kmfoda commited on
Commit
9a125cf
·
verified ·
1 Parent(s): 6840029

Run 6. Outer Step 37. Inner Step 0.

Browse files
config.json ADDED
@@ -0,0 +1,293 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "NON_PARTICIPATING",
8
+ "101": "NOT_ALIVE",
9
+ "102": "NON_PARTICIPATING",
10
+ "103": "NON_PARTICIPATING",
11
+ "104": "NOT_ALIVE",
12
+ "105": "NOT_ALIVE",
13
+ "106": "NOT_ALIVE",
14
+ "107": "NOT_ALIVE",
15
+ "108": "SUCCESS",
16
+ "109": "NOT_ALIVE",
17
+ "11": "FAIL",
18
+ "110": "FAIL",
19
+ "111": "NOT_ALIVE",
20
+ "112": "NON_PARTICIPATING",
21
+ "113": "SUCCESS",
22
+ "114": "NOT_ALIVE",
23
+ "115": "SUCCESS",
24
+ "116": "NON_PARTICIPATING",
25
+ "117": "NOT_ALIVE",
26
+ "118": "NOT_ALIVE",
27
+ "119": "NOT_ALIVE",
28
+ "12": "NOT_ALIVE",
29
+ "120": "NOT_ALIVE",
30
+ "121": "NOT_ALIVE",
31
+ "122": "NON_PARTICIPATING",
32
+ "123": "SUCCESS",
33
+ "124": "FAIL",
34
+ "125": "NOT_ALIVE",
35
+ "126": "SUCCESS",
36
+ "127": "FAIL",
37
+ "128": "NOT_ALIVE",
38
+ "129": "FAIL",
39
+ "13": "NOT_ALIVE",
40
+ "130": "FAIL",
41
+ "131": "NOT_ALIVE",
42
+ "132": "NOT_ALIVE",
43
+ "133": "NON_PARTICIPATING",
44
+ "134": "SUCCESS",
45
+ "135": "SUCCESS",
46
+ "136": "SUCCESS",
47
+ "137": "FAIL",
48
+ "138": "FAIL",
49
+ "139": "NOT_ALIVE",
50
+ "14": "NOT_ALIVE",
51
+ "140": "SUCCESS",
52
+ "141": "NON_PARTICIPATING",
53
+ "142": "NOT_ALIVE",
54
+ "143": "SUCCESS",
55
+ "144": "SUCCESS",
56
+ "145": "SUCCESS",
57
+ "146": "NOT_ALIVE",
58
+ "147": "FAIL",
59
+ "148": "FAIL",
60
+ "149": "FAIL",
61
+ "15": "SUCCESS",
62
+ "150": "SUCCESS",
63
+ "151": "NON_PARTICIPATING",
64
+ "152": "SUCCESS",
65
+ "153": "FAIL",
66
+ "154": "SUCCESS",
67
+ "155": "FAIL",
68
+ "156": "NOT_ALIVE",
69
+ "157": "NOT_ALIVE",
70
+ "158": "NOT_ALIVE",
71
+ "159": "NON_PARTICIPATING",
72
+ "16": "FAIL",
73
+ "160": "SUCCESS",
74
+ "161": "SUCCESS",
75
+ "162": "NON_PARTICIPATING",
76
+ "163": "NON_PARTICIPATING",
77
+ "164": "SUCCESS",
78
+ "165": "FAIL",
79
+ "166": "SUCCESS",
80
+ "167": "NOT_ALIVE",
81
+ "168": "FAIL",
82
+ "169": "NON_PARTICIPATING",
83
+ "17": "NOT_ALIVE",
84
+ "170": "SUCCESS",
85
+ "171": "NOT_ALIVE",
86
+ "172": "NON_PARTICIPATING",
87
+ "173": "SUCCESS",
88
+ "174": "NON_PARTICIPATING",
89
+ "175": "FAIL",
90
+ "176": "NOT_ALIVE",
91
+ "177": "NON_PARTICIPATING",
92
+ "178": "NON_PARTICIPATING",
93
+ "179": "NON_PARTICIPATING",
94
+ "18": "NOT_ALIVE",
95
+ "180": "FAIL",
96
+ "181": "NOT_ALIVE",
97
+ "182": "NOT_ALIVE",
98
+ "183": "NOT_ALIVE",
99
+ "184": "NOT_ALIVE",
100
+ "185": "NON_PARTICIPATING",
101
+ "186": "FAIL",
102
+ "187": "SUCCESS",
103
+ "188": "FAIL",
104
+ "189": "SUCCESS",
105
+ "19": "SUCCESS",
106
+ "190": "SUCCESS",
107
+ "191": "SUCCESS",
108
+ "192": "SUCCESS",
109
+ "193": "SUCCESS",
110
+ "194": "NOT_ALIVE",
111
+ "195": "NON_PARTICIPATING",
112
+ "196": "NOT_ALIVE",
113
+ "197": "NOT_ALIVE",
114
+ "198": "NON_PARTICIPATING",
115
+ "199": "SUCCESS",
116
+ "2": "FAIL",
117
+ "20": "FAIL",
118
+ "200": "NON_PARTICIPATING",
119
+ "201": "SUCCESS",
120
+ "202": "FAIL",
121
+ "203": "NOT_ALIVE",
122
+ "204": "NOT_ALIVE",
123
+ "205": "NON_PARTICIPATING",
124
+ "206": "NOT_ALIVE",
125
+ "207": "NOT_ALIVE",
126
+ "208": "NOT_ALIVE",
127
+ "209": "SUCCESS",
128
+ "21": "SUCCESS",
129
+ "210": "FAIL",
130
+ "211": "NON_PARTICIPATING",
131
+ "212": "SUCCESS",
132
+ "213": "NON_PARTICIPATING",
133
+ "214": "NON_PARTICIPATING",
134
+ "215": "NON_PARTICIPATING",
135
+ "216": "FAIL",
136
+ "217": "SUCCESS",
137
+ "218": "NON_PARTICIPATING",
138
+ "219": "SUCCESS",
139
+ "22": "NOT_ALIVE",
140
+ "220": "NOT_ALIVE",
141
+ "221": "SUCCESS",
142
+ "222": "NOT_ALIVE",
143
+ "223": "NOT_ALIVE",
144
+ "224": "NON_PARTICIPATING",
145
+ "225": "NOT_ALIVE",
146
+ "226": "NON_PARTICIPATING",
147
+ "227": "NON_PARTICIPATING",
148
+ "228": "SUCCESS",
149
+ "229": "NOT_ALIVE",
150
+ "23": "SUCCESS",
151
+ "230": "FAIL",
152
+ "231": "NOT_ALIVE",
153
+ "232": "NOT_ALIVE",
154
+ "233": "SUCCESS",
155
+ "234": "NON_PARTICIPATING",
156
+ "235": "SUCCESS",
157
+ "236": "FAIL",
158
+ "237": "NON_PARTICIPATING",
159
+ "238": "FAIL",
160
+ "239": "FAIL",
161
+ "24": "NOT_ALIVE",
162
+ "240": "FAIL",
163
+ "241": "SUCCESS",
164
+ "242": "SUCCESS",
165
+ "243": "NOT_ALIVE",
166
+ "244": "SUCCESS",
167
+ "245": "NOT_ALIVE",
168
+ "246": "SUCCESS",
169
+ "247": "NOT_ALIVE",
170
+ "248": "NOT_ALIVE",
171
+ "249": "NOT_ALIVE",
172
+ "25": "NOT_ALIVE",
173
+ "250": "NOT_ALIVE",
174
+ "251": "SUCCESS",
175
+ "252": "FAIL",
176
+ "253": "NON_PARTICIPATING",
177
+ "254": "NOT_ALIVE",
178
+ "255": "NON_PARTICIPATING",
179
+ "26": "NON_PARTICIPATING",
180
+ "27": "NON_PARTICIPATING",
181
+ "28": "NON_PARTICIPATING",
182
+ "29": "NOT_ALIVE",
183
+ "3": "FAIL",
184
+ "30": "SUCCESS",
185
+ "31": "SUCCESS",
186
+ "32": "FAIL",
187
+ "33": "NOT_ALIVE",
188
+ "34": "NON_PARTICIPATING",
189
+ "35": "SUCCESS",
190
+ "36": "SUCCESS",
191
+ "37": "NOT_ALIVE",
192
+ "38": "NON_PARTICIPATING",
193
+ "39": "SUCCESS",
194
+ "4": "NOT_ALIVE",
195
+ "40": "FAIL",
196
+ "41": "NON_PARTICIPATING",
197
+ "42": "NOT_ALIVE",
198
+ "43": "NOT_ALIVE",
199
+ "44": "NON_PARTICIPATING",
200
+ "45": "NON_PARTICIPATING",
201
+ "46": "SUCCESS",
202
+ "47": "SUCCESS",
203
+ "48": "NON_PARTICIPATING",
204
+ "49": "NOT_ALIVE",
205
+ "5": "NOT_ALIVE",
206
+ "50": "SUCCESS",
207
+ "51": "NOT_ALIVE",
208
+ "52": "FAIL",
209
+ "53": "SUCCESS",
210
+ "54": "FAIL",
211
+ "55": "NON_PARTICIPATING",
212
+ "56": "FAIL",
213
+ "57": "NON_PARTICIPATING",
214
+ "58": "FAIL",
215
+ "59": "SUCCESS",
216
+ "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
+ "61": "SUCCESS",
219
+ "62": "NOT_ALIVE",
220
+ "63": "NOT_ALIVE",
221
+ "64": "NON_PARTICIPATING",
222
+ "65": "NON_PARTICIPATING",
223
+ "66": "SUCCESS",
224
+ "67": "NON_PARTICIPATING",
225
+ "68": "NOT_ALIVE",
226
+ "69": "SUCCESS",
227
+ "7": "NOT_ALIVE",
228
+ "70": "SUCCESS",
229
+ "71": "SUCCESS",
230
+ "72": "NON_PARTICIPATING",
231
+ "73": "NOT_ALIVE",
232
+ "74": "NOT_ALIVE",
233
+ "75": "SUCCESS",
234
+ "76": "NOT_ALIVE",
235
+ "77": "FAIL",
236
+ "78": "SUCCESS",
237
+ "79": "NON_PARTICIPATING",
238
+ "8": "NOT_ALIVE",
239
+ "80": "NOT_ALIVE",
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": "SUCCESS",
247
+ "88": "NOT_ALIVE",
248
+ "89": "NOT_ALIVE",
249
+ "9": "SUCCESS",
250
+ "90": "NOT_ALIVE",
251
+ "91": "FAIL",
252
+ "92": "NOT_ALIVE",
253
+ "93": "NOT_ALIVE",
254
+ "94": "NON_PARTICIPATING",
255
+ "95": "NON_PARTICIPATING",
256
+ "96": "NON_PARTICIPATING",
257
+ "97": "NOT_ALIVE",
258
+ "98": "NOT_ALIVE",
259
+ "99": "FAIL"
260
+ },
261
+ "architectures": [
262
+ "LlamaForCausalLM"
263
+ ],
264
+ "attention_bias": false,
265
+ "attention_dropout": 0.0,
266
+ "block_list": [
267
+ 6153000,
268
+ 6153027
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": 0,
276
+ "intermediate_size": 5632,
277
+ "last_allreduce_block": 6152643,
278
+ "max_position_embeddings": 2048,
279
+ "mlp_bias": false,
280
+ "model_type": "llama",
281
+ "num_attention_heads": 32,
282
+ "num_hidden_layers": 22,
283
+ "num_key_value_heads": 4,
284
+ "pretraining_tp": 1,
285
+ "rms_norm_eps": 1e-05,
286
+ "rope_scaling": null,
287
+ "rope_theta": 10000.0,
288
+ "tie_word_embeddings": false,
289
+ "torch_dtype": "float32",
290
+ "transformers_version": "4.39.3",
291
+ "use_cache": false,
292
+ "vocab_size": 32000
293
+ }
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:e6c0dfc2e69e7c1a70bf8ed9c36d71a074f824ad1e6e04bd49ea7085358e9901
3
+ size 44585978
inner_optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e78a50b600ab7a91bada7e1584945c66327d78f26db2f050b78b68dc8fa79857
3
+ size 8800564076
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d864617d34f86347f373ff5122d788066df94bb72b9f7e92d3915299fce0f7ed
3
+ size 4400216536