snoopsy commited on
Commit
35cfd05
·
verified ·
1 Parent(s): 28e89b4

Run 8. Outer Step 56. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +102 -102
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -3,119 +3,119 @@
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
- "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "SUCCESS",
9
  "102": "NON_PARTICIPATING",
10
- "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
- "107": "SUCCESS",
15
  "108": "SUCCESS",
16
  "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
- "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
- "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
- "117": "SUCCESS",
26
  "118": "NOT_ALIVE",
27
- "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "SUCCESS",
31
- "122": "FAIL",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "FAIL",
36
  "127": "SUCCESS",
37
- "128": "SUCCESS",
38
- "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "FAIL",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
- "133": "SUCCESS",
44
  "134": "NOT_ALIVE",
45
- "135": "SUCCESS",
46
  "136": "SUCCESS",
47
- "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
- "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
- "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "FAIL",
54
  "143": "SUCCESS",
55
  "144": "NON_PARTICIPATING",
56
- "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
- "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
- "149": "SUCCESS",
61
- "15": "SUCCESS",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
- "152": "SUCCESS",
65
- "153": "NON_PARTICIPATING",
66
  "154": "NON_PARTICIPATING",
67
- "155": "FAIL",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NON_PARTICIPATING",
71
- "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "FAIL",
75
- "162": "NOT_ALIVE",
76
- "163": "SUCCESS",
77
- "164": "SUCCESS",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
- "168": "NON_PARTICIPATING",
82
- "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
- "171": "SUCCESS",
86
- "172": "FAIL",
87
- "173": "SUCCESS",
88
  "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
- "177": "SUCCESS",
92
- "178": "NOT_ALIVE",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
- "181": "NOT_ALIVE",
97
  "182": "SUCCESS",
98
  "183": "SUCCESS",
99
- "184": "SUCCESS",
100
  "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
- "189": "SUCCESS",
105
- "19": "FAIL",
106
  "190": "NON_PARTICIPATING",
107
  "191": "FAIL",
108
- "192": "NOT_ALIVE",
109
  "193": "SUCCESS",
110
- "194": "NON_PARTICIPATING",
111
- "195": "SUCCESS",
112
- "196": "SUCCESS",
113
- "197": "NON_PARTICIPATING",
114
- "198": "NON_PARTICIPATING",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
- "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
@@ -124,50 +124,50 @@
124
  "206": "SUCCESS",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
- "209": "SUCCESS",
128
- "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
- "211": "SUCCESS",
131
  "212": "SUCCESS",
132
- "213": "SUCCESS",
133
  "214": "SUCCESS",
134
  "215": "SUCCESS",
135
- "216": "FAIL",
136
  "217": "SUCCESS",
137
- "218": "SUCCESS",
138
- "219": "FAIL",
139
- "22": "FAIL",
140
- "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
  "222": "SUCCESS",
143
  "223": "SUCCESS",
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": "SUCCESS",
152
  "231": "NON_PARTICIPATING",
153
- "232": "SUCCESS",
154
- "233": "NOT_ALIVE",
155
- "234": "FAIL",
156
  "235": "SUCCESS",
157
  "236": "SUCCESS",
158
- "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
- "239": "NON_PARTICIPATING",
161
- "24": "FAIL",
162
  "240": "NON_PARTICIPATING",
163
- "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
- "244": "SUCCESS",
167
  "245": "SUCCESS",
168
- "246": "NON_PARTICIPATING",
169
  "247": "SUCCESS",
170
- "248": "FAIL",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
@@ -176,12 +176,12 @@
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "FAIL",
180
- "27": "SUCCESS",
181
  "28": "SUCCESS",
182
- "29": "SUCCESS",
183
  "3": "SUCCESS",
184
- "30": "FAIL",
185
  "31": "NON_PARTICIPATING",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
@@ -191,32 +191,32 @@
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
- "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
- "41": "SUCCESS",
197
  "42": "SUCCESS",
198
- "43": "NOT_ALIVE",
199
  "44": "FAIL",
200
- "45": "NOT_ALIVE",
201
- "46": "SUCCESS",
202
- "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
- "49": "NON_PARTICIPATING",
205
  "5": "FAIL",
206
- "50": "FAIL",
207
  "51": "SUCCESS",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
- "54": "NON_PARTICIPATING",
211
- "55": "FAIL",
212
- "56": "FAIL",
213
- "57": "FAIL",
214
  "58": "SUCCESS",
215
  "59": "NOT_ALIVE",
216
- "6": "NOT_ALIVE",
217
- "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
- "62": "SUCCESS",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
@@ -224,24 +224,24 @@
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
- "7": "SUCCESS",
228
- "70": "SUCCESS",
229
- "71": "NON_PARTICIPATING",
230
- "72": "NOT_ALIVE",
231
- "73": "NOT_ALIVE",
232
- "74": "FAIL",
233
  "75": "NON_PARTICIPATING",
234
- "76": "NON_PARTICIPATING",
235
  "77": "SUCCESS",
236
- "78": "NON_PARTICIPATING",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
  "82": "SUCCESS",
242
- "83": "SUCCESS",
243
- "84": "SUCCESS",
244
- "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
@@ -255,7 +255,7 @@
255
  "95": "SUCCESS",
256
  "96": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
- "98": "NOT_ALIVE",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6379445,
268
- 6379461
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": 63,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6378907,
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": "NOT_ALIVE",
8
  "101": "SUCCESS",
9
  "102": "NON_PARTICIPATING",
10
+ "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
+ "107": "NON_PARTICIPATING",
15
  "108": "SUCCESS",
16
  "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
+ "110": "NON_PARTICIPATING",
19
  "111": "NOT_ALIVE",
20
+ "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
+ "119": "FAIL",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "SUCCESS",
31
+ "122": "SUCCESS",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "FAIL",
36
  "127": "SUCCESS",
37
+ "128": "NOT_ALIVE",
38
+ "129": "FAIL",
39
  "13": "NOT_ALIVE",
40
  "130": "FAIL",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
+ "133": "NON_PARTICIPATING",
44
  "134": "NOT_ALIVE",
45
+ "135": "FAIL",
46
  "136": "SUCCESS",
47
+ "137": "SUCCESS",
48
  "138": "NOT_ALIVE",
49
+ "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
+ "140": "FAIL",
52
  "141": "NOT_ALIVE",
53
  "142": "FAIL",
54
  "143": "SUCCESS",
55
  "144": "NON_PARTICIPATING",
56
+ "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
+ "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "NOT_ALIVE",
61
+ "15": "FAIL",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
+ "152": "NON_PARTICIPATING",
65
+ "153": "SUCCESS",
66
  "154": "NON_PARTICIPATING",
67
+ "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "FAIL",
71
+ "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "FAIL",
75
+ "162": "NON_PARTICIPATING",
76
+ "163": "FAIL",
77
+ "164": "FAIL",
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": "NOT_ALIVE",
87
+ "173": "NON_PARTICIPATING",
88
  "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
+ "177": "FAIL",
92
+ "178": "NON_PARTICIPATING",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
+ "181": "SUCCESS",
97
  "182": "SUCCESS",
98
  "183": "SUCCESS",
99
+ "184": "FAIL",
100
  "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
+ "189": "NON_PARTICIPATING",
105
+ "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
  "191": "FAIL",
108
+ "192": "FAIL",
109
  "193": "SUCCESS",
110
+ "194": "FAIL",
111
+ "195": "FAIL",
112
+ "196": "NON_PARTICIPATING",
113
+ "197": "NOT_ALIVE",
114
+ "198": "NOT_ALIVE",
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",
 
124
  "206": "SUCCESS",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
+ "209": "NON_PARTICIPATING",
128
+ "21": "SUCCESS",
129
  "210": "NOT_ALIVE",
130
+ "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
+ "213": "FAIL",
133
  "214": "SUCCESS",
134
  "215": "SUCCESS",
135
+ "216": "SUCCESS",
136
  "217": "SUCCESS",
137
+ "218": "FAIL",
138
+ "219": "SUCCESS",
139
+ "22": "SUCCESS",
140
+ "220": "FAIL",
141
  "221": "NON_PARTICIPATING",
142
  "222": "SUCCESS",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "FAIL",
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
+ "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
+ "230": "FAIL",
152
  "231": "NON_PARTICIPATING",
153
+ "232": "FAIL",
154
+ "233": "FAIL",
155
+ "234": "SUCCESS",
156
  "235": "SUCCESS",
157
  "236": "SUCCESS",
158
+ "237": "FAIL",
159
  "238": "SUCCESS",
160
+ "239": "FAIL",
161
+ "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
+ "241": "FAIL",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
+ "244": "FAIL",
167
  "245": "SUCCESS",
168
+ "246": "NOT_ALIVE",
169
  "247": "SUCCESS",
170
+ "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
 
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "SUCCESS",
180
+ "27": "NON_PARTICIPATING",
181
  "28": "SUCCESS",
182
+ "29": "NON_PARTICIPATING",
183
  "3": "SUCCESS",
184
+ "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
 
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
+ "4": "FAIL",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "FAIL",
197
  "42": "SUCCESS",
198
+ "43": "NON_PARTICIPATING",
199
  "44": "FAIL",
200
+ "45": "FAIL",
201
+ "46": "NON_PARTICIPATING",
202
+ "47": "FAIL",
203
  "48": "NOT_ALIVE",
204
+ "49": "FAIL",
205
  "5": "FAIL",
206
+ "50": "NOT_ALIVE",
207
  "51": "SUCCESS",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
+ "54": "SUCCESS",
211
+ "55": "NOT_ALIVE",
212
+ "56": "NON_PARTICIPATING",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "SUCCESS",
215
  "59": "NOT_ALIVE",
216
+ "6": "FAIL",
217
+ "60": "SUCCESS",
218
  "61": "NON_PARTICIPATING",
219
+ "62": "FAIL",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
 
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
+ "7": "NOT_ALIVE",
228
+ "70": "FAIL",
229
+ "71": "NOT_ALIVE",
230
+ "72": "NON_PARTICIPATING",
231
+ "73": "NON_PARTICIPATING",
232
+ "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
+ "76": "FAIL",
235
  "77": "SUCCESS",
236
+ "78": "SUCCESS",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
  "82": "SUCCESS",
242
+ "83": "NON_PARTICIPATING",
243
+ "84": "FAIL",
244
+ "85": "NON_PARTICIPATING",
245
  "86": "NOT_ALIVE",
246
  "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
 
255
  "95": "SUCCESS",
256
  "96": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
+ "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6379588,
268
+ 6379608
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": 5,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6379556,
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 sha256:14b963baae97b2cd3d345c687100803dd52d5d5bf7ee3d3dc96a9f2f3e1d4ebc
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc5b00be3963b136e76a25f71e2845a0c93063a4cc3b2e9a4fbc995bc0f8c5cb
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3451a2339391cf982349c2e772532a351800a73e49200ee3f7a85505191a1c98
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:004eaaf0e2dbadf2d0194947dbc5a064f049660d18f274ad045f199b87dc4447
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d24ecff3ff3758bf1b6507e0317109785a29f264b7998f4680bfd09c800b4d0
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6883bb8d987b92e015ec642d2ac43e7bbf3be061cca9352ea4f9db6488484cdc
3
  size 4400216536