jockibaba commited on
Commit
4329224
·
verified ·
1 Parent(s): 8a57659

Run 4. Outer Step 36. Inner Step 0.

Browse files
Files changed (3) hide show
  1. config.json +52 -52
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -7,19 +7,19 @@
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": "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",
@@ -31,10 +31,10 @@
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",
@@ -45,7 +45,7 @@
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",
@@ -56,14 +56,14 @@
56
  "144": "NON_PARTICIPATING",
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",
@@ -73,23 +73,23 @@
73
  "16": "SUCCESS",
74
  "160": "NON_PARTICIPATING",
75
  "161": "NON_PARTICIPATING",
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",
@@ -98,18 +98,18 @@
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",
@@ -120,15 +120,15 @@
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",
@@ -141,16 +141,16 @@
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",
@@ -162,40 +162,40 @@
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": "NON_PARTICIPATING",
171
  "248": "NON_PARTICIPATING",
172
- "249": "SUCCESS",
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",
183
  "29": "SUCCESS",
184
  "3": "SUCCESS",
185
- "30": "NON_PARTICIPATING",
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",
195
  "4": "SUCCESS",
196
  "40": "SUCCESS",
197
  "41": "SUCCESS",
198
- "42": "NON_PARTICIPATING",
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
@@ -203,15 +203,15 @@
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",
@@ -243,7 +243,7 @@
243
  "83": "NON_PARTICIPATING",
244
  "84": "SUCCESS",
245
  "85": "SUCCESS",
246
- "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
  "88": "SUCCESS",
249
  "89": "SUCCESS",
@@ -268,20 +268,20 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5548800,
272
- 5548804,
273
- 5548808,
274
- 5548813,
275
- 5548817
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": 22,
283
  "inner_steps": 0,
284
- "last_allreduce_block": 5543976,
285
  "layer_norm_epsilon": 1e-05,
286
  "model_type": "gpt_optimized",
287
  "n_embd": 1280,
 
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",
14
  "106": "NON_PARTICIPATING",
15
+ "107": "NON_PARTICIPATING",
16
  "108": "NON_PARTICIPATING",
17
+ "109": "NON_PARTICIPATING",
18
  "11": "NON_PARTICIPATING",
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",
 
31
  "121": "NON_PARTICIPATING",
32
  "122": "NON_PARTICIPATING",
33
  "123": "NON_PARTICIPATING",
34
+ "124": "SUCCESS",
35
  "125": "NON_PARTICIPATING",
36
  "126": "NON_PARTICIPATING",
37
+ "127": "NON_PARTICIPATING",
38
  "128": "NON_PARTICIPATING",
39
  "129": "NON_PARTICIPATING",
40
  "13": "SUCCESS",
 
45
  "134": "NON_PARTICIPATING",
46
  "135": "NON_PARTICIPATING",
47
  "136": "NON_PARTICIPATING",
48
+ "137": "SUCCESS",
49
  "138": "NON_PARTICIPATING",
50
  "139": "NON_PARTICIPATING",
51
  "14": "SUCCESS",
 
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",
63
  "150": "SUCCESS",
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
66
+ "153": "SUCCESS",
67
  "154": "NON_PARTICIPATING",
68
  "155": "NON_PARTICIPATING",
69
  "156": "NON_PARTICIPATING",
 
73
  "16": "SUCCESS",
74
  "160": "NON_PARTICIPATING",
75
  "161": "NON_PARTICIPATING",
76
+ "162": "SUCCESS",
77
  "163": "NON_PARTICIPATING",
78
  "164": "NON_PARTICIPATING",
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",
 
98
  "182": "NON_PARTICIPATING",
99
  "183": "NON_PARTICIPATING",
100
  "184": "NON_PARTICIPATING",
101
+ "185": "SUCCESS",
102
+ "186": "SUCCESS",
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",
 
120
  "201": "NON_PARTICIPATING",
121
  "202": "NON_PARTICIPATING",
122
  "203": "SUCCESS",
123
+ "204": "SUCCESS",
124
+ "205": "SUCCESS",
125
  "206": "NON_PARTICIPATING",
126
  "207": "NON_PARTICIPATING",
127
+ "208": "SUCCESS",
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",
 
141
  "220": "NON_PARTICIPATING",
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": "SUCCESS",
154
  "232": "NON_PARTICIPATING",
155
  "233": "NON_PARTICIPATING",
156
  "234": "NON_PARTICIPATING",
 
162
  "24": "SUCCESS",
163
  "240": "NON_PARTICIPATING",
164
  "241": "NON_PARTICIPATING",
165
+ "242": "NON_PARTICIPATING",
166
  "243": "NON_PARTICIPATING",
167
+ "244": "SUCCESS",
168
  "245": "NON_PARTICIPATING",
169
  "246": "NON_PARTICIPATING",
170
  "247": "NON_PARTICIPATING",
171
  "248": "NON_PARTICIPATING",
172
+ "249": "NON_PARTICIPATING",
173
  "25": "SUCCESS",
174
  "250": "NON_PARTICIPATING",
175
  "251": "NON_PARTICIPATING",
176
  "252": "SUCCESS",
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": "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": "SUCCESS",
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
 
203
  "47": "NON_PARTICIPATING",
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",
 
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",
 
243
  "83": "NON_PARTICIPATING",
244
  "84": "SUCCESS",
245
  "85": "SUCCESS",
246
+ "86": "SUCCESS",
247
  "87": "SUCCESS",
248
  "88": "SUCCESS",
249
  "89": "SUCCESS",
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5550503,
272
+ 5550508,
273
+ 5550512,
274
+ 5550516,
275
+ 5550520
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": 5549491,
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:da119712bddf17f20c8916bfb1fcd89d73bf7003f0ae73602ccaf38df6e1347a
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74d67c0e51fef9b5064a7a558e1c407fa32d2baabcfcd40e121fa25d25de9709
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9e6ed780d65b5825da2385219b6824b4cdffbf76943948287c9295345001fe9
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07f83f77bb3661fe40125fec18fb9b98a7b4a7680972c58900c1f0fdfe882ae6
3
  size 4040701744