ncaagcc commited on
Commit
8cc2d1e
·
verified ·
1 Parent(s): d827a7a

Run 8. Outer Step 86. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +120 -120
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -1,18 +1,18 @@
1
  {
2
- "_name_or_path": "ncaagcc/trt1",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
  "101": "NON_PARTICIPATING",
9
- "102": "SUCCESS",
10
  "103": "FAIL",
11
- "104": "NON_PARTICIPATING",
12
- "105": "NON_PARTICIPATING",
13
  "106": "SUCCESS",
14
- "107": "NON_PARTICIPATING",
15
- "108": "SUCCESS",
16
  "109": "FAIL",
17
  "11": "NOT_ALIVE",
18
  "110": "FAIL",
@@ -20,9 +20,9 @@
20
  "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
- "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
- "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
@@ -30,18 +30,18 @@
30
  "121": "NON_PARTICIPATING",
31
  "122": "SUCCESS",
32
  "123": "SUCCESS",
33
- "124": "SUCCESS",
34
- "125": "NOT_ALIVE",
35
- "126": "FAIL",
36
- "127": "SUCCESS",
37
  "128": "NON_PARTICIPATING",
38
  "129": "FAIL",
39
- "13": "SUCCESS",
40
- "130": "SUCCESS",
41
  "131": "NON_PARTICIPATING",
42
- "132": "FAIL",
43
  "133": "SUCCESS",
44
- "134": "SUCCESS",
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "FAIL",
@@ -49,214 +49,214 @@
49
  "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
- "141": "SUCCESS",
53
  "142": "NOT_ALIVE",
54
  "143": "FAIL",
55
  "144": "NOT_ALIVE",
56
  "145": "FAIL",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
- "148": "NON_PARTICIPATING",
60
- "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
- "150": "SUCCESS",
63
- "151": "NON_PARTICIPATING",
64
- "152": "NON_PARTICIPATING",
65
- "153": "NOT_ALIVE",
66
  "154": "FAIL",
67
- "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
- "157": "SUCCESS",
70
  "158": "NON_PARTICIPATING",
71
- "159": "SUCCESS",
72
- "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
74
  "161": "SUCCESS",
75
- "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
- "164": "SUCCESS",
78
- "165": "NON_PARTICIPATING",
79
- "166": "SUCCESS",
80
- "167": "SUCCESS",
81
- "168": "NON_PARTICIPATING",
82
- "169": "SUCCESS",
83
- "17": "NOT_ALIVE",
84
  "170": "FAIL",
85
- "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
- "173": "NON_PARTICIPATING",
88
- "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
93
  "179": "SUCCESS",
94
- "18": "SUCCESS",
95
- "180": "NON_PARTICIPATING",
96
  "181": "FAIL",
97
  "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
- "184": "FAIL",
100
  "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
- "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
- "189": "SUCCESS",
105
  "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
- "191": "FAIL",
108
- "192": "SUCCESS",
109
- "193": "NON_PARTICIPATING",
110
- "194": "NON_PARTICIPATING",
111
- "195": "SUCCESS",
112
- "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
- "198": "FAIL",
115
- "199": "SUCCESS",
116
- "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
  "204": "FAIL",
123
- "205": "NOT_ALIVE",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "SUCCESS",
127
  "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "SUCCESS",
130
- "211": "SUCCESS",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
- "214": "NON_PARTICIPATING",
134
- "215": "NON_PARTICIPATING",
135
- "216": "FAIL",
136
- "217": "FAIL",
137
- "218": "SUCCESS",
138
  "219": "SUCCESS",
139
  "22": "SUCCESS",
140
- "220": "SUCCESS",
141
  "221": "NON_PARTICIPATING",
142
  "222": "SUCCESS",
143
- "223": "NON_PARTICIPATING",
144
- "224": "NON_PARTICIPATING",
145
- "225": "NON_PARTICIPATING",
146
- "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
- "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
- "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
- "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
- "24": "SUCCESS",
162
  "240": "FAIL",
163
- "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
  "243": "SUCCESS",
166
  "244": "SUCCESS",
167
  "245": "SUCCESS",
168
  "246": "SUCCESS",
169
  "247": "SUCCESS",
170
- "248": "SUCCESS",
171
- "249": "SUCCESS",
172
  "25": "SUCCESS",
173
- "250": "FAIL",
174
- "251": "NON_PARTICIPATING",
175
  "252": "SUCCESS",
176
  "253": "SUCCESS",
177
- "254": "NON_PARTICIPATING",
178
- "255": "NOT_ALIVE",
179
- "26": "FAIL",
180
- "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
- "29": "SUCCESS",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
- "31": "NOT_ALIVE",
186
- "32": "SUCCESS",
187
  "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
- "35": "SUCCESS",
190
  "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
- "38": "SUCCESS",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
  "41": "FAIL",
197
  "42": "SUCCESS",
198
- "43": "NON_PARTICIPATING",
199
  "44": "FAIL",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
  "47": "FAIL",
203
  "48": "SUCCESS",
204
- "49": "SUCCESS",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
- "51": "SUCCESS",
208
  "52": "SUCCESS",
209
- "53": "NOT_ALIVE",
210
- "54": "NON_PARTICIPATING",
211
- "55": "SUCCESS",
212
- "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
- "58": "FAIL",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "SUCCESS",
218
- "61": "NON_PARTICIPATING",
219
  "62": "SUCCESS",
220
- "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
222
- "65": "FAIL",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
- "68": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
  "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
- "72": "FAIL",
231
  "73": "NON_PARTICIPATING",
232
- "74": "NON_PARTICIPATING",
233
  "75": "NOT_ALIVE",
234
  "76": "SUCCESS",
235
  "77": "SUCCESS",
236
- "78": "SUCCESS",
237
- "79": "SUCCESS",
238
- "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
- "84": "SUCCESS",
244
- "85": "SUCCESS",
245
  "86": "NON_PARTICIPATING",
246
- "87": "FAIL",
247
- "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
- "9": "NOT_ALIVE",
250
- "90": "SUCCESS",
251
- "91": "NON_PARTICIPATING",
252
- "92": "SUCCESS",
253
- "93": "NON_PARTICIPATING",
254
- "94": "NON_PARTICIPATING",
255
  "95": "FAIL",
256
  "96": "SUCCESS",
257
- "97": "SUCCESS",
258
- "98": "NOT_ALIVE",
259
- "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6405400,
268
- 6405409
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
- "inner_step": 98,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6401912,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
  "101": "NON_PARTICIPATING",
9
+ "102": "NON_PARTICIPATING",
10
  "103": "FAIL",
11
+ "104": "FAIL",
12
+ "105": "SUCCESS",
13
  "106": "SUCCESS",
14
+ "107": "NOT_ALIVE",
15
+ "108": "NON_PARTICIPATING",
16
  "109": "FAIL",
17
  "11": "NOT_ALIVE",
18
  "110": "FAIL",
 
20
  "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
+ "115": "NOT_ALIVE",
24
  "116": "NOT_ALIVE",
25
+ "117": "NOT_ALIVE",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
 
30
  "121": "NON_PARTICIPATING",
31
  "122": "SUCCESS",
32
  "123": "SUCCESS",
33
+ "124": "NOT_ALIVE",
34
+ "125": "FAIL",
35
+ "126": "NOT_ALIVE",
36
+ "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "FAIL",
39
+ "13": "FAIL",
40
+ "130": "FAIL",
41
  "131": "NON_PARTICIPATING",
42
+ "132": "SUCCESS",
43
  "133": "SUCCESS",
44
+ "134": "FAIL",
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "FAIL",
 
49
  "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
+ "141": "NON_PARTICIPATING",
53
  "142": "NOT_ALIVE",
54
  "143": "FAIL",
55
  "144": "NOT_ALIVE",
56
  "145": "FAIL",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "SUCCESS",
60
+ "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
+ "150": "NON_PARTICIPATING",
63
+ "151": "NOT_ALIVE",
64
+ "152": "NOT_ALIVE",
65
+ "153": "SUCCESS",
66
  "154": "FAIL",
67
+ "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
+ "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "FAIL",
72
+ "16": "SUCCESS",
73
  "160": "SUCCESS",
74
  "161": "SUCCESS",
75
+ "162": "FAIL",
76
  "163": "NON_PARTICIPATING",
77
+ "164": "NON_PARTICIPATING",
78
+ "165": "SUCCESS",
79
+ "166": "NOT_ALIVE",
80
+ "167": "NOT_ALIVE",
81
+ "168": "SUCCESS",
82
+ "169": "FAIL",
83
+ "17": "FAIL",
84
  "170": "FAIL",
85
+ "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
+ "173": "SUCCESS",
88
+ "174": "FAIL",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
93
  "179": "SUCCESS",
94
+ "18": "FAIL",
95
+ "180": "SUCCESS",
96
  "181": "FAIL",
97
  "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
+ "184": "SUCCESS",
100
  "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
+ "187": "NON_PARTICIPATING",
103
  "188": "SUCCESS",
104
+ "189": "NOT_ALIVE",
105
  "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "NON_PARTICIPATING",
108
+ "192": "NON_PARTICIPATING",
109
+ "193": "SUCCESS",
110
+ "194": "SUCCESS",
111
+ "195": "NON_PARTICIPATING",
112
+ "196": "NON_PARTICIPATING",
113
  "197": "NON_PARTICIPATING",
114
+ "198": "NON_PARTICIPATING",
115
+ "199": "NON_PARTICIPATING",
116
+ "2": "SUCCESS",
117
  "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "SUCCESS",
122
  "204": "FAIL",
123
+ "205": "NON_PARTICIPATING",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "SUCCESS",
127
  "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "SUCCESS",
130
+ "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "NOT_ALIVE",
134
+ "215": "SUCCESS",
135
+ "216": "SUCCESS",
136
+ "217": "SUCCESS",
137
+ "218": "NON_PARTICIPATING",
138
  "219": "SUCCESS",
139
  "22": "SUCCESS",
140
+ "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
  "222": "SUCCESS",
143
+ "223": "NOT_ALIVE",
144
+ "224": "NOT_ALIVE",
145
+ "225": "SUCCESS",
146
+ "226": "SUCCESS",
147
  "227": "NON_PARTICIPATING",
148
+ "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
+ "234": "FAIL",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
+ "24": "NOT_ALIVE",
162
  "240": "FAIL",
163
+ "241": "FAIL",
164
  "242": "SUCCESS",
165
  "243": "SUCCESS",
166
  "244": "SUCCESS",
167
  "245": "SUCCESS",
168
  "246": "SUCCESS",
169
  "247": "SUCCESS",
170
+ "248": "NOT_ALIVE",
171
+ "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
+ "251": "SUCCESS",
175
  "252": "SUCCESS",
176
  "253": "SUCCESS",
177
+ "254": "SUCCESS",
178
+ "255": "SUCCESS",
179
+ "26": "NOT_ALIVE",
180
+ "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
+ "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
+ "31": "SUCCESS",
186
+ "32": "FAIL",
187
  "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
+ "35": "FAIL",
190
  "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
+ "38": "FAIL",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
+ "40": "FAIL",
196
  "41": "FAIL",
197
  "42": "SUCCESS",
198
+ "43": "FAIL",
199
  "44": "FAIL",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
  "47": "FAIL",
203
  "48": "SUCCESS",
204
+ "49": "FAIL",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
+ "51": "NOT_ALIVE",
208
  "52": "SUCCESS",
209
+ "53": "SUCCESS",
210
+ "54": "SUCCESS",
211
+ "55": "NOT_ALIVE",
212
+ "56": "SUCCESS",
213
  "57": "SUCCESS",
214
+ "58": "SUCCESS",
215
+ "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
+ "61": "SUCCESS",
219
  "62": "SUCCESS",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
+ "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
  "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
+ "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "SUCCESS",
233
  "75": "NOT_ALIVE",
234
  "76": "SUCCESS",
235
  "77": "SUCCESS",
236
+ "78": "FAIL",
237
+ "79": "NON_PARTICIPATING",
238
+ "8": "SUCCESS",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
+ "84": "FAIL",
244
+ "85": "FAIL",
245
  "86": "NON_PARTICIPATING",
246
+ "87": "SUCCESS",
247
+ "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
+ "9": "SUCCESS",
250
+ "90": "NON_PARTICIPATING",
251
+ "91": "NOT_ALIVE",
252
+ "92": "NON_PARTICIPATING",
253
+ "93": "SUCCESS",
254
+ "94": "SUCCESS",
255
  "95": "FAIL",
256
  "96": "SUCCESS",
257
+ "97": "NOT_ALIVE",
258
+ "98": "NON_PARTICIPATING",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6405460,
268
+ 6405473
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
+ "inner_step": 4,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6405390,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36699a49ce01f2fd3b77e45247093e8af0376a6276e02d47a1ba85531ffc91ea
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:964c66095b934eb2da63651ba8203379aa15893c7c03fc50cff73e8a921ddfd7
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a59156407f95562b551a89c5ba2d1b6363f20053307da2e59068127e29737206
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cd72aa3a265c3112971f2c02e117fb2fd5f1f2d755923b44119887751e5a80c
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4048e1bb62f1f49d8558b148e98f74ee7fcbfb5ba4b9b542ed958c40fe280f2c
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f82a5ef3cf093eb34ef158dd4c7b4f34d32a348e172807f2c219710b3cdb6371
3
  size 4400216536