ShinyUser commited on
Commit
0f905af
·
verified ·
1 Parent(s): 8b0e1d5

Run 11. Outer Step 69. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +72 -72
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -8,58 +8,58 @@
8
  "101": "NOT_ALIVE",
9
  "102": "SUCCESS",
10
  "103": "NOT_ALIVE",
11
- "104": "NON_PARTICIPATING",
12
- "105": "FAIL",
13
- "106": "FAIL",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
- "109": "FAIL",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
- "111": "FAIL",
20
  "112": "NOT_ALIVE",
21
- "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
- "115": "SUCCESS",
24
- "116": "SUCCESS",
25
- "117": "FAIL",
26
- "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
  "123": "NON_PARTICIPATING",
33
- "124": "FAIL",
34
  "125": "SUCCESS",
35
- "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
- "13": "FAIL",
40
- "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
- "133": "NON_PARTICIPATING",
44
- "134": "NON_PARTICIPATING",
45
- "135": "SUCCESS",
46
  "136": "NOT_ALIVE",
47
- "137": "NON_PARTICIPATING",
48
  "138": "NOT_ALIVE",
49
- "139": "NOT_ALIVE",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
54
- "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
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": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
@@ -70,8 +70,8 @@
70
  "158": "SUCCESS",
71
  "159": "SUCCESS",
72
  "16": "NON_PARTICIPATING",
73
- "160": "NON_PARTICIPATING",
74
- "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
@@ -85,50 +85,50 @@
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
- "174": "NOT_ALIVE",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NON_PARTICIPATING",
95
- "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
  "184": "SUCCESS",
100
- "185": "NOT_ALIVE",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
- "188": "NOT_ALIVE",
104
  "189": "NON_PARTICIPATING",
105
- "19": "NON_PARTICIPATING",
106
- "190": "FAIL",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
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",
117
- "20": "NON_PARTICIPATING",
118
- "200": "SUCCESS",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
- "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
- "21": "NON_PARTICIPATING",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
- "212": "FAIL",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
@@ -138,11 +138,11 @@
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
- "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
- "223": "FAIL",
144
  "224": "NOT_ALIVE",
145
- "225": "NON_PARTICIPATING",
146
  "226": "SUCCESS",
147
  "227": "NOT_ALIVE",
148
  "228": "NOT_ALIVE",
@@ -150,13 +150,13 @@
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
- "232": "NON_PARTICIPATING",
154
  "233": "NOT_ALIVE",
155
- "234": "FAIL",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
- "237": "NON_PARTICIPATING",
159
- "238": "FAIL",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
@@ -164,15 +164,15 @@
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
- "245": "NOT_ALIVE",
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": "NON_PARTICIPATING",
175
- "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
@@ -186,76 +186,76 @@
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
- "35": "FAIL",
190
- "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
- "39": "FAIL",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
199
- "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "NOT_ALIVE",
203
- "48": "NOT_ALIVE",
204
  "49": "SUCCESS",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
- "52": "FAIL",
209
  "53": "SUCCESS",
210
- "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
- "57": "FAIL",
214
  "58": "NOT_ALIVE",
215
- "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
- "62": "FAIL",
220
  "63": "NON_PARTICIPATING",
221
- "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
- "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
  "74": "NOT_ALIVE",
233
- "75": "SUCCESS",
234
  "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
- "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
238
- "8": "FAIL",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
- "83": "FAIL",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
- "86": "NOT_ALIVE",
246
- "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
- "90": "FAIL",
251
- "91": "FAIL",
252
- "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
- "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6579917,
268
- 6579946
269
  ],
270
  "bos_token_id": 1,
271
  "dtype": "float32",
@@ -274,9 +274,9 @@
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
- "inner_step": 36,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6579659,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
8
  "101": "NOT_ALIVE",
9
  "102": "SUCCESS",
10
  "103": "NOT_ALIVE",
11
+ "104": "NOT_ALIVE",
12
+ "105": "NON_PARTICIPATING",
13
+ "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
+ "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
+ "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
+ "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
+ "115": "NOT_ALIVE",
24
+ "116": "NON_PARTICIPATING",
25
+ "117": "SUCCESS",
26
+ "118": "NOT_ALIVE",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
  "123": "NON_PARTICIPATING",
33
+ "124": "SUCCESS",
34
  "125": "SUCCESS",
35
+ "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
+ "13": "NON_PARTICIPATING",
40
+ "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
+ "133": "SUCCESS",
44
+ "134": "SUCCESS",
45
+ "135": "FAIL",
46
  "136": "NOT_ALIVE",
47
+ "137": "SUCCESS",
48
  "138": "NOT_ALIVE",
49
+ "139": "SUCCESS",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
54
+ "143": "SUCCESS",
55
  "144": "NOT_ALIVE",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
58
  "147": "NOT_ALIVE",
59
  "148": "NOT_ALIVE",
60
+ "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
+ "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
 
70
  "158": "SUCCESS",
71
  "159": "SUCCESS",
72
  "16": "NON_PARTICIPATING",
73
+ "160": "NOT_ALIVE",
74
+ "161": "SUCCESS",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
 
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
+ "174": "NON_PARTICIPATING",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NON_PARTICIPATING",
95
+ "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
  "184": "SUCCESS",
100
+ "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
+ "188": "NON_PARTICIPATING",
104
  "189": "NON_PARTICIPATING",
105
+ "19": "SUCCESS",
106
+ "190": "SUCCESS",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
+ "195": "NOT_ALIVE",
112
  "196": "NON_PARTICIPATING",
113
  "197": "SUCCESS",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
117
+ "20": "SUCCESS",
118
+ "200": "NOT_ALIVE",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
+ "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
+ "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
+ "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
 
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
+ "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
+ "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
+ "225": "SUCCESS",
146
  "226": "SUCCESS",
147
  "227": "NOT_ALIVE",
148
  "228": "NOT_ALIVE",
 
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
+ "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
155
+ "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "SUCCESS",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
 
164
  "242": "NOT_ALIVE",
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": "SUCCESS",
176
  "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
 
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
+ "35": "NOT_ALIVE",
190
+ "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
+ "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
199
+ "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "NOT_ALIVE",
203
+ "48": "NON_PARTICIPATING",
204
  "49": "SUCCESS",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
+ "52": "NON_PARTICIPATING",
209
  "53": "SUCCESS",
210
+ "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
+ "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
+ "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
+ "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
+ "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
+ "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
  "74": "NOT_ALIVE",
233
+ "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
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": "SUCCESS",
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": "SUCCESS",
252
+ "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
+ "98": "NOT_ALIVE",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6580077,
268
+ 6580105
269
  ],
270
  "bos_token_id": 1,
271
  "dtype": "float32",
 
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
+ "inner_step": 9,
278
  "intermediate_size": 5632,
279
+ "last_allreduce_block": 6579999,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cf7aa8467438095700cb755ddac6bc3254b54a9e6b90ce79eeefe0bab3ae76e
3
  size 88390091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69af408eb19fcea9da982efbd7f075c27bf1ff11dd7fdb74d0c495d3e8e3c744
3
  size 88390091
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1d8048950567baec3ecd8f59fd68c7654ab8acf6dce58cfa06b39087933024d
3
  size 4924928111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d9909afe66ea257f1a9b47bf0b1905d7185b350411bbaea35e4004ab7c8d5ef
3
  size 4924928111
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f684c57b6f44b9c3c54c33e97cfcfe9ad61abfe2cefc280d652360e56ea0444
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3353f2eaec409e095df1070f95d24668111a1987f9705843e27e0bb13aa37f8a
3
  size 4400216536