ncaagcc commited on
Commit
c2db87b
·
verified ·
1 Parent(s): 9a8add1

Run 8. Outer Step 40. Inner Step 352.

Browse files
Files changed (4) hide show
  1. config.json +182 -182
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +2 -2
  4. model.safetensors +1 -1
config.json CHANGED
@@ -1,262 +1,262 @@
1
  {
2
- "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
- "0": "SUCCESS",
5
  "1": "SUCCESS",
6
- "10": "SUCCESS",
7
- "100": "SUCCESS",
8
  "101": "SUCCESS",
9
- "102": "SUCCESS",
10
- "103": "SUCCESS",
11
- "104": "SUCCESS",
12
  "105": "SUCCESS",
13
  "106": "SUCCESS",
14
- "107": "SUCCESS",
15
- "108": "SUCCESS",
16
- "109": "SUCCESS",
17
- "11": "SUCCESS",
18
- "110": "SUCCESS",
19
  "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
- "114": "SUCCESS",
23
- "115": "SUCCESS",
24
- "116": "SUCCESS",
25
- "117": "SUCCESS",
26
  "118": "SUCCESS",
27
- "119": "SUCCESS",
28
- "12": "SUCCESS",
29
- "120": "SUCCESS",
30
  "121": "SUCCESS",
31
- "122": "SUCCESS",
32
- "123": "SUCCESS",
33
  "124": "SUCCESS",
34
- "125": "SUCCESS",
35
- "126": "SUCCESS",
36
- "127": "SUCCESS",
37
- "128": "SUCCESS",
38
  "129": "SUCCESS",
39
- "13": "SUCCESS",
40
- "130": "SUCCESS",
41
- "131": "SUCCESS",
42
- "132": "SUCCESS",
43
  "133": "SUCCESS",
44
  "134": "SUCCESS",
45
  "135": "SUCCESS",
46
- "136": "SUCCESS",
47
- "137": "SUCCESS",
48
  "138": "SUCCESS",
49
  "139": "SUCCESS",
50
- "14": "SUCCESS",
51
  "140": "SUCCESS",
52
- "141": "SUCCESS",
53
- "142": "SUCCESS",
54
  "143": "SUCCESS",
55
  "144": "SUCCESS",
56
  "145": "SUCCESS",
57
  "146": "SUCCESS",
58
- "147": "SUCCESS",
59
  "148": "SUCCESS",
60
- "149": "SUCCESS",
61
  "15": "SUCCESS",
62
- "150": "SUCCESS",
63
- "151": "SUCCESS",
64
- "152": "SUCCESS",
65
- "153": "SUCCESS",
66
- "154": "SUCCESS",
67
  "155": "SUCCESS",
68
- "156": "SUCCESS",
69
- "157": "SUCCESS",
70
  "158": "SUCCESS",
71
- "159": "SUCCESS",
72
  "16": "SUCCESS",
73
- "160": "SUCCESS",
74
- "161": "SUCCESS",
75
- "162": "SUCCESS",
76
- "163": "SUCCESS",
77
- "164": "SUCCESS",
78
- "165": "SUCCESS",
79
  "166": "SUCCESS",
80
- "167": "SUCCESS",
81
- "168": "SUCCESS",
82
- "169": "SUCCESS",
83
- "17": "SUCCESS",
84
- "170": "SUCCESS",
85
- "171": "SUCCESS",
86
- "172": "SUCCESS",
87
- "173": "SUCCESS",
88
  "174": "SUCCESS",
89
- "175": "SUCCESS",
90
- "176": "SUCCESS",
91
  "177": "SUCCESS",
92
- "178": "SUCCESS",
93
- "179": "SUCCESS",
94
- "18": "SUCCESS",
95
- "180": "SUCCESS",
96
  "181": "SUCCESS",
97
- "182": "SUCCESS",
98
- "183": "SUCCESS",
99
- "184": "SUCCESS",
100
- "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "SUCCESS",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
- "19": "SUCCESS",
106
- "190": "SUCCESS",
107
- "191": "SUCCESS",
108
  "192": "SUCCESS",
109
  "193": "SUCCESS",
110
  "194": "SUCCESS",
111
- "195": "SUCCESS",
112
  "196": "SUCCESS",
113
- "197": "SUCCESS",
114
- "198": "SUCCESS",
115
  "199": "SUCCESS",
116
- "2": "SUCCESS",
117
- "20": "SUCCESS",
118
- "200": "SUCCESS",
119
- "201": "SUCCESS",
120
- "202": "SUCCESS",
121
- "203": "SUCCESS",
122
- "204": "SUCCESS",
123
  "205": "SUCCESS",
124
- "206": "SUCCESS",
125
- "207": "SUCCESS",
126
- "208": "SUCCESS",
127
- "209": "SUCCESS",
128
  "21": "SUCCESS",
129
- "210": "SUCCESS",
130
  "211": "SUCCESS",
131
  "212": "SUCCESS",
132
- "213": "SUCCESS",
133
  "214": "SUCCESS",
134
  "215": "SUCCESS",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
- "218": "SUCCESS",
138
- "219": "SUCCESS",
139
- "22": "SUCCESS",
140
- "220": "SUCCESS",
141
  "221": "SUCCESS",
142
  "222": "SUCCESS",
143
- "223": "SUCCESS",
144
- "224": "SUCCESS",
145
  "225": "SUCCESS",
146
- "226": "SUCCESS",
147
- "227": "SUCCESS",
148
- "228": "SUCCESS",
149
- "229": "SUCCESS",
150
- "23": "SUCCESS",
151
- "230": "SUCCESS",
152
- "231": "SUCCESS",
153
- "232": "SUCCESS",
154
- "233": "SUCCESS",
155
  "234": "SUCCESS",
156
- "235": "SUCCESS",
157
  "236": "SUCCESS",
158
- "237": "SUCCESS",
159
- "238": "SUCCESS",
160
- "239": "SUCCESS",
161
  "24": "SUCCESS",
162
- "240": "SUCCESS",
163
- "241": "SUCCESS",
164
  "242": "SUCCESS",
165
- "243": "SUCCESS",
166
- "244": "SUCCESS",
167
- "245": "SUCCESS",
168
  "246": "SUCCESS",
169
- "247": "SUCCESS",
170
- "248": "SUCCESS",
171
  "249": "SUCCESS",
172
  "25": "SUCCESS",
173
- "250": "SUCCESS",
174
- "251": "SUCCESS",
175
- "252": "SUCCESS",
176
  "253": "SUCCESS",
177
- "254": "SUCCESS",
178
- "255": "SUCCESS",
179
  "26": "SUCCESS",
180
  "27": "SUCCESS",
181
  "28": "SUCCESS",
182
- "29": "SUCCESS",
183
- "3": "SUCCESS",
184
  "30": "SUCCESS",
185
- "31": "SUCCESS",
186
- "32": "SUCCESS",
187
- "33": "SUCCESS",
188
- "34": "SUCCESS",
189
  "35": "SUCCESS",
190
- "36": "SUCCESS",
191
- "37": "SUCCESS",
192
  "38": "SUCCESS",
193
- "39": "SUCCESS",
194
- "4": "SUCCESS",
195
- "40": "SUCCESS",
196
- "41": "SUCCESS",
197
- "42": "SUCCESS",
198
  "43": "SUCCESS",
199
- "44": "SUCCESS",
200
- "45": "SUCCESS",
201
  "46": "SUCCESS",
202
  "47": "SUCCESS",
203
- "48": "SUCCESS",
204
- "49": "SUCCESS",
205
- "5": "SUCCESS",
206
- "50": "SUCCESS",
207
- "51": "SUCCESS",
208
- "52": "SUCCESS",
209
  "53": "SUCCESS",
210
- "54": "SUCCESS",
211
- "55": "SUCCESS",
212
- "56": "SUCCESS",
213
  "57": "SUCCESS",
214
- "58": "SUCCESS",
215
  "59": "SUCCESS",
216
  "6": "SUCCESS",
217
- "60": "SUCCESS",
218
- "61": "SUCCESS",
219
- "62": "SUCCESS",
220
  "63": "SUCCESS",
221
- "64": "SUCCESS",
222
- "65": "SUCCESS",
223
- "66": "SUCCESS",
224
- "67": "SUCCESS",
225
- "68": "SUCCESS",
226
  "69": "SUCCESS",
227
- "7": "SUCCESS",
228
- "70": "SUCCESS",
229
- "71": "SUCCESS",
230
- "72": "SUCCESS",
231
- "73": "SUCCESS",
232
  "74": "SUCCESS",
233
- "75": "SUCCESS",
234
- "76": "SUCCESS",
235
  "77": "SUCCESS",
236
- "78": "SUCCESS",
237
- "79": "SUCCESS",
238
- "8": "SUCCESS",
239
- "80": "SUCCESS",
240
- "81": "SUCCESS",
241
- "82": "SUCCESS",
242
- "83": "SUCCESS",
243
  "84": "SUCCESS",
244
- "85": "SUCCESS",
245
- "86": "SUCCESS",
246
- "87": "SUCCESS",
247
  "88": "SUCCESS",
248
- "89": "SUCCESS",
249
- "9": "SUCCESS",
250
- "90": "SUCCESS",
251
- "91": "SUCCESS",
252
- "92": "SUCCESS",
253
- "93": "SUCCESS",
254
- "94": "SUCCESS",
255
- "95": "SUCCESS",
256
- "96": "SUCCESS",
257
  "97": "SUCCESS",
258
  "98": "SUCCESS",
259
- "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6366208,
268
- 6366212
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": 6317911,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "ncaagcc/az2",
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",
29
+ "120": "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",
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",
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",
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",
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",
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",
258
  "98": "SUCCESS",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6366250,
268
+ 6366269
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": 352,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6359562,
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 sha256:85ef80a0695cf49aec8773de6e9900e5c6b69b36159b25b52f482163da8de547
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:301c0f1ddbacf48973114fd40f063b0a59583b4b89f500733a4220038a118150
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:112e4be11e537f5ab0c1ea51e85204c5fbd340722687348a963a3e83a165a2f3
3
- size 4924926842
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ec5e94d53cb054c8bf49f15065777f6d0f649b877960a66adaa9537b27f9da
3
+ size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:227df9dae3be7dffb678e29444487441cc28903a98384826dd8f1486cabe04c4
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a5d9bdbe0a6a18934447ee275e9160bd2418e6f5a2dff51f3c18dcd380c257b
3
  size 4400216536