ncaagcc commited on
Commit
9d9becc
·
verified ·
1 Parent(s): f19201f

Run 5. Outer Step 104. Inner Step 1.

Browse files
Files changed (3) hide show
  1. config.json +65 -65
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -7,25 +7,25 @@
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
- "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
- "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NOT_ALIVE",
17
- "11": "NOT_ALIVE",
18
- "110": "SUCCESS",
19
  "111": "NON_PARTICIPATING",
20
- "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
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": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
@@ -37,38 +37,38 @@
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
- "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "SUCCESS",
43
  "133": "SUCCESS",
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": "SUCCESS",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
- "144": "NON_PARTICIPATING",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NON_PARTICIPATING",
58
- "147": "NOT_ALIVE",
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": "SUCCESS",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
- "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NOT_ALIVE",
@@ -81,10 +81,10 @@
81
  "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
- "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
- "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
@@ -98,9 +98,9 @@
98
  "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
@@ -110,7 +110,7 @@
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NON_PARTICIPATING",
113
- "197": "SUCCESS",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
@@ -126,21 +126,21 @@
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
- "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "SUCCESS",
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": "NOT_ALIVE",
143
- "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NOT_ALIVE",
@@ -148,114 +148,114 @@
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
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": "NOT_ALIVE",
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": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
- "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
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": "NOT_ALIVE",
192
- "38": "NON_PARTICIPATING",
193
- "39": "NON_PARTICIPATING",
194
- "4": "NON_PARTICIPATING",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
- "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
- "48": "NON_PARTICIPATING",
204
- "49": "NOT_ALIVE",
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": "NOT_ALIVE",
212
- "56": "FAIL",
213
  "57": "NOT_ALIVE",
214
  "58": "NON_PARTICIPATING",
215
- "59": "NOT_ALIVE",
216
- "6": "NON_PARTICIPATING",
217
  "60": "SUCCESS",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
- "63": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
- "68": "NON_PARTICIPATING",
226
  "69": "NOT_ALIVE",
227
- "7": "NON_PARTICIPATING",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
- "73": "NON_PARTICIPATING",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
- "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
- "79": "NON_PARTICIPATING",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
- "84": "NOT_ALIVE",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NOT_ALIVE",
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": "NOT_ALIVE",
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": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5961194,
268
- 5961211
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": 152,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5957260,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
+ "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
+ "106": "NON_PARTICIPATING",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NOT_ALIVE",
17
+ "11": "NON_PARTICIPATING",
18
+ "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
+ "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
+ "116": "NOT_ALIVE",
25
  "117": "SUCCESS",
26
  "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
+ "12": "NON_PARTICIPATING",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
 
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
+ "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "SUCCESS",
43
  "133": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
+ "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "SUCCESS",
49
  "139": "NON_PARTICIPATING",
50
+ "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
+ "144": "NOT_ALIVE",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NON_PARTICIPATING",
58
+ "147": "NON_PARTICIPATING",
59
+ "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
+ "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
+ "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NOT_ALIVE",
 
81
  "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
+ "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
+ "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
 
98
  "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
101
+ "186": "NON_PARTICIPATING",
102
  "187": "NON_PARTICIPATING",
103
+ "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
 
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",
 
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
+ "210": "SUCCESS",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "SUCCESS",
135
+ "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "NOT_ALIVE",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
+ "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NOT_ALIVE",
 
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
+ "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
+ "235": "NOT_ALIVE",
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
+ "241": "NOT_ALIVE",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
+ "27": "NON_PARTICIPATING",
181
  "28": "NOT_ALIVE",
182
+ "29": "NOT_ALIVE",
183
  "3": "NON_PARTICIPATING",
184
+ "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
+ "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "SUCCESS",
190
+ "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
+ "38": "SUCCESS",
193
+ "39": "SUCCESS",
194
+ "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
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": "NOT_ALIVE",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
+ "56": "NOT_ALIVE",
213
  "57": "NOT_ALIVE",
214
  "58": "NON_PARTICIPATING",
215
+ "59": "NON_PARTICIPATING",
216
+ "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
+ "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
+ "68": "SUCCESS",
226
  "69": "NOT_ALIVE",
227
+ "7": "SUCCESS",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
+ "73": "SUCCESS",
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": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
+ "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
+ "92": "NOT_ALIVE",
253
+ "93": "NON_PARTICIPATING",
254
+ "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
+ "96": "SUCCESS",
257
  "97": "NON_PARTICIPATING",
258
+ "98": "NOT_ALIVE",
259
  "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5961303,
268
+ 5961316
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": 5961214,
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:ada000d3794fde8dd40675dd3e95c13eb60f5abdb7a895351731e394b06f4ab5
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff1dc02fe36c44ff9745df74da3ae89d87dbb2353f7d1e59f0ef2cf127246c52
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4660f4a3cc25274a8ec38223235f0a2da9ecc0e241c950b52c72a67cd6c887f
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c67ce6a17e9f08a90bc6232efc817837b343576aa9143d93a80cbdcab392192
3
  size 4400216536