snoopsy commited on
Commit
72b6518
·
verified ·
1 Parent(s): b3e7926

Run 8. Outer Step 38. Inner Step 4.

Browse files
Files changed (4) hide show
  1. config.json +78 -80
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -10,7 +10,7 @@
10
  "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
  "105": "SUCCESS",
13
- "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
@@ -20,9 +20,9 @@
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
- "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
- "117": "FAIL",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
@@ -30,63 +30,63 @@
30
  "121": "SUCCESS",
31
  "122": "FAIL",
32
  "123": "FAIL",
33
- "124": "SUCCESS",
34
  "125": "NOT_ALIVE",
35
- "126": "NON_PARTICIPATING",
36
- "127": "FAIL",
37
  "128": "FAIL",
38
  "129": "SUCCESS",
39
  "13": "NOT_ALIVE",
40
- "130": "NON_PARTICIPATING",
41
- "131": "NON_PARTICIPATING",
42
- "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
- "134": "SUCCESS",
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "SUCCESS",
49
- "139": "SUCCESS",
50
- "14": "FAIL",
51
- "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
  "142": "FAIL",
54
- "143": "SUCCESS",
55
  "144": "SUCCESS",
56
- "145": "SUCCESS",
57
  "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
  "148": "SUCCESS",
60
- "149": "NON_PARTICIPATING",
61
  "15": "SUCCESS",
62
- "150": "NOT_ALIVE",
63
- "151": "NOT_ALIVE",
64
- "152": "NON_PARTICIPATING",
65
  "153": "FAIL",
66
  "154": "NON_PARTICIPATING",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
- "157": "NOT_ALIVE",
70
  "158": "SUCCESS",
71
  "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
  "160": "NON_PARTICIPATING",
74
- "161": "FAIL",
75
- "162": "FAIL",
76
- "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
- "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
80
  "167": "NON_PARTICIPATING",
81
- "168": "FAIL",
82
  "169": "FAIL",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
- "173": "FAIL",
88
  "174": "SUCCESS",
89
- "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
@@ -95,20 +95,20 @@
95
  "180": "NON_PARTICIPATING",
96
  "181": "SUCCESS",
97
  "182": "NOT_ALIVE",
98
- "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "FAIL",
101
  "186": "SUCCESS",
102
- "187": "SUCCESS",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
- "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
  "192": "SUCCESS",
109
- "193": "SUCCESS",
110
- "194": "SUCCESS",
111
- "195": "FAIL",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
@@ -118,120 +118,120 @@
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "FAIL",
122
- "204": "FAIL",
123
- "205": "SUCCESS",
124
- "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
- "208": "FAIL",
127
  "209": "NOT_ALIVE",
128
- "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
- "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "SUCCESS",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
  "218": "FAIL",
138
- "219": "FAIL",
139
  "22": "NOT_ALIVE",
140
- "220": "NON_PARTICIPATING",
141
- "221": "SUCCESS",
142
  "222": "SUCCESS",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
- "228": "FAIL",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
- "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
- "238": "FAIL",
160
  "239": "FAIL",
161
  "24": "SUCCESS",
162
- "240": "NON_PARTICIPATING",
163
  "241": "FAIL",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
- "245": "NOT_ALIVE",
168
  "246": "SUCCESS",
169
- "247": "FAIL",
170
  "248": "NOT_ALIVE",
171
- "249": "SUCCESS",
172
  "25": "SUCCESS",
173
- "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
- "252": "FAIL",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
- "255": "NOT_ALIVE",
179
- "26": "SUCCESS",
180
- "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
  "3": "NOT_ALIVE",
184
- "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
186
  "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "SUCCESS",
190
- "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
- "38": "SUCCESS",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "FAIL",
197
  "42": "NOT_ALIVE",
198
- "43": "SUCCESS",
199
  "44": "FAIL",
200
  "45": "NOT_ALIVE",
201
- "46": "SUCCESS",
202
  "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
  "5": "FAIL",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
- "52": "FAIL",
209
- "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
- "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
- "58": "NOT_ALIVE",
215
- "59": "SUCCESS",
216
  "6": "SUCCESS",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
- "64": "FAIL",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
- "69": "SUCCESS",
227
- "7": "FAIL",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
- "74": "SUCCESS",
233
  "75": "NOT_ALIVE",
234
- "76": "FAIL",
235
  "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
  "79": "FAIL",
@@ -239,19 +239,19 @@
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
- "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "FAIL",
247
  "88": "SUCCESS",
248
- "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "FAIL",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
- "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
  "97": "SUCCESS",
@@ -264,19 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6360011,
268
- 6360031,
269
- 6360047,
270
- 6360063
271
  ],
272
  "bos_token_id": 1,
273
  "eos_token_id": 2,
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
- "inner_step": 66,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6359562,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
10
  "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
  "105": "SUCCESS",
13
+ "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
 
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
+ "115": "SUCCESS",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
 
30
  "121": "SUCCESS",
31
  "122": "FAIL",
32
  "123": "FAIL",
33
+ "124": "FAIL",
34
  "125": "NOT_ALIVE",
35
+ "126": "SUCCESS",
36
+ "127": "NOT_ALIVE",
37
  "128": "FAIL",
38
  "129": "SUCCESS",
39
  "13": "NOT_ALIVE",
40
+ "130": "SUCCESS",
41
+ "131": "NOT_ALIVE",
42
+ "132": "SUCCESS",
43
  "133": "SUCCESS",
44
+ "134": "FAIL",
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "SUCCESS",
49
+ "139": "FAIL",
50
+ "14": "SUCCESS",
51
+ "140": "FAIL",
52
  "141": "NOT_ALIVE",
53
  "142": "FAIL",
54
+ "143": "FAIL",
55
  "144": "SUCCESS",
56
+ "145": "FAIL",
57
  "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
  "148": "SUCCESS",
60
+ "149": "SUCCESS",
61
  "15": "SUCCESS",
62
+ "150": "SUCCESS",
63
+ "151": "NON_PARTICIPATING",
64
+ "152": "NOT_ALIVE",
65
  "153": "FAIL",
66
  "154": "NON_PARTICIPATING",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
+ "157": "NON_PARTICIPATING",
70
  "158": "SUCCESS",
71
  "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "NOT_ALIVE",
75
+ "162": "SUCCESS",
76
+ "163": "SUCCESS",
77
  "164": "NON_PARTICIPATING",
78
+ "165": "FAIL",
79
  "166": "SUCCESS",
80
  "167": "NON_PARTICIPATING",
81
+ "168": "NON_PARTICIPATING",
82
  "169": "FAIL",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
+ "173": "SUCCESS",
88
  "174": "SUCCESS",
89
+ "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
 
95
  "180": "NON_PARTICIPATING",
96
  "181": "SUCCESS",
97
  "182": "NOT_ALIVE",
98
+ "183": "FAIL",
99
  "184": "NOT_ALIVE",
100
  "185": "FAIL",
101
  "186": "SUCCESS",
102
+ "187": "FAIL",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
+ "190": "NON_PARTICIPATING",
107
  "191": "NON_PARTICIPATING",
108
  "192": "SUCCESS",
109
+ "193": "FAIL",
110
+ "194": "FAIL",
111
+ "195": "SUCCESS",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
 
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "SUCCESS",
122
+ "204": "SUCCESS",
123
+ "205": "NOT_ALIVE",
124
+ "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
+ "208": "SUCCESS",
127
  "209": "NOT_ALIVE",
128
+ "21": "FAIL",
129
  "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
+ "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "SUCCESS",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
  "218": "FAIL",
138
+ "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
+ "220": "FAIL",
141
+ "221": "FAIL",
142
  "222": "SUCCESS",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
+ "228": "SUCCESS",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
+ "230": "FAIL",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
+ "236": "FAIL",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "SUCCESS",
160
  "239": "FAIL",
161
  "24": "SUCCESS",
162
+ "240": "FAIL",
163
  "241": "FAIL",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
+ "245": "NON_PARTICIPATING",
168
  "246": "SUCCESS",
169
+ "247": "SUCCESS",
170
  "248": "NOT_ALIVE",
171
+ "249": "FAIL",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
+ "252": "SUCCESS",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
+ "255": "NON_PARTICIPATING",
179
+ "26": "FAIL",
180
+ "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
  "3": "NOT_ALIVE",
184
+ "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "SUCCESS",
190
+ "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
+ "38": "FAIL",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "FAIL",
197
  "42": "NOT_ALIVE",
198
+ "43": "NON_PARTICIPATING",
199
  "44": "FAIL",
200
  "45": "NOT_ALIVE",
201
+ "46": "FAIL",
202
  "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
  "5": "FAIL",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
+ "52": "NOT_ALIVE",
209
+ "53": "FAIL",
210
  "54": "NOT_ALIVE",
211
+ "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
+ "58": "FAIL",
215
+ "59": "FAIL",
216
  "6": "SUCCESS",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
+ "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
+ "69": "NON_PARTICIPATING",
227
+ "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
+ "74": "FAIL",
233
  "75": "NOT_ALIVE",
234
+ "76": "NOT_ALIVE",
235
  "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
  "79": "FAIL",
 
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "NON_PARTICIPATING",
243
  "84": "SUCCESS",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "FAIL",
247
  "88": "SUCCESS",
248
+ "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "FAIL",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
+ "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
  "97": "SUCCESS",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6360252,
268
+ 6360264
 
 
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": 6360216,
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:d01586f169f0bf56e01c627a36293b569cb1aa1ba3f5e13a89795e349f4a35cc
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18b0c7165d0941b15468658fb96af7de62d8b805c6e1fd37ea3056509a1dda22
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62e90c95586e7e89fb869b29dd93e7e3690f7b4d0b44eaa5d9c60803771927d6
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76b5467bf9f2fcb348ada470e4f15e74677e6f1530d83b82d497be57bed41c1b
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9ffb6a209ef95405765a1936216b56ef4283a799181bd98a39e3ce0ebacbecf
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4b9dab2e4914f8751737974ec382d50c87eb9adf16529c4fb73f94e08b93e6e
3
  size 4400216536