zeras141a commited on
Commit
08c0429
·
verified ·
1 Parent(s): b6fe7d6

Run 8. Outer Step 80. Inner Step 4.

Browse files
Files changed (4) hide show
  1. config.json +105 -106
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -7,209 +7,209 @@
7
  "100": "NON_PARTICIPATING",
8
  "101": "NON_PARTICIPATING",
9
  "102": "SUCCESS",
10
- "103": "SUCCESS",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
- "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "SUCCESS",
16
- "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "SUCCESS",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
- "114": "NON_PARTICIPATING",
23
- "115": "FAIL",
24
  "116": "NOT_ALIVE",
25
  "117": "SUCCESS",
26
- "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "FAIL",
30
- "121": "NOT_ALIVE",
31
- "122": "NOT_ALIVE",
32
- "123": "NOT_ALIVE",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "FAIL",
36
- "127": "FAIL",
37
  "128": "SUCCESS",
38
- "129": "SUCCESS",
39
  "13": "SUCCESS",
40
- "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
  "133": "SUCCESS",
44
- "134": "SUCCESS",
45
- "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "FAIL",
48
- "138": "FAIL",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
- "143": "NON_PARTICIPATING",
55
- "144": "NON_PARTICIPATING",
56
- "145": "SUCCESS",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
- "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
- "150": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
71
- "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
- "160": "NON_PARTICIPATING",
74
- "161": "FAIL",
75
- "162": "SUCCESS",
76
  "163": "SUCCESS",
77
  "164": "SUCCESS",
78
- "165": "NON_PARTICIPATING",
79
- "166": "SUCCESS",
80
- "167": "NOT_ALIVE",
81
  "168": "SUCCESS",
82
- "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
  "171": "SUCCESS",
86
- "172": "FAIL",
87
  "173": "SUCCESS",
88
- "174": "NOT_ALIVE",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
- "178": "SUCCESS",
93
- "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
- "180": "SUCCESS",
96
- "181": "SUCCESS",
97
- "182": "NOT_ALIVE",
98
  "183": "SUCCESS",
99
  "184": "SUCCESS",
100
  "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
- "187": "NON_PARTICIPATING",
103
  "188": "SUCCESS",
104
- "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
- "190": "NOT_ALIVE",
107
  "191": "FAIL",
108
  "192": "SUCCESS",
109
- "193": "FAIL",
110
  "194": "NON_PARTICIPATING",
111
- "195": "NON_PARTICIPATING",
112
- "196": "NON_PARTICIPATING",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
- "199": "FAIL",
116
  "2": "SUCCESS",
117
- "20": "SUCCESS",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "FAIL",
122
- "204": "SUCCESS",
123
- "205": "NON_PARTICIPATING",
124
- "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
- "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
- "210": "NOT_ALIVE",
130
  "211": "FAIL",
131
- "212": "SUCCESS",
132
- "213": "FAIL",
133
- "214": "FAIL",
134
- "215": "SUCCESS",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
- "218": "SUCCESS",
138
- "219": "SUCCESS",
139
  "22": "SUCCESS",
140
  "220": "SUCCESS",
141
  "221": "NON_PARTICIPATING",
142
- "222": "SUCCESS",
143
- "223": "NON_PARTICIPATING",
144
- "224": "NON_PARTICIPATING",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
- "229": "SUCCESS",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
- "235": "FAIL",
157
  "236": "NON_PARTICIPATING",
158
- "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
- "240": "FAIL",
163
- "241": "SUCCESS",
164
- "242": "NON_PARTICIPATING",
165
- "243": "FAIL",
166
  "244": "SUCCESS",
167
- "245": "FAIL",
168
- "246": "SUCCESS",
169
  "247": "SUCCESS",
170
- "248": "SUCCESS",
171
- "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NOT_ALIVE",
174
- "251": "NON_PARTICIPATING",
175
  "252": "SUCCESS",
176
  "253": "SUCCESS",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
  "26": "SUCCESS",
180
- "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
- "33": "NON_PARTICIPATING",
188
  "34": "SUCCESS",
189
- "35": "NOT_ALIVE",
190
- "36": "NON_PARTICIPATING",
191
- "37": "NOT_ALIVE",
192
- "38": "FAIL",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
- "41": "FAIL",
197
- "42": "FAIL",
198
- "43": "NOT_ALIVE",
199
- "44": "FAIL",
200
  "45": "NON_PARTICIPATING",
201
- "46": "SUCCESS",
202
- "47": "SUCCESS",
203
- "48": "SUCCESS",
204
  "49": "NON_PARTICIPATING",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
- "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "SUCCESS",
212
- "56": "SUCCESS",
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
215
  "59": "NON_PARTICIPATING",
@@ -217,9 +217,9 @@
217
  "60": "SUCCESS",
218
  "61": "SUCCESS",
219
  "62": "SUCCESS",
220
- "63": "SUCCESS",
221
- "64": "NOT_ALIVE",
222
- "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "SUCCESS",
@@ -229,31 +229,31 @@
229
  "71": "SUCCESS",
230
  "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
- "74": "SUCCESS",
233
  "75": "NOT_ALIVE",
234
  "76": "SUCCESS",
235
- "77": "SUCCESS",
236
  "78": "FAIL",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
- "80": "SUCCESS",
240
  "81": "NON_PARTICIPATING",
241
  "82": "SUCCESS",
242
  "83": "SUCCESS",
243
- "84": "FAIL",
244
  "85": "SUCCESS",
245
  "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
- "90": "SUCCESS",
251
  "91": "NON_PARTICIPATING",
252
  "92": "SUCCESS",
253
- "93": "SUCCESS",
254
  "94": "NON_PARTICIPATING",
255
- "95": "SUCCESS",
256
- "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NOT_ALIVE",
259
  "99": "NON_PARTICIPATING"
@@ -264,18 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6398929,
268
- 6398944,
269
- 6398956
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": 48,
277
  "intermediate_size": 5632,
278
- "last_allreduce_block": 6398628,
279
  "max_position_embeddings": 2048,
280
  "mlp_bias": false,
281
  "model_type": "llama",
 
7
  "100": "NON_PARTICIPATING",
8
  "101": "NON_PARTICIPATING",
9
  "102": "SUCCESS",
10
+ "103": "FAIL",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
+ "106": "SUCCESS",
14
  "107": "NON_PARTICIPATING",
15
  "108": "SUCCESS",
16
+ "109": "FAIL",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "SUCCESS",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
+ "114": "NOT_ALIVE",
23
+ "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
  "117": "SUCCESS",
26
+ "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "FAIL",
30
+ "121": "NON_PARTICIPATING",
31
+ "122": "SUCCESS",
32
+ "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "FAIL",
36
+ "127": "NON_PARTICIPATING",
37
  "128": "SUCCESS",
38
+ "129": "FAIL",
39
  "13": "SUCCESS",
40
+ "130": "FAIL",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
  "133": "SUCCESS",
44
+ "134": "FAIL",
45
+ "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "FAIL",
48
+ "138": "SUCCESS",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
+ "143": "FAIL",
55
+ "144": "SUCCESS",
56
+ "145": "FAIL",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
+ "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
+ "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
+ "154": "NON_PARTICIPATING",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
+ "157": "FAIL",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "SUCCESS",
72
  "16": "SUCCESS",
73
+ "160": "SUCCESS",
74
+ "161": "SUCCESS",
75
+ "162": "NON_PARTICIPATING",
76
  "163": "SUCCESS",
77
  "164": "SUCCESS",
78
+ "165": "FAIL",
79
+ "166": "FAIL",
80
+ "167": "SUCCESS",
81
  "168": "SUCCESS",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
  "171": "SUCCESS",
86
+ "172": "NOT_ALIVE",
87
  "173": "SUCCESS",
88
+ "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
+ "178": "NOT_ALIVE",
93
+ "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
+ "180": "NON_PARTICIPATING",
96
+ "181": "NON_PARTICIPATING",
97
+ "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
  "184": "SUCCESS",
100
  "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
+ "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
+ "189": "FAIL",
105
  "19": "NOT_ALIVE",
106
+ "190": "NON_PARTICIPATING",
107
  "191": "FAIL",
108
  "192": "SUCCESS",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
+ "195": "SUCCESS",
112
+ "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
+ "199": "NON_PARTICIPATING",
116
  "2": "SUCCESS",
117
+ "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "SUCCESS",
122
+ "204": "FAIL",
123
+ "205": "NOT_ALIVE",
124
+ "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
+ "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
+ "210": "SUCCESS",
130
  "211": "FAIL",
131
+ "212": "NON_PARTICIPATING",
132
+ "213": "SUCCESS",
133
+ "214": "NON_PARTICIPATING",
134
+ "215": "FAIL",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
+ "218": "NOT_ALIVE",
138
+ "219": "NOT_ALIVE",
139
  "22": "SUCCESS",
140
  "220": "SUCCESS",
141
  "221": "NON_PARTICIPATING",
142
+ "222": "NON_PARTICIPATING",
143
+ "223": "NOT_ALIVE",
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": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
+ "233": "SUCCESS",
155
  "234": "SUCCESS",
156
+ "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "NOT_ALIVE",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
+ "240": "NON_PARTICIPATING",
163
+ "241": "NON_PARTICIPATING",
164
+ "242": "SUCCESS",
165
+ "243": "SUCCESS",
166
  "244": "SUCCESS",
167
+ "245": "SUCCESS",
168
+ "246": "FAIL",
169
  "247": "SUCCESS",
170
+ "248": "FAIL",
171
+ "249": "FAIL",
172
  "25": "SUCCESS",
173
+ "250": "SUCCESS",
174
+ "251": "FAIL",
175
  "252": "SUCCESS",
176
  "253": "SUCCESS",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
  "26": "SUCCESS",
180
+ "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
+ "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
+ "35": "SUCCESS",
190
+ "36": "FAIL",
191
+ "37": "NON_PARTICIPATING",
192
+ "38": "NON_PARTICIPATING",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "SUCCESS",
197
+ "42": "SUCCESS",
198
+ "43": "NON_PARTICIPATING",
199
+ "44": "SUCCESS",
200
  "45": "NON_PARTICIPATING",
201
+ "46": "NOT_ALIVE",
202
+ "47": "NON_PARTICIPATING",
203
+ "48": "FAIL",
204
  "49": "NON_PARTICIPATING",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
+ "53": "NOT_ALIVE",
210
  "54": "NON_PARTICIPATING",
211
  "55": "SUCCESS",
212
+ "56": "FAIL",
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
215
  "59": "NON_PARTICIPATING",
 
217
  "60": "SUCCESS",
218
  "61": "SUCCESS",
219
  "62": "SUCCESS",
220
+ "63": "NON_PARTICIPATING",
221
+ "64": "NON_PARTICIPATING",
222
+ "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "SUCCESS",
 
229
  "71": "SUCCESS",
230
  "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "NON_PARTICIPATING",
233
  "75": "NOT_ALIVE",
234
  "76": "SUCCESS",
235
+ "77": "NON_PARTICIPATING",
236
  "78": "FAIL",
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": "SUCCESS",
245
  "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
+ "90": "FAIL",
251
  "91": "NON_PARTICIPATING",
252
  "92": "SUCCESS",
253
+ "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
+ "95": "NOT_ALIVE",
256
+ "96": "SUCCESS",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NOT_ALIVE",
259
  "99": "NON_PARTICIPATING"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6400176,
268
+ 6400189
 
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": 6399900,
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:f1b9d01dd9d97e4bf0fe763b7a947a5be0c667731dda4c9c9aa73b2578ee33c4
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5326b8f8055e9ca13ea6d15f7f125eeefbfe06de1dd92b25dced106dc0460f6e
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2c22a16cd4a646706e6c923744d5f348a83a95570bc1e18c242f51540efbf27
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ff7213638342d93449ca1c2461b3bb5fec53e609c5532e7f9f935db3331b95
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9cd82df7a6471736dcfc82fbce58e3066fe7e8b9474f0bc93ab1114b6b5b16b
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7f1512a76120f997cf9b2af40a78ab7388a992bf18abbd3e42032c6eb3a876
3
  size 4400216536