ncaagcc commited on
Commit
5ab0b85
·
verified ·
1 Parent(s): dfbdc32

Run 5. Outer Step 141. Inner Step 1.

Browse files
Files changed (4) hide show
  1. config.json +52 -52
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -12,17 +12,17 @@
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
- "108": "SUCCESS",
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": "NON_PARTICIPATING",
25
- "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
@@ -31,40 +31,40 @@
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",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
- "130": "NOT_ALIVE",
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": "NOT_ALIVE",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
- "145": "NOT_ALIVE",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
- "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
- "15": "NON_PARTICIPATING",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
  "153": "NOT_ALIVE",
66
- "154": "SUCCESS",
67
- "155": "FAIL",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NOT_ALIVE",
70
  "158": "NOT_ALIVE",
@@ -83,7 +83,7 @@
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
- "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NOT_ALIVE",
@@ -102,38 +102,38 @@
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
- "19": "NOT_ALIVE",
106
- "190": "NON_PARTICIPATING",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
- "196": "NOT_ALIVE",
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": "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",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
- "211": "NOT_ALIVE",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
- "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
- "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NOT_ALIVE",
139
  "22": "NON_PARTICIPATING",
@@ -148,29 +148,29 @@
148
  "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "NOT_ALIVE",
156
- "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
- "237": "NOT_ALIVE",
159
- "238": "NOT_ALIVE",
160
- "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
163
- "241": "NOT_ALIVE",
164
- "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NOT_ALIVE",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
171
- "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
  "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
@@ -183,26 +183,26 @@
183
  "3": "NON_PARTICIPATING",
184
  "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
186
- "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
- "39": "FAIL",
194
  "4": "NON_PARTICIPATING",
195
  "40": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
203
- "48": "NOT_ALIVE",
204
- "49": "NON_PARTICIPATING",
205
- "5": "NON_PARTICIPATING",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NOT_ALIVE",
208
  "52": "SUCCESS",
@@ -217,7 +217,7 @@
217
  "60": "NOT_ALIVE",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
- "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
@@ -232,8 +232,8 @@
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
- "77": "SUCCESS",
236
- "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
@@ -241,19 +241,19 @@
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
- "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
246
  "87": "NOT_ALIVE",
247
- "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NON_PARTICIPATING",
250
  "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
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": "NOT_ALIVE",
259
  "99": "NOT_ALIVE"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6015236,
268
- 6015262
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": 23,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6013968,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
+ "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NON_PARTICIPATING",
20
+ "112": "NOT_ALIVE",
21
+ "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
+ "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "SUCCESS",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
 
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",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
+ "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
+ "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "NOT_ALIVE",
60
  "149": "NON_PARTICIPATING",
61
+ "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
  "153": "NOT_ALIVE",
66
+ "154": "NON_PARTICIPATING",
67
+ "155": "SUCCESS",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NOT_ALIVE",
70
  "158": "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": "NOT_ALIVE",
 
102
  "187": "NON_PARTICIPATING",
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": "NOT_ALIVE",
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": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
+ "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
+ "215": "SUCCESS",
135
  "216": "NOT_ALIVE",
136
+ "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NOT_ALIVE",
139
  "22": "NON_PARTICIPATING",
 
148
  "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
+ "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "NOT_ALIVE",
156
+ "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "NON_PARTICIPATING",
159
+ "238": "NON_PARTICIPATING",
160
+ "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
163
+ "241": "SUCCESS",
164
+ "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NOT_ALIVE",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
171
+ "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
+ "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
  "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
 
183
  "3": "NON_PARTICIPATING",
184
  "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
186
+ "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
+ "39": "NON_PARTICIPATING",
194
  "4": "NON_PARTICIPATING",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "NON_PARTICIPATING",
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": "NOT_ALIVE",
205
+ "5": "SUCCESS",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NOT_ALIVE",
208
  "52": "SUCCESS",
 
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",
 
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
+ "77": "NON_PARTICIPATING",
236
+ "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
 
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
+ "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
  "87": "NOT_ALIVE",
247
+ "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NON_PARTICIPATING",
250
  "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
+ "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
+ "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NOT_ALIVE",
259
  "99": "NOT_ALIVE"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6015385,
268
+ 6015410
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": 6015271,
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:e824d12bb5251356da684add17189f78dd8f624f476cd2d606004720a6f0b635
3
  size 44585978
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99efd64e948419f208745a9490b970fc7f02d149950c578394d902c52e2dcfdf
3
  size 44585978
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:489b2b6a3e0dd8b91dd6e4317b7120645cc82c02260d66670d6eab6b67b0c142
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def8329b6c262a7648a5da0f0708cc780b364d1468ffa42d78a4b3875f4190ca
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71ef952d3d590da86595db8d58615546f24fbbd502790a1e11f512bcef2f22ee
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5da1b3426bf2271af3ab91094e14e6f2fb59f90e7fa39e6cfefe055a1b94ed9
3
  size 4400216536