snoopsy commited on
Commit
ab574cc
·
verified ·
1 Parent(s): 41d82a4

Run 8. Outer Step 55. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +87 -87
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -3,57 +3,57 @@
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
- "10": "FAIL",
7
  "100": "NOT_ALIVE",
8
  "101": "SUCCESS",
9
  "102": "NON_PARTICIPATING",
10
- "103": "NON_PARTICIPATING",
11
- "104": "NOT_ALIVE",
12
  "105": "NOT_ALIVE",
13
- "106": "FAIL",
14
  "107": "SUCCESS",
15
  "108": "SUCCESS",
16
  "109": "NON_PARTICIPATING",
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": "NOT_ALIVE",
25
  "117": "SUCCESS",
26
  "118": "NOT_ALIVE",
27
  "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "SUCCESS",
31
- "122": "SUCCESS",
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": "SUCCESS",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
- "133": "FAIL",
44
  "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
  "136": "SUCCESS",
47
- "137": "FAIL",
48
  "138": "NOT_ALIVE",
49
- "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
- "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
- "142": "NON_PARTICIPATING",
54
  "143": "SUCCESS",
55
- "144": "SUCCESS",
56
- "145": "FAIL",
57
  "146": "NON_PARTICIPATING",
58
  "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
@@ -62,9 +62,9 @@
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
  "152": "SUCCESS",
65
- "153": "NOT_ALIVE",
66
  "154": "NON_PARTICIPATING",
67
- "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
@@ -72,16 +72,16 @@
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "FAIL",
75
- "162": "NON_PARTICIPATING",
76
  "163": "SUCCESS",
77
  "164": "SUCCESS",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
- "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
  "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
- "170": "NON_PARTICIPATING",
85
  "171": "SUCCESS",
86
  "172": "FAIL",
87
  "173": "SUCCESS",
@@ -93,20 +93,20 @@
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": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
- "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
- "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
- "193": "FAIL",
110
  "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
  "196": "SUCCESS",
@@ -115,59 +115,59 @@
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
- "200": "FAIL",
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": "SUCCESS",
133
  "214": "SUCCESS",
134
  "215": "SUCCESS",
135
- "216": "NOT_ALIVE",
136
- "217": "FAIL",
137
  "218": "SUCCESS",
138
  "219": "FAIL",
139
- "22": "SUCCESS",
140
- "220": "SUCCESS",
141
- "221": "FAIL",
142
  "222": "SUCCESS",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
- "225": "NON_PARTICIPATING",
146
  "226": "NOT_ALIVE",
147
- "227": "NON_PARTICIPATING",
148
- "228": "FAIL",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
- "230": "NON_PARTICIPATING",
152
- "231": "NOT_ALIVE",
153
  "232": "SUCCESS",
154
- "233": "SUCCESS",
155
- "234": "NON_PARTICIPATING",
156
- "235": "FAIL",
157
- "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
- "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
- "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
- "241": "NOT_ALIVE",
164
- "242": "FAIL",
165
  "243": "NON_PARTICIPATING",
166
  "244": "SUCCESS",
167
- "245": "FAIL",
168
  "246": "NON_PARTICIPATING",
169
  "247": "SUCCESS",
170
- "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
@@ -175,42 +175,42 @@
175
  "252": "SUCCESS",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
- "255": "NOT_ALIVE",
179
- "26": "SUCCESS",
180
  "27": "SUCCESS",
181
- "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
- "30": "SUCCESS",
185
- "31": "NOT_ALIVE",
186
- "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "FAIL",
190
- "36": "SUCCESS",
191
- "37": "SUCCESS",
192
  "38": "NOT_ALIVE",
193
- "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "SUCCESS",
197
- "42": "FAIL",
198
- "43": "NON_PARTICIPATING",
199
  "44": "FAIL",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
- "5": "SUCCESS",
206
  "50": "FAIL",
207
- "51": "FAIL",
208
  "52": "SUCCESS",
209
- "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
- "55": "NON_PARTICIPATING",
212
- "56": "SUCCESS",
213
- "57": "NON_PARTICIPATING",
214
  "58": "SUCCESS",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
@@ -222,28 +222,28 @@
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
- "68": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
  "7": "SUCCESS",
228
  "70": "SUCCESS",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
- "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
- "77": "FAIL",
236
- "78": "FAIL",
237
- "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
- "80": "NOT_ALIVE",
240
  "81": "NON_PARTICIPATING",
241
- "82": "NOT_ALIVE",
242
- "83": "NON_PARTICIPATING",
243
  "84": "SUCCESS",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
- "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
@@ -252,10 +252,10 @@
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NOT_ALIVE",
255
- "95": "FAIL",
256
- "96": "NOT_ALIVE",
257
  "97": "SUCCESS",
258
- "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6378875,
268
- 6378885
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": 139,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6378225,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
+ "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "SUCCESS",
9
  "102": "NON_PARTICIPATING",
10
+ "103": "NOT_ALIVE",
11
+ "104": "NON_PARTICIPATING",
12
  "105": "NOT_ALIVE",
13
+ "106": "SUCCESS",
14
  "107": "SUCCESS",
15
  "108": "SUCCESS",
16
  "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
+ "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
+ "112": "NON_PARTICIPATING",
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",
31
+ "122": "FAIL",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "FAIL",
36
  "127": "SUCCESS",
37
+ "128": "SUCCESS",
38
+ "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
+ "130": "FAIL",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
+ "133": "SUCCESS",
44
  "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
  "136": "SUCCESS",
47
+ "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
+ "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
+ "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
+ "142": "FAIL",
54
  "143": "SUCCESS",
55
+ "144": "NON_PARTICIPATING",
56
+ "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
  "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
 
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
  "152": "SUCCESS",
65
+ "153": "NON_PARTICIPATING",
66
  "154": "NON_PARTICIPATING",
67
+ "155": "FAIL",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
 
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "FAIL",
75
+ "162": "NOT_ALIVE",
76
  "163": "SUCCESS",
77
  "164": "SUCCESS",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
+ "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
+ "170": "SUCCESS",
85
  "171": "SUCCESS",
86
  "172": "FAIL",
87
  "173": "SUCCESS",
 
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
+ "181": "NOT_ALIVE",
97
  "182": "SUCCESS",
98
+ "183": "SUCCESS",
99
  "184": "SUCCESS",
100
+ "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
+ "19": "FAIL",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "FAIL",
108
  "192": "NOT_ALIVE",
109
+ "193": "SUCCESS",
110
  "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
  "196": "SUCCESS",
 
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "NON_PARTICIPATING",
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": "SUCCESS",
128
+ "21": "NOT_ALIVE",
129
+ "210": "NOT_ALIVE",
130
  "211": "SUCCESS",
131
  "212": "SUCCESS",
132
  "213": "SUCCESS",
133
  "214": "SUCCESS",
134
  "215": "SUCCESS",
135
+ "216": "FAIL",
136
+ "217": "SUCCESS",
137
  "218": "SUCCESS",
138
  "219": "FAIL",
139
+ "22": "FAIL",
140
+ "220": "NON_PARTICIPATING",
141
+ "221": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
+ "233": "NOT_ALIVE",
155
+ "234": "FAIL",
156
+ "235": "SUCCESS",
157
+ "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
+ "24": "FAIL",
162
  "240": "NON_PARTICIPATING",
163
+ "241": "NON_PARTICIPATING",
164
+ "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "SUCCESS",
167
+ "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
  "247": "SUCCESS",
170
+ "248": "FAIL",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
 
175
  "252": "SUCCESS",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
+ "255": "NON_PARTICIPATING",
179
+ "26": "FAIL",
180
  "27": "SUCCESS",
181
+ "28": "SUCCESS",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
+ "30": "FAIL",
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": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "SUCCESS",
197
+ "42": "SUCCESS",
198
+ "43": "NOT_ALIVE",
199
  "44": "FAIL",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "FAIL",
206
  "50": "FAIL",
207
+ "51": "SUCCESS",
208
  "52": "SUCCESS",
209
+ "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
211
+ "55": "FAIL",
212
+ "56": "FAIL",
213
+ "57": "FAIL",
214
  "58": "SUCCESS",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
 
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "SUCCESS",
228
  "70": "SUCCESS",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
+ "74": "FAIL",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
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": "SUCCESS",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
+ "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "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": "NOT_ALIVE",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6378962,
268
+ 6378971
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": 6378907,
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 sha256:778890508a5548657cd7b5b1f4b04de6bd55bce383f85309360b33df81d82a97
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e188cdc578ffa66e9931ff27888a7b92d7f5a23ac2001e8b8c02dc6a1907fd56
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ffc878227e647bc952ff3b6a38770ee6d39105d978f45e937e70feef0337a42
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ef7db7cac3f7246d7790dd04fcef3da4154b428bcf57b5f292900a536ccffc
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89592e6a12b3ba147111dc737edd9a9f3f7a4d12f3065ba16a54c09cd2ec4e9a
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1251ff3fd71b5f1020c25223839f4c2eab0eeb67f42070aa0c4ceee303ec0c5
3
  size 4400216536