snoopsy commited on
Commit
bfb7d6d
·
verified ·
1 Parent(s): 8ec31db

Run 8. Outer Step 84. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +102 -102
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -6,140 +6,140 @@
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
  "101": "NON_PARTICIPATING",
9
- "102": "NON_PARTICIPATING",
10
- "103": "SUCCESS",
11
  "104": "NON_PARTICIPATING",
12
- "105": "FAIL",
13
- "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
- "110": "FAIL",
19
- "111": "SUCCESS",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
- "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
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": "SUCCESS",
34
  "125": "NOT_ALIVE",
35
  "126": "FAIL",
36
  "127": "SUCCESS",
37
  "128": "NON_PARTICIPATING",
38
- "129": "SUCCESS",
39
  "13": "SUCCESS",
40
  "130": "SUCCESS",
41
- "131": "NOT_ALIVE",
42
  "132": "SUCCESS",
43
- "133": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
- "137": "NON_PARTICIPATING",
48
  "138": "NOT_ALIVE",
49
  "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
- "141": "NON_PARTICIPATING",
53
  "142": "SUCCESS",
54
  "143": "SUCCESS",
55
- "144": "SUCCESS",
56
- "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
- "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
65
  "153": "NOT_ALIVE",
66
  "154": "SUCCESS",
67
- "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
- "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
72
- "16": "SUCCESS",
73
  "160": "NON_PARTICIPATING",
74
- "161": "NOT_ALIVE",
75
- "162": "NON_PARTICIPATING",
76
- "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
- "165": "NON_PARTICIPATING",
79
- "166": "SUCCESS",
80
- "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
- "17": "NOT_ALIVE",
84
- "170": "SUCCESS",
85
- "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "SUCCESS",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
- "177": "NOT_ALIVE",
92
- "178": "SUCCESS",
93
- "179": "SUCCESS",
94
- "18": "NOT_ALIVE",
95
- "180": "FAIL",
96
  "181": "NON_PARTICIPATING",
97
- "182": "NOT_ALIVE",
98
- "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
- "185": "NON_PARTICIPATING",
101
- "186": "SUCCESS",
102
  "187": "NON_PARTICIPATING",
103
  "188": "SUCCESS",
104
- "189": "SUCCESS",
105
  "19": "SUCCESS",
106
- "190": "NOT_ALIVE",
107
- "191": "SUCCESS",
108
  "192": "SUCCESS",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
- "195": "SUCCESS",
112
- "196": "NON_PARTICIPATING",
113
  "197": "NOT_ALIVE",
114
- "198": "SUCCESS",
115
  "199": "FAIL",
116
  "2": "SUCCESS",
117
  "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
- "202": "NOT_ALIVE",
121
- "203": "SUCCESS",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NON_PARTICIPATING",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
- "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
- "210": "SUCCESS",
130
  "211": "SUCCESS",
131
- "212": "NON_PARTICIPATING",
132
- "213": "SUCCESS",
133
- "214": "NON_PARTICIPATING",
134
  "215": "SUCCESS",
135
- "216": "SUCCESS",
136
  "217": "SUCCESS",
137
  "218": "SUCCESS",
138
  "219": "SUCCESS",
139
- "22": "SUCCESS",
140
- "220": "NON_PARTICIPATING",
141
- "221": "NOT_ALIVE",
142
- "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
  "225": "NON_PARTICIPATING",
@@ -151,23 +151,23 @@
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "NOT_ALIVE",
155
- "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
- "237": "NOT_ALIVE",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
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": "SUCCESS",
169
  "247": "FAIL",
170
- "248": "SUCCESS",
171
  "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
@@ -175,7 +175,7 @@
175
  "252": "SUCCESS",
176
  "253": "SUCCESS",
177
  "254": "NON_PARTICIPATING",
178
- "255": "NOT_ALIVE",
179
  "26": "FAIL",
180
  "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
@@ -185,46 +185,46 @@
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NON_PARTICIPATING",
188
- "34": "SUCCESS",
189
  "35": "FAIL",
190
- "36": "SUCCESS",
191
- "37": "NON_PARTICIPATING",
192
- "38": "NON_PARTICIPATING",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
- "40": "FAIL",
196
  "41": "FAIL",
197
- "42": "NON_PARTICIPATING",
198
- "43": "FAIL",
199
- "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NOT_ALIVE",
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": "NOT_ALIVE",
210
- "54": "NON_PARTICIPATING",
211
  "55": "SUCCESS",
212
  "56": "FAIL",
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
215
- "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
- "60": "SUCCESS",
218
- "61": "NON_PARTICIPATING",
219
- "62": "SUCCESS",
220
- "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
- "67": "NOT_ALIVE",
225
- "68": "SUCCESS",
226
  "69": "SUCCESS",
227
- "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
  "72": "NON_PARTICIPATING",
@@ -232,27 +232,27 @@
232
  "74": "SUCCESS",
233
  "75": "NOT_ALIVE",
234
  "76": "SUCCESS",
235
- "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
  "79": "SUCCESS",
238
  "8": "SUCCESS",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
- "82": "NON_PARTICIPATING",
242
  "83": "SUCCESS",
243
  "84": "SUCCESS",
244
- "85": "NON_PARTICIPATING",
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": "FAIL",
254
- "94": "NON_PARTICIPATING",
255
- "95": "NON_PARTICIPATING",
256
  "96": "SUCCESS",
257
  "97": "SUCCESS",
258
  "98": "NOT_ALIVE",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6402579,
268
- 6402591
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": 94,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6401224,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
  "101": "NON_PARTICIPATING",
9
+ "102": "FAIL",
10
+ "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
+ "105": "SUCCESS",
13
+ "106": "FAIL",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
+ "110": "NON_PARTICIPATING",
19
+ "111": "NOT_ALIVE",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
+ "115": "SUCCESS",
24
  "116": "NOT_ALIVE",
25
  "117": "SUCCESS",
26
+ "118": "NOT_ALIVE",
27
+ "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
+ "120": "SUCCESS",
30
  "121": "NON_PARTICIPATING",
31
  "122": "SUCCESS",
32
+ "123": "FAIL",
33
+ "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "FAIL",
36
  "127": "SUCCESS",
37
  "128": "NON_PARTICIPATING",
38
+ "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
  "130": "SUCCESS",
41
+ "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
+ "133": "NOT_ALIVE",
44
  "134": "NON_PARTICIPATING",
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
+ "137": "FAIL",
48
  "138": "NOT_ALIVE",
49
  "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
+ "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
54
  "143": "SUCCESS",
55
+ "144": "NOT_ALIVE",
56
+ "145": "SUCCESS",
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": "NON_PARTICIPATING",
65
  "153": "NOT_ALIVE",
66
  "154": "SUCCESS",
67
+ "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
+ "157": "SUCCESS",
70
  "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
72
+ "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "SUCCESS",
75
+ "162": "SUCCESS",
76
+ "163": "SUCCESS",
77
  "164": "NON_PARTICIPATING",
78
+ "165": "SUCCESS",
79
+ "166": "NOT_ALIVE",
80
+ "167": "SUCCESS",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
+ "17": "SUCCESS",
84
+ "170": "NON_PARTICIPATING",
85
+ "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "SUCCESS",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
+ "177": "SUCCESS",
92
+ "178": "FAIL",
93
+ "179": "FAIL",
94
+ "18": "FAIL",
95
+ "180": "SUCCESS",
96
  "181": "NON_PARTICIPATING",
97
+ "182": "NON_PARTICIPATING",
98
+ "183": "SUCCESS",
99
  "184": "SUCCESS",
100
+ "185": "SUCCESS",
101
+ "186": "FAIL",
102
  "187": "NON_PARTICIPATING",
103
  "188": "SUCCESS",
104
+ "189": "NOT_ALIVE",
105
  "19": "SUCCESS",
106
+ "190": "NON_PARTICIPATING",
107
+ "191": "FAIL",
108
  "192": "SUCCESS",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
+ "195": "NON_PARTICIPATING",
112
+ "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
+ "198": "FAIL",
115
  "199": "FAIL",
116
  "2": "SUCCESS",
117
  "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
+ "202": "NON_PARTICIPATING",
121
+ "203": "FAIL",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NON_PARTICIPATING",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
+ "208": "SUCCESS",
127
  "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
+ "210": "FAIL",
130
  "211": "SUCCESS",
131
+ "212": "SUCCESS",
132
+ "213": "NON_PARTICIPATING",
133
+ "214": "NOT_ALIVE",
134
  "215": "SUCCESS",
135
+ "216": "FAIL",
136
  "217": "SUCCESS",
137
  "218": "SUCCESS",
138
  "219": "SUCCESS",
139
+ "22": "FAIL",
140
+ "220": "SUCCESS",
141
+ "221": "NON_PARTICIPATING",
142
+ "222": "SUCCESS",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
  "225": "NON_PARTICIPATING",
 
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
+ "233": "NON_PARTICIPATING",
155
+ "234": "NOT_ALIVE",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
+ "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
+ "24": "NOT_ALIVE",
162
+ "240": "FAIL",
163
  "241": "NON_PARTICIPATING",
164
+ "242": "NON_PARTICIPATING",
165
+ "243": "FAIL",
166
  "244": "SUCCESS",
167
  "245": "SUCCESS",
168
  "246": "SUCCESS",
169
  "247": "FAIL",
170
+ "248": "NOT_ALIVE",
171
  "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
 
175
  "252": "SUCCESS",
176
  "253": "SUCCESS",
177
  "254": "NON_PARTICIPATING",
178
+ "255": "SUCCESS",
179
  "26": "FAIL",
180
  "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
 
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NON_PARTICIPATING",
188
+ "34": "NON_PARTICIPATING",
189
  "35": "FAIL",
190
+ "36": "FAIL",
191
+ "37": "NOT_ALIVE",
192
+ "38": "FAIL",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
+ "40": "SUCCESS",
196
  "41": "FAIL",
197
+ "42": "SUCCESS",
198
+ "43": "SUCCESS",
199
+ "44": "FAIL",
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": "SUCCESS",
208
  "52": "SUCCESS",
209
  "53": "NOT_ALIVE",
210
+ "54": "SUCCESS",
211
  "55": "SUCCESS",
212
  "56": "FAIL",
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
215
+ "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
+ "61": "FAIL",
219
+ "62": "NOT_ALIVE",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
+ "67": "NON_PARTICIPATING",
225
+ "68": "NON_PARTICIPATING",
226
  "69": "SUCCESS",
227
+ "7": "FAIL",
228
  "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
  "72": "NON_PARTICIPATING",
 
232
  "74": "SUCCESS",
233
  "75": "NOT_ALIVE",
234
  "76": "SUCCESS",
235
+ "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "SUCCESS",
238
  "8": "SUCCESS",
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": "NOT_ALIVE",
248
+ "89": "SUCCESS",
249
  "9": "NOT_ALIVE",
250
+ "90": "SUCCESS",
251
+ "91": "NOT_ALIVE",
252
  "92": "SUCCESS",
253
+ "93": "NON_PARTICIPATING",
254
+ "94": "SUCCESS",
255
+ "95": "FAIL",
256
  "96": "SUCCESS",
257
  "97": "SUCCESS",
258
  "98": "NOT_ALIVE",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6402660,
268
+ 6402677
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": 5,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6402610,
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 sha256:5cba17e7230affe5f4cddb78f185fc476df556d82b80014756406798c40e6be1
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a5852d4281fb08079960dc17602b3bce4d8174226e2ac9c82c793e197f2ef63
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeac209ef4ab6566eb43dd06434d85fce3b5c83a677dcf775be92b213f36e95f
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b78cefff0ad5ca0c53c3d784842f4e53295c199ba3c703f64c4490f029ca9154
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c85a6308132bf58c210f30161ebc6ec225fb7e56c4f21fe0cf3ff14dd8e0e7f
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f10f85fc4c7c6004052c65b6809ee189b241d969732a99f879d867fe460147b
3
  size 4400216536