subhan1122 commited on
Commit
29e47a2
·
verified ·
1 Parent(s): 2e82c68

Run 8. Outer Step 69. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +154 -154
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -1,260 +1,260 @@
1
  {
2
- "_name_or_path": "Subhan1123/M2",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "FAIL",
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
- "101": "FAIL",
9
- "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
- "106": "SUCCESS",
14
- "107": "NON_PARTICIPATING",
15
  "108": "FAIL",
16
- "109": "FAIL",
17
- "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
- "112": "FAIL",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
- "115": "FAIL",
24
  "116": "NON_PARTICIPATING",
25
- "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
- "119": "FAIL",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
- "121": "FAIL",
31
- "122": "FAIL",
32
- "123": "FAIL",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "FAIL",
36
- "127": "FAIL",
37
- "128": "SUCCESS",
38
- "129": "NON_PARTICIPATING",
39
- "13": "FAIL",
40
- "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
  "132": "FAIL",
43
- "133": "NON_PARTICIPATING",
44
- "134": "SUCCESS",
45
- "135": "FAIL",
46
- "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NOT_ALIVE",
49
- "139": "FAIL",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
- "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
- "144": "NON_PARTICIPATING",
56
- "145": "SUCCESS",
57
- "146": "NON_PARTICIPATING",
58
- "147": "FAIL",
59
  "148": "NON_PARTICIPATING",
60
- "149": "FAIL",
61
  "15": "FAIL",
62
- "150": "FAIL",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
- "154": "NOT_ALIVE",
67
- "155": "FAIL",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NON_PARTICIPATING",
71
- "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
- "160": "NON_PARTICIPATING",
74
- "161": "NOT_ALIVE",
75
- "162": "NOT_ALIVE",
76
  "163": "SUCCESS",
77
- "164": "FAIL",
78
- "165": "FAIL",
79
- "166": "NOT_ALIVE",
80
- "167": "FAIL",
81
  "168": "SUCCESS",
82
- "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
- "170": "NON_PARTICIPATING",
85
  "171": "SUCCESS",
86
  "172": "FAIL",
87
- "173": "SUCCESS",
88
- "174": "NON_PARTICIPATING",
89
- "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
- "177": "FAIL",
92
  "178": "FAIL",
93
- "179": "FAIL",
94
- "18": "NOT_ALIVE",
95
- "180": "FAIL",
96
  "181": "SUCCESS",
97
- "182": "NOT_ALIVE",
98
  "183": "SUCCESS",
99
- "184": "FAIL",
100
- "185": "SUCCESS",
101
- "186": "SUCCESS",
102
  "187": "NON_PARTICIPATING",
103
  "188": "SUCCESS",
104
  "189": "NON_PARTICIPATING",
105
- "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "FAIL",
108
- "192": "FAIL",
109
- "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
  "196": "FAIL",
113
  "197": "NON_PARTICIPATING",
114
- "198": "NON_PARTICIPATING",
115
- "199": "FAIL",
116
  "2": "NOT_ALIVE",
117
- "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
- "202": "FAIL",
121
- "203": "FAIL",
122
- "204": "SUCCESS",
123
- "205": "FAIL",
124
- "206": "FAIL",
125
  "207": "NON_PARTICIPATING",
126
- "208": "FAIL",
127
- "209": "NON_PARTICIPATING",
128
- "21": "FAIL",
129
  "210": "NON_PARTICIPATING",
130
- "211": "FAIL",
131
- "212": "NON_PARTICIPATING",
132
- "213": "FAIL",
133
  "214": "FAIL",
134
  "215": "SUCCESS",
135
  "216": "FAIL",
136
  "217": "SUCCESS",
137
- "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "SUCCESS",
140
- "220": "NON_PARTICIPATING",
141
- "221": "FAIL",
142
- "222": "SUCCESS",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
- "225": "FAIL",
146
- "226": "NON_PARTICIPATING",
147
- "227": "NON_PARTICIPATING",
148
- "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
- "23": "NOT_ALIVE",
151
- "230": "FAIL",
152
- "231": "NON_PARTICIPATING",
153
- "232": "NOT_ALIVE",
154
- "233": "FAIL",
155
  "234": "SUCCESS",
156
- "235": "NOT_ALIVE",
157
- "236": "SUCCESS",
158
- "237": "NOT_ALIVE",
159
- "238": "FAIL",
160
- "239": "NON_PARTICIPATING",
161
- "24": "FAIL",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
- "242": "FAIL",
165
- "243": "NOT_ALIVE",
166
- "244": "FAIL",
167
  "245": "FAIL",
168
  "246": "NON_PARTICIPATING",
169
- "247": "SUCCESS",
170
- "248": "NON_PARTICIPATING",
171
- "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
- "252": "FAIL",
176
- "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "FAIL",
180
- "27": "FAIL",
181
- "28": "FAIL",
182
  "29": "SUCCESS",
183
- "3": "SUCCESS",
184
  "30": "FAIL",
185
- "31": "FAIL",
186
- "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
- "34": "NON_PARTICIPATING",
189
- "35": "SUCCESS",
190
- "36": "FAIL",
191
- "37": "SUCCESS",
192
- "38": "NON_PARTICIPATING",
193
- "39": "FAIL",
194
  "4": "NOT_ALIVE",
195
- "40": "FAIL",
196
- "41": "FAIL",
197
- "42": "FAIL",
198
  "43": "NON_PARTICIPATING",
199
  "44": "SUCCESS",
200
- "45": "NOT_ALIVE",
201
- "46": "FAIL",
202
- "47": "SUCCESS",
203
- "48": "NOT_ALIVE",
204
  "49": "FAIL",
205
- "5": "FAIL",
206
- "50": "FAIL",
207
  "51": "NON_PARTICIPATING",
208
- "52": "NON_PARTICIPATING",
209
- "53": "FAIL",
210
- "54": "FAIL",
211
  "55": "SUCCESS",
212
- "56": "FAIL",
213
- "57": "NON_PARTICIPATING",
214
- "58": "NOT_ALIVE",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "FAIL",
218
- "61": "NON_PARTICIPATING",
219
- "62": "FAIL",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
- "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
- "67": "NON_PARTICIPATING",
225
  "68": "SUCCESS",
226
- "69": "NON_PARTICIPATING",
227
  "7": "FAIL",
228
- "70": "FAIL",
229
- "71": "NON_PARTICIPATING",
230
  "72": "FAIL",
231
  "73": "NON_PARTICIPATING",
232
- "74": "SUCCESS",
233
- "75": "FAIL",
234
- "76": "NON_PARTICIPATING",
235
- "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
- "79": "FAIL",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
- "82": "FAIL",
242
- "83": "NOT_ALIVE",
243
- "84": "NON_PARTICIPATING",
244
- "85": "NON_PARTICIPATING",
245
- "86": "NOT_ALIVE",
246
- "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "FAIL",
251
  "91": "NOT_ALIVE",
252
- "92": "FAIL",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "FAIL",
256
- "96": "NON_PARTICIPATING",
257
- "97": "FAIL",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6392482,
268
- 6392518
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": 85,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6386584,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
+ "101": "SUCCESS",
9
+ "102": "FAIL",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
+ "106": "FAIL",
14
+ "107": "SUCCESS",
15
  "108": "FAIL",
16
+ "109": "NON_PARTICIPATING",
17
+ "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
+ "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
+ "115": "SUCCESS",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "SUCCESS",
26
  "118": "NON_PARTICIPATING",
27
+ "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
+ "121": "NON_PARTICIPATING",
31
+ "122": "SUCCESS",
32
+ "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "FAIL",
36
+ "127": "SUCCESS",
37
+ "128": "FAIL",
38
+ "129": "NOT_ALIVE",
39
+ "13": "SUCCESS",
40
+ "130": "FAIL",
41
  "131": "NON_PARTICIPATING",
42
  "132": "FAIL",
43
+ "133": "SUCCESS",
44
+ "134": "NOT_ALIVE",
45
+ "135": "NOT_ALIVE",
46
+ "136": "SUCCESS",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NOT_ALIVE",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
+ "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
+ "144": "SUCCESS",
56
+ "145": "FAIL",
57
+ "146": "NOT_ALIVE",
58
+ "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "NON_PARTICIPATING",
61
  "15": "FAIL",
62
+ "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
+ "154": "SUCCESS",
67
+ "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "FAIL",
71
+ "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
+ "160": "NOT_ALIVE",
74
+ "161": "SUCCESS",
75
+ "162": "FAIL",
76
  "163": "SUCCESS",
77
+ "164": "SUCCESS",
78
+ "165": "SUCCESS",
79
+ "166": "NON_PARTICIPATING",
80
+ "167": "SUCCESS",
81
  "168": "SUCCESS",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
+ "170": "SUCCESS",
85
  "171": "SUCCESS",
86
  "172": "FAIL",
87
+ "173": "NON_PARTICIPATING",
88
+ "174": "FAIL",
89
+ "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
+ "177": "NON_PARTICIPATING",
92
  "178": "FAIL",
93
+ "179": "SUCCESS",
94
+ "18": "SUCCESS",
95
+ "180": "SUCCESS",
96
  "181": "SUCCESS",
97
+ "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
+ "184": "NON_PARTICIPATING",
100
+ "185": "FAIL",
101
+ "186": "FAIL",
102
  "187": "NON_PARTICIPATING",
103
  "188": "SUCCESS",
104
  "189": "NON_PARTICIPATING",
105
+ "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
  "191": "FAIL",
108
+ "192": "NON_PARTICIPATING",
109
+ "193": "FAIL",
110
  "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
  "196": "FAIL",
113
  "197": "NON_PARTICIPATING",
114
+ "198": "NOT_ALIVE",
115
+ "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
+ "20": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
+ "202": "NOT_ALIVE",
121
+ "203": "NON_PARTICIPATING",
122
+ "204": "NON_PARTICIPATING",
123
+ "205": "NON_PARTICIPATING",
124
+ "206": "NON_PARTICIPATING",
125
  "207": "NON_PARTICIPATING",
126
+ "208": "SUCCESS",
127
+ "209": "SUCCESS",
128
+ "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "NON_PARTICIPATING",
131
+ "212": "SUCCESS",
132
+ "213": "SUCCESS",
133
  "214": "FAIL",
134
  "215": "SUCCESS",
135
  "216": "FAIL",
136
  "217": "SUCCESS",
137
+ "218": "FAIL",
138
  "219": "NON_PARTICIPATING",
139
  "22": "SUCCESS",
140
+ "220": "SUCCESS",
141
+ "221": "NON_PARTICIPATING",
142
+ "222": "NOT_ALIVE",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "NON_PARTICIPATING",
146
+ "226": "NOT_ALIVE",
147
+ "227": "NOT_ALIVE",
148
+ "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
150
+ "23": "SUCCESS",
151
+ "230": "SUCCESS",
152
+ "231": "NOT_ALIVE",
153
+ "232": "SUCCESS",
154
+ "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
+ "235": "NON_PARTICIPATING",
157
+ "236": "FAIL",
158
+ "237": "NON_PARTICIPATING",
159
+ "238": "NON_PARTICIPATING",
160
+ "239": "FAIL",
161
+ "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
+ "242": "SUCCESS",
165
+ "243": "NON_PARTICIPATING",
166
+ "244": "SUCCESS",
167
  "245": "FAIL",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "FAIL",
170
+ "248": "SUCCESS",
171
+ "249": "FAIL",
172
  "25": "SUCCESS",
173
+ "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
+ "252": "SUCCESS",
176
+ "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "FAIL",
180
+ "27": "SUCCESS",
181
+ "28": "SUCCESS",
182
  "29": "SUCCESS",
183
+ "3": "NOT_ALIVE",
184
  "30": "FAIL",
185
+ "31": "NON_PARTICIPATING",
186
+ "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
+ "34": "SUCCESS",
189
+ "35": "FAIL",
190
+ "36": "NON_PARTICIPATING",
191
+ "37": "NOT_ALIVE",
192
+ "38": "SUCCESS",
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": "NON_PARTICIPATING",
201
+ "46": "NON_PARTICIPATING",
202
+ "47": "FAIL",
203
+ "48": "NON_PARTICIPATING",
204
  "49": "FAIL",
205
+ "5": "SUCCESS",
206
+ "50": "SUCCESS",
207
  "51": "NON_PARTICIPATING",
208
+ "52": "SUCCESS",
209
+ "53": "SUCCESS",
210
+ "54": "NON_PARTICIPATING",
211
  "55": "SUCCESS",
212
+ "56": "SUCCESS",
213
+ "57": "SUCCESS",
214
+ "58": "FAIL",
215
+ "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
+ "61": "FAIL",
219
+ "62": "SUCCESS",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
+ "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
+ "67": "NOT_ALIVE",
225
  "68": "SUCCESS",
226
+ "69": "SUCCESS",
227
  "7": "FAIL",
228
+ "70": "NOT_ALIVE",
229
+ "71": "NOT_ALIVE",
230
  "72": "FAIL",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "FAIL",
233
+ "75": "NON_PARTICIPATING",
234
+ "76": "SUCCESS",
235
+ "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
+ "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
+ "82": "SUCCESS",
242
+ "83": "SUCCESS",
243
+ "84": "NOT_ALIVE",
244
+ "85": "FAIL",
245
+ "86": "NON_PARTICIPATING",
246
+ "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "FAIL",
251
  "91": "NOT_ALIVE",
252
+ "92": "SUCCESS",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "FAIL",
256
+ "96": "FAIL",
257
+ "97": "SUCCESS",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6392617,
268
+ 6392646
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": 9,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6392575,
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 sha256:0fbef9e93aac3ea94940462c55bd8cf4186386885fb8c2bde33ea729e247e3e3
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f02ced58e43d238842450a69819d025633da491a493848f9828964c80c315483
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:899b8065837f2105c53baabb6a11d2fc631ceb605d1a2991b6f3027bd46c5ba4
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4764c0a692948e4deb1a3c41f922c3f0c8f5c4660b5c3fc39e9c0642d8d8c6ec
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a418ad9189c2b4b4330c42e64f91c6d8af84edf552e322e5661ab455749a61d
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d144d04016a9dcb242fd05f7de90f9a82336e0556efc12a7d59e16ced209c5f
3
  size 4400216536