Run 5. Outer Step 37. Inner Step 2.
Browse files- config.json +42 -42
- inner_optimizer.pt +1 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -1,16 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"all_reduce_scores": {
|
| 4 |
"0": "NON_PARTICIPATING",
|
| 5 |
-
"1": "
|
| 6 |
"10": "SUCCESS",
|
| 7 |
"100": "NON_PARTICIPATING",
|
| 8 |
"101": "NON_PARTICIPATING",
|
| 9 |
"102": "NON_PARTICIPATING",
|
| 10 |
"103": "NON_PARTICIPATING",
|
| 11 |
"104": "NON_PARTICIPATING",
|
| 12 |
-
"105": "
|
| 13 |
-
"106": "
|
| 14 |
"107": "NON_PARTICIPATING",
|
| 15 |
"108": "NON_PARTICIPATING",
|
| 16 |
"109": "NON_PARTICIPATING",
|
|
@@ -25,13 +25,13 @@
|
|
| 25 |
"117": "NON_PARTICIPATING",
|
| 26 |
"118": "NON_PARTICIPATING",
|
| 27 |
"119": "NON_PARTICIPATING",
|
| 28 |
-
"12": "
|
| 29 |
"120": "NON_PARTICIPATING",
|
| 30 |
"121": "NON_PARTICIPATING",
|
| 31 |
"122": "NON_PARTICIPATING",
|
| 32 |
"123": "NON_PARTICIPATING",
|
| 33 |
"124": "NON_PARTICIPATING",
|
| 34 |
-
"125": "
|
| 35 |
"126": "NON_PARTICIPATING",
|
| 36 |
"127": "NON_PARTICIPATING",
|
| 37 |
"128": "NON_PARTICIPATING",
|
|
@@ -79,8 +79,8 @@
|
|
| 79 |
"166": "NON_PARTICIPATING",
|
| 80 |
"167": "SUCCESS",
|
| 81 |
"168": "NON_PARTICIPATING",
|
| 82 |
-
"169": "
|
| 83 |
-
"17": "
|
| 84 |
"170": "NON_PARTICIPATING",
|
| 85 |
"171": "NON_PARTICIPATING",
|
| 86 |
"172": "NON_PARTICIPATING",
|
|
@@ -94,11 +94,11 @@
|
|
| 94 |
"18": "SUCCESS",
|
| 95 |
"180": "NON_PARTICIPATING",
|
| 96 |
"181": "NON_PARTICIPATING",
|
| 97 |
-
"182": "
|
| 98 |
"183": "NON_PARTICIPATING",
|
| 99 |
"184": "NON_PARTICIPATING",
|
| 100 |
"185": "NON_PARTICIPATING",
|
| 101 |
-
"186": "
|
| 102 |
"187": "NON_PARTICIPATING",
|
| 103 |
"188": "NON_PARTICIPATING",
|
| 104 |
"189": "NON_PARTICIPATING",
|
|
@@ -107,7 +107,7 @@
|
|
| 107 |
"191": "NON_PARTICIPATING",
|
| 108 |
"192": "NON_PARTICIPATING",
|
| 109 |
"193": "NON_PARTICIPATING",
|
| 110 |
-
"194": "
|
| 111 |
"195": "NON_PARTICIPATING",
|
| 112 |
"196": "NON_PARTICIPATING",
|
| 113 |
"197": "NON_PARTICIPATING",
|
|
@@ -128,7 +128,7 @@
|
|
| 128 |
"21": "SUCCESS",
|
| 129 |
"210": "NON_PARTICIPATING",
|
| 130 |
"211": "NON_PARTICIPATING",
|
| 131 |
-
"212": "
|
| 132 |
"213": "NON_PARTICIPATING",
|
| 133 |
"214": "NON_PARTICIPATING",
|
| 134 |
"215": "NON_PARTICIPATING",
|
|
@@ -136,7 +136,7 @@
|
|
| 136 |
"217": "NON_PARTICIPATING",
|
| 137 |
"218": "NON_PARTICIPATING",
|
| 138 |
"219": "NON_PARTICIPATING",
|
| 139 |
-
"22": "
|
| 140 |
"220": "NON_PARTICIPATING",
|
| 141 |
"221": "NON_PARTICIPATING",
|
| 142 |
"222": "NON_PARTICIPATING",
|
|
@@ -176,11 +176,11 @@
|
|
| 176 |
"253": "NON_PARTICIPATING",
|
| 177 |
"254": "NON_PARTICIPATING",
|
| 178 |
"255": "NON_PARTICIPATING",
|
| 179 |
-
"26": "
|
| 180 |
-
"27": "
|
| 181 |
-
"28": "
|
| 182 |
"29": "SUCCESS",
|
| 183 |
-
"3": "
|
| 184 |
"30": "SUCCESS",
|
| 185 |
"31": "SUCCESS",
|
| 186 |
"32": "SUCCESS",
|
|
@@ -189,39 +189,39 @@
|
|
| 189 |
"35": "SUCCESS",
|
| 190 |
"36": "SUCCESS",
|
| 191 |
"37": "SUCCESS",
|
| 192 |
-
"38": "
|
| 193 |
-
"39": "
|
| 194 |
-
"4": "
|
| 195 |
"40": "SUCCESS",
|
| 196 |
"41": "SUCCESS",
|
| 197 |
"42": "SUCCESS",
|
| 198 |
-
"43": "
|
| 199 |
"44": "SUCCESS",
|
| 200 |
"45": "SUCCESS",
|
| 201 |
-
"46": "
|
| 202 |
-
"47": "
|
| 203 |
"48": "SUCCESS",
|
| 204 |
"49": "SUCCESS",
|
| 205 |
"5": "SUCCESS",
|
| 206 |
"50": "SUCCESS",
|
| 207 |
"51": "SUCCESS",
|
| 208 |
-
"52": "
|
| 209 |
"53": "SUCCESS",
|
| 210 |
"54": "SUCCESS",
|
| 211 |
"55": "SUCCESS",
|
| 212 |
-
"56": "
|
| 213 |
"57": "SUCCESS",
|
| 214 |
-
"58": "
|
| 215 |
"59": "SUCCESS",
|
| 216 |
"6": "SUCCESS",
|
| 217 |
"60": "SUCCESS",
|
| 218 |
-
"61": "
|
| 219 |
"62": "SUCCESS",
|
| 220 |
"63": "SUCCESS",
|
| 221 |
"64": "SUCCESS",
|
| 222 |
"65": "SUCCESS",
|
| 223 |
"66": "SUCCESS",
|
| 224 |
-
"67": "
|
| 225 |
"68": "SUCCESS",
|
| 226 |
"69": "SUCCESS",
|
| 227 |
"7": "SUCCESS",
|
|
@@ -229,29 +229,29 @@
|
|
| 229 |
"71": "SUCCESS",
|
| 230 |
"72": "SUCCESS",
|
| 231 |
"73": "SUCCESS",
|
| 232 |
-
"74": "
|
| 233 |
-
"75": "
|
| 234 |
"76": "SUCCESS",
|
| 235 |
"77": "SUCCESS",
|
| 236 |
"78": "SUCCESS",
|
| 237 |
"79": "SUCCESS",
|
| 238 |
"8": "SUCCESS",
|
| 239 |
-
"80": "
|
| 240 |
-
"81": "
|
| 241 |
"82": "SUCCESS",
|
| 242 |
-
"83": "
|
| 243 |
"84": "SUCCESS",
|
| 244 |
"85": "SUCCESS",
|
| 245 |
"86": "SUCCESS",
|
| 246 |
"87": "SUCCESS",
|
| 247 |
-
"88": "
|
| 248 |
-
"89": "
|
| 249 |
"9": "SUCCESS",
|
| 250 |
"90": "SUCCESS",
|
| 251 |
-
"91": "
|
| 252 |
-
"92": "
|
| 253 |
"93": "SUCCESS",
|
| 254 |
-
"94": "
|
| 255 |
"95": "SUCCESS",
|
| 256 |
"96": "NON_PARTICIPATING",
|
| 257 |
"97": "SUCCESS",
|
|
@@ -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",
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "distributed/llama-1b",
|
| 3 |
"all_reduce_scores": {
|
| 4 |
"0": "NON_PARTICIPATING",
|
| 5 |
+
"1": "SUCCESS",
|
| 6 |
"10": "SUCCESS",
|
| 7 |
"100": "NON_PARTICIPATING",
|
| 8 |
"101": "NON_PARTICIPATING",
|
| 9 |
"102": "NON_PARTICIPATING",
|
| 10 |
"103": "NON_PARTICIPATING",
|
| 11 |
"104": "NON_PARTICIPATING",
|
| 12 |
+
"105": "SUCCESS",
|
| 13 |
+
"106": "SUCCESS",
|
| 14 |
"107": "NON_PARTICIPATING",
|
| 15 |
"108": "NON_PARTICIPATING",
|
| 16 |
"109": "NON_PARTICIPATING",
|
|
|
|
| 25 |
"117": "NON_PARTICIPATING",
|
| 26 |
"118": "NON_PARTICIPATING",
|
| 27 |
"119": "NON_PARTICIPATING",
|
| 28 |
+
"12": "NON_PARTICIPATING",
|
| 29 |
"120": "NON_PARTICIPATING",
|
| 30 |
"121": "NON_PARTICIPATING",
|
| 31 |
"122": "NON_PARTICIPATING",
|
| 32 |
"123": "NON_PARTICIPATING",
|
| 33 |
"124": "NON_PARTICIPATING",
|
| 34 |
+
"125": "NON_PARTICIPATING",
|
| 35 |
"126": "NON_PARTICIPATING",
|
| 36 |
"127": "NON_PARTICIPATING",
|
| 37 |
"128": "NON_PARTICIPATING",
|
|
|
|
| 79 |
"166": "NON_PARTICIPATING",
|
| 80 |
"167": "SUCCESS",
|
| 81 |
"168": "NON_PARTICIPATING",
|
| 82 |
+
"169": "NON_PARTICIPATING",
|
| 83 |
+
"17": "SUCCESS",
|
| 84 |
"170": "NON_PARTICIPATING",
|
| 85 |
"171": "NON_PARTICIPATING",
|
| 86 |
"172": "NON_PARTICIPATING",
|
|
|
|
| 94 |
"18": "SUCCESS",
|
| 95 |
"180": "NON_PARTICIPATING",
|
| 96 |
"181": "NON_PARTICIPATING",
|
| 97 |
+
"182": "NON_PARTICIPATING",
|
| 98 |
"183": "NON_PARTICIPATING",
|
| 99 |
"184": "NON_PARTICIPATING",
|
| 100 |
"185": "NON_PARTICIPATING",
|
| 101 |
+
"186": "SUCCESS",
|
| 102 |
"187": "NON_PARTICIPATING",
|
| 103 |
"188": "NON_PARTICIPATING",
|
| 104 |
"189": "NON_PARTICIPATING",
|
|
|
|
| 107 |
"191": "NON_PARTICIPATING",
|
| 108 |
"192": "NON_PARTICIPATING",
|
| 109 |
"193": "NON_PARTICIPATING",
|
| 110 |
+
"194": "NON_PARTICIPATING",
|
| 111 |
"195": "NON_PARTICIPATING",
|
| 112 |
"196": "NON_PARTICIPATING",
|
| 113 |
"197": "NON_PARTICIPATING",
|
|
|
|
| 128 |
"21": "SUCCESS",
|
| 129 |
"210": "NON_PARTICIPATING",
|
| 130 |
"211": "NON_PARTICIPATING",
|
| 131 |
+
"212": "SUCCESS",
|
| 132 |
"213": "NON_PARTICIPATING",
|
| 133 |
"214": "NON_PARTICIPATING",
|
| 134 |
"215": "NON_PARTICIPATING",
|
|
|
|
| 136 |
"217": "NON_PARTICIPATING",
|
| 137 |
"218": "NON_PARTICIPATING",
|
| 138 |
"219": "NON_PARTICIPATING",
|
| 139 |
+
"22": "SUCCESS",
|
| 140 |
"220": "NON_PARTICIPATING",
|
| 141 |
"221": "NON_PARTICIPATING",
|
| 142 |
"222": "NON_PARTICIPATING",
|
|
|
|
| 176 |
"253": "NON_PARTICIPATING",
|
| 177 |
"254": "NON_PARTICIPATING",
|
| 178 |
"255": "NON_PARTICIPATING",
|
| 179 |
+
"26": "NON_PARTICIPATING",
|
| 180 |
+
"27": "SUCCESS",
|
| 181 |
+
"28": "SUCCESS",
|
| 182 |
"29": "SUCCESS",
|
| 183 |
+
"3": "SUCCESS",
|
| 184 |
"30": "SUCCESS",
|
| 185 |
"31": "SUCCESS",
|
| 186 |
"32": "SUCCESS",
|
|
|
|
| 189 |
"35": "SUCCESS",
|
| 190 |
"36": "SUCCESS",
|
| 191 |
"37": "SUCCESS",
|
| 192 |
+
"38": "SUCCESS",
|
| 193 |
+
"39": "SUCCESS",
|
| 194 |
+
"4": "SUCCESS",
|
| 195 |
"40": "SUCCESS",
|
| 196 |
"41": "SUCCESS",
|
| 197 |
"42": "SUCCESS",
|
| 198 |
+
"43": "SUCCESS",
|
| 199 |
"44": "SUCCESS",
|
| 200 |
"45": "SUCCESS",
|
| 201 |
+
"46": "SUCCESS",
|
| 202 |
+
"47": "SUCCESS",
|
| 203 |
"48": "SUCCESS",
|
| 204 |
"49": "SUCCESS",
|
| 205 |
"5": "SUCCESS",
|
| 206 |
"50": "SUCCESS",
|
| 207 |
"51": "SUCCESS",
|
| 208 |
+
"52": "SUCCESS",
|
| 209 |
"53": "SUCCESS",
|
| 210 |
"54": "SUCCESS",
|
| 211 |
"55": "SUCCESS",
|
| 212 |
+
"56": "SUCCESS",
|
| 213 |
"57": "SUCCESS",
|
| 214 |
+
"58": "SUCCESS",
|
| 215 |
"59": "SUCCESS",
|
| 216 |
"6": "SUCCESS",
|
| 217 |
"60": "SUCCESS",
|
| 218 |
+
"61": "SUCCESS",
|
| 219 |
"62": "SUCCESS",
|
| 220 |
"63": "SUCCESS",
|
| 221 |
"64": "SUCCESS",
|
| 222 |
"65": "SUCCESS",
|
| 223 |
"66": "SUCCESS",
|
| 224 |
+
"67": "SUCCESS",
|
| 225 |
"68": "SUCCESS",
|
| 226 |
"69": "SUCCESS",
|
| 227 |
"7": "SUCCESS",
|
|
|
|
| 229 |
"71": "SUCCESS",
|
| 230 |
"72": "SUCCESS",
|
| 231 |
"73": "SUCCESS",
|
| 232 |
+
"74": "SUCCESS",
|
| 233 |
+
"75": "SUCCESS",
|
| 234 |
"76": "SUCCESS",
|
| 235 |
"77": "SUCCESS",
|
| 236 |
"78": "SUCCESS",
|
| 237 |
"79": "SUCCESS",
|
| 238 |
"8": "SUCCESS",
|
| 239 |
+
"80": "SUCCESS",
|
| 240 |
+
"81": "SUCCESS",
|
| 241 |
"82": "SUCCESS",
|
| 242 |
+
"83": "SUCCESS",
|
| 243 |
"84": "SUCCESS",
|
| 244 |
"85": "SUCCESS",
|
| 245 |
"86": "SUCCESS",
|
| 246 |
"87": "SUCCESS",
|
| 247 |
+
"88": "SUCCESS",
|
| 248 |
+
"89": "SUCCESS",
|
| 249 |
"9": "SUCCESS",
|
| 250 |
"90": "SUCCESS",
|
| 251 |
+
"91": "SUCCESS",
|
| 252 |
+
"92": "SUCCESS",
|
| 253 |
"93": "SUCCESS",
|
| 254 |
+
"94": "SUCCESS",
|
| 255 |
"95": "SUCCESS",
|
| 256 |
"96": "NON_PARTICIPATING",
|
| 257 |
"97": "SUCCESS",
|
|
|
|
| 264 |
"attention_bias": false,
|
| 265 |
"attention_dropout": 0.0,
|
| 266 |
"block_list": [
|
| 267 |
+
5748608,
|
| 268 |
+
5748637
|
| 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": 2,
|
| 276 |
"intermediate_size": 5632,
|
| 277 |
+
"last_allreduce_block": 5748531,
|
| 278 |
"max_position_embeddings": 2048,
|
| 279 |
"mlp_bias": false,
|
| 280 |
"model_type": "llama",
|
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:b5eec1ccc838e7d1a7ffa23e2cc82684fb2081d53c33623e7ec596f7580e3056
|
| 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 sha256:4d3149037da350762ff4f4023ef46390aaf8806025e2069749e1ff1ebcb42b03
|
| 3 |
size 4400216536
|