philip324mark commited on
Commit
f6772e6
·
verified ·
1 Parent(s): bdf1590

Run 4. Outer Step 48. Inner Step 0.

Browse files
Files changed (3) hide show
  1. config.json +51 -51
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "philip324mark/mark1",
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
@@ -12,11 +12,11 @@
12
  "104": "NON_PARTICIPATING",
13
  "105": "NON_PARTICIPATING",
14
  "106": "NON_PARTICIPATING",
15
- "107": "SUCCESS",
16
- "108": "SUCCESS",
17
  "109": "NON_PARTICIPATING",
18
- "11": "NON_PARTICIPATING",
19
- "110": "SUCCESS",
20
  "111": "NON_PARTICIPATING",
21
  "112": "NON_PARTICIPATING",
22
  "113": "NON_PARTICIPATING",
@@ -30,27 +30,27 @@
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": "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": "SUCCESS",
49
- "138": "SUCCESS",
50
  "139": "NON_PARTICIPATING",
51
- "14": "SUCCESS",
52
  "140": "NON_PARTICIPATING",
53
- "141": "SUCCESS",
54
  "142": "NON_PARTICIPATING",
55
  "143": "NON_PARTICIPATING",
56
  "144": "NON_PARTICIPATING",
@@ -58,7 +58,7 @@
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",
@@ -66,8 +66,8 @@
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",
73
  "16": "SUCCESS",
@@ -75,37 +75,37 @@
75
  "161": "NON_PARTICIPATING",
76
  "162": "NON_PARTICIPATING",
77
  "163": "NON_PARTICIPATING",
78
- "164": "SUCCESS",
79
  "165": "NON_PARTICIPATING",
80
  "166": "NON_PARTICIPATING",
81
- "167": "NON_PARTICIPATING",
82
  "168": "NON_PARTICIPATING",
83
  "169": "NON_PARTICIPATING",
84
  "17": "SUCCESS",
85
- "170": "NON_PARTICIPATING",
86
- "171": "NON_PARTICIPATING",
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": "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": "NON_PARTICIPATING",
107
  "190": "NON_PARTICIPATING",
108
- "191": "NON_PARTICIPATING",
109
  "192": "NON_PARTICIPATING",
110
  "193": "NON_PARTICIPATING",
111
  "194": "NON_PARTICIPATING",
@@ -116,10 +116,10 @@
116
  "199": "NON_PARTICIPATING",
117
  "2": "SUCCESS",
118
  "20": "SUCCESS",
119
- "200": "SUCCESS",
120
- "201": "SUCCESS",
121
- "202": "SUCCESS",
122
- "203": "NON_PARTICIPATING",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
125
  "206": "NON_PARTICIPATING",
@@ -128,7 +128,7 @@
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",
@@ -143,11 +143,11 @@
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": "SUCCESS",
151
  "23": "SUCCESS",
152
  "230": "NON_PARTICIPATING",
153
  "231": "NON_PARTICIPATING",
@@ -155,8 +155,8 @@
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",
@@ -171,31 +171,31 @@
171
  "248": "NON_PARTICIPATING",
172
  "249": "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",
183
  "29": "SUCCESS",
184
  "3": "SUCCESS",
185
- "30": "SUCCESS",
186
- "31": "NON_PARTICIPATING",
187
  "32": "SUCCESS",
188
  "33": "NON_PARTICIPATING",
189
  "34": "SUCCESS",
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": "SUCCESS",
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
@@ -203,14 +203,14 @@
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": "NON_PARTICIPATING",
214
  "57": "SUCCESS",
215
  "58": "NON_PARTICIPATING",
216
  "59": "SUCCESS",
@@ -243,11 +243,11 @@
243
  "83": "NON_PARTICIPATING",
244
  "84": "SUCCESS",
245
  "85": "NON_PARTICIPATING",
246
- "86": "SUCCESS",
247
  "87": "SUCCESS",
248
  "88": "SUCCESS",
249
  "89": "SUCCESS",
250
- "9": "NON_PARTICIPATING",
251
  "90": "SUCCESS",
252
  "91": "SUCCESS",
253
  "92": "SUCCESS",
@@ -268,20 +268,20 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5568845,
272
- 5568850,
273
- 5568854,
274
- 5568858,
275
- 5568862
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": 45,
283
  "inner_steps": 0,
284
- "last_allreduce_block": 5553805,
285
  "layer_norm_epsilon": 1e-05,
286
  "model_type": "gpt_optimized",
287
  "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": "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",
 
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": "NON_PARTICIPATING",
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",
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": "NON_PARTICIPATING",
52
  "140": "NON_PARTICIPATING",
53
+ "141": "NON_PARTICIPATING",
54
  "142": "NON_PARTICIPATING",
55
  "143": "NON_PARTICIPATING",
56
  "144": "NON_PARTICIPATING",
 
58
  "146": "NON_PARTICIPATING",
59
  "147": "NON_PARTICIPATING",
60
  "148": "NON_PARTICIPATING",
61
+ "149": "SUCCESS",
62
  "15": "SUCCESS",
63
  "150": "NON_PARTICIPATING",
64
  "151": "NON_PARTICIPATING",
 
66
  "153": "NON_PARTICIPATING",
67
  "154": "NON_PARTICIPATING",
68
  "155": "NON_PARTICIPATING",
69
+ "156": "SUCCESS",
70
+ "157": "SUCCESS",
71
  "158": "NON_PARTICIPATING",
72
  "159": "NON_PARTICIPATING",
73
  "16": "SUCCESS",
 
75
  "161": "NON_PARTICIPATING",
76
  "162": "NON_PARTICIPATING",
77
  "163": "NON_PARTICIPATING",
78
+ "164": "NON_PARTICIPATING",
79
  "165": "NON_PARTICIPATING",
80
  "166": "NON_PARTICIPATING",
81
+ "167": "SUCCESS",
82
  "168": "NON_PARTICIPATING",
83
  "169": "NON_PARTICIPATING",
84
  "17": "SUCCESS",
85
+ "170": "SUCCESS",
86
+ "171": "SUCCESS",
87
  "172": "NON_PARTICIPATING",
88
  "173": "NON_PARTICIPATING",
89
  "174": "NON_PARTICIPATING",
90
+ "175": "SUCCESS",
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": "SUCCESS",
101
+ "185": "SUCCESS",
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": "SUCCESS",
109
  "192": "NON_PARTICIPATING",
110
  "193": "NON_PARTICIPATING",
111
  "194": "NON_PARTICIPATING",
 
116
  "199": "NON_PARTICIPATING",
117
  "2": "SUCCESS",
118
  "20": "SUCCESS",
119
+ "200": "NON_PARTICIPATING",
120
+ "201": "NON_PARTICIPATING",
121
+ "202": "NON_PARTICIPATING",
122
+ "203": "SUCCESS",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
125
  "206": "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",
 
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": "NON_PARTICIPATING",
151
  "23": "SUCCESS",
152
  "230": "NON_PARTICIPATING",
153
  "231": "NON_PARTICIPATING",
 
155
  "233": "NON_PARTICIPATING",
156
  "234": "NON_PARTICIPATING",
157
  "235": "NON_PARTICIPATING",
158
+ "236": "SUCCESS",
159
+ "237": "SUCCESS",
160
  "238": "NON_PARTICIPATING",
161
  "239": "NON_PARTICIPATING",
162
  "24": "SUCCESS",
 
171
  "248": "NON_PARTICIPATING",
172
  "249": "NON_PARTICIPATING",
173
  "25": "SUCCESS",
174
+ "250": "SUCCESS",
175
  "251": "NON_PARTICIPATING",
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": "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",
195
  "4": "SUCCESS",
196
  "40": "SUCCESS",
197
  "41": "SUCCESS",
198
+ "42": "NON_PARTICIPATING",
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
 
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",
 
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",
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5568980,
272
+ 5568984,
273
+ 5568988,
274
+ 5568992,
275
+ 5568997
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": 5568918,
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 sha256:7cdb1c97bdd6904b3c40f9d53f57fd4332badb34303c62f348a5fb928d83db7b
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54ed24188e716091efa8d2c7644edef3bd22232b4b98a010d1a36f466e70221
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6657837f762689aeff4d69a9dbc6dd0514b4108ba2bc32ee4eb1a473fe230fc0
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0bb6a8e948a955f499b1f3826d908182f924141a7c75b181aa0111c5f383772
3
  size 4040701744