Hugging Face's logo

adobeXd
/
nexus

Text Generation
PyTorch
English
metacontrol
neural-controller
llm-agent
kv-cache
mamba
lora
token-efficiency
tool-routing
belief-tracking
Model card Files
xet
 Community
adobeXd commited on
Commit
3421853
·
verified ·
1 Parent(s): eb681a8

Upload checkpoints/training_metrics.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoints/training_metrics.json +262 -0
checkpoints/training_metrics.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "neural_router": {
3
+ "train_loss": [
4
+ 1.0922,
5
+ 0.2192,
6
+ 0.1393,
7
+ 0.1132,
8
+ 0.0939,
9
+ 0.0795,
10
+ 0.0696,
11
+ 0.0606,
12
+ 0.0529,
13
+ 0.0462,
14
+ 0.039,
15
+ 0.0342,
16
+ 0.0282,
17
+ 0.0244,
18
+ 0.0205,
19
+ 0.0176,
20
+ 0.0155,
21
+ 0.0136,
22
+ 0.0121,
23
+ 0.011,
24
+ 0.0103,
25
+ 0.0095,
26
+ 0.009,
27
+ 0.0086,
28
+ 0.0083,
29
+ 0.008,
30
+ 0.0079,
31
+ 0.0077,
32
+ 0.0076,
33
+ 0.0076
34
+ ],
35
+ "train_acc": [
36
+ 0.7601,
37
+ 0.9435,
38
+ 0.9576,
39
+ 0.9637,
40
+ 0.9727,
41
+ 0.9784,
42
+ 0.9805,
43
+ 0.9836,
44
+ 0.9866,
45
+ 0.9872,
46
+ 0.992,
47
+ 0.9924,
48
+ 0.9958,
49
+ 0.9975,
50
+ 0.9985,
51
+ 0.9987,
52
+ 0.9996,
53
+ 0.9996,
54
+ 0.9996,
55
+ 1.0,
56
+ 1.0,
57
+ 1.0,
58
+ 1.0,
59
+ 1.0,
60
+ 1.0,
61
+ 1.0,
62
+ 1.0,
63
+ 1.0,
64
+ 1.0,
65
+ 1.0
66
+ ],
67
+ "val_loss": [
68
+ 0.3292,
69
+ 0.1662,
70
+ 0.162,
71
+ 0.1654,
72
+ 0.1727,
73
+ 0.1877,
74
+ 0.194,
75
+ 0.1953,
76
+ 0.203,
77
+ 0.2305,
78
+ 0.2257,
79
+ 0.236,
80
+ 0.2473,
81
+ 0.2507,
82
+ 0.2601,
83
+ 0.2621,
84
+ 0.2651,
85
+ 0.2715,
86
+ 0.2743,
87
+ 0.2786,
88
+ 0.278,
89
+ 0.2824,
90
+ 0.2828,
91
+ 0.2826,
92
+ 0.2842,
93
+ 0.2851,
94
+ 0.2858,
95
+ 0.2859,
96
+ 0.2861,
97
+ 0.2862
98
+ ],
99
+ "val_acc": [
100
+ 0.944,
101
+ 0.9548,
102
+ 0.9488,
103
+ 0.9476,
104
+ 0.9464,
105
+ 0.9417,
106
+ 0.9429,
107
+ 0.9476,
108
+ 0.9405,
109
+ 0.9393,
110
+ 0.9417,
111
+ 0.9405,
112
+ 0.9333,
113
+ 0.9417,
114
+ 0.9369,
115
+ 0.9393,
116
+ 0.9381,
117
+ 0.9381,
118
+ 0.9393,
119
+ 0.9381,
120
+ 0.9393,
121
+ 0.9381,
122
+ 0.9393,
123
+ 0.9393,
124
+ 0.9381,
125
+ 0.9393,
126
+ 0.9393,
127
+ 0.9393,
128
+ 0.9393,
129
+ 0.9393
130
+ ]
131
+ },
132
+ "subtask_classifier": {
133
+ "train_loss": [
134
+ 1.0938,
135
+ 0.213,
136
+ 0.0447,
137
+ 0.0207,
138
+ 0.0124,
139
+ 0.0084,
140
+ 0.0061,
141
+ 0.0047,
142
+ 0.0038,
143
+ 0.0031,
144
+ 0.0027,
145
+ 0.0023,
146
+ 0.002,
147
+ 0.0018,
148
+ 0.0016,
149
+ 0.0015,
150
+ 0.0014,
151
+ 0.0013,
152
+ 0.0012,
153
+ 0.0011,
154
+ 0.0011,
155
+ 0.0011,
156
+ 0.001,
157
+ 0.001,
158
+ 0.001,
159
+ 0.001,
160
+ 0.001,
161
+ 0.0009,
162
+ 0.0009,
163
+ 0.0009
164
+ ],
165
+ "train_acc": [
166
+ 0.795,
167
+ 0.9962,
168
+ 0.9997,
169
+ 1.0,
170
+ 1.0,
171
+ 1.0,
172
+ 1.0,
173
+ 1.0,
174
+ 1.0,
175
+ 1.0,
176
+ 1.0,
177
+ 1.0,
178
+ 1.0,
179
+ 1.0,
180
+ 1.0,
181
+ 1.0,
182
+ 1.0,
183
+ 1.0,
184
+ 1.0,
185
+ 1.0,
186
+ 1.0,
187
+ 1.0,
188
+ 1.0,
189
+ 1.0,
190
+ 1.0,
191
+ 1.0,
192
+ 1.0,
193
+ 1.0,
194
+ 1.0,
195
+ 1.0
196
+ ],
197
+ "val_loss": [
198
+ 0.4999,
199
+ 0.0774,
200
+ 0.0359,
201
+ 0.0241,
202
+ 0.0189,
203
+ 0.016,
204
+ 0.0143,
205
+ 0.013,
206
+ 0.0123,
207
+ 0.0116,
208
+ 0.0112,
209
+ 0.0108,
210
+ 0.0106,
211
+ 0.0104,
212
+ 0.0102,
213
+ 0.0101,
214
+ 0.0099,
215
+ 0.0098,
216
+ 0.0097,
217
+ 0.0096,
218
+ 0.0096,
219
+ 0.0095,
220
+ 0.0095,
221
+ 0.0095,
222
+ 0.0094,
223
+ 0.0094,
224
+ 0.0094,
225
+ 0.0094,
226
+ 0.0094,
227
+ 0.0094
228
+ ],
229
+ "val_acc": [
230
+ 0.9933,
231
+ 0.9983,
232
+ 0.9983,
233
+ 0.9967,
234
+ 0.9983,
235
+ 0.9983,
236
+ 0.9983,
237
+ 0.9983,
238
+ 0.9983,
239
+ 0.9983,
240
+ 0.9983,
241
+ 0.9983,
242
+ 0.9983,
243
+ 0.9983,
244
+ 0.9983,
245
+ 0.9983,
246
+ 0.9983,
247
+ 0.9983,
248
+ 0.9983,
249
+ 0.9983,
250
+ 0.9983,
251
+ 0.9983,
252
+ 0.9983,
253
+ 0.9983,
254
+ 0.9983,
255
+ 0.9983,
256
+ 0.9983,
257
+ 0.9983,
258
+ 0.9983,
259
+ 0.9983
260
+ ]
261
+ }
262
+ }