ncaagcc commited on
Commit
568af70
·
verified ·
1 Parent(s): fedeccb

Run 5. Outer Step 115. Inner Step 1.

Browse files
Files changed (3) hide show
  1. config.json +147 -147
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -2,259 +2,259 @@
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "NON_PARTICIPATING",
6
- "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
- "101": "NON_PARTICIPATING",
9
- "102": "NON_PARTICIPATING",
10
- "103": "SUCCESS",
11
- "104": "NON_PARTICIPATING",
12
- "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
- "107": "NON_PARTICIPATING",
15
- "108": "NON_PARTICIPATING",
16
  "109": "NOT_ALIVE",
17
- "11": "SUCCESS",
18
- "110": "NOT_ALIVE",
19
- "111": "NON_PARTICIPATING",
20
- "112": "NOT_ALIVE",
21
- "113": "NON_PARTICIPATING",
22
- "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
- "118": "NON_PARTICIPATING",
27
  "119": "NOT_ALIVE",
28
  "12": "NON_PARTICIPATING",
29
- "120": "NON_PARTICIPATING",
30
- "121": "NON_PARTICIPATING",
31
- "122": "SUCCESS",
32
- "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
- "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
37
- "128": "NON_PARTICIPATING",
38
- "129": "NON_PARTICIPATING",
39
- "13": "NON_PARTICIPATING",
40
- "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
- "132": "NOT_ALIVE",
43
- "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
- "136": "NOT_ALIVE",
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": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NON_PARTICIPATING",
57
- "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
- "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
- "15": "NON_PARTICIPATING",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
- "152": "NON_PARTICIPATING",
65
  "153": "NOT_ALIVE",
66
- "154": "NON_PARTICIPATING",
67
- "155": "NON_PARTICIPATING",
68
- "156": "NON_PARTICIPATING",
69
- "157": "NON_PARTICIPATING",
70
- "158": "NON_PARTICIPATING",
71
- "159": "NON_PARTICIPATING",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
- "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
- "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
- "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
- "168": "SUCCESS",
82
- "169": "NON_PARTICIPATING",
83
- "17": "NON_PARTICIPATING",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
- "172": "NON_PARTICIPATING",
87
- "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
- "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
- "177": "NON_PARTICIPATING",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NOT_ALIVE",
94
- "18": "NON_PARTICIPATING",
95
  "180": "NOT_ALIVE",
96
- "181": "SUCCESS",
97
  "182": "NOT_ALIVE",
98
- "183": "NON_PARTICIPATING",
99
- "184": "NON_PARTICIPATING",
100
- "185": "NON_PARTICIPATING",
101
- "186": "NON_PARTICIPATING",
102
  "187": "NOT_ALIVE",
103
- "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
- "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
- "194": "NON_PARTICIPATING",
111
- "195": "NON_PARTICIPATING",
112
- "196": "NON_PARTICIPATING",
113
- "197": "NOT_ALIVE",
114
  "198": "NOT_ALIVE",
115
  "199": "NON_PARTICIPATING",
116
- "2": "NON_PARTICIPATING",
117
  "20": "NOT_ALIVE",
118
- "200": "NON_PARTICIPATING",
119
- "201": "NON_PARTICIPATING",
120
- "202": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
- "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
- "208": "NON_PARTICIPATING",
127
- "209": "NON_PARTICIPATING",
128
- "21": "NON_PARTICIPATING",
129
  "210": "NON_PARTICIPATING",
130
- "211": "NON_PARTICIPATING",
131
- "212": "NON_PARTICIPATING",
132
- "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
- "215": "NON_PARTICIPATING",
135
- "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
- "218": "NON_PARTICIPATING",
138
- "219": "NON_PARTICIPATING",
139
- "22": "NON_PARTICIPATING",
140
- "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
142
- "222": "NON_PARTICIPATING",
143
- "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
- "225": "NON_PARTICIPATING",
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
- "228": "NON_PARTICIPATING",
149
- "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
- "232": "NON_PARTICIPATING",
154
- "233": "NON_PARTICIPATING",
155
- "234": "NON_PARTICIPATING",
156
- "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
- "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
- "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
- "240": "NON_PARTICIPATING",
163
- "241": "NON_PARTICIPATING",
164
- "242": "NON_PARTICIPATING",
165
- "243": "NON_PARTICIPATING",
166
- "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
- "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
- "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
- "253": "NON_PARTICIPATING",
177
- "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
- "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
183
- "3": "NOT_ALIVE",
184
- "30": "NOT_ALIVE",
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": "SUCCESS",
196
- "41": "SUCCESS",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
- "46": "NON_PARTICIPATING",
202
- "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
- "5": "SUCCESS",
206
- "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NOT_ALIVE",
210
  "54": "NON_PARTICIPATING",
211
- "55": "NON_PARTICIPATING",
212
- "56": "SUCCESS",
213
  "57": "NON_PARTICIPATING",
214
- "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NON_PARTICIPATING",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
- "62": "SUCCESS",
220
- "63": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
- "66": "NON_PARTICIPATING",
224
- "67": "NON_PARTICIPATING",
225
  "68": "NON_PARTICIPATING",
226
- "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
- "70": "NON_PARTICIPATING",
229
- "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
- "73": "NON_PARTICIPATING",
232
  "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
- "76": "NOT_ALIVE",
235
- "77": "NON_PARTICIPATING",
236
- "78": "NON_PARTICIPATING",
237
- "79": "NON_PARTICIPATING",
238
- "8": "NON_PARTICIPATING",
239
- "80": "NON_PARTICIPATING",
240
- "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
- "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
246
  "87": "NON_PARTICIPATING",
247
- "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NON_PARTICIPATING",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NON_PARTICIPATING",
254
- "94": "NON_PARTICIPATING",
255
- "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
- "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NOT_ALIVE"
260
  },
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5931068,
268
- 5931085
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": 39,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5930047,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "NOT_ALIVE",
6
+ "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
+ "101": "NOT_ALIVE",
9
+ "102": "NOT_ALIVE",
10
+ "103": "NON_PARTICIPATING",
11
+ "104": "NOT_ALIVE",
12
+ "105": "NOT_ALIVE",
13
  "106": "NOT_ALIVE",
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": "SUCCESS",
21
+ "113": "NOT_ALIVE",
22
+ "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
+ "118": "NOT_ALIVE",
27
  "119": "NOT_ALIVE",
28
  "12": "NON_PARTICIPATING",
29
+ "120": "NOT_ALIVE",
30
+ "121": "NOT_ALIVE",
31
+ "122": "NON_PARTICIPATING",
32
+ "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
+ "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
37
+ "128": "NOT_ALIVE",
38
+ "129": "NOT_ALIVE",
39
+ "13": "NOT_ALIVE",
40
+ "130": "NOT_ALIVE",
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": "NOT_ALIVE",
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": "NON_PARTICIPATING",
56
  "145": "NON_PARTICIPATING",
57
+ "146": "NOT_ALIVE",
58
  "147": "NOT_ALIVE",
59
+ "148": "SUCCESS",
60
  "149": "NON_PARTICIPATING",
61
+ "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
+ "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
+ "154": "SUCCESS",
67
+ "155": "SUCCESS",
68
+ "156": "NOT_ALIVE",
69
+ "157": "NOT_ALIVE",
70
+ "158": "NOT_ALIVE",
71
+ "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
+ "165": "NOT_ALIVE",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
+ "168": "NON_PARTICIPATING",
82
+ "169": "NOT_ALIVE",
83
+ "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
+ "172": "NOT_ALIVE",
87
+ "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
+ "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
+ "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NOT_ALIVE",
94
+ "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
+ "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
+ "183": "NOT_ALIVE",
99
+ "184": "NOT_ALIVE",
100
+ "185": "NOT_ALIVE",
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": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
+ "194": "NOT_ALIVE",
111
+ "195": "NOT_ALIVE",
112
+ "196": "SUCCESS",
113
+ "197": "SUCCESS",
114
  "198": "NOT_ALIVE",
115
  "199": "NON_PARTICIPATING",
116
+ "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "NOT_ALIVE",
119
+ "201": "NOT_ALIVE",
120
+ "202": "NOT_ALIVE",
121
+ "203": "NOT_ALIVE",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
+ "208": "NOT_ALIVE",
127
+ "209": "NOT_ALIVE",
128
+ "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "NOT_ALIVE",
131
+ "212": "SUCCESS",
132
+ "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
+ "215": "SUCCESS",
135
+ "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
+ "218": "NOT_ALIVE",
138
+ "219": "NOT_ALIVE",
139
+ "22": "NOT_ALIVE",
140
+ "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
+ "222": "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",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
+ "232": "NOT_ALIVE",
154
+ "233": "NOT_ALIVE",
155
+ "234": "NOT_ALIVE",
156
+ "235": "NOT_ALIVE",
157
  "236": "NOT_ALIVE",
158
+ "237": "SUCCESS",
159
  "238": "NON_PARTICIPATING",
160
+ "239": "NOT_ALIVE",
161
  "24": "NON_PARTICIPATING",
162
+ "240": "NOT_ALIVE",
163
+ "241": "NOT_ALIVE",
164
+ "242": "NOT_ALIVE",
165
+ "243": "NOT_ALIVE",
166
+ "244": "NOT_ALIVE",
167
  "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
+ "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NOT_ALIVE",
174
+ "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
+ "253": "NOT_ALIVE",
177
+ "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "NOT_ALIVE",
180
  "27": "NON_PARTICIPATING",
181
+ "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
183
+ "3": "NON_PARTICIPATING",
184
+ "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
186
+ "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
+ "34": "NON_PARTICIPATING",
189
+ "35": "NOT_ALIVE",
190
+ "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
+ "38": "NOT_ALIVE",
193
+ "39": "SUCCESS",
194
+ "4": "NOT_ALIVE",
195
+ "40": "NON_PARTICIPATING",
196
+ "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
+ "46": "NOT_ALIVE",
202
+ "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "NON_PARTICIPATING",
206
+ "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NOT_ALIVE",
210
  "54": "NON_PARTICIPATING",
211
+ "55": "NOT_ALIVE",
212
+ "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
+ "58": "SUCCESS",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NON_PARTICIPATING",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
+ "62": "NOT_ALIVE",
220
+ "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
+ "66": "NOT_ALIVE",
224
+ "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
+ "69": "NOT_ALIVE",
227
  "7": "NON_PARTICIPATING",
228
+ "70": "NOT_ALIVE",
229
+ "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
+ "73": "SUCCESS",
232
  "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
+ "76": "NON_PARTICIPATING",
235
+ "77": "NOT_ALIVE",
236
+ "78": "NOT_ALIVE",
237
+ "79": "NOT_ALIVE",
238
+ "8": "NOT_ALIVE",
239
+ "80": "NOT_ALIVE",
240
+ "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
246
  "87": "NON_PARTICIPATING",
247
+ "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NON_PARTICIPATING",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NON_PARTICIPATING",
254
+ "94": "SUCCESS",
255
+ "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
+ "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NOT_ALIVE"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5976124,
268
+ 5976139
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": 5975514,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba9ae1c17aa77386c0ac69cba3cb7d3fffcba5311a5ecaff4b21430a2e72b54d
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0afe47dd835d082d9a4c550733586d3d9716f061fd41f4f5690b259d3c9e46b
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4df7e68d417cfd0d4b011a541a1b2dced9533b799ebbf95f17fef2534de6d33
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2ff2dc691545660d490b15268ba0870451c6ae37210c4c5f34b3a858fa08307
3
  size 4400216536