model checkpoints

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8bb9f6c25f922713aecb2a43bf2d42d559a3dbbc3ef44396e8dcf0c171a897f
+size 791578182

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeca78e4ef0ca09c3c9dc1af619d8d6c62a5ad7cc2eb5e1cb43545819c3ab2e0
+size 791578182

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d408d33f4b506621f90cc288c5605d75180856e41c97eb2027dd80bc22d772c4
+size 791578182

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e2871b27628bb900154ef54695732d144b4d92ee183dfcd79c2e36d80feeed3
+size 791578182

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394a6f23d83467aedbce42c5ed1673db2949c93ebebcac355ea55b0341562a72
+size 791576546

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64048e71939bae354a5cfc2dc307d22b969178dca83bd954db8b8a53bf028330
+size 791578182

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d93683a32e9d01822aa90755c31264af9ef316e04454e8d9f0f42e5a018d880
+size 791576546

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5522748e360cabea27255f519e3f61d67f315fbd5f05216185677341a578b6
+size 791576546

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/0_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.759765148162842,
+      "learning_rate": 2e-05,
+      "loss": 0.1885,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.2997606992721558,
+      "learning_rate": 2e-05,
+      "loss": 0.2334,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.5568311214447021,
+      "learning_rate": 2e-05,
+      "loss": 0.0361,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.2341224104166031,
+      "learning_rate": 2e-05,
+      "loss": 0.0355,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.724339008331299,
+      "learning_rate": 2e-05,
+      "loss": 0.2466,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.4435043334960938,
+      "learning_rate": 2e-05,
+      "loss": 0.2427,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.4326348304748535,
+      "learning_rate": 2e-05,
+      "loss": 0.117,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.502455949783325,
+      "learning_rate": 2e-05,
+      "loss": 0.4245,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.409182548522949,
+      "learning_rate": 2e-05,
+      "loss": 0.9624,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.573906660079956,
+      "learning_rate": 2e-05,
+      "loss": 0.3429,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.15512648224830627,
+      "learning_rate": 2e-05,
+      "loss": 0.0114,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.8118834495544434,
+      "learning_rate": 2e-05,
+      "loss": 0.4072,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.21215975284576416,
+      "learning_rate": 2e-05,
+      "loss": 0.1748,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.37227046489715576,
+      "learning_rate": 2e-05,
+      "loss": 0.2236,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.839745283126831,
+      "learning_rate": 2e-05,
+      "loss": 0.2748,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.12957799434661865,
+      "learning_rate": 2e-05,
+      "loss": 0.0251,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.0497076511383057,
+      "learning_rate": 2e-05,
+      "loss": 0.1551,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 4.895009994506836,
+      "learning_rate": 2e-05,
+      "loss": 0.3552,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.4893113076686859,
+      "learning_rate": 2e-05,
+      "loss": 0.1992,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.2643682956695557,
+      "learning_rate": 2e-05,
+      "loss": 0.0922,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.1882655769586563,
+      "learning_rate": 2e-05,
+      "loss": 0.0144,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.109602451324463,
+      "learning_rate": 2e-05,
+      "loss": 0.293,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.8853396773338318,
+      "learning_rate": 2e-05,
+      "loss": 0.1328,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.3761306703090668,
+      "learning_rate": 2e-05,
+      "loss": 0.1832,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.1210752725601196,
+      "learning_rate": 2e-05,
+      "loss": 0.074,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.428300619125366,
+      "learning_rate": 2e-05,
+      "loss": 0.0995,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.44176599383354187,
+      "learning_rate": 2e-05,
+      "loss": 0.1278,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.9758191108703613,
+      "learning_rate": 2e-05,
+      "loss": 0.1159,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.313375949859619,
+      "learning_rate": 2e-05,
+      "loss": 0.5219,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.09026255458593369,
+      "learning_rate": 2e-05,
+      "loss": 0.0056,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.7812584042549133,
+      "learning_rate": 2e-05,
+      "loss": 0.0965,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.6800825595855713,
+      "learning_rate": 2e-05,
+      "loss": 0.1061,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.4965532124042511,
+      "learning_rate": 2e-05,
+      "loss": 0.0178,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.302773118019104,
+      "learning_rate": 2e-05,
+      "loss": 0.119,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.1201677322387695,
+      "learning_rate": 2e-05,
+      "loss": 0.2618,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.332615613937378,
+      "learning_rate": 2e-05,
+      "loss": 0.1052,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 5.7126946449279785,
+      "learning_rate": 2e-05,
+      "loss": 0.9101,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.0343668460845947,
+      "learning_rate": 2e-05,
+      "loss": 0.4634,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.6162095069885254,
+      "learning_rate": 2e-05,
+      "loss": 0.279,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5746565461158752,
+      "learning_rate": 2e-05,
+      "loss": 0.3177,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.0711337327957153,
+      "learning_rate": 2e-05,
+      "loss": 0.0829,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.581429958343506,
+      "learning_rate": 2e-05,
+      "loss": 0.1843,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.9817764163017273,
+      "learning_rate": 2e-05,
+      "loss": 0.039,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.4033353328704834,
+      "learning_rate": 2e-05,
+      "loss": 0.1229,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.7180047035217285,
+      "learning_rate": 2e-05,
+      "loss": 0.1123,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.8907074928283691,
+      "learning_rate": 2e-05,
+      "loss": 0.1681,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.818262100219727,
+      "learning_rate": 2e-05,
+      "loss": 1.121,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.6582738161087036,
+      "learning_rate": 2e-05,
+      "loss": 0.5114,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.4680819511413574,
+      "learning_rate": 2e-05,
+      "loss": 0.3985,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.24810414016246796,
+      "learning_rate": 2e-05,
+      "loss": 0.0458,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5289495989583872.0,
+      "train_loss": 0.2355753231048584,
+      "train_runtime": 110.53,
+      "train_samples_per_second": 3.619,
+      "train_steps_per_second": 0.905
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5289495989583872.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/10_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b43fd483b22c0b98362e12a01cbd0574094a0efb2fc57fb7b27447ff25f2c3ac
+size 368444338

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/10_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8103244c88a9cfcb174f8d9d278adc0bc0127fc3a361d35e1168688e1a79b26f
+size 368444338

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/10_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6e90c54180d6764f135d50ed6915d26fdb056aca74456293bb244dfd645455
+size 368444338

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/10_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:723859a1018b828db3e4426ccfbcfa1597d88954e6a1b43f88374e6fb6bbb1d5
+size 368444338

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/10_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174d8bde30c02f56fe4eabdfdcaecb2adbfcb42b0be74e7d9438fd47ab79b254
+size 368443438

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/10_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:166873487ba1961535ec009c0e8b1c1d8d72a93b57f7fae5922c34fa3aed4970
+size 368444338

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/10_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a950eefd09d65bd8f3545dbe3c427d41ec5653a7bf4113dcafcf230f65620f7
+size 368443438

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/10_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1914008c9c6462d95eb96625020daec333f96a21b7442e428eafff9a874dbef
+size 368443438

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/10_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.540152549743652,
+      "learning_rate": 2e-05,
+      "loss": 0.4112,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.820958375930786,
+      "learning_rate": 2e-05,
+      "loss": 0.123,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.2911338806152344,
+      "learning_rate": 2e-05,
+      "loss": 0.1151,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 5.34431266784668,
+      "learning_rate": 2e-05,
+      "loss": 0.6437,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.554713726043701,
+      "learning_rate": 2e-05,
+      "loss": 0.3202,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.19470170140266418,
+      "learning_rate": 2e-05,
+      "loss": 0.0132,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 6.95194673538208,
+      "learning_rate": 2e-05,
+      "loss": 0.3958,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.7412580251693726,
+      "learning_rate": 2e-05,
+      "loss": 0.1572,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 4.699458122253418,
+      "learning_rate": 2e-05,
+      "loss": 0.1354,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.3113508224487305,
+      "learning_rate": 2e-05,
+      "loss": 0.3508,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 4.73491907119751,
+      "learning_rate": 2e-05,
+      "loss": 0.2418,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.238286018371582,
+      "learning_rate": 2e-05,
+      "loss": 0.1221,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 5.935497283935547,
+      "learning_rate": 2e-05,
+      "loss": 0.5967,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 9.50597858428955,
+      "learning_rate": 2e-05,
+      "loss": 0.6172,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 8.673219680786133,
+      "learning_rate": 2e-05,
+      "loss": 0.5515,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.0694637298583984,
+      "learning_rate": 2e-05,
+      "loss": 0.0626,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.6291310787200928,
+      "learning_rate": 2e-05,
+      "loss": 0.1058,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.465129554271698,
+      "learning_rate": 2e-05,
+      "loss": 0.2965,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.1682217121124268,
+      "learning_rate": 2e-05,
+      "loss": 0.176,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.369879961013794,
+      "learning_rate": 2e-05,
+      "loss": 0.2682,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.5110698938369751,
+      "learning_rate": 2e-05,
+      "loss": 0.0655,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.19209489226341248,
+      "learning_rate": 2e-05,
+      "loss": 0.5971,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.3685367703437805,
+      "learning_rate": 2e-05,
+      "loss": 0.0502,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.7339094877243042,
+      "learning_rate": 2e-05,
+      "loss": 0.2632,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.006829261779785,
+      "learning_rate": 2e-05,
+      "loss": 0.1007,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.7255167961120605,
+      "learning_rate": 2e-05,
+      "loss": 0.9134,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 12.463668823242188,
+      "learning_rate": 2e-05,
+      "loss": 1.3237,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.31620460748672485,
+      "learning_rate": 2e-05,
+      "loss": 0.0115,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.888059616088867,
+      "learning_rate": 2e-05,
+      "loss": 0.1024,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 9.215259552001953,
+      "learning_rate": 2e-05,
+      "loss": 0.335,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 6.971097469329834,
+      "learning_rate": 2e-05,
+      "loss": 0.4281,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.5247466564178467,
+      "learning_rate": 2e-05,
+      "loss": 0.0873,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.305556297302246,
+      "learning_rate": 2e-05,
+      "loss": 0.8254,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.3106958866119385,
+      "learning_rate": 2e-05,
+      "loss": 0.4049,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.9962230324745178,
+      "learning_rate": 2e-05,
+      "loss": 0.0339,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 15.942362785339355,
+      "learning_rate": 2e-05,
+      "loss": 0.917,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 4.5281805992126465,
+      "learning_rate": 2e-05,
+      "loss": 0.2087,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 9.443400382995605,
+      "learning_rate": 2e-05,
+      "loss": 0.4157,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 6.793636798858643,
+      "learning_rate": 2e-05,
+      "loss": 0.8669,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.395467758178711,
+      "learning_rate": 2e-05,
+      "loss": 0.732,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 7.989163398742676,
+      "learning_rate": 2e-05,
+      "loss": 0.402,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.12291645258665085,
+      "learning_rate": 2e-05,
+      "loss": 0.0088,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 5.78603982925415,
+      "learning_rate": 2e-05,
+      "loss": 0.3615,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 5.31522274017334,
+      "learning_rate": 2e-05,
+      "loss": 0.5243,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.1642500162124634,
+      "learning_rate": 2e-05,
+      "loss": 0.1487,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.8082680702209473,
+      "learning_rate": 2e-05,
+      "loss": 0.4324,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 5.412454605102539,
+      "learning_rate": 2e-05,
+      "loss": 0.7421,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.5595290660858154,
+      "learning_rate": 2e-05,
+      "loss": 0.121,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.6381373405456543,
+      "learning_rate": 2e-05,
+      "loss": 0.2491,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7060370445251465,
+      "learning_rate": 2e-05,
+      "loss": 0.5233,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2220576018006016.0,
+      "train_loss": 0.35800392150878907,
+      "train_runtime": 82.3263,
+      "train_samples_per_second": 4.859,
+      "train_steps_per_second": 1.215
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2220576018006016.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/11_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c7dabf9a1e6938c5ad868400abd8bfb93de9b8018beb56e924aee4ff8da4615
+size 368444338

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/11_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dbfa77c2b17796f76a16e1bc345aa3003103d7751c7f027622bb97b93371097
+size 368444338

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/11_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec59bb41278eef1a16c3ec9c38b5725a99e3a0d1a8a0744597d6d53665e49e56
+size 368444338

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/11_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3d9536f47b9667a637006fb5cd0c09495296df2b95c762598639f0a28211e6
+size 368444338

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/11_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8416029955098733bd16102f51e5190913435a273688a56109d7e28971a62703
+size 368443438

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/11_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:512ce8d54f2e758e8aaff9a3225b056dd058a92c7d661054042a8d2f964b6a48
+size 368444338

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/11_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df17747c40ec198afdcc951a4e99fd8683cd84e079d089eadb40ca3dbb8ca8e6
+size 368443438

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/11_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eaf6003474ef273ca56a9a823bc0540d3448b4f0f8be5e9c93504a9ff99277b
+size 368443438

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/11_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.755228042602539,
+      "learning_rate": 2e-05,
+      "loss": 0.4839,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.927358150482178,
+      "learning_rate": 2e-05,
+      "loss": 0.3677,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.49658465385437,
+      "learning_rate": 2e-05,
+      "loss": 0.381,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.028351306915283,
+      "learning_rate": 2e-05,
+      "loss": 0.2484,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 6.260554313659668,
+      "learning_rate": 2e-05,
+      "loss": 0.793,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.9733984470367432,
+      "learning_rate": 2e-05,
+      "loss": 0.4696,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.129627227783203,
+      "learning_rate": 2e-05,
+      "loss": 0.9727,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.833235263824463,
+      "learning_rate": 2e-05,
+      "loss": 0.71,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.3442604541778564,
+      "learning_rate": 2e-05,
+      "loss": 0.5811,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.6310151815414429,
+      "learning_rate": 2e-05,
+      "loss": 0.359,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.7572506666183472,
+      "learning_rate": 2e-05,
+      "loss": 0.2868,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.0499885082244873,
+      "learning_rate": 2e-05,
+      "loss": 0.4556,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.5038318634033203,
+      "learning_rate": 2e-05,
+      "loss": 0.3833,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 7.785128593444824,
+      "learning_rate": 2e-05,
+      "loss": 0.4614,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.476345062255859,
+      "learning_rate": 2e-05,
+      "loss": 0.54,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.5807504653930664,
+      "learning_rate": 2e-05,
+      "loss": 0.4373,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.6199612617492676,
+      "learning_rate": 2e-05,
+      "loss": 0.5078,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 5.068996906280518,
+      "learning_rate": 2e-05,
+      "loss": 0.4609,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.555264949798584,
+      "learning_rate": 2e-05,
+      "loss": 0.4846,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.7653462290763855,
+      "learning_rate": 2e-05,
+      "loss": 0.4608,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 6.7089691162109375,
+      "learning_rate": 2e-05,
+      "loss": 0.3584,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.8125996589660645,
+      "learning_rate": 2e-05,
+      "loss": 0.6569,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.4853155612945557,
+      "learning_rate": 2e-05,
+      "loss": 0.4939,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.0506442785263062,
+      "learning_rate": 2e-05,
+      "loss": 0.2601,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 5.831657886505127,
+      "learning_rate": 2e-05,
+      "loss": 0.6602,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.004698753356934,
+      "learning_rate": 2e-05,
+      "loss": 0.5503,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.582853078842163,
+      "learning_rate": 2e-05,
+      "loss": 0.3324,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.086846828460693,
+      "learning_rate": 2e-05,
+      "loss": 0.2622,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.316006898880005,
+      "learning_rate": 2e-05,
+      "loss": 0.235,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.871242880821228,
+      "learning_rate": 2e-05,
+      "loss": 0.3149,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.0035479068756104,
+      "learning_rate": 2e-05,
+      "loss": 0.3652,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.884969711303711,
+      "learning_rate": 2e-05,
+      "loss": 0.3341,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 6.4319562911987305,
+      "learning_rate": 2e-05,
+      "loss": 0.6167,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.11548277735710144,
+      "learning_rate": 2e-05,
+      "loss": 0.1651,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.814781427383423,
+      "learning_rate": 2e-05,
+      "loss": 0.3645,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.4434401988983154,
+      "learning_rate": 2e-05,
+      "loss": 0.4271,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.981860876083374,
+      "learning_rate": 2e-05,
+      "loss": 0.5566,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.0367769002914429,
+      "learning_rate": 2e-05,
+      "loss": 0.4013,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 6.169937610626221,
+      "learning_rate": 2e-05,
+      "loss": 0.6856,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.215674877166748,
+      "learning_rate": 2e-05,
+      "loss": 0.6436,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.0360214710235596,
+      "learning_rate": 2e-05,
+      "loss": 0.7363,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.0028862953186035,
+      "learning_rate": 2e-05,
+      "loss": 0.6914,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.7605392336845398,
+      "learning_rate": 2e-05,
+      "loss": 0.3038,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.8313522338867188,
+      "learning_rate": 2e-05,
+      "loss": 0.4746,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.02323991432785988,
+      "learning_rate": 2e-05,
+      "loss": 0.4973,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 5.001913070678711,
+      "learning_rate": 2e-05,
+      "loss": 0.3467,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.9565664529800415,
+      "learning_rate": 2e-05,
+      "loss": 0.4761,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.934812307357788,
+      "learning_rate": 2e-05,
+      "loss": 0.4241,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.334172010421753,
+      "learning_rate": 2e-05,
+      "loss": 0.3789,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.261927604675293,
+      "learning_rate": 2e-05,
+      "loss": 0.4741,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2191347477905408.0,
+      "train_loss": 0.4666449117660523,
+      "train_runtime": 64.5127,
+      "train_samples_per_second": 6.2,
+      "train_steps_per_second": 1.55
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2191347477905408.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/12_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4afee4d1a1c8be3faf3ec0f2f95a54a22205e4c00c40ee6186d5456d64fb8c
+size 791579754

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/12_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65f6deb5ebd27fae9647a6aa87cf2025b7df287976fe43f55d8659a0a3ec8206
+size 791579754

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/12_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf3b7b44d41068d7ec41829ea125b4836111669f344efe3b993d9d58829e674
+size 791579754

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/12_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c9fdf5d2bdd6f772d243ef751ff09df048c6154ab0b54061ba3b3698e51c93
+size 791579754

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/12_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1215abb22b5f3080310503750e09f5540b438773e81753bd7a1be135fb7ea31
+size 791578182

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/12_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8fa0b2d3b8067f842b2ac6fdde666556f9f0ad2f82fa22823a8f92213eb015a
+size 791579754

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/12_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccfd3fe6c7e97d0404cb0e743cc1812b686fe243246905373d7ab085be433fc8
+size 791578182

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/12_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4589a160b67e1c081ab2e0d17dbcdead79c6ba28c25b2e158ab6f6f3baf883b2
+size 791578182

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/12_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.2920405864715576,
+      "learning_rate": 2e-05,
+      "loss": 0.0386,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.0024220957420766354,
+      "learning_rate": 2e-05,
+      "loss": 0.0005,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.042690176516771317,
+      "learning_rate": 2e-05,
+      "loss": 0.0126,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.620497465133667,
+      "learning_rate": 2e-05,
+      "loss": 0.0201,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.22719046473503113,
+      "learning_rate": 2e-05,
+      "loss": 0.0145,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.07465826719999313,
+      "learning_rate": 2e-05,
+      "loss": 0.0023,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 4.26301908493042,
+      "learning_rate": 2e-05,
+      "loss": 0.604,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.5791594982147217,
+      "learning_rate": 2e-05,
+      "loss": 0.2624,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.459093302488327,
+      "learning_rate": 2e-05,
+      "loss": 0.1353,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.221980571746826,
+      "learning_rate": 2e-05,
+      "loss": 0.2825,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.17288897931575775,
+      "learning_rate": 2e-05,
+      "loss": 0.0922,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.26775988936424255,
+      "learning_rate": 2e-05,
+      "loss": 0.0136,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.4521391987800598,
+      "learning_rate": 2e-05,
+      "loss": 0.0704,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.4336092472076416,
+      "learning_rate": 2e-05,
+      "loss": 0.1329,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.026113972067832947,
+      "learning_rate": 2e-05,
+      "loss": 0.0106,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.06741499155759811,
+      "learning_rate": 2e-05,
+      "loss": 0.0105,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.10180412232875824,
+      "learning_rate": 2e-05,
+      "loss": 0.0316,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.2327575832605362,
+      "learning_rate": 2e-05,
+      "loss": 0.0671,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.21509437263011932,
+      "learning_rate": 2e-05,
+      "loss": 0.0205,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.175586462020874,
+      "learning_rate": 2e-05,
+      "loss": 0.0603,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.097664833068848,
+      "learning_rate": 2e-05,
+      "loss": 0.3459,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.04044518247246742,
+      "learning_rate": 2e-05,
+      "loss": 0.0197,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.225965976715088,
+      "learning_rate": 2e-05,
+      "loss": 0.1946,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.1212005615234375,
+      "learning_rate": 2e-05,
+      "loss": 0.0359,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.05873919650912285,
+      "learning_rate": 2e-05,
+      "loss": 0.0022,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.07613237202167511,
+      "learning_rate": 2e-05,
+      "loss": 0.0024,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.06085467338562012,
+      "learning_rate": 2e-05,
+      "loss": 0.0019,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.0594962015748024,
+      "learning_rate": 2e-05,
+      "loss": 0.002,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.022673513740301132,
+      "learning_rate": 2e-05,
+      "loss": 0.0023,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.09007851779460907,
+      "learning_rate": 2e-05,
+      "loss": 0.0046,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.006416500546038151,
+      "learning_rate": 2e-05,
+      "loss": 0.0075,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.008369038812816143,
+      "learning_rate": 2e-05,
+      "loss": 0.0033,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.07328344881534576,
+      "learning_rate": 2e-05,
+      "loss": 0.0019,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.7168121933937073,
+      "learning_rate": 2e-05,
+      "loss": 0.0257,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.006075312849134207,
+      "learning_rate": 2e-05,
+      "loss": 0.0004,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.027319282293319702,
+      "learning_rate": 2e-05,
+      "loss": 0.3296,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.05318591743707657,
+      "learning_rate": 2e-05,
+      "loss": 0.0021,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.008996729739010334,
+      "learning_rate": 2e-05,
+      "loss": 0.0185,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.26109060645103455,
+      "learning_rate": 2e-05,
+      "loss": 0.2289,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.0030557974241673946,
+      "learning_rate": 2e-05,
+      "loss": 0.0078,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.0699257180094719,
+      "learning_rate": 2e-05,
+      "loss": 0.0027,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.06251349300146103,
+      "learning_rate": 2e-05,
+      "loss": 0.0082,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.0034623832907527685,
+      "learning_rate": 2e-05,
+      "loss": 0.0086,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.582453727722168,
+      "learning_rate": 2e-05,
+      "loss": 0.2078,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.005348577164113522,
+      "learning_rate": 2e-05,
+      "loss": 0.0123,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.48420047760009766,
+      "learning_rate": 2e-05,
+      "loss": 0.0835,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.969717025756836,
+      "learning_rate": 2e-05,
+      "loss": 0.4384,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.030660836026072502,
+      "learning_rate": 2e-05,
+      "loss": 0.3863,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.05689483880996704,
+      "learning_rate": 2e-05,
+      "loss": 0.0024,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1647011041641235,
+      "learning_rate": 2e-05,
+      "loss": 0.0288,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5285302658662400.0,
+      "train_loss": 0.08597439825534821,
+      "train_runtime": 99.8483,
+      "train_samples_per_second": 4.006,
+      "train_steps_per_second": 1.002
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5285302658662400.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/13_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6045ff56789a2787a3639b748e163b57c539b585db7f974197cb4d2616f738a
+size 791579754

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/13_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2427fc2ce472d6b450bc333eea0aaa7ccba73863e4570b5e475ba2ed62a2674
+size 791579754

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/13_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abbe7751f467131dbb9b0ed8e7049d134839bcda9e91f70ccb1360425ea95344
+size 791579754

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/13_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b1a1314d2b743e3c567022ffc38e6db93d7a89db83083d75dc0ad60020b818
+size 791579754

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/13_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e198c8ca1c2f53cdf9ac3cda0051878b7582318d64562b4c88545fa94ec4647b
+size 791578182

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/13_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd3b9f4ca4475c87bc11a49a5debfc1ae0450831f2d55196a4cc9e31e1ea89f7
+size 791579754

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/13_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb14a353f3c12858de38a9f49f39ca99e3ce1f0800729d70182c9241f4c48689
+size 791578182

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/13_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33d113484917d92fca14d16bf0d06ce34c11e46aa6d5179c8dfc8ce893d1f19d
+size 791578182

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/13_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.778566360473633,
+      "learning_rate": 2e-05,
+      "loss": 0.3427,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.5951638221740723,
+      "learning_rate": 2e-05,
+      "loss": 0.2446,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.247312307357788,
+      "learning_rate": 2e-05,
+      "loss": 0.3885,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.3595407009124756,
+      "learning_rate": 2e-05,
+      "loss": 0.0998,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.8933051228523254,
+      "learning_rate": 2e-05,
+      "loss": 0.0959,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.20830616354942322,
+      "learning_rate": 2e-05,
+      "loss": 0.0334,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.4658172130584717,
+      "learning_rate": 2e-05,
+      "loss": 0.1042,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.962435722351074,
+      "learning_rate": 2e-05,
+      "loss": 0.429,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.4839186668395996,
+      "learning_rate": 2e-05,
+      "loss": 0.1982,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.563016414642334,
+      "learning_rate": 2e-05,
+      "loss": 1.2359,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 6.918004989624023,
+      "learning_rate": 2e-05,
+      "loss": 0.5588,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 7.100998878479004,
+      "learning_rate": 2e-05,
+      "loss": 0.2685,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.131011009216309,
+      "learning_rate": 2e-05,
+      "loss": 0.9571,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.1804964542388916,
+      "learning_rate": 2e-05,
+      "loss": 0.1269,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.373103380203247,
+      "learning_rate": 2e-05,
+      "loss": 0.2773,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.8673224449157715,
+      "learning_rate": 2e-05,
+      "loss": 0.1382,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.9214558601379395,
+      "learning_rate": 2e-05,
+      "loss": 0.2176,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.2953531742095947,
+      "learning_rate": 2e-05,
+      "loss": 0.3478,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.48850154876709,
+      "learning_rate": 2e-05,
+      "loss": 0.1105,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.431159257888794,
+      "learning_rate": 2e-05,
+      "loss": 0.2718,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.0679343119263649,
+      "learning_rate": 2e-05,
+      "loss": 0.2713,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.108593463897705,
+      "learning_rate": 2e-05,
+      "loss": 0.3638,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.01567334122955799,
+      "learning_rate": 2e-05,
+      "loss": 0.0121,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.7148890495300293,
+      "learning_rate": 2e-05,
+      "loss": 0.2139,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.34122204780578613,
+      "learning_rate": 2e-05,
+      "loss": 0.1943,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.237427234649658,
+      "learning_rate": 2e-05,
+      "loss": 0.4129,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.882807493209839,
+      "learning_rate": 2e-05,
+      "loss": 0.3954,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.5616434812545776,
+      "learning_rate": 2e-05,
+      "loss": 0.1976,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.07391391694545746,
+      "learning_rate": 2e-05,
+      "loss": 0.0307,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.12220025807619095,
+      "learning_rate": 2e-05,
+      "loss": 0.0502,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.797428846359253,
+      "learning_rate": 2e-05,
+      "loss": 0.184,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.5082601308822632,
+      "learning_rate": 2e-05,
+      "loss": 0.067,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.5079703330993652,
+      "learning_rate": 2e-05,
+      "loss": 0.3816,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 4.023115158081055,
+      "learning_rate": 2e-05,
+      "loss": 0.3118,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.5129783153533936,
+      "learning_rate": 2e-05,
+      "loss": 0.2305,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.47571924328804016,
+      "learning_rate": 2e-05,
+      "loss": 0.0345,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.9408183693885803,
+      "learning_rate": 2e-05,
+      "loss": 0.563,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.6250778436660767,
+      "learning_rate": 2e-05,
+      "loss": 0.1207,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.6771740913391113,
+      "learning_rate": 2e-05,
+      "loss": 0.2536,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.673983097076416,
+      "learning_rate": 2e-05,
+      "loss": 0.0871,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.856926441192627,
+      "learning_rate": 2e-05,
+      "loss": 0.1238,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 6.238300323486328,
+      "learning_rate": 2e-05,
+      "loss": 0.7711,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 6.600960731506348,
+      "learning_rate": 2e-05,
+      "loss": 0.6233,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.1156471967697144,
+      "learning_rate": 2e-05,
+      "loss": 0.135,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.041778326034546,
+      "learning_rate": 2e-05,
+      "loss": 0.1254,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.35611891746521,
+      "learning_rate": 2e-05,
+      "loss": 0.5919,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.3482422828674316,
+      "learning_rate": 2e-05,
+      "loss": 0.0314,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.902723789215088,
+      "learning_rate": 2e-05,
+      "loss": 0.2435,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.3907882273197174,
+      "learning_rate": 2e-05,
+      "loss": 0.3463,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.294113636016846,
+      "learning_rate": 2e-05,
+      "loss": 0.3237,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5322110830379008.0,
+      "train_loss": 0.2827692413330078,
+      "train_runtime": 110.5433,
+      "train_samples_per_second": 3.618,
+      "train_steps_per_second": 0.905
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5322110830379008.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/14_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b97ed5f57a071bb8d6d641af5ccd55ab115b7ba5ba65cef3293e05f4a0740e
+size 791579754

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/14_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e82666a5ee5251162c7a298a5785069be482719070acffabd09a3bea7951d9e8
+size 791579754

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/14_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a61109378eb3292593745ee8b3477e53e54e11da2a1e7de078f8ab0ab06d439
+size 791579754

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/14_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de2fa8c21d1b8a2894e8b4e5c1498375bd2be76dc3837828926973ea44ab50c3
+size 791579754

client_states_feddat_feddualMulti05pqfullfreeze_homoAggOnly_iter100_round5_hetero/14_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6b3863d8225a6a2c32460c2ca425e71237b4f897dc75dc369e7f9e807eae9df
+size 791578182