mujerry commited on
Commit
b525d90
·
verified ·
1 Parent(s): 7ceccb5

Run 11. Outer Step 206. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +52 -52
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,46 +2,46 @@
2
  "_name_or_path": "dstrbtd/llama-1b",
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",
10
  "103": "NON_PARTICIPATING",
11
  "104": "SUCCESS",
12
- "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
- "107": "NOT_ALIVE",
15
  "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
- "110": "NOT_ALIVE",
19
- "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
- "116": "SUCCESS",
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": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
- "128": "SUCCESS",
38
  "129": "NON_PARTICIPATING",
39
- "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
- "134": "SUCCESS",
45
  "135": "SUCCESS",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
@@ -50,32 +50,32 @@
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": "NON_PARTICIPATING",
58
- "147": "NOT_ALIVE",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "SUCCESS",
66
- "154": "NON_PARTICIPATING",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "SUCCESS",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
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": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NOT_ALIVE",
@@ -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",
@@ -98,8 +98,8 @@
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",
105
  "19": "NOT_ALIVE",
@@ -108,11 +108,11 @@
108
  "192": "NOT_ALIVE",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
- "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "SUCCESS",
114
  "198": "NOT_ALIVE",
115
- "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
@@ -126,45 +126,45 @@
126
  "208": "NOT_ALIVE",
127
  "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
- "210": "NOT_ALIVE",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
- "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
  "216": "NON_PARTICIPATING",
136
- "217": "NON_PARTICIPATING",
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": "NOT_ALIVE",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
- "23": "SUCCESS",
151
- "230": "NOT_ALIVE",
152
- "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "SUCCESS",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
- "237": "SUCCESS",
159
  "238": "SUCCESS",
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",
@@ -193,14 +193,14 @@
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
- "41": "NON_PARTICIPATING",
197
- "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
- "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
- "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
@@ -208,9 +208,9 @@
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "SUCCESS",
211
- "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
- "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
@@ -238,7 +238,7 @@
238
  "8": "SUCCESS",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
- "82": "NON_PARTICIPATING",
242
  "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
@@ -248,12 +248,12 @@
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": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
- "96": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
  "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6661390,
268
- 6661427
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": 63,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6659044,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
2
  "_name_or_path": "dstrbtd/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "NOT_ALIVE",
6
+ "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "SUCCESS",
12
+ "105": "NON_PARTICIPATING",
13
  "106": "SUCCESS",
14
+ "107": "SUCCESS",
15
  "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
+ "110": "NON_PARTICIPATING",
19
+ "111": "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": "NON_PARTICIPATING",
31
+ "122": "NOT_ALIVE",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
+ "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
+ "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
+ "134": "NON_PARTICIPATING",
45
  "135": "SUCCESS",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
 
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",
58
+ "147": "SUCCESS",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "NON_PARTICIPATING",
66
+ "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "SUCCESS",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
+ "16": "NON_PARTICIPATING",
73
  "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
+ "162": "SUCCESS",
76
  "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
+ "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NOT_ALIVE",
 
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
+ "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "SUCCESS",
 
98
  "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
  "185": "SUCCESS",
101
+ "186": "NON_PARTICIPATING",
102
+ "187": "NOT_ALIVE",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
 
108
  "192": "NOT_ALIVE",
109
  "193": "SUCCESS",
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",
 
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",
133
+ "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NON_PARTICIPATING",
136
+ "217": "SUCCESS",
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": "SUCCESS",
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": "NOT_ALIVE",
151
+ "230": "SUCCESS",
152
+ "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
+ "233": "FAIL",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
+ "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
163
+ "241": "SUCCESS",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
 
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
+ "41": "NOT_ALIVE",
197
+ "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
+ "45": "SUCCESS",
201
  "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
+ "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
 
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "SUCCESS",
211
+ "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
213
+ "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
 
238
  "8": "SUCCESS",
239
  "80": "NOT_ALIVE",
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": "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": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6661500,
268
+ 6661553
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": 6661467,
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:e2f63a88333eeef532f5e43e8c11275b2015d10df8f795a3adc9870e4af4b2a4
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12fca75ea835e48f2448469e337d1382ea03aa42595d4f11cad4eb2b565f591c
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8859bd9ac42583f74b71163fe1a16c1787dc9b448459ba7804ab2e246dcaf45
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b43f95de530cd2c7377e48d4b84fdd9b201c91bbdb0b035eee0cdc7ccf1dc85c
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b19ee524701a3dad0b228f93e8f3ad55c4157a500e95c28661769449d00a7bfa
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:496692a054d4b4c07a43f3fdd795ab50fb164ed1f5458e33d80f0430c1d168ae
3
  size 4400216536