Run 11. Outer Step 409. Inner Step 5.
Browse files- config.json +30 -30
- gradients.pt +1 -1
- inner_optimizer.pt +1 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"all_reduce_scores": {
|
| 4 |
"0": "NOT_ALIVE",
|
| 5 |
"1": "NOT_ALIVE",
|
| 6 |
-
"10": "
|
| 7 |
"100": "NOT_ALIVE",
|
| 8 |
"101": "SUCCESS",
|
| 9 |
"102": "NOT_ALIVE",
|
|
@@ -13,15 +13,15 @@
|
|
| 13 |
"106": "NOT_ALIVE",
|
| 14 |
"107": "NON_PARTICIPATING",
|
| 15 |
"108": "SUCCESS",
|
| 16 |
-
"109": "
|
| 17 |
"11": "NOT_ALIVE",
|
| 18 |
"110": "SUCCESS",
|
| 19 |
"111": "NON_PARTICIPATING",
|
| 20 |
"112": "SUCCESS",
|
| 21 |
-
"113": "
|
| 22 |
"114": "NOT_ALIVE",
|
| 23 |
-
"115": "
|
| 24 |
-
"116": "
|
| 25 |
"117": "NOT_ALIVE",
|
| 26 |
"118": "NOT_ALIVE",
|
| 27 |
"119": "SUCCESS",
|
|
@@ -33,21 +33,21 @@
|
|
| 33 |
"124": "NOT_ALIVE",
|
| 34 |
"125": "NOT_ALIVE",
|
| 35 |
"126": "NOT_ALIVE",
|
| 36 |
-
"127": "
|
| 37 |
"128": "NOT_ALIVE",
|
| 38 |
"129": "NOT_ALIVE",
|
| 39 |
-
"13": "
|
| 40 |
"130": "NON_PARTICIPATING",
|
| 41 |
"131": "NOT_ALIVE",
|
| 42 |
"132": "NOT_ALIVE",
|
| 43 |
"133": "NOT_ALIVE",
|
| 44 |
-
"134": "
|
| 45 |
-
"135": "
|
| 46 |
"136": "NOT_ALIVE",
|
| 47 |
"137": "NOT_ALIVE",
|
| 48 |
"138": "NOT_ALIVE",
|
| 49 |
"139": "NON_PARTICIPATING",
|
| 50 |
-
"14": "
|
| 51 |
"140": "SUCCESS",
|
| 52 |
"141": "NOT_ALIVE",
|
| 53 |
"142": "NOT_ALIVE",
|
|
@@ -66,13 +66,13 @@
|
|
| 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",
|
| 73 |
"160": "SUCCESS",
|
| 74 |
"161": "NOT_ALIVE",
|
| 75 |
-
"162": "
|
| 76 |
"163": "NOT_ALIVE",
|
| 77 |
"164": "NOT_ALIVE",
|
| 78 |
"165": "NOT_ALIVE",
|
|
@@ -84,9 +84,9 @@
|
|
| 84 |
"170": "NOT_ALIVE",
|
| 85 |
"171": "NOT_ALIVE",
|
| 86 |
"172": "NOT_ALIVE",
|
| 87 |
-
"173": "
|
| 88 |
"174": "NOT_ALIVE",
|
| 89 |
-
"175": "
|
| 90 |
"176": "NOT_ALIVE",
|
| 91 |
"177": "NOT_ALIVE",
|
| 92 |
"178": "NOT_ALIVE",
|
|
@@ -124,11 +124,11 @@
|
|
| 124 |
"206": "NOT_ALIVE",
|
| 125 |
"207": "NOT_ALIVE",
|
| 126 |
"208": "NOT_ALIVE",
|
| 127 |
-
"209": "
|
| 128 |
"21": "NOT_ALIVE",
|
| 129 |
"210": "NOT_ALIVE",
|
| 130 |
"211": "SUCCESS",
|
| 131 |
-
"212": "
|
| 132 |
"213": "NON_PARTICIPATING",
|
| 133 |
"214": "NOT_ALIVE",
|
| 134 |
"215": "NON_PARTICIPATING",
|
|
@@ -148,25 +148,25 @@
|
|
| 148 |
"228": "NOT_ALIVE",
|
| 149 |
"229": "NOT_ALIVE",
|
| 150 |
"23": "NOT_ALIVE",
|
| 151 |
-
"230": "
|
| 152 |
-
"231": "
|
| 153 |
"232": "NOT_ALIVE",
|
| 154 |
"233": "NON_PARTICIPATING",
|
| 155 |
"234": "NON_PARTICIPATING",
|
| 156 |
-
"235": "
|
| 157 |
"236": "SUCCESS",
|
| 158 |
"237": "SUCCESS",
|
| 159 |
"238": "NOT_ALIVE",
|
| 160 |
"239": "NOT_ALIVE",
|
| 161 |
"24": "NON_PARTICIPATING",
|
| 162 |
"240": "NOT_ALIVE",
|
| 163 |
-
"241": "
|
| 164 |
"242": "NOT_ALIVE",
|
| 165 |
"243": "NOT_ALIVE",
|
| 166 |
"244": "NOT_ALIVE",
|
| 167 |
"245": "NON_PARTICIPATING",
|
| 168 |
"246": "NOT_ALIVE",
|
| 169 |
-
"247": "
|
| 170 |
"248": "NOT_ALIVE",
|
| 171 |
"249": "NOT_ALIVE",
|
| 172 |
"25": "SUCCESS",
|
|
@@ -179,7 +179,7 @@
|
|
| 179 |
"26": "SUCCESS",
|
| 180 |
"27": "NOT_ALIVE",
|
| 181 |
"28": "NOT_ALIVE",
|
| 182 |
-
"29": "
|
| 183 |
"3": "NOT_ALIVE",
|
| 184 |
"30": "NOT_ALIVE",
|
| 185 |
"31": "SUCCESS",
|
|
@@ -230,13 +230,13 @@
|
|
| 230 |
"72": "NOT_ALIVE",
|
| 231 |
"73": "NOT_ALIVE",
|
| 232 |
"74": "NOT_ALIVE",
|
| 233 |
-
"75": "
|
| 234 |
"76": "NOT_ALIVE",
|
| 235 |
"77": "NOT_ALIVE",
|
| 236 |
"78": "NOT_ALIVE",
|
| 237 |
"79": "NOT_ALIVE",
|
| 238 |
"8": "SUCCESS",
|
| 239 |
-
"80": "
|
| 240 |
"81": "NOT_ALIVE",
|
| 241 |
"82": "NOT_ALIVE",
|
| 242 |
"83": "SUCCESS",
|
|
@@ -264,9 +264,6 @@
|
|
| 264 |
"attention_bias": false,
|
| 265 |
"attention_dropout": 0.0,
|
| 266 |
"block_list": [
|
| 267 |
-
6750211,
|
| 268 |
-
6750244,
|
| 269 |
-
6750298,
|
| 270 |
6750334,
|
| 271 |
6750357,
|
| 272 |
6750391,
|
|
@@ -274,7 +271,10 @@
|
|
| 274 |
6750460,
|
| 275 |
6750495,
|
| 276 |
6750529,
|
| 277 |
-
6750561
|
|
|
|
|
|
|
|
|
|
| 278 |
],
|
| 279 |
"bos_token_id": 1,
|
| 280 |
"dtype": "float32",
|
|
@@ -283,9 +283,9 @@
|
|
| 283 |
"hidden_act": "silu",
|
| 284 |
"hidden_size": 2048,
|
| 285 |
"initializer_range": 0.02,
|
| 286 |
-
"inner_step":
|
| 287 |
"intermediate_size": 5632,
|
| 288 |
-
"last_allreduce_block":
|
| 289 |
"max_position_embeddings": 2048,
|
| 290 |
"mlp_bias": false,
|
| 291 |
"model_type": "llama",
|
|
|
|
| 3 |
"all_reduce_scores": {
|
| 4 |
"0": "NOT_ALIVE",
|
| 5 |
"1": "NOT_ALIVE",
|
| 6 |
+
"10": "SUCCESS",
|
| 7 |
"100": "NOT_ALIVE",
|
| 8 |
"101": "SUCCESS",
|
| 9 |
"102": "NOT_ALIVE",
|
|
|
|
| 13 |
"106": "NOT_ALIVE",
|
| 14 |
"107": "NON_PARTICIPATING",
|
| 15 |
"108": "SUCCESS",
|
| 16 |
+
"109": "SUCCESS",
|
| 17 |
"11": "NOT_ALIVE",
|
| 18 |
"110": "SUCCESS",
|
| 19 |
"111": "NON_PARTICIPATING",
|
| 20 |
"112": "SUCCESS",
|
| 21 |
+
"113": "NON_PARTICIPATING",
|
| 22 |
"114": "NOT_ALIVE",
|
| 23 |
+
"115": "NOT_ALIVE",
|
| 24 |
+
"116": "NOT_ALIVE",
|
| 25 |
"117": "NOT_ALIVE",
|
| 26 |
"118": "NOT_ALIVE",
|
| 27 |
"119": "SUCCESS",
|
|
|
|
| 33 |
"124": "NOT_ALIVE",
|
| 34 |
"125": "NOT_ALIVE",
|
| 35 |
"126": "NOT_ALIVE",
|
| 36 |
+
"127": "SUCCESS",
|
| 37 |
"128": "NOT_ALIVE",
|
| 38 |
"129": "NOT_ALIVE",
|
| 39 |
+
"13": "NON_PARTICIPATING",
|
| 40 |
"130": "NON_PARTICIPATING",
|
| 41 |
"131": "NOT_ALIVE",
|
| 42 |
"132": "NOT_ALIVE",
|
| 43 |
"133": "NOT_ALIVE",
|
| 44 |
+
"134": "NOT_ALIVE",
|
| 45 |
+
"135": "NON_PARTICIPATING",
|
| 46 |
"136": "NOT_ALIVE",
|
| 47 |
"137": "NOT_ALIVE",
|
| 48 |
"138": "NOT_ALIVE",
|
| 49 |
"139": "NON_PARTICIPATING",
|
| 50 |
+
"14": "NOT_ALIVE",
|
| 51 |
"140": "SUCCESS",
|
| 52 |
"141": "NOT_ALIVE",
|
| 53 |
"142": "NOT_ALIVE",
|
|
|
|
| 66 |
"154": "NOT_ALIVE",
|
| 67 |
"155": "NOT_ALIVE",
|
| 68 |
"156": "NOT_ALIVE",
|
| 69 |
+
"157": "NON_PARTICIPATING",
|
| 70 |
"158": "NOT_ALIVE",
|
| 71 |
"159": "NOT_ALIVE",
|
| 72 |
"16": "NOT_ALIVE",
|
| 73 |
"160": "SUCCESS",
|
| 74 |
"161": "NOT_ALIVE",
|
| 75 |
+
"162": "NON_PARTICIPATING",
|
| 76 |
"163": "NOT_ALIVE",
|
| 77 |
"164": "NOT_ALIVE",
|
| 78 |
"165": "NOT_ALIVE",
|
|
|
|
| 84 |
"170": "NOT_ALIVE",
|
| 85 |
"171": "NOT_ALIVE",
|
| 86 |
"172": "NOT_ALIVE",
|
| 87 |
+
"173": "NON_PARTICIPATING",
|
| 88 |
"174": "NOT_ALIVE",
|
| 89 |
+
"175": "NON_PARTICIPATING",
|
| 90 |
"176": "NOT_ALIVE",
|
| 91 |
"177": "NOT_ALIVE",
|
| 92 |
"178": "NOT_ALIVE",
|
|
|
|
| 124 |
"206": "NOT_ALIVE",
|
| 125 |
"207": "NOT_ALIVE",
|
| 126 |
"208": "NOT_ALIVE",
|
| 127 |
+
"209": "SUCCESS",
|
| 128 |
"21": "NOT_ALIVE",
|
| 129 |
"210": "NOT_ALIVE",
|
| 130 |
"211": "SUCCESS",
|
| 131 |
+
"212": "NON_PARTICIPATING",
|
| 132 |
"213": "NON_PARTICIPATING",
|
| 133 |
"214": "NOT_ALIVE",
|
| 134 |
"215": "NON_PARTICIPATING",
|
|
|
|
| 148 |
"228": "NOT_ALIVE",
|
| 149 |
"229": "NOT_ALIVE",
|
| 150 |
"23": "NOT_ALIVE",
|
| 151 |
+
"230": "SUCCESS",
|
| 152 |
+
"231": "NON_PARTICIPATING",
|
| 153 |
"232": "NOT_ALIVE",
|
| 154 |
"233": "NON_PARTICIPATING",
|
| 155 |
"234": "NON_PARTICIPATING",
|
| 156 |
+
"235": "NOT_ALIVE",
|
| 157 |
"236": "SUCCESS",
|
| 158 |
"237": "SUCCESS",
|
| 159 |
"238": "NOT_ALIVE",
|
| 160 |
"239": "NOT_ALIVE",
|
| 161 |
"24": "NON_PARTICIPATING",
|
| 162 |
"240": "NOT_ALIVE",
|
| 163 |
+
"241": "NON_PARTICIPATING",
|
| 164 |
"242": "NOT_ALIVE",
|
| 165 |
"243": "NOT_ALIVE",
|
| 166 |
"244": "NOT_ALIVE",
|
| 167 |
"245": "NON_PARTICIPATING",
|
| 168 |
"246": "NOT_ALIVE",
|
| 169 |
+
"247": "NON_PARTICIPATING",
|
| 170 |
"248": "NOT_ALIVE",
|
| 171 |
"249": "NOT_ALIVE",
|
| 172 |
"25": "SUCCESS",
|
|
|
|
| 179 |
"26": "SUCCESS",
|
| 180 |
"27": "NOT_ALIVE",
|
| 181 |
"28": "NOT_ALIVE",
|
| 182 |
+
"29": "NOT_ALIVE",
|
| 183 |
"3": "NOT_ALIVE",
|
| 184 |
"30": "NOT_ALIVE",
|
| 185 |
"31": "SUCCESS",
|
|
|
|
| 230 |
"72": "NOT_ALIVE",
|
| 231 |
"73": "NOT_ALIVE",
|
| 232 |
"74": "NOT_ALIVE",
|
| 233 |
+
"75": "SUCCESS",
|
| 234 |
"76": "NOT_ALIVE",
|
| 235 |
"77": "NOT_ALIVE",
|
| 236 |
"78": "NOT_ALIVE",
|
| 237 |
"79": "NOT_ALIVE",
|
| 238 |
"8": "SUCCESS",
|
| 239 |
+
"80": "NON_PARTICIPATING",
|
| 240 |
"81": "NOT_ALIVE",
|
| 241 |
"82": "NOT_ALIVE",
|
| 242 |
"83": "SUCCESS",
|
|
|
|
| 264 |
"attention_bias": false,
|
| 265 |
"attention_dropout": 0.0,
|
| 266 |
"block_list": [
|
|
|
|
|
|
|
|
|
|
| 267 |
6750334,
|
| 268 |
6750357,
|
| 269 |
6750391,
|
|
|
|
| 271 |
6750460,
|
| 272 |
6750495,
|
| 273 |
6750529,
|
| 274 |
+
6750561,
|
| 275 |
+
6750594,
|
| 276 |
+
6750600,
|
| 277 |
+
6750651
|
| 278 |
],
|
| 279 |
"bos_token_id": 1,
|
| 280 |
"dtype": "float32",
|
|
|
|
| 283 |
"hidden_act": "silu",
|
| 284 |
"hidden_size": 2048,
|
| 285 |
"initializer_range": 0.02,
|
| 286 |
+
"inner_step": 4,
|
| 287 |
"intermediate_size": 5632,
|
| 288 |
+
"last_allreduce_block": 6750582,
|
| 289 |
"max_position_embeddings": 2048,
|
| 290 |
"mlp_bias": false,
|
| 291 |
"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 sha256:8e3db67ec2a87194f3e48c164ac69612ea3d5e476a9ba7b346a4069d0cd2c595
|
| 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:a88877e3962496d58665567fe2bbd8a5d10599d70f5b2a980e52467cab986888
|
| 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 sha256:7c669491c27907d90f4f7ed0bbf7877e5ce10f89faca2b7cd130c8f8056b31d0
|
| 3 |
size 4400216536
|