zeras141a commited on
Commit
c9e4990
·
verified ·
1 Parent(s): 495813b

Run 6. Outer Step 81. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +40 -40
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -4,9 +4,9 @@
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
- "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
- "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
@@ -23,17 +23,17 @@
23
  "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
- "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
- "122": "NON_PARTICIPATING",
32
- "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
- "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
@@ -43,37 +43,37 @@
43
  "133": "NON_PARTICIPATING",
44
  "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
- "136": "NOT_ALIVE",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
- "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
53
- "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
- "146": "NOT_ALIVE",
58
  "147": "NOT_ALIVE",
59
- "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
- "154": "NON_PARTICIPATING",
67
- "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
- "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
- "163": "NOT_ALIVE",
77
  "164": "SUCCESS",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
@@ -84,7 +84,7 @@
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
- "173": "NOT_ALIVE",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
@@ -93,18 +93,18 @@
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
- "181": "NON_PARTICIPATING",
97
- "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
101
- "186": "NON_PARTICIPATING",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
- "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
@@ -120,18 +120,18 @@
120
  "202": "NOT_ALIVE",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
- "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
- "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
- "215": "NOT_ALIVE",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
@@ -145,7 +145,7 @@
145
  "225": "NOT_ALIVE",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NOT_ALIVE",
148
- "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "SUCCESS",
@@ -154,14 +154,14 @@
154
  "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
- "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
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": "NOT_ALIVE",
@@ -174,11 +174,11 @@
174
  "251": "NOT_ALIVE",
175
  "252": "NOT_ALIVE",
176
  "253": "NON_PARTICIPATING",
177
- "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
- "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
@@ -193,10 +193,10 @@
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
- "41": "NOT_ALIVE",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
- "44": "SUCCESS",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
@@ -208,7 +208,7 @@
208
  "52": "NOT_ALIVE",
209
  "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
- "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
@@ -226,20 +226,20 @@
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
- "71": "SUCCESS",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
- "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
- "77": "NON_PARTICIPATING",
236
  "78": "SUCCESS",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
- "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
@@ -255,7 +255,7 @@
255
  "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
- "98": "NOT_ALIVE",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6186138,
268
- 6186156
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": 70,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6185426,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
+ "100": "NON_PARTICIPATING",
8
  "101": "NOT_ALIVE",
9
+ "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
 
23
  "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
+ "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
+ "122": "NOT_ALIVE",
32
+ "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
+ "127": "NOT_ALIVE",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
 
43
  "133": "NON_PARTICIPATING",
44
  "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
+ "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
+ "140": "NOT_ALIVE",
52
  "141": "NON_PARTICIPATING",
53
+ "142": "NOT_ALIVE",
54
  "143": "NOT_ALIVE",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
+ "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
+ "148": "NOT_ALIVE",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
+ "154": "SUCCESS",
67
+ "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "NON_PARTICIPATING",
77
  "164": "SUCCESS",
78
  "165": "NON_PARTICIPATING",
79
  "166": "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",
 
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
+ "181": "NOT_ALIVE",
97
+ "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
101
+ "186": "NOT_ALIVE",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
+ "191": "SUCCESS",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
 
120
  "202": "NOT_ALIVE",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
+ "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
+ "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
+ "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
 
145
  "225": "NOT_ALIVE",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NOT_ALIVE",
148
+ "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "SUCCESS",
 
154
  "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
+ "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
+ "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
 
174
  "251": "NOT_ALIVE",
175
  "252": "NOT_ALIVE",
176
  "253": "NON_PARTICIPATING",
177
+ "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
+ "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
 
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
+ "44": "NOT_ALIVE",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
 
208
  "52": "NOT_ALIVE",
209
  "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
+ "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
 
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
+ "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
+ "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
+ "77": "SUCCESS",
236
  "78": "SUCCESS",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
 
255
  "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
+ "98": "NON_PARTICIPATING",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6186267,
268
+ 6186283
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": 4,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6186102,
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 sha256:1711a9add7aa7624c114f3c2725f68d0a46206c27eb9ee561b81749bb38ce59c
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d6e3905b72f35e42d4b2573c886023e8de51710fd80e81dd1c1e8f3979e4170
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd1506216c0a01c388121a0478d04338e6b0984084fd506d918c1dd12e324a34
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b2bc87e4162bca512226a9c0df4ef54dc0948f6fe8efd5ad99f992ade12ac37
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8dec2b6a239c363662d12389788f54d784770aa07c94f36b9331bb2ffa8d874
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d692608806ab42baa74b2a6dc9d7659e7d294e5d979bc97e8551c8dc7d78eac5
3
  size 4400216536