Run 4. Outer Step 75. Inner Step 0. Peers 21.
Browse files- config.json +111 -111
- inner_optimizer.pt +1 -1
- model.safetensors +1 -1
- outer_optimizer.pt +1 -1
config.json
CHANGED
@@ -3,21 +3,21 @@
|
|
3 |
"activation_function": "gelu_new",
|
4 |
"all_reduce_scores": {
|
5 |
"0": "NON_PARTICIPATING",
|
6 |
-
"1": "
|
7 |
"10": "NON_PARTICIPATING",
|
8 |
"100": "NON_PARTICIPATING",
|
9 |
"101": "NON_PARTICIPATING",
|
10 |
-
"102": "
|
11 |
"103": "NON_PARTICIPATING",
|
12 |
-
"104": "
|
13 |
-
"105": "
|
14 |
"106": "NON_PARTICIPATING",
|
15 |
-
"107": "
|
16 |
"108": "NON_PARTICIPATING",
|
17 |
"109": "NON_PARTICIPATING",
|
18 |
-
"11": "
|
19 |
"110": "NON_PARTICIPATING",
|
20 |
-
"111": "
|
21 |
"112": "NON_PARTICIPATING",
|
22 |
"113": "NON_PARTICIPATING",
|
23 |
"114": "NON_PARTICIPATING",
|
@@ -26,18 +26,18 @@
|
|
26 |
"117": "NON_PARTICIPATING",
|
27 |
"118": "NON_PARTICIPATING",
|
28 |
"119": "NON_PARTICIPATING",
|
29 |
-
"12": "
|
30 |
-
"120": "
|
31 |
-
"121": "
|
32 |
"122": "NON_PARTICIPATING",
|
33 |
"123": "NON_PARTICIPATING",
|
34 |
"124": "NON_PARTICIPATING",
|
35 |
-
"125": "
|
36 |
-
"126": "
|
37 |
"127": "NON_PARTICIPATING",
|
38 |
-
"128": "
|
39 |
-
"129": "
|
40 |
-
"13": "
|
41 |
"130": "NON_PARTICIPATING",
|
42 |
"131": "NON_PARTICIPATING",
|
43 |
"132": "NON_PARTICIPATING",
|
@@ -48,21 +48,21 @@
|
|
48 |
"137": "NON_PARTICIPATING",
|
49 |
"138": "NON_PARTICIPATING",
|
50 |
"139": "NON_PARTICIPATING",
|
51 |
-
"14": "
|
52 |
-
"140": "
|
53 |
-
"141": "
|
54 |
"142": "NON_PARTICIPATING",
|
55 |
-
"143": "
|
56 |
"144": "NON_PARTICIPATING",
|
57 |
"145": "NON_PARTICIPATING",
|
58 |
"146": "NON_PARTICIPATING",
|
59 |
"147": "NON_PARTICIPATING",
|
60 |
"148": "NON_PARTICIPATING",
|
61 |
"149": "NON_PARTICIPATING",
|
62 |
-
"15": "
|
63 |
"150": "NON_PARTICIPATING",
|
64 |
"151": "NON_PARTICIPATING",
|
65 |
-
"152": "
|
66 |
"153": "NON_PARTICIPATING",
|
67 |
"154": "NON_PARTICIPATING",
|
68 |
"155": "NON_PARTICIPATING",
|
@@ -70,7 +70,7 @@
|
|
70 |
"157": "NON_PARTICIPATING",
|
71 |
"158": "NON_PARTICIPATING",
|
72 |
"159": "NON_PARTICIPATING",
|
73 |
-
"16": "
|
74 |
"160": "NON_PARTICIPATING",
|
75 |
"161": "NON_PARTICIPATING",
|
76 |
"162": "NON_PARTICIPATING",
|
@@ -78,12 +78,12 @@
|
|
78 |
"164": "NON_PARTICIPATING",
|
79 |
"165": "NON_PARTICIPATING",
|
80 |
"166": "NON_PARTICIPATING",
|
81 |
-
"167": "
|
82 |
"168": "NON_PARTICIPATING",
|
83 |
-
"169": "
|
84 |
-
"17": "
|
85 |
"170": "NON_PARTICIPATING",
|
86 |
-
"171": "
|
87 |
"172": "NON_PARTICIPATING",
|
88 |
"173": "NON_PARTICIPATING",
|
89 |
"174": "NON_PARTICIPATING",
|
@@ -92,41 +92,41 @@
|
|
92 |
"177": "NON_PARTICIPATING",
|
93 |
"178": "NON_PARTICIPATING",
|
94 |
"179": "NON_PARTICIPATING",
|
95 |
-
"18": "
|
96 |
"180": "NON_PARTICIPATING",
|
97 |
"181": "NON_PARTICIPATING",
|
98 |
"182": "NON_PARTICIPATING",
|
99 |
-
"183": "
|
100 |
"184": "NON_PARTICIPATING",
|
101 |
"185": "NON_PARTICIPATING",
|
102 |
"186": "NON_PARTICIPATING",
|
103 |
"187": "NON_PARTICIPATING",
|
104 |
"188": "NON_PARTICIPATING",
|
105 |
"189": "NON_PARTICIPATING",
|
106 |
-
"19": "
|
107 |
"190": "NON_PARTICIPATING",
|
108 |
"191": "NON_PARTICIPATING",
|
109 |
"192": "NON_PARTICIPATING",
|
110 |
-
"193": "
|
111 |
"194": "NON_PARTICIPATING",
|
112 |
"195": "NON_PARTICIPATING",
|
113 |
-
"196": "
|
114 |
"197": "NON_PARTICIPATING",
|
115 |
"198": "NON_PARTICIPATING",
|
116 |
"199": "NON_PARTICIPATING",
|
117 |
-
"2": "
|
118 |
"20": "SUCCESS",
|
119 |
"200": "NON_PARTICIPATING",
|
120 |
"201": "NON_PARTICIPATING",
|
121 |
"202": "NON_PARTICIPATING",
|
122 |
"203": "NON_PARTICIPATING",
|
123 |
"204": "NON_PARTICIPATING",
|
124 |
-
"205": "
|
125 |
"206": "NON_PARTICIPATING",
|
126 |
"207": "NON_PARTICIPATING",
|
127 |
"208": "NON_PARTICIPATING",
|
128 |
"209": "NON_PARTICIPATING",
|
129 |
-
"21": "
|
130 |
"210": "NON_PARTICIPATING",
|
131 |
"211": "NON_PARTICIPATING",
|
132 |
"212": "NON_PARTICIPATING",
|
@@ -134,10 +134,10 @@
|
|
134 |
"214": "NON_PARTICIPATING",
|
135 |
"215": "NON_PARTICIPATING",
|
136 |
"216": "NON_PARTICIPATING",
|
137 |
-
"217": "
|
138 |
"218": "NON_PARTICIPATING",
|
139 |
"219": "NON_PARTICIPATING",
|
140 |
-
"22": "
|
141 |
"220": "NON_PARTICIPATING",
|
142 |
"221": "NON_PARTICIPATING",
|
143 |
"222": "NON_PARTICIPATING",
|
@@ -145,21 +145,21 @@
|
|
145 |
"224": "NON_PARTICIPATING",
|
146 |
"225": "NON_PARTICIPATING",
|
147 |
"226": "NON_PARTICIPATING",
|
148 |
-
"227": "
|
149 |
"228": "NON_PARTICIPATING",
|
150 |
"229": "NON_PARTICIPATING",
|
151 |
-
"23": "
|
152 |
"230": "NON_PARTICIPATING",
|
153 |
"231": "NON_PARTICIPATING",
|
154 |
"232": "NON_PARTICIPATING",
|
155 |
"233": "NON_PARTICIPATING",
|
156 |
"234": "NON_PARTICIPATING",
|
157 |
"235": "NON_PARTICIPATING",
|
158 |
-
"236": "
|
159 |
"237": "NON_PARTICIPATING",
|
160 |
"238": "NON_PARTICIPATING",
|
161 |
-
"239": "
|
162 |
-
"24": "
|
163 |
"240": "NON_PARTICIPATING",
|
164 |
"241": "NON_PARTICIPATING",
|
165 |
"242": "NON_PARTICIPATING",
|
@@ -168,96 +168,96 @@
|
|
168 |
"245": "NON_PARTICIPATING",
|
169 |
"246": "NON_PARTICIPATING",
|
170 |
"247": "NON_PARTICIPATING",
|
171 |
-
"248": "
|
172 |
"249": "NON_PARTICIPATING",
|
173 |
"25": "SUCCESS",
|
174 |
-
"250": "
|
175 |
"251": "NON_PARTICIPATING",
|
176 |
"252": "NON_PARTICIPATING",
|
177 |
"253": "NON_PARTICIPATING",
|
178 |
"254": "NON_PARTICIPATING",
|
179 |
-
"255": "
|
180 |
"26": "NON_PARTICIPATING",
|
181 |
-
"27": "
|
182 |
-
"28": "
|
183 |
-
"29": "
|
184 |
-
"3": "
|
185 |
"30": "NON_PARTICIPATING",
|
186 |
-
"31": "
|
187 |
-
"32": "
|
188 |
"33": "NON_PARTICIPATING",
|
189 |
-
"34": "
|
190 |
-
"35": "
|
191 |
-
"36": "
|
192 |
-
"37": "
|
193 |
-
"38": "
|
194 |
-
"39": "
|
195 |
-
"4": "
|
196 |
-
"40": "
|
197 |
-
"41": "
|
198 |
-
"42": "
|
199 |
-
"43": "
|
200 |
-
"44": "
|
201 |
-
"45": "
|
202 |
"46": "NON_PARTICIPATING",
|
203 |
-
"47": "
|
204 |
"48": "NON_PARTICIPATING",
|
205 |
-
"49": "
|
206 |
-
"5": "
|
207 |
-
"50": "
|
208 |
-
"51": "
|
209 |
-
"52": "
|
210 |
-
"53": "
|
211 |
-
"54": "
|
212 |
-
"55": "
|
213 |
-
"56": "
|
214 |
"57": "NON_PARTICIPATING",
|
215 |
"58": "NON_PARTICIPATING",
|
216 |
"59": "NON_PARTICIPATING",
|
217 |
-
"6": "
|
218 |
-
"60": "
|
219 |
-
"61": "
|
220 |
"62": "NON_PARTICIPATING",
|
221 |
-
"63": "
|
222 |
-
"64": "
|
223 |
-
"65": "
|
224 |
-
"66": "
|
225 |
-
"67": "
|
226 |
-
"68": "
|
227 |
-
"69": "
|
228 |
-
"7": "
|
229 |
-
"70": "
|
230 |
-
"71": "
|
231 |
-
"72": "
|
232 |
-
"73": "
|
233 |
-
"74": "
|
234 |
-
"75": "
|
235 |
-
"76": "
|
236 |
"77": "SUCCESS",
|
237 |
-
"78": "
|
238 |
"79": "NON_PARTICIPATING",
|
239 |
"8": "NON_PARTICIPATING",
|
240 |
-
"80": "
|
241 |
-
"81": "
|
242 |
-
"82": "
|
243 |
-
"83": "
|
244 |
-
"84": "
|
245 |
"85": "NON_PARTICIPATING",
|
246 |
"86": "NON_PARTICIPATING",
|
247 |
-
"87": "
|
248 |
-
"88": "
|
249 |
-
"89": "
|
250 |
-
"9": "
|
251 |
-
"90": "
|
252 |
-
"91": "
|
253 |
-
"92": "
|
254 |
"93": "NON_PARTICIPATING",
|
255 |
-
"94": "
|
256 |
-
"95": "
|
257 |
-
"96": "
|
258 |
-
"97": "
|
259 |
-
"98": "
|
260 |
-
"99": "
|
261 |
},
|
262 |
"architectures": [
|
263 |
"GPTOptim"
|
@@ -275,7 +275,7 @@
|
|
275 |
"initializer_range": 0.02,
|
276 |
"inner_step": 0,
|
277 |
"inner_steps": 0,
|
278 |
-
"last_allreduce_block":
|
279 |
"layer_norm_epsilon": 1e-05,
|
280 |
"model_type": "gpt_optimized",
|
281 |
"n_embd": 1280,
|
|
|
3 |
"activation_function": "gelu_new",
|
4 |
"all_reduce_scores": {
|
5 |
"0": "NON_PARTICIPATING",
|
6 |
+
"1": "NON_PARTICIPATING",
|
7 |
"10": "NON_PARTICIPATING",
|
8 |
"100": "NON_PARTICIPATING",
|
9 |
"101": "NON_PARTICIPATING",
|
10 |
+
"102": "SUCCESS",
|
11 |
"103": "NON_PARTICIPATING",
|
12 |
+
"104": "SUCCESS",
|
13 |
+
"105": "SUCCESS",
|
14 |
"106": "NON_PARTICIPATING",
|
15 |
+
"107": "NON_PARTICIPATING",
|
16 |
"108": "NON_PARTICIPATING",
|
17 |
"109": "NON_PARTICIPATING",
|
18 |
+
"11": "NON_PARTICIPATING",
|
19 |
"110": "NON_PARTICIPATING",
|
20 |
+
"111": "NON_PARTICIPATING",
|
21 |
"112": "NON_PARTICIPATING",
|
22 |
"113": "NON_PARTICIPATING",
|
23 |
"114": "NON_PARTICIPATING",
|
|
|
26 |
"117": "NON_PARTICIPATING",
|
27 |
"118": "NON_PARTICIPATING",
|
28 |
"119": "NON_PARTICIPATING",
|
29 |
+
"12": "NON_PARTICIPATING",
|
30 |
+
"120": "SUCCESS",
|
31 |
+
"121": "SUCCESS",
|
32 |
"122": "NON_PARTICIPATING",
|
33 |
"123": "NON_PARTICIPATING",
|
34 |
"124": "NON_PARTICIPATING",
|
35 |
+
"125": "NON_PARTICIPATING",
|
36 |
+
"126": "NON_PARTICIPATING",
|
37 |
"127": "NON_PARTICIPATING",
|
38 |
+
"128": "SUCCESS",
|
39 |
+
"129": "NON_PARTICIPATING",
|
40 |
+
"13": "NON_PARTICIPATING",
|
41 |
"130": "NON_PARTICIPATING",
|
42 |
"131": "NON_PARTICIPATING",
|
43 |
"132": "NON_PARTICIPATING",
|
|
|
48 |
"137": "NON_PARTICIPATING",
|
49 |
"138": "NON_PARTICIPATING",
|
50 |
"139": "NON_PARTICIPATING",
|
51 |
+
"14": "NON_PARTICIPATING",
|
52 |
+
"140": "SUCCESS",
|
53 |
+
"141": "SUCCESS",
|
54 |
"142": "NON_PARTICIPATING",
|
55 |
+
"143": "SUCCESS",
|
56 |
"144": "NON_PARTICIPATING",
|
57 |
"145": "NON_PARTICIPATING",
|
58 |
"146": "NON_PARTICIPATING",
|
59 |
"147": "NON_PARTICIPATING",
|
60 |
"148": "NON_PARTICIPATING",
|
61 |
"149": "NON_PARTICIPATING",
|
62 |
+
"15": "NON_PARTICIPATING",
|
63 |
"150": "NON_PARTICIPATING",
|
64 |
"151": "NON_PARTICIPATING",
|
65 |
+
"152": "SUCCESS",
|
66 |
"153": "NON_PARTICIPATING",
|
67 |
"154": "NON_PARTICIPATING",
|
68 |
"155": "NON_PARTICIPATING",
|
|
|
70 |
"157": "NON_PARTICIPATING",
|
71 |
"158": "NON_PARTICIPATING",
|
72 |
"159": "NON_PARTICIPATING",
|
73 |
+
"16": "NON_PARTICIPATING",
|
74 |
"160": "NON_PARTICIPATING",
|
75 |
"161": "NON_PARTICIPATING",
|
76 |
"162": "NON_PARTICIPATING",
|
|
|
78 |
"164": "NON_PARTICIPATING",
|
79 |
"165": "NON_PARTICIPATING",
|
80 |
"166": "NON_PARTICIPATING",
|
81 |
+
"167": "SUCCESS",
|
82 |
"168": "NON_PARTICIPATING",
|
83 |
+
"169": "NON_PARTICIPATING",
|
84 |
+
"17": "NON_PARTICIPATING",
|
85 |
"170": "NON_PARTICIPATING",
|
86 |
+
"171": "NON_PARTICIPATING",
|
87 |
"172": "NON_PARTICIPATING",
|
88 |
"173": "NON_PARTICIPATING",
|
89 |
"174": "NON_PARTICIPATING",
|
|
|
92 |
"177": "NON_PARTICIPATING",
|
93 |
"178": "NON_PARTICIPATING",
|
94 |
"179": "NON_PARTICIPATING",
|
95 |
+
"18": "NON_PARTICIPATING",
|
96 |
"180": "NON_PARTICIPATING",
|
97 |
"181": "NON_PARTICIPATING",
|
98 |
"182": "NON_PARTICIPATING",
|
99 |
+
"183": "NON_PARTICIPATING",
|
100 |
"184": "NON_PARTICIPATING",
|
101 |
"185": "NON_PARTICIPATING",
|
102 |
"186": "NON_PARTICIPATING",
|
103 |
"187": "NON_PARTICIPATING",
|
104 |
"188": "NON_PARTICIPATING",
|
105 |
"189": "NON_PARTICIPATING",
|
106 |
+
"19": "NON_PARTICIPATING",
|
107 |
"190": "NON_PARTICIPATING",
|
108 |
"191": "NON_PARTICIPATING",
|
109 |
"192": "NON_PARTICIPATING",
|
110 |
+
"193": "NON_PARTICIPATING",
|
111 |
"194": "NON_PARTICIPATING",
|
112 |
"195": "NON_PARTICIPATING",
|
113 |
+
"196": "SUCCESS",
|
114 |
"197": "NON_PARTICIPATING",
|
115 |
"198": "NON_PARTICIPATING",
|
116 |
"199": "NON_PARTICIPATING",
|
117 |
+
"2": "NON_PARTICIPATING",
|
118 |
"20": "SUCCESS",
|
119 |
"200": "NON_PARTICIPATING",
|
120 |
"201": "NON_PARTICIPATING",
|
121 |
"202": "NON_PARTICIPATING",
|
122 |
"203": "NON_PARTICIPATING",
|
123 |
"204": "NON_PARTICIPATING",
|
124 |
+
"205": "SUCCESS",
|
125 |
"206": "NON_PARTICIPATING",
|
126 |
"207": "NON_PARTICIPATING",
|
127 |
"208": "NON_PARTICIPATING",
|
128 |
"209": "NON_PARTICIPATING",
|
129 |
+
"21": "NON_PARTICIPATING",
|
130 |
"210": "NON_PARTICIPATING",
|
131 |
"211": "NON_PARTICIPATING",
|
132 |
"212": "NON_PARTICIPATING",
|
|
|
134 |
"214": "NON_PARTICIPATING",
|
135 |
"215": "NON_PARTICIPATING",
|
136 |
"216": "NON_PARTICIPATING",
|
137 |
+
"217": "NON_PARTICIPATING",
|
138 |
"218": "NON_PARTICIPATING",
|
139 |
"219": "NON_PARTICIPATING",
|
140 |
+
"22": "NON_PARTICIPATING",
|
141 |
"220": "NON_PARTICIPATING",
|
142 |
"221": "NON_PARTICIPATING",
|
143 |
"222": "NON_PARTICIPATING",
|
|
|
145 |
"224": "NON_PARTICIPATING",
|
146 |
"225": "NON_PARTICIPATING",
|
147 |
"226": "NON_PARTICIPATING",
|
148 |
+
"227": "SUCCESS",
|
149 |
"228": "NON_PARTICIPATING",
|
150 |
"229": "NON_PARTICIPATING",
|
151 |
+
"23": "NON_PARTICIPATING",
|
152 |
"230": "NON_PARTICIPATING",
|
153 |
"231": "NON_PARTICIPATING",
|
154 |
"232": "NON_PARTICIPATING",
|
155 |
"233": "NON_PARTICIPATING",
|
156 |
"234": "NON_PARTICIPATING",
|
157 |
"235": "NON_PARTICIPATING",
|
158 |
+
"236": "SUCCESS",
|
159 |
"237": "NON_PARTICIPATING",
|
160 |
"238": "NON_PARTICIPATING",
|
161 |
+
"239": "SUCCESS",
|
162 |
+
"24": "NON_PARTICIPATING",
|
163 |
"240": "NON_PARTICIPATING",
|
164 |
"241": "NON_PARTICIPATING",
|
165 |
"242": "NON_PARTICIPATING",
|
|
|
168 |
"245": "NON_PARTICIPATING",
|
169 |
"246": "NON_PARTICIPATING",
|
170 |
"247": "NON_PARTICIPATING",
|
171 |
+
"248": "SUCCESS",
|
172 |
"249": "NON_PARTICIPATING",
|
173 |
"25": "SUCCESS",
|
174 |
+
"250": "NON_PARTICIPATING",
|
175 |
"251": "NON_PARTICIPATING",
|
176 |
"252": "NON_PARTICIPATING",
|
177 |
"253": "NON_PARTICIPATING",
|
178 |
"254": "NON_PARTICIPATING",
|
179 |
+
"255": "NON_PARTICIPATING",
|
180 |
"26": "NON_PARTICIPATING",
|
181 |
+
"27": "NON_PARTICIPATING",
|
182 |
+
"28": "NON_PARTICIPATING",
|
183 |
+
"29": "NON_PARTICIPATING",
|
184 |
+
"3": "NON_PARTICIPATING",
|
185 |
"30": "NON_PARTICIPATING",
|
186 |
+
"31": "NON_PARTICIPATING",
|
187 |
+
"32": "NON_PARTICIPATING",
|
188 |
"33": "NON_PARTICIPATING",
|
189 |
+
"34": "NON_PARTICIPATING",
|
190 |
+
"35": "NON_PARTICIPATING",
|
191 |
+
"36": "NON_PARTICIPATING",
|
192 |
+
"37": "NON_PARTICIPATING",
|
193 |
+
"38": "NON_PARTICIPATING",
|
194 |
+
"39": "NON_PARTICIPATING",
|
195 |
+
"4": "NON_PARTICIPATING",
|
196 |
+
"40": "NON_PARTICIPATING",
|
197 |
+
"41": "NON_PARTICIPATING",
|
198 |
+
"42": "NON_PARTICIPATING",
|
199 |
+
"43": "NON_PARTICIPATING",
|
200 |
+
"44": "NON_PARTICIPATING",
|
201 |
+
"45": "NON_PARTICIPATING",
|
202 |
"46": "NON_PARTICIPATING",
|
203 |
+
"47": "NON_PARTICIPATING",
|
204 |
"48": "NON_PARTICIPATING",
|
205 |
+
"49": "NON_PARTICIPATING",
|
206 |
+
"5": "NON_PARTICIPATING",
|
207 |
+
"50": "NON_PARTICIPATING",
|
208 |
+
"51": "NON_PARTICIPATING",
|
209 |
+
"52": "NON_PARTICIPATING",
|
210 |
+
"53": "NON_PARTICIPATING",
|
211 |
+
"54": "NON_PARTICIPATING",
|
212 |
+
"55": "NON_PARTICIPATING",
|
213 |
+
"56": "NON_PARTICIPATING",
|
214 |
"57": "NON_PARTICIPATING",
|
215 |
"58": "NON_PARTICIPATING",
|
216 |
"59": "NON_PARTICIPATING",
|
217 |
+
"6": "NON_PARTICIPATING",
|
218 |
+
"60": "NON_PARTICIPATING",
|
219 |
+
"61": "NON_PARTICIPATING",
|
220 |
"62": "NON_PARTICIPATING",
|
221 |
+
"63": "NON_PARTICIPATING",
|
222 |
+
"64": "NON_PARTICIPATING",
|
223 |
+
"65": "NON_PARTICIPATING",
|
224 |
+
"66": "NON_PARTICIPATING",
|
225 |
+
"67": "NON_PARTICIPATING",
|
226 |
+
"68": "NON_PARTICIPATING",
|
227 |
+
"69": "NON_PARTICIPATING",
|
228 |
+
"7": "NON_PARTICIPATING",
|
229 |
+
"70": "NON_PARTICIPATING",
|
230 |
+
"71": "NON_PARTICIPATING",
|
231 |
+
"72": "NON_PARTICIPATING",
|
232 |
+
"73": "NON_PARTICIPATING",
|
233 |
+
"74": "NON_PARTICIPATING",
|
234 |
+
"75": "NON_PARTICIPATING",
|
235 |
+
"76": "NON_PARTICIPATING",
|
236 |
"77": "SUCCESS",
|
237 |
+
"78": "NON_PARTICIPATING",
|
238 |
"79": "NON_PARTICIPATING",
|
239 |
"8": "NON_PARTICIPATING",
|
240 |
+
"80": "NON_PARTICIPATING",
|
241 |
+
"81": "NON_PARTICIPATING",
|
242 |
+
"82": "NON_PARTICIPATING",
|
243 |
+
"83": "NON_PARTICIPATING",
|
244 |
+
"84": "NON_PARTICIPATING",
|
245 |
"85": "NON_PARTICIPATING",
|
246 |
"86": "NON_PARTICIPATING",
|
247 |
+
"87": "NON_PARTICIPATING",
|
248 |
+
"88": "NON_PARTICIPATING",
|
249 |
+
"89": "NON_PARTICIPATING",
|
250 |
+
"9": "NON_PARTICIPATING",
|
251 |
+
"90": "NON_PARTICIPATING",
|
252 |
+
"91": "NON_PARTICIPATING",
|
253 |
+
"92": "NON_PARTICIPATING",
|
254 |
"93": "NON_PARTICIPATING",
|
255 |
+
"94": "NON_PARTICIPATING",
|
256 |
+
"95": "NON_PARTICIPATING",
|
257 |
+
"96": "NON_PARTICIPATING",
|
258 |
+
"97": "NON_PARTICIPATING",
|
259 |
+
"98": "NON_PARTICIPATING",
|
260 |
+
"99": "NON_PARTICIPATING"
|
261 |
},
|
262 |
"architectures": [
|
263 |
"GPTOptim"
|
|
|
275 |
"initializer_range": 0.02,
|
276 |
"inner_step": 0,
|
277 |
"inner_steps": 0,
|
278 |
+
"last_allreduce_block": 5662361,
|
279 |
"layer_norm_epsilon": 1e-05,
|
280 |
"model_type": "gpt_optimized",
|
281 |
"n_embd": 1280,
|
inner_optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 8081782026
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11fbbfbddbb638890c3280e382b04e56295adc12bcf2fff421160d24dd92e765
|
3 |
size 8081782026
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4040701744
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d925a06cf746fb73f55f3183d8f4a675f340cf13d5bd0abf3cf6765ea8a4f0f
|
3 |
size 4040701744
|
outer_optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4040805354
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e49093f4a7dafa1344be887312b3fe6909ced2210a44b35c4807c0a3e8029b5
|
3 |
size 4040805354
|