ShinyUser commited on
Commit
3c9385a
·
verified ·
1 Parent(s): dc016f9

Run 11. Outer Step 201. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +37 -39
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -3,13 +3,13 @@
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
6
- "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "SUCCESS",
12
- "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "SUCCESS",
@@ -20,13 +20,13 @@
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
- "115": "NON_PARTICIPATING",
24
- "116": "SUCCESS",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
  "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
- "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
@@ -35,27 +35,27 @@
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
  "128": "SUCCESS",
38
- "129": "NON_PARTICIPATING",
39
- "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "SUCCESS",
45
- "135": "SUCCESS",
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": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
- "146": "NON_PARTICIPATING",
58
- "147": "NOT_ALIVE",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
@@ -72,10 +72,10 @@
72
  "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
- "162": "NOT_ALIVE",
76
  "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
- "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NOT_ALIVE",
@@ -106,13 +106,13 @@
106
  "190": "NOT_ALIVE",
107
  "191": "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": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
@@ -126,14 +126,14 @@
126
  "208": "NOT_ALIVE",
127
  "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
- "210": "NOT_ALIVE",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
  "216": "NON_PARTICIPATING",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
@@ -144,18 +144,18 @@
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": "SUCCESS",
151
- "230": "NOT_ALIVE",
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",
@@ -188,16 +188,16 @@
188
  "34": "NOT_ALIVE",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
- "37": "SUCCESS",
192
  "38": "SUCCESS",
193
  "39": "NOT_ALIVE",
194
- "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
- "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
@@ -215,8 +215,8 @@
215
  "59": "NOT_ALIVE",
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",
@@ -236,7 +236,7 @@
236
  "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
238
  "8": "SUCCESS",
239
- "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "SUCCESS",
@@ -247,16 +247,16 @@
247
  "88": "NON_PARTICIPATING",
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": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
- "98": "SUCCESS",
259
- "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,10 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6659276,
268
- 6659304,
269
- 6659325,
270
- 6659346
271
  ],
272
  "bos_token_id": 1,
273
  "dtype": "float32",
@@ -276,9 +274,9 @@
276
  "hidden_act": "silu",
277
  "hidden_size": 2048,
278
  "initializer_range": 0.02,
279
- "inner_step": 50,
280
  "intermediate_size": 5632,
281
- "last_allreduce_block": 6659044,
282
  "max_position_embeddings": 2048,
283
  "mlp_bias": false,
284
  "model_type": "llama",
 
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
6
+ "10": "NON_PARTICIPATING",
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": "NOT_ALIVE",
15
  "108": "SUCCESS",
 
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
+ "115": "NOT_ALIVE",
24
+ "116": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
 
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
  "128": "SUCCESS",
38
+ "129": "SUCCESS",
39
+ "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "SUCCESS",
45
+ "135": "NOT_ALIVE",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
+ "140": "NOT_ALIVE",
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": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
 
72
  "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
+ "162": "SUCCESS",
76
  "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
+ "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NOT_ALIVE",
 
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
+ "193": "NON_PARTICIPATING",
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",
 
126
  "208": "NOT_ALIVE",
127
  "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
  "216": "NON_PARTICIPATING",
136
+ "217": "SUCCESS",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
 
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": "SUCCESS",
151
+ "230": "SUCCESS",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
+ "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
+ "237": "NOT_ALIVE",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
 
188
  "34": "NOT_ALIVE",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
+ "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
  "39": "NOT_ALIVE",
194
+ "4": "NON_PARTICIPATING",
195
  "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
+ "45": "SUCCESS",
201
  "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
 
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
+ "61": "NOT_ALIVE",
219
+ "62": "NON_PARTICIPATING",
220
  "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
  "65": "SUCCESS",
 
236
  "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
238
  "8": "SUCCESS",
239
+ "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "SUCCESS",
 
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
+ "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
+ "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
+ "98": "NOT_ALIVE",
259
+ "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6659475,
268
+ 6659493
 
 
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": 6659442,
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:b5694ab5e36f1abe2ded91633fde1fb3803b9d9fb89ace1b6188209727028f37
3
  size 88390091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a70711aa8986cc247e7bf3b44862c7c40a87220c211613f5a86ac98a11caa85
3
  size 88390091
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e34182425cfd11dd666810e0e809b99144e0401892670e9118e9d00baf072b1e
3
  size 4924928111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eaf8fde184d10954632d847a5c43e285d626bd012fd22ed687754cf139fa36a
3
  size 4924928111
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84c7f718c9fed06097d57ea909974249946e5766a47d2aa05677b9d686d9362c
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:571b298277780a9ad72126163676e437a622b6aae5554bef94d12bb762267614
3
  size 4400216536