mizzaay commited on
Commit
d32e061
·
verified ·
1 Parent(s): 776c593

Run 6. Outer Step 61. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +44 -44
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,24 +2,24 @@
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": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
- "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
- "111": "NOT_ALIVE",
20
- "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
- "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
@@ -34,7 +34,7 @@
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NON_PARTICIPATING",
37
- "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
@@ -54,7 +54,7 @@
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NON_PARTICIPATING",
57
- "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
@@ -63,25 +63,25 @@
63
  "151": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
78
- "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
- "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
@@ -101,38 +101,38 @@
101
  "186": "NON_PARTICIPATING",
102
  "187": "SUCCESS",
103
  "188": "NOT_ALIVE",
104
- "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
- "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
- "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
- "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
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": "SUCCESS",
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": "NOT_ALIVE",
@@ -140,7 +140,7 @@
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
- "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
@@ -148,11 +148,11 @@
148
  "228": "SUCCESS",
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": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
@@ -179,12 +179,12 @@
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
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": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
@@ -197,11 +197,11 @@
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
  "44": "NOT_ALIVE",
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": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
@@ -215,7 +215,7 @@
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
- "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
@@ -225,10 +225,10 @@
225
  "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
- "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
- "73": "NON_PARTICIPATING",
232
  "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
@@ -239,7 +239,7 @@
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
- "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
@@ -249,14 +249,14 @@
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
- "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
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
- 6170104,
268
- 6170146
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": 33,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6169441,
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": "NON_PARTICIPATING",
8
  "101": "NOT_ALIVE",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
+ "105": "NOT_ALIVE",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
+ "111": "NON_PARTICIPATING",
20
+ "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
22
+ "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
 
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NON_PARTICIPATING",
37
+ "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
 
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NON_PARTICIPATING",
57
+ "146": "NOT_ALIVE",
58
  "147": "NOT_ALIVE",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
 
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
+ "154": "NON_PARTICIPATING",
67
+ "155": "NON_PARTICIPATING",
68
+ "156": "SUCCESS",
69
  "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
+ "160": "NON_PARTICIPATING",
74
+ "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
+ "163": "NOT_ALIVE",
77
+ "164": "SUCCESS",
78
+ "165": "NOT_ALIVE",
79
  "166": "SUCCESS",
80
  "167": "NON_PARTICIPATING",
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",
 
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": "NOT_ALIVE",
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": "NOT_ALIVE",
119
  "201": "SUCCESS",
120
+ "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NOT_ALIVE",
124
+ "206": "NOT_ALIVE",
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": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
+ "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NOT_ALIVE",
 
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
+ "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
 
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
+ "230": "NOT_ALIVE",
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": "SUCCESS",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
 
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
+ "29": "NON_PARTICIPATING",
183
+ "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
+ "31": "SUCCESS",
186
  "32": "NON_PARTICIPATING",
187
+ "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
 
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
  "44": "NOT_ALIVE",
200
+ "45": "NOT_ALIVE",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
+ "49": "NON_PARTICIPATING",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "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": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
+ "73": "NOT_ALIVE",
232
  "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
 
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
 
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
+ "92": "NON_PARTICIPATING",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6170265,
268
+ 6170306
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": 6170077,
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 sha256:0b2591041b2f6fb0ec247f62367f4c8b2b102feaaba0cc98d9a4b4b217308e9f
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8bfd8b5962b64897ac47fd1c1cc26d0ef0fb5301542cc7a70c2cedb9815febe
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:becaa090487098734bdb1410ecc6df58fcf2a7a9242450753f4dea2421defc1a
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c73713bd02e4fa6a1b355d1d88cad41b6661e885860bec5ae762b6666877298
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:939b571bc2cc6601461bf01720f4cc79ecbd13fe1f43bda7c61ec2cbef68041f
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb2dc0e530702c564fc50da8a8e3d8fb769e7ce65577e5e58e3edb7bb272a04c
3
  size 4400216536