aalv2 commited on
Commit
fb6c98e
·
verified ·
1 Parent(s): 4b68354

Run 6. Outer Step 19. Inner Step 36.

Browse files
config.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distributed/llama-1b",
3
+ "all_reduce_scores": {
4
+ "0": "NOT_ALIVE",
5
+ "1": "SUCCESS",
6
+ "10": "NOT_ALIVE",
7
+ "100": "NOT_ALIVE",
8
+ "101": "NOT_ALIVE",
9
+ "102": "NOT_ALIVE",
10
+ "103": "NOT_ALIVE",
11
+ "104": "NOT_ALIVE",
12
+ "105": "NON_PARTICIPATING",
13
+ "106": "NOT_ALIVE",
14
+ "107": "NOT_ALIVE",
15
+ "108": "NON_PARTICIPATING",
16
+ "109": "NOT_ALIVE",
17
+ "11": "NOT_ALIVE",
18
+ "110": "NON_PARTICIPATING",
19
+ "111": "NON_PARTICIPATING",
20
+ "112": "NOT_ALIVE",
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": "NOT_ALIVE",
28
+ "12": "NOT_ALIVE",
29
+ "120": "NON_PARTICIPATING",
30
+ "121": "NOT_ALIVE",
31
+ "122": "NON_PARTICIPATING",
32
+ "123": "NOT_ALIVE",
33
+ "124": "NON_PARTICIPATING",
34
+ "125": "NOT_ALIVE",
35
+ "126": "NOT_ALIVE",
36
+ "127": "NOT_ALIVE",
37
+ "128": "NOT_ALIVE",
38
+ "129": "NOT_ALIVE",
39
+ "13": "NOT_ALIVE",
40
+ "130": "NOT_ALIVE",
41
+ "131": "NOT_ALIVE",
42
+ "132": "NOT_ALIVE",
43
+ "133": "SUCCESS",
44
+ "134": "NOT_ALIVE",
45
+ "135": "NON_PARTICIPATING",
46
+ "136": "NON_PARTICIPATING",
47
+ "137": "NON_PARTICIPATING",
48
+ "138": "NON_PARTICIPATING",
49
+ "139": "NON_PARTICIPATING",
50
+ "14": "NOT_ALIVE",
51
+ "140": "SUCCESS",
52
+ "141": "NON_PARTICIPATING",
53
+ "142": "NON_PARTICIPATING",
54
+ "143": "NON_PARTICIPATING",
55
+ "144": "SUCCESS",
56
+ "145": "NOT_ALIVE",
57
+ "146": "NON_PARTICIPATING",
58
+ "147": "SUCCESS",
59
+ "148": "SUCCESS",
60
+ "149": "NOT_ALIVE",
61
+ "15": "NOT_ALIVE",
62
+ "150": "NOT_ALIVE",
63
+ "151": "NON_PARTICIPATING",
64
+ "152": "NOT_ALIVE",
65
+ "153": "NOT_ALIVE",
66
+ "154": "NON_PARTICIPATING",
67
+ "155": "NON_PARTICIPATING",
68
+ "156": "NOT_ALIVE",
69
+ "157": "NOT_ALIVE",
70
+ "158": "NON_PARTICIPATING",
71
+ "159": "NON_PARTICIPATING",
72
+ "16": "NOT_ALIVE",
73
+ "160": "NON_PARTICIPATING",
74
+ "161": "NON_PARTICIPATING",
75
+ "162": "NON_PARTICIPATING",
76
+ "163": "NON_PARTICIPATING",
77
+ "164": "NOT_ALIVE",
78
+ "165": "NON_PARTICIPATING",
79
+ "166": "NOT_ALIVE",
80
+ "167": "NOT_ALIVE",
81
+ "168": "NON_PARTICIPATING",
82
+ "169": "NON_PARTICIPATING",
83
+ "17": "NOT_ALIVE",
84
+ "170": "NON_PARTICIPATING",
85
+ "171": "NON_PARTICIPATING",
86
+ "172": "NON_PARTICIPATING",
87
+ "173": "NON_PARTICIPATING",
88
+ "174": "NON_PARTICIPATING",
89
+ "175": "NON_PARTICIPATING",
90
+ "176": "NOT_ALIVE",
91
+ "177": "NOT_ALIVE",
92
+ "178": "NOT_ALIVE",
93
+ "179": "NOT_ALIVE",
94
+ "18": "NOT_ALIVE",
95
+ "180": "NON_PARTICIPATING",
96
+ "181": "NOT_ALIVE",
97
+ "182": "NON_PARTICIPATING",
98
+ "183": "NOT_ALIVE",
99
+ "184": "NON_PARTICIPATING",
100
+ "185": "NON_PARTICIPATING",
101
+ "186": "NOT_ALIVE",
102
+ "187": "SUCCESS",
103
+ "188": "SUCCESS",
104
+ "189": "SUCCESS",
105
+ "19": "NOT_ALIVE",
106
+ "190": "SUCCESS",
107
+ "191": "NON_PARTICIPATING",
108
+ "192": "NON_PARTICIPATING",
109
+ "193": "NOT_ALIVE",
110
+ "194": "NOT_ALIVE",
111
+ "195": "NOT_ALIVE",
112
+ "196": "NOT_ALIVE",
113
+ "197": "SUCCESS",
114
+ "198": "NON_PARTICIPATING",
115
+ "199": "NOT_ALIVE",
116
+ "2": "NOT_ALIVE",
117
+ "20": "NOT_ALIVE",
118
+ "200": "NON_PARTICIPATING",
119
+ "201": "SUCCESS",
120
+ "202": "NOT_ALIVE",
121
+ "203": "NON_PARTICIPATING",
122
+ "204": "NON_PARTICIPATING",
123
+ "205": "NON_PARTICIPATING",
124
+ "206": "NOT_ALIVE",
125
+ "207": "NOT_ALIVE",
126
+ "208": "NOT_ALIVE",
127
+ "209": "NON_PARTICIPATING",
128
+ "21": "NOT_ALIVE",
129
+ "210": "NOT_ALIVE",
130
+ "211": "NON_PARTICIPATING",
131
+ "212": "NON_PARTICIPATING",
132
+ "213": "NON_PARTICIPATING",
133
+ "214": "NON_PARTICIPATING",
134
+ "215": "NON_PARTICIPATING",
135
+ "216": "SUCCESS",
136
+ "217": "SUCCESS",
137
+ "218": "NOT_ALIVE",
138
+ "219": "SUCCESS",
139
+ "22": "NOT_ALIVE",
140
+ "220": "NOT_ALIVE",
141
+ "221": "NON_PARTICIPATING",
142
+ "222": "NON_PARTICIPATING",
143
+ "223": "NOT_ALIVE",
144
+ "224": "NOT_ALIVE",
145
+ "225": "NOT_ALIVE",
146
+ "226": "NON_PARTICIPATING",
147
+ "227": "NON_PARTICIPATING",
148
+ "228": "SUCCESS",
149
+ "229": "NOT_ALIVE",
150
+ "23": "SUCCESS",
151
+ "230": "SUCCESS",
152
+ "231": "NOT_ALIVE",
153
+ "232": "NOT_ALIVE",
154
+ "233": "NON_PARTICIPATING",
155
+ "234": "NON_PARTICIPATING",
156
+ "235": "NON_PARTICIPATING",
157
+ "236": "NOT_ALIVE",
158
+ "237": "NON_PARTICIPATING",
159
+ "238": "NON_PARTICIPATING",
160
+ "239": "NON_PARTICIPATING",
161
+ "24": "NOT_ALIVE",
162
+ "240": "NOT_ALIVE",
163
+ "241": "NON_PARTICIPATING",
164
+ "242": "SUCCESS",
165
+ "243": "NOT_ALIVE",
166
+ "244": "NON_PARTICIPATING",
167
+ "245": "NON_PARTICIPATING",
168
+ "246": "NON_PARTICIPATING",
169
+ "247": "NOT_ALIVE",
170
+ "248": "NOT_ALIVE",
171
+ "249": "NOT_ALIVE",
172
+ "25": "SUCCESS",
173
+ "250": "NOT_ALIVE",
174
+ "251": "NON_PARTICIPATING",
175
+ "252": "NON_PARTICIPATING",
176
+ "253": "NON_PARTICIPATING",
177
+ "254": "NON_PARTICIPATING",
178
+ "255": "NON_PARTICIPATING",
179
+ "26": "NON_PARTICIPATING",
180
+ "27": "NOT_ALIVE",
181
+ "28": "NON_PARTICIPATING",
182
+ "29": "NOT_ALIVE",
183
+ "3": "SUCCESS",
184
+ "30": "NOT_ALIVE",
185
+ "31": "SUCCESS",
186
+ "32": "SUCCESS",
187
+ "33": "NOT_ALIVE",
188
+ "34": "NON_PARTICIPATING",
189
+ "35": "NON_PARTICIPATING",
190
+ "36": "NON_PARTICIPATING",
191
+ "37": "NOT_ALIVE",
192
+ "38": "NON_PARTICIPATING",
193
+ "39": "SUCCESS",
194
+ "4": "NOT_ALIVE",
195
+ "40": "NOT_ALIVE",
196
+ "41": "NOT_ALIVE",
197
+ "42": "NOT_ALIVE",
198
+ "43": "NOT_ALIVE",
199
+ "44": "NON_PARTICIPATING",
200
+ "45": "NOT_ALIVE",
201
+ "46": "SUCCESS",
202
+ "47": "NOT_ALIVE",
203
+ "48": "NON_PARTICIPATING",
204
+ "49": "NOT_ALIVE",
205
+ "5": "NOT_ALIVE",
206
+ "50": "SUCCESS",
207
+ "51": "NOT_ALIVE",
208
+ "52": "NOT_ALIVE",
209
+ "53": "NON_PARTICIPATING",
210
+ "54": "NOT_ALIVE",
211
+ "55": "NON_PARTICIPATING",
212
+ "56": "NON_PARTICIPATING",
213
+ "57": "NON_PARTICIPATING",
214
+ "58": "NOT_ALIVE",
215
+ "59": "NOT_ALIVE",
216
+ "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
+ "61": "NON_PARTICIPATING",
219
+ "62": "NOT_ALIVE",
220
+ "63": "SUCCESS",
221
+ "64": "NON_PARTICIPATING",
222
+ "65": "NON_PARTICIPATING",
223
+ "66": "NON_PARTICIPATING",
224
+ "67": "NON_PARTICIPATING",
225
+ "68": "NOT_ALIVE",
226
+ "69": "NOT_ALIVE",
227
+ "7": "NOT_ALIVE",
228
+ "70": "NOT_ALIVE",
229
+ "71": "NON_PARTICIPATING",
230
+ "72": "NOT_ALIVE",
231
+ "73": "NOT_ALIVE",
232
+ "74": "NOT_ALIVE",
233
+ "75": "NON_PARTICIPATING",
234
+ "76": "NOT_ALIVE",
235
+ "77": "NON_PARTICIPATING",
236
+ "78": "NON_PARTICIPATING",
237
+ "79": "NOT_ALIVE",
238
+ "8": "NOT_ALIVE",
239
+ "80": "SUCCESS",
240
+ "81": "NON_PARTICIPATING",
241
+ "82": "NOT_ALIVE",
242
+ "83": "SUCCESS",
243
+ "84": "NON_PARTICIPATING",
244
+ "85": "NOT_ALIVE",
245
+ "86": "NON_PARTICIPATING",
246
+ "87": "NOT_ALIVE",
247
+ "88": "NON_PARTICIPATING",
248
+ "89": "NOT_ALIVE",
249
+ "9": "NOT_ALIVE",
250
+ "90": "NOT_ALIVE",
251
+ "91": "NOT_ALIVE",
252
+ "92": "NOT_ALIVE",
253
+ "93": "NON_PARTICIPATING",
254
+ "94": "NON_PARTICIPATING",
255
+ "95": "NON_PARTICIPATING",
256
+ "96": "NOT_ALIVE",
257
+ "97": "NON_PARTICIPATING",
258
+ "98": "NON_PARTICIPATING",
259
+ "99": "SUCCESS"
260
+ },
261
+ "architectures": [
262
+ "LlamaForCausalLM"
263
+ ],
264
+ "attention_bias": false,
265
+ "attention_dropout": 0.0,
266
+ "block_list": [
267
+ 6138363,
268
+ 6138372,
269
+ 6138382,
270
+ 6138390,
271
+ 6138399,
272
+ 6138408,
273
+ 6138416,
274
+ 6138425
275
+ ],
276
+ "bos_token_id": 1,
277
+ "eos_token_id": 2,
278
+ "hidden_act": "silu",
279
+ "hidden_size": 2048,
280
+ "initializer_range": 0.02,
281
+ "inner_step": 36,
282
+ "intermediate_size": 5632,
283
+ "last_allreduce_block": 6138225,
284
+ "max_position_embeddings": 2048,
285
+ "mlp_bias": false,
286
+ "model_type": "llama",
287
+ "num_attention_heads": 32,
288
+ "num_hidden_layers": 22,
289
+ "num_key_value_heads": 4,
290
+ "pretraining_tp": 1,
291
+ "rms_norm_eps": 1e-05,
292
+ "rope_scaling": null,
293
+ "rope_theta": 10000.0,
294
+ "tie_word_embeddings": false,
295
+ "torch_dtype": "float32",
296
+ "transformers_version": "4.39.3",
297
+ "use_cache": false,
298
+ "vocab_size": 32000
299
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.39.3",
6
+ "use_cache": false
7
+ }
gradients.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42de76157602d5ac14865367785357399bef856b7344e5f5a02d698c111ac1ad
3
+ size 88390091
inner_optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d69c908abeed6505e4563841917bf0d316dc2e7959aef90676407de525f346a
3
+ size 8800564561
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c368d67953c6c12df18d84573cbb6b05341b58aa467b483629f4d793a81f2f5
3
+ size 4400216536