Alir332 commited on
Commit
dbaeef4
·
verified ·
1 Parent(s): 6f9cad3

Run 11. Outer Step 221. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +50 -50
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -11,7 +11,7 @@
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",
@@ -20,24 +20,24 @@
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
- "115": "NOT_ALIVE",
24
- "116": "SUCCESS",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
- "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
- "120": "NOT_ALIVE",
30
- "121": "SUCCESS",
31
  "122": "NOT_ALIVE",
32
- "123": "NOT_ALIVE",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
- "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
- "13": "NON_PARTICIPATING",
40
- "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
@@ -49,14 +49,14 @@
49
  "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
  "140": "SUCCESS",
52
- "141": "NOT_ALIVE",
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",
@@ -79,17 +79,17 @@
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": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
@@ -110,11 +110,11 @@
110
  "194": "NOT_ALIVE",
111
  "195": "SUCCESS",
112
  "196": "NOT_ALIVE",
113
- "197": "NOT_ALIVE",
114
  "198": "NOT_ALIVE",
115
- "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
- "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
@@ -129,42 +129,42 @@
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
- "213": "NOT_ALIVE",
133
- "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
- "216": "NOT_ALIVE",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
- "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
  "223": "SUCCESS",
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": "SUCCESS",
153
  "232": "NOT_ALIVE",
154
- "233": "SUCCESS",
155
  "234": "NON_PARTICIPATING",
156
- "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "SUCCESS",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
- "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
- "241": "NOT_ALIVE",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
- "245": "SUCCESS",
168
  "246": "NOT_ALIVE",
169
  "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
@@ -172,7 +172,7 @@
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
  "251": "SUCCESS",
175
- "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
@@ -185,7 +185,7 @@
185
  "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
- "34": "SUCCESS",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "SUCCESS",
@@ -208,16 +208,16 @@
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "SUCCESS",
211
- "55": "SUCCESS",
212
  "56": "NOT_ALIVE",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "NOT_ALIVE",
218
- "61": "NOT_ALIVE",
219
  "62": "NON_PARTICIPATING",
220
- "63": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
222
  "65": "SUCCESS",
223
  "66": "NOT_ALIVE",
@@ -231,15 +231,15 @@
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": "SUCCESS",
238
- "8": "SUCCESS",
239
- "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
- "82": "NON_PARTICIPATING",
242
- "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
@@ -247,15 +247,15 @@
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
- "90": "NON_PARTICIPATING",
251
- "91": "NON_PARTICIPATING",
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": "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
- 6667156,
268
- 6667190
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": 45,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6666862,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "SUCCESS",
14
+ "107": "NOT_ALIVE",
15
  "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
 
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",
28
  "12": "NOT_ALIVE",
29
+ "120": "NON_PARTICIPATING",
30
+ "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
32
+ "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
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
  "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": "NON_PARTICIPATING",
58
  "147": "SUCCESS",
59
+ "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "SUCCESS",
 
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NOT_ALIVE",
82
+ "169": "NOT_ALIVE",
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": "NON_PARTICIPATING",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
 
110
  "194": "NOT_ALIVE",
111
  "195": "SUCCESS",
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",
 
129
  "210": "NON_PARTICIPATING",
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",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
+ "220": "NOT_ALIVE",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
  "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
  "226": "SUCCESS",
147
+ "227": "NOT_ALIVE",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "SUCCESS",
152
  "231": "SUCCESS",
153
  "232": "NOT_ALIVE",
154
+ "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
+ "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
  "237": "SUCCESS",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
+ "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
163
+ "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NOT_ALIVE",
168
  "246": "NOT_ALIVE",
169
  "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
 
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
  "251": "SUCCESS",
175
+ "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
 
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",
 
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "SUCCESS",
211
+ "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "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": "NOT_ALIVE",
239
+ "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
+ "82": "NOT_ALIVE",
242
+ "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
 
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
+ "90": "NOT_ALIVE",
251
+ "91": "SUCCESS",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
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
+ 6667312,
268
+ 6667340
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": 6667265,
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 sha256:4ec0a0793946dcf97a04e2131dff30adca88e385afdd7e2f2b2a6d45da45705e
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6caf27ff43910cc7f011671b82e6b8a5ba18d41e93f503c07243d30f98e8fcd7
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4f10a2ef55a7d6feff3b44c788364fe026aa6eb1f4980470c93eb728df581d7
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ba4e32acd77692d4b02cd4d2d406a13480c593015f5c5e82f26e4c75616289
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5709177a3bf1fff1e25a4167a84dbbd5b9110ea9e1ea4f6e30e7833d0536c1f
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e03fc9b1692d8103be92ce194339a8489ef83898b48f821d754150c55af95d7
3
  size 4400216536