Run 6. Outer Step 22. Inner Step 6.
Browse files- config.json +42 -42
- gradients.pt +1 -1
- inner_optimizer.pt +1 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -2,22 +2,22 @@
|
|
| 2 |
"_name_or_path": "distributed/llama-1b",
|
| 3 |
"all_reduce_scores": {
|
| 4 |
"0": "NOT_ALIVE",
|
| 5 |
-
"1": "
|
| 6 |
"10": "NOT_ALIVE",
|
| 7 |
-
"100": "
|
| 8 |
"101": "NON_PARTICIPATING",
|
| 9 |
-
"102": "
|
| 10 |
"103": "NOT_ALIVE",
|
| 11 |
"104": "NOT_ALIVE",
|
| 12 |
"105": "NON_PARTICIPATING",
|
| 13 |
"106": "NOT_ALIVE",
|
| 14 |
"107": "NOT_ALIVE",
|
| 15 |
-
"108": "
|
| 16 |
"109": "NOT_ALIVE",
|
| 17 |
"11": "NOT_ALIVE",
|
| 18 |
"110": "NOT_ALIVE",
|
| 19 |
"111": "NON_PARTICIPATING",
|
| 20 |
-
"112": "
|
| 21 |
"113": "NOT_ALIVE",
|
| 22 |
"114": "NOT_ALIVE",
|
| 23 |
"115": "NOT_ALIVE",
|
|
@@ -42,16 +42,16 @@
|
|
| 42 |
"132": "NOT_ALIVE",
|
| 43 |
"133": "SUCCESS",
|
| 44 |
"134": "NOT_ALIVE",
|
| 45 |
-
"135": "
|
| 46 |
"136": "NON_PARTICIPATING",
|
| 47 |
"137": "NON_PARTICIPATING",
|
| 48 |
"138": "NON_PARTICIPATING",
|
| 49 |
-
"139": "
|
| 50 |
"14": "NOT_ALIVE",
|
| 51 |
"140": "SUCCESS",
|
| 52 |
"141": "NON_PARTICIPATING",
|
| 53 |
"142": "NON_PARTICIPATING",
|
| 54 |
-
"143": "
|
| 55 |
"144": "SUCCESS",
|
| 56 |
"145": "NOT_ALIVE",
|
| 57 |
"146": "NON_PARTICIPATING",
|
|
@@ -68,12 +68,12 @@
|
|
| 68 |
"156": "NOT_ALIVE",
|
| 69 |
"157": "NOT_ALIVE",
|
| 70 |
"158": "NON_PARTICIPATING",
|
| 71 |
-
"159": "
|
| 72 |
"16": "NOT_ALIVE",
|
| 73 |
"160": "NON_PARTICIPATING",
|
| 74 |
"161": "NON_PARTICIPATING",
|
| 75 |
"162": "NON_PARTICIPATING",
|
| 76 |
-
"163": "
|
| 77 |
"164": "NOT_ALIVE",
|
| 78 |
"165": "NON_PARTICIPATING",
|
| 79 |
"166": "NON_PARTICIPATING",
|
|
@@ -90,15 +90,15 @@
|
|
| 90 |
"176": "NOT_ALIVE",
|
| 91 |
"177": "NOT_ALIVE",
|
| 92 |
"178": "NOT_ALIVE",
|
| 93 |
-
"179": "
|
| 94 |
"18": "SUCCESS",
|
| 95 |
"180": "NON_PARTICIPATING",
|
| 96 |
"181": "NOT_ALIVE",
|
| 97 |
"182": "NON_PARTICIPATING",
|
| 98 |
"183": "NOT_ALIVE",
|
| 99 |
-
"184": "
|
| 100 |
"185": "NON_PARTICIPATING",
|
| 101 |
-
"186": "
|
| 102 |
"187": "SUCCESS",
|
| 103 |
"188": "SUCCESS",
|
| 104 |
"189": "SUCCESS",
|
|
@@ -116,11 +116,11 @@
|
|
| 116 |
"2": "NOT_ALIVE",
|
| 117 |
"20": "NOT_ALIVE",
|
| 118 |
"200": "NON_PARTICIPATING",
|
| 119 |
-
"201": "
|
| 120 |
"202": "NON_PARTICIPATING",
|
| 121 |
"203": "NON_PARTICIPATING",
|
| 122 |
-
"204": "
|
| 123 |
-
"205": "
|
| 124 |
"206": "NOT_ALIVE",
|
| 125 |
"207": "NOT_ALIVE",
|
| 126 |
"208": "NOT_ALIVE",
|
|
@@ -141,10 +141,10 @@
|
|
| 141 |
"221": "NOT_ALIVE",
|
| 142 |
"222": "NON_PARTICIPATING",
|
| 143 |
"223": "NOT_ALIVE",
|
| 144 |
-
"224": "
|
| 145 |
-
"225": "
|
| 146 |
-
"226": "
|
| 147 |
-
"227": "
|
| 148 |
"228": "SUCCESS",
|
| 149 |
"229": "NOT_ALIVE",
|
| 150 |
"23": "SUCCESS",
|
|
@@ -165,7 +165,7 @@
|
|
| 165 |
"243": "NOT_ALIVE",
|
| 166 |
"244": "NON_PARTICIPATING",
|
| 167 |
"245": "NON_PARTICIPATING",
|
| 168 |
-
"246": "
|
| 169 |
"247": "NOT_ALIVE",
|
| 170 |
"248": "NOT_ALIVE",
|
| 171 |
"249": "NOT_ALIVE",
|
|
@@ -174,23 +174,23 @@
|
|
| 174 |
"251": "NON_PARTICIPATING",
|
| 175 |
"252": "NON_PARTICIPATING",
|
| 176 |
"253": "NON_PARTICIPATING",
|
| 177 |
-
"254": "
|
| 178 |
"255": "NON_PARTICIPATING",
|
| 179 |
-
"26": "
|
| 180 |
"27": "NOT_ALIVE",
|
| 181 |
"28": "NON_PARTICIPATING",
|
| 182 |
"29": "NOT_ALIVE",
|
| 183 |
"3": "SUCCESS",
|
| 184 |
"30": "NOT_ALIVE",
|
| 185 |
-
"31": "
|
| 186 |
-
"32": "
|
| 187 |
"33": "NOT_ALIVE",
|
| 188 |
"34": "NON_PARTICIPATING",
|
| 189 |
"35": "NON_PARTICIPATING",
|
| 190 |
"36": "SUCCESS",
|
| 191 |
"37": "NOT_ALIVE",
|
| 192 |
"38": "NON_PARTICIPATING",
|
| 193 |
-
"39": "
|
| 194 |
"4": "NOT_ALIVE",
|
| 195 |
"40": "NON_PARTICIPATING",
|
| 196 |
"41": "NOT_ALIVE",
|
|
@@ -198,7 +198,7 @@
|
|
| 198 |
"43": "NON_PARTICIPATING",
|
| 199 |
"44": "NON_PARTICIPATING",
|
| 200 |
"45": "NOT_ALIVE",
|
| 201 |
-
"46": "
|
| 202 |
"47": "NOT_ALIVE",
|
| 203 |
"48": "NON_PARTICIPATING",
|
| 204 |
"49": "NOT_ALIVE",
|
|
@@ -209,40 +209,40 @@
|
|
| 209 |
"53": "NON_PARTICIPATING",
|
| 210 |
"54": "NOT_ALIVE",
|
| 211 |
"55": "NON_PARTICIPATING",
|
| 212 |
-
"56": "
|
| 213 |
"57": "NON_PARTICIPATING",
|
| 214 |
"58": "NOT_ALIVE",
|
| 215 |
"59": "NON_PARTICIPATING",
|
| 216 |
"6": "NOT_ALIVE",
|
| 217 |
-
"60": "
|
| 218 |
"61": "NON_PARTICIPATING",
|
| 219 |
"62": "NOT_ALIVE",
|
| 220 |
-
"63": "
|
| 221 |
-
"64": "
|
| 222 |
"65": "NON_PARTICIPATING",
|
| 223 |
"66": "NON_PARTICIPATING",
|
| 224 |
"67": "NON_PARTICIPATING",
|
| 225 |
"68": "NOT_ALIVE",
|
| 226 |
"69": "NOT_ALIVE",
|
| 227 |
"7": "NOT_ALIVE",
|
| 228 |
-
"70": "
|
| 229 |
-
"71": "
|
| 230 |
-
"72": "
|
| 231 |
"73": "NOT_ALIVE",
|
| 232 |
"74": "NOT_ALIVE",
|
| 233 |
"75": "NON_PARTICIPATING",
|
| 234 |
"76": "NOT_ALIVE",
|
| 235 |
-
"77": "
|
| 236 |
"78": "NON_PARTICIPATING",
|
| 237 |
"79": "NOT_ALIVE",
|
| 238 |
"8": "NOT_ALIVE",
|
| 239 |
"80": "SUCCESS",
|
| 240 |
"81": "NON_PARTICIPATING",
|
| 241 |
"82": "NOT_ALIVE",
|
| 242 |
-
"83": "
|
| 243 |
-
"84": "
|
| 244 |
"85": "NOT_ALIVE",
|
| 245 |
-
"86": "
|
| 246 |
"87": "NOT_ALIVE",
|
| 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",
|
|
|
|
| 2 |
"_name_or_path": "distributed/llama-1b",
|
| 3 |
"all_reduce_scores": {
|
| 4 |
"0": "NOT_ALIVE",
|
| 5 |
+
"1": "SUCCESS",
|
| 6 |
"10": "NOT_ALIVE",
|
| 7 |
+
"100": "NOT_ALIVE",
|
| 8 |
"101": "NON_PARTICIPATING",
|
| 9 |
+
"102": "NOT_ALIVE",
|
| 10 |
"103": "NOT_ALIVE",
|
| 11 |
"104": "NOT_ALIVE",
|
| 12 |
"105": "NON_PARTICIPATING",
|
| 13 |
"106": "NOT_ALIVE",
|
| 14 |
"107": "NOT_ALIVE",
|
| 15 |
+
"108": "NON_PARTICIPATING",
|
| 16 |
"109": "NOT_ALIVE",
|
| 17 |
"11": "NOT_ALIVE",
|
| 18 |
"110": "NOT_ALIVE",
|
| 19 |
"111": "NON_PARTICIPATING",
|
| 20 |
+
"112": "NON_PARTICIPATING",
|
| 21 |
"113": "NOT_ALIVE",
|
| 22 |
"114": "NOT_ALIVE",
|
| 23 |
"115": "NOT_ALIVE",
|
|
|
|
| 42 |
"132": "NOT_ALIVE",
|
| 43 |
"133": "SUCCESS",
|
| 44 |
"134": "NOT_ALIVE",
|
| 45 |
+
"135": "NON_PARTICIPATING",
|
| 46 |
"136": "NON_PARTICIPATING",
|
| 47 |
"137": "NON_PARTICIPATING",
|
| 48 |
"138": "NON_PARTICIPATING",
|
| 49 |
+
"139": "NOT_ALIVE",
|
| 50 |
"14": "NOT_ALIVE",
|
| 51 |
"140": "SUCCESS",
|
| 52 |
"141": "NON_PARTICIPATING",
|
| 53 |
"142": "NON_PARTICIPATING",
|
| 54 |
+
"143": "NON_PARTICIPATING",
|
| 55 |
"144": "SUCCESS",
|
| 56 |
"145": "NOT_ALIVE",
|
| 57 |
"146": "NON_PARTICIPATING",
|
|
|
|
| 68 |
"156": "NOT_ALIVE",
|
| 69 |
"157": "NOT_ALIVE",
|
| 70 |
"158": "NON_PARTICIPATING",
|
| 71 |
+
"159": "NOT_ALIVE",
|
| 72 |
"16": "NOT_ALIVE",
|
| 73 |
"160": "NON_PARTICIPATING",
|
| 74 |
"161": "NON_PARTICIPATING",
|
| 75 |
"162": "NON_PARTICIPATING",
|
| 76 |
+
"163": "NOT_ALIVE",
|
| 77 |
"164": "NOT_ALIVE",
|
| 78 |
"165": "NON_PARTICIPATING",
|
| 79 |
"166": "NON_PARTICIPATING",
|
|
|
|
| 90 |
"176": "NOT_ALIVE",
|
| 91 |
"177": "NOT_ALIVE",
|
| 92 |
"178": "NOT_ALIVE",
|
| 93 |
+
"179": "NOT_ALIVE",
|
| 94 |
"18": "SUCCESS",
|
| 95 |
"180": "NON_PARTICIPATING",
|
| 96 |
"181": "NOT_ALIVE",
|
| 97 |
"182": "NON_PARTICIPATING",
|
| 98 |
"183": "NOT_ALIVE",
|
| 99 |
+
"184": "NON_PARTICIPATING",
|
| 100 |
"185": "NON_PARTICIPATING",
|
| 101 |
+
"186": "NON_PARTICIPATING",
|
| 102 |
"187": "SUCCESS",
|
| 103 |
"188": "SUCCESS",
|
| 104 |
"189": "SUCCESS",
|
|
|
|
| 116 |
"2": "NOT_ALIVE",
|
| 117 |
"20": "NOT_ALIVE",
|
| 118 |
"200": "NON_PARTICIPATING",
|
| 119 |
+
"201": "SUCCESS",
|
| 120 |
"202": "NON_PARTICIPATING",
|
| 121 |
"203": "NON_PARTICIPATING",
|
| 122 |
+
"204": "NOT_ALIVE",
|
| 123 |
+
"205": "NOT_ALIVE",
|
| 124 |
"206": "NOT_ALIVE",
|
| 125 |
"207": "NOT_ALIVE",
|
| 126 |
"208": "NOT_ALIVE",
|
|
|
|
| 141 |
"221": "NOT_ALIVE",
|
| 142 |
"222": "NON_PARTICIPATING",
|
| 143 |
"223": "NOT_ALIVE",
|
| 144 |
+
"224": "NOT_ALIVE",
|
| 145 |
+
"225": "NOT_ALIVE",
|
| 146 |
+
"226": "NON_PARTICIPATING",
|
| 147 |
+
"227": "NON_PARTICIPATING",
|
| 148 |
"228": "SUCCESS",
|
| 149 |
"229": "NOT_ALIVE",
|
| 150 |
"23": "SUCCESS",
|
|
|
|
| 165 |
"243": "NOT_ALIVE",
|
| 166 |
"244": "NON_PARTICIPATING",
|
| 167 |
"245": "NON_PARTICIPATING",
|
| 168 |
+
"246": "NON_PARTICIPATING",
|
| 169 |
"247": "NOT_ALIVE",
|
| 170 |
"248": "NOT_ALIVE",
|
| 171 |
"249": "NOT_ALIVE",
|
|
|
|
| 174 |
"251": "NON_PARTICIPATING",
|
| 175 |
"252": "NON_PARTICIPATING",
|
| 176 |
"253": "NON_PARTICIPATING",
|
| 177 |
+
"254": "NON_PARTICIPATING",
|
| 178 |
"255": "NON_PARTICIPATING",
|
| 179 |
+
"26": "NON_PARTICIPATING",
|
| 180 |
"27": "NOT_ALIVE",
|
| 181 |
"28": "NON_PARTICIPATING",
|
| 182 |
"29": "NOT_ALIVE",
|
| 183 |
"3": "SUCCESS",
|
| 184 |
"30": "NOT_ALIVE",
|
| 185 |
+
"31": "NOT_ALIVE",
|
| 186 |
+
"32": "FAIL",
|
| 187 |
"33": "NOT_ALIVE",
|
| 188 |
"34": "NON_PARTICIPATING",
|
| 189 |
"35": "NON_PARTICIPATING",
|
| 190 |
"36": "SUCCESS",
|
| 191 |
"37": "NOT_ALIVE",
|
| 192 |
"38": "NON_PARTICIPATING",
|
| 193 |
+
"39": "NOT_ALIVE",
|
| 194 |
"4": "NOT_ALIVE",
|
| 195 |
"40": "NON_PARTICIPATING",
|
| 196 |
"41": "NOT_ALIVE",
|
|
|
|
| 198 |
"43": "NON_PARTICIPATING",
|
| 199 |
"44": "NON_PARTICIPATING",
|
| 200 |
"45": "NOT_ALIVE",
|
| 201 |
+
"46": "SUCCESS",
|
| 202 |
"47": "NOT_ALIVE",
|
| 203 |
"48": "NON_PARTICIPATING",
|
| 204 |
"49": "NOT_ALIVE",
|
|
|
|
| 209 |
"53": "NON_PARTICIPATING",
|
| 210 |
"54": "NOT_ALIVE",
|
| 211 |
"55": "NON_PARTICIPATING",
|
| 212 |
+
"56": "NOT_ALIVE",
|
| 213 |
"57": "NON_PARTICIPATING",
|
| 214 |
"58": "NOT_ALIVE",
|
| 215 |
"59": "NON_PARTICIPATING",
|
| 216 |
"6": "NOT_ALIVE",
|
| 217 |
+
"60": "NOT_ALIVE",
|
| 218 |
"61": "NON_PARTICIPATING",
|
| 219 |
"62": "NOT_ALIVE",
|
| 220 |
+
"63": "FAIL",
|
| 221 |
+
"64": "NOT_ALIVE",
|
| 222 |
"65": "NON_PARTICIPATING",
|
| 223 |
"66": "NON_PARTICIPATING",
|
| 224 |
"67": "NON_PARTICIPATING",
|
| 225 |
"68": "NOT_ALIVE",
|
| 226 |
"69": "NOT_ALIVE",
|
| 227 |
"7": "NOT_ALIVE",
|
| 228 |
+
"70": "NOT_ALIVE",
|
| 229 |
+
"71": "NON_PARTICIPATING",
|
| 230 |
+
"72": "NOT_ALIVE",
|
| 231 |
"73": "NOT_ALIVE",
|
| 232 |
"74": "NOT_ALIVE",
|
| 233 |
"75": "NON_PARTICIPATING",
|
| 234 |
"76": "NOT_ALIVE",
|
| 235 |
+
"77": "NOT_ALIVE",
|
| 236 |
"78": "NON_PARTICIPATING",
|
| 237 |
"79": "NOT_ALIVE",
|
| 238 |
"8": "NOT_ALIVE",
|
| 239 |
"80": "SUCCESS",
|
| 240 |
"81": "NON_PARTICIPATING",
|
| 241 |
"82": "NOT_ALIVE",
|
| 242 |
+
"83": "FAIL",
|
| 243 |
+
"84": "NOT_ALIVE",
|
| 244 |
"85": "NOT_ALIVE",
|
| 245 |
+
"86": "NOT_ALIVE",
|
| 246 |
"87": "NOT_ALIVE",
|
| 247 |
"88": "NON_PARTICIPATING",
|
| 248 |
"89": "NOT_ALIVE",
|
|
|
|
| 264 |
"attention_bias": false,
|
| 265 |
"attention_dropout": 0.0,
|
| 266 |
"block_list": [
|
| 267 |
+
6140177,
|
| 268 |
+
6140193
|
| 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": 5,
|
| 276 |
"intermediate_size": 5632,
|
| 277 |
+
"last_allreduce_block": 6140120,
|
| 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:a8eeaad438c4f63166b74cf0acb24bc08da4b083bce878faf1b7cf7389212e27
|
| 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 8800564076
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63759b8415ada75d6711e7c8b5f48d6d0e4e7734d6efc20b46321545cb14f7ef
|
| 3 |
size 8800564076
|
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 sha256:7a74184bf38408442eb09cd8edddc53b5b59cbbe9415a3b6e5d280623da2a05b
|
| 3 |
size 4400216536
|