ncaagcc commited on
Commit
9953d22
·
verified ·
1 Parent(s): dcf018f

Run 8. Outer Step 100. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +76 -76
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -9,25 +9,25 @@
9
  "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
- "105": "NOT_ALIVE",
13
- "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
- "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
- "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
- "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
  "118": "NON_PARTICIPATING",
27
- "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
@@ -37,17 +37,17 @@
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
- "130": "SUCCESS",
41
  "131": "NON_PARTICIPATING",
42
- "132": "SUCCESS",
43
  "133": "NOT_ALIVE",
44
- "134": "SUCCESS",
45
- "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
- "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
- "14": "SUCCESS",
51
  "140": "NOT_ALIVE",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NOT_ALIVE",
@@ -57,61 +57,61 @@
57
  "146": "NON_PARTICIPATING",
58
  "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
- "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
- "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
- "154": "SUCCESS",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
- "158": "SUCCESS",
71
  "159": "SUCCESS",
72
  "16": "SUCCESS",
73
  "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
- "162": "NOT_ALIVE",
76
  "163": "NOT_ALIVE",
77
- "164": "NOT_ALIVE",
78
- "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
- "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
- "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
93
- "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
- "181": "SUCCESS",
97
  "182": "NOT_ALIVE",
98
- "183": "NON_PARTICIPATING",
99
  "184": "SUCCESS",
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": "FAIL",
108
  "192": "NON_PARTICIPATING",
109
- "193": "SUCCESS",
110
  "194": "SUCCESS",
111
  "195": "NON_PARTICIPATING",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
- "198": "NON_PARTICIPATING",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
@@ -119,24 +119,24 @@
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NOT_ALIVE",
122
- "204": "SUCCESS",
123
  "205": "NOT_ALIVE",
124
- "206": "SUCCESS",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
- "21": "NOT_ALIVE",
129
- "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
  "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
- "215": "NOT_ALIVE",
135
  "216": "SUCCESS",
136
- "217": "SUCCESS",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
- "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
  "221": "NON_PARTICIPATING",
142
  "222": "SUCCESS",
@@ -146,77 +146,77 @@
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
  "228": "SUCCESS",
149
- "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
- "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
- "235": "SUCCESS",
157
  "236": "SUCCESS",
158
  "237": "SUCCESS",
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
- "241": "SUCCESS",
164
- "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
- "247": "NON_PARTICIPATING",
170
  "248": "SUCCESS",
171
- "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
  "251": "SUCCESS",
175
  "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "SUCCESS",
179
  "26": "SUCCESS",
180
- "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
182
- "29": "NOT_ALIVE",
183
- "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
- "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
- "35": "NON_PARTICIPATING",
190
  "36": "FAIL",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
- "39": "NON_PARTICIPATING",
194
- "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "SUCCESS",
197
  "42": "NOT_ALIVE",
198
  "43": "SUCCESS",
199
  "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
- "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
- "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "SUCCESS",
208
- "52": "NOT_ALIVE",
209
- "53": "NOT_ALIVE",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
  "56": "SUCCESS",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
- "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
- "60": "NON_PARTICIPATING",
218
- "61": "NON_PARTICIPATING",
219
- "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
@@ -226,12 +226,12 @@
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
- "71": "SUCCESS",
230
- "72": "NON_PARTICIPATING",
231
- "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
- "76": "SUCCESS",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
@@ -241,9 +241,9 @@
241
  "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
- "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
246
- "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "SUCCESS",
@@ -251,11 +251,11 @@
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
- "94": "NOT_ALIVE",
255
  "95": "NON_PARTICIPATING",
256
- "96": "FAIL",
257
  "97": "NON_PARTICIPATING",
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
- 6423799,
268
- 6423807
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": 133,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6423242,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
9
  "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
+ "105": "NON_PARTICIPATING",
13
+ "106": "FAIL",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
+ "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "NOT_ALIVE",
20
  "112": "NON_PARTICIPATING",
21
+ "113": "SUCCESS",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
 
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
+ "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
+ "132": "NON_PARTICIPATING",
43
  "133": "NOT_ALIVE",
44
+ "134": "NOT_ALIVE",
45
+ "135": "NOT_ALIVE",
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",
 
57
  "146": "NON_PARTICIPATING",
58
  "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
+ "152": "SUCCESS",
65
  "153": "NON_PARTICIPATING",
66
+ "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "FAIL",
71
  "159": "SUCCESS",
72
  "16": "SUCCESS",
73
  "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
+ "162": "SUCCESS",
76
  "163": "NOT_ALIVE",
77
+ "164": "NON_PARTICIPATING",
78
+ "165": "NOT_ALIVE",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
+ "168": "FAIL",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
+ "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
93
+ "179": "FAIL",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
+ "181": "NON_PARTICIPATING",
97
  "182": "NOT_ALIVE",
98
+ "183": "SUCCESS",
99
  "184": "SUCCESS",
100
+ "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
+ "187": "NON_PARTICIPATING",
103
+ "188": "SUCCESS",
104
+ "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "SUCCESS",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "SUCCESS",
111
  "195": "NON_PARTICIPATING",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
+ "198": "NOT_ALIVE",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
 
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NOT_ALIVE",
122
+ "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
+ "206": "NON_PARTICIPATING",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
+ "21": "FAIL",
129
+ "210": "SUCCESS",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
  "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
+ "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
+ "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
+ "22": "SUCCESS",
140
  "220": "NOT_ALIVE",
141
  "221": "NON_PARTICIPATING",
142
  "222": "SUCCESS",
 
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
  "228": "SUCCESS",
149
+ "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
+ "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
+ "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
+ "235": "FAIL",
157
  "236": "SUCCESS",
158
  "237": "SUCCESS",
159
  "238": "SUCCESS",
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": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "SUCCESS",
170
  "248": "SUCCESS",
171
+ "249": "SUCCESS",
172
  "25": "SUCCESS",
173
+ "250": "FAIL",
174
  "251": "SUCCESS",
175
  "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "SUCCESS",
179
  "26": "SUCCESS",
180
+ "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
+ "29": "NON_PARTICIPATING",
183
+ "3": "FAIL",
184
  "30": "NOT_ALIVE",
185
+ "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
+ "35": "FAIL",
190
  "36": "FAIL",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
+ "39": "NOT_ALIVE",
194
+ "4": "SUCCESS",
195
  "40": "NON_PARTICIPATING",
196
  "41": "SUCCESS",
197
  "42": "NOT_ALIVE",
198
  "43": "SUCCESS",
199
  "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
+ "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
+ "48": "FAIL",
204
  "49": "NON_PARTICIPATING",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "SUCCESS",
208
+ "52": "NON_PARTICIPATING",
209
+ "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
  "56": "SUCCESS",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
+ "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
+ "60": "FAIL",
218
+ "61": "FAIL",
219
+ "62": "SUCCESS",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
 
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
+ "71": "NON_PARTICIPATING",
230
+ "72": "NOT_ALIVE",
231
+ "73": "NON_PARTICIPATING",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
+ "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
 
241
  "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
+ "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
+ "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "SUCCESS",
 
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
+ "94": "NON_PARTICIPATING",
255
  "95": "NON_PARTICIPATING",
256
+ "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
+ "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6423857,
268
+ 6423865
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": 6423834,
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 sha256:2d4661622ad5635544ac9847b51dfbf8b4cd75a4d0d968ffaec6d2a2c34b26b3
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e79096e82e663ae8a40dfd01154f9bf1c192e40d71be475e34bc72a00c2c74c
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bc3ef97965e052d10a24cb24fe3b404523f1cab76083f1c4be34b1d2c1cabc5
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:389b55065b553d8b5d8d219d856cac736ae7ada5e72efdfc26e262a113b895cd
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:677184de6ec90f96ab18a9e9d21796be2babcfe5e280aa04f92afd82261a7e59
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ed55b3ef351e191dca8b154bd144a4fa239c912c54bed4a7de89832dd17b419
3
  size 4400216536