shotnikwg commited on
Commit
8cd1ee9
·
verified ·
1 Parent(s): db7cdee

Run 11. Outer Step 285. Inner Step 9.

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
@@ -3,25 +3,25 @@
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
- "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
- "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "SUCCESS",
15
  "108": "SUCCESS",
16
- "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "SUCCESS",
19
  "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
- "114": "NON_PARTICIPATING",
23
- "115": "NON_PARTICIPATING",
24
- "116": "SUCCESS",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
  "119": "SUCCESS",
@@ -29,15 +29,15 @@
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
  "122": "NOT_ALIVE",
32
- "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
- "127": "NON_PARTICIPATING",
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": "NOT_ALIVE",
@@ -48,7 +48,7 @@
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
- "140": "NOT_ALIVE",
52
  "141": "SUCCESS",
53
  "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
@@ -70,21 +70,21 @@
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
- "160": "NON_PARTICIPATING",
74
  "161": "NOT_ALIVE",
75
  "162": "SUCCESS",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "NOT_ALIVE",
80
- "167": "SUCCESS",
81
  "168": "NOT_ALIVE",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
- "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
@@ -98,7 +98,7 @@
98
  "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
  "185": "NOT_ALIVE",
101
- "186": "NOT_ALIVE",
102
  "187": "SUCCESS",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
@@ -106,7 +106,7 @@
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
- "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
@@ -115,7 +115,7 @@
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
- "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
@@ -129,11 +129,11 @@
129
  "210": "NOT_ALIVE",
130
  "211": "SUCCESS",
131
  "212": "NOT_ALIVE",
132
- "213": "NON_PARTICIPATING",
133
- "214": "NON_PARTICIPATING",
134
- "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
- "217": "SUCCESS",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
@@ -143,7 +143,7 @@
143
  "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
- "226": "SUCCESS",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
@@ -152,8 +152,8 @@
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "SUCCESS",
155
- "234": "NOT_ALIVE",
156
- "235": "NOT_ALIVE",
157
  "236": "SUCCESS",
158
  "237": "SUCCESS",
159
  "238": "SUCCESS",
@@ -171,8 +171,8 @@
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
- "251": "NON_PARTICIPATING",
175
- "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
@@ -210,14 +210,14 @@
210
  "54": "SUCCESS",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
- "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
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": "NOT_ALIVE",
@@ -231,7 +231,7 @@
231
  "73": "SUCCESS",
232
  "74": "NOT_ALIVE",
233
  "75": "SUCCESS",
234
- "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
@@ -245,16 +245,16 @@
245
  "86": "NOT_ALIVE",
246
  "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
- "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "SUCCESS",
252
- "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
- "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6693144,
268
- 6693172
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": 6692885,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
+ "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
+ "104": "SUCCESS",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "SUCCESS",
15
  "108": "SUCCESS",
16
+ "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "SUCCESS",
19
  "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
+ "114": "NOT_ALIVE",
23
+ "115": "SUCCESS",
24
+ "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
  "119": "SUCCESS",
 
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
  "122": "NOT_ALIVE",
32
+ "123": "NOT_ALIVE",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
+ "127": "SUCCESS",
37
+ "128": "NON_PARTICIPATING",
38
+ "129": "NON_PARTICIPATING",
39
+ "13": "SUCCESS",
40
+ "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
 
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
+ "140": "SUCCESS",
52
  "141": "SUCCESS",
53
  "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
 
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
+ "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
  "162": "SUCCESS",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "NOT_ALIVE",
80
+ "167": "NOT_ALIVE",
81
  "168": "NOT_ALIVE",
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": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
 
98
  "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
  "185": "NOT_ALIVE",
101
+ "186": "NON_PARTICIPATING",
102
  "187": "SUCCESS",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
 
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
 
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
+ "200": "SUCCESS",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
 
129
  "210": "NOT_ALIVE",
130
  "211": "SUCCESS",
131
  "212": "NOT_ALIVE",
132
+ "213": "NOT_ALIVE",
133
+ "214": "NOT_ALIVE",
134
+ "215": "NOT_ALIVE",
135
  "216": "NON_PARTICIPATING",
136
+ "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
 
143
  "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
+ "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
 
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "SUCCESS",
155
+ "234": "NON_PARTICIPATING",
156
+ "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
  "237": "SUCCESS",
159
  "238": "SUCCESS",
 
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
+ "251": "NOT_ALIVE",
175
+ "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
 
210
  "54": "SUCCESS",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
+ "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
+ "61": "NOT_ALIVE",
219
  "62": "NON_PARTICIPATING",
220
+ "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
 
231
  "73": "SUCCESS",
232
  "74": "NOT_ALIVE",
233
  "75": "SUCCESS",
234
+ "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
 
245
  "86": "NOT_ALIVE",
246
  "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
+ "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "SUCCESS",
252
+ "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
+ "97": "NON_PARTICIPATING",
258
  "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6693314,
268
+ 6693341
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": 6693249,
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 sha256:75243b3b306d3f0369daac7ba1f80c4dcc83b45ffd003287d19d4cbf31c0bff6
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ca9a554de6c75b6c6227e1201ba22d3de4c7d0e4322671026fa8d2aeaeedbda
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00255268061cf8b0289dd762f47ab14d09350de2e51efadcb6981db9ae80a429
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ab8ecd141af2c100ced2462f531a1bce9bd1e1456967fa14332e0626cbf9af
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9c2c35bb13e802472c2f2d1e791d627c11dd4164db736495cdaab07c86d499b
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1feccaf9d11a2c1c1113dfed6d7a7e2a93300e15a36d88bfb0f084e3c095ee6d
3
  size 4400216536