tensorwa commited on
Commit
3308aca
·
verified ·
1 Parent(s): 8d5ace7

Run 5. Outer Step 101. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +82 -82
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "tensorwa/sn38",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
@@ -7,15 +7,15 @@
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
10
- "103": "NOT_ALIVE",
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": "NON_PARTICIPATING",
18
- "110": "NOT_ALIVE",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
@@ -23,8 +23,8 @@
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
- "118": "SUCCESS",
27
- "119": "SUCCESS",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
@@ -32,8 +32,8 @@
32
  "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
- "126": "NOT_ALIVE",
36
- "127": "NON_PARTICIPATING",
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
@@ -41,13 +41,13 @@
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
- "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
- "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
- "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "SUCCESS",
53
  "142": "SUCCESS",
@@ -56,29 +56,29 @@
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
- "148": "NOT_ALIVE",
60
  "149": "NON_PARTICIPATING",
61
- "15": "NON_PARTICIPATING",
62
  "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "NON_PARTICIPATING",
66
  "154": "NOT_ALIVE",
67
- "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
- "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
- "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
- "160": "NON_PARTICIPATING",
74
- "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "SUCCESS",
77
  "164": "SUCCESS",
78
- "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
- "168": "NON_PARTICIPATING",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
@@ -89,32 +89,32 @@
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
- "178": "NON_PARTICIPATING",
93
  "179": "NOT_ALIVE",
94
  "18": "SUCCESS",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
- "183": "SUCCESS",
99
- "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
  "187": "SUCCESS",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
- "19": "NON_PARTICIPATING",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
- "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
- "196": "NON_PARTICIPATING",
113
  "197": "NOT_ALIVE",
114
  "198": "NOT_ALIVE",
115
- "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
- "20": "NON_PARTICIPATING",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
@@ -123,116 +123,116 @@
123
  "205": "NOT_ALIVE",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
- "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "SUCCESS",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
- "214": "NOT_ALIVE",
134
- "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
- "219": "NON_PARTICIPATING",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
- "222": "NON_PARTICIPATING",
143
  "223": "NOT_ALIVE",
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": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
- "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "NOT_ALIVE",
156
- "235": "NON_PARTICIPATING",
157
- "236": "NON_PARTICIPATING",
158
- "237": "NOT_ALIVE",
159
  "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
- "24": "SUCCESS",
162
- "240": "NON_PARTICIPATING",
163
- "241": "NON_PARTICIPATING",
164
- "242": "NOT_ALIVE",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
- "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
- "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
- "252": "NOT_ALIVE",
176
- "253": "FAIL",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "NOT_ALIVE",
180
- "27": "NON_PARTICIPATING",
181
  "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
- "3": "NON_PARTICIPATING",
184
  "30": "NOT_ALIVE",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
- "35": "NON_PARTICIPATING",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
- "38": "SUCCESS",
193
- "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "SUCCESS",
197
  "42": "SUCCESS",
198
- "43": "SUCCESS",
199
  "44": "NOT_ALIVE",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NOT_ALIVE",
202
- "47": "NON_PARTICIPATING",
203
- "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NON_PARTICIPATING",
206
- "50": "NON_PARTICIPATING",
207
  "51": "NOT_ALIVE",
208
- "52": "NON_PARTICIPATING",
209
- "53": "NON_PARTICIPATING",
210
  "54": "SUCCESS",
211
  "55": "NOT_ALIVE",
212
  "56": "SUCCESS",
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
215
  "59": "NOT_ALIVE",
216
- "6": "NON_PARTICIPATING",
217
  "60": "NON_PARTICIPATING",
218
- "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
- "63": "NON_PARTICIPATING",
221
- "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
- "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
- "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "SUCCESS",
228
- "70": "NON_PARTICIPATING",
229
- "71": "NOT_ALIVE",
230
- "72": "NON_PARTICIPATING",
231
  "73": "SUCCESS",
232
  "74": "SUCCESS",
233
- "75": "SUCCESS",
234
- "76": "NON_PARTICIPATING",
235
- "77": "NON_PARTICIPATING",
236
  "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
@@ -248,15 +248,15 @@
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "SUCCESS",
251
- "91": "NON_PARTICIPATING",
252
- "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
- "96": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
- "98": "SUCCESS",
259
- "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5872398,
268
- 5872418
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": 127,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5864939,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
 
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": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
  "109": "NOT_ALIVE",
17
+ "11": "NOT_ALIVE",
18
+ "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
 
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
+ "118": "NOT_ALIVE",
27
+ "119": "NOT_ALIVE",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
 
32
  "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
+ "126": "NON_PARTICIPATING",
36
+ "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
 
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
+ "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
+ "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
+ "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "SUCCESS",
53
  "142": "SUCCESS",
 
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "SUCCESS",
60
  "149": "NON_PARTICIPATING",
61
+ "15": "NOT_ALIVE",
62
  "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "NOT_ALIVE",
66
  "154": "NOT_ALIVE",
67
+ "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
+ "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "NON_PARTICIPATING",
72
  "16": "NON_PARTICIPATING",
73
+ "160": "NOT_ALIVE",
74
+ "161": "SUCCESS",
75
  "162": "NON_PARTICIPATING",
76
  "163": "SUCCESS",
77
  "164": "SUCCESS",
78
+ "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
+ "168": "NOT_ALIVE",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
 
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
+ "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "SUCCESS",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
+ "183": "NOT_ALIVE",
99
+ "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
  "187": "SUCCESS",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
+ "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
+ "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NOT_ALIVE",
115
+ "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
+ "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
 
123
  "205": "NOT_ALIVE",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
+ "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "SUCCESS",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
+ "214": "NON_PARTICIPATING",
134
+ "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "NOT_ALIVE",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
+ "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "NOT_ALIVE",
156
+ "235": "NOT_ALIVE",
157
+ "236": "NOT_ALIVE",
158
+ "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
+ "24": "NOT_ALIVE",
162
+ "240": "NOT_ALIVE",
163
+ "241": "NOT_ALIVE",
164
+ "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
+ "246": "NOT_ALIVE",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
+ "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
+ "252": "NON_PARTICIPATING",
176
+ "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "SUCCESS",
180
+ "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
+ "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
+ "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
+ "38": "NOT_ALIVE",
193
+ "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "SUCCESS",
197
  "42": "SUCCESS",
198
+ "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NOT_ALIVE",
202
+ "47": "NOT_ALIVE",
203
+ "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NON_PARTICIPATING",
206
+ "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
+ "52": "NOT_ALIVE",
209
+ "53": "NOT_ALIVE",
210
  "54": "SUCCESS",
211
  "55": "NOT_ALIVE",
212
  "56": "SUCCESS",
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
215
  "59": "NOT_ALIVE",
216
+ "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
+ "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
+ "63": "NOT_ALIVE",
221
+ "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
+ "66": "SUCCESS",
224
  "67": "NOT_ALIVE",
225
+ "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
  "7": "SUCCESS",
228
+ "70": "NOT_ALIVE",
229
+ "71": "NON_PARTICIPATING",
230
+ "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
  "74": "SUCCESS",
233
+ "75": "NOT_ALIVE",
234
+ "76": "SUCCESS",
235
+ "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
 
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "SUCCESS",
251
+ "91": "NOT_ALIVE",
252
+ "92": "SUCCESS",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
+ "96": "NOT_ALIVE",
257
  "97": "SUCCESS",
258
+ "98": "NOT_ALIVE",
259
+ "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5872480,
268
+ 5872520
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": 2,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 5872367,
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 sha256:7030c1c263149b2db29ae627d9379804b41e1d8b8390c134bad1596567c463a7
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ed081fbbff3a61ab04e66ba5093d7025cfbc1401a3253b14227a71a72dc6af
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db17f3faab8f776796cd3a3bcc0d8969e9ddf2bee87655e505765ca214e5ab3d
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1b8d68aaf52cb1a8ada1ea9a7058bbbc43db5fdc26c8c50add339e6eda7f94a
3
  size 4400216536