Run 6. Outer Step 27. Inner Step 4.
Browse files- config.json +77 -77
- inner_optimizer.pt +1 -1
- model.safetensors +1 -1
config.json
CHANGED
@@ -1,23 +1,23 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"all_reduce_scores": {
|
4 |
"0": "NOT_ALIVE",
|
5 |
-
"1": "
|
6 |
"10": "NOT_ALIVE",
|
7 |
"100": "NON_PARTICIPATING",
|
8 |
"101": "NOT_ALIVE",
|
9 |
-
"102": "
|
10 |
"103": "NOT_ALIVE",
|
11 |
"104": "NOT_ALIVE",
|
12 |
"105": "NON_PARTICIPATING",
|
13 |
-
"106": "
|
14 |
"107": "NOT_ALIVE",
|
15 |
"108": "NON_PARTICIPATING",
|
16 |
"109": "NOT_ALIVE",
|
17 |
"11": "NOT_ALIVE",
|
18 |
-
"110": "
|
19 |
-
"111": "
|
20 |
-
"112": "
|
21 |
"113": "NOT_ALIVE",
|
22 |
"114": "NOT_ALIVE",
|
23 |
"115": "NOT_ALIVE",
|
@@ -38,126 +38,126 @@
|
|
38 |
"129": "NOT_ALIVE",
|
39 |
"13": "NOT_ALIVE",
|
40 |
"130": "NOT_ALIVE",
|
41 |
-
"131": "
|
42 |
"132": "NOT_ALIVE",
|
43 |
-
"133": "
|
44 |
-
"134": "
|
45 |
"135": "NON_PARTICIPATING",
|
46 |
"136": "NON_PARTICIPATING",
|
47 |
-
"137": "
|
48 |
-
"138": "
|
49 |
"139": "NON_PARTICIPATING",
|
50 |
"14": "NOT_ALIVE",
|
51 |
"140": "NOT_ALIVE",
|
52 |
"141": "NON_PARTICIPATING",
|
53 |
-
"142": "
|
54 |
"143": "NON_PARTICIPATING",
|
55 |
"144": "SUCCESS",
|
56 |
-
"145": "
|
57 |
-
"146": "
|
58 |
-
"147": "
|
59 |
-
"148": "
|
60 |
"149": "NOT_ALIVE",
|
61 |
"15": "SUCCESS",
|
62 |
"150": "NOT_ALIVE",
|
63 |
"151": "NOT_ALIVE",
|
64 |
"152": "NOT_ALIVE",
|
65 |
"153": "NOT_ALIVE",
|
66 |
-
"154": "
|
67 |
-
"155": "
|
68 |
"156": "NOT_ALIVE",
|
69 |
"157": "NOT_ALIVE",
|
70 |
-
"158": "
|
71 |
-
"159": "
|
72 |
"16": "NOT_ALIVE",
|
73 |
-
"160": "
|
74 |
-
"161": "
|
75 |
-
"162": "
|
76 |
-
"163": "
|
77 |
"164": "NOT_ALIVE",
|
78 |
"165": "NOT_ALIVE",
|
79 |
-
"166": "
|
80 |
"167": "NOT_ALIVE",
|
81 |
"168": "NON_PARTICIPATING",
|
82 |
"169": "NON_PARTICIPATING",
|
83 |
"17": "NOT_ALIVE",
|
84 |
"170": "NON_PARTICIPATING",
|
85 |
-
"171": "
|
86 |
-
"172": "
|
87 |
-
"173": "
|
88 |
"174": "NON_PARTICIPATING",
|
89 |
-
"175": "
|
90 |
"176": "NOT_ALIVE",
|
91 |
"177": "NOT_ALIVE",
|
92 |
"178": "NOT_ALIVE",
|
93 |
"179": "NOT_ALIVE",
|
94 |
-
"18": "
|
95 |
-
"180": "
|
96 |
"181": "NOT_ALIVE",
|
97 |
"182": "NON_PARTICIPATING",
|
98 |
"183": "NOT_ALIVE",
|
99 |
"184": "NOT_ALIVE",
|
100 |
-
"185": "
|
101 |
-
"186": "
|
102 |
"187": "NON_PARTICIPATING",
|
103 |
-
"188": "
|
104 |
"189": "SUCCESS",
|
105 |
"19": "NOT_ALIVE",
|
106 |
-
"190": "
|
107 |
"191": "NON_PARTICIPATING",
|
108 |
-
"192": "
|
109 |
"193": "SUCCESS",
|
110 |
"194": "NOT_ALIVE",
|
111 |
"195": "NOT_ALIVE",
|
112 |
"196": "NOT_ALIVE",
|
113 |
-
"197": "
|
114 |
-
"198": "
|
115 |
"199": "NOT_ALIVE",
|
116 |
"2": "NOT_ALIVE",
|
117 |
"20": "NOT_ALIVE",
|
118 |
"200": "NOT_ALIVE",
|
119 |
"201": "SUCCESS",
|
120 |
"202": "NON_PARTICIPATING",
|
121 |
-
"203": "
|
122 |
"204": "NON_PARTICIPATING",
|
123 |
-
"205": "
|
124 |
"206": "NOT_ALIVE",
|
125 |
"207": "NOT_ALIVE",
|
126 |
"208": "NOT_ALIVE",
|
127 |
"209": "SUCCESS",
|
128 |
-
"21": "
|
129 |
"210": "NOT_ALIVE",
|
130 |
-
"211": "
|
131 |
-
"212": "
|
132 |
-
"213": "
|
133 |
"214": "NON_PARTICIPATING",
|
134 |
"215": "NON_PARTICIPATING",
|
135 |
"216": "SUCCESS",
|
136 |
-
"217": "
|
137 |
"218": "NON_PARTICIPATING",
|
138 |
"219": "SUCCESS",
|
139 |
"22": "NOT_ALIVE",
|
140 |
"220": "NOT_ALIVE",
|
141 |
-
"221": "
|
142 |
-
"222": "
|
143 |
"223": "NOT_ALIVE",
|
144 |
-
"224": "
|
145 |
"225": "NON_PARTICIPATING",
|
146 |
"226": "NON_PARTICIPATING",
|
147 |
-
"227": "
|
148 |
"228": "SUCCESS",
|
149 |
"229": "NOT_ALIVE",
|
150 |
-
"23": "
|
151 |
"230": "SUCCESS",
|
152 |
"231": "NOT_ALIVE",
|
153 |
"232": "NOT_ALIVE",
|
154 |
-
"233": "
|
155 |
"234": "NON_PARTICIPATING",
|
156 |
"235": "NOT_ALIVE",
|
157 |
"236": "NOT_ALIVE",
|
158 |
-
"237": "
|
159 |
"238": "NON_PARTICIPATING",
|
160 |
-
"239": "
|
161 |
"24": "NOT_ALIVE",
|
162 |
"240": "NOT_ALIVE",
|
163 |
"241": "NON_PARTICIPATING",
|
@@ -171,8 +171,8 @@
|
|
171 |
"249": "NOT_ALIVE",
|
172 |
"25": "SUCCESS",
|
173 |
"250": "NOT_ALIVE",
|
174 |
-
"251": "
|
175 |
-
"252": "
|
176 |
"253": "NON_PARTICIPATING",
|
177 |
"254": "NON_PARTICIPATING",
|
178 |
"255": "NON_PARTICIPATING",
|
@@ -183,10 +183,10 @@
|
|
183 |
"3": "SUCCESS",
|
184 |
"30": "NOT_ALIVE",
|
185 |
"31": "SUCCESS",
|
186 |
-
"32": "
|
187 |
"33": "NOT_ALIVE",
|
188 |
-
"34": "
|
189 |
-
"35": "
|
190 |
"36": "SUCCESS",
|
191 |
"37": "NOT_ALIVE",
|
192 |
"38": "NON_PARTICIPATING",
|
@@ -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",
|
@@ -208,9 +208,9 @@
|
|
208 |
"52": "NOT_ALIVE",
|
209 |
"53": "NON_PARTICIPATING",
|
210 |
"54": "NOT_ALIVE",
|
211 |
-
"55": "
|
212 |
"56": "NON_PARTICIPATING",
|
213 |
-
"57": "
|
214 |
"58": "NOT_ALIVE",
|
215 |
"59": "NON_PARTICIPATING",
|
216 |
"6": "NOT_ALIVE",
|
@@ -219,11 +219,11 @@
|
|
219 |
"62": "NOT_ALIVE",
|
220 |
"63": "NON_PARTICIPATING",
|
221 |
"64": "NON_PARTICIPATING",
|
222 |
-
"65": "
|
223 |
"66": "NON_PARTICIPATING",
|
224 |
-
"67": "
|
225 |
"68": "NOT_ALIVE",
|
226 |
-
"69": "
|
227 |
"7": "NOT_ALIVE",
|
228 |
"70": "NON_PARTICIPATING",
|
229 |
"71": "SUCCESS",
|
@@ -233,18 +233,18 @@
|
|
233 |
"75": "NON_PARTICIPATING",
|
234 |
"76": "NOT_ALIVE",
|
235 |
"77": "NON_PARTICIPATING",
|
236 |
-
"78": "
|
237 |
"79": "NOT_ALIVE",
|
238 |
"8": "NOT_ALIVE",
|
239 |
"80": "SUCCESS",
|
240 |
-
"81": "
|
241 |
"82": "NOT_ALIVE",
|
242 |
-
"83": "
|
243 |
"84": "NOT_ALIVE",
|
244 |
-
"85": "
|
245 |
-
"86": "
|
246 |
"87": "NOT_ALIVE",
|
247 |
-
"88": "
|
248 |
"89": "NOT_ALIVE",
|
249 |
"9": "NOT_ALIVE",
|
250 |
"90": "NOT_ALIVE",
|
@@ -252,10 +252,10 @@
|
|
252 |
"92": "NOT_ALIVE",
|
253 |
"93": "NON_PARTICIPATING",
|
254 |
"94": "NON_PARTICIPATING",
|
255 |
-
"95": "
|
256 |
"96": "NON_PARTICIPATING",
|
257 |
-
"97": "
|
258 |
-
"98": "
|
259 |
"99": "SUCCESS"
|
260 |
},
|
261 |
"architectures": [
|
@@ -264,8 +264,8 @@
|
|
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,
|
@@ -274,7 +274,7 @@
|
|
274 |
"initializer_range": 0.02,
|
275 |
"inner_step": 3,
|
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": "NOT_ALIVE",
|
5 |
+
"1": "FAIL",
|
6 |
"10": "NOT_ALIVE",
|
7 |
"100": "NON_PARTICIPATING",
|
8 |
"101": "NOT_ALIVE",
|
9 |
+
"102": "NON_PARTICIPATING",
|
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": "NOT_ALIVE",
|
20 |
+
"112": "NON_PARTICIPATING",
|
21 |
"113": "NOT_ALIVE",
|
22 |
"114": "NOT_ALIVE",
|
23 |
"115": "NOT_ALIVE",
|
|
|
38 |
"129": "NOT_ALIVE",
|
39 |
"13": "NOT_ALIVE",
|
40 |
"130": "NOT_ALIVE",
|
41 |
+
"131": "NOT_ALIVE",
|
42 |
"132": "NOT_ALIVE",
|
43 |
+
"133": "NON_PARTICIPATING",
|
44 |
+
"134": "NOT_ALIVE",
|
45 |
"135": "NON_PARTICIPATING",
|
46 |
"136": "NON_PARTICIPATING",
|
47 |
+
"137": "NON_PARTICIPATING",
|
48 |
+
"138": "NON_PARTICIPATING",
|
49 |
"139": "NON_PARTICIPATING",
|
50 |
"14": "NOT_ALIVE",
|
51 |
"140": "NOT_ALIVE",
|
52 |
"141": "NON_PARTICIPATING",
|
53 |
+
"142": "NOT_ALIVE",
|
54 |
"143": "NON_PARTICIPATING",
|
55 |
"144": "SUCCESS",
|
56 |
+
"145": "SUCCESS",
|
57 |
+
"146": "NON_PARTICIPATING",
|
58 |
+
"147": "NOT_ALIVE",
|
59 |
+
"148": "SUCCESS",
|
60 |
"149": "NOT_ALIVE",
|
61 |
"15": "SUCCESS",
|
62 |
"150": "NOT_ALIVE",
|
63 |
"151": "NOT_ALIVE",
|
64 |
"152": "NOT_ALIVE",
|
65 |
"153": "NOT_ALIVE",
|
66 |
+
"154": "NOT_ALIVE",
|
67 |
+
"155": "NON_PARTICIPATING",
|
68 |
"156": "NOT_ALIVE",
|
69 |
"157": "NOT_ALIVE",
|
70 |
+
"158": "NOT_ALIVE",
|
71 |
+
"159": "NON_PARTICIPATING",
|
72 |
"16": "NOT_ALIVE",
|
73 |
+
"160": "NON_PARTICIPATING",
|
74 |
+
"161": "NON_PARTICIPATING",
|
75 |
+
"162": "NOT_ALIVE",
|
76 |
+
"163": "NON_PARTICIPATING",
|
77 |
"164": "NOT_ALIVE",
|
78 |
"165": "NOT_ALIVE",
|
79 |
+
"166": "SUCCESS",
|
80 |
"167": "NOT_ALIVE",
|
81 |
"168": "NON_PARTICIPATING",
|
82 |
"169": "NON_PARTICIPATING",
|
83 |
"17": "NOT_ALIVE",
|
84 |
"170": "NON_PARTICIPATING",
|
85 |
+
"171": "NON_PARTICIPATING",
|
86 |
+
"172": "NOT_ALIVE",
|
87 |
+
"173": "NON_PARTICIPATING",
|
88 |
"174": "NON_PARTICIPATING",
|
89 |
+
"175": "NON_PARTICIPATING",
|
90 |
"176": "NOT_ALIVE",
|
91 |
"177": "NOT_ALIVE",
|
92 |
"178": "NOT_ALIVE",
|
93 |
"179": "NOT_ALIVE",
|
94 |
+
"18": "NOT_ALIVE",
|
95 |
+
"180": "NON_PARTICIPATING",
|
96 |
"181": "NOT_ALIVE",
|
97 |
"182": "NON_PARTICIPATING",
|
98 |
"183": "NOT_ALIVE",
|
99 |
"184": "NOT_ALIVE",
|
100 |
+
"185": "NOT_ALIVE",
|
101 |
+
"186": "NON_PARTICIPATING",
|
102 |
"187": "NON_PARTICIPATING",
|
103 |
+
"188": "NON_PARTICIPATING",
|
104 |
"189": "SUCCESS",
|
105 |
"19": "NOT_ALIVE",
|
106 |
+
"190": "SUCCESS",
|
107 |
"191": "NON_PARTICIPATING",
|
108 |
+
"192": "SUCCESS",
|
109 |
"193": "SUCCESS",
|
110 |
"194": "NOT_ALIVE",
|
111 |
"195": "NOT_ALIVE",
|
112 |
"196": "NOT_ALIVE",
|
113 |
+
"197": "NOT_ALIVE",
|
114 |
+
"198": "NON_PARTICIPATING",
|
115 |
"199": "NOT_ALIVE",
|
116 |
"2": "NOT_ALIVE",
|
117 |
"20": "NOT_ALIVE",
|
118 |
"200": "NOT_ALIVE",
|
119 |
"201": "SUCCESS",
|
120 |
"202": "NON_PARTICIPATING",
|
121 |
+
"203": "NOT_ALIVE",
|
122 |
"204": "NON_PARTICIPATING",
|
123 |
+
"205": "NOT_ALIVE",
|
124 |
"206": "NOT_ALIVE",
|
125 |
"207": "NOT_ALIVE",
|
126 |
"208": "NOT_ALIVE",
|
127 |
"209": "SUCCESS",
|
128 |
+
"21": "SUCCESS",
|
129 |
"210": "NOT_ALIVE",
|
130 |
+
"211": "NOT_ALIVE",
|
131 |
+
"212": "NOT_ALIVE",
|
132 |
+
"213": "NOT_ALIVE",
|
133 |
"214": "NON_PARTICIPATING",
|
134 |
"215": "NON_PARTICIPATING",
|
135 |
"216": "SUCCESS",
|
136 |
+
"217": "SUCCESS",
|
137 |
"218": "NON_PARTICIPATING",
|
138 |
"219": "SUCCESS",
|
139 |
"22": "NOT_ALIVE",
|
140 |
"220": "NOT_ALIVE",
|
141 |
+
"221": "NOT_ALIVE",
|
142 |
+
"222": "NOT_ALIVE",
|
143 |
"223": "NOT_ALIVE",
|
144 |
+
"224": "NON_PARTICIPATING",
|
145 |
"225": "NON_PARTICIPATING",
|
146 |
"226": "NON_PARTICIPATING",
|
147 |
+
"227": "NON_PARTICIPATING",
|
148 |
"228": "SUCCESS",
|
149 |
"229": "NOT_ALIVE",
|
150 |
+
"23": "NOT_ALIVE",
|
151 |
"230": "SUCCESS",
|
152 |
"231": "NOT_ALIVE",
|
153 |
"232": "NOT_ALIVE",
|
154 |
+
"233": "NON_PARTICIPATING",
|
155 |
"234": "NON_PARTICIPATING",
|
156 |
"235": "NOT_ALIVE",
|
157 |
"236": "NOT_ALIVE",
|
158 |
+
"237": "NON_PARTICIPATING",
|
159 |
"238": "NON_PARTICIPATING",
|
160 |
+
"239": "NOT_ALIVE",
|
161 |
"24": "NOT_ALIVE",
|
162 |
"240": "NOT_ALIVE",
|
163 |
"241": "NON_PARTICIPATING",
|
|
|
171 |
"249": "NOT_ALIVE",
|
172 |
"25": "SUCCESS",
|
173 |
"250": "NOT_ALIVE",
|
174 |
+
"251": "NOT_ALIVE",
|
175 |
+
"252": "NOT_ALIVE",
|
176 |
"253": "NON_PARTICIPATING",
|
177 |
"254": "NON_PARTICIPATING",
|
178 |
"255": "NON_PARTICIPATING",
|
|
|
183 |
"3": "SUCCESS",
|
184 |
"30": "NOT_ALIVE",
|
185 |
"31": "SUCCESS",
|
186 |
+
"32": "SUCCESS",
|
187 |
"33": "NOT_ALIVE",
|
188 |
+
"34": "NON_PARTICIPATING",
|
189 |
+
"35": "NOT_ALIVE",
|
190 |
"36": "SUCCESS",
|
191 |
"37": "NOT_ALIVE",
|
192 |
"38": "NON_PARTICIPATING",
|
|
|
198 |
"43": "NON_PARTICIPATING",
|
199 |
"44": "NON_PARTICIPATING",
|
200 |
"45": "NOT_ALIVE",
|
201 |
+
"46": "NON_PARTICIPATING",
|
202 |
"47": "NOT_ALIVE",
|
203 |
"48": "NON_PARTICIPATING",
|
204 |
"49": "NOT_ALIVE",
|
|
|
208 |
"52": "NOT_ALIVE",
|
209 |
"53": "NON_PARTICIPATING",
|
210 |
"54": "NOT_ALIVE",
|
211 |
+
"55": "NON_PARTICIPATING",
|
212 |
"56": "NON_PARTICIPATING",
|
213 |
+
"57": "NON_PARTICIPATING",
|
214 |
"58": "NOT_ALIVE",
|
215 |
"59": "NON_PARTICIPATING",
|
216 |
"6": "NOT_ALIVE",
|
|
|
219 |
"62": "NOT_ALIVE",
|
220 |
"63": "NON_PARTICIPATING",
|
221 |
"64": "NON_PARTICIPATING",
|
222 |
+
"65": "NON_PARTICIPATING",
|
223 |
"66": "NON_PARTICIPATING",
|
224 |
+
"67": "NOT_ALIVE",
|
225 |
"68": "NOT_ALIVE",
|
226 |
+
"69": "SUCCESS",
|
227 |
"7": "NOT_ALIVE",
|
228 |
"70": "NON_PARTICIPATING",
|
229 |
"71": "SUCCESS",
|
|
|
233 |
"75": "NON_PARTICIPATING",
|
234 |
"76": "NOT_ALIVE",
|
235 |
"77": "NON_PARTICIPATING",
|
236 |
+
"78": "NON_PARTICIPATING",
|
237 |
"79": "NOT_ALIVE",
|
238 |
"8": "NOT_ALIVE",
|
239 |
"80": "SUCCESS",
|
240 |
+
"81": "NOT_ALIVE",
|
241 |
"82": "NOT_ALIVE",
|
242 |
+
"83": "SUCCESS",
|
243 |
"84": "NOT_ALIVE",
|
244 |
+
"85": "NOT_ALIVE",
|
245 |
+
"86": "NON_PARTICIPATING",
|
246 |
"87": "NOT_ALIVE",
|
247 |
+
"88": "NON_PARTICIPATING",
|
248 |
"89": "NOT_ALIVE",
|
249 |
"9": "NOT_ALIVE",
|
250 |
"90": "NOT_ALIVE",
|
|
|
252 |
"92": "NOT_ALIVE",
|
253 |
"93": "NON_PARTICIPATING",
|
254 |
"94": "NON_PARTICIPATING",
|
255 |
+
"95": "NOT_ALIVE",
|
256 |
"96": "NON_PARTICIPATING",
|
257 |
+
"97": "NON_PARTICIPATING",
|
258 |
+
"98": "NOT_ALIVE",
|
259 |
"99": "SUCCESS"
|
260 |
},
|
261 |
"architectures": [
|
|
|
264 |
"attention_bias": false,
|
265 |
"attention_dropout": 0.0,
|
266 |
"block_list": [
|
267 |
+
6145047,
|
268 |
+
6145060
|
269 |
],
|
270 |
"bos_token_id": 1,
|
271 |
"eos_token_id": 2,
|
|
|
274 |
"initializer_range": 0.02,
|
275 |
"inner_step": 3,
|
276 |
"intermediate_size": 5632,
|
277 |
+
"last_allreduce_block": 6144349,
|
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:abd79a455a27e1b2c18b15cadd6441abe52499afd6f16d4af08d2a7ed70f3cdb
|
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 sha256:638b83814b0b9055eaa9d9e4ea1d1674ec0bfe06d962c32d48826535b57d2f1f
|
3 |
size 4400216536
|