mujerry commited on
Commit
3af2495
·
verified ·
1 Parent(s): 7c5b916

Run 11. Outer Step 220. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +51 -51
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -3,30 +3,30 @@
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
6
- "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
- "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
10
- "103": "FAIL",
11
  "104": "NON_PARTICIPATING",
12
- "105": "SUCCESS",
13
  "106": "SUCCESS",
14
  "107": "NON_PARTICIPATING",
15
  "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
- "110": "SUCCESS",
19
  "111": "NON_PARTICIPATING",
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",
28
  "12": "NOT_ALIVE",
29
- "120": "SUCCESS",
30
  "121": "SUCCESS",
31
  "122": "NOT_ALIVE",
32
  "123": "NOT_ALIVE",
@@ -34,10 +34,10 @@
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
- "128": "SUCCESS",
38
  "129": "NOT_ALIVE",
39
- "13": "NOT_ALIVE",
40
- "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
@@ -47,19 +47,19 @@
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
- "14": "NOT_ALIVE",
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": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
@@ -84,8 +84,8 @@
84
  "170": "NOT_ALIVE",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
- "173": "SUCCESS",
88
- "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
@@ -110,11 +110,11 @@
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",
@@ -129,11 +129,11 @@
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",
@@ -143,11 +143,11 @@
143
  "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
- "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
- "23": "NOT_ALIVE",
151
  "230": "SUCCESS",
152
  "231": "SUCCESS",
153
  "232": "NOT_ALIVE",
@@ -158,21 +158,21 @@
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": "SUCCESS",
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",
178
  "255": "NOT_ALIVE",
@@ -185,19 +185,19 @@
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",
192
- "38": "NON_PARTICIPATING",
193
  "39": "NOT_ALIVE",
194
- "4": "NON_PARTICIPATING",
195
  "40": "NOT_ALIVE",
196
- "41": "SUCCESS",
197
- "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
- "45": "NON_PARTICIPATING",
201
  "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
@@ -208,14 +208,14 @@
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": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
@@ -234,7 +234,7 @@
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
- "79": "NON_PARTICIPATING",
238
  "8": "SUCCESS",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
@@ -244,19 +244,19 @@
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
247
- "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
- "91": "NOT_ALIVE",
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"
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6666767,
268
- 6666804
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": 54,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6665282,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
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": "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",
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",
 
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",
 
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
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",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
 
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",
 
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
  "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",
 
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",
 
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",
171
  "249": "NOT_ALIVE",
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
  "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",
192
+ "38": "SUCCESS",
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",
200
+ "45": "SUCCESS",
201
  "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
 
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",
 
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",
 
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
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": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6666911,
268
+ 6666941
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": 6666862,
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:eae0b516f21a1f342a6b0969c46387cc45675d2a48f368d34d8d2cc4412ae976
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfa3630f9468af67d4a71851d2b4ca3fc15858a401c6f705079ee9483ec76341
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4322609b19f86f77254323b8bd746469ebc66c3e15b2e8748815d7da37ea4a52
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddeba3f95d00097919e9d9804b687bb4aa859cb8a77498ff4714920d2d8fa4fe
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45b4cc3f46f24f961e69156a8dcf39807bd8898d0473500f0dafeb36fa3d8ca2
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d92d7e4f0a617b379424ddf30eb404c99357334e146372ff63fef4066bf094e
3
  size 4400216536