ncaagcc commited on
Commit
cbaad20
·
verified ·
1 Parent(s): 2468bac

Run 10. Outer Step 49. Inner Step 4.

Browse files
Files changed (4) hide show
  1. config.json +94 -94
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,7 +2,7 @@
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "SUCCESS",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
@@ -10,75 +10,75 @@
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
- "106": "NON_PARTICIPATING",
14
- "107": "SUCCESS",
15
  "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
17
- "11": "SUCCESS",
18
- "110": "SUCCESS",
19
- "111": "NON_PARTICIPATING",
20
- "112": "NOT_ALIVE",
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NOT_ALIVE",
25
- "117": "NOT_ALIVE",
26
- "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
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": "SUCCESS",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
  "128": "SUCCESS",
38
- "129": "NOT_ALIVE",
39
- "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
- "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
- "138": "SUCCESS",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
- "140": "NOT_ALIVE",
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": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
- "15": "SUCCESS",
62
- "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "NOT_ALIVE",
66
  "154": "NOT_ALIVE",
67
- "155": "NON_PARTICIPATING",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
- "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
- "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
  "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
- "166": "NON_PARTICIPATING",
80
- "167": "NON_PARTICIPATING",
81
- "168": "NOT_ALIVE",
82
  "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
@@ -94,8 +94,8 @@
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
- "182": "NON_PARTICIPATING",
98
- "183": "NON_PARTICIPATING",
99
  "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
@@ -105,105 +105,105 @@
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
- "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
- "194": "NON_PARTICIPATING",
111
  "195": "NOT_ALIVE",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
- "198": "NOT_ALIVE",
115
- "199": "NOT_ALIVE",
116
- "2": "NON_PARTICIPATING",
117
  "20": "SUCCESS",
118
- "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
- "202": "NOT_ALIVE",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
- "205": "NON_PARTICIPATING",
124
- "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
- "209": "SUCCESS",
128
- "21": "SUCCESS",
129
- "210": "NOT_ALIVE",
130
- "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
- "213": "NOT_ALIVE",
133
- "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
  "219": "SUCCESS",
139
  "22": "NON_PARTICIPATING",
140
- "220": "NOT_ALIVE",
141
  "221": "SUCCESS",
142
- "222": "SUCCESS",
143
- "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
- "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
- "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
- "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
- "232": "NOT_ALIVE",
154
- "233": "SUCCESS",
155
  "234": "SUCCESS",
156
  "235": "SUCCESS",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
- "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
168
- "246": "NOT_ALIVE",
169
  "247": "NOT_ALIVE",
170
  "248": "NON_PARTICIPATING",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
- "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "SUCCESS",
178
- "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
- "28": "NON_PARTICIPATING",
182
- "29": "SUCCESS",
183
  "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
- "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
- "34": "NON_PARTICIPATING",
189
- "35": "NON_PARTICIPATING",
190
- "36": "SUCCESS",
191
- "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
- "39": "NON_PARTICIPATING",
194
  "4": "SUCCESS",
195
- "40": "SUCCESS",
196
- "41": "NON_PARTICIPATING",
197
- "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
- "45": "SUCCESS",
201
- "46": "NON_PARTICIPATING",
202
- "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
- "5": "SUCCESS",
206
- "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
@@ -215,45 +215,45 @@
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
- "61": "NOT_ALIVE",
219
- "62": "NON_PARTICIPATING",
220
  "63": "NOT_ALIVE",
221
- "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
- "7": "NON_PARTICIPATING",
228
- "70": "SUCCESS",
229
  "71": "NON_PARTICIPATING",
230
- "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
- "74": "NON_PARTICIPATING",
233
  "75": "NOT_ALIVE",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
- "8": "SUCCESS",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
- "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
- "86": "SUCCESS",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
249
- "9": "SUCCESS",
250
- "90": "NON_PARTICIPATING",
251
- "91": "SUCCESS",
252
- "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
- "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6488467,
268
- 6488476
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
- "inner_step": 121,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6487477,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "NON_PARTICIPATING",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
 
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
+ "106": "SUCCESS",
14
+ "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
17
+ "11": "NOT_ALIVE",
18
+ "110": "NOT_ALIVE",
19
+ "111": "SUCCESS",
20
+ "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "SUCCESS",
25
+ "117": "NON_PARTICIPATING",
26
+ "118": "NOT_ALIVE",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
+ "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
+ "124": "NON_PARTICIPATING",
34
+ "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
  "128": "SUCCESS",
38
+ "129": "NON_PARTICIPATING",
39
+ "13": "NON_PARTICIPATING",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
+ "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
+ "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
+ "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
+ "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
+ "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
+ "15": "NOT_ALIVE",
62
+ "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
+ "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
+ "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
  "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
+ "166": "SUCCESS",
80
+ "167": "NOT_ALIVE",
81
+ "168": "NON_PARTICIPATING",
82
  "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
 
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
+ "182": "SUCCESS",
98
+ "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
 
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
+ "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
+ "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
+ "198": "SUCCESS",
115
+ "199": "NON_PARTICIPATING",
116
+ "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
+ "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
+ "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
+ "205": "SUCCESS",
124
+ "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
+ "209": "NON_PARTICIPATING",
128
+ "21": "NOT_ALIVE",
129
+ "210": "NON_PARTICIPATING",
130
+ "211": "NOT_ALIVE",
131
  "212": "SUCCESS",
132
+ "213": "NON_PARTICIPATING",
133
+ "214": "SUCCESS",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
  "219": "SUCCESS",
139
  "22": "NON_PARTICIPATING",
140
+ "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
+ "222": "NOT_ALIVE",
143
+ "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
+ "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
+ "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
+ "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
+ "232": "SUCCESS",
154
+ "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
  "235": "SUCCESS",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
+ "24": "NOT_ALIVE",
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": "SUCCESS",
169
  "247": "NOT_ALIVE",
170
  "248": "NON_PARTICIPATING",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
+ "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "SUCCESS",
178
+ "255": "SUCCESS",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
+ "28": "SUCCESS",
182
+ "29": "NON_PARTICIPATING",
183
  "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
+ "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
+ "34": "NOT_ALIVE",
189
+ "35": "SUCCESS",
190
+ "36": "NON_PARTICIPATING",
191
+ "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
+ "39": "SUCCESS",
194
  "4": "SUCCESS",
195
+ "40": "NON_PARTICIPATING",
196
+ "41": "NOT_ALIVE",
197
+ "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
+ "45": "NON_PARTICIPATING",
201
+ "46": "NOT_ALIVE",
202
+ "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "NON_PARTICIPATING",
206
+ "50": "SUCCESS",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
 
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
+ "61": "NON_PARTICIPATING",
219
+ "62": "SUCCESS",
220
  "63": "NOT_ALIVE",
221
+ "64": "SUCCESS",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
+ "7": "SUCCESS",
228
+ "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
+ "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
+ "74": "SUCCESS",
233
  "75": "NOT_ALIVE",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
+ "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
+ "82": "SUCCESS",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
249
+ "9": "NON_PARTICIPATING",
250
+ "90": "NOT_ALIVE",
251
+ "91": "NON_PARTICIPATING",
252
+ "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
+ "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6495211,
268
+ 6495217
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
+ "inner_step": 4,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6494836,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0539689c4977ac53fcfc4f10ec1fbca5757302751317616a97c096c580849fe6
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a71b7feb64934ddc96588b67c60cc7ef0e08c8c2684a1a001cb8eea1ee778a29
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e3b8768658437dfdc5414394aabd0c2f1b0ec0debdf47a83e41ae567b298e61
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b346d2edbabd18ddc0552b671fd24d82119966c6114afbee318d128531d322
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c27ad61736846e6fa84a3b05a56360d122455f8d04bf24db2b60b20c9326f767
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efd36ddc9b1ce89659c745c5e5fe430513b5468689169fa3ff9f47a5f5e29215
3
  size 4400216536