Alir332 commited on
Commit
cefb8bc
·
verified ·
1 Parent(s): b6e47d0

Run 11. Outer Step 232. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +46 -46
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,39 +2,39 @@
2
  "_name_or_path": "dstrbtd/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "NON_PARTICIPATING",
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
- "103": "SUCCESS",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
- "106": "SUCCESS",
14
  "107": "NON_PARTICIPATING",
15
- "108": "FAIL",
16
- "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
- "115": "SUCCESS",
24
- "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
- "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
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": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "SUCCESS",
@@ -42,27 +42,27 @@
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": "NOT_ALIVE",
50
  "14": "NON_PARTICIPATING",
51
  "140": "SUCCESS",
52
- "141": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "NOT_ALIVE",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
@@ -89,15 +89,15 @@
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
- "178": "NON_PARTICIPATING",
93
  "179": "SUCCESS",
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": "SUCCESS",
103
  "188": "NOT_ALIVE",
@@ -106,25 +106,25 @@
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
- "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
- "197": "SUCCESS",
114
  "198": "NOT_ALIVE",
115
- "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
- "200": "NOT_ALIVE",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NOT_ALIVE",
124
- "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
- "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
@@ -132,7 +132,7 @@
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",
@@ -148,14 +148,14 @@
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "SUCCESS",
151
- "230": "NOT_ALIVE",
152
- "231": "SUCCESS",
153
  "232": "NOT_ALIVE",
154
- "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
- "236": "NON_PARTICIPATING",
158
- "237": "NOT_ALIVE",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
@@ -164,7 +164,7 @@
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",
@@ -188,8 +188,8 @@
188
  "34": "SUCCESS",
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",
@@ -197,7 +197,7 @@
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
- "45": "NON_PARTICIPATING",
201
  "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
@@ -217,9 +217,9 @@
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
  "62": "NON_PARTICIPATING",
220
- "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
- "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "SUCCESS",
@@ -235,7 +235,7 @@
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
238
- "8": "NOT_ALIVE",
239
  "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
  "82": "SUCCESS",
@@ -244,18 +244,18 @@
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
247
- "88": "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": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
- "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6671496,
268
- 6671525
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": 40,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6671231,
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": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
+ "106": "NON_PARTICIPATING",
14
  "107": "NON_PARTICIPATING",
15
+ "108": "NON_PARTICIPATING",
16
+ "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
+ "115": "NON_PARTICIPATING",
24
+ "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
+ "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
32
+ "123": "NOT_ALIVE",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
+ "127": "NOT_ALIVE",
37
+ "128": "SUCCESS",
38
  "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "SUCCESS",
 
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": "SUCCESS",
52
+ "141": "NOT_ALIVE",
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": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
 
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
+ "178": "NOT_ALIVE",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
+ "182": "NOT_ALIVE",
98
  "183": "NOT_ALIVE",
99
+ "184": "NOT_ALIVE",
100
+ "185": "NOT_ALIVE",
101
  "186": "SUCCESS",
102
  "187": "SUCCESS",
103
  "188": "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": "NON_PARTICIPATING",
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",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NOT_ALIVE",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
+ "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
 
132
  "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
+ "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
 
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "SUCCESS",
151
+ "230": "SUCCESS",
152
+ "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
+ "233": "SUCCESS",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
+ "236": "NOT_ALIVE",
158
+ "237": "SUCCESS",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
 
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NON_PARTICIPATING",
168
  "246": "NOT_ALIVE",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
 
188
  "34": "SUCCESS",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
+ "37": "NOT_ALIVE",
192
+ "38": "NON_PARTICIPATING",
193
  "39": "NOT_ALIVE",
194
  "4": "SUCCESS",
195
  "40": "NOT_ALIVE",
 
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
+ "45": "FAIL",
201
  "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
 
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
  "62": "NON_PARTICIPATING",
220
+ "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
222
+ "65": "SUCCESS",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "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",
 
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
247
+ "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
+ "91": "SUCCESS",
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": "NON_PARTICIPATING",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6671662,
268
+ 6671691
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": 6671624,
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 sha256:45e75b837e8e92ef27153fcaebc42306dfd5734012c892f151dddf159161b79f
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff07f7becf5de8ead31032bf770aa91f74190ce173625cec33c9b25a81d614b0
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94d5d737fb70f55df5df33007a0122f96f15bdd5e4fa5eb2d175b59560c0a36b
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e964a19d74c9a34a24080ea7d842114d44391b00673bcf042dea5e44b8d30b56
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb1b898332aff2430ccf142ed51f009e8b3f5535723c331c52fb65a521aa4afa
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad6db1b3e6576e187e87b1c6837659daed2ac9df8ce44e9c3411af6d1fe7cc5
3
  size 4400216536