ncaagcc commited on
Commit
84be65d
·
verified ·
1 Parent(s): 2779dd1

Run 8. Outer Step 73. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +183 -182
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -5,258 +5,258 @@
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
- "101": "FAIL",
9
- "102": "FAIL",
10
  "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
- "106": "FAIL",
14
- "107": "FAIL",
15
- "108": "NON_PARTICIPATING",
16
- "109": "NON_PARTICIPATING",
17
- "11": "NOT_ALIVE",
18
- "110": "NOT_ALIVE",
19
- "111": "FAIL",
20
- "112": "FAIL",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
- "115": "FAIL",
24
- "116": "NON_PARTICIPATING",
25
- "117": "FAIL",
26
- "118": "NON_PARTICIPATING",
27
- "119": "FAIL",
28
  "12": "NOT_ALIVE",
29
- "120": "NON_PARTICIPATING",
30
- "121": "FAIL",
31
- "122": "FAIL",
32
- "123": "FAIL",
33
- "124": "FAIL",
34
  "125": "NOT_ALIVE",
35
- "126": "FAIL",
36
- "127": "FAIL",
37
- "128": "FAIL",
38
- "129": "FAIL",
39
- "13": "FAIL",
40
- "130": "FAIL",
41
  "131": "NON_PARTICIPATING",
42
- "132": "FAIL",
43
- "133": "FAIL",
44
- "134": "FAIL",
45
- "135": "NON_PARTICIPATING",
46
- "136": "FAIL",
47
- "137": "NON_PARTICIPATING",
48
- "138": "FAIL",
49
- "139": "FAIL",
50
  "14": "NOT_ALIVE",
51
- "140": "FAIL",
52
- "141": "NON_PARTICIPATING",
53
- "142": "FAIL",
54
- "143": "FAIL",
55
- "144": "NON_PARTICIPATING",
56
- "145": "FAIL",
57
  "146": "NON_PARTICIPATING",
58
- "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
- "149": "FAIL",
61
  "15": "NOT_ALIVE",
62
- "150": "FAIL",
63
  "151": "NON_PARTICIPATING",
64
- "152": "SUCCESS",
65
  "153": "NON_PARTICIPATING",
66
- "154": "FAIL",
67
- "155": "FAIL",
68
  "156": "NOT_ALIVE",
69
- "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
- "159": "NON_PARTICIPATING",
72
- "16": "FAIL",
73
  "160": "NON_PARTICIPATING",
74
- "161": "FAIL",
75
- "162": "FAIL",
76
  "163": "NON_PARTICIPATING",
77
- "164": "FAIL",
78
- "165": "FAIL",
79
- "166": "NON_PARTICIPATING",
80
- "167": "FAIL",
81
- "168": "FAIL",
82
- "169": "FAIL",
83
  "17": "NOT_ALIVE",
84
- "170": "NON_PARTICIPATING",
85
- "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
- "173": "NON_PARTICIPATING",
88
- "174": "FAIL",
89
  "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
- "177": "FAIL",
92
  "178": "NOT_ALIVE",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
- "180": "FAIL",
96
- "181": "NON_PARTICIPATING",
97
- "182": "FAIL",
98
- "183": "FAIL",
99
- "184": "FAIL",
100
- "185": "NOT_ALIVE",
101
- "186": "FAIL",
102
  "187": "NON_PARTICIPATING",
103
  "188": "FAIL",
104
- "189": "FAIL",
105
- "19": "FAIL",
106
  "190": "NON_PARTICIPATING",
107
- "191": "FAIL",
108
- "192": "NON_PARTICIPATING",
109
- "193": "FAIL",
110
- "194": "NON_PARTICIPATING",
111
- "195": "FAIL",
112
  "196": "FAIL",
113
  "197": "NOT_ALIVE",
114
- "198": "NOT_ALIVE",
115
  "199": "FAIL",
116
- "2": "NOT_ALIVE",
117
- "20": "FAIL",
118
- "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
- "202": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
- "204": "FAIL",
123
- "205": "FAIL",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NON_PARTICIPATING",
126
- "208": "NON_PARTICIPATING",
127
- "209": "FAIL",
128
  "21": "NOT_ALIVE",
129
- "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
- "212": "FAIL",
132
- "213": "FAIL",
133
  "214": "FAIL",
134
- "215": "FAIL",
135
- "216": "FAIL",
136
- "217": "FAIL",
137
- "218": "FAIL",
138
  "219": "NON_PARTICIPATING",
139
  "22": "FAIL",
140
- "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
- "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
- "225": "FAIL",
146
  "226": "NON_PARTICIPATING",
147
- "227": "NOT_ALIVE",
148
- "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
150
- "23": "NOT_ALIVE",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "FAIL",
155
- "234": "FAIL",
156
- "235": "NON_PARTICIPATING",
157
- "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
- "238": "NON_PARTICIPATING",
160
- "239": "NON_PARTICIPATING",
161
- "24": "FAIL",
162
- "240": "FAIL",
163
- "241": "NON_PARTICIPATING",
164
- "242": "FAIL",
165
  "243": "NON_PARTICIPATING",
166
- "244": "FAIL",
167
- "245": "FAIL",
168
- "246": "NON_PARTICIPATING",
169
- "247": "FAIL",
170
- "248": "FAIL",
171
- "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "FAIL",
174
- "251": "FAIL",
175
- "252": "NON_PARTICIPATING",
176
- "253": "FAIL",
177
- "254": "NOT_ALIVE",
178
- "255": "NOT_ALIVE",
179
- "26": "FAIL",
180
- "27": "FAIL",
181
- "28": "FAIL",
182
- "29": "FAIL",
183
  "3": "NOT_ALIVE",
184
  "30": "FAIL",
185
- "31": "NON_PARTICIPATING",
186
- "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
- "34": "FAIL",
189
  "35": "FAIL",
190
- "36": "FAIL",
191
- "37": "FAIL",
192
- "38": "NON_PARTICIPATING",
193
- "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
- "40": "FAIL",
196
- "41": "FAIL",
197
- "42": "NON_PARTICIPATING",
198
- "43": "FAIL",
199
- "44": "FAIL",
200
- "45": "NON_PARTICIPATING",
201
- "46": "FAIL",
202
  "47": "NON_PARTICIPATING",
203
- "48": "FAIL",
204
  "49": "FAIL",
205
- "5": "NOT_ALIVE",
206
- "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
- "52": "FAIL",
209
- "53": "FAIL",
210
- "54": "NON_PARTICIPATING",
211
- "55": "FAIL",
212
  "56": "NON_PARTICIPATING",
213
- "57": "FAIL",
214
- "58": "FAIL",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
- "60": "FAIL",
218
- "61": "NON_PARTICIPATING",
219
- "62": "FAIL",
220
- "63": "FAIL",
221
- "64": "NOT_ALIVE",
222
- "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
- "67": "NOT_ALIVE",
225
- "68": "FAIL",
226
- "69": "NON_PARTICIPATING",
227
- "7": "FAIL",
228
  "70": "NOT_ALIVE",
229
- "71": "NON_PARTICIPATING",
230
- "72": "FAIL",
231
  "73": "NON_PARTICIPATING",
232
- "74": "FAIL",
233
  "75": "NON_PARTICIPATING",
234
- "76": "FAIL",
235
- "77": "FAIL",
236
  "78": "NON_PARTICIPATING",
237
- "79": "FAIL",
238
  "8": "NOT_ALIVE",
239
- "80": "NON_PARTICIPATING",
240
- "81": "NON_PARTICIPATING",
241
- "82": "FAIL",
242
- "83": "FAIL",
243
  "84": "NON_PARTICIPATING",
244
- "85": "NON_PARTICIPATING",
245
- "86": "NOT_ALIVE",
246
- "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "FAIL",
251
- "91": "NOT_ALIVE",
252
- "92": "FAIL",
253
- "93": "FAIL",
254
  "94": "NON_PARTICIPATING",
255
  "95": "FAIL",
256
- "96": "FAIL",
257
- "97": "FAIL",
258
  "98": "NON_PARTICIPATING",
259
- "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,18 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6395001,
268
- 6395015
 
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": 67,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6394503,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
+ "101": "SUCCESS",
9
+ "102": "NON_PARTICIPATING",
10
  "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
+ "106": "SUCCESS",
14
+ "107": "SUCCESS",
15
+ "108": "SUCCESS",
16
+ "109": "SUCCESS",
17
+ "11": "SUCCESS",
18
+ "110": "NON_PARTICIPATING",
19
+ "111": "NON_PARTICIPATING",
20
+ "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
+ "115": "SUCCESS",
24
+ "116": "SUCCESS",
25
+ "117": "SUCCESS",
26
+ "118": "SUCCESS",
27
+ "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
+ "120": "FAIL",
30
+ "121": "NON_PARTICIPATING",
31
+ "122": "SUCCESS",
32
+ "123": "SUCCESS",
33
+ "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
+ "126": "SUCCESS",
36
+ "127": "SUCCESS",
37
+ "128": "NON_PARTICIPATING",
38
+ "129": "NON_PARTICIPATING",
39
+ "13": "SUCCESS",
40
+ "130": "SUCCESS",
41
  "131": "NON_PARTICIPATING",
42
+ "132": "SUCCESS",
43
+ "133": "SUCCESS",
44
+ "134": "NON_PARTICIPATING",
45
+ "135": "SUCCESS",
46
+ "136": "NON_PARTICIPATING",
47
+ "137": "FAIL",
48
+ "138": "NOT_ALIVE",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
+ "140": "SUCCESS",
52
+ "141": "SUCCESS",
53
+ "142": "SUCCESS",
54
+ "143": "NON_PARTICIPATING",
55
+ "144": "SUCCESS",
56
+ "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
+ "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
+ "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
+ "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
+ "154": "SUCCESS",
67
+ "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
+ "157": "FAIL",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "SUCCESS",
72
+ "16": "SUCCESS",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "NON_PARTICIPATING",
75
+ "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
+ "164": "SUCCESS",
78
+ "165": "SUCCESS",
79
+ "166": "SUCCESS",
80
+ "167": "NON_PARTICIPATING",
81
+ "168": "NON_PARTICIPATING",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
+ "170": "SUCCESS",
85
+ "171": "SUCCESS",
86
  "172": "NON_PARTICIPATING",
87
+ "173": "SUCCESS",
88
+ "174": "SUCCESS",
89
  "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
+ "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
+ "180": "SUCCESS",
96
+ "181": "NOT_ALIVE",
97
+ "182": "NON_PARTICIPATING",
98
+ "183": "NON_PARTICIPATING",
99
+ "184": "NON_PARTICIPATING",
100
+ "185": "SUCCESS",
101
+ "186": "SUCCESS",
102
  "187": "NON_PARTICIPATING",
103
  "188": "FAIL",
104
+ "189": "SUCCESS",
105
+ "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "NON_PARTICIPATING",
108
+ "192": "SUCCESS",
109
+ "193": "NOT_ALIVE",
110
+ "194": "SUCCESS",
111
+ "195": "NON_PARTICIPATING",
112
  "196": "FAIL",
113
  "197": "NOT_ALIVE",
114
+ "198": "NON_PARTICIPATING",
115
  "199": "FAIL",
116
+ "2": "SUCCESS",
117
+ "20": "NOT_ALIVE",
118
+ "200": "FAIL",
119
  "201": "NOT_ALIVE",
120
+ "202": "FAIL",
121
+ "203": "FAIL",
122
+ "204": "NON_PARTICIPATING",
123
+ "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NON_PARTICIPATING",
126
+ "208": "SUCCESS",
127
+ "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
+ "212": "SUCCESS",
132
+ "213": "NON_PARTICIPATING",
133
  "214": "FAIL",
134
+ "215": "NON_PARTICIPATING",
135
+ "216": "NOT_ALIVE",
136
+ "217": "SUCCESS",
137
+ "218": "SUCCESS",
138
  "219": "NON_PARTICIPATING",
139
  "22": "FAIL",
140
+ "220": "SUCCESS",
141
  "221": "NON_PARTICIPATING",
142
+ "222": "SUCCESS",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
+ "227": "NON_PARTICIPATING",
148
+ "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
+ "23": "SUCCESS",
151
+ "230": "FAIL",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
+ "233": "SUCCESS",
155
+ "234": "SUCCESS",
156
+ "235": "SUCCESS",
157
+ "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "SUCCESS",
160
+ "239": "SUCCESS",
161
+ "24": "SUCCESS",
162
+ "240": "NOT_ALIVE",
163
+ "241": "NOT_ALIVE",
164
+ "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
+ "244": "SUCCESS",
167
+ "245": "SUCCESS",
168
+ "246": "SUCCESS",
169
+ "247": "NON_PARTICIPATING",
170
+ "248": "NOT_ALIVE",
171
+ "249": "SUCCESS",
172
  "25": "SUCCESS",
173
+ "250": "SUCCESS",
174
+ "251": "NOT_ALIVE",
175
+ "252": "SUCCESS",
176
+ "253": "NOT_ALIVE",
177
+ "254": "NON_PARTICIPATING",
178
+ "255": "NON_PARTICIPATING",
179
+ "26": "SUCCESS",
180
+ "27": "SUCCESS",
181
+ "28": "SUCCESS",
182
+ "29": "SUCCESS",
183
  "3": "NOT_ALIVE",
184
  "30": "FAIL",
185
+ "31": "SUCCESS",
186
+ "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
+ "34": "SUCCESS",
189
  "35": "FAIL",
190
+ "36": "SUCCESS",
191
+ "37": "SUCCESS",
192
+ "38": "FAIL",
193
+ "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
+ "40": "NOT_ALIVE",
196
+ "41": "SUCCESS",
197
+ "42": "SUCCESS",
198
+ "43": "NOT_ALIVE",
199
+ "44": "NOT_ALIVE",
200
+ "45": "NOT_ALIVE",
201
+ "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
+ "48": "SUCCESS",
204
  "49": "FAIL",
205
+ "5": "SUCCESS",
206
+ "50": "SUCCESS",
207
  "51": "NON_PARTICIPATING",
208
+ "52": "SUCCESS",
209
+ "53": "SUCCESS",
210
+ "54": "SUCCESS",
211
+ "55": "SUCCESS",
212
  "56": "NON_PARTICIPATING",
213
+ "57": "SUCCESS",
214
+ "58": "SUCCESS",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
+ "61": "FAIL",
219
+ "62": "SUCCESS",
220
+ "63": "SUCCESS",
221
+ "64": "NON_PARTICIPATING",
222
+ "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
+ "67": "NON_PARTICIPATING",
225
+ "68": "SUCCESS",
226
+ "69": "SUCCESS",
227
+ "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
+ "71": "SUCCESS",
230
+ "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
+ "76": "SUCCESS",
235
+ "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
+ "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
+ "80": "SUCCESS",
240
+ "81": "NOT_ALIVE",
241
+ "82": "NON_PARTICIPATING",
242
+ "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
+ "85": "SUCCESS",
245
+ "86": "NON_PARTICIPATING",
246
+ "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "FAIL",
251
+ "91": "NON_PARTICIPATING",
252
+ "92": "SUCCESS",
253
+ "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "FAIL",
256
+ "96": "NON_PARTICIPATING",
257
+ "97": "SUCCESS",
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
+ 6395212,
268
+ 6395228,
269
+ 6395246
270
  ],
271
  "bos_token_id": 1,
272
  "eos_token_id": 2,
273
  "hidden_act": "silu",
274
  "hidden_size": 2048,
275
  "initializer_range": 0.02,
276
+ "inner_step": 4,
277
  "intermediate_size": 5632,
278
+ "last_allreduce_block": 6395177,
279
  "max_position_embeddings": 2048,
280
  "mlp_bias": false,
281
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:548ba78a55f8a811d07c6f5c33055620fb092ec54b889fd8a49ea2864dd8e4a0
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6942f3b665124a7aa1fc2f904fb88c658713d9c49f116ee941290d99007d5598
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6846090d40ae82db27b9f57a2944944d964ddf35b12ed4192b6f2748440d7edd
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fdf547dc041179bcbcbb6655cc1c7f7ae978af2bb9e37e1def757adf483b363
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77bd59ef1cdc5e3f85bd7c9cfb89d65b86aa89799c0f5fe782b62add7cc27c1e
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9bb02110dfd3ed555681f5714b0570368efce08419fffadf28db2b908288c40
3
  size 4400216536