mizzaay commited on
Commit
48742f0
·
verified ·
1 Parent(s): 964a3f0

Run 8. Outer Step 117. Inner Step 6.

Browse files
Files changed (4) hide show
  1. config.json +77 -77
  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": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
@@ -10,36 +10,36 @@
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
- "106": "SUCCESS",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
- "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
- "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
- "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
- "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
- "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NOT_ALIVE",
33
- "124": "NON_PARTICIPATING",
34
- "125": "SUCCESS",
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
- "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
- "130": "NOT_ALIVE",
41
  "131": "NON_PARTICIPATING",
42
- "132": "NON_PARTICIPATING",
43
  "133": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NOT_ALIVE",
@@ -51,31 +51,31 @@
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
- "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
- "146": "NOT_ALIVE",
58
- "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
- "150": "NON_PARTICIPATING",
63
- "151": "NOT_ALIVE",
64
  "152": "SUCCESS",
65
- "153": "NON_PARTICIPATING",
66
  "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
- "157": "SUCCESS",
70
  "158": "SUCCESS",
71
  "159": "NOT_ALIVE",
72
- "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
- "162": "NON_PARTICIPATING",
76
- "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
- "165": "NOT_ALIVE",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
@@ -83,29 +83,29 @@
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "SUCCESS",
86
- "172": "NOT_ALIVE",
87
  "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
89
- "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
- "181": "NON_PARTICIPATING",
97
  "182": "SUCCESS",
98
  "183": "SUCCESS",
99
- "184": "SUCCESS",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
- "188": "NOT_ALIVE",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
- "190": "NON_PARTICIPATING",
107
- "191": "NOT_ALIVE",
108
- "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "SUCCESS",
111
  "195": "NON_PARTICIPATING",
@@ -115,7 +115,7 @@
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
- "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NOT_ALIVE",
@@ -126,95 +126,95 @@
126
  "208": "NON_PARTICIPATING",
127
  "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
- "210": "SUCCESS",
130
  "211": "SUCCESS",
131
  "212": "NON_PARTICIPATING",
132
  "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
- "216": "SUCCESS",
136
- "217": "FAIL",
137
  "218": "SUCCESS",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
- "221": "SUCCESS",
142
  "222": "NON_PARTICIPATING",
143
- "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
- "226": "NON_PARTICIPATING",
147
- "227": "NON_PARTICIPATING",
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "SUCCESS",
151
  "230": "NON_PARTICIPATING",
152
- "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
- "234": "NON_PARTICIPATING",
156
- "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
- "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
- "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
  "247": "SUCCESS",
170
- "248": "FAIL",
171
  "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
- "251": "FAIL",
175
  "252": "NON_PARTICIPATING",
176
- "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
- "26": "SUCCESS",
180
  "27": "SUCCESS",
181
- "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NOT_ALIVE",
186
- "32": "NOT_ALIVE",
187
- "33": "NOT_ALIVE",
188
- "34": "NON_PARTICIPATING",
189
- "35": "NOT_ALIVE",
190
  "36": "SUCCESS",
191
- "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
  "39": "NON_PARTICIPATING",
194
  "4": "SUCCESS",
195
  "40": "NOT_ALIVE",
196
- "41": "NOT_ALIVE",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
- "46": "SUCCESS",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
- "50": "NOT_ALIVE",
207
- "51": "SUCCESS",
208
  "52": "SUCCESS",
209
- "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
- "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "SUCCESS",
218
  "61": "SUCCESS",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
@@ -223,15 +223,15 @@
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "SUCCESS",
226
- "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
- "70": "NON_PARTICIPATING",
229
  "71": "SUCCESS",
230
- "72": "NON_PARTICIPATING",
231
- "73": "NOT_ALIVE",
232
- "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
- "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
@@ -239,7 +239,7 @@
239
  "80": "NOT_ALIVE",
240
  "81": "NON_PARTICIPATING",
241
  "82": "SUCCESS",
242
- "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
@@ -248,15 +248,15 @@
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
- "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NON_PARTICIPATING",
254
  "94": "SUCCESS",
255
  "95": "NON_PARTICIPATING",
256
- "96": "NON_PARTICIPATING",
257
- "97": "NOT_ALIVE",
258
  "98": "NOT_ALIVE",
259
- "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6434666,
268
- 6434681
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
- "inner_step": 83,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6434047,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "SUCCESS",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
 
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
+ "106": "FAIL",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
+ "111": "SUCCESS",
20
  "112": "NOT_ALIVE",
21
+ "113": "SUCCESS",
22
  "114": "NON_PARTICIPATING",
23
+ "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "NON_PARTICIPATING",
26
  "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
+ "12": "SUCCESS",
29
  "120": "NOT_ALIVE",
30
+ "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
+ "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
+ "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NOT_ALIVE",
 
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
+ "143": "NOT_ALIVE",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
+ "146": "NON_PARTICIPATING",
58
+ "147": "NOT_ALIVE",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
+ "150": "NOT_ALIVE",
63
+ "151": "NON_PARTICIPATING",
64
  "152": "SUCCESS",
65
+ "153": "NOT_ALIVE",
66
  "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
+ "157": "NOT_ALIVE",
70
  "158": "SUCCESS",
71
  "159": "NOT_ALIVE",
72
+ "16": "SUCCESS",
73
  "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
+ "162": "NOT_ALIVE",
76
+ "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
+ "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
 
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "SUCCESS",
86
+ "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
89
+ "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
+ "181": "NOT_ALIVE",
97
  "182": "SUCCESS",
98
  "183": "SUCCESS",
99
+ "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
+ "188": "NON_PARTICIPATING",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
+ "190": "SUCCESS",
107
+ "191": "NON_PARTICIPATING",
108
+ "192": "SUCCESS",
109
  "193": "NON_PARTICIPATING",
110
  "194": "SUCCESS",
111
  "195": "NON_PARTICIPATING",
 
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NOT_ALIVE",
 
126
  "208": "NON_PARTICIPATING",
127
  "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
+ "210": "NOT_ALIVE",
130
  "211": "SUCCESS",
131
  "212": "NON_PARTICIPATING",
132
  "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
+ "216": "FAIL",
136
+ "217": "NON_PARTICIPATING",
137
  "218": "SUCCESS",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
+ "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
143
+ "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
+ "226": "NOT_ALIVE",
147
+ "227": "NOT_ALIVE",
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "SUCCESS",
151
  "230": "NON_PARTICIPATING",
152
+ "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
+ "234": "SUCCESS",
156
+ "235": "NOT_ALIVE",
157
  "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "FAIL",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
+ "242": "NOT_ALIVE",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
  "247": "SUCCESS",
170
+ "248": "SUCCESS",
171
  "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
+ "251": "SUCCESS",
175
  "252": "NON_PARTICIPATING",
176
+ "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
+ "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
+ "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NOT_ALIVE",
186
+ "32": "NON_PARTICIPATING",
187
+ "33": "NON_PARTICIPATING",
188
+ "34": "NOT_ALIVE",
189
+ "35": "NON_PARTICIPATING",
190
  "36": "SUCCESS",
191
+ "37": "NON_PARTICIPATING",
192
  "38": "NON_PARTICIPATING",
193
  "39": "NON_PARTICIPATING",
194
  "4": "SUCCESS",
195
  "40": "NOT_ALIVE",
196
+ "41": "NON_PARTICIPATING",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
+ "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
+ "50": "FAIL",
207
+ "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
+ "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
 
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "SUCCESS",
226
+ "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
+ "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
+ "72": "SUCCESS",
231
+ "73": "NON_PARTICIPATING",
232
+ "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
234
+ "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
 
239
  "80": "NOT_ALIVE",
240
  "81": "NON_PARTICIPATING",
241
  "82": "SUCCESS",
242
+ "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
 
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
+ "91": "NON_PARTICIPATING",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NON_PARTICIPATING",
254
  "94": "SUCCESS",
255
  "95": "NON_PARTICIPATING",
256
+ "96": "SUCCESS",
257
+ "97": "NON_PARTICIPATING",
258
  "98": "NOT_ALIVE",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6434750,
268
+ 6434777
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
+ "inner_step": 5,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6434725,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cc6aec0767c39bc02ad713d7f60b376e0b280454889ddc32f69f574d4594f71
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9ed5367a10ad6f4f58195b84c71af1c419f08dfb01a21e45ba0a41d98b69b14
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73288f2c0e56418614716a8741ec0f630d8a6b83d3f405bb1f83c38c0cc6e4e1
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a81bbe1a635675656f1be4b7dcb94a72c14d5ef4931629fbc1fee1ccfc17125
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9af265f01a74a79e85fdd663521ece2958849672adff014d01ac636df87d91dc
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:917d093d784ae47695830992730e90b81a805980b14edab1ffde9f8f88c61a36
3
  size 4400216536