mizzaay commited on
Commit
270d77c
·
verified ·
1 Parent(s): 79dde32

Run 6. Outer Step 49. Inner Step 4.

Browse files
Files changed (4) hide show
  1. config.json +60 -60
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,14 +2,14 @@
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "SUCCESS",
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
  "101": "NOT_ALIVE",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
- "105": "NOT_ALIVE",
13
  "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
@@ -19,20 +19,20 @@
19
  "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
- "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
- "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
32
- "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
- "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
@@ -41,18 +41,18 @@
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
- "134": "NON_PARTICIPATING",
45
- "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
- "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
- "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
- "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
@@ -64,28 +64,28 @@
64
  "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
  "154": "SUCCESS",
67
- "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
- "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
- "160": "NOT_ALIVE",
74
- "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
80
- "167": "NON_PARTICIPATING",
81
- "168": "NOT_ALIVE",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
- "173": "NOT_ALIVE",
88
- "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
@@ -97,42 +97,42 @@
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
  "184": "NOT_ALIVE",
100
- "185": "NOT_ALIVE",
101
  "186": "NON_PARTICIPATING",
102
  "187": "SUCCESS",
103
  "188": "NOT_ALIVE",
104
  "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
106
- "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
- "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
- "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
- "200": "NON_PARTICIPATING",
119
  "201": "SUCCESS",
120
  "202": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
- "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
- "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
- "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
- "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "SUCCESS",
@@ -140,19 +140,19 @@
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
- "223": "NOT_ALIVE",
144
- "224": "NOT_ALIVE",
145
- "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NOT_ALIVE",
148
- "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
- "234": "NOT_ALIVE",
156
  "235": "NOT_ALIVE",
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
@@ -161,7 +161,7 @@
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
- "242": "SUCCESS",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
@@ -170,32 +170,32 @@
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
- "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "NON_PARTICIPATING",
180
- "27": "NON_PARTICIPATING",
181
- "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
183
- "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "NOT_ALIVE",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NON_PARTICIPATING",
188
- "34": "NOT_ALIVE",
189
- "35": "NON_PARTICIPATING",
190
- "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
- "41": "NOT_ALIVE",
197
  "42": "NON_PARTICIPATING",
198
- "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
@@ -205,17 +205,17 @@
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
- "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
- "54": "NOT_ALIVE",
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": "NOT_ALIVE",
218
- "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
@@ -225,9 +225,9 @@
225
  "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
- "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
- "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
@@ -242,8 +242,8 @@
242
  "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
- "86": "NON_PARTICIPATING",
246
- "87": "NOT_ALIVE",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
@@ -251,8 +251,8 @@
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NON_PARTICIPATING",
254
- "94": "NON_PARTICIPATING",
255
- "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6162232,
268
- 6162271
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": 42,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6161553,
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": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
  "101": "NOT_ALIVE",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
+ "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
 
19
  "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
+ "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
+ "117": "NON_PARTICIPATING",
26
  "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
32
+ "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
+ "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
 
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
+ "134": "NOT_ALIVE",
45
+ "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
+ "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
+ "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
+ "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
 
64
  "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
  "154": "SUCCESS",
67
+ "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
+ "160": "NON_PARTICIPATING",
74
+ "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
80
+ "167": "NOT_ALIVE",
81
+ "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
+ "173": "NON_PARTICIPATING",
88
+ "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
 
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
  "184": "NOT_ALIVE",
100
+ "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
102
  "187": "SUCCESS",
103
  "188": "NOT_ALIVE",
104
  "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
106
+ "190": "SUCCESS",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
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": "NOT_ALIVE",
119
  "201": "SUCCESS",
120
  "202": "NON_PARTICIPATING",
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": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "NOT_ALIVE",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "NOT_ALIVE",
134
  "215": "NON_PARTICIPATING",
135
+ "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "SUCCESS",
 
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
+ "223": "NON_PARTICIPATING",
144
+ "224": "NON_PARTICIPATING",
145
+ "225": "NOT_ALIVE",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NOT_ALIVE",
148
+ "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
+ "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
 
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
+ "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
 
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
+ "252": "NOT_ALIVE",
176
  "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "NOT_ALIVE",
180
+ "27": "NOT_ALIVE",
181
+ "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
183
+ "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
  "31": "NOT_ALIVE",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NON_PARTICIPATING",
188
+ "34": "NON_PARTICIPATING",
189
+ "35": "NOT_ALIVE",
190
+ "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
+ "43": "NON_PARTICIPATING",
199
  "44": "NOT_ALIVE",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
 
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
+ "52": "NON_PARTICIPATING",
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": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
 
225
  "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
+ "70": "SUCCESS",
229
  "71": "NON_PARTICIPATING",
230
+ "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
 
242
  "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
+ "86": "NOT_ALIVE",
246
+ "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
 
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NON_PARTICIPATING",
254
+ "94": "NOT_ALIVE",
255
+ "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6162424,
268
+ 6162457
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": 4,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6162264,
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 sha256:8a759f6bdf6e1d7ae8fbe040dff179bdbc4aa77cf0cbab25dc3ad1c13b7fbdfb
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b92b9c829a5c2d654c7f6288b93067f9038eb46cb74d6c5788beb27752b8d4f8
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef3bfe2a903853335eb647fa99b4e903108d9efa5d0042629b98cb748146b592
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0c123c96f87bddff5fa9368d974b276ca1d74e505cd23b0a1e64411d7fb36e1
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b862048fb7dcfa3c9481e7d8a305069c463cc2e3f14697b324a4e23b37e0c345
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ab8fab3aab26a93c5b2525e5b7ba3e5b0b625328a70eb49b9a7ab81fc42433
3
  size 4400216536