Run 5. Outer Step 149. Inner Step 0. Peers 1.
Browse files- config.json +46 -46
- inner_optimizer.pt +1 -1
- model.safetensors +1 -1
- outer_optimizer.pt +1 -1
config.json
CHANGED
@@ -2,26 +2,26 @@
|
|
2 |
"_name_or_path": "distributed/llama-1b",
|
3 |
"all_reduce_scores": {
|
4 |
"0": "NOT_ALIVE",
|
5 |
-
"1": "
|
6 |
"10": "NOT_ALIVE",
|
7 |
"100": "NOT_ALIVE",
|
8 |
"101": "NOT_ALIVE",
|
9 |
-
"102": "
|
10 |
-
"103": "
|
11 |
"104": "NON_PARTICIPATING",
|
12 |
-
"105": "
|
13 |
"106": "NOT_ALIVE",
|
14 |
"107": "NON_PARTICIPATING",
|
15 |
-
"108": "
|
16 |
"109": "NOT_ALIVE",
|
17 |
"11": "NOT_ALIVE",
|
18 |
"110": "NOT_ALIVE",
|
19 |
"111": "NOT_ALIVE",
|
20 |
"112": "NON_PARTICIPATING",
|
21 |
-
"113": "
|
22 |
-
"114": "
|
23 |
-
"115": "
|
24 |
-
"116": "
|
25 |
"117": "NOT_ALIVE",
|
26 |
"118": "NOT_ALIVE",
|
27 |
"119": "NOT_ALIVE",
|
@@ -32,23 +32,23 @@
|
|
32 |
"123": "NON_PARTICIPATING",
|
33 |
"124": "NON_PARTICIPATING",
|
34 |
"125": "NON_PARTICIPATING",
|
35 |
-
"126": "
|
36 |
-
"127": "
|
37 |
"128": "NON_PARTICIPATING",
|
38 |
"129": "NOT_ALIVE",
|
39 |
"13": "NOT_ALIVE",
|
40 |
-
"130": "
|
41 |
"131": "NOT_ALIVE",
|
42 |
-
"132": "
|
43 |
-
"133": "
|
44 |
"134": "NON_PARTICIPATING",
|
45 |
"135": "NON_PARTICIPATING",
|
46 |
"136": "NON_PARTICIPATING",
|
47 |
"137": "NOT_ALIVE",
|
48 |
"138": "NON_PARTICIPATING",
|
49 |
-
"139": "
|
50 |
-
"14": "
|
51 |
-
"140": "
|
52 |
"141": "NON_PARTICIPATING",
|
53 |
"142": "NOT_ALIVE",
|
54 |
"143": "NOT_ALIVE",
|
@@ -64,10 +64,10 @@
|
|
64 |
"152": "NON_PARTICIPATING",
|
65 |
"153": "NOT_ALIVE",
|
66 |
"154": "NOT_ALIVE",
|
67 |
-
"155": "
|
68 |
"156": "NOT_ALIVE",
|
69 |
"157": "NOT_ALIVE",
|
70 |
-
"158": "
|
71 |
"159": "NOT_ALIVE",
|
72 |
"16": "NOT_ALIVE",
|
73 |
"160": "NOT_ALIVE",
|
@@ -83,8 +83,8 @@
|
|
83 |
"17": "NOT_ALIVE",
|
84 |
"170": "NOT_ALIVE",
|
85 |
"171": "NOT_ALIVE",
|
86 |
-
"172": "
|
87 |
-
"173": "
|
88 |
"174": "NOT_ALIVE",
|
89 |
"175": "NOT_ALIVE",
|
90 |
"176": "NOT_ALIVE",
|
@@ -94,7 +94,7 @@
|
|
94 |
"18": "NON_PARTICIPATING",
|
95 |
"180": "NOT_ALIVE",
|
96 |
"181": "NOT_ALIVE",
|
97 |
-
"182": "
|
98 |
"183": "NON_PARTICIPATING",
|
99 |
"184": "NOT_ALIVE",
|
100 |
"185": "NON_PARTICIPATING",
|
@@ -103,14 +103,14 @@
|
|
103 |
"188": "NON_PARTICIPATING",
|
104 |
"189": "NOT_ALIVE",
|
105 |
"19": "NOT_ALIVE",
|
106 |
-
"190": "
|
107 |
"191": "NOT_ALIVE",
|
108 |
"192": "NOT_ALIVE",
|
109 |
"193": "NON_PARTICIPATING",
|
110 |
"194": "NON_PARTICIPATING",
|
111 |
-
"195": "
|
112 |
"196": "NON_PARTICIPATING",
|
113 |
-
"197": "
|
114 |
"198": "NON_PARTICIPATING",
|
115 |
"199": "NON_PARTICIPATING",
|
116 |
"2": "NON_PARTICIPATING",
|
@@ -123,7 +123,7 @@
|
|
123 |
"205": "NOT_ALIVE",
|
124 |
"206": "NOT_ALIVE",
|
125 |
"207": "NOT_ALIVE",
|
126 |
-
"208": "
|
127 |
"209": "NOT_ALIVE",
|
128 |
"21": "NOT_ALIVE",
|
129 |
"210": "NOT_ALIVE",
|
@@ -131,15 +131,15 @@
|
|
131 |
"212": "NON_PARTICIPATING",
|
132 |
"213": "NOT_ALIVE",
|
133 |
"214": "NOT_ALIVE",
|
134 |
-
"215": "
|
135 |
"216": "NON_PARTICIPATING",
|
136 |
"217": "NOT_ALIVE",
|
137 |
"218": "NON_PARTICIPATING",
|
138 |
"219": "NOT_ALIVE",
|
139 |
"22": "NON_PARTICIPATING",
|
140 |
-
"220": "
|
141 |
"221": "NOT_ALIVE",
|
142 |
-
"222": "
|
143 |
"223": "NON_PARTICIPATING",
|
144 |
"224": "NOT_ALIVE",
|
145 |
"225": "NON_PARTICIPATING",
|
@@ -160,8 +160,8 @@
|
|
160 |
"239": "NOT_ALIVE",
|
161 |
"24": "NOT_ALIVE",
|
162 |
"240": "NON_PARTICIPATING",
|
163 |
-
"241": "
|
164 |
-
"242": "
|
165 |
"243": "NON_PARTICIPATING",
|
166 |
"244": "NON_PARTICIPATING",
|
167 |
"245": "NOT_ALIVE",
|
@@ -176,23 +176,23 @@
|
|
176 |
"253": "NON_PARTICIPATING",
|
177 |
"254": "NOT_ALIVE",
|
178 |
"255": "NOT_ALIVE",
|
179 |
-
"26": "
|
180 |
"27": "NOT_ALIVE",
|
181 |
"28": "NOT_ALIVE",
|
182 |
"29": "NOT_ALIVE",
|
183 |
"3": "NOT_ALIVE",
|
184 |
"30": "NON_PARTICIPATING",
|
185 |
"31": "NON_PARTICIPATING",
|
186 |
-
"32": "
|
187 |
"33": "NOT_ALIVE",
|
188 |
"34": "NOT_ALIVE",
|
189 |
-
"35": "
|
190 |
"36": "NOT_ALIVE",
|
191 |
-
"37": "
|
192 |
"38": "NOT_ALIVE",
|
193 |
"39": "NON_PARTICIPATING",
|
194 |
-
"4": "
|
195 |
-
"40": "
|
196 |
"41": "NOT_ALIVE",
|
197 |
"42": "NOT_ALIVE",
|
198 |
"43": "NOT_ALIVE",
|
@@ -205,18 +205,18 @@
|
|
205 |
"5": "NON_PARTICIPATING",
|
206 |
"50": "NON_PARTICIPATING",
|
207 |
"51": "NON_PARTICIPATING",
|
208 |
-
"52": "
|
209 |
-
"53": "
|
210 |
"54": "NOT_ALIVE",
|
211 |
"55": "NOT_ALIVE",
|
212 |
"56": "NOT_ALIVE",
|
213 |
"57": "NOT_ALIVE",
|
214 |
"58": "NON_PARTICIPATING",
|
215 |
"59": "NON_PARTICIPATING",
|
216 |
-
"6": "
|
217 |
"60": "NOT_ALIVE",
|
218 |
-
"61": "
|
219 |
-
"62": "
|
220 |
"63": "NON_PARTICIPATING",
|
221 |
"64": "NOT_ALIVE",
|
222 |
"65": "NON_PARTICIPATING",
|
@@ -227,7 +227,7 @@
|
|
227 |
"7": "NOT_ALIVE",
|
228 |
"70": "NON_PARTICIPATING",
|
229 |
"71": "NON_PARTICIPATING",
|
230 |
-
"72": "
|
231 |
"73": "NOT_ALIVE",
|
232 |
"74": "NOT_ALIVE",
|
233 |
"75": "NON_PARTICIPATING",
|
@@ -248,13 +248,13 @@
|
|
248 |
"89": "NOT_ALIVE",
|
249 |
"9": "NOT_ALIVE",
|
250 |
"90": "NOT_ALIVE",
|
251 |
-
"91": "
|
252 |
"92": "NOT_ALIVE",
|
253 |
"93": "NOT_ALIVE",
|
254 |
"94": "NOT_ALIVE",
|
255 |
"95": "NOT_ALIVE",
|
256 |
"96": "NOT_ALIVE",
|
257 |
-
"97": "
|
258 |
"98": "NOT_ALIVE",
|
259 |
"99": "NOT_ALIVE"
|
260 |
},
|
@@ -271,7 +271,7 @@
|
|
271 |
"initializer_range": 0.02,
|
272 |
"inner_step": 0,
|
273 |
"intermediate_size": 5632,
|
274 |
-
"last_allreduce_block":
|
275 |
"max_position_embeddings": 2048,
|
276 |
"mlp_bias": false,
|
277 |
"model_type": "llama",
|
|
|
2 |
"_name_or_path": "distributed/llama-1b",
|
3 |
"all_reduce_scores": {
|
4 |
"0": "NOT_ALIVE",
|
5 |
+
"1": "NOT_ALIVE",
|
6 |
"10": "NOT_ALIVE",
|
7 |
"100": "NOT_ALIVE",
|
8 |
"101": "NOT_ALIVE",
|
9 |
+
"102": "NOT_ALIVE",
|
10 |
+
"103": "NON_PARTICIPATING",
|
11 |
"104": "NON_PARTICIPATING",
|
12 |
+
"105": "NOT_ALIVE",
|
13 |
"106": "NOT_ALIVE",
|
14 |
"107": "NON_PARTICIPATING",
|
15 |
+
"108": "NOT_ALIVE",
|
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": "NON_PARTICIPATING",
|
23 |
+
"115": "NOT_ALIVE",
|
24 |
+
"116": "NON_PARTICIPATING",
|
25 |
"117": "NOT_ALIVE",
|
26 |
"118": "NOT_ALIVE",
|
27 |
"119": "NOT_ALIVE",
|
|
|
32 |
"123": "NON_PARTICIPATING",
|
33 |
"124": "NON_PARTICIPATING",
|
34 |
"125": "NON_PARTICIPATING",
|
35 |
+
"126": "NON_PARTICIPATING",
|
36 |
+
"127": "NOT_ALIVE",
|
37 |
"128": "NON_PARTICIPATING",
|
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": "NON_PARTICIPATING",
|
45 |
"135": "NON_PARTICIPATING",
|
46 |
"136": "NON_PARTICIPATING",
|
47 |
"137": "NOT_ALIVE",
|
48 |
"138": "NON_PARTICIPATING",
|
49 |
+
"139": "NOT_ALIVE",
|
50 |
+
"14": "NOT_ALIVE",
|
51 |
+
"140": "NOT_ALIVE",
|
52 |
"141": "NON_PARTICIPATING",
|
53 |
"142": "NOT_ALIVE",
|
54 |
"143": "NOT_ALIVE",
|
|
|
64 |
"152": "NON_PARTICIPATING",
|
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": "NOT_ALIVE",
|
72 |
"16": "NOT_ALIVE",
|
73 |
"160": "NOT_ALIVE",
|
|
|
83 |
"17": "NOT_ALIVE",
|
84 |
"170": "NOT_ALIVE",
|
85 |
"171": "NOT_ALIVE",
|
86 |
+
"172": "NOT_ALIVE",
|
87 |
+
"173": "NOT_ALIVE",
|
88 |
"174": "NOT_ALIVE",
|
89 |
"175": "NOT_ALIVE",
|
90 |
"176": "NOT_ALIVE",
|
|
|
94 |
"18": "NON_PARTICIPATING",
|
95 |
"180": "NOT_ALIVE",
|
96 |
"181": "NOT_ALIVE",
|
97 |
+
"182": "NOT_ALIVE",
|
98 |
"183": "NON_PARTICIPATING",
|
99 |
"184": "NOT_ALIVE",
|
100 |
"185": "NON_PARTICIPATING",
|
|
|
103 |
"188": "NON_PARTICIPATING",
|
104 |
"189": "NOT_ALIVE",
|
105 |
"19": "NOT_ALIVE",
|
106 |
+
"190": "NON_PARTICIPATING",
|
107 |
"191": "NOT_ALIVE",
|
108 |
"192": "NOT_ALIVE",
|
109 |
"193": "NON_PARTICIPATING",
|
110 |
"194": "NON_PARTICIPATING",
|
111 |
+
"195": "NOT_ALIVE",
|
112 |
"196": "NON_PARTICIPATING",
|
113 |
+
"197": "NOT_ALIVE",
|
114 |
"198": "NON_PARTICIPATING",
|
115 |
"199": "NON_PARTICIPATING",
|
116 |
"2": "NON_PARTICIPATING",
|
|
|
123 |
"205": "NOT_ALIVE",
|
124 |
"206": "NOT_ALIVE",
|
125 |
"207": "NOT_ALIVE",
|
126 |
+
"208": "NOT_ALIVE",
|
127 |
"209": "NOT_ALIVE",
|
128 |
"21": "NOT_ALIVE",
|
129 |
"210": "NOT_ALIVE",
|
|
|
131 |
"212": "NON_PARTICIPATING",
|
132 |
"213": "NOT_ALIVE",
|
133 |
"214": "NOT_ALIVE",
|
134 |
+
"215": "NON_PARTICIPATING",
|
135 |
"216": "NON_PARTICIPATING",
|
136 |
"217": "NOT_ALIVE",
|
137 |
"218": "NON_PARTICIPATING",
|
138 |
"219": "NOT_ALIVE",
|
139 |
"22": "NON_PARTICIPATING",
|
140 |
+
"220": "NOT_ALIVE",
|
141 |
"221": "NOT_ALIVE",
|
142 |
+
"222": "NON_PARTICIPATING",
|
143 |
"223": "NON_PARTICIPATING",
|
144 |
"224": "NOT_ALIVE",
|
145 |
"225": "NON_PARTICIPATING",
|
|
|
160 |
"239": "NOT_ALIVE",
|
161 |
"24": "NOT_ALIVE",
|
162 |
"240": "NON_PARTICIPATING",
|
163 |
+
"241": "NOT_ALIVE",
|
164 |
+
"242": "NOT_ALIVE",
|
165 |
"243": "NON_PARTICIPATING",
|
166 |
"244": "NON_PARTICIPATING",
|
167 |
"245": "NOT_ALIVE",
|
|
|
176 |
"253": "NON_PARTICIPATING",
|
177 |
"254": "NOT_ALIVE",
|
178 |
"255": "NOT_ALIVE",
|
179 |
+
"26": "NOT_ALIVE",
|
180 |
"27": "NOT_ALIVE",
|
181 |
"28": "NOT_ALIVE",
|
182 |
"29": "NOT_ALIVE",
|
183 |
"3": "NOT_ALIVE",
|
184 |
"30": "NON_PARTICIPATING",
|
185 |
"31": "NON_PARTICIPATING",
|
186 |
+
"32": "NON_PARTICIPATING",
|
187 |
"33": "NOT_ALIVE",
|
188 |
"34": "NOT_ALIVE",
|
189 |
+
"35": "NOT_ALIVE",
|
190 |
"36": "NOT_ALIVE",
|
191 |
+
"37": "NOT_ALIVE",
|
192 |
"38": "NOT_ALIVE",
|
193 |
"39": "NON_PARTICIPATING",
|
194 |
+
"4": "NOT_ALIVE",
|
195 |
+
"40": "NOT_ALIVE",
|
196 |
"41": "NOT_ALIVE",
|
197 |
"42": "NOT_ALIVE",
|
198 |
"43": "NOT_ALIVE",
|
|
|
205 |
"5": "NON_PARTICIPATING",
|
206 |
"50": "NON_PARTICIPATING",
|
207 |
"51": "NON_PARTICIPATING",
|
208 |
+
"52": "NON_PARTICIPATING",
|
209 |
+
"53": "NOT_ALIVE",
|
210 |
"54": "NOT_ALIVE",
|
211 |
"55": "NOT_ALIVE",
|
212 |
"56": "NOT_ALIVE",
|
213 |
"57": "NOT_ALIVE",
|
214 |
"58": "NON_PARTICIPATING",
|
215 |
"59": "NON_PARTICIPATING",
|
216 |
+
"6": "NOT_ALIVE",
|
217 |
"60": "NOT_ALIVE",
|
218 |
+
"61": "NOT_ALIVE",
|
219 |
+
"62": "NOT_ALIVE",
|
220 |
"63": "NON_PARTICIPATING",
|
221 |
"64": "NOT_ALIVE",
|
222 |
"65": "NON_PARTICIPATING",
|
|
|
227 |
"7": "NOT_ALIVE",
|
228 |
"70": "NON_PARTICIPATING",
|
229 |
"71": "NON_PARTICIPATING",
|
230 |
+
"72": "NOT_ALIVE",
|
231 |
"73": "NOT_ALIVE",
|
232 |
"74": "NOT_ALIVE",
|
233 |
"75": "NON_PARTICIPATING",
|
|
|
248 |
"89": "NOT_ALIVE",
|
249 |
"9": "NOT_ALIVE",
|
250 |
"90": "NOT_ALIVE",
|
251 |
+
"91": "NON_PARTICIPATING",
|
252 |
"92": "NOT_ALIVE",
|
253 |
"93": "NOT_ALIVE",
|
254 |
"94": "NOT_ALIVE",
|
255 |
"95": "NOT_ALIVE",
|
256 |
"96": "NOT_ALIVE",
|
257 |
+
"97": "NON_PARTICIPATING",
|
258 |
"98": "NOT_ALIVE",
|
259 |
"99": "NOT_ALIVE"
|
260 |
},
|
|
|
271 |
"initializer_range": 0.02,
|
272 |
"inner_step": 0,
|
273 |
"intermediate_size": 5632,
|
274 |
+
"last_allreduce_block": 6059469,
|
275 |
"max_position_embeddings": 2048,
|
276 |
"mlp_bias": false,
|
277 |
"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 sha256:8e874fc0fd66f2ada48c03624740df94db0f83e00b16569d4c9b4bd03ea354b1
|
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 sha256:2b906ac7dd1c48143caec8a1b5e4d057b561f68eb6433fb9c7c4e66e16763419
|
3 |
size 4400216536
|
outer_optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4400252568
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fafd7ad8e66630a098d752f47a55cbd7c3353497ba358183d703f3331e1898a9
|
3 |
size 4400252568
|