mizzaay commited on
Commit
c486621
·
verified ·
1 Parent(s): 6727e44

Run 8. Outer Step 113. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +63 -63
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -3,16 +3,16 @@
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
- "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
- "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
- "108": "NOT_ALIVE",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
@@ -22,48 +22,48 @@
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
- "117": "NON_PARTICIPATING",
26
  "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
- "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
- "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
37
- "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
- "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
- "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "SUCCESS",
50
  "14": "SUCCESS",
51
  "140": "NOT_ALIVE",
52
- "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
- "147": "NOT_ALIVE",
59
- "148": "NOT_ALIVE",
60
- "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
- "151": "NOT_ALIVE",
64
- "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
- "154": "SUCCESS",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
@@ -81,18 +81,18 @@
81
  "168": "SUCCESS",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
- "170": "SUCCESS",
85
- "171": "SUCCESS",
86
  "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
- "178": "SUCCESS",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
- "180": "NON_PARTICIPATING",
96
  "181": "NON_PARTICIPATING",
97
  "182": "SUCCESS",
98
  "183": "SUCCESS",
@@ -105,50 +105,50 @@
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
- "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
  "194": "SUCCESS",
111
  "195": "NON_PARTICIPATING",
112
- "196": "NON_PARTICIPATING",
113
  "197": "NOT_ALIVE",
114
  "198": "SUCCESS",
115
- "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
  "206": "SUCCESS",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
- "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
  "210": "SUCCESS",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
- "213": "SUCCESS",
133
  "214": "SUCCESS",
134
  "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
  "218": "SUCCESS",
138
- "219": "NON_PARTICIPATING",
139
  "22": "SUCCESS",
140
  "220": "SUCCESS",
141
- "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
- "226": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
@@ -159,55 +159,55 @@
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
- "240": "SUCCESS",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
- "246": "NOT_ALIVE",
169
- "247": "SUCCESS",
170
- "248": "NON_PARTICIPATING",
171
- "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "SUCCESS",
175
  "252": "NON_PARTICIPATING",
176
- "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
- "29": "NOT_ALIVE",
183
  "3": "NOT_ALIVE",
184
- "30": "NON_PARTICIPATING",
185
- "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
- "35": "NOT_ALIVE",
190
- "36": "SUCCESS",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NON_PARTICIPATING",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
- "41": "SUCCESS",
197
  "42": "NOT_ALIVE",
198
  "43": "SUCCESS",
199
  "44": "NON_PARTICIPATING",
200
- "45": "NOT_ALIVE",
201
  "46": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
- "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
  "57": "NOT_ALIVE",
@@ -216,22 +216,22 @@
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
- "62": "SUCCESS",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
- "68": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
- "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
- "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
- "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
- "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
@@ -241,21 +241,21 @@
241
  "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
- "85": "NOT_ALIVE",
245
  "86": "SUCCESS",
246
  "87": "SUCCESS",
247
- "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
- "93": "NON_PARTICIPATING",
254
  "94": "SUCCESS",
255
  "95": "NON_PARTICIPATING",
256
  "96": "SUCCESS",
257
- "97": "NOT_ALIVE",
258
- "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6432014,
268
- 6432031
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": 83,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6431412,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
+ "10": "SUCCESS",
7
  "100": "NON_PARTICIPATING",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
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": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
 
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
+ "122": "NOT_ALIVE",
32
  "123": "NON_PARTICIPATING",
33
+ "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
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": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
+ "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "SUCCESS",
50
  "14": "SUCCESS",
51
  "140": "NOT_ALIVE",
52
+ "141": "SUCCESS",
53
  "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
+ "147": "NON_PARTICIPATING",
59
+ "148": "NON_PARTICIPATING",
60
+ "149": "NOT_ALIVE",
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": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
 
81
  "168": "SUCCESS",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
+ "170": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
+ "180": "NOT_ALIVE",
96
  "181": "NON_PARTICIPATING",
97
  "182": "SUCCESS",
98
  "183": "SUCCESS",
 
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
+ "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "SUCCESS",
111
  "195": "NON_PARTICIPATING",
112
+ "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "SUCCESS",
115
+ "199": "FAIL",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "NOT_ALIVE",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
  "206": "SUCCESS",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
+ "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "SUCCESS",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
+ "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
  "218": "SUCCESS",
138
+ "219": "SUCCESS",
139
  "22": "SUCCESS",
140
  "220": "SUCCESS",
141
+ "221": "SUCCESS",
142
  "222": "NON_PARTICIPATING",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
+ "226": "NOT_ALIVE",
147
+ "227": "NON_PARTICIPATING",
148
+ "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
+ "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
 
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
+ "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
176
+ "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
+ "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
+ "30": "NOT_ALIVE",
185
+ "31": "NOT_ALIVE",
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": "NON_PARTICIPATING",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "SUCCESS",
199
  "44": "NON_PARTICIPATING",
200
+ "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
+ "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "SUCCESS",
208
+ "52": "SUCCESS",
209
  "53": "NON_PARTICIPATING",
210
+ "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
  "57": "NOT_ALIVE",
 
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
+ "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
+ "70": "FAIL",
229
  "71": "NON_PARTICIPATING",
230
+ "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
+ "76": "SUCCESS",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
 
241
  "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
+ "85": "NON_PARTICIPATING",
245
  "86": "SUCCESS",
246
  "87": "SUCCESS",
247
+ "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
+ "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NON_PARTICIPATING",
256
  "96": "SUCCESS",
257
+ "97": "NON_PARTICIPATING",
258
+ "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6432100,
268
+ 6432126
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": 6432065,
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 sha256:5f015474444a61cd6b3930e6855e168e74bab61cc5f8e77dffe9ca5c5386ea72
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20fed691043429c23f49e69d24d1e4a17b371b77e5915fde147a17327253b21b
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b60d51ef809ea1cfdbaecd70c760efa36d8af268f0a33d4bac0eae17fbef8c8
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbb308990d36fc710ab11ea441c846eb75fdd14beb88a992ca082225fd6f50eb
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d055c7aff0c4dfea7de8e3ef6290ee0128ddf7144464486925c9d8d504748dfa
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25452d33ccb70f2d3c6c643b86767f20ffb568d8c6a4c58bc9c43cd8129b741d
3
  size 4400216536