ncaagcc commited on
Commit
58a4c56
·
verified ·
1 Parent(s): 69efac6

Run 8. Outer Step 57. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +113 -113
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,29 +2,29 @@
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "NOT_ALIVE",
6
- "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
  "101": "SUCCESS",
9
- "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
- "107": "NON_PARTICIPATING",
15
  "108": "SUCCESS",
16
- "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
- "110": "NON_PARTICIPATING",
19
  "111": "NOT_ALIVE",
20
  "112": "SUCCESS",
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": "FAIL",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "SUCCESS",
@@ -32,142 +32,142 @@
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
- "126": "FAIL",
36
- "127": "SUCCESS",
37
- "128": "NOT_ALIVE",
38
  "129": "FAIL",
39
  "13": "NOT_ALIVE",
40
- "130": "FAIL",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
- "133": "NON_PARTICIPATING",
44
  "134": "NOT_ALIVE",
45
- "135": "FAIL",
46
  "136": "SUCCESS",
47
  "137": "SUCCESS",
48
- "138": "NOT_ALIVE",
49
- "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
- "140": "FAIL",
52
  "141": "NOT_ALIVE",
53
  "142": "FAIL",
54
- "143": "SUCCESS",
55
  "144": "NON_PARTICIPATING",
56
- "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
- "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
- "15": "FAIL",
62
- "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
- "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
  "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
- "158": "FAIL",
71
- "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
- "161": "FAIL",
75
  "162": "NON_PARTICIPATING",
76
- "163": "FAIL",
77
- "164": "FAIL",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
- "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
- "171": "NON_PARTICIPATING",
86
- "172": "NOT_ALIVE",
87
- "173": "NON_PARTICIPATING",
88
  "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
- "177": "FAIL",
92
  "178": "NON_PARTICIPATING",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
  "181": "SUCCESS",
97
  "182": "SUCCESS",
98
- "183": "SUCCESS",
99
- "184": "FAIL",
100
- "185": "NON_PARTICIPATING",
101
- "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
- "189": "NON_PARTICIPATING",
105
- "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
  "191": "FAIL",
108
- "192": "FAIL",
109
- "193": "SUCCESS",
110
- "194": "FAIL",
111
- "195": "FAIL",
112
  "196": "NON_PARTICIPATING",
113
- "197": "NOT_ALIVE",
114
- "198": "NOT_ALIVE",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
  "204": "SUCCESS",
123
  "205": "SUCCESS",
124
- "206": "SUCCESS",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
- "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
- "210": "NOT_ALIVE",
130
- "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
- "213": "FAIL",
133
  "214": "SUCCESS",
134
  "215": "SUCCESS",
135
  "216": "SUCCESS",
136
- "217": "SUCCESS",
137
- "218": "FAIL",
138
  "219": "SUCCESS",
139
- "22": "SUCCESS",
140
- "220": "FAIL",
141
- "221": "NON_PARTICIPATING",
142
  "222": "SUCCESS",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
- "225": "FAIL",
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
- "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
- "230": "FAIL",
152
- "231": "NON_PARTICIPATING",
153
- "232": "FAIL",
154
- "233": "FAIL",
155
  "234": "SUCCESS",
156
  "235": "SUCCESS",
157
  "236": "SUCCESS",
158
- "237": "FAIL",
159
  "238": "SUCCESS",
160
- "239": "FAIL",
161
- "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
- "241": "FAIL",
164
  "242": "SUCCESS",
165
- "243": "NON_PARTICIPATING",
166
- "244": "FAIL",
167
  "245": "SUCCESS",
168
- "246": "NOT_ALIVE",
169
- "247": "SUCCESS",
170
- "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
@@ -177,70 +177,70 @@
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "SUCCESS",
180
- "27": "NON_PARTICIPATING",
181
  "28": "SUCCESS",
182
- "29": "NON_PARTICIPATING",
183
  "3": "SUCCESS",
184
- "30": "NON_PARTICIPATING",
185
- "31": "NON_PARTICIPATING",
186
- "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
- "34": "NOT_ALIVE",
189
  "35": "FAIL",
190
- "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
- "4": "FAIL",
195
  "40": "NON_PARTICIPATING",
196
- "41": "FAIL",
197
- "42": "SUCCESS",
198
  "43": "NON_PARTICIPATING",
199
- "44": "FAIL",
200
- "45": "FAIL",
201
- "46": "NON_PARTICIPATING",
202
- "47": "FAIL",
203
  "48": "NOT_ALIVE",
204
- "49": "FAIL",
205
- "5": "FAIL",
206
- "50": "NOT_ALIVE",
207
  "51": "SUCCESS",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "SUCCESS",
211
- "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
- "57": "NON_PARTICIPATING",
214
  "58": "SUCCESS",
215
- "59": "NOT_ALIVE",
216
- "6": "FAIL",
217
  "60": "SUCCESS",
218
  "61": "NON_PARTICIPATING",
219
- "62": "FAIL",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
- "65": "SUCCESS",
223
- "66": "NON_PARTICIPATING",
224
- "67": "NON_PARTICIPATING",
225
- "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
- "70": "FAIL",
229
- "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
- "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
- "76": "FAIL",
235
- "77": "SUCCESS",
236
  "78": "SUCCESS",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
- "81": "NON_PARTICIPATING",
241
  "82": "SUCCESS",
242
- "83": "NON_PARTICIPATING",
243
- "84": "FAIL",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NOT_ALIVE",
246
  "87": "FAIL",
@@ -248,12 +248,12 @@
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "SUCCESS",
251
- "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NOT_ALIVE",
255
- "95": "SUCCESS",
256
- "96": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
@@ -264,18 +264,18 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6380187,
268
- 6380200,
269
- 6380227
270
  ],
271
  "bos_token_id": 1,
272
  "eos_token_id": 2,
273
  "hidden_act": "silu",
274
  "hidden_size": 2048,
275
  "initializer_range": 0.02,
276
- "inner_step": 86,
277
  "intermediate_size": 5632,
278
- "last_allreduce_block": 6379556,
279
  "max_position_embeddings": 2048,
280
  "mlp_bias": false,
281
  "model_type": "llama",
 
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "SUCCESS",
6
+ "10": "FAIL",
7
  "100": "NOT_ALIVE",
8
  "101": "SUCCESS",
9
+ "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
+ "107": "SUCCESS",
15
  "108": "SUCCESS",
16
+ "109": "NOT_ALIVE",
17
  "11": "SUCCESS",
18
+ "110": "FAIL",
19
  "111": "NOT_ALIVE",
20
  "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "SUCCESS",
26
  "118": "NOT_ALIVE",
27
+ "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "SUCCESS",
 
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
+ "126": "SUCCESS",
36
+ "127": "NON_PARTICIPATING",
37
+ "128": "SUCCESS",
38
  "129": "FAIL",
39
  "13": "NOT_ALIVE",
40
+ "130": "SUCCESS",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
+ "133": "SUCCESS",
44
  "134": "NOT_ALIVE",
45
+ "135": "SUCCESS",
46
  "136": "SUCCESS",
47
  "137": "SUCCESS",
48
+ "138": "NON_PARTICIPATING",
49
+ "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
+ "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "FAIL",
54
+ "143": "FAIL",
55
  "144": "NON_PARTICIPATING",
56
+ "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
+ "147": "FAIL",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
+ "15": "SUCCESS",
62
+ "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
+ "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
66
  "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NON_PARTICIPATING",
71
+ "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "SUCCESS",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "SUCCESS",
77
+ "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
+ "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
+ "171": "SUCCESS",
86
+ "172": "SUCCESS",
87
+ "173": "SUCCESS",
88
  "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
+ "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
  "181": "SUCCESS",
97
  "182": "SUCCESS",
98
+ "183": "FAIL",
99
+ "184": "SUCCESS",
100
+ "185": "FAIL",
101
+ "186": "NON_PARTICIPATING",
102
  "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
+ "189": "FAIL",
105
+ "19": "FAIL",
106
  "190": "NON_PARTICIPATING",
107
  "191": "FAIL",
108
+ "192": "SUCCESS",
109
+ "193": "FAIL",
110
+ "194": "NON_PARTICIPATING",
111
+ "195": "SUCCESS",
112
  "196": "NON_PARTICIPATING",
113
+ "197": "NON_PARTICIPATING",
114
+ "198": "NON_PARTICIPATING",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "SUCCESS",
122
  "204": "SUCCESS",
123
  "205": "SUCCESS",
124
+ "206": "NON_PARTICIPATING",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
+ "209": "SUCCESS",
128
  "21": "SUCCESS",
129
+ "210": "NON_PARTICIPATING",
130
+ "211": "SUCCESS",
131
  "212": "SUCCESS",
132
+ "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "SUCCESS",
135
  "216": "SUCCESS",
136
+ "217": "NON_PARTICIPATING",
137
+ "218": "NON_PARTICIPATING",
138
  "219": "SUCCESS",
139
+ "22": "FAIL",
140
+ "220": "SUCCESS",
141
+ "221": "SUCCESS",
142
  "222": "SUCCESS",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
+ "228": "SUCCESS",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
+ "230": "SUCCESS",
152
+ "231": "NOT_ALIVE",
153
+ "232": "NOT_ALIVE",
154
+ "233": "SUCCESS",
155
  "234": "SUCCESS",
156
  "235": "SUCCESS",
157
  "236": "SUCCESS",
158
+ "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
+ "239": "SUCCESS",
161
+ "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
163
+ "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
+ "243": "NOT_ALIVE",
166
+ "244": "SUCCESS",
167
  "245": "SUCCESS",
168
+ "246": "NON_PARTICIPATING",
169
+ "247": "FAIL",
170
+ "248": "FAIL",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
 
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "SUCCESS",
180
+ "27": "FAIL",
181
  "28": "SUCCESS",
182
+ "29": "SUCCESS",
183
  "3": "SUCCESS",
184
+ "30": "FAIL",
185
+ "31": "SUCCESS",
186
+ "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
+ "34": "SUCCESS",
189
  "35": "FAIL",
190
+ "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
+ "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "NON_PARTICIPATING",
197
+ "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
199
+ "44": "SUCCESS",
200
+ "45": "NOT_ALIVE",
201
+ "46": "FAIL",
202
+ "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
204
+ "49": "NOT_ALIVE",
205
+ "5": "SUCCESS",
206
+ "50": "FAIL",
207
  "51": "SUCCESS",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "SUCCESS",
211
+ "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
+ "57": "SUCCESS",
214
  "58": "SUCCESS",
215
+ "59": "NON_PARTICIPATING",
216
+ "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
  "61": "NON_PARTICIPATING",
219
+ "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
+ "65": "NOT_ALIVE",
223
+ "66": "NOT_ALIVE",
224
+ "67": "NOT_ALIVE",
225
+ "68": "FAIL",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
+ "70": "NOT_ALIVE",
229
+ "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
234
+ "76": "NON_PARTICIPATING",
235
+ "77": "NON_PARTICIPATING",
236
  "78": "SUCCESS",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
+ "81": "NOT_ALIVE",
241
  "82": "SUCCESS",
242
+ "83": "SUCCESS",
243
+ "84": "NOT_ALIVE",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NOT_ALIVE",
246
  "87": "FAIL",
 
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "SUCCESS",
251
+ "91": "SUCCESS",
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NOT_ALIVE",
255
+ "95": "FAIL",
256
+ "96": "SUCCESS",
257
  "97": "SUCCESS",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6380315,
268
+ 6380333,
269
+ 6380350
270
  ],
271
  "bos_token_id": 1,
272
  "eos_token_id": 2,
273
  "hidden_act": "silu",
274
  "hidden_size": 2048,
275
  "initializer_range": 0.02,
276
+ "inner_step": 4,
277
  "intermediate_size": 5632,
278
+ "last_allreduce_block": 6380215,
279
  "max_position_embeddings": 2048,
280
  "mlp_bias": false,
281
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35c1ea1c40d84addf84b27f822e1a561f9e381c0737c94a77b12030d9a4c6a88
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a448f11e307d10c1755e0f518d6bf9a730735b3c27fbee9810a4dc51c7b1d7f5
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8f19bc21c0a67847f19b47f792d627dc6c53934285893a6686c4dbb7dd4515f
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcc9d182bbf01a264b18cb2b14301126112776be6b86f56c0b397ff346d1cb0c
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2e51d110c86b8681ef77bd98139cb6c7f92d8f78d26c42c2502cc5f4f5475a6
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a5900f4226d45e55f6bd972dfdeff4f99aefa140ed3a15fc255a12e923bc534
3
  size 4400216536