mujerry commited on
Commit
bc0f5b2
·
verified ·
1 Parent(s): b8e0a2f

Run 11. Outer Step 223. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +44 -44
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -3,7 +3,7 @@
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
6
- "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
@@ -15,28 +15,28 @@
15
  "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
- "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
- "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
24
- "116": "SUCCESS",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
- "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "SUCCESS",
31
  "122": "NOT_ALIVE",
32
- "123": "NOT_ALIVE",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
- "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
- "13": "NON_PARTICIPATING",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
@@ -49,14 +49,14 @@
49
  "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
  "140": "SUCCESS",
52
- "141": "NOT_ALIVE",
53
  "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
- "146": "SUCCESS",
58
  "147": "SUCCESS",
59
- "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "SUCCESS",
@@ -72,7 +72,7 @@
72
  "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
- "162": "SUCCESS",
76
  "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
@@ -84,12 +84,12 @@
84
  "170": "NOT_ALIVE",
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": "SUCCESS",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
@@ -97,7 +97,7 @@
97
  "182": "SUCCESS",
98
  "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
- "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
@@ -108,11 +108,11 @@
108
  "192": "NOT_ALIVE",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
- "195": "SUCCESS",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NOT_ALIVE",
115
- "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
@@ -129,10 +129,10 @@
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
- "213": "NOT_ALIVE",
133
- "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
- "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
@@ -149,30 +149,30 @@
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "SUCCESS",
152
- "231": "SUCCESS",
153
  "232": "NOT_ALIVE",
154
  "233": "SUCCESS",
155
- "234": "NON_PARTICIPATING",
156
- "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "SUCCESS",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
- "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
- "241": "NOT_ALIVE",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "SUCCESS",
168
  "246": "NOT_ALIVE",
169
- "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
  "251": "SUCCESS",
175
- "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
@@ -185,11 +185,11 @@
185
  "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
- "34": "SUCCESS",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "SUCCESS",
192
- "38": "SUCCESS",
193
  "39": "NOT_ALIVE",
194
  "4": "SUCCESS",
195
  "40": "NOT_ALIVE",
@@ -208,14 +208,14 @@
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "SUCCESS",
211
- "55": "SUCCESS",
212
  "56": "NOT_ALIVE",
213
- "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "NOT_ALIVE",
218
- "61": "NOT_ALIVE",
219
  "62": "NON_PARTICIPATING",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
@@ -231,14 +231,14 @@
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
- "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
- "79": "SUCCESS",
238
  "8": "SUCCESS",
239
- "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
- "82": "NON_PARTICIPATING",
242
  "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
@@ -248,14 +248,14 @@
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
- "91": "NON_PARTICIPATING",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
  "97": "SUCCESS",
258
- "98": "NOT_ALIVE",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6667886,
268
- 6667930
269
  ],
270
  "bos_token_id": 1,
271
  "dtype": "float32",
@@ -274,9 +274,9 @@
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
- "inner_step": 45,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6666862,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
6
+ "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
 
15
  "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
+ "110": "SUCCESS",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
+ "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
24
+ "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
+ "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
+ "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
32
+ "123": "NON_PARTICIPATING",
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": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
 
49
  "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
  "140": "SUCCESS",
52
+ "141": "SUCCESS",
53
  "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
+ "146": "NOT_ALIVE",
58
  "147": "SUCCESS",
59
+ "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "SUCCESS",
 
72
  "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
+ "162": "NOT_ALIVE",
76
  "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
 
84
  "170": "NOT_ALIVE",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
+ "173": "NOT_ALIVE",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
+ "178": "NON_PARTICIPATING",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
 
97
  "182": "SUCCESS",
98
  "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
+ "185": "NOT_ALIVE",
101
  "186": "SUCCESS",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
 
108
  "192": "NOT_ALIVE",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
+ "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NOT_ALIVE",
115
+ "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
 
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
+ "213": "NON_PARTICIPATING",
133
+ "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
+ "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
 
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "SUCCESS",
152
+ "231": "FAIL",
153
  "232": "NOT_ALIVE",
154
  "233": "SUCCESS",
155
+ "234": "SUCCESS",
156
+ "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
  "237": "SUCCESS",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
+ "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
+ "241": "SUCCESS",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "SUCCESS",
168
  "246": "NOT_ALIVE",
169
+ "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
  "251": "SUCCESS",
175
+ "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
 
185
  "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
+ "34": "NOT_ALIVE",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "SUCCESS",
192
+ "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "SUCCESS",
195
  "40": "NOT_ALIVE",
 
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "SUCCESS",
211
+ "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
+ "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
 
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
+ "76": "SUCCESS",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
+ "79": "NON_PARTICIPATING",
238
  "8": "SUCCESS",
239
+ "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
+ "82": "SUCCESS",
242
  "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
 
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
+ "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
  "97": "SUCCESS",
258
+ "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6668085,
268
+ 6668116
269
  ],
270
  "bos_token_id": 1,
271
  "dtype": "float32",
 
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
+ "inner_step": 9,
278
  "intermediate_size": 5632,
279
+ "last_allreduce_block": 6668039,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50a42cf5702fa0ab3736122daaac2d72b39cd727ed61a23bf94c53e47ef849c7
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:789edfd2b4af37a13d08ade652cbf2a01dc60bf82f2d8756513f0f155372670a
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83c654b93769316e930c1518909c4ad070947bc76705be75edf9da50675c8041
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfacdb16cf5a8f2423a547218516abe8dd8379fbd2eae4c63bb294af493bf586
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7207c85f880ebae633e1267d94ce8c091399acdb40bfb387b186d6e9f96efd4
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e7bbf821e20518b4d1f84677b83738d6f2fd00a7e236d3c6737289efed0aecb
3
  size 4400216536