Run 10. Outer Step 52. Inner Step 9.
Browse files- config.json +108 -108
- gradients.pt +1 -1
- inner_optimizer.pt +1 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -2,47 +2,47 @@
|
|
| 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": "NOT_ALIVE",
|
| 9 |
-
"102": "
|
| 10 |
-
"103": "
|
| 11 |
"104": "NOT_ALIVE",
|
| 12 |
-
"105": "
|
| 13 |
-
"106": "
|
| 14 |
"107": "NON_PARTICIPATING",
|
| 15 |
"108": "NON_PARTICIPATING",
|
| 16 |
-
"109": "
|
| 17 |
-
"11": "
|
| 18 |
"110": "NON_PARTICIPATING",
|
| 19 |
-
"111": "
|
| 20 |
"112": "NON_PARTICIPATING",
|
| 21 |
-
"113": "
|
| 22 |
-
"114": "
|
| 23 |
"115": "NON_PARTICIPATING",
|
| 24 |
-
"116": "
|
| 25 |
"117": "NON_PARTICIPATING",
|
| 26 |
-
"118": "
|
| 27 |
"119": "NON_PARTICIPATING",
|
| 28 |
"12": "NOT_ALIVE",
|
| 29 |
"120": "NOT_ALIVE",
|
| 30 |
"121": "NON_PARTICIPATING",
|
| 31 |
"122": "NON_PARTICIPATING",
|
| 32 |
-
"123": "
|
| 33 |
"124": "NON_PARTICIPATING",
|
| 34 |
-
"125": "
|
| 35 |
-
"126": "
|
| 36 |
"127": "NON_PARTICIPATING",
|
| 37 |
-
"128": "
|
| 38 |
-
"129": "
|
| 39 |
-
"13": "
|
| 40 |
"130": "NOT_ALIVE",
|
| 41 |
"131": "NOT_ALIVE",
|
| 42 |
"132": "NOT_ALIVE",
|
| 43 |
"133": "NOT_ALIVE",
|
| 44 |
"134": "NOT_ALIVE",
|
| 45 |
-
"135": "
|
| 46 |
"136": "NON_PARTICIPATING",
|
| 47 |
"137": "NOT_ALIVE",
|
| 48 |
"138": "NON_PARTICIPATING",
|
|
@@ -50,210 +50,210 @@
|
|
| 50 |
"14": "NOT_ALIVE",
|
| 51 |
"140": "NON_PARTICIPATING",
|
| 52 |
"141": "NOT_ALIVE",
|
| 53 |
-
"142": "
|
| 54 |
"143": "NON_PARTICIPATING",
|
| 55 |
"144": "NON_PARTICIPATING",
|
| 56 |
"145": "NOT_ALIVE",
|
| 57 |
-
"146": "
|
| 58 |
-
"147": "
|
| 59 |
-
"148": "
|
| 60 |
"149": "NON_PARTICIPATING",
|
| 61 |
"15": "NON_PARTICIPATING",
|
| 62 |
"150": "NOT_ALIVE",
|
| 63 |
"151": "NOT_ALIVE",
|
| 64 |
"152": "NOT_ALIVE",
|
| 65 |
-
"153": "
|
| 66 |
-
"154": "
|
| 67 |
-
"155": "
|
| 68 |
"156": "NON_PARTICIPATING",
|
| 69 |
"157": "NON_PARTICIPATING",
|
| 70 |
"158": "NON_PARTICIPATING",
|
| 71 |
-
"159": "
|
| 72 |
"16": "NOT_ALIVE",
|
| 73 |
"160": "NOT_ALIVE",
|
| 74 |
"161": "NON_PARTICIPATING",
|
| 75 |
"162": "NOT_ALIVE",
|
| 76 |
-
"163": "
|
| 77 |
"164": "NOT_ALIVE",
|
| 78 |
"165": "NOT_ALIVE",
|
| 79 |
-
"166": "
|
| 80 |
-
"167": "
|
| 81 |
"168": "NON_PARTICIPATING",
|
| 82 |
-
"169": "
|
| 83 |
"17": "NON_PARTICIPATING",
|
| 84 |
-
"170": "
|
| 85 |
-
"171": "
|
| 86 |
"172": "NOT_ALIVE",
|
| 87 |
"173": "NON_PARTICIPATING",
|
| 88 |
"174": "NOT_ALIVE",
|
| 89 |
-
"175": "
|
| 90 |
"176": "NOT_ALIVE",
|
| 91 |
"177": "NON_PARTICIPATING",
|
| 92 |
"178": "NOT_ALIVE",
|
| 93 |
"179": "NOT_ALIVE",
|
| 94 |
"18": "NOT_ALIVE",
|
| 95 |
-
"180": "
|
| 96 |
"181": "NOT_ALIVE",
|
| 97 |
-
"182": "
|
| 98 |
-
"183": "
|
| 99 |
-
"184": "
|
| 100 |
-
"185": "
|
| 101 |
-
"186": "
|
| 102 |
-
"187": "
|
| 103 |
"188": "NON_PARTICIPATING",
|
| 104 |
"189": "NOT_ALIVE",
|
| 105 |
-
"19": "
|
| 106 |
"190": "NON_PARTICIPATING",
|
| 107 |
"191": "NOT_ALIVE",
|
| 108 |
"192": "NON_PARTICIPATING",
|
| 109 |
"193": "NON_PARTICIPATING",
|
| 110 |
"194": "NOT_ALIVE",
|
| 111 |
"195": "NOT_ALIVE",
|
| 112 |
-
"196": "
|
| 113 |
-
"197": "
|
| 114 |
-
"198": "
|
| 115 |
-
"199": "
|
| 116 |
"2": "NON_PARTICIPATING",
|
| 117 |
-
"20": "
|
| 118 |
-
"200": "
|
| 119 |
"201": "NOT_ALIVE",
|
| 120 |
"202": "NON_PARTICIPATING",
|
| 121 |
-
"203": "
|
| 122 |
"204": "NOT_ALIVE",
|
| 123 |
-
"205": "
|
| 124 |
-
"206": "
|
| 125 |
"207": "NOT_ALIVE",
|
| 126 |
"208": "NON_PARTICIPATING",
|
| 127 |
-
"209": "
|
| 128 |
-
"21": "
|
| 129 |
"210": "NON_PARTICIPATING",
|
| 130 |
-
"211": "
|
| 131 |
-
"212": "
|
| 132 |
"213": "NON_PARTICIPATING",
|
| 133 |
-
"214": "
|
| 134 |
"215": "NON_PARTICIPATING",
|
| 135 |
"216": "NOT_ALIVE",
|
| 136 |
"217": "NOT_ALIVE",
|
| 137 |
"218": "NON_PARTICIPATING",
|
| 138 |
-
"219": "
|
| 139 |
"22": "NOT_ALIVE",
|
| 140 |
"220": "NON_PARTICIPATING",
|
| 141 |
-
"221": "
|
| 142 |
-
"222": "
|
| 143 |
"223": "NON_PARTICIPATING",
|
| 144 |
"224": "NOT_ALIVE",
|
| 145 |
"225": "NON_PARTICIPATING",
|
| 146 |
"226": "NON_PARTICIPATING",
|
| 147 |
-
"227": "
|
| 148 |
-
"228": "
|
| 149 |
-
"229": "
|
| 150 |
"23": "NOT_ALIVE",
|
| 151 |
-
"230": "
|
| 152 |
"231": "NON_PARTICIPATING",
|
| 153 |
-
"232": "
|
| 154 |
"233": "NON_PARTICIPATING",
|
| 155 |
-
"234": "
|
| 156 |
-
"235": "
|
| 157 |
"236": "NON_PARTICIPATING",
|
| 158 |
-
"237": "
|
| 159 |
"238": "NON_PARTICIPATING",
|
| 160 |
"239": "NON_PARTICIPATING",
|
| 161 |
-
"24": "
|
| 162 |
"240": "NOT_ALIVE",
|
| 163 |
-
"241": "
|
| 164 |
"242": "NOT_ALIVE",
|
| 165 |
"243": "NOT_ALIVE",
|
| 166 |
"244": "NOT_ALIVE",
|
| 167 |
"245": "NON_PARTICIPATING",
|
| 168 |
-
"246": "
|
| 169 |
"247": "NOT_ALIVE",
|
| 170 |
"248": "NON_PARTICIPATING",
|
| 171 |
"249": "NON_PARTICIPATING",
|
| 172 |
"25": "SUCCESS",
|
| 173 |
-
"250": "
|
| 174 |
"251": "NOT_ALIVE",
|
| 175 |
-
"252": "
|
| 176 |
"253": "NOT_ALIVE",
|
| 177 |
-
"254": "
|
| 178 |
-
"255": "
|
| 179 |
"26": "NON_PARTICIPATING",
|
| 180 |
"27": "NOT_ALIVE",
|
| 181 |
-
"28": "
|
| 182 |
-
"29": "
|
| 183 |
-
"3": "
|
| 184 |
"30": "NON_PARTICIPATING",
|
| 185 |
-
"31": "
|
| 186 |
"32": "NOT_ALIVE",
|
| 187 |
"33": "NOT_ALIVE",
|
| 188 |
"34": "NON_PARTICIPATING",
|
| 189 |
-
"35": "
|
| 190 |
"36": "NON_PARTICIPATING",
|
| 191 |
"37": "NON_PARTICIPATING",
|
| 192 |
"38": "NON_PARTICIPATING",
|
| 193 |
"39": "NOT_ALIVE",
|
| 194 |
-
"4": "
|
| 195 |
"40": "NON_PARTICIPATING",
|
| 196 |
"41": "NOT_ALIVE",
|
| 197 |
"42": "NON_PARTICIPATING",
|
| 198 |
"43": "NOT_ALIVE",
|
| 199 |
-
"44": "
|
| 200 |
"45": "NON_PARTICIPATING",
|
| 201 |
-
"46": "
|
| 202 |
"47": "NON_PARTICIPATING",
|
| 203 |
"48": "NOT_ALIVE",
|
| 204 |
"49": "NON_PARTICIPATING",
|
| 205 |
"5": "NON_PARTICIPATING",
|
| 206 |
-
"50": "
|
| 207 |
-
"51": "
|
| 208 |
"52": "NON_PARTICIPATING",
|
| 209 |
"53": "NON_PARTICIPATING",
|
| 210 |
"54": "NOT_ALIVE",
|
| 211 |
"55": "NOT_ALIVE",
|
| 212 |
"56": "NON_PARTICIPATING",
|
| 213 |
-
"57": "
|
| 214 |
"58": "NOT_ALIVE",
|
| 215 |
"59": "NON_PARTICIPATING",
|
| 216 |
"6": "NOT_ALIVE",
|
| 217 |
-
"60": "
|
| 218 |
"61": "NON_PARTICIPATING",
|
| 219 |
-
"62": "
|
| 220 |
-
"63": "
|
| 221 |
-
"64": "
|
| 222 |
"65": "NON_PARTICIPATING",
|
| 223 |
"66": "NON_PARTICIPATING",
|
| 224 |
"67": "NON_PARTICIPATING",
|
| 225 |
"68": "NOT_ALIVE",
|
| 226 |
-
"69": "
|
| 227 |
-
"7": "
|
| 228 |
-
"70": "
|
| 229 |
"71": "NON_PARTICIPATING",
|
| 230 |
"72": "NON_PARTICIPATING",
|
| 231 |
"73": "NON_PARTICIPATING",
|
| 232 |
-
"74": "
|
| 233 |
-
"75": "
|
| 234 |
"76": "NON_PARTICIPATING",
|
| 235 |
"77": "NOT_ALIVE",
|
| 236 |
"78": "NOT_ALIVE",
|
| 237 |
"79": "NOT_ALIVE",
|
| 238 |
-
"8": "
|
| 239 |
"80": "NON_PARTICIPATING",
|
| 240 |
"81": "NOT_ALIVE",
|
| 241 |
-
"82": "
|
| 242 |
"83": "NOT_ALIVE",
|
| 243 |
-
"84": "
|
| 244 |
"85": "NON_PARTICIPATING",
|
| 245 |
-
"86": "
|
| 246 |
"87": "NON_PARTICIPATING",
|
| 247 |
"88": "NOT_ALIVE",
|
| 248 |
-
"89": "
|
| 249 |
"9": "NON_PARTICIPATING",
|
| 250 |
-
"90": "
|
| 251 |
"91": "NON_PARTICIPATING",
|
| 252 |
-
"92": "
|
| 253 |
"93": "NOT_ALIVE",
|
| 254 |
-
"94": "
|
| 255 |
"95": "NOT_ALIVE",
|
| 256 |
-
"96": "
|
| 257 |
"97": "NOT_ALIVE",
|
| 258 |
"98": "NON_PARTICIPATING",
|
| 259 |
"99": "NON_PARTICIPATING"
|
|
@@ -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",
|
|
|
|
| 2 |
"_name_or_path": "distributed/llama-1b",
|
| 3 |
"all_reduce_scores": {
|
| 4 |
"0": "NOT_ALIVE",
|
| 5 |
+
"1": "NON_PARTICIPATING",
|
| 6 |
+
"10": "FAIL",
|
| 7 |
"100": "NOT_ALIVE",
|
| 8 |
"101": "NOT_ALIVE",
|
| 9 |
+
"102": "FAIL",
|
| 10 |
+
"103": "FAIL",
|
| 11 |
"104": "NOT_ALIVE",
|
| 12 |
+
"105": "FAIL",
|
| 13 |
+
"106": "FAIL",
|
| 14 |
"107": "NON_PARTICIPATING",
|
| 15 |
"108": "NON_PARTICIPATING",
|
| 16 |
+
"109": "FAIL",
|
| 17 |
+
"11": "FAIL",
|
| 18 |
"110": "NON_PARTICIPATING",
|
| 19 |
+
"111": "FAIL",
|
| 20 |
"112": "NON_PARTICIPATING",
|
| 21 |
+
"113": "FAIL",
|
| 22 |
+
"114": "FAIL",
|
| 23 |
"115": "NON_PARTICIPATING",
|
| 24 |
+
"116": "FAIL",
|
| 25 |
"117": "NON_PARTICIPATING",
|
| 26 |
+
"118": "NOT_ALIVE",
|
| 27 |
"119": "NON_PARTICIPATING",
|
| 28 |
"12": "NOT_ALIVE",
|
| 29 |
"120": "NOT_ALIVE",
|
| 30 |
"121": "NON_PARTICIPATING",
|
| 31 |
"122": "NON_PARTICIPATING",
|
| 32 |
+
"123": "FAIL",
|
| 33 |
"124": "NON_PARTICIPATING",
|
| 34 |
+
"125": "NON_PARTICIPATING",
|
| 35 |
+
"126": "FAIL",
|
| 36 |
"127": "NON_PARTICIPATING",
|
| 37 |
+
"128": "NON_PARTICIPATING",
|
| 38 |
+
"129": "NON_PARTICIPATING",
|
| 39 |
+
"13": "FAIL",
|
| 40 |
"130": "NOT_ALIVE",
|
| 41 |
"131": "NOT_ALIVE",
|
| 42 |
"132": "NOT_ALIVE",
|
| 43 |
"133": "NOT_ALIVE",
|
| 44 |
"134": "NOT_ALIVE",
|
| 45 |
+
"135": "NOT_ALIVE",
|
| 46 |
"136": "NON_PARTICIPATING",
|
| 47 |
"137": "NOT_ALIVE",
|
| 48 |
"138": "NON_PARTICIPATING",
|
|
|
|
| 50 |
"14": "NOT_ALIVE",
|
| 51 |
"140": "NON_PARTICIPATING",
|
| 52 |
"141": "NOT_ALIVE",
|
| 53 |
+
"142": "FAIL",
|
| 54 |
"143": "NON_PARTICIPATING",
|
| 55 |
"144": "NON_PARTICIPATING",
|
| 56 |
"145": "NOT_ALIVE",
|
| 57 |
+
"146": "FAIL",
|
| 58 |
+
"147": "FAIL",
|
| 59 |
+
"148": "NOT_ALIVE",
|
| 60 |
"149": "NON_PARTICIPATING",
|
| 61 |
"15": "NON_PARTICIPATING",
|
| 62 |
"150": "NOT_ALIVE",
|
| 63 |
"151": "NOT_ALIVE",
|
| 64 |
"152": "NOT_ALIVE",
|
| 65 |
+
"153": "FAIL",
|
| 66 |
+
"154": "FAIL",
|
| 67 |
+
"155": "FAIL",
|
| 68 |
"156": "NON_PARTICIPATING",
|
| 69 |
"157": "NON_PARTICIPATING",
|
| 70 |
"158": "NON_PARTICIPATING",
|
| 71 |
+
"159": "NOT_ALIVE",
|
| 72 |
"16": "NOT_ALIVE",
|
| 73 |
"160": "NOT_ALIVE",
|
| 74 |
"161": "NON_PARTICIPATING",
|
| 75 |
"162": "NOT_ALIVE",
|
| 76 |
+
"163": "FAIL",
|
| 77 |
"164": "NOT_ALIVE",
|
| 78 |
"165": "NOT_ALIVE",
|
| 79 |
+
"166": "FAIL",
|
| 80 |
+
"167": "NON_PARTICIPATING",
|
| 81 |
"168": "NON_PARTICIPATING",
|
| 82 |
+
"169": "NON_PARTICIPATING",
|
| 83 |
"17": "NON_PARTICIPATING",
|
| 84 |
+
"170": "NOT_ALIVE",
|
| 85 |
+
"171": "FAIL",
|
| 86 |
"172": "NOT_ALIVE",
|
| 87 |
"173": "NON_PARTICIPATING",
|
| 88 |
"174": "NOT_ALIVE",
|
| 89 |
+
"175": "FAIL",
|
| 90 |
"176": "NOT_ALIVE",
|
| 91 |
"177": "NON_PARTICIPATING",
|
| 92 |
"178": "NOT_ALIVE",
|
| 93 |
"179": "NOT_ALIVE",
|
| 94 |
"18": "NOT_ALIVE",
|
| 95 |
+
"180": "NOT_ALIVE",
|
| 96 |
"181": "NOT_ALIVE",
|
| 97 |
+
"182": "NON_PARTICIPATING",
|
| 98 |
+
"183": "FAIL",
|
| 99 |
+
"184": "FAIL",
|
| 100 |
+
"185": "FAIL",
|
| 101 |
+
"186": "FAIL",
|
| 102 |
+
"187": "NON_PARTICIPATING",
|
| 103 |
"188": "NON_PARTICIPATING",
|
| 104 |
"189": "NOT_ALIVE",
|
| 105 |
+
"19": "NON_PARTICIPATING",
|
| 106 |
"190": "NON_PARTICIPATING",
|
| 107 |
"191": "NOT_ALIVE",
|
| 108 |
"192": "NON_PARTICIPATING",
|
| 109 |
"193": "NON_PARTICIPATING",
|
| 110 |
"194": "NOT_ALIVE",
|
| 111 |
"195": "NOT_ALIVE",
|
| 112 |
+
"196": "FAIL",
|
| 113 |
+
"197": "NON_PARTICIPATING",
|
| 114 |
+
"198": "FAIL",
|
| 115 |
+
"199": "NON_PARTICIPATING",
|
| 116 |
"2": "NON_PARTICIPATING",
|
| 117 |
+
"20": "FAIL",
|
| 118 |
+
"200": "FAIL",
|
| 119 |
"201": "NOT_ALIVE",
|
| 120 |
"202": "NON_PARTICIPATING",
|
| 121 |
+
"203": "NOT_ALIVE",
|
| 122 |
"204": "NOT_ALIVE",
|
| 123 |
+
"205": "FAIL",
|
| 124 |
+
"206": "FAIL",
|
| 125 |
"207": "NOT_ALIVE",
|
| 126 |
"208": "NON_PARTICIPATING",
|
| 127 |
+
"209": "NON_PARTICIPATING",
|
| 128 |
+
"21": "NON_PARTICIPATING",
|
| 129 |
"210": "NON_PARTICIPATING",
|
| 130 |
+
"211": "FAIL",
|
| 131 |
+
"212": "NOT_ALIVE",
|
| 132 |
"213": "NON_PARTICIPATING",
|
| 133 |
+
"214": "NOT_ALIVE",
|
| 134 |
"215": "NON_PARTICIPATING",
|
| 135 |
"216": "NOT_ALIVE",
|
| 136 |
"217": "NOT_ALIVE",
|
| 137 |
"218": "NON_PARTICIPATING",
|
| 138 |
+
"219": "FAIL",
|
| 139 |
"22": "NOT_ALIVE",
|
| 140 |
"220": "NON_PARTICIPATING",
|
| 141 |
+
"221": "FAIL",
|
| 142 |
+
"222": "FAIL",
|
| 143 |
"223": "NON_PARTICIPATING",
|
| 144 |
"224": "NOT_ALIVE",
|
| 145 |
"225": "NON_PARTICIPATING",
|
| 146 |
"226": "NON_PARTICIPATING",
|
| 147 |
+
"227": "NON_PARTICIPATING",
|
| 148 |
+
"228": "NOT_ALIVE",
|
| 149 |
+
"229": "NOT_ALIVE",
|
| 150 |
"23": "NOT_ALIVE",
|
| 151 |
+
"230": "FAIL",
|
| 152 |
"231": "NON_PARTICIPATING",
|
| 153 |
+
"232": "FAIL",
|
| 154 |
"233": "NON_PARTICIPATING",
|
| 155 |
+
"234": "FAIL",
|
| 156 |
+
"235": "FAIL",
|
| 157 |
"236": "NON_PARTICIPATING",
|
| 158 |
+
"237": "FAIL",
|
| 159 |
"238": "NON_PARTICIPATING",
|
| 160 |
"239": "NON_PARTICIPATING",
|
| 161 |
+
"24": "NON_PARTICIPATING",
|
| 162 |
"240": "NOT_ALIVE",
|
| 163 |
+
"241": "FAIL",
|
| 164 |
"242": "NOT_ALIVE",
|
| 165 |
"243": "NOT_ALIVE",
|
| 166 |
"244": "NOT_ALIVE",
|
| 167 |
"245": "NON_PARTICIPATING",
|
| 168 |
+
"246": "NOT_ALIVE",
|
| 169 |
"247": "NOT_ALIVE",
|
| 170 |
"248": "NON_PARTICIPATING",
|
| 171 |
"249": "NON_PARTICIPATING",
|
| 172 |
"25": "SUCCESS",
|
| 173 |
+
"250": "FAIL",
|
| 174 |
"251": "NOT_ALIVE",
|
| 175 |
+
"252": "NOT_ALIVE",
|
| 176 |
"253": "NOT_ALIVE",
|
| 177 |
+
"254": "NOT_ALIVE",
|
| 178 |
+
"255": "FAIL",
|
| 179 |
"26": "NON_PARTICIPATING",
|
| 180 |
"27": "NOT_ALIVE",
|
| 181 |
+
"28": "NOT_ALIVE",
|
| 182 |
+
"29": "FAIL",
|
| 183 |
+
"3": "FAIL",
|
| 184 |
"30": "NON_PARTICIPATING",
|
| 185 |
+
"31": "FAIL",
|
| 186 |
"32": "NOT_ALIVE",
|
| 187 |
"33": "NOT_ALIVE",
|
| 188 |
"34": "NON_PARTICIPATING",
|
| 189 |
+
"35": "FAIL",
|
| 190 |
"36": "NON_PARTICIPATING",
|
| 191 |
"37": "NON_PARTICIPATING",
|
| 192 |
"38": "NON_PARTICIPATING",
|
| 193 |
"39": "NOT_ALIVE",
|
| 194 |
+
"4": "FAIL",
|
| 195 |
"40": "NON_PARTICIPATING",
|
| 196 |
"41": "NOT_ALIVE",
|
| 197 |
"42": "NON_PARTICIPATING",
|
| 198 |
"43": "NOT_ALIVE",
|
| 199 |
+
"44": "FAIL",
|
| 200 |
"45": "NON_PARTICIPATING",
|
| 201 |
+
"46": "FAIL",
|
| 202 |
"47": "NON_PARTICIPATING",
|
| 203 |
"48": "NOT_ALIVE",
|
| 204 |
"49": "NON_PARTICIPATING",
|
| 205 |
"5": "NON_PARTICIPATING",
|
| 206 |
+
"50": "NOT_ALIVE",
|
| 207 |
+
"51": "FAIL",
|
| 208 |
"52": "NON_PARTICIPATING",
|
| 209 |
"53": "NON_PARTICIPATING",
|
| 210 |
"54": "NOT_ALIVE",
|
| 211 |
"55": "NOT_ALIVE",
|
| 212 |
"56": "NON_PARTICIPATING",
|
| 213 |
+
"57": "NON_PARTICIPATING",
|
| 214 |
"58": "NOT_ALIVE",
|
| 215 |
"59": "NON_PARTICIPATING",
|
| 216 |
"6": "NOT_ALIVE",
|
| 217 |
+
"60": "NON_PARTICIPATING",
|
| 218 |
"61": "NON_PARTICIPATING",
|
| 219 |
+
"62": "NOT_ALIVE",
|
| 220 |
+
"63": "NON_PARTICIPATING",
|
| 221 |
+
"64": "FAIL",
|
| 222 |
"65": "NON_PARTICIPATING",
|
| 223 |
"66": "NON_PARTICIPATING",
|
| 224 |
"67": "NON_PARTICIPATING",
|
| 225 |
"68": "NOT_ALIVE",
|
| 226 |
+
"69": "NON_PARTICIPATING",
|
| 227 |
+
"7": "FAIL",
|
| 228 |
+
"70": "NON_PARTICIPATING",
|
| 229 |
"71": "NON_PARTICIPATING",
|
| 230 |
"72": "NON_PARTICIPATING",
|
| 231 |
"73": "NON_PARTICIPATING",
|
| 232 |
+
"74": "FAIL",
|
| 233 |
+
"75": "NOT_ALIVE",
|
| 234 |
"76": "NON_PARTICIPATING",
|
| 235 |
"77": "NOT_ALIVE",
|
| 236 |
"78": "NOT_ALIVE",
|
| 237 |
"79": "NOT_ALIVE",
|
| 238 |
+
"8": "NON_PARTICIPATING",
|
| 239 |
"80": "NON_PARTICIPATING",
|
| 240 |
"81": "NOT_ALIVE",
|
| 241 |
+
"82": "NON_PARTICIPATING",
|
| 242 |
"83": "NOT_ALIVE",
|
| 243 |
+
"84": "FAIL",
|
| 244 |
"85": "NON_PARTICIPATING",
|
| 245 |
+
"86": "NOT_ALIVE",
|
| 246 |
"87": "NON_PARTICIPATING",
|
| 247 |
"88": "NOT_ALIVE",
|
| 248 |
+
"89": "FAIL",
|
| 249 |
"9": "NON_PARTICIPATING",
|
| 250 |
+
"90": "FAIL",
|
| 251 |
"91": "NON_PARTICIPATING",
|
| 252 |
+
"92": "FAIL",
|
| 253 |
"93": "NOT_ALIVE",
|
| 254 |
+
"94": "FAIL",
|
| 255 |
"95": "NOT_ALIVE",
|
| 256 |
+
"96": "FAIL",
|
| 257 |
"97": "NOT_ALIVE",
|
| 258 |
"98": "NON_PARTICIPATING",
|
| 259 |
"99": "NON_PARTICIPATING"
|
|
|
|
| 264 |
"attention_bias": false,
|
| 265 |
"attention_dropout": 0.0,
|
| 266 |
"block_list": [
|
| 267 |
+
6496077,
|
| 268 |
+
6496121
|
| 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": 6495996,
|
| 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 88389626
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ccb2493b27ddb99c4b915d1bdf2760683e44c29257c6c45ceb7f21cf72cca54
|
| 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:cef65fed9ee4cecda96a0a339be879b37b1f1315b7c0e6e90562eed164b0657d
|
| 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 sha256:727ed76d262e71cf37aad590e4220ffcbcf9f211f8f8aae8df3135842323c8a2
|
| 3 |
size 4400216536
|