ncaagcc commited on
Commit
626b56d
·
verified ·
1 Parent(s): 78f8e75

Run 8. Outer Step 37. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +71 -71
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,27 +2,27 @@
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "FAIL",
6
- "10": "SUCCESS",
7
- "100": "NON_PARTICIPATING",
8
- "101": "FAIL",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
- "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
- "110": "SUCCESS",
19
  "111": "SUCCESS",
20
- "112": "FAIL",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
- "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
@@ -30,24 +30,24 @@
30
  "121": "SUCCESS",
31
  "122": "FAIL",
32
  "123": "FAIL",
33
- "124": "FAIL",
34
  "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
36
  "127": "FAIL",
37
  "128": "FAIL",
38
  "129": "SUCCESS",
39
  "13": "NOT_ALIVE",
40
- "130": "NOT_ALIVE",
41
  "131": "NON_PARTICIPATING",
42
  "132": "NOT_ALIVE",
43
- "133": "NOT_ALIVE",
44
  "134": "SUCCESS",
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
- "137": "SUCCESS",
48
  "138": "SUCCESS",
49
  "139": "SUCCESS",
50
- "14": "SUCCESS",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
  "142": "FAIL",
@@ -56,9 +56,9 @@
56
  "145": "SUCCESS",
57
  "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
- "148": "FAIL",
60
- "149": "FAIL",
61
- "15": "FAIL",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
@@ -67,19 +67,19 @@
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
- "158": "NOT_ALIVE",
71
  "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
  "160": "NON_PARTICIPATING",
74
- "161": "SUCCESS",
75
- "162": "SUCCESS",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
80
  "167": "NON_PARTICIPATING",
81
  "168": "FAIL",
82
- "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
@@ -88,46 +88,46 @@
88
  "174": "SUCCESS",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
- "177": "FAIL",
92
  "178": "NON_PARTICIPATING",
93
- "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
  "181": "SUCCESS",
97
  "182": "NOT_ALIVE",
98
- "183": "NOT_ALIVE",
99
  "184": "NOT_ALIVE",
100
- "185": "NOT_ALIVE",
101
  "186": "SUCCESS",
102
  "187": "SUCCESS",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
- "19": "SUCCESS",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
  "192": "SUCCESS",
109
  "193": "SUCCESS",
110
- "194": "FAIL",
111
- "195": "NOT_ALIVE",
112
- "196": "FAIL",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
- "199": "FAIL",
116
  "2": "NOT_ALIVE",
117
- "20": "SUCCESS",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
- "202": "SUCCESS",
121
  "203": "FAIL",
122
  "204": "FAIL",
123
  "205": "SUCCESS",
124
  "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
- "208": "SUCCESS",
127
- "209": "FAIL",
128
- "21": "FAIL",
129
- "210": "SUCCESS",
130
- "211": "FAIL",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
@@ -135,58 +135,58 @@
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
  "218": "FAIL",
138
- "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
- "220": "NOT_ALIVE",
141
  "221": "SUCCESS",
142
  "222": "SUCCESS",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
- "225": "FAIL",
146
  "226": "NOT_ALIVE",
147
- "227": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
156
- "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
- "238": "SUCCESS",
160
  "239": "FAIL",
161
- "24": "FAIL",
162
- "240": "FAIL",
163
  "241": "FAIL",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
  "246": "SUCCESS",
169
- "247": "SUCCESS",
170
  "248": "NOT_ALIVE",
171
  "249": "SUCCESS",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "FAIL",
176
- "253": "FAIL",
177
  "254": "NOT_ALIVE",
178
- "255": "NON_PARTICIPATING",
179
  "26": "SUCCESS",
180
  "27": "SUCCESS",
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": "NON_PARTICIPATING",
189
- "35": "FAIL",
190
  "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
@@ -196,8 +196,8 @@
196
  "41": "FAIL",
197
  "42": "NOT_ALIVE",
198
  "43": "SUCCESS",
199
- "44": "NON_PARTICIPATING",
200
- "45": "NON_PARTICIPATING",
201
  "46": "SUCCESS",
202
  "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
@@ -205,10 +205,10 @@
205
  "5": "FAIL",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
- "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
- "55": "SUCCESS",
212
  "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
@@ -218,32 +218,32 @@
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
- "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
  "69": "SUCCESS",
227
- "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "SUCCESS",
233
- "75": "SUCCESS",
234
  "76": "FAIL",
235
- "77": "FAIL",
236
  "78": "NON_PARTICIPATING",
237
  "79": "FAIL",
238
  "8": "NOT_ALIVE",
239
- "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
- "84": "FAIL",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
- "87": "SUCCESS",
247
  "88": "SUCCESS",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
@@ -254,7 +254,7 @@
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
- "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
@@ -264,18 +264,18 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6359433,
268
- 6359448,
269
- 6359448
270
  ],
271
  "bos_token_id": 1,
272
  "eos_token_id": 2,
273
  "hidden_act": "silu",
274
  "hidden_size": 2048,
275
  "initializer_range": 0.02,
276
- "inner_step": 71,
277
  "intermediate_size": 5632,
278
- "last_allreduce_block": 6358925,
279
  "max_position_embeddings": 2048,
280
  "mlp_bias": false,
281
  "model_type": "llama",
 
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "SUCCESS",
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": "SUCCESS",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
+ "110": "NON_PARTICIPATING",
19
  "111": "SUCCESS",
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
  "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",
 
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",
 
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",
 
88
  "174": "SUCCESS",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
+ "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
93
+ "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
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",
115
+ "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
+ "20": "NOT_ALIVE",
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",
 
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",
 
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",
 
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",
 
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",
238
  "8": "NOT_ALIVE",
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",
 
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
+ "97": "SUCCESS",
258
  "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6359601,
268
+ 6359608,
269
+ 6359632
270
  ],
271
  "bos_token_id": 1,
272
  "eos_token_id": 2,
273
  "hidden_act": "silu",
274
  "hidden_size": 2048,
275
  "initializer_range": 0.02,
276
+ "inner_step": 4,
277
  "intermediate_size": 5632,
278
+ "last_allreduce_block": 6359562,
279
  "max_position_embeddings": 2048,
280
  "mlp_bias": false,
281
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78aea40f4f1163628a8fe24b635ad00be3f53920bc20fc7400386aaf2cf7ca6a
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29df697fc6628e123a6586afdc9b41f3d27500a6932837c3485b57f04e88ae2e
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:944f779a59a387004acac5d36f864dd78914b6078bdb00aa43746c0dc28c767c
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90901867d8bb2d97973a044345d40b2a943273a5da346ff29bc89ad982160bb5
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c66612033539ddcfabd6832bda3a35f7d7e2eda68f825c24e17533b338803e91
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a112ce14ea43bdd8e11ee15c6e77c39343023bfb19ae0aba981f1180aadb952
3
  size 4400216536