ShinyUser commited on
Commit
63432ea
·
verified ·
1 Parent(s): 269303d

Run 11. Outer Step 207. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +45 -45
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,13 +2,13 @@
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",
9
  "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
- "104": "SUCCESS",
12
  "105": "NON_PARTICIPATING",
13
  "106": "SUCCESS",
14
  "107": "SUCCESS",
@@ -16,12 +16,12 @@
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",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
  "119": "SUCCESS",
@@ -34,9 +34,9 @@
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
- "128": "NON_PARTICIPATING",
38
- "129": "NON_PARTICIPATING",
39
- "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
@@ -46,23 +46,23 @@
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
- "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
- "140": "SUCCESS",
52
  "141": "SUCCESS",
53
  "142": "NON_PARTICIPATING",
54
- "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
  "147": "SUCCESS",
59
- "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "NON_PARTICIPATING",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
@@ -77,7 +77,7 @@
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
- "167": "NON_PARTICIPATING",
81
  "168": "NOT_ALIVE",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
@@ -86,7 +86,7 @@
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
- "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "SUCCESS",
@@ -97,9 +97,9 @@
97
  "182": "SUCCESS",
98
  "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
- "185": "SUCCESS",
101
- "186": "NON_PARTICIPATING",
102
- "187": "NOT_ALIVE",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
@@ -108,20 +108,20 @@
108
  "192": "NOT_ALIVE",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
- "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "SUCCESS",
114
  "198": "NOT_ALIVE",
115
- "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
- "20": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
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",
@@ -130,7 +130,7 @@
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
- "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NON_PARTICIPATING",
136
  "217": "SUCCESS",
@@ -144,18 +144,18 @@
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": "NOT_ALIVE",
151
  "230": "SUCCESS",
152
- "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
- "233": "FAIL",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
- "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
@@ -164,14 +164,14 @@
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
- "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
- "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
- "251": "SUCCESS",
175
  "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
@@ -185,7 +185,7 @@
185
  "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
- "34": "NOT_ALIVE",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "SUCCESS",
@@ -193,7 +193,7 @@
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
- "41": "NOT_ALIVE",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
@@ -216,8 +216,8 @@
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
- "62": "NOT_ALIVE",
220
- "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
  "65": "SUCCESS",
223
  "66": "NOT_ALIVE",
@@ -231,14 +231,14 @@
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
- "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
- "79": "SUCCESS",
238
  "8": "SUCCESS",
239
- "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
- "82": "SUCCESS",
242
  "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
@@ -253,10 +253,10 @@
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"
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6661852,
268
- 6661888
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": 63,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6661467,
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": "SUCCESS",
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
+ "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "SUCCESS",
14
  "107": "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",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
  "119": "SUCCESS",
 
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
+ "128": "SUCCESS",
38
+ "129": "NOT_ALIVE",
39
+ "13": "NON_PARTICIPATING",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
 
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
+ "139": "NOT_ALIVE",
50
  "14": "NON_PARTICIPATING",
51
+ "140": "NON_PARTICIPATING",
52
  "141": "SUCCESS",
53
  "142": "NON_PARTICIPATING",
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": "NOT_ALIVE",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
 
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
+ "167": "NOT_ALIVE",
81
  "168": "NOT_ALIVE",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
 
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
+ "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "SUCCESS",
 
97
  "182": "SUCCESS",
98
  "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
+ "185": "NOT_ALIVE",
101
+ "186": "NOT_ALIVE",
102
+ "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
 
108
  "192": "NOT_ALIVE",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
+ "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "SUCCESS",
114
  "198": "NOT_ALIVE",
115
+ "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
+ "20": "NON_PARTICIPATING",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NOT_ALIVE",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "SUCCESS",
 
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NON_PARTICIPATING",
136
  "217": "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": "SUCCESS",
151
  "230": "SUCCESS",
152
+ "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
+ "233": "SUCCESS",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
+ "237": "SUCCESS",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
 
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
+ "251": "NON_PARTICIPATING",
175
  "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
 
185
  "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
+ "34": "NON_PARTICIPATING",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "SUCCESS",
 
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
+ "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
 
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
+ "62": "NON_PARTICIPATING",
220
+ "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
222
  "65": "SUCCESS",
223
  "66": "NOT_ALIVE",
 
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",
238
  "8": "SUCCESS",
239
+ "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
+ "82": "NON_PARTICIPATING",
242
  "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
 
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
+ "96": "NON_PARTICIPATING",
257
+ "97": "NON_PARTICIPATING",
258
  "98": "SUCCESS",
259
+ "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6661976,
268
+ 6661993
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": 8,
278
  "intermediate_size": 5632,
279
+ "last_allreduce_block": 6661918,
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 sha256:60396c3a95661d7d2dd07d938dd371a2ffb415af1fd48361137ce32c3c117f7d
3
  size 88390091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb48af4a2ffbefcf24f880fcf4cf0a5eaefacd7837b8044c19a4a06bf33ea134
3
  size 88390091
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1144e671098fac7d5d1eb3fa9fdc0b4559f5ea8710c2a2a30b2aebfe0f83cceb
3
  size 4924928111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac8a1f39e3a87a617b9120e24eb0ef1c6152d8ca74b855a964154e234d304f1a
3
  size 4924928111
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e840b76dac2c7a14904dfa8f29b43aeb48dfcbc1fd2b0c6583292df344f72c41
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c73a59cb389f4758f0b66afcf1d16612ed31992e29215303cc08c6ae97d8b9e9
3
  size 4400216536