ncaagcc commited on
Commit
c877292
·
verified ·
1 Parent(s): 006e661

Run 5. Outer Step 131. Inner Step 1.

Browse files
Files changed (3) hide show
  1. config.json +61 -61
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -13,26 +13,26 @@
13
  "106": "NON_PARTICIPATING",
14
  "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
16
- "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
- "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
- "117": "NON_PARTICIPATING",
26
  "118": "NOT_ALIVE",
27
- "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
- "124": "NOT_ALIVE",
34
  "125": "NON_PARTICIPATING",
35
- "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
@@ -40,30 +40,30 @@
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
- "133": "NOT_ALIVE",
44
  "134": "NON_PARTICIPATING",
45
- "135": "NOT_ALIVE",
46
- "136": "NOT_ALIVE",
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": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
- "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
- "148": "NOT_ALIVE",
60
  "149": "NON_PARTICIPATING",
61
- "15": "NOT_ALIVE",
62
- "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "NON_PARTICIPATING",
66
- "154": "NOT_ALIVE",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
@@ -75,10 +75,10 @@
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
- "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
- "168": "NOT_ALIVE",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
@@ -95,7 +95,7 @@
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
- "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
100
  "185": "NOT_ALIVE",
101
  "186": "NOT_ALIVE",
@@ -104,13 +104,13 @@
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
- "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NOT_ALIVE",
110
- "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NON_PARTICIPATING",
113
- "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
@@ -119,26 +119,26 @@
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
- "204": "NON_PARTICIPATING",
123
  "205": "NON_PARTICIPATING",
124
- "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
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": "NOT_ALIVE",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
- "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
@@ -146,7 +146,7 @@
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
- "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
@@ -155,69 +155,69 @@
155
  "234": "NOT_ALIVE",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
- "237": "NOT_ALIVE",
159
- "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
- "242": "NOT_ALIVE",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
171
- "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
  "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
- "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
183
  "3": "NON_PARTICIPATING",
184
- "30": "NOT_ALIVE",
185
- "31": "NOT_ALIVE",
186
- "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "NOT_ALIVE",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
- "38": "NON_PARTICIPATING",
193
- "39": "SUCCESS",
194
  "4": "NON_PARTICIPATING",
195
- "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
- "47": "NON_PARTICIPATING",
203
- "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
- "5": "NON_PARTICIPATING",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
- "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
- "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
- "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
@@ -230,20 +230,20 @@
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
- "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
- "77": "NON_PARTICIPATING",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
- "80": "NON_PARTICIPATING",
240
- "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
- "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
- "86": "SUCCESS",
246
- "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NON_PARTICIPATING",
@@ -251,7 +251,7 @@
251
  "91": "NOT_ALIVE",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
- "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5999590,
268
- 5999607
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": 29,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5998439,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
13
  "106": "NON_PARTICIPATING",
14
  "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
16
+ "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
+ "112": "SUCCESS",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "SUCCESS",
26
  "118": "NOT_ALIVE",
27
+ "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
+ "124": "SUCCESS",
34
  "125": "NON_PARTICIPATING",
35
+ "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
 
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
+ "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
+ "135": "NON_PARTICIPATING",
46
+ "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
+ "14": "NON_PARTICIPATING",
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": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "SUCCESS",
60
  "149": "NON_PARTICIPATING",
61
+ "15": "SUCCESS",
62
+ "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "SUCCESS",
66
+ "154": "SUCCESS",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
 
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
+ "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
+ "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
 
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
+ "183": "SUCCESS",
99
  "184": "NON_PARTICIPATING",
100
  "185": "NOT_ALIVE",
101
  "186": "NOT_ALIVE",
 
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NOT_ALIVE",
110
+ "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NON_PARTICIPATING",
113
+ "197": "SUCCESS",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
 
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
+ "204": "SUCCESS",
123
  "205": "NON_PARTICIPATING",
124
+ "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
+ "212": "SUCCESS",
132
+ "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
+ "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
+ "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
 
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
+ "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
 
155
  "234": "NOT_ALIVE",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
+ "237": "NON_PARTICIPATING",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
+ "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
171
+ "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
+ "250": "SUCCESS",
174
  "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
+ "254": "SUCCESS",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
183
  "3": "NON_PARTICIPATING",
184
+ "30": "NON_PARTICIPATING",
185
+ "31": "NON_PARTICIPATING",
186
+ "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
+ "38": "NOT_ALIVE",
193
+ "39": "NON_PARTICIPATING",
194
  "4": "NON_PARTICIPATING",
195
+ "40": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
+ "47": "SUCCESS",
203
+ "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
+ "52": "SUCCESS",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
+ "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
 
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
+ "75": "NOT_ALIVE",
234
  "76": "NON_PARTICIPATING",
235
+ "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
+ "80": "NOT_ALIVE",
240
+ "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "NON_PARTICIPATING",
246
+ "87": "NOT_ALIVE",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NON_PARTICIPATING",
 
251
  "91": "NOT_ALIVE",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
+ "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5999748,
268
+ 5999769
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": 1,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 5999601,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c2a025ce56cf10111e8480160481f072c29c175cd91bdaa387ec2228a7651be
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749536c0b11f5725d34464da7bb80a564a2b1a8339a0e9f2ee8062eb7c7aa663
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d62c8680a438d9c9b95a2a28fe3d9b0d37336334b12b526be14cec58a7d2730
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd413bae45ccd46e3de71342c8a35eb61d16e28d0f8c8bfc75a6a8a864abc01c
3
  size 4400216536