markalan324 commited on
Commit
fb0aa5d
·
verified ·
1 Parent(s): d64bdbe

Run 4. Outer Step 59. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +49 -49
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,20 +1,20 @@
1
  {
2
- "_name_or_path": "markalan324/minor12",
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
6
  "1": "SUCCESS",
7
  "10": "NON_PARTICIPATING",
8
  "100": "NON_PARTICIPATING",
9
- "101": "NON_PARTICIPATING",
10
  "102": "NON_PARTICIPATING",
11
  "103": "NON_PARTICIPATING",
12
- "104": "NON_PARTICIPATING",
13
  "105": "NON_PARTICIPATING",
14
- "106": "NON_PARTICIPATING",
15
- "107": "NON_PARTICIPATING",
16
  "108": "NON_PARTICIPATING",
17
- "109": "NON_PARTICIPATING",
18
  "11": "SUCCESS",
19
  "110": "NON_PARTICIPATING",
20
  "111": "SUCCESS",
@@ -23,8 +23,8 @@
23
  "114": "NON_PARTICIPATING",
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
26
- "117": "NON_PARTICIPATING",
27
- "118": "NON_PARTICIPATING",
28
  "119": "NON_PARTICIPATING",
29
  "12": "SUCCESS",
30
  "120": "NON_PARTICIPATING",
@@ -32,13 +32,13 @@
32
  "122": "NON_PARTICIPATING",
33
  "123": "NON_PARTICIPATING",
34
  "124": "NON_PARTICIPATING",
35
- "125": "SUCCESS",
36
  "126": "SUCCESS",
37
  "127": "NON_PARTICIPATING",
38
  "128": "NON_PARTICIPATING",
39
  "129": "SUCCESS",
40
  "13": "SUCCESS",
41
- "130": "NON_PARTICIPATING",
42
  "131": "NON_PARTICIPATING",
43
  "132": "NON_PARTICIPATING",
44
  "133": "NON_PARTICIPATING",
@@ -47,16 +47,16 @@
47
  "136": "NON_PARTICIPATING",
48
  "137": "NON_PARTICIPATING",
49
  "138": "NON_PARTICIPATING",
50
- "139": "NON_PARTICIPATING",
51
  "14": "NON_PARTICIPATING",
52
  "140": "NON_PARTICIPATING",
53
- "141": "NON_PARTICIPATING",
54
  "142": "NON_PARTICIPATING",
55
  "143": "NON_PARTICIPATING",
56
  "144": "NON_PARTICIPATING",
57
  "145": "NON_PARTICIPATING",
58
  "146": "NON_PARTICIPATING",
59
- "147": "SUCCESS",
60
  "148": "NON_PARTICIPATING",
61
  "149": "NON_PARTICIPATING",
62
  "15": "SUCCESS",
@@ -66,7 +66,7 @@
66
  "153": "NON_PARTICIPATING",
67
  "154": "NON_PARTICIPATING",
68
  "155": "NON_PARTICIPATING",
69
- "156": "SUCCESS",
70
  "157": "NON_PARTICIPATING",
71
  "158": "NON_PARTICIPATING",
72
  "159": "NON_PARTICIPATING",
@@ -83,10 +83,10 @@
83
  "169": "NON_PARTICIPATING",
84
  "17": "SUCCESS",
85
  "170": "NON_PARTICIPATING",
86
- "171": "SUCCESS",
87
  "172": "NON_PARTICIPATING",
88
  "173": "SUCCESS",
89
- "174": "NON_PARTICIPATING",
90
  "175": "NON_PARTICIPATING",
91
  "176": "NON_PARTICIPATING",
92
  "177": "NON_PARTICIPATING",
@@ -95,12 +95,12 @@
95
  "18": "SUCCESS",
96
  "180": "NON_PARTICIPATING",
97
  "181": "NON_PARTICIPATING",
98
- "182": "NON_PARTICIPATING",
99
  "183": "NON_PARTICIPATING",
100
  "184": "NON_PARTICIPATING",
101
- "185": "NON_PARTICIPATING",
102
  "186": "NON_PARTICIPATING",
103
- "187": "SUCCESS",
104
  "188": "NON_PARTICIPATING",
105
  "189": "NON_PARTICIPATING",
106
  "19": "NON_PARTICIPATING",
@@ -116,9 +116,9 @@
116
  "199": "NON_PARTICIPATING",
117
  "2": "SUCCESS",
118
  "20": "NON_PARTICIPATING",
119
- "200": "SUCCESS",
120
  "201": "NON_PARTICIPATING",
121
- "202": "SUCCESS",
122
  "203": "NON_PARTICIPATING",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
@@ -129,12 +129,12 @@
129
  "21": "SUCCESS",
130
  "210": "SUCCESS",
131
  "211": "NON_PARTICIPATING",
132
- "212": "NON_PARTICIPATING",
133
  "213": "NON_PARTICIPATING",
134
  "214": "NON_PARTICIPATING",
135
  "215": "NON_PARTICIPATING",
136
- "216": "SUCCESS",
137
- "217": "NON_PARTICIPATING",
138
  "218": "NON_PARTICIPATING",
139
  "219": "NON_PARTICIPATING",
140
  "22": "SUCCESS",
@@ -143,15 +143,15 @@
143
  "222": "NON_PARTICIPATING",
144
  "223": "NON_PARTICIPATING",
145
  "224": "NON_PARTICIPATING",
146
- "225": "NON_PARTICIPATING",
147
  "226": "NON_PARTICIPATING",
148
  "227": "NON_PARTICIPATING",
149
  "228": "NON_PARTICIPATING",
150
- "229": "SUCCESS",
151
  "23": "SUCCESS",
152
- "230": "SUCCESS",
153
  "231": "NON_PARTICIPATING",
154
- "232": "NON_PARTICIPATING",
155
  "233": "NON_PARTICIPATING",
156
  "234": "NON_PARTICIPATING",
157
  "235": "NON_PARTICIPATING",
@@ -159,12 +159,12 @@
159
  "237": "NON_PARTICIPATING",
160
  "238": "NON_PARTICIPATING",
161
  "239": "NON_PARTICIPATING",
162
- "24": "SUCCESS",
163
  "240": "NON_PARTICIPATING",
164
  "241": "NON_PARTICIPATING",
165
- "242": "SUCCESS",
166
  "243": "NON_PARTICIPATING",
167
- "244": "SUCCESS",
168
  "245": "NON_PARTICIPATING",
169
  "246": "NON_PARTICIPATING",
170
  "247": "NON_PARTICIPATING",
@@ -175,7 +175,7 @@
175
  "251": "NON_PARTICIPATING",
176
  "252": "NON_PARTICIPATING",
177
  "253": "NON_PARTICIPATING",
178
- "254": "NON_PARTICIPATING",
179
  "255": "NON_PARTICIPATING",
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
@@ -198,16 +198,16 @@
198
  "42": "SUCCESS",
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
- "45": "SUCCESS",
202
  "46": "NON_PARTICIPATING",
203
  "47": "SUCCESS",
204
  "48": "NON_PARTICIPATING",
205
- "49": "SUCCESS",
206
  "5": "SUCCESS",
207
- "50": "NON_PARTICIPATING",
208
  "51": "SUCCESS",
209
  "52": "NON_PARTICIPATING",
210
- "53": "SUCCESS",
211
  "54": "SUCCESS",
212
  "55": "SUCCESS",
213
  "56": "SUCCESS",
@@ -218,17 +218,17 @@
218
  "60": "SUCCESS",
219
  "61": "NON_PARTICIPATING",
220
  "62": "SUCCESS",
221
- "63": "SUCCESS",
222
- "64": "SUCCESS",
223
  "65": "NON_PARTICIPATING",
224
- "66": "SUCCESS",
225
  "67": "SUCCESS",
226
  "68": "SUCCESS",
227
  "69": "SUCCESS",
228
- "7": "SUCCESS",
229
  "70": "SUCCESS",
230
  "71": "SUCCESS",
231
- "72": "SUCCESS",
232
  "73": "NON_PARTICIPATING",
233
  "74": "SUCCESS",
234
  "75": "SUCCESS",
@@ -240,12 +240,12 @@
240
  "80": "SUCCESS",
241
  "81": "SUCCESS",
242
  "82": "SUCCESS",
243
- "83": "NON_PARTICIPATING",
244
  "84": "SUCCESS",
245
- "85": "SUCCESS",
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
- "88": "SUCCESS",
249
  "89": "SUCCESS",
250
  "9": "SUCCESS",
251
  "90": "SUCCESS",
@@ -255,7 +255,7 @@
255
  "94": "SUCCESS",
256
  "95": "SUCCESS",
257
  "96": "SUCCESS",
258
- "97": "SUCCESS",
259
  "98": "SUCCESS",
260
  "99": "SUCCESS"
261
  },
@@ -268,17 +268,17 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5638025,
272
- 5638059
273
  ],
274
  "block_size": 1024,
275
  "bos_token_id": 50256,
276
  "embd_pdrop": 0.1,
277
  "eos_token_id": 50256,
278
  "initializer_range": 0.02,
279
- "inner_step": 37,
280
  "inner_steps": 0,
281
- "last_allreduce_block": 5634142,
282
  "layer_norm_epsilon": 1e-05,
283
  "model_type": "gpt_optimized",
284
  "n_embd": 1280,
 
1
  {
2
+ "_name_or_path": "distributed/optimized-gpt2-1b",
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
6
  "1": "SUCCESS",
7
  "10": "NON_PARTICIPATING",
8
  "100": "NON_PARTICIPATING",
9
+ "101": "SUCCESS",
10
  "102": "NON_PARTICIPATING",
11
  "103": "NON_PARTICIPATING",
12
+ "104": "SUCCESS",
13
  "105": "NON_PARTICIPATING",
14
+ "106": "SUCCESS",
15
+ "107": "SUCCESS",
16
  "108": "NON_PARTICIPATING",
17
+ "109": "FAIL",
18
  "11": "SUCCESS",
19
  "110": "NON_PARTICIPATING",
20
  "111": "SUCCESS",
 
23
  "114": "NON_PARTICIPATING",
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
26
+ "117": "SUCCESS",
27
+ "118": "SUCCESS",
28
  "119": "NON_PARTICIPATING",
29
  "12": "SUCCESS",
30
  "120": "NON_PARTICIPATING",
 
32
  "122": "NON_PARTICIPATING",
33
  "123": "NON_PARTICIPATING",
34
  "124": "NON_PARTICIPATING",
35
+ "125": "NON_PARTICIPATING",
36
  "126": "SUCCESS",
37
  "127": "NON_PARTICIPATING",
38
  "128": "NON_PARTICIPATING",
39
  "129": "SUCCESS",
40
  "13": "SUCCESS",
41
+ "130": "SUCCESS",
42
  "131": "NON_PARTICIPATING",
43
  "132": "NON_PARTICIPATING",
44
  "133": "NON_PARTICIPATING",
 
47
  "136": "NON_PARTICIPATING",
48
  "137": "NON_PARTICIPATING",
49
  "138": "NON_PARTICIPATING",
50
+ "139": "SUCCESS",
51
  "14": "NON_PARTICIPATING",
52
  "140": "NON_PARTICIPATING",
53
+ "141": "SUCCESS",
54
  "142": "NON_PARTICIPATING",
55
  "143": "NON_PARTICIPATING",
56
  "144": "NON_PARTICIPATING",
57
  "145": "NON_PARTICIPATING",
58
  "146": "NON_PARTICIPATING",
59
+ "147": "NON_PARTICIPATING",
60
  "148": "NON_PARTICIPATING",
61
  "149": "NON_PARTICIPATING",
62
  "15": "SUCCESS",
 
66
  "153": "NON_PARTICIPATING",
67
  "154": "NON_PARTICIPATING",
68
  "155": "NON_PARTICIPATING",
69
+ "156": "NON_PARTICIPATING",
70
  "157": "NON_PARTICIPATING",
71
  "158": "NON_PARTICIPATING",
72
  "159": "NON_PARTICIPATING",
 
83
  "169": "NON_PARTICIPATING",
84
  "17": "SUCCESS",
85
  "170": "NON_PARTICIPATING",
86
+ "171": "NON_PARTICIPATING",
87
  "172": "NON_PARTICIPATING",
88
  "173": "SUCCESS",
89
+ "174": "FAIL",
90
  "175": "NON_PARTICIPATING",
91
  "176": "NON_PARTICIPATING",
92
  "177": "NON_PARTICIPATING",
 
95
  "18": "SUCCESS",
96
  "180": "NON_PARTICIPATING",
97
  "181": "NON_PARTICIPATING",
98
+ "182": "SUCCESS",
99
  "183": "NON_PARTICIPATING",
100
  "184": "NON_PARTICIPATING",
101
+ "185": "FAIL",
102
  "186": "NON_PARTICIPATING",
103
+ "187": "NON_PARTICIPATING",
104
  "188": "NON_PARTICIPATING",
105
  "189": "NON_PARTICIPATING",
106
  "19": "NON_PARTICIPATING",
 
116
  "199": "NON_PARTICIPATING",
117
  "2": "SUCCESS",
118
  "20": "NON_PARTICIPATING",
119
+ "200": "NON_PARTICIPATING",
120
  "201": "NON_PARTICIPATING",
121
+ "202": "NON_PARTICIPATING",
122
  "203": "NON_PARTICIPATING",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
 
129
  "21": "SUCCESS",
130
  "210": "SUCCESS",
131
  "211": "NON_PARTICIPATING",
132
+ "212": "SUCCESS",
133
  "213": "NON_PARTICIPATING",
134
  "214": "NON_PARTICIPATING",
135
  "215": "NON_PARTICIPATING",
136
+ "216": "NON_PARTICIPATING",
137
+ "217": "SUCCESS",
138
  "218": "NON_PARTICIPATING",
139
  "219": "NON_PARTICIPATING",
140
  "22": "SUCCESS",
 
143
  "222": "NON_PARTICIPATING",
144
  "223": "NON_PARTICIPATING",
145
  "224": "NON_PARTICIPATING",
146
+ "225": "SUCCESS",
147
  "226": "NON_PARTICIPATING",
148
  "227": "NON_PARTICIPATING",
149
  "228": "NON_PARTICIPATING",
150
+ "229": "NON_PARTICIPATING",
151
  "23": "SUCCESS",
152
+ "230": "NON_PARTICIPATING",
153
  "231": "NON_PARTICIPATING",
154
+ "232": "SUCCESS",
155
  "233": "NON_PARTICIPATING",
156
  "234": "NON_PARTICIPATING",
157
  "235": "NON_PARTICIPATING",
 
159
  "237": "NON_PARTICIPATING",
160
  "238": "NON_PARTICIPATING",
161
  "239": "NON_PARTICIPATING",
162
+ "24": "FAIL",
163
  "240": "NON_PARTICIPATING",
164
  "241": "NON_PARTICIPATING",
165
+ "242": "NON_PARTICIPATING",
166
  "243": "NON_PARTICIPATING",
167
+ "244": "NON_PARTICIPATING",
168
  "245": "NON_PARTICIPATING",
169
  "246": "NON_PARTICIPATING",
170
  "247": "NON_PARTICIPATING",
 
175
  "251": "NON_PARTICIPATING",
176
  "252": "NON_PARTICIPATING",
177
  "253": "NON_PARTICIPATING",
178
+ "254": "FAIL",
179
  "255": "NON_PARTICIPATING",
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
 
198
  "42": "SUCCESS",
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
+ "45": "FAIL",
202
  "46": "NON_PARTICIPATING",
203
  "47": "SUCCESS",
204
  "48": "NON_PARTICIPATING",
205
+ "49": "FAIL",
206
  "5": "SUCCESS",
207
+ "50": "SUCCESS",
208
  "51": "SUCCESS",
209
  "52": "NON_PARTICIPATING",
210
+ "53": "NON_PARTICIPATING",
211
  "54": "SUCCESS",
212
  "55": "SUCCESS",
213
  "56": "SUCCESS",
 
218
  "60": "SUCCESS",
219
  "61": "NON_PARTICIPATING",
220
  "62": "SUCCESS",
221
+ "63": "FAIL",
222
+ "64": "NON_PARTICIPATING",
223
  "65": "NON_PARTICIPATING",
224
+ "66": "NON_PARTICIPATING",
225
  "67": "SUCCESS",
226
  "68": "SUCCESS",
227
  "69": "SUCCESS",
228
+ "7": "FAIL",
229
  "70": "SUCCESS",
230
  "71": "SUCCESS",
231
+ "72": "NON_PARTICIPATING",
232
  "73": "NON_PARTICIPATING",
233
  "74": "SUCCESS",
234
  "75": "SUCCESS",
 
240
  "80": "SUCCESS",
241
  "81": "SUCCESS",
242
  "82": "SUCCESS",
243
+ "83": "SUCCESS",
244
  "84": "SUCCESS",
245
+ "85": "NON_PARTICIPATING",
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
+ "88": "FAIL",
249
  "89": "SUCCESS",
250
  "9": "SUCCESS",
251
  "90": "SUCCESS",
 
255
  "94": "SUCCESS",
256
  "95": "SUCCESS",
257
  "96": "SUCCESS",
258
+ "97": "NON_PARTICIPATING",
259
  "98": "SUCCESS",
260
  "99": "SUCCESS"
261
  },
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5638253,
272
+ 5638283
273
  ],
274
  "block_size": 1024,
275
  "bos_token_id": 50256,
276
  "embd_pdrop": 0.1,
277
  "eos_token_id": 50256,
278
  "initializer_range": 0.02,
279
+ "inner_step": 2,
280
  "inner_steps": 0,
281
+ "last_allreduce_block": 5638171,
282
  "layer_norm_epsilon": 1e-05,
283
  "model_type": "gpt_optimized",
284
  "n_embd": 1280,
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43834f32d7d5653c32f13c14ffb76bfb3f530339a07beceba1320511b589aa8f
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf79d8c593a0e525757b11d70bdbb5ac5b941e4fc74420cd6addb62cbad6114
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:889ffaa141eb67d0e25c931ce430669951fbfecc09330f65a5dcd611e8da82d2
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a828aa1fe1ccab8028b23c04f0b2e8b61858eb338e31d4134b181cf6cfd026bc
3
  size 4040701744