ncaagcc commited on
Commit
9bf5c42
·
verified ·
1 Parent(s): e14bc87

Run 10. Outer Step 27. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +84 -84
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -6,22 +6,22 @@
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
- "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
- "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
14
- "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
- "109": "SUCCESS",
17
- "11": "NON_PARTICIPATING",
18
  "110": "NOT_ALIVE",
19
- "111": "SUCCESS",
20
- "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
- "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
  "119": "SUCCESS",
@@ -29,12 +29,12 @@
29
  "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
- "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
- "125": "NON_PARTICIPATING",
35
- "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
- "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
@@ -45,27 +45,27 @@
45
  "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
- "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
54
- "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
- "146": "SUCCESS",
58
  "147": "NOT_ALIVE",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
- "15": "SUCCESS",
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": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
71
  "159": "NON_PARTICIPATING",
@@ -77,16 +77,16 @@
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "NOT_ALIVE",
80
- "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
- "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
- "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
- "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
89
- "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
@@ -95,55 +95,55 @@
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
- "183": "SUCCESS",
99
- "184": "SUCCESS",
100
- "185": "NOT_ALIVE",
101
- "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
- "188": "SUCCESS",
104
  "189": "NOT_ALIVE",
105
- "19": "NON_PARTICIPATING",
106
- "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
- "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
  "198": "SUCCESS",
115
  "199": "NON_PARTICIPATING",
116
- "2": "NON_PARTICIPATING",
117
  "20": "NOT_ALIVE",
118
- "200": "SUCCESS",
119
  "201": "NON_PARTICIPATING",
120
- "202": "NOT_ALIVE",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
- "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
- "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
- "211": "NON_PARTICIPATING",
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": "SUCCESS",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NOT_ALIVE",
141
  "221": "SUCCESS",
142
- "222": "SUCCESS",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
- "225": "NOT_ALIVE",
146
- "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
@@ -151,58 +151,58 @@
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NON_PARTICIPATING",
154
- "233": "NON_PARTICIPATING",
155
- "234": "NON_PARTICIPATING",
156
  "235": "SUCCESS",
157
- "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
- "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
- "241": "SUCCESS",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
- "245": "NOT_ALIVE",
168
- "246": "SUCCESS",
169
  "247": "NOT_ALIVE",
170
  "248": "NON_PARTICIPATING",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
- "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
- "255": "SUCCESS",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
- "28": "NOT_ALIVE",
182
- "29": "SUCCESS",
183
  "3": "SUCCESS",
184
  "30": "NON_PARTICIPATING",
185
- "31": "NON_PARTICIPATING",
186
- "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
- "34": "SUCCESS",
189
- "35": "SUCCESS",
190
- "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
- "39": "SUCCESS",
194
  "4": "SUCCESS",
195
- "40": "SUCCESS",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
- "46": "SUCCESS",
202
- "47": "SUCCESS",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
- "5": "NOT_ALIVE",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
@@ -210,18 +210,18 @@
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
- "57": "SUCCESS",
214
  "58": "NON_PARTICIPATING",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
- "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
- "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
  "7": "SUCCESS",
@@ -231,24 +231,24 @@
231
  "73": "NON_PARTICIPATING",
232
  "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
234
- "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
- "79": "NOT_ALIVE",
238
- "8": "SUCCESS",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
- "86": "NON_PARTICIPATING",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "NON_PARTICIPATING",
249
  "9": "SUCCESS",
250
- "90": "SUCCESS",
251
- "91": "SUCCESS",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
@@ -256,7 +256,7 @@
256
  "96": "SUCCESS",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
259
- "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6481746,
268
- 6481763
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": 97,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6481031,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
+ "102": "FAIL",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "FAIL",
13
  "106": "NON_PARTICIPATING",
14
+ "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
+ "109": "FAIL",
17
+ "11": "FAIL",
18
  "110": "NOT_ALIVE",
19
+ "111": "NON_PARTICIPATING",
20
+ "112": "FAIL",
21
  "113": "SUCCESS",
22
+ "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "FAIL",
25
  "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
  "119": "SUCCESS",
 
29
  "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "FAIL",
33
  "124": "NOT_ALIVE",
34
+ "125": "NOT_ALIVE",
35
+ "126": "NON_PARTICIPATING",
36
  "127": "NON_PARTICIPATING",
37
+ "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
 
45
  "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
+ "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
54
+ "143": "NOT_ALIVE",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
+ "146": "FAIL",
58
  "147": "NOT_ALIVE",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
+ "15": "FAIL",
62
+ "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
+ "153": "FAIL",
66
+ "154": "SUCCESS",
67
+ "155": "NON_PARTICIPATING",
68
+ "156": "FAIL",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
71
  "159": "NON_PARTICIPATING",
 
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "NOT_ALIVE",
80
+ "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "FAIL",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
+ "171": "FAIL",
86
  "172": "NOT_ALIVE",
87
+ "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
+ "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
 
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
+ "183": "NON_PARTICIPATING",
99
+ "184": "FAIL",
100
+ "185": "SUCCESS",
101
+ "186": "NOT_ALIVE",
102
  "187": "NOT_ALIVE",
103
+ "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
+ "19": "NOT_ALIVE",
106
+ "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
  "198": "SUCCESS",
115
  "199": "NON_PARTICIPATING",
116
+ "2": "FAIL",
117
  "20": "NOT_ALIVE",
118
+ "200": "FAIL",
119
  "201": "NON_PARTICIPATING",
120
+ "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
+ "21": "FAIL",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "NOT_ALIVE",
131
+ "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "SUCCESS",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "FAIL",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NOT_ALIVE",
141
  "221": "SUCCESS",
142
+ "222": "FAIL",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
+ "225": "NON_PARTICIPATING",
146
+ "226": "NON_PARTICIPATING",
147
  "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
 
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NON_PARTICIPATING",
154
+ "233": "FAIL",
155
+ "234": "SUCCESS",
156
  "235": "SUCCESS",
157
+ "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
+ "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NON_PARTICIPATING",
168
+ "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
  "248": "NON_PARTICIPATING",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
+ "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
+ "252": "FAIL",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
+ "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
+ "28": "NON_PARTICIPATING",
182
+ "29": "FAIL",
183
  "3": "SUCCESS",
184
  "30": "NON_PARTICIPATING",
185
+ "31": "NOT_ALIVE",
186
+ "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
+ "34": "FAIL",
189
+ "35": "FAIL",
190
+ "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
+ "39": "FAIL",
194
  "4": "SUCCESS",
195
+ "40": "FAIL",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
+ "46": "NON_PARTICIPATING",
202
+ "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "NON_PARTICIPATING",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
 
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
215
+ "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
+ "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
+ "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
  "7": "SUCCESS",
 
231
  "73": "NON_PARTICIPATING",
232
  "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
234
+ "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
+ "79": "NON_PARTICIPATING",
238
+ "8": "FAIL",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "FAIL",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "NON_PARTICIPATING",
249
  "9": "SUCCESS",
250
+ "90": "FAIL",
251
+ "91": "FAIL",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
 
256
  "96": "SUCCESS",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
259
+ "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6481859,
268
+ 6481875
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": 6481823,
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 sha256:7bc70420f75eae672cdef8ccb1ae7da73bac15d121416281d1d5881c9657ac9f
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:674cce0ae5ac3d6ca2b1bfb2895a84926e4edecdecb4f63fa0d6bf78115a9e39
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d8dfab8fc36b8dd50ebe40917324e059c69aac914bab1983412bf3fe5667876
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff26bba00f6a6cb63ee56124dc84021e5d137698dbc3aaadf5385cf43c9720f4
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e06db807d7c2fa7d6569313330001c9e10d21cdc2de2e8799a8de720f6869f5
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:211e1c7511468bc8cfad606c3b6c04bbf6c00a03ee4f02f18adb15cdbced78eb
3
  size 4400216536