ShinyUser commited on
Commit
a8062c1
·
verified ·
1 Parent(s): c4fb61f

Run 11. Outer Step 66. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +57 -57
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -8,7 +8,7 @@
8
  "101": "NOT_ALIVE",
9
  "102": "SUCCESS",
10
  "103": "NOT_ALIVE",
11
- "104": "NON_PARTICIPATING",
12
  "105": "SUCCESS",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
@@ -16,12 +16,12 @@
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
- "111": "SUCCESS",
20
  "112": "NOT_ALIVE",
21
- "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
- "115": "NON_PARTICIPATING",
24
- "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
@@ -29,14 +29,14 @@
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
- "123": "NON_PARTICIPATING",
33
  "124": "SUCCESS",
34
- "125": "SUCCESS",
35
  "126": "NON_PARTICIPATING",
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",
@@ -46,20 +46,20 @@
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": "NOT_ALIVE",
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",
@@ -76,17 +76,17 @@
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
- "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
81
  "168": "SUCCESS",
82
- "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "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",
@@ -95,20 +95,20 @@
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
- "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
- "189": "NON_PARTICIPATING",
105
- "19": "NON_PARTICIPATING",
106
- "190": "SUCCESS",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
- "194": "NOT_ALIVE",
111
- "195": "NOT_ALIVE",
112
  "196": "NON_PARTICIPATING",
113
  "197": "SUCCESS",
114
  "198": "NON_PARTICIPATING",
@@ -120,20 +120,20 @@
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
- "205": "NON_PARTICIPATING",
124
- "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
- "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
- "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
@@ -143,28 +143,28 @@
143
  "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
- "226": "FAIL",
147
- "227": "NON_PARTICIPATING",
148
  "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
- "232": "NON_PARTICIPATING",
154
  "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
- "237": "NON_PARTICIPATING",
159
- "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
163
- "241": "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": "SUCCESS",
@@ -176,7 +176,7 @@
176
  "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
- "26": "NOT_ALIVE",
180
  "27": "SUCCESS",
181
  "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
@@ -185,12 +185,12 @@
185
  "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
- "34": "SUCCESS",
189
- "35": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
- "38": "NON_PARTICIPATING",
193
- "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
@@ -205,18 +205,18 @@
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
- "52": "NOT_ALIVE",
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": "NON_PARTICIPATING",
220
  "63": "NON_PARTICIPATING",
221
  "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
@@ -230,25 +230,25 @@
230
  "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
  "74": "NOT_ALIVE",
233
- "75": "SUCCESS",
234
- "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
- "78": "SUCCESS",
237
  "79": "NON_PARTICIPATING",
238
  "8": "SUCCESS",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
- "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
- "85": "NON_PARTICIPATING",
245
- "86": "NOT_ALIVE",
246
- "87": "NOT_ALIVE",
247
- "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
- "90": "NOT_ALIVE",
251
- "91": "SUCCESS",
252
  "92": "SUCCESS",
253
  "93": "SUCCESS",
254
  "94": "NON_PARTICIPATING",
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6578807,
268
- 6578836
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": 22,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6578595,
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": "SUCCESS",
12
  "105": "SUCCESS",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
 
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
+ "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
+ "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
+ "115": "SUCCESS",
24
+ "116": "SUCCESS",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
 
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
+ "123": "NOT_ALIVE",
33
  "124": "SUCCESS",
34
+ "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
+ "13": "NOT_ALIVE",
40
  "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
 
46
  "136": "NOT_ALIVE",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NOT_ALIVE",
49
+ "139": "SUCCESS",
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",
 
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
+ "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
  "168": "SUCCESS",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
+ "174": "NOT_ALIVE",
89
+ "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
 
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
+ "183": "NON_PARTICIPATING",
99
  "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
+ "189": "NOT_ALIVE",
105
+ "19": "SUCCESS",
106
+ "190": "NOT_ALIVE",
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",
 
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": "FAIL",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
+ "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
+ "217": "SUCCESS",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
 
143
  "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
+ "226": "SUCCESS",
147
+ "227": "NOT_ALIVE",
148
  "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
+ "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "SUCCESS",
159
+ "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
163
+ "241": "NON_PARTICIPATING",
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": "SUCCESS",
 
176
  "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
+ "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
  "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
 
185
  "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
+ "34": "NOT_ALIVE",
189
+ "35": "NOT_ALIVE",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
+ "38": "SUCCESS",
193
+ "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
 
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
+ "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
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": "SUCCESS",
222
  "65": "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": "SUCCESS",
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": "NON_PARTICIPATING",
246
+ "87": "SUCCESS",
247
+ "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
+ "90": "NON_PARTICIPATING",
251
+ "91": "FAIL",
252
  "92": "SUCCESS",
253
  "93": "SUCCESS",
254
  "94": "NON_PARTICIPATING",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6578961,
268
+ 6578990
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": 8,
278
  "intermediate_size": 5632,
279
+ "last_allreduce_block": 6578941,
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:e68fa0d990dd3661234d67755bfbf3f6c475014a2fadd10a795423bae404b0f8
3
  size 88390091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c505f59d79ff5d0f5154b5876e9723faa7a1e6ffd827b0330659fd3f5d86a09b
3
  size 88390091
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65e23844d71ee94fe3625db0d9ad50c8891805f73b0c33617473b7b884e591ff
3
  size 4924928111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23dbc5571f33b763815829e72f89c1172955d07517f982f0f091a4efdf45bfff
3
  size 4924928111
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83451dac35ae49245bafeb34fbfa78ef24048fe404ac8f81b15e92f08ca098b1
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7349d1b0e0b75b63b4a9156334f7cddaf82fa935d5604e868ad324e4dfff8ef
3
  size 4400216536