL",
|
| 105 |
+
"19": "FAIL",
|
| 106 |
"190": "NON_PARTICIPATING",
|
| 107 |
"191": "FAIL",
|
| 108 |
+
"192": "SUCCESS",
|
| 109 |
+
"193": "FAIL",
|
| 110 |
+
"194": "NON_PARTICIPATING",
|
| 111 |
+
"195": "SUCCESS",
|
| 112 |
"196": "NON_PARTICIPATING",
|
| 113 |
+
"197": "NON_PARTICIPATING",
|
| 114 |
+
"198": "NON_PARTICIPATING",
|
| 115 |
"199": "SUCCESS",
|
| 116 |
"2": "NOT_ALIVE",
|
| 117 |
"20": "NOT_ALIVE",
|
| 118 |
"200": "SUCCESS",
|
| 119 |
"201": "NOT_ALIVE",
|
| 120 |
"202": "NON_PARTICIPATING",
|
| 121 |
+
"203": "SUCCESS",
|
| 122 |
"204": "SUCCESS",
|
| 123 |
"205": "SUCCESS",
|
| 124 |
+
"206": "NON_PARTICIPATING",
|
| 125 |
"207": "NON_PARTICIPATING",
|
| 126 |
"208": "NON_PARTICIPATING",
|
| 127 |
+
"209": "SUCCESS",
|
| 128 |
"21": "SUCCESS",
|
| 129 |
+
"210": "NON_PARTICIPATING",
|
| 130 |
+
"211": "SUCCESS",
|
| 131 |
"212": "SUCCESS",
|
| 132 |
+
"213": "NON_PARTICIPATING",
|
| 133 |
"214": "SUCCESS",
|
| 134 |
"215": "SUCCESS",
|
| 135 |
"216": "SUCCESS",
|
| 136 |
+
"217": "NON_PARTICIPATING",
|
| 137 |
+
"218": "NON_PARTICIPATING",
|
| 138 |
"219": "SUCCESS",
|
| 139 |
+
"22": "FAIL",
|
| 140 |
+
"220": "SUCCESS",
|
| 141 |
+
"221": "SUCCESS",
|
| 142 |
"222": "SUCCESS",
|
| 143 |
"223": "SUCCESS",
|
| 144 |
"224": "NON_PARTICIPATING",
|
| 145 |
+
"225": "SUCCESS",
|
| 146 |
"226": "NOT_ALIVE",
|
| 147 |
"227": "NOT_ALIVE",
|
| 148 |
+
"228": "SUCCESS",
|
| 149 |
"229": "NON_PARTICIPATING",
|
| 150 |
"23": "NOT_ALIVE",
|
| 151 |
+
"230": "SUCCESS",
|
| 152 |
+
"231": "NOT_ALIVE",
|
| 153 |
+
"232": "NOT_ALIVE",
|
| 154 |
+
"233": "SUCCESS",
|
| 155 |
"234": "SUCCESS",
|
| 156 |
"235": "SUCCESS",
|
| 157 |
"236": "SUCCESS",
|
| 158 |
+
"237": "NON_PARTICIPATING",
|
| 159 |
"238": "SUCCESS",
|
| 160 |
+
"239": "SUCCESS",
|
| 161 |
+
"24": "NOT_ALIVE",
|
| 162 |
"240": "NON_PARTICIPATING",
|
| 163 |
+
"241": "NON_PARTICIPATING",
|
| 164 |
"242": "SUCCESS",
|
| 165 |
+
"243": "NOT_ALIVE",
|
| 166 |
+
"244": "SUCCESS",
|
| 167 |
"245": "SUCCESS",
|
| 168 |
+
"246": "NON_PARTICIPATING",
|
| 169 |
+
"247": "FAIL",
|
| 170 |
+
"248": "FAIL",
|
| 171 |
"249": "NOT_ALIVE",
|
| 172 |
"25": "SUCCESS",
|
| 173 |
"250": "FAIL",
|
|
|
|
| 177 |
"254": "NOT_ALIVE",
|
| 178 |
"255": "NON_PARTICIPATING",
|
| 179 |
"26": "SUCCESS",
|
| 180 |
+
"27": "FAIL",
|
| 181 |
"28": "SUCCESS",
|
| 182 |
+
"29": "SUCCESS",
|
| 183 |
"3": "SUCCESS",
|
| 184 |
+
"30": "FAIL",
|
| 185 |
+
"31": "SUCCESS",
|
| 186 |
+
"32": "NOT_ALIVE",
|
| 187 |
"33": "NOT_ALIVE",
|
| 188 |
+
"34": "SUCCESS",
|
| 189 |
"35": "FAIL",
|
| 190 |
+
"36": "SUCCESS",
|
| 191 |
"37": "NOT_ALIVE",
|
| 192 |
"38": "NOT_ALIVE",
|
| 193 |
"39": "NON_PARTICIPATING",
|
| 194 |
+
"4": "NOT_ALIVE",
|
| 195 |
"40": "NON_PARTICIPATING",
|
| 196 |
+
"41": "NON_PARTICIPATING",
|
| 197 |
+
"42": "NOT_ALIVE",
|
| 198 |
"43": "NON_PARTICIPATING",
|
| 199 |
+
"44": "SUCCESS",
|
| 200 |
+
"45": "NOT_ALIVE",
|
| 201 |
+
"46": "FAIL",
|
| 202 |
+
"47": "SUCCESS",
|
| 203 |
"48": "NOT_ALIVE",
|
| 204 |
+
"49": "NOT_ALIVE",
|
| 205 |
+
"5": "SUCCESS",
|
| 206 |
+
"50": "FAIL",
|
| 207 |
"51": "SUCCESS",
|
| 208 |
"52": "SUCCESS",
|
| 209 |
"53": "SUCCESS",
|
| 210 |
"54": "SUCCESS",
|
| 211 |
+
"55": "NON_PARTICIPATING",
|
| 212 |
"56": "NON_PARTICIPATING",
|
| 213 |
+
"57": "SUCCESS",
|
| 214 |
"58": "SUCCESS",
|
| 215 |
+
"59": "NON_PARTICIPATING",
|
| 216 |
+
"6": "NOT_ALIVE",
|
| 217 |
"60": "SUCCESS",
|
| 218 |
"61": "NON_PARTICIPATING",
|
| 219 |
+
"62": "NOT_ALIVE",
|
| 220 |
"63": "SUCCESS",
|
| 221 |
"64": "SUCCESS",
|
| 222 |
+
"65": "NOT_ALIVE",
|
| 223 |
+
"66": "NOT_ALIVE",
|
| 224 |
+
"67": "NOT_ALIVE",
|
| 225 |
+
"68": "FAIL",
|
| 226 |
"69": "NON_PARTICIPATING",
|
| 227 |
"7": "NOT_ALIVE",
|
| 228 |
+
"70": "NOT_ALIVE",
|
| 229 |
+
"71": "NON_PARTICIPATING",
|
| 230 |
"72": "NON_PARTICIPATING",
|
| 231 |
"73": "NON_PARTICIPATING",
|
| 232 |
+
"74": "SUCCESS",
|
| 233 |
"75": "NON_PARTICIPATING",
|
| 234 |
+
"76": "NON_PARTICIPATING",
|
| 235 |
+
"77": "NON_PARTICIPATING",
|
| 236 |
"78": "SUCCESS",
|
| 237 |
"79": "SUCCESS",
|
| 238 |
"8": "NOT_ALIVE",
|
| 239 |
"80": "NON_PARTICIPATING",
|
| 240 |
+
"81": "NOT_ALIVE",
|
| 241 |
"82": "SUCCESS",
|
| 242 |
+
"83": "SUCCESS",
|
| 243 |
+
"84": "NOT_ALIVE",
|
| 244 |
"85": "NON_PARTICIPATING",
|
| 245 |
"86": "NOT_ALIVE",
|
| 246 |
"87": "FAIL",
|
|
|
|
| 248 |
"89": "NON_PARTICIPATING",
|
| 249 |
"9": "NOT_ALIVE",
|
| 250 |
"90": "SUCCESS",
|
| 251 |
+
"91": "SUCCESS",
|
| 252 |
"92": "NOT_ALIVE",
|
| 253 |
"93": "NON_PARTICIPATING",
|
| 254 |
"94": "NOT_ALIVE",
|
| 255 |
+
"95": "FAIL",
|
| 256 |
+
"96": "SUCCESS",
|
| 257 |
"97": "SUCCESS",
|
| 258 |
"98": "NON_PARTICIPATING",
|
| 259 |
"99": "NON_PARTICIPATING"
|
|
|
|
| 264 |
"attention_bias": false,
|
| 265 |
"attention_dropout": 0.0,
|
| 266 |
"block_list": [
|
| 267 |
+
6380315,
|
| 268 |
+
6380333,
|
| 269 |
+
6380350
|
| 270 |
],
|
| 271 |
"bos_token_id": 1,
|
| 272 |
"eos_token_id": 2,
|
| 273 |
"hidden_act": "silu",
|
| 274 |
"hidden_size": 2048,
|
| 275 |
"initializer_range": 0.02,
|
| 276 |
+
"inner_step": 4,
|
| 277 |
"intermediate_size": 5632,
|
| 278 |
+
"last_allreduce_block": 6380215,
|
| 279 |
"max_position_embeddings": 2048,
|
| 280 |
"mlp_bias": false,
|
| 281 |
"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:a448f11e307d10c1755e0f518d6bf9a730735b3c27fbee9810a4dc51c7b1d7f5
|
| 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:bcc9d182bbf01a264b18cb2b14301126112776be6b86f56c0b397ff346d1cb0c
|
| 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 sha256:5a5900f4226d45e55f6bd972dfdeff4f99aefa140ed3a15fc255a12e923bc534
|
| 3 |
size 4400216536
|