thkim0305 commited on
Commit
3f3bffb
·
verified ·
1 Parent(s): 7fc1aec

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round10.pth +3 -0
  2. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round12.pth +3 -0
  3. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round15.pth +3 -0
  4. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round17.pth +3 -0
  5. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round2.pth +3 -0
  6. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round20.pth +3 -0
  7. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round5.pth +3 -0
  8. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round7.pth +3 -0
  9. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_trainer_state.json +392 -0
  10. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round10.pth +3 -0
  11. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round12.pth +3 -0
  12. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round15.pth +3 -0
  13. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round17.pth +3 -0
  14. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round2.pth +3 -0
  15. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round20.pth +3 -0
  16. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round5.pth +3 -0
  17. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round7.pth +3 -0
  18. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_trainer_state.json +392 -0
  19. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round10.pth +3 -0
  20. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round12.pth +3 -0
  21. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round15.pth +3 -0
  22. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round17.pth +3 -0
  23. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round2.pth +3 -0
  24. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round20.pth +3 -0
  25. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round5.pth +3 -0
  26. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round7.pth +3 -0
  27. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_trainer_state.json +392 -0
  28. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round10.pth +3 -0
  29. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round12.pth +3 -0
  30. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round15.pth +3 -0
  31. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round17.pth +3 -0
  32. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round2.pth +3 -0
  33. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round20.pth +3 -0
  34. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round5.pth +3 -0
  35. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round7.pth +3 -0
  36. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_trainer_state.json +392 -0
  37. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round10.pth +3 -0
  38. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round12.pth +3 -0
  39. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round15.pth +3 -0
  40. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round17.pth +3 -0
  41. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round2.pth +3 -0
  42. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round20.pth +3 -0
  43. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round5.pth +3 -0
  44. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round7.pth +3 -0
  45. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_trainer_state.json +392 -0
  46. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round10.pth +3 -0
  47. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round12.pth +3 -0
  48. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round15.pth +3 -0
  49. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round17.pth +3 -0
  50. client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round2.pth +3 -0
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round10.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08e85a1c9db7a1806f6816c8ec5d08e440d39ed6b8720487abfb403901094230
3
+ size 146570638
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round12.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49992a92e9770b7fea30d2e0bf7034581bc364c4f14e46c70a542d4ea85f15d7
3
+ size 146570638
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round15.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e9ca435c80f5082c8f8f4463364e801845fb1caf53c0585f49e522c47633aea
3
+ size 146570638
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round17.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0207a476b0cc3584fb29079858da7873f8d8daa5c4aab704017a91b36e9b032d
3
+ size 146570638
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08cd2e96b0cf243a44752709350f1b6cc54f266d133ae21853c926b10d847b0d
3
+ size 146569898
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round20.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aae6ed0bfa93f1c2b5253a6c6407d3827a13bdc875766a6cbb7f9b589fa03153
3
+ size 146570638
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1abbd2d72b344daafc715a3b1890434d14ead2f95c28a653f0258e26e8c3134a
3
+ size 146569898
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9196798c14902438c1ecd9dc92ead770fa03fc697ef026a461d990fab8e2d63
3
+ size 146569898
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/0_trainer_state.json ADDED
@@ -0,0 +1,392 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "grad_norm": 2.1783547401428223,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.3076,
16
+ "step": 2
17
+ },
18
+ {
19
+ "epoch": 0.04,
20
+ "grad_norm": 4.245744228363037,
21
+ "learning_rate": 2e-05,
22
+ "loss": 1.485,
23
+ "step": 4
24
+ },
25
+ {
26
+ "epoch": 0.06,
27
+ "grad_norm": 5.0618062019348145,
28
+ "learning_rate": 2e-05,
29
+ "loss": 0.9309,
30
+ "step": 6
31
+ },
32
+ {
33
+ "epoch": 0.08,
34
+ "grad_norm": 5.149890899658203,
35
+ "learning_rate": 2e-05,
36
+ "loss": 2.2529,
37
+ "step": 8
38
+ },
39
+ {
40
+ "epoch": 0.1,
41
+ "grad_norm": 1.8187313079833984,
42
+ "learning_rate": 2e-05,
43
+ "loss": 0.4769,
44
+ "step": 10
45
+ },
46
+ {
47
+ "epoch": 0.12,
48
+ "grad_norm": 3.3214118480682373,
49
+ "learning_rate": 2e-05,
50
+ "loss": 0.7902,
51
+ "step": 12
52
+ },
53
+ {
54
+ "epoch": 0.14,
55
+ "grad_norm": 6.81147575378418,
56
+ "learning_rate": 2e-05,
57
+ "loss": 1.791,
58
+ "step": 14
59
+ },
60
+ {
61
+ "epoch": 0.16,
62
+ "grad_norm": 1.4837002754211426,
63
+ "learning_rate": 2e-05,
64
+ "loss": 0.8222,
65
+ "step": 16
66
+ },
67
+ {
68
+ "epoch": 0.18,
69
+ "grad_norm": 4.7753520011901855,
70
+ "learning_rate": 2e-05,
71
+ "loss": 0.9105,
72
+ "step": 18
73
+ },
74
+ {
75
+ "epoch": 0.2,
76
+ "grad_norm": 8.150045394897461,
77
+ "learning_rate": 2e-05,
78
+ "loss": 1.1695,
79
+ "step": 20
80
+ },
81
+ {
82
+ "epoch": 0.22,
83
+ "grad_norm": 3.5341460704803467,
84
+ "learning_rate": 2e-05,
85
+ "loss": 0.6647,
86
+ "step": 22
87
+ },
88
+ {
89
+ "epoch": 0.24,
90
+ "grad_norm": 2.2373862266540527,
91
+ "learning_rate": 2e-05,
92
+ "loss": 0.6913,
93
+ "step": 24
94
+ },
95
+ {
96
+ "epoch": 0.26,
97
+ "grad_norm": 3.1278488636016846,
98
+ "learning_rate": 2e-05,
99
+ "loss": 1.054,
100
+ "step": 26
101
+ },
102
+ {
103
+ "epoch": 0.28,
104
+ "grad_norm": 3.5463902950286865,
105
+ "learning_rate": 2e-05,
106
+ "loss": 0.9895,
107
+ "step": 28
108
+ },
109
+ {
110
+ "epoch": 0.3,
111
+ "grad_norm": 3.2314953804016113,
112
+ "learning_rate": 2e-05,
113
+ "loss": 1.1185,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 0.32,
118
+ "grad_norm": 3.0395631790161133,
119
+ "learning_rate": 2e-05,
120
+ "loss": 1.9604,
121
+ "step": 32
122
+ },
123
+ {
124
+ "epoch": 0.34,
125
+ "grad_norm": 1.1910229921340942,
126
+ "learning_rate": 2e-05,
127
+ "loss": 0.4833,
128
+ "step": 34
129
+ },
130
+ {
131
+ "epoch": 0.36,
132
+ "grad_norm": 3.351118326187134,
133
+ "learning_rate": 2e-05,
134
+ "loss": 1.5392,
135
+ "step": 36
136
+ },
137
+ {
138
+ "epoch": 0.38,
139
+ "grad_norm": 5.666720390319824,
140
+ "learning_rate": 2e-05,
141
+ "loss": 2.3187,
142
+ "step": 38
143
+ },
144
+ {
145
+ "epoch": 0.4,
146
+ "grad_norm": 3.7589361667633057,
147
+ "learning_rate": 2e-05,
148
+ "loss": 1.5715,
149
+ "step": 40
150
+ },
151
+ {
152
+ "epoch": 0.42,
153
+ "grad_norm": 3.8645544052124023,
154
+ "learning_rate": 2e-05,
155
+ "loss": 1.2631,
156
+ "step": 42
157
+ },
158
+ {
159
+ "epoch": 0.44,
160
+ "grad_norm": 17.528564453125,
161
+ "learning_rate": 2e-05,
162
+ "loss": 0.8849,
163
+ "step": 44
164
+ },
165
+ {
166
+ "epoch": 0.46,
167
+ "grad_norm": 3.9329302310943604,
168
+ "learning_rate": 2e-05,
169
+ "loss": 1.2254,
170
+ "step": 46
171
+ },
172
+ {
173
+ "epoch": 0.48,
174
+ "grad_norm": 2.1174557209014893,
175
+ "learning_rate": 2e-05,
176
+ "loss": 0.7726,
177
+ "step": 48
178
+ },
179
+ {
180
+ "epoch": 0.5,
181
+ "grad_norm": 3.8675169944763184,
182
+ "learning_rate": 2e-05,
183
+ "loss": 1.3245,
184
+ "step": 50
185
+ },
186
+ {
187
+ "epoch": 0.52,
188
+ "grad_norm": 2.2555489540100098,
189
+ "learning_rate": 2e-05,
190
+ "loss": 0.3804,
191
+ "step": 52
192
+ },
193
+ {
194
+ "epoch": 0.54,
195
+ "grad_norm": 4.924727916717529,
196
+ "learning_rate": 2e-05,
197
+ "loss": 1.5787,
198
+ "step": 54
199
+ },
200
+ {
201
+ "epoch": 0.56,
202
+ "grad_norm": 3.8834705352783203,
203
+ "learning_rate": 2e-05,
204
+ "loss": 1.8066,
205
+ "step": 56
206
+ },
207
+ {
208
+ "epoch": 0.58,
209
+ "grad_norm": 3.8141536712646484,
210
+ "learning_rate": 2e-05,
211
+ "loss": 0.9591,
212
+ "step": 58
213
+ },
214
+ {
215
+ "epoch": 0.6,
216
+ "grad_norm": 3.8433034420013428,
217
+ "learning_rate": 2e-05,
218
+ "loss": 0.8489,
219
+ "step": 60
220
+ },
221
+ {
222
+ "epoch": 0.62,
223
+ "grad_norm": 7.238494873046875,
224
+ "learning_rate": 2e-05,
225
+ "loss": 1.7647,
226
+ "step": 62
227
+ },
228
+ {
229
+ "epoch": 0.64,
230
+ "grad_norm": 3.9665000438690186,
231
+ "learning_rate": 2e-05,
232
+ "loss": 1.5032,
233
+ "step": 64
234
+ },
235
+ {
236
+ "epoch": 0.66,
237
+ "grad_norm": 4.422421455383301,
238
+ "learning_rate": 2e-05,
239
+ "loss": 0.8178,
240
+ "step": 66
241
+ },
242
+ {
243
+ "epoch": 0.68,
244
+ "grad_norm": 1.6917370557785034,
245
+ "learning_rate": 2e-05,
246
+ "loss": 0.5592,
247
+ "step": 68
248
+ },
249
+ {
250
+ "epoch": 0.7,
251
+ "grad_norm": 7.7742791175842285,
252
+ "learning_rate": 2e-05,
253
+ "loss": 1.6059,
254
+ "step": 70
255
+ },
256
+ {
257
+ "epoch": 0.72,
258
+ "grad_norm": 3.268321990966797,
259
+ "learning_rate": 2e-05,
260
+ "loss": 0.9526,
261
+ "step": 72
262
+ },
263
+ {
264
+ "epoch": 0.74,
265
+ "grad_norm": 2.443695306777954,
266
+ "learning_rate": 2e-05,
267
+ "loss": 0.6655,
268
+ "step": 74
269
+ },
270
+ {
271
+ "epoch": 0.76,
272
+ "grad_norm": 2.7728331089019775,
273
+ "learning_rate": 2e-05,
274
+ "loss": 1.2299,
275
+ "step": 76
276
+ },
277
+ {
278
+ "epoch": 0.78,
279
+ "grad_norm": 3.187366247177124,
280
+ "learning_rate": 2e-05,
281
+ "loss": 1.4123,
282
+ "step": 78
283
+ },
284
+ {
285
+ "epoch": 0.8,
286
+ "grad_norm": 2.3169496059417725,
287
+ "learning_rate": 2e-05,
288
+ "loss": 1.4742,
289
+ "step": 80
290
+ },
291
+ {
292
+ "epoch": 0.82,
293
+ "grad_norm": 2.5007076263427734,
294
+ "learning_rate": 2e-05,
295
+ "loss": 1.4303,
296
+ "step": 82
297
+ },
298
+ {
299
+ "epoch": 0.84,
300
+ "grad_norm": 2.3087682723999023,
301
+ "learning_rate": 2e-05,
302
+ "loss": 1.1173,
303
+ "step": 84
304
+ },
305
+ {
306
+ "epoch": 0.86,
307
+ "grad_norm": 2.937824249267578,
308
+ "learning_rate": 2e-05,
309
+ "loss": 1.0919,
310
+ "step": 86
311
+ },
312
+ {
313
+ "epoch": 0.88,
314
+ "grad_norm": 4.138759136199951,
315
+ "learning_rate": 2e-05,
316
+ "loss": 1.3053,
317
+ "step": 88
318
+ },
319
+ {
320
+ "epoch": 0.9,
321
+ "grad_norm": 2.9441945552825928,
322
+ "learning_rate": 2e-05,
323
+ "loss": 0.4144,
324
+ "step": 90
325
+ },
326
+ {
327
+ "epoch": 0.92,
328
+ "grad_norm": 1.4768455028533936,
329
+ "learning_rate": 2e-05,
330
+ "loss": 0.7732,
331
+ "step": 92
332
+ },
333
+ {
334
+ "epoch": 0.94,
335
+ "grad_norm": 1.5441049337387085,
336
+ "learning_rate": 2e-05,
337
+ "loss": 0.9284,
338
+ "step": 94
339
+ },
340
+ {
341
+ "epoch": 0.96,
342
+ "grad_norm": 4.727484703063965,
343
+ "learning_rate": 2e-05,
344
+ "loss": 1.1998,
345
+ "step": 96
346
+ },
347
+ {
348
+ "epoch": 0.98,
349
+ "grad_norm": 5.3145976066589355,
350
+ "learning_rate": 2e-05,
351
+ "loss": 1.3966,
352
+ "step": 98
353
+ },
354
+ {
355
+ "epoch": 1.0,
356
+ "grad_norm": 3.2736685276031494,
357
+ "learning_rate": 2e-05,
358
+ "loss": 0.8992,
359
+ "step": 100
360
+ },
361
+ {
362
+ "epoch": 1.0,
363
+ "step": 100,
364
+ "total_flos": 2957751584030720.0,
365
+ "train_loss": 1.1582752799987792,
366
+ "train_runtime": 265.724,
367
+ "train_samples_per_second": 1.505,
368
+ "train_steps_per_second": 0.376
369
+ }
370
+ ],
371
+ "logging_steps": 2,
372
+ "max_steps": 100,
373
+ "num_input_tokens_seen": 0,
374
+ "num_train_epochs": 1,
375
+ "save_steps": 500,
376
+ "stateful_callbacks": {
377
+ "TrainerControl": {
378
+ "args": {
379
+ "should_epoch_stop": false,
380
+ "should_evaluate": false,
381
+ "should_log": false,
382
+ "should_save": false,
383
+ "should_training_stop": false
384
+ },
385
+ "attributes": {}
386
+ }
387
+ },
388
+ "total_flos": 2957751584030720.0,
389
+ "train_batch_size": 1,
390
+ "trial_name": null,
391
+ "trial_params": null
392
+ }
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round10.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:669e16a688d5cd2d10e50ddacf1c235990019cf91616aca864fd26e8d6b1ab81
3
+ size 146570638
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round12.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cb1000229a8197155d5355952ab57762117f7039e8c5b73eb0d4461acff91d2
3
+ size 146570638
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round15.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18a6f48c38f05d2ea650cd97feece1f29e640fa5c85eb407afb5f02d05af3531
3
+ size 146570638
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round17.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ac47372f18c51b8ffbad67fe1f0260e5f5021bf97c9ef5cf209663e8961bf27
3
+ size 146570638
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a3b0cf25703306e4da54824676aa95292c36374b6ae8ee00be93ffe6ef75ab
3
+ size 146569898
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round20.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bd6efd8fd8637fd80ccdec17c07302c18289fa803a4b682d880e40e4be10c3a
3
+ size 146570638
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dd6552f29ab87af4910ff86d37c609f3bccb27d0cddbfeca6856a62efa2edf8
3
+ size 146569898
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57994b56489b415d8eb9c1cc965f66e9e70558340caca98f5982a371ad662e05
3
+ size 146569898
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/1_trainer_state.json ADDED
@@ -0,0 +1,392 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "grad_norm": 11.650079727172852,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.5769,
16
+ "step": 2
17
+ },
18
+ {
19
+ "epoch": 0.04,
20
+ "grad_norm": 2.6111807823181152,
21
+ "learning_rate": 2e-05,
22
+ "loss": 1.0938,
23
+ "step": 4
24
+ },
25
+ {
26
+ "epoch": 0.06,
27
+ "grad_norm": 3.289921283721924,
28
+ "learning_rate": 2e-05,
29
+ "loss": 1.2549,
30
+ "step": 6
31
+ },
32
+ {
33
+ "epoch": 0.08,
34
+ "grad_norm": 3.2822048664093018,
35
+ "learning_rate": 2e-05,
36
+ "loss": 1.0166,
37
+ "step": 8
38
+ },
39
+ {
40
+ "epoch": 0.1,
41
+ "grad_norm": 2.3175249099731445,
42
+ "learning_rate": 2e-05,
43
+ "loss": 1.3632,
44
+ "step": 10
45
+ },
46
+ {
47
+ "epoch": 0.12,
48
+ "grad_norm": 2.365558624267578,
49
+ "learning_rate": 2e-05,
50
+ "loss": 0.765,
51
+ "step": 12
52
+ },
53
+ {
54
+ "epoch": 0.14,
55
+ "grad_norm": 10.960704803466797,
56
+ "learning_rate": 2e-05,
57
+ "loss": 1.7861,
58
+ "step": 14
59
+ },
60
+ {
61
+ "epoch": 0.16,
62
+ "grad_norm": 1.6251875162124634,
63
+ "learning_rate": 2e-05,
64
+ "loss": 1.1516,
65
+ "step": 16
66
+ },
67
+ {
68
+ "epoch": 0.18,
69
+ "grad_norm": 1.9684007167816162,
70
+ "learning_rate": 2e-05,
71
+ "loss": 1.1882,
72
+ "step": 18
73
+ },
74
+ {
75
+ "epoch": 0.2,
76
+ "grad_norm": 2.846146583557129,
77
+ "learning_rate": 2e-05,
78
+ "loss": 1.0967,
79
+ "step": 20
80
+ },
81
+ {
82
+ "epoch": 0.22,
83
+ "grad_norm": 1.5514401197433472,
84
+ "learning_rate": 2e-05,
85
+ "loss": 1.3148,
86
+ "step": 22
87
+ },
88
+ {
89
+ "epoch": 0.24,
90
+ "grad_norm": 1.7850255966186523,
91
+ "learning_rate": 2e-05,
92
+ "loss": 1.124,
93
+ "step": 24
94
+ },
95
+ {
96
+ "epoch": 0.26,
97
+ "grad_norm": 1.7735031843185425,
98
+ "learning_rate": 2e-05,
99
+ "loss": 1.0864,
100
+ "step": 26
101
+ },
102
+ {
103
+ "epoch": 0.28,
104
+ "grad_norm": 3.5185093879699707,
105
+ "learning_rate": 2e-05,
106
+ "loss": 1.2681,
107
+ "step": 28
108
+ },
109
+ {
110
+ "epoch": 0.3,
111
+ "grad_norm": 2.3928451538085938,
112
+ "learning_rate": 2e-05,
113
+ "loss": 1.4307,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 0.32,
118
+ "grad_norm": 1.6934328079223633,
119
+ "learning_rate": 2e-05,
120
+ "loss": 1.3853,
121
+ "step": 32
122
+ },
123
+ {
124
+ "epoch": 0.34,
125
+ "grad_norm": 1.7155604362487793,
126
+ "learning_rate": 2e-05,
127
+ "loss": 1.3599,
128
+ "step": 34
129
+ },
130
+ {
131
+ "epoch": 0.36,
132
+ "grad_norm": 4.783634662628174,
133
+ "learning_rate": 2e-05,
134
+ "loss": 1.2217,
135
+ "step": 36
136
+ },
137
+ {
138
+ "epoch": 0.38,
139
+ "grad_norm": 3.7151565551757812,
140
+ "learning_rate": 2e-05,
141
+ "loss": 1.2546,
142
+ "step": 38
143
+ },
144
+ {
145
+ "epoch": 0.4,
146
+ "grad_norm": 2.280892848968506,
147
+ "learning_rate": 2e-05,
148
+ "loss": 1.0852,
149
+ "step": 40
150
+ },
151
+ {
152
+ "epoch": 0.42,
153
+ "grad_norm": 5.8292388916015625,
154
+ "learning_rate": 2e-05,
155
+ "loss": 1.1193,
156
+ "step": 42
157
+ },
158
+ {
159
+ "epoch": 0.44,
160
+ "grad_norm": 0.8880971074104309,
161
+ "learning_rate": 2e-05,
162
+ "loss": 1.3125,
163
+ "step": 44
164
+ },
165
+ {
166
+ "epoch": 0.46,
167
+ "grad_norm": 2.424363851547241,
168
+ "learning_rate": 2e-05,
169
+ "loss": 1.3774,
170
+ "step": 46
171
+ },
172
+ {
173
+ "epoch": 0.48,
174
+ "grad_norm": 2.1493723392486572,
175
+ "learning_rate": 2e-05,
176
+ "loss": 1.1858,
177
+ "step": 48
178
+ },
179
+ {
180
+ "epoch": 0.5,
181
+ "grad_norm": 4.051686763763428,
182
+ "learning_rate": 2e-05,
183
+ "loss": 1.229,
184
+ "step": 50
185
+ },
186
+ {
187
+ "epoch": 0.52,
188
+ "grad_norm": 2.629678249359131,
189
+ "learning_rate": 2e-05,
190
+ "loss": 1.625,
191
+ "step": 52
192
+ },
193
+ {
194
+ "epoch": 0.54,
195
+ "grad_norm": 4.3641180992126465,
196
+ "learning_rate": 2e-05,
197
+ "loss": 1.3242,
198
+ "step": 54
199
+ },
200
+ {
201
+ "epoch": 0.56,
202
+ "grad_norm": 1.2128645181655884,
203
+ "learning_rate": 2e-05,
204
+ "loss": 0.7709,
205
+ "step": 56
206
+ },
207
+ {
208
+ "epoch": 0.58,
209
+ "grad_norm": 4.08689546585083,
210
+ "learning_rate": 2e-05,
211
+ "loss": 1.1609,
212
+ "step": 58
213
+ },
214
+ {
215
+ "epoch": 0.6,
216
+ "grad_norm": 2.1526641845703125,
217
+ "learning_rate": 2e-05,
218
+ "loss": 1.3274,
219
+ "step": 60
220
+ },
221
+ {
222
+ "epoch": 0.62,
223
+ "grad_norm": 2.317962884902954,
224
+ "learning_rate": 2e-05,
225
+ "loss": 1.5199,
226
+ "step": 62
227
+ },
228
+ {
229
+ "epoch": 0.64,
230
+ "grad_norm": 2.7177441120147705,
231
+ "learning_rate": 2e-05,
232
+ "loss": 0.8069,
233
+ "step": 64
234
+ },
235
+ {
236
+ "epoch": 0.66,
237
+ "grad_norm": 3.4422905445098877,
238
+ "learning_rate": 2e-05,
239
+ "loss": 1.4839,
240
+ "step": 66
241
+ },
242
+ {
243
+ "epoch": 0.68,
244
+ "grad_norm": 3.5150182247161865,
245
+ "learning_rate": 2e-05,
246
+ "loss": 1.3704,
247
+ "step": 68
248
+ },
249
+ {
250
+ "epoch": 0.7,
251
+ "grad_norm": 2.2003188133239746,
252
+ "learning_rate": 2e-05,
253
+ "loss": 1.2437,
254
+ "step": 70
255
+ },
256
+ {
257
+ "epoch": 0.72,
258
+ "grad_norm": 4.292349815368652,
259
+ "learning_rate": 2e-05,
260
+ "loss": 1.2998,
261
+ "step": 72
262
+ },
263
+ {
264
+ "epoch": 0.74,
265
+ "grad_norm": 2.0096230506896973,
266
+ "learning_rate": 2e-05,
267
+ "loss": 1.0886,
268
+ "step": 74
269
+ },
270
+ {
271
+ "epoch": 0.76,
272
+ "grad_norm": 2.447622060775757,
273
+ "learning_rate": 2e-05,
274
+ "loss": 1.6987,
275
+ "step": 76
276
+ },
277
+ {
278
+ "epoch": 0.78,
279
+ "grad_norm": 7.821030616760254,
280
+ "learning_rate": 2e-05,
281
+ "loss": 1.1805,
282
+ "step": 78
283
+ },
284
+ {
285
+ "epoch": 0.8,
286
+ "grad_norm": 5.617863655090332,
287
+ "learning_rate": 2e-05,
288
+ "loss": 1.7441,
289
+ "step": 80
290
+ },
291
+ {
292
+ "epoch": 0.82,
293
+ "grad_norm": 1.202296257019043,
294
+ "learning_rate": 2e-05,
295
+ "loss": 1.194,
296
+ "step": 82
297
+ },
298
+ {
299
+ "epoch": 0.84,
300
+ "grad_norm": 2.8690929412841797,
301
+ "learning_rate": 2e-05,
302
+ "loss": 1.2336,
303
+ "step": 84
304
+ },
305
+ {
306
+ "epoch": 0.86,
307
+ "grad_norm": 3.079529047012329,
308
+ "learning_rate": 2e-05,
309
+ "loss": 1.1582,
310
+ "step": 86
311
+ },
312
+ {
313
+ "epoch": 0.88,
314
+ "grad_norm": 4.479701995849609,
315
+ "learning_rate": 2e-05,
316
+ "loss": 1.4976,
317
+ "step": 88
318
+ },
319
+ {
320
+ "epoch": 0.9,
321
+ "grad_norm": 3.7412679195404053,
322
+ "learning_rate": 2e-05,
323
+ "loss": 1.3562,
324
+ "step": 90
325
+ },
326
+ {
327
+ "epoch": 0.92,
328
+ "grad_norm": 2.56575345993042,
329
+ "learning_rate": 2e-05,
330
+ "loss": 1.3418,
331
+ "step": 92
332
+ },
333
+ {
334
+ "epoch": 0.94,
335
+ "grad_norm": 4.356723785400391,
336
+ "learning_rate": 2e-05,
337
+ "loss": 1.2173,
338
+ "step": 94
339
+ },
340
+ {
341
+ "epoch": 0.96,
342
+ "grad_norm": 3.159822463989258,
343
+ "learning_rate": 2e-05,
344
+ "loss": 1.1695,
345
+ "step": 96
346
+ },
347
+ {
348
+ "epoch": 0.98,
349
+ "grad_norm": 4.106565952301025,
350
+ "learning_rate": 2e-05,
351
+ "loss": 1.4507,
352
+ "step": 98
353
+ },
354
+ {
355
+ "epoch": 1.0,
356
+ "grad_norm": 1.6499196290969849,
357
+ "learning_rate": 2e-05,
358
+ "loss": 1.1914,
359
+ "step": 100
360
+ },
361
+ {
362
+ "epoch": 1.0,
363
+ "step": 100,
364
+ "total_flos": 2943785130524672.0,
365
+ "train_loss": 1.2700509643554687,
366
+ "train_runtime": 263.8247,
367
+ "train_samples_per_second": 1.516,
368
+ "train_steps_per_second": 0.379
369
+ }
370
+ ],
371
+ "logging_steps": 2,
372
+ "max_steps": 100,
373
+ "num_input_tokens_seen": 0,
374
+ "num_train_epochs": 1,
375
+ "save_steps": 500,
376
+ "stateful_callbacks": {
377
+ "TrainerControl": {
378
+ "args": {
379
+ "should_epoch_stop": false,
380
+ "should_evaluate": false,
381
+ "should_log": false,
382
+ "should_save": false,
383
+ "should_training_stop": false
384
+ },
385
+ "attributes": {}
386
+ }
387
+ },
388
+ "total_flos": 2943785130524672.0,
389
+ "train_batch_size": 1,
390
+ "trial_name": null,
391
+ "trial_params": null
392
+ }
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round10.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4184eae34a132bb5dde42abad4eea9745acc2ae660e1b817b4baf938baaf719a
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round12.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9e01d669410338b22491f1b409779985aba25521a7f7eb3b2f7013f56d06bf
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round15.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2aa21aebc4646073343bd94e9fcbc13172df9504fb241e584c8b58cf0cf464f
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round17.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f2be9f26b90abf8db6359924ebe41237335963516356a6bb1408ea271faff29
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e19f3e9cef5d744dde56b10fa7b9d2a6743335765a008f2cb017af34a884467
3
+ size 487635186
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round20.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f53edfd37d4ab42ea662553fb796cee11428381b5f6b5aed73ccdd2247bac6a
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ecce3bb7e50cb035c8f1f4f6c26d9c78982342ae98808f4d275f2f6f995b4d
3
+ size 487635186
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf74fcbfd93a92ab6ba35bb84a8abac286340409fed9445d741077476e646fd2
3
+ size 487635186
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/2_trainer_state.json ADDED
@@ -0,0 +1,392 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "grad_norm": 5.458401679992676,
14
+ "learning_rate": 2e-05,
15
+ "loss": 0.837,
16
+ "step": 2
17
+ },
18
+ {
19
+ "epoch": 0.04,
20
+ "grad_norm": 1.2612700462341309,
21
+ "learning_rate": 2e-05,
22
+ "loss": 0.276,
23
+ "step": 4
24
+ },
25
+ {
26
+ "epoch": 0.06,
27
+ "grad_norm": 1.1327815055847168,
28
+ "learning_rate": 2e-05,
29
+ "loss": 0.3382,
30
+ "step": 6
31
+ },
32
+ {
33
+ "epoch": 0.08,
34
+ "grad_norm": 1.1331257820129395,
35
+ "learning_rate": 2e-05,
36
+ "loss": 0.1784,
37
+ "step": 8
38
+ },
39
+ {
40
+ "epoch": 0.1,
41
+ "grad_norm": 0.635192334651947,
42
+ "learning_rate": 2e-05,
43
+ "loss": 0.3557,
44
+ "step": 10
45
+ },
46
+ {
47
+ "epoch": 0.12,
48
+ "grad_norm": 3.573460340499878,
49
+ "learning_rate": 2e-05,
50
+ "loss": 0.8625,
51
+ "step": 12
52
+ },
53
+ {
54
+ "epoch": 0.14,
55
+ "grad_norm": 9.723386764526367,
56
+ "learning_rate": 2e-05,
57
+ "loss": 1.998,
58
+ "step": 14
59
+ },
60
+ {
61
+ "epoch": 0.16,
62
+ "grad_norm": 2.2706878185272217,
63
+ "learning_rate": 2e-05,
64
+ "loss": 0.8455,
65
+ "step": 16
66
+ },
67
+ {
68
+ "epoch": 0.18,
69
+ "grad_norm": 3.7457892894744873,
70
+ "learning_rate": 2e-05,
71
+ "loss": 0.6981,
72
+ "step": 18
73
+ },
74
+ {
75
+ "epoch": 0.2,
76
+ "grad_norm": 3.1565046310424805,
77
+ "learning_rate": 2e-05,
78
+ "loss": 0.7933,
79
+ "step": 20
80
+ },
81
+ {
82
+ "epoch": 0.22,
83
+ "grad_norm": 3.9325082302093506,
84
+ "learning_rate": 2e-05,
85
+ "loss": 1.0315,
86
+ "step": 22
87
+ },
88
+ {
89
+ "epoch": 0.24,
90
+ "grad_norm": 6.040102481842041,
91
+ "learning_rate": 2e-05,
92
+ "loss": 1.1477,
93
+ "step": 24
94
+ },
95
+ {
96
+ "epoch": 0.26,
97
+ "grad_norm": 1.8885166645050049,
98
+ "learning_rate": 2e-05,
99
+ "loss": 0.559,
100
+ "step": 26
101
+ },
102
+ {
103
+ "epoch": 0.28,
104
+ "grad_norm": 17.197229385375977,
105
+ "learning_rate": 2e-05,
106
+ "loss": 1.1963,
107
+ "step": 28
108
+ },
109
+ {
110
+ "epoch": 0.3,
111
+ "grad_norm": 0.8790152668952942,
112
+ "learning_rate": 2e-05,
113
+ "loss": 1.0769,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 0.32,
118
+ "grad_norm": 6.46113395690918,
119
+ "learning_rate": 2e-05,
120
+ "loss": 0.6283,
121
+ "step": 32
122
+ },
123
+ {
124
+ "epoch": 0.34,
125
+ "grad_norm": 1.132616639137268,
126
+ "learning_rate": 2e-05,
127
+ "loss": 0.8621,
128
+ "step": 34
129
+ },
130
+ {
131
+ "epoch": 0.36,
132
+ "grad_norm": 5.730275630950928,
133
+ "learning_rate": 2e-05,
134
+ "loss": 0.6177,
135
+ "step": 36
136
+ },
137
+ {
138
+ "epoch": 0.38,
139
+ "grad_norm": 3.353694200515747,
140
+ "learning_rate": 2e-05,
141
+ "loss": 1.0918,
142
+ "step": 38
143
+ },
144
+ {
145
+ "epoch": 0.4,
146
+ "grad_norm": 3.6260006427764893,
147
+ "learning_rate": 2e-05,
148
+ "loss": 0.7253,
149
+ "step": 40
150
+ },
151
+ {
152
+ "epoch": 0.42,
153
+ "grad_norm": 8.504569053649902,
154
+ "learning_rate": 2e-05,
155
+ "loss": 1.6229,
156
+ "step": 42
157
+ },
158
+ {
159
+ "epoch": 0.44,
160
+ "grad_norm": 0.88211590051651,
161
+ "learning_rate": 2e-05,
162
+ "loss": 0.204,
163
+ "step": 44
164
+ },
165
+ {
166
+ "epoch": 0.46,
167
+ "grad_norm": 2.519777297973633,
168
+ "learning_rate": 2e-05,
169
+ "loss": 0.7479,
170
+ "step": 46
171
+ },
172
+ {
173
+ "epoch": 0.48,
174
+ "grad_norm": 2.69463849067688,
175
+ "learning_rate": 2e-05,
176
+ "loss": 0.9365,
177
+ "step": 48
178
+ },
179
+ {
180
+ "epoch": 0.5,
181
+ "grad_norm": 4.025172710418701,
182
+ "learning_rate": 2e-05,
183
+ "loss": 0.9575,
184
+ "step": 50
185
+ },
186
+ {
187
+ "epoch": 0.52,
188
+ "grad_norm": 4.425539493560791,
189
+ "learning_rate": 2e-05,
190
+ "loss": 0.8633,
191
+ "step": 52
192
+ },
193
+ {
194
+ "epoch": 0.54,
195
+ "grad_norm": 1.1571135520935059,
196
+ "learning_rate": 2e-05,
197
+ "loss": 0.5536,
198
+ "step": 54
199
+ },
200
+ {
201
+ "epoch": 0.56,
202
+ "grad_norm": 2.1840813159942627,
203
+ "learning_rate": 2e-05,
204
+ "loss": 0.7365,
205
+ "step": 56
206
+ },
207
+ {
208
+ "epoch": 0.58,
209
+ "grad_norm": 1.7292118072509766,
210
+ "learning_rate": 2e-05,
211
+ "loss": 0.3736,
212
+ "step": 58
213
+ },
214
+ {
215
+ "epoch": 0.6,
216
+ "grad_norm": 2.315370559692383,
217
+ "learning_rate": 2e-05,
218
+ "loss": 0.7374,
219
+ "step": 60
220
+ },
221
+ {
222
+ "epoch": 0.62,
223
+ "grad_norm": 8.24770450592041,
224
+ "learning_rate": 2e-05,
225
+ "loss": 1.4765,
226
+ "step": 62
227
+ },
228
+ {
229
+ "epoch": 0.64,
230
+ "grad_norm": 1.0524805784225464,
231
+ "learning_rate": 2e-05,
232
+ "loss": 0.6016,
233
+ "step": 64
234
+ },
235
+ {
236
+ "epoch": 0.66,
237
+ "grad_norm": 2.975933074951172,
238
+ "learning_rate": 2e-05,
239
+ "loss": 0.8192,
240
+ "step": 66
241
+ },
242
+ {
243
+ "epoch": 0.68,
244
+ "grad_norm": 0.9761468172073364,
245
+ "learning_rate": 2e-05,
246
+ "loss": 0.5861,
247
+ "step": 68
248
+ },
249
+ {
250
+ "epoch": 0.7,
251
+ "grad_norm": 1.1564667224884033,
252
+ "learning_rate": 2e-05,
253
+ "loss": 0.2796,
254
+ "step": 70
255
+ },
256
+ {
257
+ "epoch": 0.72,
258
+ "grad_norm": 2.524449110031128,
259
+ "learning_rate": 2e-05,
260
+ "loss": 0.2125,
261
+ "step": 72
262
+ },
263
+ {
264
+ "epoch": 0.74,
265
+ "grad_norm": 3.109388828277588,
266
+ "learning_rate": 2e-05,
267
+ "loss": 0.8686,
268
+ "step": 74
269
+ },
270
+ {
271
+ "epoch": 0.76,
272
+ "grad_norm": 3.0532543659210205,
273
+ "learning_rate": 2e-05,
274
+ "loss": 0.9248,
275
+ "step": 76
276
+ },
277
+ {
278
+ "epoch": 0.78,
279
+ "grad_norm": 0.6633667945861816,
280
+ "learning_rate": 2e-05,
281
+ "loss": 0.1003,
282
+ "step": 78
283
+ },
284
+ {
285
+ "epoch": 0.8,
286
+ "grad_norm": 4.027904510498047,
287
+ "learning_rate": 2e-05,
288
+ "loss": 0.6071,
289
+ "step": 80
290
+ },
291
+ {
292
+ "epoch": 0.82,
293
+ "grad_norm": 6.348594665527344,
294
+ "learning_rate": 2e-05,
295
+ "loss": 0.8632,
296
+ "step": 82
297
+ },
298
+ {
299
+ "epoch": 0.84,
300
+ "grad_norm": 5.252925395965576,
301
+ "learning_rate": 2e-05,
302
+ "loss": 0.6217,
303
+ "step": 84
304
+ },
305
+ {
306
+ "epoch": 0.86,
307
+ "grad_norm": 7.334709644317627,
308
+ "learning_rate": 2e-05,
309
+ "loss": 0.5262,
310
+ "step": 86
311
+ },
312
+ {
313
+ "epoch": 0.88,
314
+ "grad_norm": 9.935879707336426,
315
+ "learning_rate": 2e-05,
316
+ "loss": 2.0981,
317
+ "step": 88
318
+ },
319
+ {
320
+ "epoch": 0.9,
321
+ "grad_norm": 2.1889235973358154,
322
+ "learning_rate": 2e-05,
323
+ "loss": 0.4266,
324
+ "step": 90
325
+ },
326
+ {
327
+ "epoch": 0.92,
328
+ "grad_norm": 1.0436700582504272,
329
+ "learning_rate": 2e-05,
330
+ "loss": 0.4967,
331
+ "step": 92
332
+ },
333
+ {
334
+ "epoch": 0.94,
335
+ "grad_norm": 3.2247464656829834,
336
+ "learning_rate": 2e-05,
337
+ "loss": 0.7774,
338
+ "step": 94
339
+ },
340
+ {
341
+ "epoch": 0.96,
342
+ "grad_norm": 5.61541748046875,
343
+ "learning_rate": 2e-05,
344
+ "loss": 1.9872,
345
+ "step": 96
346
+ },
347
+ {
348
+ "epoch": 0.98,
349
+ "grad_norm": 5.334161758422852,
350
+ "learning_rate": 2e-05,
351
+ "loss": 1.3802,
352
+ "step": 98
353
+ },
354
+ {
355
+ "epoch": 1.0,
356
+ "grad_norm": 12.052146911621094,
357
+ "learning_rate": 2e-05,
358
+ "loss": 1.3031,
359
+ "step": 100
360
+ },
361
+ {
362
+ "epoch": 1.0,
363
+ "step": 100,
364
+ "total_flos": 1.4729370459439104e+16,
365
+ "train_loss": 0.816181755065918,
366
+ "train_runtime": 450.073,
367
+ "train_samples_per_second": 0.889,
368
+ "train_steps_per_second": 0.222
369
+ }
370
+ ],
371
+ "logging_steps": 2,
372
+ "max_steps": 100,
373
+ "num_input_tokens_seen": 0,
374
+ "num_train_epochs": 1,
375
+ "save_steps": 500,
376
+ "stateful_callbacks": {
377
+ "TrainerControl": {
378
+ "args": {
379
+ "should_epoch_stop": false,
380
+ "should_evaluate": false,
381
+ "should_log": false,
382
+ "should_save": false,
383
+ "should_training_stop": false
384
+ },
385
+ "attributes": {}
386
+ }
387
+ },
388
+ "total_flos": 1.4729370459439104e+16,
389
+ "train_batch_size": 1,
390
+ "trial_name": null,
391
+ "trial_params": null
392
+ }
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round10.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11dc1077e04b70ccec4e47319dcf1c70f04ca3667ec674a60bf8aaceed764aa1
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round12.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ea74eb8bd0a2b3e5be15f0c645fa80d854e23787165d03dd9280c77a5e8e3b
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round15.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2887a447447a9a1d3df7d53d3226823920314a838d710c37e2d6be12a7717498
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round17.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4936832036a2425ebc8e2bb4cdd8e5e51347713215a97be2b404682f8a7eb6f7
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e475695129d206a720d93ba7d7a7a12a602f4fd8afb4dd6527ab9d94c2c229
3
+ size 487635186
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round20.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8104c78d457123827fa922b9773813b8f7e3f6a143a0a56411d1df297b0ddd2
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a4650f57b1099ee351d5bcb03faf3dcfc0a74b067e3718e3cec176b8c134589
3
+ size 487635186
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3479a846e1d95f8acc50a361316b09a78ec8280b91dfb8d282b985138ae47cd8
3
+ size 487635186
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/3_trainer_state.json ADDED
@@ -0,0 +1,392 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "grad_norm": 1.8200491666793823,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.1211,
16
+ "step": 2
17
+ },
18
+ {
19
+ "epoch": 0.04,
20
+ "grad_norm": 2.162048578262329,
21
+ "learning_rate": 2e-05,
22
+ "loss": 0.5269,
23
+ "step": 4
24
+ },
25
+ {
26
+ "epoch": 0.06,
27
+ "grad_norm": 1.2126283645629883,
28
+ "learning_rate": 2e-05,
29
+ "loss": 0.5046,
30
+ "step": 6
31
+ },
32
+ {
33
+ "epoch": 0.08,
34
+ "grad_norm": 1.27145254611969,
35
+ "learning_rate": 2e-05,
36
+ "loss": 0.6663,
37
+ "step": 8
38
+ },
39
+ {
40
+ "epoch": 0.1,
41
+ "grad_norm": 2.976205348968506,
42
+ "learning_rate": 2e-05,
43
+ "loss": 1.0173,
44
+ "step": 10
45
+ },
46
+ {
47
+ "epoch": 0.12,
48
+ "grad_norm": 3.1909773349761963,
49
+ "learning_rate": 2e-05,
50
+ "loss": 0.3709,
51
+ "step": 12
52
+ },
53
+ {
54
+ "epoch": 0.14,
55
+ "grad_norm": 1.0841128826141357,
56
+ "learning_rate": 2e-05,
57
+ "loss": 0.5963,
58
+ "step": 14
59
+ },
60
+ {
61
+ "epoch": 0.16,
62
+ "grad_norm": 1.0888885259628296,
63
+ "learning_rate": 2e-05,
64
+ "loss": 0.6043,
65
+ "step": 16
66
+ },
67
+ {
68
+ "epoch": 0.18,
69
+ "grad_norm": 2.2815592288970947,
70
+ "learning_rate": 2e-05,
71
+ "loss": 1.4713,
72
+ "step": 18
73
+ },
74
+ {
75
+ "epoch": 0.2,
76
+ "grad_norm": 0.9630957841873169,
77
+ "learning_rate": 2e-05,
78
+ "loss": 0.6231,
79
+ "step": 20
80
+ },
81
+ {
82
+ "epoch": 0.22,
83
+ "grad_norm": 1.6307340860366821,
84
+ "learning_rate": 2e-05,
85
+ "loss": 0.2991,
86
+ "step": 22
87
+ },
88
+ {
89
+ "epoch": 0.24,
90
+ "grad_norm": 0.1688595414161682,
91
+ "learning_rate": 2e-05,
92
+ "loss": 0.1757,
93
+ "step": 24
94
+ },
95
+ {
96
+ "epoch": 0.26,
97
+ "grad_norm": 2.5731940269470215,
98
+ "learning_rate": 2e-05,
99
+ "loss": 0.2614,
100
+ "step": 26
101
+ },
102
+ {
103
+ "epoch": 0.28,
104
+ "grad_norm": 6.695366859436035,
105
+ "learning_rate": 2e-05,
106
+ "loss": 1.3547,
107
+ "step": 28
108
+ },
109
+ {
110
+ "epoch": 0.3,
111
+ "grad_norm": 7.323204517364502,
112
+ "learning_rate": 2e-05,
113
+ "loss": 1.8154,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 0.32,
118
+ "grad_norm": 3.8765008449554443,
119
+ "learning_rate": 2e-05,
120
+ "loss": 0.9686,
121
+ "step": 32
122
+ },
123
+ {
124
+ "epoch": 0.34,
125
+ "grad_norm": 1.544974684715271,
126
+ "learning_rate": 2e-05,
127
+ "loss": 0.5223,
128
+ "step": 34
129
+ },
130
+ {
131
+ "epoch": 0.36,
132
+ "grad_norm": 1.5188812017440796,
133
+ "learning_rate": 2e-05,
134
+ "loss": 1.0867,
135
+ "step": 36
136
+ },
137
+ {
138
+ "epoch": 0.38,
139
+ "grad_norm": 2.7388813495635986,
140
+ "learning_rate": 2e-05,
141
+ "loss": 0.8593,
142
+ "step": 38
143
+ },
144
+ {
145
+ "epoch": 0.4,
146
+ "grad_norm": 0.4976053535938263,
147
+ "learning_rate": 2e-05,
148
+ "loss": 0.3185,
149
+ "step": 40
150
+ },
151
+ {
152
+ "epoch": 0.42,
153
+ "grad_norm": 1.32295823097229,
154
+ "learning_rate": 2e-05,
155
+ "loss": 0.6378,
156
+ "step": 42
157
+ },
158
+ {
159
+ "epoch": 0.44,
160
+ "grad_norm": 2.448402166366577,
161
+ "learning_rate": 2e-05,
162
+ "loss": 1.5394,
163
+ "step": 44
164
+ },
165
+ {
166
+ "epoch": 0.46,
167
+ "grad_norm": 1.7574583292007446,
168
+ "learning_rate": 2e-05,
169
+ "loss": 0.6097,
170
+ "step": 46
171
+ },
172
+ {
173
+ "epoch": 0.48,
174
+ "grad_norm": 1.3849269151687622,
175
+ "learning_rate": 2e-05,
176
+ "loss": 0.5439,
177
+ "step": 48
178
+ },
179
+ {
180
+ "epoch": 0.5,
181
+ "grad_norm": 1.7697196006774902,
182
+ "learning_rate": 2e-05,
183
+ "loss": 0.8721,
184
+ "step": 50
185
+ },
186
+ {
187
+ "epoch": 0.52,
188
+ "grad_norm": 0.20334148406982422,
189
+ "learning_rate": 2e-05,
190
+ "loss": 0.3783,
191
+ "step": 52
192
+ },
193
+ {
194
+ "epoch": 0.54,
195
+ "grad_norm": 0.44660478830337524,
196
+ "learning_rate": 2e-05,
197
+ "loss": 0.8572,
198
+ "step": 54
199
+ },
200
+ {
201
+ "epoch": 0.56,
202
+ "grad_norm": 1.5733959674835205,
203
+ "learning_rate": 2e-05,
204
+ "loss": 1.1162,
205
+ "step": 56
206
+ },
207
+ {
208
+ "epoch": 0.58,
209
+ "grad_norm": 2.594515323638916,
210
+ "learning_rate": 2e-05,
211
+ "loss": 0.5829,
212
+ "step": 58
213
+ },
214
+ {
215
+ "epoch": 0.6,
216
+ "grad_norm": 2.182734727859497,
217
+ "learning_rate": 2e-05,
218
+ "loss": 0.3221,
219
+ "step": 60
220
+ },
221
+ {
222
+ "epoch": 0.62,
223
+ "grad_norm": 2.866267681121826,
224
+ "learning_rate": 2e-05,
225
+ "loss": 1.3275,
226
+ "step": 62
227
+ },
228
+ {
229
+ "epoch": 0.64,
230
+ "grad_norm": 2.2026476860046387,
231
+ "learning_rate": 2e-05,
232
+ "loss": 0.9077,
233
+ "step": 64
234
+ },
235
+ {
236
+ "epoch": 0.66,
237
+ "grad_norm": 2.018399238586426,
238
+ "learning_rate": 2e-05,
239
+ "loss": 0.6664,
240
+ "step": 66
241
+ },
242
+ {
243
+ "epoch": 0.68,
244
+ "grad_norm": 0.394215852022171,
245
+ "learning_rate": 2e-05,
246
+ "loss": 0.4503,
247
+ "step": 68
248
+ },
249
+ {
250
+ "epoch": 0.7,
251
+ "grad_norm": 8.52250862121582,
252
+ "learning_rate": 2e-05,
253
+ "loss": 1.0485,
254
+ "step": 70
255
+ },
256
+ {
257
+ "epoch": 0.72,
258
+ "grad_norm": 0.4918105900287628,
259
+ "learning_rate": 2e-05,
260
+ "loss": 0.2853,
261
+ "step": 72
262
+ },
263
+ {
264
+ "epoch": 0.74,
265
+ "grad_norm": 0.3466466963291168,
266
+ "learning_rate": 2e-05,
267
+ "loss": 0.2182,
268
+ "step": 74
269
+ },
270
+ {
271
+ "epoch": 0.76,
272
+ "grad_norm": 2.0345993041992188,
273
+ "learning_rate": 2e-05,
274
+ "loss": 0.9427,
275
+ "step": 76
276
+ },
277
+ {
278
+ "epoch": 0.78,
279
+ "grad_norm": 1.4644876718521118,
280
+ "learning_rate": 2e-05,
281
+ "loss": 0.5684,
282
+ "step": 78
283
+ },
284
+ {
285
+ "epoch": 0.8,
286
+ "grad_norm": 1.935638427734375,
287
+ "learning_rate": 2e-05,
288
+ "loss": 0.5808,
289
+ "step": 80
290
+ },
291
+ {
292
+ "epoch": 0.82,
293
+ "grad_norm": 4.591555595397949,
294
+ "learning_rate": 2e-05,
295
+ "loss": 1.1056,
296
+ "step": 82
297
+ },
298
+ {
299
+ "epoch": 0.84,
300
+ "grad_norm": 1.283273696899414,
301
+ "learning_rate": 2e-05,
302
+ "loss": 1.0448,
303
+ "step": 84
304
+ },
305
+ {
306
+ "epoch": 0.86,
307
+ "grad_norm": 1.7218679189682007,
308
+ "learning_rate": 2e-05,
309
+ "loss": 0.8757,
310
+ "step": 86
311
+ },
312
+ {
313
+ "epoch": 0.88,
314
+ "grad_norm": 3.3882131576538086,
315
+ "learning_rate": 2e-05,
316
+ "loss": 0.9019,
317
+ "step": 88
318
+ },
319
+ {
320
+ "epoch": 0.9,
321
+ "grad_norm": 3.5981903076171875,
322
+ "learning_rate": 2e-05,
323
+ "loss": 0.7649,
324
+ "step": 90
325
+ },
326
+ {
327
+ "epoch": 0.92,
328
+ "grad_norm": 1.4270544052124023,
329
+ "learning_rate": 2e-05,
330
+ "loss": 0.8064,
331
+ "step": 92
332
+ },
333
+ {
334
+ "epoch": 0.94,
335
+ "grad_norm": 1.155638337135315,
336
+ "learning_rate": 2e-05,
337
+ "loss": 0.676,
338
+ "step": 94
339
+ },
340
+ {
341
+ "epoch": 0.96,
342
+ "grad_norm": 2.43051815032959,
343
+ "learning_rate": 2e-05,
344
+ "loss": 0.5135,
345
+ "step": 96
346
+ },
347
+ {
348
+ "epoch": 0.98,
349
+ "grad_norm": 0.801724374294281,
350
+ "learning_rate": 2e-05,
351
+ "loss": 0.4598,
352
+ "step": 98
353
+ },
354
+ {
355
+ "epoch": 1.0,
356
+ "grad_norm": 0.32986071705818176,
357
+ "learning_rate": 2e-05,
358
+ "loss": 0.1707,
359
+ "step": 100
360
+ },
361
+ {
362
+ "epoch": 1.0,
363
+ "step": 100,
364
+ "total_flos": 2.0512792897388544e+16,
365
+ "train_loss": 0.7387669396400451,
366
+ "train_runtime": 466.0594,
367
+ "train_samples_per_second": 0.858,
368
+ "train_steps_per_second": 0.215
369
+ }
370
+ ],
371
+ "logging_steps": 2,
372
+ "max_steps": 100,
373
+ "num_input_tokens_seen": 0,
374
+ "num_train_epochs": 1,
375
+ "save_steps": 500,
376
+ "stateful_callbacks": {
377
+ "TrainerControl": {
378
+ "args": {
379
+ "should_epoch_stop": false,
380
+ "should_evaluate": false,
381
+ "should_log": false,
382
+ "should_save": false,
383
+ "should_training_stop": false
384
+ },
385
+ "attributes": {}
386
+ }
387
+ },
388
+ "total_flos": 2.0512792897388544e+16,
389
+ "train_batch_size": 1,
390
+ "trial_name": null,
391
+ "trial_params": null
392
+ }
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round10.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9abe3681d4ccb07f1555a3f9983f769ce9660a6ddc63ba7c9cb50a7c992dfcc
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round12.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a82d150377e74e85e3aded9f1e3e4b082b05abc21fe18c9f72d8736b0144f694
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round15.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c4a43e6c0b5fc2c28274f30baf940edd56b33041115b489da6993e9af5d90ed
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round17.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d00eb04aa368a1a7a00cd986aabbd59673d32679412a823b34764742a94a01b
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74572e5d8381ba7b9d9c176738bc12ef4122bd6709b36787a31c7c3255d95774
3
+ size 487635186
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round20.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e00f0770b28557ccd62b9f5288c61d053e07d8f52b49844c1aa5d728926111c
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22877b1822b5fccaba7fb1e341589d4e7896fb5ca8c591ff067834a7d6649a3a
3
+ size 487635186
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552d3a5ae1213079cd72982e002815f050b3331b373def27052240a6d2e5c361
3
+ size 487635186
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/4_trainer_state.json ADDED
@@ -0,0 +1,392 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "grad_norm": 0.5643351078033447,
14
+ "learning_rate": 2e-05,
15
+ "loss": 0.3751,
16
+ "step": 2
17
+ },
18
+ {
19
+ "epoch": 0.04,
20
+ "grad_norm": 3.1339523792266846,
21
+ "learning_rate": 2e-05,
22
+ "loss": 1.001,
23
+ "step": 4
24
+ },
25
+ {
26
+ "epoch": 0.06,
27
+ "grad_norm": 6.592704772949219,
28
+ "learning_rate": 2e-05,
29
+ "loss": 2.1898,
30
+ "step": 6
31
+ },
32
+ {
33
+ "epoch": 0.08,
34
+ "grad_norm": 1.5465654134750366,
35
+ "learning_rate": 2e-05,
36
+ "loss": 0.3701,
37
+ "step": 8
38
+ },
39
+ {
40
+ "epoch": 0.1,
41
+ "grad_norm": 3.207089424133301,
42
+ "learning_rate": 2e-05,
43
+ "loss": 1.1161,
44
+ "step": 10
45
+ },
46
+ {
47
+ "epoch": 0.12,
48
+ "grad_norm": 4.006984710693359,
49
+ "learning_rate": 2e-05,
50
+ "loss": 1.1308,
51
+ "step": 12
52
+ },
53
+ {
54
+ "epoch": 0.14,
55
+ "grad_norm": 3.619018077850342,
56
+ "learning_rate": 2e-05,
57
+ "loss": 0.3147,
58
+ "step": 14
59
+ },
60
+ {
61
+ "epoch": 0.16,
62
+ "grad_norm": 6.889374256134033,
63
+ "learning_rate": 2e-05,
64
+ "loss": 1.3693,
65
+ "step": 16
66
+ },
67
+ {
68
+ "epoch": 0.18,
69
+ "grad_norm": 2.5987589359283447,
70
+ "learning_rate": 2e-05,
71
+ "loss": 0.904,
72
+ "step": 18
73
+ },
74
+ {
75
+ "epoch": 0.2,
76
+ "grad_norm": 3.8015196323394775,
77
+ "learning_rate": 2e-05,
78
+ "loss": 0.7912,
79
+ "step": 20
80
+ },
81
+ {
82
+ "epoch": 0.22,
83
+ "grad_norm": 3.647202491760254,
84
+ "learning_rate": 2e-05,
85
+ "loss": 0.9558,
86
+ "step": 22
87
+ },
88
+ {
89
+ "epoch": 0.24,
90
+ "grad_norm": 4.409989356994629,
91
+ "learning_rate": 2e-05,
92
+ "loss": 1.3611,
93
+ "step": 24
94
+ },
95
+ {
96
+ "epoch": 0.26,
97
+ "grad_norm": 5.640492916107178,
98
+ "learning_rate": 2e-05,
99
+ "loss": 2.138,
100
+ "step": 26
101
+ },
102
+ {
103
+ "epoch": 0.28,
104
+ "grad_norm": 3.6392550468444824,
105
+ "learning_rate": 2e-05,
106
+ "loss": 1.2712,
107
+ "step": 28
108
+ },
109
+ {
110
+ "epoch": 0.3,
111
+ "grad_norm": 4.6605706214904785,
112
+ "learning_rate": 2e-05,
113
+ "loss": 1.8568,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 0.32,
118
+ "grad_norm": 4.0251145362854,
119
+ "learning_rate": 2e-05,
120
+ "loss": 0.7705,
121
+ "step": 32
122
+ },
123
+ {
124
+ "epoch": 0.34,
125
+ "grad_norm": 2.9077367782592773,
126
+ "learning_rate": 2e-05,
127
+ "loss": 0.807,
128
+ "step": 34
129
+ },
130
+ {
131
+ "epoch": 0.36,
132
+ "grad_norm": 3.0343000888824463,
133
+ "learning_rate": 2e-05,
134
+ "loss": 1.3898,
135
+ "step": 36
136
+ },
137
+ {
138
+ "epoch": 0.38,
139
+ "grad_norm": 2.1082653999328613,
140
+ "learning_rate": 2e-05,
141
+ "loss": 0.4319,
142
+ "step": 38
143
+ },
144
+ {
145
+ "epoch": 0.4,
146
+ "grad_norm": 6.019985198974609,
147
+ "learning_rate": 2e-05,
148
+ "loss": 1.3727,
149
+ "step": 40
150
+ },
151
+ {
152
+ "epoch": 0.42,
153
+ "grad_norm": 0.04979081451892853,
154
+ "learning_rate": 2e-05,
155
+ "loss": 0.1901,
156
+ "step": 42
157
+ },
158
+ {
159
+ "epoch": 0.44,
160
+ "grad_norm": 4.032464027404785,
161
+ "learning_rate": 2e-05,
162
+ "loss": 1.3319,
163
+ "step": 44
164
+ },
165
+ {
166
+ "epoch": 0.46,
167
+ "grad_norm": 7.7898149490356445,
168
+ "learning_rate": 2e-05,
169
+ "loss": 1.1413,
170
+ "step": 46
171
+ },
172
+ {
173
+ "epoch": 0.48,
174
+ "grad_norm": 2.6529541015625,
175
+ "learning_rate": 2e-05,
176
+ "loss": 0.7235,
177
+ "step": 48
178
+ },
179
+ {
180
+ "epoch": 0.5,
181
+ "grad_norm": 1.9444777965545654,
182
+ "learning_rate": 2e-05,
183
+ "loss": 0.4748,
184
+ "step": 50
185
+ },
186
+ {
187
+ "epoch": 0.52,
188
+ "grad_norm": 5.084156036376953,
189
+ "learning_rate": 2e-05,
190
+ "loss": 1.6947,
191
+ "step": 52
192
+ },
193
+ {
194
+ "epoch": 0.54,
195
+ "grad_norm": 0.2125542163848877,
196
+ "learning_rate": 2e-05,
197
+ "loss": 1.2667,
198
+ "step": 54
199
+ },
200
+ {
201
+ "epoch": 0.56,
202
+ "grad_norm": 2.440829277038574,
203
+ "learning_rate": 2e-05,
204
+ "loss": 0.4801,
205
+ "step": 56
206
+ },
207
+ {
208
+ "epoch": 0.58,
209
+ "grad_norm": 4.308220386505127,
210
+ "learning_rate": 2e-05,
211
+ "loss": 0.8368,
212
+ "step": 58
213
+ },
214
+ {
215
+ "epoch": 0.6,
216
+ "grad_norm": 4.229564666748047,
217
+ "learning_rate": 2e-05,
218
+ "loss": 0.8174,
219
+ "step": 60
220
+ },
221
+ {
222
+ "epoch": 0.62,
223
+ "grad_norm": 1.7232249975204468,
224
+ "learning_rate": 2e-05,
225
+ "loss": 0.6071,
226
+ "step": 62
227
+ },
228
+ {
229
+ "epoch": 0.64,
230
+ "grad_norm": 5.111297607421875,
231
+ "learning_rate": 2e-05,
232
+ "loss": 2.1503,
233
+ "step": 64
234
+ },
235
+ {
236
+ "epoch": 0.66,
237
+ "grad_norm": 4.520809173583984,
238
+ "learning_rate": 2e-05,
239
+ "loss": 1.2316,
240
+ "step": 66
241
+ },
242
+ {
243
+ "epoch": 0.68,
244
+ "grad_norm": 0.13663725554943085,
245
+ "learning_rate": 2e-05,
246
+ "loss": 0.2026,
247
+ "step": 68
248
+ },
249
+ {
250
+ "epoch": 0.7,
251
+ "grad_norm": 2.979079246520996,
252
+ "learning_rate": 2e-05,
253
+ "loss": 1.0173,
254
+ "step": 70
255
+ },
256
+ {
257
+ "epoch": 0.72,
258
+ "grad_norm": 3.677243709564209,
259
+ "learning_rate": 2e-05,
260
+ "loss": 0.4886,
261
+ "step": 72
262
+ },
263
+ {
264
+ "epoch": 0.74,
265
+ "grad_norm": 1.3996766805648804,
266
+ "learning_rate": 2e-05,
267
+ "loss": 1.2772,
268
+ "step": 74
269
+ },
270
+ {
271
+ "epoch": 0.76,
272
+ "grad_norm": 5.615224838256836,
273
+ "learning_rate": 2e-05,
274
+ "loss": 0.8728,
275
+ "step": 76
276
+ },
277
+ {
278
+ "epoch": 0.78,
279
+ "grad_norm": 4.682277679443359,
280
+ "learning_rate": 2e-05,
281
+ "loss": 1.2741,
282
+ "step": 78
283
+ },
284
+ {
285
+ "epoch": 0.8,
286
+ "grad_norm": 6.370571136474609,
287
+ "learning_rate": 2e-05,
288
+ "loss": 0.8218,
289
+ "step": 80
290
+ },
291
+ {
292
+ "epoch": 0.82,
293
+ "grad_norm": 8.115623474121094,
294
+ "learning_rate": 2e-05,
295
+ "loss": 1.8396,
296
+ "step": 82
297
+ },
298
+ {
299
+ "epoch": 0.84,
300
+ "grad_norm": 5.059908390045166,
301
+ "learning_rate": 2e-05,
302
+ "loss": 2.0093,
303
+ "step": 84
304
+ },
305
+ {
306
+ "epoch": 0.86,
307
+ "grad_norm": 2.8391244411468506,
308
+ "learning_rate": 2e-05,
309
+ "loss": 0.7854,
310
+ "step": 86
311
+ },
312
+ {
313
+ "epoch": 0.88,
314
+ "grad_norm": 5.532837867736816,
315
+ "learning_rate": 2e-05,
316
+ "loss": 1.3439,
317
+ "step": 88
318
+ },
319
+ {
320
+ "epoch": 0.9,
321
+ "grad_norm": 7.941919326782227,
322
+ "learning_rate": 2e-05,
323
+ "loss": 0.7711,
324
+ "step": 90
325
+ },
326
+ {
327
+ "epoch": 0.92,
328
+ "grad_norm": 6.921679973602295,
329
+ "learning_rate": 2e-05,
330
+ "loss": 1.8244,
331
+ "step": 92
332
+ },
333
+ {
334
+ "epoch": 0.94,
335
+ "grad_norm": 2.1267218589782715,
336
+ "learning_rate": 2e-05,
337
+ "loss": 0.4627,
338
+ "step": 94
339
+ },
340
+ {
341
+ "epoch": 0.96,
342
+ "grad_norm": 6.3464579582214355,
343
+ "learning_rate": 2e-05,
344
+ "loss": 1.8958,
345
+ "step": 96
346
+ },
347
+ {
348
+ "epoch": 0.98,
349
+ "grad_norm": 1.9987305402755737,
350
+ "learning_rate": 2e-05,
351
+ "loss": 0.5773,
352
+ "step": 98
353
+ },
354
+ {
355
+ "epoch": 1.0,
356
+ "grad_norm": 2.5314383506774902,
357
+ "learning_rate": 2e-05,
358
+ "loss": 1.0929,
359
+ "step": 100
360
+ },
361
+ {
362
+ "epoch": 1.0,
363
+ "step": 100,
364
+ "total_flos": 1.9330344696152064e+16,
365
+ "train_loss": 1.0684044027328492,
366
+ "train_runtime": 469.8384,
367
+ "train_samples_per_second": 0.851,
368
+ "train_steps_per_second": 0.213
369
+ }
370
+ ],
371
+ "logging_steps": 2,
372
+ "max_steps": 100,
373
+ "num_input_tokens_seen": 0,
374
+ "num_train_epochs": 1,
375
+ "save_steps": 500,
376
+ "stateful_callbacks": {
377
+ "TrainerControl": {
378
+ "args": {
379
+ "should_epoch_stop": false,
380
+ "should_evaluate": false,
381
+ "should_log": false,
382
+ "should_save": false,
383
+ "should_training_stop": false
384
+ },
385
+ "attributes": {}
386
+ }
387
+ },
388
+ "total_flos": 1.9330344696152064e+16,
389
+ "train_batch_size": 1,
390
+ "trial_name": null,
391
+ "trial_params": null
392
+ }
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round10.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30523e046be589034dbb720d8509a87b3195afefa5480ee9f16d3a504851e202
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round12.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4d02a3045df12d6b0104e4f5cef507b7c810e1820da39a1f5bc85b8d4124470
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round15.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37473880f87b2230cc1d0371a0b75fdfe9404baa3beb4afe18978d9e1876c92a
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round17.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b8b5db9ab5e30a7e20566d4e6eaee29cf4c1d4202e481b1755589fa92d786ea
3
+ size 487636262
client_states_fedMultipqfullfreeze_homoAgg_bs4_saveoptim_lr2e-5_sc1137_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e49ebba937da809aed044ea1a65baf28f139432436e0168fd5867f6bf2c8af72
3
+ size 487635186