jockibaba commited on
Commit
1819342
·
verified ·
1 Parent(s): 06421bb

Run 4. Outer Step 49. Inner Step 0.

Browse files
Files changed (3) hide show
  1. config.json +60 -54
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "jockibaba/jockibaba10",
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
@@ -12,14 +12,14 @@
12
  "104": "NON_PARTICIPATING",
13
  "105": "NON_PARTICIPATING",
14
  "106": "NON_PARTICIPATING",
15
- "107": "SUCCESS",
16
- "108": "NON_PARTICIPATING",
17
- "109": "SUCCESS",
18
- "11": "NON_PARTICIPATING",
19
  "110": "NON_PARTICIPATING",
20
  "111": "NON_PARTICIPATING",
21
  "112": "NON_PARTICIPATING",
22
- "113": "SUCCESS",
23
  "114": "NON_PARTICIPATING",
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
@@ -30,15 +30,15 @@
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": "SUCCESS",
38
  "128": "NON_PARTICIPATING",
39
  "129": "NON_PARTICIPATING",
40
  "13": "SUCCESS",
41
- "130": "SUCCESS",
42
  "131": "NON_PARTICIPATING",
43
  "132": "NON_PARTICIPATING",
44
  "133": "NON_PARTICIPATING",
@@ -48,7 +48,7 @@
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",
@@ -57,13 +57,13 @@
57
  "145": "NON_PARTICIPATING",
58
  "146": "NON_PARTICIPATING",
59
  "147": "NON_PARTICIPATING",
60
- "148": "SUCCESS",
61
  "149": "NON_PARTICIPATING",
62
  "15": "SUCCESS",
63
- "150": "SUCCESS",
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
66
- "153": "NON_PARTICIPATING",
67
  "154": "NON_PARTICIPATING",
68
  "155": "NON_PARTICIPATING",
69
  "156": "NON_PARTICIPATING",
@@ -76,40 +76,40 @@
76
  "162": "NON_PARTICIPATING",
77
  "163": "NON_PARTICIPATING",
78
  "164": "NON_PARTICIPATING",
79
- "165": "SUCCESS",
80
  "166": "NON_PARTICIPATING",
81
  "167": "NON_PARTICIPATING",
82
- "168": "NON_PARTICIPATING",
83
- "169": "SUCCESS",
84
  "17": "SUCCESS",
85
  "170": "NON_PARTICIPATING",
86
  "171": "SUCCESS",
87
  "172": "NON_PARTICIPATING",
88
- "173": "NON_PARTICIPATING",
89
  "174": "NON_PARTICIPATING",
90
  "175": "NON_PARTICIPATING",
91
  "176": "NON_PARTICIPATING",
92
- "177": "SUCCESS",
93
  "178": "NON_PARTICIPATING",
94
  "179": "NON_PARTICIPATING",
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": "SUCCESS",
106
- "19": "NON_PARTICIPATING",
107
- "190": "SUCCESS",
108
  "191": "NON_PARTICIPATING",
109
- "192": "SUCCESS",
110
  "193": "NON_PARTICIPATING",
111
  "194": "NON_PARTICIPATING",
112
- "195": "SUCCESS",
113
  "196": "NON_PARTICIPATING",
114
  "197": "NON_PARTICIPATING",
115
  "198": "NON_PARTICIPATING",
@@ -119,45 +119,45 @@
119
  "200": "NON_PARTICIPATING",
120
  "201": "NON_PARTICIPATING",
121
  "202": "NON_PARTICIPATING",
122
- "203": "SUCCESS",
123
  "204": "NON_PARTICIPATING",
124
- "205": "FAIL",
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": "SUCCESS",
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": "NON_PARTICIPATING",
144
- "223": "SUCCESS",
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": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
159
  "237": "NON_PARTICIPATING",
160
- "238": "NON_PARTICIPATING",
161
  "239": "NON_PARTICIPATING",
162
  "24": "SUCCESS",
163
  "240": "NON_PARTICIPATING",
@@ -173,10 +173,10 @@
173
  "25": "SUCCESS",
174
  "250": "NON_PARTICIPATING",
175
  "251": "NON_PARTICIPATING",
176
- "252": "SUCCESS",
177
  "253": "NON_PARTICIPATING",
178
  "254": "NON_PARTICIPATING",
179
- "255": "SUCCESS",
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
182
  "28": "SUCCESS",
@@ -186,9 +186,9 @@
186
  "31": "SUCCESS",
187
  "32": "SUCCESS",
188
  "33": "NON_PARTICIPATING",
189
- "34": "NON_PARTICIPATING",
190
  "35": "SUCCESS",
191
- "36": "NON_PARTICIPATING",
192
  "37": "SUCCESS",
193
  "38": "SUCCESS",
194
  "39": "SUCCESS",
@@ -200,18 +200,18 @@
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
202
  "46": "NON_PARTICIPATING",
203
- "47": "NON_PARTICIPATING",
204
  "48": "NON_PARTICIPATING",
205
  "49": "SUCCESS",
206
  "5": "NON_PARTICIPATING",
207
  "50": "SUCCESS",
208
  "51": "SUCCESS",
209
  "52": "SUCCESS",
210
- "53": "NON_PARTICIPATING",
211
  "54": "SUCCESS",
212
  "55": "SUCCESS",
213
  "56": "SUCCESS",
214
- "57": "FAIL",
215
  "58": "NON_PARTICIPATING",
216
  "59": "SUCCESS",
217
  "6": "NON_PARTICIPATING",
@@ -223,8 +223,8 @@
223
  "65": "SUCCESS",
224
  "66": "SUCCESS",
225
  "67": "SUCCESS",
226
- "68": "NON_PARTICIPATING",
227
- "69": "NON_PARTICIPATING",
228
  "7": "SUCCESS",
229
  "70": "NON_PARTICIPATING",
230
  "71": "NON_PARTICIPATING",
@@ -234,7 +234,7 @@
234
  "75": "SUCCESS",
235
  "76": "SUCCESS",
236
  "77": "SUCCESS",
237
- "78": "NON_PARTICIPATING",
238
  "79": "NON_PARTICIPATING",
239
  "8": "SUCCESS",
240
  "80": "SUCCESS",
@@ -242,12 +242,12 @@
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": "NON_PARTICIPATING",
251
  "90": "SUCCESS",
252
  "91": "SUCCESS",
253
  "92": "SUCCESS",
@@ -267,7 +267,13 @@
267
  "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
- "block_list": [],
 
 
 
 
 
 
271
  "block_size": 1024,
272
  "bos_token_id": 50256,
273
  "embd_pdrop": 0.1,
@@ -275,7 +281,7 @@
275
  "initializer_range": 0.02,
276
  "inner_step": 0,
277
  "inner_steps": 0,
278
- "last_allreduce_block": 5543976,
279
  "layer_norm_epsilon": 1e-05,
280
  "model_type": "gpt_optimized",
281
  "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",
 
12
  "104": "NON_PARTICIPATING",
13
  "105": "NON_PARTICIPATING",
14
  "106": "NON_PARTICIPATING",
15
+ "107": "NON_PARTICIPATING",
16
+ "108": "SUCCESS",
17
+ "109": "NON_PARTICIPATING",
18
+ "11": "SUCCESS",
19
  "110": "NON_PARTICIPATING",
20
  "111": "NON_PARTICIPATING",
21
  "112": "NON_PARTICIPATING",
22
+ "113": "NON_PARTICIPATING",
23
  "114": "NON_PARTICIPATING",
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
 
30
  "120": "NON_PARTICIPATING",
31
  "121": "NON_PARTICIPATING",
32
  "122": "NON_PARTICIPATING",
33
+ "123": "SUCCESS",
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": "SUCCESS",
41
+ "130": "NON_PARTICIPATING",
42
  "131": "NON_PARTICIPATING",
43
  "132": "NON_PARTICIPATING",
44
  "133": "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",
 
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",
 
76
  "162": "NON_PARTICIPATING",
77
  "163": "NON_PARTICIPATING",
78
  "164": "NON_PARTICIPATING",
79
+ "165": "NON_PARTICIPATING",
80
  "166": "NON_PARTICIPATING",
81
  "167": "NON_PARTICIPATING",
82
+ "168": "SUCCESS",
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",
93
  "178": "NON_PARTICIPATING",
94
  "179": "NON_PARTICIPATING",
95
  "18": "SUCCESS",
96
+ "180": "SUCCESS",
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": "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",
113
  "196": "NON_PARTICIPATING",
114
  "197": "NON_PARTICIPATING",
115
  "198": "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",
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": "SUCCESS",
139
  "219": "NON_PARTICIPATING",
140
  "22": "SUCCESS",
141
+ "220": "SUCCESS",
142
+ "221": "SUCCESS",
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": "SUCCESS",
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": "SUCCESS",
161
  "239": "NON_PARTICIPATING",
162
  "24": "SUCCESS",
163
  "240": "NON_PARTICIPATING",
 
173
  "25": "SUCCESS",
174
  "250": "NON_PARTICIPATING",
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",
182
  "28": "SUCCESS",
 
186
  "31": "SUCCESS",
187
  "32": "SUCCESS",
188
  "33": "NON_PARTICIPATING",
189
+ "34": "SUCCESS",
190
  "35": "SUCCESS",
191
+ "36": "SUCCESS",
192
  "37": "SUCCESS",
193
  "38": "SUCCESS",
194
  "39": "SUCCESS",
 
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
202
  "46": "NON_PARTICIPATING",
203
+ "47": "SUCCESS",
204
  "48": "NON_PARTICIPATING",
205
  "49": "SUCCESS",
206
  "5": "NON_PARTICIPATING",
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",
 
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",
 
234
  "75": "SUCCESS",
235
  "76": "SUCCESS",
236
  "77": "SUCCESS",
237
+ "78": "SUCCESS",
238
  "79": "NON_PARTICIPATING",
239
  "8": "SUCCESS",
240
  "80": "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",
 
267
  "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
+ "block_list": [
271
+ 5571190,
272
+ 5571195,
273
+ 5571199,
274
+ 5571203,
275
+ 5571207
276
+ ],
277
  "block_size": 1024,
278
  "bos_token_id": 50256,
279
  "embd_pdrop": 0.1,
 
281
  "initializer_range": 0.02,
282
  "inner_step": 0,
283
  "inner_steps": 0,
284
+ "last_allreduce_block": 5570305,
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 sha256:9fa32ae54655675d10cb46f1d8acd8bd46db2a5ba4721fb67f318ced3776079e
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd489ac6622a6829bec909c4262f8afe391c746608aa6ab0e070dd4c3c0c5087
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e18b2b6fb366410e9de4a989d7b215596c0c6542a1ca528a189af865a9eb5f25
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07d3be1eea69687235f406b64077a3173335c2612286440a4f01f7a725f20223
3
  size 4040701744