ShinyUser commited on
Commit
2714244
·
verified ·
1 Parent(s): 0018477

Run 11. Outer Step 202. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +40 -40
  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": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
@@ -12,7 +12,7 @@
12
  "105": "NON_PARTICIPATING",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
- "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
@@ -20,15 +20,15 @@
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
30
- "121": "NON_PARTICIPATING",
31
- "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
@@ -36,22 +36,22 @@
36
  "127": "SUCCESS",
37
  "128": "SUCCESS",
38
  "129": "SUCCESS",
39
- "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "SUCCESS",
45
- "135": "NOT_ALIVE",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
- "140": "NOT_ALIVE",
52
  "141": "SUCCESS",
53
  "142": "NON_PARTICIPATING",
54
- "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
@@ -70,9 +70,9 @@
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
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",
@@ -86,7 +86,7 @@
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
- "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "SUCCESS",
@@ -94,11 +94,11 @@
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
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",
104
  "189": "NOT_ALIVE",
@@ -106,15 +106,15 @@
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
- "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
- "197": "SUCCESS",
114
  "198": "NOT_ALIVE",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
- "20": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
@@ -126,7 +126,7 @@
126
  "208": "NOT_ALIVE",
127
  "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
- "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
@@ -137,22 +137,22 @@
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
- "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
  "226": "SUCCESS",
147
- "227": "NON_PARTICIPATING",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "SUCCESS",
151
  "230": "SUCCESS",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "NOT_ALIVE",
155
- "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
  "237": "NOT_ALIVE",
@@ -160,13 +160,13 @@
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
163
- "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
- "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
- "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
@@ -188,7 +188,7 @@
188
  "34": "NOT_ALIVE",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
- "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
  "39": "NOT_ALIVE",
194
  "4": "NON_PARTICIPATING",
@@ -204,10 +204,10 @@
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
- "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
- "54": "SUCCESS",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
  "57": "NON_PARTICIPATING",
@@ -215,8 +215,8 @@
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
- "61": "NOT_ALIVE",
219
- "62": "NON_PARTICIPATING",
220
  "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
  "65": "SUCCESS",
@@ -231,14 +231,14 @@
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
- "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
238
  "8": "SUCCESS",
239
  "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
- "82": "NON_PARTICIPATING",
242
  "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
@@ -247,15 +247,15 @@
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
- "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
- "96": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
- "98": "NOT_ALIVE",
259
  "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6659782,
268
- 6659807
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": 72,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6659442,
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": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
 
12
  "105": "NON_PARTICIPATING",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
+ "108": "NOT_ALIVE",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
 
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
+ "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
  "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
+ "121": "SUCCESS",
31
+ "122": "NOT_ALIVE",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
 
36
  "127": "SUCCESS",
37
  "128": "SUCCESS",
38
  "129": "SUCCESS",
39
+ "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "SUCCESS",
45
+ "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
+ "140": "SUCCESS",
52
  "141": "SUCCESS",
53
  "142": "NON_PARTICIPATING",
54
+ "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
 
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
+ "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
+ "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
 
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
+ "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "SUCCESS",
 
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
+ "182": "NOT_ALIVE",
98
  "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
+ "185": "NON_PARTICIPATING",
101
+ "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
 
106
  "190": "NOT_ALIVE",
107
  "191": "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",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
 
126
  "208": "NOT_ALIVE",
127
  "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
+ "210": "SUCCESS",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
 
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
+ "220": "NOT_ALIVE",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
  "226": "SUCCESS",
147
+ "227": "SUCCESS",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "SUCCESS",
151
  "230": "SUCCESS",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
+ "233": "SUCCESS",
155
+ "234": "NOT_ALIVE",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
  "237": "NOT_ALIVE",
 
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
163
+ "241": "NOT_ALIVE",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
 
188
  "34": "NOT_ALIVE",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
+ "37": "SUCCESS",
192
  "38": "SUCCESS",
193
  "39": "NOT_ALIVE",
194
  "4": "NON_PARTICIPATING",
 
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
+ "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
+ "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
  "57": "NON_PARTICIPATING",
 
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
+ "61": "SUCCESS",
219
+ "62": "SUCCESS",
220
  "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
  "65": "SUCCESS",
 
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": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
+ "82": "NOT_ALIVE",
242
  "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
 
247
  "88": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
259
  "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6659880,
268
+ 6659900
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": 6659802,
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:ca6f8ef276bbc9ca06883024f676f7c5384b4476a1bfdcfff46ff26c24a82ba1
3
  size 88390091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0dfe363b3c5402b6f60fa9eb4c02749e3992388f0fbd4d333ad62148ac46d1e
3
  size 88390091
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c82389097fe872be373830f21ba73be4609e81edd33e0790bca0a3e2dfbcac4
3
  size 4924928111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0f0be8889c8ff1d7b0beaf0a5b10d1f272384143c701996487928a547d77786
3
  size 4924928111
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9310091fdb57bd0cc15c42b23b4bc0fcf28f237d95562cf9cc3c47ab4e744c43
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c3c12deb2894f88ac0cd5d00b0f36788080b5957618f5d7add4643b0ab518b5
3
  size 4400216536