thieu86 commited on
Commit
eaddd1c
·
verified ·
1 Parent(s): 5cbb03a

Run 5. Outer Step 71. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +71 -71
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -6,30 +6,30 @@
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
- "102": "NON_PARTICIPATING",
10
  "103": "SUCCESS",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
- "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NON_PARTICIPATING",
18
  "110": "SUCCESS",
19
- "111": "NOT_ALIVE",
20
- "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
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": "SUCCESS",
32
- "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
  "126": "NON_PARTICIPATING",
@@ -37,29 +37,29 @@
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NON_PARTICIPATING",
40
- "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
- "133": "SUCCESS",
44
- "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
  "136": "SUCCESS",
47
  "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
49
- "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "NON_PARTICIPATING",
53
  "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
- "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
- "146": "NON_PARTICIPATING",
58
- "147": "NON_PARTICIPATING",
59
  "148": "SUCCESS",
60
- "149": "NOT_ALIVE",
61
  "15": "NON_PARTICIPATING",
62
- "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
@@ -68,7 +68,7 @@
68
  "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
71
- "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
@@ -80,11 +80,11 @@
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
  "169": "NON_PARTICIPATING",
83
- "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
- "172": "NON_PARTICIPATING",
87
- "173": "NOT_ALIVE",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
@@ -100,7 +100,7 @@
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
- "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
@@ -110,18 +110,18 @@
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
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",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
- "204": "NOT_ALIVE",
123
- "205": "NON_PARTICIPATING",
124
- "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
@@ -129,22 +129,22 @@
129
  "210": "SUCCESS",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
- "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
- "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
  "222": "NOT_ALIVE",
143
- "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
- "225": "SUCCESS",
146
  "226": "NON_PARTICIPATING",
147
- "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
@@ -161,37 +161,37 @@
161
  "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
- "242": "SUCCESS",
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": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
- "253": "NON_PARTICIPATING",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
- "27": "SUCCESS",
181
- "28": "NOT_ALIVE",
182
- "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
  "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
- "34": "NOT_ALIVE",
189
- "35": "NOT_ALIVE",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "SUCCESS",
193
  "39": "SUCCESS",
194
- "4": "NON_PARTICIPATING",
195
  "40": "SUCCESS",
196
  "41": "SUCCESS",
197
  "42": "NON_PARTICIPATING",
@@ -200,63 +200,63 @@
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": "NOT_ALIVE",
207
- "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
  "53": "NOT_ALIVE",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
- "56": "SUCCESS",
213
- "57": "NOT_ALIVE",
214
- "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
- "6": "NON_PARTICIPATING",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
  "62": "SUCCESS",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
- "66": "NOT_ALIVE",
224
- "67": "NOT_ALIVE",
225
- "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
- "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NON_PARTICIPATING",
233
  "75": "SUCCESS",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
- "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
- "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
- "83": "NON_PARTICIPATING",
243
- "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
245
- "86": "SUCCESS",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
- "9": "NON_PARTICIPATING",
250
  "90": "SUCCESS",
251
  "91": "NON_PARTICIPATING",
252
- "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
- "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
- "98": "NOT_ALIVE",
259
- "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5912945,
268
- 5912990
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
@@ -274,7 +274,7 @@
274
  "initializer_range": 0.02,
275
  "inner_step": 2,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5911865,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
+ "102": "NOT_ALIVE",
10
  "103": "SUCCESS",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
+ "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NON_PARTICIPATING",
18
  "110": "SUCCESS",
19
+ "111": "NON_PARTICIPATING",
20
+ "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
+ "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
+ "12": "NON_PARTICIPATING",
29
+ "120": "NOT_ALIVE",
30
+ "121": "NOT_ALIVE",
31
  "122": "SUCCESS",
32
+ "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
  "126": "NON_PARTICIPATING",
 
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NON_PARTICIPATING",
40
+ "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
+ "133": "NOT_ALIVE",
44
+ "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "SUCCESS",
47
  "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "NON_PARTICIPATING",
53
  "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
+ "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
+ "146": "NOT_ALIVE",
58
+ "147": "NOT_ALIVE",
59
  "148": "SUCCESS",
60
+ "149": "NON_PARTICIPATING",
61
  "15": "NON_PARTICIPATING",
62
+ "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
 
68
  "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
71
+ "159": "NON_PARTICIPATING",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
 
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
  "169": "NON_PARTICIPATING",
83
+ "17": "NON_PARTICIPATING",
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",
 
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
+ "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
 
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
+ "197": "NOT_ALIVE",
114
+ "198": "NOT_ALIVE",
115
  "199": "NON_PARTICIPATING",
116
+ "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
+ "204": "NON_PARTICIPATING",
123
+ "205": "NOT_ALIVE",
124
+ "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
 
129
  "210": "SUCCESS",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
+ "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
+ "215": "SUCCESS",
135
  "216": "NOT_ALIVE",
136
+ "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
  "222": "NOT_ALIVE",
143
+ "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
+ "225": "NOT_ALIVE",
146
  "226": "NON_PARTICIPATING",
147
+ "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
 
161
  "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
+ "242": "NOT_ALIVE",
165
+ "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
+ "27": "NOT_ALIVE",
181
+ "28": "NON_PARTICIPATING",
182
+ "29": "NOT_ALIVE",
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": "NON_PARTICIPATING",
192
  "38": "SUCCESS",
193
  "39": "SUCCESS",
194
+ "4": "NOT_ALIVE",
195
  "40": "SUCCESS",
196
  "41": "SUCCESS",
197
  "42": "NON_PARTICIPATING",
 
200
  "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
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": "NOT_ALIVE",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
+ "56": "NOT_ALIVE",
213
+ "57": "NON_PARTICIPATING",
214
+ "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
+ "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
  "62": "SUCCESS",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
+ "66": "NON_PARTICIPATING",
224
+ "67": "NON_PARTICIPATING",
225
+ "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
+ "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NON_PARTICIPATING",
233
  "75": "SUCCESS",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
+ "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
+ "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
+ "83": "NOT_ALIVE",
243
+ "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
+ "86": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
+ "9": "SUCCESS",
250
  "90": "SUCCESS",
251
  "91": "NON_PARTICIPATING",
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"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5913158,
268
+ 5913188
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
 
274
  "initializer_range": 0.02,
275
  "inner_step": 2,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 5913076,
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 sha256:9d6c2604ad8674e13efd3fc2f0ed348ba231ac1e9b6444933294b53fc4e78c86
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac33dd7c0d42cee22ffae13d1bb4e9c962a4f7984e2d511703bf0c39e3c47a17
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cdf7bcdc9e757b5bbe22461a605cae62fbbd7c25f5b7f7ef32d74a688236bf9
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44d4667c45445dc5b67d7eecdd1016b90d48cbb75653edcdb228258a96f2f48e
3
  size 4400216536