Alir332 commited on
Commit
48bc769
·
verified ·
1 Parent(s): c49c64c

Run 11. Outer Step 226. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +41 -41
  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": "dstrbtd/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "NOT_ALIVE",
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
@@ -10,13 +10,13 @@
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
- "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
- "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
@@ -27,17 +27,17 @@
27
  "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
- "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
32
- "123": "NOT_ALIVE",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
- "127": "NON_PARTICIPATING",
37
- "128": "SUCCESS",
38
  "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
- "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
@@ -49,24 +49,24 @@
49
  "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
  "140": "SUCCESS",
52
- "141": "SUCCESS",
53
  "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
  "147": "SUCCESS",
59
- "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
- "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
- "157": "SUCCESS",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
@@ -79,18 +79,18 @@
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NOT_ALIVE",
82
- "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
- "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "SUCCESS",
93
- "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
@@ -121,10 +121,10 @@
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NOT_ALIVE",
124
- "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
- "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
@@ -132,26 +132,26 @@
132
  "213": "NON_PARTICIPATING",
133
  "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
- "216": "NON_PARTICIPATING",
136
  "217": "SUCCESS",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
- "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
- "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
  "226": "SUCCESS",
147
- "227": "SUCCESS",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "SUCCESS",
152
- "231": "SUCCESS",
153
  "232": "NOT_ALIVE",
154
- "233": "SUCCESS",
155
  "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
@@ -189,11 +189,11 @@
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "SUCCESS",
192
- "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "SUCCESS",
195
  "40": "NOT_ALIVE",
196
- "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
@@ -206,23 +206,23 @@
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
- "53": "NON_PARTICIPATING",
210
  "54": "SUCCESS",
211
- "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "NOT_ALIVE",
218
- "61": "SUCCESS",
219
  "62": "NON_PARTICIPATING",
220
- "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
- "65": "SUCCESS",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
- "68": "NON_PARTICIPATING",
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
@@ -231,7 +231,7 @@
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
- "76": "SUCCESS",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
@@ -239,7 +239,7 @@
239
  "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
  "82": "SUCCESS",
242
- "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
@@ -253,9 +253,9 @@
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
- "96": "NOT_ALIVE",
257
- "97": "SUCCESS",
258
- "98": "NOT_ALIVE",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6669206,
268
- 6669249
269
  ],
270
  "bos_token_id": 1,
271
  "dtype": "float32",
@@ -274,9 +274,9 @@
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
- "inner_step": 49,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6668857,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
2
  "_name_or_path": "dstrbtd/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "NON_PARTICIPATING",
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
 
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
+ "106": "SUCCESS",
14
  "107": "NON_PARTICIPATING",
15
  "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "NOT_ALIVE",
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
 
27
  "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
+ "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
+ "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
+ "127": "SUCCESS",
37
+ "128": "FAIL",
38
  "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
+ "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
 
49
  "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
  "140": "SUCCESS",
52
+ "141": "NON_PARTICIPATING",
53
  "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
  "147": "SUCCESS",
59
+ "148": "NOT_ALIVE",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
+ "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
+ "157": "NOT_ALIVE",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
 
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NOT_ALIVE",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
+ "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "SUCCESS",
93
+ "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
 
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NOT_ALIVE",
124
+ "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
+ "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
 
132
  "213": "NON_PARTICIPATING",
133
  "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
+ "216": "NOT_ALIVE",
136
  "217": "SUCCESS",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
+ "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
+ "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
  "226": "SUCCESS",
147
+ "227": "NON_PARTICIPATING",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "SUCCESS",
152
+ "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
+ "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
 
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "SUCCESS",
192
+ "38": "NON_PARTICIPATING",
193
  "39": "NOT_ALIVE",
194
  "4": "SUCCESS",
195
  "40": "NOT_ALIVE",
196
+ "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
 
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
+ "53": "NOT_ALIVE",
210
  "54": "SUCCESS",
211
+ "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
+ "61": "NOT_ALIVE",
219
  "62": "NON_PARTICIPATING",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
222
+ "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
+ "68": "SUCCESS",
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
 
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
+ "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
 
239
  "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
  "82": "SUCCESS",
242
+ "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
 
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
+ "96": "NON_PARTICIPATING",
257
+ "97": "NOT_ALIVE",
258
+ "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6669311,
268
+ 6669340
269
  ],
270
  "bos_token_id": 1,
271
  "dtype": "float32",
 
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
+ "inner_step": 9,
278
  "intermediate_size": 5632,
279
+ "last_allreduce_block": 6669252,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9caab001c952d58ab238673a50959af00414ff81142b6345b81d876c28a12fd6
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c03bcc0c8878cde278b9c30c4bf9957c2876bf8bec32ebc2d6df57574873251
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4c853bb20c071f544568def7de74f1e8b6cf065feb118c7ccfcff3db93ba848
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f022be7c590659ec0d5ea70823707c9f7d0647dd53f8fcf07eeebf8727ae6a1e
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f8576c7443316e51cc301bbb1b52c8a9a3e1e9161236c3372c8fd720eff8aa7
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e32e69be3024c07039d5eab116541fe366acffad24d3aa00a9786f0320580fe2
3
  size 4400216536