zeras141a commited on
Commit
8da32e9
·
verified ·
1 Parent(s): 493ab39

Run 6. Outer Step 72. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +48 -48
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -7,7 +7,7 @@
7
  "100": "NON_PARTICIPATING",
8
  "101": "NOT_ALIVE",
9
  "102": "NON_PARTICIPATING",
10
- "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
@@ -28,53 +28,53 @@
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
- "122": "NOT_ALIVE",
32
- "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NON_PARTICIPATING",
37
- "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NON_PARTICIPATING",
44
- "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
- "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
- "141": "NOT_ALIVE",
53
- "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
  "148": "NON_PARTICIPATING",
60
- "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
- "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
- "156": "SUCCESS",
69
  "157": "NOT_ALIVE",
70
- "158": "NOT_ALIVE",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
- "160": "NOT_ALIVE",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
- "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
@@ -83,30 +83,30 @@
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
- "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
- "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
- "180": "NON_PARTICIPATING",
96
  "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
100
- "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
- "190": "SUCCESS",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
- "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
@@ -116,12 +116,12 @@
116
  "2": "SUCCESS",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
- "201": "FAIL",
120
  "202": "NON_PARTICIPATING",
121
- "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
- "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "SUCCESS",
@@ -129,7 +129,7 @@
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
- "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
@@ -140,7 +140,7 @@
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
- "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
@@ -155,15 +155,15 @@
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
- "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
- "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
- "244": "NOT_ALIVE",
167
  "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
@@ -174,9 +174,9 @@
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
177
- "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
@@ -184,7 +184,7 @@
184
  "30": "NOT_ALIVE",
185
  "31": "NOT_ALIVE",
186
  "32": "NON_PARTICIPATING",
187
- "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
  "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
@@ -200,13 +200,13 @@
200
  "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
- "48": "NON_PARTICIPATING",
204
- "49": "NON_PARTICIPATING",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
- "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
@@ -218,27 +218,27 @@
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
- "64": "NON_PARTICIPATING",
222
  "65": "NON_PARTICIPATING",
223
- "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
- "70": "SUCCESS",
229
  "71": "SUCCESS",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
- "74": "NON_PARTICIPATING",
233
- "75": "NON_PARTICIPATING",
234
- "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
- "78": "NOT_ALIVE",
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": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
@@ -250,8 +250,8 @@
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
- "93": "NON_PARTICIPATING",
254
- "94": "NON_PARTICIPATING",
255
  "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6177651,
268
- 6177668
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": 70,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6177024,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
7
  "100": "NON_PARTICIPATING",
8
  "101": "NOT_ALIVE",
9
  "102": "NON_PARTICIPATING",
10
+ "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
 
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
+ "122": "NON_PARTICIPATING",
32
+ "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NON_PARTICIPATING",
37
+ "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NON_PARTICIPATING",
44
+ "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
+ "136": "SUCCESS",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
+ "141": "NON_PARTICIPATING",
53
+ "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
+ "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
+ "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
+ "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
+ "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
+ "164": "SUCCESS",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
 
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
+ "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
+ "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
+ "180": "NOT_ALIVE",
96
  "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
100
+ "185": "NOT_ALIVE",
101
  "186": "NON_PARTICIPATING",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
 
116
  "2": "SUCCESS",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
+ "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
+ "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "SUCCESS",
 
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
+ "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
 
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
+ "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
 
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "NOT_ALIVE",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
+ "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
+ "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
 
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
177
+ "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "NOT_ALIVE",
180
  "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
 
184
  "30": "NOT_ALIVE",
185
  "31": "NOT_ALIVE",
186
  "32": "NON_PARTICIPATING",
187
+ "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
  "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
 
200
  "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
+ "48": "NOT_ALIVE",
204
+ "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
+ "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
 
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
+ "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
+ "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
+ "70": "NON_PARTICIPATING",
229
  "71": "SUCCESS",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
+ "74": "NOT_ALIVE",
233
+ "75": "NOT_ALIVE",
234
+ "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
+ "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NON_PARTICIPATING",
241
+ "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
 
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
+ "93": "NOT_ALIVE",
254
+ "94": "NOT_ALIVE",
255
  "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6177786,
268
+ 6177805
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": 6177675,
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:f69a2c29391bff92bcaa0635fc3f559d9f355849351106b4df1e5926ab68dabc
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51960f65e2d485031857bbb7d8f0f80c8629aa959651cc45a31ea05f58f63970
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32c557599dc5367689a95814a893d50f040a8a01c6c22a054541fe31e9490d82
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00cbd7bca2aaef5ab023f98a917ba0eb07652f798e797eb82b3282eeac3befd9
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b7b65b2cb145c07a6ce4d9194615ff2ec3c85e5baec6194ce536cc555b367d6
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5e961cfab613eaed6a7fd3ed061ab1b08f8a8670c62d79ab5b1f6c2ff62457b
3
  size 4400216536