ncaagcc commited on
Commit
53a82ea
·
verified ·
1 Parent(s): c72c981

Run 8. Outer Step 104. 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
@@ -2,7 +2,7 @@
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": "NON_PARTICIPATING",
@@ -13,19 +13,19 @@
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
- "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
- "110": "NOT_ALIVE",
19
- "111": "NOT_ALIVE",
20
  "112": "SUCCESS",
21
- "113": "NON_PARTICIPATING",
22
  "114": "SUCCESS",
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
- "118": "NOT_ALIVE",
27
- "119": "NOT_ALIVE",
28
- "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
@@ -38,36 +38,36 @@
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": "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": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "SUCCESS",
55
  "144": "NON_PARTICIPATING",
56
- "145": "NOT_ALIVE",
57
- "146": "SUCCESS",
58
  "147": "SUCCESS",
59
- "148": "SUCCESS",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
- "152": "SUCCESS",
65
- "153": "NOT_ALIVE",
66
- "154": "NOT_ALIVE",
67
- "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
- "158": "SUCCESS",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
@@ -76,13 +76,13 @@
76
  "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NOT_ALIVE",
79
- "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
- "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
- "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
@@ -90,14 +90,14 @@
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": "NON_PARTICIPATING",
97
  "182": "NOT_ALIVE",
98
  "183": "SUCCESS",
99
  "184": "SUCCESS",
100
- "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
  "187": "SUCCESS",
103
  "188": "SUCCESS",
@@ -105,17 +105,17 @@
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": "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",
@@ -124,9 +124,9 @@
124
  "206": "SUCCESS",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
- "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
- "210": "NOT_ALIVE",
130
  "211": "NOT_ALIVE",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
@@ -134,27 +134,27 @@
134
  "215": "NOT_ALIVE",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
- "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
- "22": "SUCCESS",
140
  "220": "NOT_ALIVE",
141
- "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
- "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
- "227": "SUCCESS",
148
  "228": "SUCCESS",
149
- "229": "NOT_ALIVE",
150
- "23": "FAIL",
151
- "230": "NON_PARTICIPATING",
152
  "231": "SUCCESS",
153
  "232": "NOT_ALIVE",
154
- "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
- "236": "SUCCESS",
158
  "237": "SUCCESS",
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
@@ -162,7 +162,7 @@
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
- "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
@@ -172,62 +172,62 @@
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
174
  "251": "SUCCESS",
175
- "252": "NON_PARTICIPATING",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
- "255": "FAIL",
179
  "26": "NON_PARTICIPATING",
180
- "27": "FAIL",
181
- "28": "NOT_ALIVE",
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": "FAIL",
190
  "36": "FAIL",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
- "4": "SUCCESS",
195
  "40": "NOT_ALIVE",
196
  "41": "SUCCESS",
197
  "42": "NOT_ALIVE",
198
- "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
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": "NOT_ALIVE",
210
  "54": "NON_PARTICIPATING",
211
- "55": "NOT_ALIVE",
212
- "56": "SUCCESS",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
- "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
- "62": "SUCCESS",
220
- "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
- "68": "NOT_ALIVE",
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
- "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
- "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
@@ -240,9 +240,9 @@
240
  "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
- "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
- "86": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
@@ -250,9 +250,9 @@
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
- "93": "NOT_ALIVE",
254
- "94": "NON_PARTICIPATING",
255
- "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
  "98": "SUCCESS",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6426365,
268
- 6426375
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": 49,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6425746,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
 
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
+ "109": "FAIL",
17
  "11": "NOT_ALIVE",
18
+ "110": "NON_PARTICIPATING",
19
+ "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
+ "113": "SUCCESS",
22
  "114": "SUCCESS",
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
+ "118": "NON_PARTICIPATING",
27
+ "119": "NON_PARTICIPATING",
28
+ "12": "SUCCESS",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
 
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
  "130": "NON_PARTICIPATING",
41
+ "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
+ "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
+ "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "SUCCESS",
51
  "140": "NOT_ALIVE",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "SUCCESS",
55
  "144": "NON_PARTICIPATING",
56
+ "145": "NON_PARTICIPATING",
57
+ "146": "NON_PARTICIPATING",
58
  "147": "SUCCESS",
59
+ "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
+ "152": "NON_PARTICIPATING",
65
+ "153": "NON_PARTICIPATING",
66
+ "154": "SUCCESS",
67
+ "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
 
76
  "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NOT_ALIVE",
79
+ "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
+ "169": "FAIL",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
+ "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
 
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
93
+ "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NON_PARTICIPATING",
97
  "182": "NOT_ALIVE",
98
  "183": "SUCCESS",
99
  "184": "SUCCESS",
100
+ "185": "SUCCESS",
101
  "186": "NOT_ALIVE",
102
  "187": "SUCCESS",
103
  "188": "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": "SUCCESS",
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",
 
124
  "206": "SUCCESS",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
+ "209": "SUCCESS",
128
  "21": "SUCCESS",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
 
134
  "215": "NOT_ALIVE",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
+ "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
+ "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
+ "221": "SUCCESS",
142
  "222": "NOT_ALIVE",
143
+ "223": "NON_PARTICIPATING",
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": "NOT_ALIVE",
152
  "231": "SUCCESS",
153
  "232": "NOT_ALIVE",
154
+ "233": "SUCCESS",
155
  "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
+ "236": "FAIL",
158
  "237": "SUCCESS",
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
 
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
+ "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
 
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
174
  "251": "SUCCESS",
175
+ "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
+ "255": "SUCCESS",
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": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
+ "35": "SUCCESS",
190
  "36": "FAIL",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
+ "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
  "41": "SUCCESS",
197
  "42": "NOT_ALIVE",
198
+ "43": "SUCCESS",
199
  "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
+ "47": "SUCCESS",
203
+ "48": "SUCCESS",
204
+ "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "SUCCESS",
208
  "52": "NON_PARTICIPATING",
209
+ "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
+ "55": "NON_PARTICIPATING",
212
+ "56": "NON_PARTICIPATING",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
+ "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
+ "62": "FAIL",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "NON_PARTICIPATING",
226
  "69": "NOT_ALIVE",
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",
 
240
  "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
+ "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
245
+ "86": "NON_PARTICIPATING",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
 
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
+ "93": "NON_PARTICIPATING",
254
+ "94": "SUCCESS",
255
+ "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
  "98": "SUCCESS",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6426400,
268
+ 6426414
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": 6426368,
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:c29c9e191decf53c0293e098e3b3332694b453cd31a615fa1fe46e97787fe754
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5b6fa0d74ca52b0807b13455af24efd77a087d8e122bca98825bb6e22375978
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48cf6cfebaa65ad750b974121be5b725623a1df0ccaf6d415e617cd566c73fa0
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd991c9e49323843298b040116676ac602d5be9ddc9d6f94c2b1cc6acafe014f
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d17bbff95087f61673b22f156724956803d5de7b5df79f4dc5ff87e09d212834
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea90f92baa7877f2e5aa0dff7759f0397c4c6bd16d16cdb35748cc3f16e77ed8
3
  size 4400216536