thieu86 commited on
Commit
a557fd5
·
verified ·
1 Parent(s): 1a158ef

Run 5. Outer Step 85. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +78 -78
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -13,25 +13,25 @@
13
  "106": "NON_PARTICIPATING",
14
  "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
16
- "109": "NOT_ALIVE",
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
- "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
- "117": "SUCCESS",
26
- "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
- "12": "NON_PARTICIPATING",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
- "125": "NON_PARTICIPATING",
35
  "126": "NON_PARTICIPATING",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
@@ -41,50 +41,50 @@
41
  "131": "NOT_ALIVE",
42
  "132": "NON_PARTICIPATING",
43
  "133": "NON_PARTICIPATING",
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": "NOT_ALIVE",
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": "NOT_ALIVE",
59
- "148": "NOT_ALIVE",
60
- "149": "NON_PARTICIPATING",
61
  "15": "NON_PARTICIPATING",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
- "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
- "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
- "159": "SUCCESS",
72
  "16": "NON_PARTICIPATING",
73
- "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
- "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
- "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
- "172": "NON_PARTICIPATING",
87
- "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
@@ -106,13 +106,13 @@
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": "NOT_ALIVE",
113
- "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
- "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
@@ -120,23 +120,23 @@
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
- "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
- "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
- "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
- "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
- "215": "SUCCESS",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
- "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
- "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
142
  "222": "NON_PARTICIPATING",
@@ -150,90 +150,90 @@
150
  "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
- "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
- "235": "NOT_ALIVE",
157
- "236": "NON_PARTICIPATING",
158
- "237": "NOT_ALIVE",
159
- "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
- "242": "NOT_ALIVE",
165
- "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
174
  "251": "NON_PARTICIPATING",
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",
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": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
- "38": "NON_PARTICIPATING",
193
- "39": "NON_PARTICIPATING",
194
  "4": "NON_PARTICIPATING",
195
  "40": "SUCCESS",
196
- "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
- "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
- "46": "NOT_ALIVE",
202
- "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
- "5": "SUCCESS",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
- "56": "SUCCESS",
213
  "57": "NON_PARTICIPATING",
214
- "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
- "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
- "62": "SUCCESS",
220
  "63": "NON_PARTICIPATING",
221
- "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
- "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NON_PARTICIPATING",
229
- "71": "NON_PARTICIPATING",
230
- "72": "NOT_ALIVE",
231
- "73": "NOT_ALIVE",
232
- "74": "NOT_ALIVE",
233
- "75": "NOT_ALIVE",
234
- "76": "NON_PARTICIPATING",
235
- "77": "NOT_ALIVE",
236
- "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
@@ -241,19 +241,19 @@
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
- "85": "NON_PARTICIPATING",
245
- "86": "NON_PARTICIPATING",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
- "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
- "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NOT_ALIVE"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5932556,
268
- 5932585
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": 45,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5931232,
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": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
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": "NON_PARTICIPATING",
34
+ "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
 
41
  "131": "NOT_ALIVE",
42
  "132": "NON_PARTICIPATING",
43
  "133": "NON_PARTICIPATING",
44
+ "134": "NOT_ALIVE",
45
+ "135": "NON_PARTICIPATING",
46
+ "136": "NON_PARTICIPATING",
47
+ "137": "SUCCESS",
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": "NON_PARTICIPATING",
56
+ "145": "NON_PARTICIPATING",
57
+ "146": "NON_PARTICIPATING",
58
+ "147": "NON_PARTICIPATING",
59
+ "148": "NON_PARTICIPATING",
60
+ "149": "NOT_ALIVE",
61
  "15": "NON_PARTICIPATING",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
+ "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
+ "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "NON_PARTICIPATING",
72
  "16": "NON_PARTICIPATING",
73
+ "160": "NOT_ALIVE",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
+ "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "NOT_ALIVE",
83
  "17": "NON_PARTICIPATING",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
+ "172": "SUCCESS",
87
+ "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
 
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
+ "196": "NON_PARTICIPATING",
113
+ "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
+ "199": "NOT_ALIVE",
116
  "2": "NON_PARTICIPATING",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
 
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
+ "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
+ "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
+ "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
+ "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
+ "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
+ "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
+ "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
142
  "222": "NON_PARTICIPATING",
 
150
  "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
+ "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
+ "235": "NON_PARTICIPATING",
157
+ "236": "NOT_ALIVE",
158
+ "237": "NON_PARTICIPATING",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
+ "242": "NON_PARTICIPATING",
165
+ "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "NOT_ALIVE",
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": "NON_PARTICIPATING",
177
+ "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
+ "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
186
+ "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
+ "34": "NON_PARTICIPATING",
189
  "35": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
+ "38": "NOT_ALIVE",
193
+ "39": "SUCCESS",
194
  "4": "NON_PARTICIPATING",
195
  "40": "SUCCESS",
196
+ "41": "SUCCESS",
197
  "42": "NON_PARTICIPATING",
198
+ "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
+ "46": "NON_PARTICIPATING",
202
+ "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "NON_PARTICIPATING",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
+ "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
+ "58": "NON_PARTICIPATING",
215
  "59": "SUCCESS",
216
+ "6": "NON_PARTICIPATING",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
+ "62": "NON_PARTICIPATING",
220
  "63": "NON_PARTICIPATING",
221
+ "64": "NON_PARTICIPATING",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
+ "69": "NOT_ALIVE",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NON_PARTICIPATING",
229
+ "71": "NOT_ALIVE",
230
+ "72": "NON_PARTICIPATING",
231
+ "73": "NON_PARTICIPATING",
232
+ "74": "NON_PARTICIPATING",
233
+ "75": "NON_PARTICIPATING",
234
+ "76": "NOT_ALIVE",
235
+ "77": "NON_PARTICIPATING",
236
+ "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
 
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
+ "85": "NOT_ALIVE",
245
+ "86": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
+ "9": "NON_PARTICIPATING",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
+ "96": "NOT_ALIVE",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NOT_ALIVE"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5932649,
268
+ 5932679
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": 2,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 5932508,
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 sha256:7706242c207b23d0c8938c2024ca850ba15d02e1f58078477c96e80dc87ada83
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a4c32c539e3af8a68562e4208382c54260a5d5e3e49c4a4a058211ab9132a7c
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20f47a4fb17ed21b5344d10c9150b88b4edcb44c538e672559c3463e6bc9654b
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92bf526d7951e3be12d8d5a1be8f69ef37c93979883d8fbea066b2d69f12503f
3
  size 4400216536