Run 5. Outer Step 38. Inner Step 1.
Browse files- config.json +24 -24
- inner_optimizer.pt +1 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -2,15 +2,15 @@
|
|
| 2 |
"_name_or_path": "distributed/llama-1b",
|
| 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",
|
|
@@ -25,7 +25,7 @@
|
|
| 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",
|
|
@@ -36,12 +36,12 @@
|
|
| 36 |
"127": "NON_PARTICIPATING",
|
| 37 |
"128": "NON_PARTICIPATING",
|
| 38 |
"129": "NON_PARTICIPATING",
|
| 39 |
-
"13": "
|
| 40 |
"130": "NON_PARTICIPATING",
|
| 41 |
"131": "NON_PARTICIPATING",
|
| 42 |
"132": "NON_PARTICIPATING",
|
| 43 |
"133": "NON_PARTICIPATING",
|
| 44 |
-
"134": "
|
| 45 |
"135": "NON_PARTICIPATING",
|
| 46 |
"136": "NON_PARTICIPATING",
|
| 47 |
"137": "NON_PARTICIPATING",
|
|
@@ -77,7 +77,7 @@
|
|
| 77 |
"164": "NON_PARTICIPATING",
|
| 78 |
"165": "NON_PARTICIPATING",
|
| 79 |
"166": "NON_PARTICIPATING",
|
| 80 |
-
"167": "
|
| 81 |
"168": "NON_PARTICIPATING",
|
| 82 |
"169": "NON_PARTICIPATING",
|
| 83 |
"17": "SUCCESS",
|
|
@@ -88,7 +88,7 @@
|
|
| 88 |
"174": "NON_PARTICIPATING",
|
| 89 |
"175": "NON_PARTICIPATING",
|
| 90 |
"176": "NON_PARTICIPATING",
|
| 91 |
-
"177": "
|
| 92 |
"178": "NON_PARTICIPATING",
|
| 93 |
"179": "NON_PARTICIPATING",
|
| 94 |
"18": "SUCCESS",
|
|
@@ -98,19 +98,19 @@
|
|
| 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",
|
| 105 |
"19": "SUCCESS",
|
| 106 |
"190": "NON_PARTICIPATING",
|
| 107 |
-
"191": "
|
| 108 |
"192": "NON_PARTICIPATING",
|
| 109 |
"193": "NON_PARTICIPATING",
|
| 110 |
"194": "NON_PARTICIPATING",
|
| 111 |
"195": "NON_PARTICIPATING",
|
| 112 |
"196": "NON_PARTICIPATING",
|
| 113 |
-
"197": "
|
| 114 |
"198": "NON_PARTICIPATING",
|
| 115 |
"199": "NON_PARTICIPATING",
|
| 116 |
"2": "SUCCESS",
|
|
@@ -120,7 +120,7 @@
|
|
| 120 |
"202": "NON_PARTICIPATING",
|
| 121 |
"203": "NON_PARTICIPATING",
|
| 122 |
"204": "NON_PARTICIPATING",
|
| 123 |
-
"205": "
|
| 124 |
"206": "NON_PARTICIPATING",
|
| 125 |
"207": "NON_PARTICIPATING",
|
| 126 |
"208": "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",
|
|
@@ -170,7 +170,7 @@
|
|
| 170 |
"248": "NON_PARTICIPATING",
|
| 171 |
"249": "NON_PARTICIPATING",
|
| 172 |
"25": "SUCCESS",
|
| 173 |
-
"250": "
|
| 174 |
"251": "NON_PARTICIPATING",
|
| 175 |
"252": "NON_PARTICIPATING",
|
| 176 |
"253": "NON_PARTICIPATING",
|
|
@@ -192,7 +192,7 @@
|
|
| 192 |
"38": "SUCCESS",
|
| 193 |
"39": "SUCCESS",
|
| 194 |
"4": "SUCCESS",
|
| 195 |
-
"40": "
|
| 196 |
"41": "SUCCESS",
|
| 197 |
"42": "SUCCESS",
|
| 198 |
"43": "SUCCESS",
|
|
@@ -219,15 +219,15 @@
|
|
| 219 |
"62": "SUCCESS",
|
| 220 |
"63": "SUCCESS",
|
| 221 |
"64": "SUCCESS",
|
| 222 |
-
"65": "
|
| 223 |
-
"66": "
|
| 224 |
-
"67": "
|
| 225 |
"68": "SUCCESS",
|
| 226 |
"69": "SUCCESS",
|
| 227 |
"7": "SUCCESS",
|
| 228 |
"70": "SUCCESS",
|
| 229 |
-
"71": "
|
| 230 |
-
"72": "
|
| 231 |
"73": "SUCCESS",
|
| 232 |
"74": "SUCCESS",
|
| 233 |
"75": "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",
|
|
|
|
| 2 |
"_name_or_path": "distributed/llama-1b",
|
| 3 |
"all_reduce_scores": {
|
| 4 |
"0": "NON_PARTICIPATING",
|
| 5 |
+
"1": "FAIL",
|
| 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": "NON_PARTICIPATING",
|
| 13 |
+
"106": "NON_PARTICIPATING",
|
| 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": "SUCCESS",
|
| 29 |
"120": "NON_PARTICIPATING",
|
| 30 |
"121": "NON_PARTICIPATING",
|
| 31 |
"122": "NON_PARTICIPATING",
|
|
|
|
| 36 |
"127": "NON_PARTICIPATING",
|
| 37 |
"128": "NON_PARTICIPATING",
|
| 38 |
"129": "NON_PARTICIPATING",
|
| 39 |
+
"13": "FAIL",
|
| 40 |
"130": "NON_PARTICIPATING",
|
| 41 |
"131": "NON_PARTICIPATING",
|
| 42 |
"132": "NON_PARTICIPATING",
|
| 43 |
"133": "NON_PARTICIPATING",
|
| 44 |
+
"134": "SUCCESS",
|
| 45 |
"135": "NON_PARTICIPATING",
|
| 46 |
"136": "NON_PARTICIPATING",
|
| 47 |
"137": "NON_PARTICIPATING",
|
|
|
|
| 77 |
"164": "NON_PARTICIPATING",
|
| 78 |
"165": "NON_PARTICIPATING",
|
| 79 |
"166": "NON_PARTICIPATING",
|
| 80 |
+
"167": "NON_PARTICIPATING",
|
| 81 |
"168": "NON_PARTICIPATING",
|
| 82 |
"169": "NON_PARTICIPATING",
|
| 83 |
"17": "SUCCESS",
|
|
|
|
| 88 |
"174": "NON_PARTICIPATING",
|
| 89 |
"175": "NON_PARTICIPATING",
|
| 90 |
"176": "NON_PARTICIPATING",
|
| 91 |
+
"177": "SUCCESS",
|
| 92 |
"178": "NON_PARTICIPATING",
|
| 93 |
"179": "NON_PARTICIPATING",
|
| 94 |
"18": "SUCCESS",
|
|
|
|
| 98 |
"183": "NON_PARTICIPATING",
|
| 99 |
"184": "NON_PARTICIPATING",
|
| 100 |
"185": "NON_PARTICIPATING",
|
| 101 |
+
"186": "NON_PARTICIPATING",
|
| 102 |
"187": "NON_PARTICIPATING",
|
| 103 |
"188": "NON_PARTICIPATING",
|
| 104 |
"189": "NON_PARTICIPATING",
|
| 105 |
"19": "SUCCESS",
|
| 106 |
"190": "NON_PARTICIPATING",
|
| 107 |
+
"191": "SUCCESS",
|
| 108 |
"192": "NON_PARTICIPATING",
|
| 109 |
"193": "NON_PARTICIPATING",
|
| 110 |
"194": "NON_PARTICIPATING",
|
| 111 |
"195": "NON_PARTICIPATING",
|
| 112 |
"196": "NON_PARTICIPATING",
|
| 113 |
+
"197": "SUCCESS",
|
| 114 |
"198": "NON_PARTICIPATING",
|
| 115 |
"199": "NON_PARTICIPATING",
|
| 116 |
"2": "SUCCESS",
|
|
|
|
| 120 |
"202": "NON_PARTICIPATING",
|
| 121 |
"203": "NON_PARTICIPATING",
|
| 122 |
"204": "NON_PARTICIPATING",
|
| 123 |
+
"205": "SUCCESS",
|
| 124 |
"206": "NON_PARTICIPATING",
|
| 125 |
"207": "NON_PARTICIPATING",
|
| 126 |
"208": "NON_PARTICIPATING",
|
|
|
|
| 128 |
"21": "SUCCESS",
|
| 129 |
"210": "NON_PARTICIPATING",
|
| 130 |
"211": "NON_PARTICIPATING",
|
| 131 |
+
"212": "NON_PARTICIPATING",
|
| 132 |
"213": "NON_PARTICIPATING",
|
| 133 |
"214": "NON_PARTICIPATING",
|
| 134 |
"215": "NON_PARTICIPATING",
|
|
|
|
| 170 |
"248": "NON_PARTICIPATING",
|
| 171 |
"249": "NON_PARTICIPATING",
|
| 172 |
"25": "SUCCESS",
|
| 173 |
+
"250": "SUCCESS",
|
| 174 |
"251": "NON_PARTICIPATING",
|
| 175 |
"252": "NON_PARTICIPATING",
|
| 176 |
"253": "NON_PARTICIPATING",
|
|
|
|
| 192 |
"38": "SUCCESS",
|
| 193 |
"39": "SUCCESS",
|
| 194 |
"4": "SUCCESS",
|
| 195 |
+
"40": "FAIL",
|
| 196 |
"41": "SUCCESS",
|
| 197 |
"42": "SUCCESS",
|
| 198 |
"43": "SUCCESS",
|
|
|
|
| 219 |
"62": "SUCCESS",
|
| 220 |
"63": "SUCCESS",
|
| 221 |
"64": "SUCCESS",
|
| 222 |
+
"65": "NON_PARTICIPATING",
|
| 223 |
+
"66": "FAIL",
|
| 224 |
+
"67": "FAIL",
|
| 225 |
"68": "SUCCESS",
|
| 226 |
"69": "SUCCESS",
|
| 227 |
"7": "SUCCESS",
|
| 228 |
"70": "SUCCESS",
|
| 229 |
+
"71": "NON_PARTICIPATING",
|
| 230 |
+
"72": "FAIL",
|
| 231 |
"73": "SUCCESS",
|
| 232 |
"74": "SUCCESS",
|
| 233 |
"75": "SUCCESS",
|
|
|
|
| 264 |
"attention_bias": false,
|
| 265 |
"attention_dropout": 0.0,
|
| 266 |
"block_list": [
|
| 267 |
+
5751484,
|
| 268 |
+
5751499
|
| 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": 1,
|
| 276 |
"intermediate_size": 5632,
|
| 277 |
+
"last_allreduce_block": 5751391,
|
| 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 sha256:8fe094f4f8cddd3d5dee7bf11b8d0c88b53e0cd077d5983f63867ce6bfb116e0
|
| 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 sha256:295751dd0869b10fbd75af2b02722a4bce95ab37566d0347bccc62e91aa9a9e3
|
| 3 |
size 4400216536
|