zeras141a commited on
Commit
691ca1a
·
verified ·
1 Parent(s): 2403a48

Run 8. Outer Step 105. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +73 -73
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -1,36 +1,36 @@
1
  {
2
- "_name_or_path": "zeras141a/a6",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
- "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
- "104": "NOT_ALIVE",
12
  "105": "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",
32
  "123": "NON_PARTICIPATING",
33
- "124": "SUCCESS",
34
  "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
@@ -38,20 +38,20 @@
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",
@@ -61,13 +61,13 @@
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",
@@ -78,11 +78,11 @@
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",
@@ -99,8 +99,8 @@
99
  "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "NOT_ALIVE",
102
- "187": "SUCCESS",
103
- "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
@@ -108,7 +108,7 @@
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",
@@ -124,45 +124,45 @@
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",
133
  "214": "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",
161
  "24": "NOT_ALIVE",
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",
@@ -170,8 +170,8 @@
170
  "248": "SUCCESS",
171
  "249": "SUCCESS",
172
  "25": "SUCCESS",
173
- "250": "SUCCESS",
174
- "251": "SUCCESS",
175
  "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
@@ -180,54 +180,54 @@
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",
@@ -236,15 +236,15 @@
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
- "80": "NOT_ALIVE",
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",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
@@ -253,9 +253,9 @@
253
  "93": "NON_PARTICIPATING",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
- "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
- "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6426905,
268
- 6426917
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": 61,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6426368,
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": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
+ "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
+ "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
+ "108": "NON_PARTICIPATING",
16
+ "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "FAIL",
20
+ "112": "NON_PARTICIPATING",
21
+ "113": "NON_PARTICIPATING",
22
+ "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
+ "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
+ "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
+ "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
 
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
  "130": "NON_PARTICIPATING",
41
+ "131": "NON_PARTICIPATING",
42
  "132": "NOT_ALIVE",
43
  "133": "NON_PARTICIPATING",
44
+ "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
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": "FAIL",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NON_PARTICIPATING",
 
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
+ "152": "SUCCESS",
65
+ "153": "NOT_ALIVE",
66
  "154": "SUCCESS",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
+ "157": "NOT_ALIVE",
70
+ "158": "FAIL",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
 
78
  "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
+ "168": "NON_PARTICIPATING",
82
+ "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
+ "170": "NOT_ALIVE",
85
+ "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
 
99
  "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "NOT_ALIVE",
102
+ "187": "FAIL",
103
+ "188": "FAIL",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
 
108
  "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "SUCCESS",
111
+ "195": "NOT_ALIVE",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
  "198": "SUCCESS",
 
124
  "206": "SUCCESS",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
+ "209": "FAIL",
128
  "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
  "212": "NON_PARTICIPATING",
132
+ "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
+ "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
+ "218": "SUCCESS",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
+ "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
+ "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "NON_PARTICIPATING",
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
+ "228": "FAIL",
149
  "229": "NON_PARTICIPATING",
150
+ "23": "FAIL",
151
+ "230": "NON_PARTICIPATING",
152
+ "231": "FAIL",
153
  "232": "NOT_ALIVE",
154
+ "233": "NON_PARTICIPATING",
155
+ "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
+ "236": "SUCCESS",
158
  "237": "SUCCESS",
159
  "238": "SUCCESS",
160
+ "239": "SUCCESS",
161
  "24": "NOT_ALIVE",
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",
 
170
  "248": "SUCCESS",
171
  "249": "SUCCESS",
172
  "25": "SUCCESS",
173
+ "250": "FAIL",
174
+ "251": "FAIL",
175
  "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
 
180
  "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
+ "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
+ "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
+ "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
+ "35": "FAIL",
190
  "36": "FAIL",
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": "NOT_ALIVE",
198
+ "43": "FAIL",
199
  "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
+ "46": "NON_PARTICIPATING",
202
  "47": "SUCCESS",
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": "NON_PARTICIPATING",
210
+ "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
+ "56": "SUCCESS",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
+ "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
+ "61": "FAIL",
219
  "62": "FAIL",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
+ "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
+ "69": "NON_PARTICIPATING",
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",
 
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
+ "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
+ "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
246
+ "87": "SUCCESS",
247
+ "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
 
253
  "93": "NON_PARTICIPATING",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
+ "96": "SUCCESS",
257
  "97": "NON_PARTICIPATING",
258
+ "98": "FAIL",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6427058,
268
+ 6427074
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": 6426986,
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:ea7aca959db21e1a2cfd23ff0a3414ecb66309161eeb9d81addffb59a8570977
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f7e6adfcc8366c1ff8a582f3de973a6081cca58266acc2205a4acdd0b39ced3
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8b03239ca27ad2382305e00eb50076d76725c856ee426a4cc34da987b2202b3
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4bc5a86a18f92ad3ff6c50732c52933bee909e21c5201af4340aac48834816e
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb8236d4fd6f0db4ec01ea8796bdabf7db7a98cd262b1619b246fe264e0d8e47
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9614539563b9d15b3991522ffc37f0b957ba5a75434c6e1495f24be31b4ab868
3
  size 4400216536