zeras141a commited on
Commit
fb97889
·
verified ·
1 Parent(s): 34a4d58

Run 6. Outer Step 89. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +50 -50
  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",
@@ -16,20 +16,20 @@
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
- "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
- "113": "SUCCESS",
22
- "114": "NOT_ALIVE",
23
- "115": "NOT_ALIVE",
24
  "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
- "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
- "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
@@ -40,27 +40,27 @@
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
- "133": "NON_PARTICIPATING",
44
- "134": "SUCCESS",
45
  "135": "SUCCESS",
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": "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": "NOT_ALIVE",
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": "NON_PARTICIPATING",
@@ -73,18 +73,18 @@
73
  "160": "NON_PARTICIPATING",
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",
81
- "168": "NOT_ALIVE",
82
- "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
- "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
@@ -99,27 +99,27 @@
99
  "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
102
- "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
- "192": "NON_PARTICIPATING",
109
- "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
- "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
- "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
- "200": "SUCCESS",
119
  "201": "SUCCESS",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
- "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
@@ -127,7 +127,7 @@
127
  "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
- "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
@@ -138,17 +138,17 @@
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
- "221": "SUCCESS",
142
  "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
- "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NOT_ALIVE",
148
- "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
@@ -156,7 +156,7 @@
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
- "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
@@ -183,25 +183,25 @@
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "NOT_ALIVE",
186
- "32": "NON_PARTICIPATING",
187
  "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
- "35": "NOT_ALIVE",
190
- "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
- "41": "NOT_ALIVE",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
- "44": "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",
@@ -209,7 +209,7 @@
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
- "56": "NOT_ALIVE",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
@@ -223,10 +223,10 @@
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
- "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
- "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NOT_ALIVE",
@@ -238,7 +238,7 @@
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",
@@ -250,7 +250,7 @@
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",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6191883,
268
- 6191899
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": 90,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6191205,
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",
 
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
+ "111": "SUCCESS",
20
  "112": "SUCCESS",
21
+ "113": "NOT_ALIVE",
22
+ "114": "NON_PARTICIPATING",
23
+ "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
+ "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
 
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
+ "133": "SUCCESS",
44
+ "134": "NON_PARTICIPATING",
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "NOT_ALIVE",
49
+ "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
+ "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
+ "143": "SUCCESS",
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": "SUCCESS",
63
+ "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
  "154": "NON_PARTICIPATING",
 
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
+ "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
+ "168": "NON_PARTICIPATING",
82
+ "169": "NON_PARTICIPATING",
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",
 
99
  "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
102
+ "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
+ "192": "NOT_ALIVE",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
+ "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
+ "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "NON_PARTICIPATING",
119
  "201": "SUCCESS",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
+ "204": "NON_PARTICIPATING",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
 
127
  "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
+ "211": "NOT_ALIVE",
131
  "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
 
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
+ "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "NOT_ALIVE",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NOT_ALIVE",
148
+ "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
+ "230": "FAIL",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
 
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",
 
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "NOT_ALIVE",
186
+ "32": "NOT_ALIVE",
187
  "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
+ "35": "SUCCESS",
190
+ "36": "NOT_ALIVE",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
+ "44": "NOT_ALIVE",
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",
 
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
+ "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
 
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
232
  "74": "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
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
+ "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6191969,
268
+ 6191986
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": 6191887,
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 sha256:0eaed813a8da7ebb30153a492b9570c9a8e3d813d22f2b9ecff360bfb5a6038e
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9246bb0a9c932a2898fc4934c30c491dd98435cc27e67e83e471a59647de969f
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2844145b6a03fd5e6b44341336b26de7278979f809f0674376212e8115b117d5
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9af74c7884602a918812513b6e4ebbbfcf2ba3cf0662d1f4a542915f7db260ac
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6965b8c095652c935544ac03641cc71b2077a043cf4cacf30d7e482723767242
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:905eb8ab6c0f849723f8ec30458d792ed7bdb2f14163eba72f32f7b5392c5673
3
  size 4400216536