jockibaba commited on
Commit
33ecc14
·
verified ·
1 Parent(s): 6325b5c

Run 4. Outer Step 50. Inner Step 0.

Browse files
Files changed (3) hide show
  1. config.json +59 -59
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -3,11 +3,11 @@
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
6
- "1": "NON_PARTICIPATING",
7
  "10": "NON_PARTICIPATING",
8
  "100": "NON_PARTICIPATING",
9
  "101": "NON_PARTICIPATING",
10
- "102": "SUCCESS",
11
  "103": "NON_PARTICIPATING",
12
  "104": "NON_PARTICIPATING",
13
  "105": "NON_PARTICIPATING",
@@ -16,7 +16,7 @@
16
  "108": "NON_PARTICIPATING",
17
  "109": "NON_PARTICIPATING",
18
  "11": "SUCCESS",
19
- "110": "SUCCESS",
20
  "111": "NON_PARTICIPATING",
21
  "112": "NON_PARTICIPATING",
22
  "113": "NON_PARTICIPATING",
@@ -24,54 +24,54 @@
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": "SUCCESS",
31
  "121": "NON_PARTICIPATING",
32
- "122": "SUCCESS",
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": "NON_PARTICIPATING",
40
- "13": "NON_PARTICIPATING",
41
- "130": "SUCCESS",
42
  "131": "NON_PARTICIPATING",
43
  "132": "NON_PARTICIPATING",
44
  "133": "NON_PARTICIPATING",
45
  "134": "NON_PARTICIPATING",
46
  "135": "NON_PARTICIPATING",
47
- "136": "NON_PARTICIPATING",
48
  "137": "NON_PARTICIPATING",
49
- "138": "NON_PARTICIPATING",
50
  "139": "NON_PARTICIPATING",
51
  "14": "SUCCESS",
52
  "140": "NON_PARTICIPATING",
53
  "141": "NON_PARTICIPATING",
54
- "142": "NON_PARTICIPATING",
55
- "143": "SUCCESS",
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",
63
  "150": "NON_PARTICIPATING",
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
66
- "153": "SUCCESS",
67
  "154": "NON_PARTICIPATING",
68
  "155": "NON_PARTICIPATING",
69
  "156": "NON_PARTICIPATING",
70
- "157": "NON_PARTICIPATING",
71
  "158": "NON_PARTICIPATING",
72
  "159": "NON_PARTICIPATING",
73
  "16": "SUCCESS",
74
- "160": "NON_PARTICIPATING",
75
  "161": "NON_PARTICIPATING",
76
  "162": "NON_PARTICIPATING",
77
  "163": "NON_PARTICIPATING",
@@ -87,26 +87,26 @@
87
  "172": "NON_PARTICIPATING",
88
  "173": "NON_PARTICIPATING",
89
  "174": "NON_PARTICIPATING",
90
- "175": "NON_PARTICIPATING",
91
  "176": "NON_PARTICIPATING",
92
- "177": "NON_PARTICIPATING",
93
  "178": "NON_PARTICIPATING",
94
  "179": "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": "NON_PARTICIPATING",
102
  "186": "NON_PARTICIPATING",
103
- "187": "SUCCESS",
104
  "188": "NON_PARTICIPATING",
105
  "189": "NON_PARTICIPATING",
106
  "19": "SUCCESS",
107
  "190": "NON_PARTICIPATING",
108
  "191": "NON_PARTICIPATING",
109
- "192": "SUCCESS",
110
  "193": "NON_PARTICIPATING",
111
  "194": "NON_PARTICIPATING",
112
  "195": "NON_PARTICIPATING",
@@ -117,57 +117,57 @@
117
  "2": "SUCCESS",
118
  "20": "SUCCESS",
119
  "200": "NON_PARTICIPATING",
120
- "201": "NON_PARTICIPATING",
121
  "202": "NON_PARTICIPATING",
122
- "203": "NON_PARTICIPATING",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
125
  "206": "NON_PARTICIPATING",
126
  "207": "NON_PARTICIPATING",
127
- "208": "SUCCESS",
128
- "209": "SUCCESS",
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": "NON_PARTICIPATING",
137
  "217": "NON_PARTICIPATING",
138
  "218": "NON_PARTICIPATING",
139
  "219": "NON_PARTICIPATING",
140
  "22": "SUCCESS",
141
- "220": "NON_PARTICIPATING",
142
  "221": "NON_PARTICIPATING",
143
- "222": "SUCCESS",
144
  "223": "NON_PARTICIPATING",
145
  "224": "NON_PARTICIPATING",
146
- "225": "SUCCESS",
147
  "226": "NON_PARTICIPATING",
148
  "227": "NON_PARTICIPATING",
149
- "228": "SUCCESS",
150
- "229": "NON_PARTICIPATING",
151
  "23": "SUCCESS",
152
  "230": "NON_PARTICIPATING",
153
  "231": "NON_PARTICIPATING",
154
  "232": "NON_PARTICIPATING",
155
- "233": "NON_PARTICIPATING",
156
  "234": "NON_PARTICIPATING",
157
  "235": "NON_PARTICIPATING",
158
- "236": "SUCCESS",
159
  "237": "NON_PARTICIPATING",
160
  "238": "NON_PARTICIPATING",
161
- "239": "SUCCESS",
162
  "24": "SUCCESS",
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",
171
  "248": "NON_PARTICIPATING",
172
  "249": "NON_PARTICIPATING",
173
  "25": "SUCCESS",
@@ -176,13 +176,13 @@
176
  "252": "NON_PARTICIPATING",
177
  "253": "NON_PARTICIPATING",
178
  "254": "NON_PARTICIPATING",
179
- "255": "SUCCESS",
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
182
  "28": "SUCCESS",
183
  "29": "SUCCESS",
184
  "3": "SUCCESS",
185
- "30": "NON_PARTICIPATING",
186
  "31": "NON_PARTICIPATING",
187
  "32": "SUCCESS",
188
  "33": "NON_PARTICIPATING",
@@ -190,43 +190,43 @@
190
  "35": "SUCCESS",
191
  "36": "SUCCESS",
192
  "37": "SUCCESS",
193
- "38": "SUCCESS",
194
  "39": "SUCCESS",
195
  "4": "SUCCESS",
196
  "40": "SUCCESS",
197
  "41": "SUCCESS",
198
- "42": "SUCCESS",
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
202
  "46": "NON_PARTICIPATING",
203
- "47": "NON_PARTICIPATING",
204
  "48": "NON_PARTICIPATING",
205
  "49": "SUCCESS",
206
  "5": "SUCCESS",
207
  "50": "SUCCESS",
208
  "51": "SUCCESS",
209
- "52": "NON_PARTICIPATING",
210
  "53": "SUCCESS",
211
  "54": "SUCCESS",
212
  "55": "SUCCESS",
213
  "56": "SUCCESS",
214
- "57": "NON_PARTICIPATING",
215
  "58": "NON_PARTICIPATING",
216
  "59": "SUCCESS",
217
  "6": "NON_PARTICIPATING",
218
  "60": "SUCCESS",
219
  "61": "NON_PARTICIPATING",
220
  "62": "SUCCESS",
221
- "63": "NON_PARTICIPATING",
222
- "64": "SUCCESS",
223
  "65": "SUCCESS",
224
  "66": "SUCCESS",
225
  "67": "SUCCESS",
226
  "68": "SUCCESS",
227
  "69": "SUCCESS",
228
  "7": "SUCCESS",
229
- "70": "SUCCESS",
230
  "71": "NON_PARTICIPATING",
231
  "72": "SUCCESS",
232
  "73": "NON_PARTICIPATING",
@@ -240,14 +240,14 @@
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": "SUCCESS",
249
  "89": "SUCCESS",
250
- "9": "NON_PARTICIPATING",
251
  "90": "SUCCESS",
252
  "91": "SUCCESS",
253
  "92": "SUCCESS",
@@ -255,7 +255,7 @@
255
  "94": "SUCCESS",
256
  "95": "SUCCESS",
257
  "96": "SUCCESS",
258
- "97": "NON_PARTICIPATING",
259
  "98": "SUCCESS",
260
  "99": "SUCCESS"
261
  },
@@ -268,20 +268,20 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5619015,
272
- 5619019,
273
- 5619022,
274
- 5619026,
275
- 5619029
276
  ],
277
  "block_size": 1024,
278
  "bos_token_id": 50256,
279
  "embd_pdrop": 0.1,
280
  "eos_token_id": 50256,
281
  "initializer_range": 0.02,
282
- "inner_step": 44,
283
  "inner_steps": 0,
284
- "last_allreduce_block": 5617822,
285
  "layer_norm_epsilon": 1e-05,
286
  "model_type": "gpt_optimized",
287
  "n_embd": 1280,
 
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",
 
16
  "108": "NON_PARTICIPATING",
17
  "109": "NON_PARTICIPATING",
18
  "11": "SUCCESS",
19
+ "110": "NON_PARTICIPATING",
20
  "111": "NON_PARTICIPATING",
21
  "112": "NON_PARTICIPATING",
22
  "113": "NON_PARTICIPATING",
 
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
26
  "117": "NON_PARTICIPATING",
27
+ "118": "SUCCESS",
28
  "119": "NON_PARTICIPATING",
29
  "12": "SUCCESS",
30
+ "120": "NON_PARTICIPATING",
31
  "121": "NON_PARTICIPATING",
32
+ "122": "NON_PARTICIPATING",
33
  "123": "NON_PARTICIPATING",
34
  "124": "NON_PARTICIPATING",
35
  "125": "NON_PARTICIPATING",
36
+ "126": "NON_PARTICIPATING",
37
  "127": "NON_PARTICIPATING",
38
  "128": "NON_PARTICIPATING",
39
  "129": "NON_PARTICIPATING",
40
+ "13": "SUCCESS",
41
+ "130": "NON_PARTICIPATING",
42
  "131": "NON_PARTICIPATING",
43
  "132": "NON_PARTICIPATING",
44
  "133": "NON_PARTICIPATING",
45
  "134": "NON_PARTICIPATING",
46
  "135": "NON_PARTICIPATING",
47
+ "136": "SUCCESS",
48
  "137": "NON_PARTICIPATING",
49
+ "138": "SUCCESS",
50
  "139": "NON_PARTICIPATING",
51
  "14": "SUCCESS",
52
  "140": "NON_PARTICIPATING",
53
  "141": "NON_PARTICIPATING",
54
+ "142": "SUCCESS",
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": "NON_PARTICIPATING",
63
  "150": "NON_PARTICIPATING",
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
66
+ "153": "NON_PARTICIPATING",
67
  "154": "NON_PARTICIPATING",
68
  "155": "NON_PARTICIPATING",
69
  "156": "NON_PARTICIPATING",
70
+ "157": "SUCCESS",
71
  "158": "NON_PARTICIPATING",
72
  "159": "NON_PARTICIPATING",
73
  "16": "SUCCESS",
74
+ "160": "SUCCESS",
75
  "161": "NON_PARTICIPATING",
76
  "162": "NON_PARTICIPATING",
77
  "163": "NON_PARTICIPATING",
 
87
  "172": "NON_PARTICIPATING",
88
  "173": "NON_PARTICIPATING",
89
  "174": "NON_PARTICIPATING",
90
+ "175": "SUCCESS",
91
  "176": "NON_PARTICIPATING",
92
+ "177": "SUCCESS",
93
  "178": "NON_PARTICIPATING",
94
  "179": "NON_PARTICIPATING",
95
  "18": "SUCCESS",
96
  "180": "NON_PARTICIPATING",
97
+ "181": "SUCCESS",
98
+ "182": "NON_PARTICIPATING",
99
  "183": "NON_PARTICIPATING",
100
  "184": "NON_PARTICIPATING",
101
  "185": "NON_PARTICIPATING",
102
  "186": "NON_PARTICIPATING",
103
+ "187": "NON_PARTICIPATING",
104
  "188": "NON_PARTICIPATING",
105
  "189": "NON_PARTICIPATING",
106
  "19": "SUCCESS",
107
  "190": "NON_PARTICIPATING",
108
  "191": "NON_PARTICIPATING",
109
+ "192": "NON_PARTICIPATING",
110
  "193": "NON_PARTICIPATING",
111
  "194": "NON_PARTICIPATING",
112
  "195": "NON_PARTICIPATING",
 
117
  "2": "SUCCESS",
118
  "20": "SUCCESS",
119
  "200": "NON_PARTICIPATING",
120
+ "201": "SUCCESS",
121
  "202": "NON_PARTICIPATING",
122
+ "203": "SUCCESS",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
125
  "206": "NON_PARTICIPATING",
126
  "207": "NON_PARTICIPATING",
127
+ "208": "NON_PARTICIPATING",
128
+ "209": "NON_PARTICIPATING",
129
  "21": "SUCCESS",
130
+ "210": "NON_PARTICIPATING",
131
  "211": "NON_PARTICIPATING",
132
  "212": "NON_PARTICIPATING",
133
  "213": "NON_PARTICIPATING",
134
  "214": "NON_PARTICIPATING",
135
+ "215": "SUCCESS",
136
  "216": "NON_PARTICIPATING",
137
  "217": "NON_PARTICIPATING",
138
  "218": "NON_PARTICIPATING",
139
  "219": "NON_PARTICIPATING",
140
  "22": "SUCCESS",
141
+ "220": "SUCCESS",
142
  "221": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
153
  "231": "NON_PARTICIPATING",
154
  "232": "NON_PARTICIPATING",
155
+ "233": "SUCCESS",
156
  "234": "NON_PARTICIPATING",
157
  "235": "NON_PARTICIPATING",
158
+ "236": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
168
  "245": "NON_PARTICIPATING",
169
  "246": "NON_PARTICIPATING",
170
+ "247": "SUCCESS",
171
  "248": "NON_PARTICIPATING",
172
  "249": "NON_PARTICIPATING",
173
  "25": "SUCCESS",
 
176
  "252": "NON_PARTICIPATING",
177
  "253": "NON_PARTICIPATING",
178
  "254": "NON_PARTICIPATING",
179
+ "255": "NON_PARTICIPATING",
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
182
  "28": "SUCCESS",
183
  "29": "SUCCESS",
184
  "3": "SUCCESS",
185
+ "30": "SUCCESS",
186
  "31": "NON_PARTICIPATING",
187
  "32": "SUCCESS",
188
  "33": "NON_PARTICIPATING",
 
190
  "35": "SUCCESS",
191
  "36": "SUCCESS",
192
  "37": "SUCCESS",
193
+ "38": "NON_PARTICIPATING",
194
  "39": "SUCCESS",
195
  "4": "SUCCESS",
196
  "40": "SUCCESS",
197
  "41": "SUCCESS",
198
+ "42": "NON_PARTICIPATING",
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": "SUCCESS",
208
  "51": "SUCCESS",
209
+ "52": "SUCCESS",
210
  "53": "SUCCESS",
211
  "54": "SUCCESS",
212
  "55": "SUCCESS",
213
  "56": "SUCCESS",
214
+ "57": "SUCCESS",
215
  "58": "NON_PARTICIPATING",
216
  "59": "SUCCESS",
217
  "6": "NON_PARTICIPATING",
218
  "60": "SUCCESS",
219
  "61": "NON_PARTICIPATING",
220
  "62": "SUCCESS",
221
+ "63": "SUCCESS",
222
+ "64": "NON_PARTICIPATING",
223
  "65": "SUCCESS",
224
  "66": "SUCCESS",
225
  "67": "SUCCESS",
226
  "68": "SUCCESS",
227
  "69": "SUCCESS",
228
  "7": "SUCCESS",
229
+ "70": "NON_PARTICIPATING",
230
  "71": "NON_PARTICIPATING",
231
  "72": "SUCCESS",
232
  "73": "NON_PARTICIPATING",
 
240
  "80": "SUCCESS",
241
  "81": "SUCCESS",
242
  "82": "SUCCESS",
243
+ "83": "NON_PARTICIPATING",
244
  "84": "SUCCESS",
245
  "85": "NON_PARTICIPATING",
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
  "88": "SUCCESS",
249
  "89": "SUCCESS",
250
+ "9": "SUCCESS",
251
  "90": "SUCCESS",
252
  "91": "SUCCESS",
253
  "92": "SUCCESS",
 
255
  "94": "SUCCESS",
256
  "95": "SUCCESS",
257
  "96": "SUCCESS",
258
+ "97": "SUCCESS",
259
  "98": "SUCCESS",
260
  "99": "SUCCESS"
261
  },
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5622673,
272
+ 5622676,
273
+ 5622680,
274
+ 5622683,
275
+ 5622687
276
  ],
277
  "block_size": 1024,
278
  "bos_token_id": 50256,
279
  "embd_pdrop": 0.1,
280
  "eos_token_id": 50256,
281
  "initializer_range": 0.02,
282
+ "inner_step": 0,
283
  "inner_steps": 0,
284
+ "last_allreduce_block": 5571611,
285
  "layer_norm_epsilon": 1e-05,
286
  "model_type": "gpt_optimized",
287
  "n_embd": 1280,
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5af60aec4c4ee82dd2115fe77ad2a05c76236965a43ce6f2c2528a1ac9ffd961
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a2a0cbd13d1df2fb67e6ed8feaa25aeaee68b7ee9840f2c8914b16ce6f3e484
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef686e036684854e7925c34f48eb4bffa71b26fd892eaa097bc5f58ab68bb121
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51896991661e02507298ba54890fd1fc262804a915cbfa14522803049877c769
3
  size 4040701744