zeras141a commited on
Commit
1dbcdf6
·
verified ·
1 Parent(s): e7ad62b

Run 8. Outer Step 126. Inner Step 4.

Browse files
Files changed (4) hide show
  1. config.json +90 -90
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -12,35 +12,35 @@
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
- "108": "NON_PARTICIPATING",
16
- "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
- "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "NON_PARTICIPATING",
22
  "114": "SUCCESS",
23
- "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
- "117": "NOT_ALIVE",
26
- "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
- "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
- "125": "SUCCESS",
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
37
- "128": "NOT_ALIVE",
38
- "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
- "130": "SUCCESS",
41
  "131": "NON_PARTICIPATING",
42
- "132": "NON_PARTICIPATING",
43
- "133": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
@@ -49,73 +49,73 @@
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
- "141": "SUCCESS",
53
- "142": "SUCCESS",
54
- "143": "SUCCESS",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
- "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
- "151": "NOT_ALIVE",
64
- "152": "SUCCESS",
65
  "153": "NON_PARTICIPATING",
66
  "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
- "158": "SUCCESS",
71
  "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
- "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
- "165": "SUCCESS",
79
- "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
- "168": "SUCCESS",
82
- "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
- "171": "SUCCESS",
86
- "172": "NOT_ALIVE",
87
- "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
89
- "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
- "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NON_PARTICIPATING",
97
- "182": "SUCCESS",
98
  "183": "SUCCESS",
99
- "184": "SUCCESS",
100
- "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
- "187": "NOT_ALIVE",
103
- "188": "NOT_ALIVE",
104
- "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NON_PARTICIPATING",
108
  "192": "SUCCESS",
109
  "193": "NON_PARTICIPATING",
110
- "194": "SUCCESS",
111
  "195": "NON_PARTICIPATING",
112
- "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
- "198": "SUCCESS",
115
- "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
- "200": "NON_PARTICIPATING",
119
  "201": "SUCCESS",
120
  "202": "NON_PARTICIPATING",
121
  "203": "SUCCESS",
@@ -129,83 +129,83 @@
129
  "210": "FAIL",
130
  "211": "SUCCESS",
131
  "212": "NON_PARTICIPATING",
132
- "213": "SUCCESS",
133
- "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "FAIL",
136
- "217": "SUCCESS",
137
  "218": "SUCCESS",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "SUCCESS",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
143
- "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
- "225": "SUCCESS",
146
  "226": "NON_PARTICIPATING",
147
- "227": "NON_PARTICIPATING",
148
- "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
  "231": "SUCCESS",
153
  "232": "NOT_ALIVE",
154
- "233": "NON_PARTICIPATING",
155
- "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
  "237": "SUCCESS",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
- "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
- "247": "SUCCESS",
170
- "248": "SUCCESS",
171
- "249": "SUCCESS",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
- "251": "SUCCESS",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
- "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
- "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
  "30": "NON_PARTICIPATING",
185
- "31": "NON_PARTICIPATING",
186
- "32": "NOT_ALIVE",
187
- "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
- "35": "NOT_ALIVE",
190
- "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
- "41": "NOT_ALIVE",
197
- "42": "NON_PARTICIPATING",
198
- "43": "SUCCESS",
199
  "44": "NOT_ALIVE",
200
- "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
- "47": "SUCCESS",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
- "50": "SUCCESS",
207
  "51": "NON_PARTICIPATING",
208
- "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
@@ -213,25 +213,25 @@
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
- "6": "SUCCESS",
217
- "60": "NOT_ALIVE",
218
- "61": "SUCCESS",
219
  "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
- "68": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
- "73": "NOT_ALIVE",
232
  "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
234
- "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
@@ -242,21 +242,21 @@
242
  "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
- "86": "SUCCESS",
246
- "87": "NON_PARTICIPATING",
247
- "88": "SUCCESS",
248
- "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
- "90": "NON_PARTICIPATING",
251
  "91": "SUCCESS",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NON_PARTICIPATING",
254
  "94": "SUCCESS",
255
  "95": "NON_PARTICIPATING",
256
- "96": "SUCCESS",
257
- "97": "NOT_ALIVE",
258
- "98": "NOT_ALIVE",
259
- "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6443044,
268
- 6443058
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": 11,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6442570,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
+ "108": "NOT_ALIVE",
16
+ "109": "FAIL",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "FAIL",
20
  "112": "SUCCESS",
21
  "113": "NON_PARTICIPATING",
22
  "114": "SUCCESS",
23
+ "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "NON_PARTICIPATING",
26
+ "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
+ "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
+ "125": "FAIL",
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
37
+ "128": "NON_PARTICIPATING",
38
+ "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
+ "130": "FAIL",
41
  "131": "NON_PARTICIPATING",
42
+ "132": "NOT_ALIVE",
43
+ "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
 
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
+ "141": "FAIL",
53
+ "142": "FAIL",
54
+ "143": "FAIL",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
+ "146": "FAIL",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
+ "151": "NON_PARTICIPATING",
64
+ "152": "FAIL",
65
  "153": "NON_PARTICIPATING",
66
  "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
+ "158": "FAIL",
71
  "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
+ "162": "NOT_ALIVE",
76
  "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
+ "165": "FAIL",
79
+ "166": "SUCCESS",
80
  "167": "NON_PARTICIPATING",
81
+ "168": "FAIL",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
+ "171": "FAIL",
86
+ "172": "NON_PARTICIPATING",
87
+ "173": "NOT_ALIVE",
88
  "174": "NON_PARTICIPATING",
89
+ "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
+ "178": "NOT_ALIVE",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NON_PARTICIPATING",
97
+ "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
+ "184": "FAIL",
100
+ "185": "FAIL",
101
  "186": "NOT_ALIVE",
102
+ "187": "NON_PARTICIPATING",
103
+ "188": "NON_PARTICIPATING",
104
+ "189": "FAIL",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NON_PARTICIPATING",
108
  "192": "SUCCESS",
109
  "193": "NON_PARTICIPATING",
110
+ "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
+ "196": "FAIL",
113
  "197": "NOT_ALIVE",
114
+ "198": "FAIL",
115
+ "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "SUCCESS",
119
  "201": "SUCCESS",
120
  "202": "NON_PARTICIPATING",
121
  "203": "SUCCESS",
 
129
  "210": "FAIL",
130
  "211": "SUCCESS",
131
  "212": "NON_PARTICIPATING",
132
+ "213": "FAIL",
133
+ "214": "SUCCESS",
134
  "215": "NON_PARTICIPATING",
135
  "216": "FAIL",
136
+ "217": "FAIL",
137
  "218": "SUCCESS",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "SUCCESS",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
143
+ "223": "FAIL",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
+ "227": "NOT_ALIVE",
148
+ "228": "FAIL",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
  "231": "SUCCESS",
153
  "232": "NOT_ALIVE",
154
+ "233": "NOT_ALIVE",
155
+ "234": "FAIL",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
  "237": "SUCCESS",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
+ "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "FAIL",
170
+ "248": "NON_PARTICIPATING",
171
+ "249": "FAIL",
172
  "25": "SUCCESS",
173
+ "250": "NOT_ALIVE",
174
+ "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
+ "26": "NOT_ALIVE",
180
  "27": "NON_PARTICIPATING",
181
+ "28": "FAIL",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
  "30": "NON_PARTICIPATING",
185
+ "31": "NOT_ALIVE",
186
+ "32": "NON_PARTICIPATING",
187
+ "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
+ "35": "NON_PARTICIPATING",
190
+ "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
+ "41": "NON_PARTICIPATING",
197
+ "42": "NOT_ALIVE",
198
+ "43": "FAIL",
199
  "44": "NOT_ALIVE",
200
+ "45": "NOT_ALIVE",
201
  "46": "NON_PARTICIPATING",
202
+ "47": "FAIL",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
+ "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
+ "52": "FAIL",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
 
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
+ "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
+ "61": "FAIL",
219
  "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "FAIL",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
+ "73": "NON_PARTICIPATING",
232
  "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
234
+ "76": "FAIL",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
 
242
  "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "NON_PARTICIPATING",
246
+ "87": "FAIL",
247
+ "88": "FAIL",
248
+ "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
+ "90": "NOT_ALIVE",
251
  "91": "SUCCESS",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NON_PARTICIPATING",
254
  "94": "SUCCESS",
255
  "95": "NON_PARTICIPATING",
256
+ "96": "NON_PARTICIPATING",
257
+ "97": "NON_PARTICIPATING",
258
+ "98": "SUCCESS",
259
+ "99": "FAIL"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6443304,
268
+ 6443321
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": 6443186,
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 sha256:1997166d07e3126cdc1541a50b7852822ea610a15d7ce9f842710485abf4cfe4
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:980fdaa1cef5f325e49102daaeb5765e3d8f0a65ee6b4c3960397e35aeb6acaf
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:547cc3154ef601956e0ecbcc972b93e80f4268e3dbbb229283e71a97f61b7873
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:243c49445a93d275f40388f697c6da2e1e94115a7c126860fd628721743ae57f
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf56bcc4c33d7e8f8678692e63a786cc550034969c7a5c1a9158bca8a2badcc5
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef0fb1e3dec279e7a655ddad1a84cfee8e1a87706d454f5851b0d6a0db20e18d
3
  size 4400216536