ncaagcc commited on
Commit
5bd5e1c
·
verified ·
1 Parent(s): 40df16e

Run 5. Outer Step 139. Inner Step 1.

Browse files
Files changed (4) hide show
  1. config.json +64 -64
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -5,9 +5,9 @@
5
  "1": "NON_PARTICIPATING",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
- "101": "NOT_ALIVE",
9
  "102": "NON_PARTICIPATING",
10
- "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
@@ -16,22 +16,22 @@
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
- "111": "NOT_ALIVE",
20
  "112": "NON_PARTICIPATING",
21
- "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NON_PARTICIPATING",
25
- "117": "NOT_ALIVE",
26
  "118": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
34
- "125": "SUCCESS",
35
  "126": "NON_PARTICIPATING",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
@@ -39,13 +39,13 @@
39
  "13": "NOT_ALIVE",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
- "132": "NON_PARTICIPATING",
43
- "133": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
- "138": "SUCCESS",
49
  "139": "NON_PARTICIPATING",
50
  "14": "SUCCESS",
51
  "140": "NON_PARTICIPATING",
@@ -56,27 +56,27 @@
56
  "145": "NOT_ALIVE",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
- "148": "NOT_ALIVE",
60
  "149": "NON_PARTICIPATING",
61
- "15": "NON_PARTICIPATING",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
- "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
- "154": "NOT_ALIVE",
67
- "155": "SUCCESS",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NOT_ALIVE",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
- "161": "NON_PARTICIPATING",
75
- "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
- "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NOT_ALIVE",
@@ -91,11 +91,11 @@
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
- "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
- "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
  "185": "NOT_ALIVE",
101
  "186": "NOT_ALIVE",
@@ -103,23 +103,23 @@
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
- "190": "NON_PARTICIPATING",
107
  "191": "NON_PARTICIPATING",
108
- "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
- "199": "NOT_ALIVE",
116
  "2": "NON_PARTICIPATING",
117
  "20": "NON_PARTICIPATING",
118
  "200": "NOT_ALIVE",
119
- "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NOT_ALIVE",
122
- "204": "NON_PARTICIPATING",
123
  "205": "NON_PARTICIPATING",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
@@ -129,23 +129,23 @@
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
- "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
- "215": "SUCCESS",
135
  "216": "NOT_ALIVE",
136
- "217": "NOT_ALIVE",
137
- "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NON_PARTICIPATING",
140
- "220": "NOT_ALIVE",
141
- "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "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",
@@ -153,16 +153,16 @@
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "NOT_ALIVE",
156
- "235": "NON_PARTICIPATING",
157
- "236": "NON_PARTICIPATING",
158
- "237": "NON_PARTICIPATING",
159
- "238": "NON_PARTICIPATING",
160
- "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
163
- "241": "NON_PARTICIPATING",
164
- "242": "NON_PARTICIPATING",
165
- "243": "SUCCESS",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NOT_ALIVE",
@@ -176,13 +176,13 @@
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
- "26": "NOT_ALIVE",
180
  "27": "NOT_ALIVE",
181
  "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
- "30": "NON_PARTICIPATING",
185
- "31": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
@@ -190,34 +190,34 @@
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
- "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
- "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
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": "NOT_ALIVE",
206
- "50": "NON_PARTICIPATING",
207
- "51": "NON_PARTICIPATING",
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": "SUCCESS",
216
  "6": "NON_PARTICIPATING",
217
  "60": "NOT_ALIVE",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
- "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
@@ -226,11 +226,11 @@
226
  "69": "NOT_ALIVE",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
- "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
- "73": "NON_PARTICIPATING",
232
  "74": "NOT_ALIVE",
233
- "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
  "77": "SUCCESS",
236
  "78": "NOT_ALIVE",
@@ -242,14 +242,14 @@
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": "NON_PARTICIPATING",
250
  "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
252
- "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6012620,
268
- 6012658
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": 22,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6011356,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
5
  "1": "NON_PARTICIPATING",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
+ "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
+ "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
 
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
+ "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
+ "113": "SUCCESS",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "NOT_ALIVE",
25
+ "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
+ "120": "NOT_ALIVE",
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",
 
39
  "13": "NOT_ALIVE",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
+ "132": "NOT_ALIVE",
43
+ "133": "NOT_ALIVE",
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": "NON_PARTICIPATING",
 
56
  "145": "NOT_ALIVE",
57
  "146": "NOT_ALIVE",
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": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
+ "154": "SUCCESS",
67
+ "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NOT_ALIVE",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "NOT_ALIVE",
75
+ "162": "NOT_ALIVE",
76
  "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
+ "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NOT_ALIVE",
 
91
  "177": "NOT_ALIVE",
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": "NON_PARTICIPATING",
100
  "185": "NOT_ALIVE",
101
  "186": "NOT_ALIVE",
 
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
+ "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
+ "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
+ "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
117
  "20": "NON_PARTICIPATING",
118
  "200": "NOT_ALIVE",
119
+ "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NOT_ALIVE",
122
+ "204": "SUCCESS",
123
  "205": "NON_PARTICIPATING",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
 
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
+ "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
+ "215": "NON_PARTICIPATING",
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": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
+ "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
 
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "NOT_ALIVE",
156
+ "235": "NOT_ALIVE",
157
+ "236": "NOT_ALIVE",
158
+ "237": "NOT_ALIVE",
159
+ "238": "NOT_ALIVE",
160
+ "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
163
+ "241": "SUCCESS",
164
+ "242": "NOT_ALIVE",
165
+ "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NOT_ALIVE",
 
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
+ "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
+ "30": "SUCCESS",
185
+ "31": "NOT_ALIVE",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
 
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
+ "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
+ "40": "NOT_ALIVE",
196
+ "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
+ "44": "NOT_ALIVE",
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": "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": "SUCCESS",
216
  "6": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
 
226
  "69": "NOT_ALIVE",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
+ "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
+ "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
+ "75": "SUCCESS",
234
  "76": "NOT_ALIVE",
235
  "77": "SUCCESS",
236
  "78": "NOT_ALIVE",
 
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": "NON_PARTICIPATING",
250
  "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
252
+ "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6012833,
268
+ 6012861
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": 6012664,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0ba74c7b36d7db3ff059bd10ffd1c6328d77436eb4e7ed1b11588a57ff23827
3
  size 44585978
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8303d677211c62b22748ded8305dba981fdbf52b4e288c11a3a0fa2486514f0a
3
  size 44585978
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38caaf88b580c33cdbab3c5e304f048d0f04d925ffd41ed4240f26f411c3bdc3
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:539a98b1887a00ebc4d044fa55fdd4b11f9371f5356b2de697bbbd9f6a947553
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2b533771903f5fd1125f89b9c3ee8dcf1ffd828a4a5a0ee5ba7337162a393fb
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df94e3869eea7c07d2108062c18a184a8ef461b43437a0609b13c22709e0e637
3
  size 4400216536