tchbcb commited on
Commit
06528bd
·
verified ·
1 Parent(s): 1ef640f

backup s27_train_metrics.json

Browse files
Files changed (1) hide show
  1. sft-adapter/s27_train_metrics.json +258 -0
sft-adapter/s27_train_metrics.json ADDED
@@ -0,0 +1,258 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train_loss": 0.5060088133367782,
3
+ "train_runtime": 4619.2889,
4
+ "trainable_params": 124657736,
5
+ "feats": 831,
6
+ "epochs": 1,
7
+ "mtp_loss_weight": 0.0,
8
+ "mtp_note": "MTP loss disabled for T4 VRAM (full-seq fp32 logits chain); MTP is bypassed at inference & dropped in GGUF",
9
+ "maxlen": 256,
10
+ "max_ponder_steps": 4,
11
+ "eos_id": 248046,
12
+ "device_map": {
13
+ "model.language_model.embed_tokens": "0",
14
+ "model.language_model.layers.0": "0",
15
+ "model.language_model.layers.1": "0",
16
+ "model.language_model.layers.2": "0",
17
+ "model.language_model.layers.3": "0",
18
+ "model.language_model.layers.4": "0",
19
+ "model.language_model.layers.5": "0",
20
+ "model.language_model.layers.6": "0",
21
+ "model.language_model.layers.7": "0",
22
+ "model.language_model.layers.8": "0",
23
+ "model.language_model.layers.9": "0",
24
+ "model.language_model.layers.10": "0",
25
+ "model.language_model.layers.11": "0",
26
+ "model.language_model.layers.12": "0",
27
+ "model.language_model.layers.13": "0",
28
+ "model.language_model.layers.14": "0",
29
+ "model.language_model.layers.15": "0",
30
+ "model.language_model.layers.16": "0",
31
+ "model.language_model.layers.17": "0",
32
+ "model.language_model.layers.18": "0",
33
+ "model.language_model.layers.19": "0",
34
+ "model.language_model.layers.20": "0",
35
+ "model.language_model.layers.21": "0",
36
+ "model.language_model.layers.22": "0",
37
+ "model.language_model.layers.23": "0",
38
+ "model.language_model.layers.24": "0",
39
+ "model.language_model.layers.25": "0",
40
+ "model.language_model.layers.26": "0",
41
+ "model.language_model.layers.27": "0",
42
+ "model.language_model.layers.28": "0",
43
+ "model.language_model.layers.29": "0",
44
+ "model.language_model.layers.30": "0",
45
+ "model.language_model.layers.31": "0",
46
+ "model.language_model.layers.32": "0",
47
+ "model.language_model.layers.33": "0",
48
+ "model.language_model.layers.34": "0",
49
+ "model.language_model.layers.35": "0",
50
+ "model.language_model.layers.36": "0",
51
+ "model.language_model.layers.37": "0",
52
+ "model.language_model.layers.38": "1",
53
+ "model.language_model.layers.39": "1",
54
+ "model.language_model.layers.40": "1",
55
+ "model.language_model.layers.41": "1",
56
+ "model.language_model.layers.42": "1",
57
+ "model.language_model.layers.43": "1",
58
+ "model.language_model.layers.44": "1",
59
+ "model.language_model.layers.45": "1",
60
+ "model.language_model.layers.46": "1",
61
+ "model.language_model.layers.47": "1",
62
+ "model.language_model.layers.48": "1",
63
+ "model.language_model.layers.49": "1",
64
+ "model.language_model.layers.50": "1",
65
+ "model.language_model.layers.51": "1",
66
+ "model.language_model.layers.52": "1",
67
+ "model.language_model.layers.53": "1",
68
+ "model.language_model.layers.54": "1",
69
+ "model.language_model.layers.55": "1",
70
+ "model.language_model.layers.56": "1",
71
+ "model.language_model.layers.57": "1",
72
+ "model.language_model.layers.58": "1",
73
+ "model.language_model.layers.59": "1",
74
+ "model.language_model.layers.60": "1",
75
+ "model.language_model.layers.61": "1",
76
+ "model.language_model.layers.62": "1",
77
+ "model.language_model.layers.63": "1",
78
+ "model.language_model.norm": "1",
79
+ "mtp": "1",
80
+ "lm_head": "1",
81
+ "model.visual": "cpu",
82
+ "model.language_model.rotary_emb": "0"
83
+ },
84
+ "ponder_stats": {
85
+ "layers": [
86
+ {
87
+ "layer": 35,
88
+ "executed": 2,
89
+ "steps_mean": 1.5032258033752441,
90
+ "moe_active": 2.9612903594970703,
91
+ "moe_aux": 3.4045186042785645
92
+ },
93
+ {
94
+ "layer": 39,
95
+ "executed": 4,
96
+ "steps_mean": 2.2387096881866455,
97
+ "moe_active": 2.8516128063201904,
98
+ "moe_aux": 3.1677749156951904
99
+ },
100
+ {
101
+ "layer": 43,
102
+ "executed": 4,
103
+ "steps_mean": 2.59354829788208,
104
+ "moe_active": 3.3935482501983643,
105
+ "moe_aux": 3.4541893005371094
106
+ },
107
+ {
108
+ "layer": 47,
109
+ "executed": 4,
110
+ "steps_mean": 1.6322580575942993,
111
+ "moe_active": 2.664515972137451,
112
+ "moe_aux": 3.1744186878204346
113
+ },
114
+ {
115
+ "layer": 51,
116
+ "executed": 4,
117
+ "steps_mean": 1.793548345565796,
118
+ "moe_active": 2.8258063793182373,
119
+ "moe_aux": 3.864419460296631
120
+ },
121
+ {
122
+ "layer": 55,
123
+ "executed": 4,
124
+ "steps_mean": 1.3096773624420166,
125
+ "moe_active": 2.2580645084381104,
126
+ "moe_aux": 3.897202491760254
127
+ },
128
+ {
129
+ "layer": 59,
130
+ "executed": 4,
131
+ "steps_mean": 1.0903226137161255,
132
+ "moe_active": 3.245161294937134,
133
+ "moe_aux": 3.8669705390930176
134
+ },
135
+ {
136
+ "layer": 63,
137
+ "executed": 3,
138
+ "steps_mean": 1.0322580337524414,
139
+ "moe_active": 2.8322579860687256,
140
+ "moe_aux": 5.9470534324646
141
+ }
142
+ ],
143
+ "log_tail": [
144
+ {
145
+ "mode": "train",
146
+ "executed": [
147
+ 2,
148
+ 4,
149
+ 4,
150
+ 4,
151
+ 4,
152
+ 4,
153
+ 4,
154
+ 3
155
+ ],
156
+ "steps_mean": 1.6166
157
+ },
158
+ {
159
+ "mode": "train",
160
+ "executed": [
161
+ 2,
162
+ 4,
163
+ 4,
164
+ 4,
165
+ 4,
166
+ 4,
167
+ 4,
168
+ 3
169
+ ],
170
+ "steps_mean": 1.6105
171
+ },
172
+ {
173
+ "mode": "train",
174
+ "executed": [
175
+ 2,
176
+ 4,
177
+ 4,
178
+ 4,
179
+ 4,
180
+ 4,
181
+ 4,
182
+ 3
183
+ ],
184
+ "steps_mean": 1.6435
185
+ },
186
+ {
187
+ "mode": "train",
188
+ "executed": [
189
+ 2,
190
+ 4,
191
+ 4,
192
+ 4,
193
+ 4,
194
+ 4,
195
+ 4,
196
+ 3
197
+ ],
198
+ "steps_mean": 1.564
199
+ },
200
+ {
201
+ "mode": "train",
202
+ "executed": [
203
+ 2,
204
+ 4,
205
+ 4,
206
+ 4,
207
+ 4,
208
+ 4,
209
+ 4,
210
+ 3
211
+ ],
212
+ "steps_mean": 1.6875
213
+ },
214
+ {
215
+ "mode": "train",
216
+ "executed": [
217
+ 3,
218
+ 4,
219
+ 4,
220
+ 4,
221
+ 4,
222
+ 4,
223
+ 4,
224
+ 3
225
+ ],
226
+ "steps_mean": 1.6344
227
+ },
228
+ {
229
+ "mode": "train",
230
+ "executed": [
231
+ 3,
232
+ 4,
233
+ 4,
234
+ 4,
235
+ 4,
236
+ 4,
237
+ 4,
238
+ 3
239
+ ],
240
+ "steps_mean": 1.6526
241
+ },
242
+ {
243
+ "mode": "train",
244
+ "executed": [
245
+ 2,
246
+ 4,
247
+ 4,
248
+ 4,
249
+ 4,
250
+ 4,
251
+ 4,
252
+ 3
253
+ ],
254
+ "steps_mean": 1.6492
255
+ }
256
+ ]
257
+ }
258
+ }