Upload folder using huggingface_hub

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a9f85ad249652150004f11a8edeb8cb682edfb7c260b1a3a7661d7a6a0bfe8
+size 184221358

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea76b394921e71d4f273d63ccbf2a91ea1600f2d7ce92ea586148b87ef987522
+size 184221358

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00558004043bac6060c1cb9b9edbe7d888314dc03530e726b9c843e9541fe635
+size 184221358

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b8ff3a15e2f67f72ce680eef53f3ec39d52eca5bbe934f9b057865091a9d328
+size 184221358

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c94b87ec7bdc096f517b2a952dd6aee70979217078bb6c98daaab77c566d935
+size 184220842

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a7691d3653185f7cc8fded73d48f785d1d21a557cf4c3cf43011f8460b0d72
+size 184221358

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4273f9b055b13427bbf4b96a430e8112924fd7655ccc1085b5671c2c9c41d547
+size 184220842

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf963d8c24fbdbced9f5e74f78122adf3d39f007bfedba7c3d00b372bd4fc247
+size 184220842

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_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": 3.6521377563476562,
+      "learning_rate": 2e-05,
+      "loss": 0.9124,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.1854143142700195,
+      "learning_rate": 2e-05,
+      "loss": 1.2244,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 9.416618347167969,
+      "learning_rate": 2e-05,
+      "loss": 1.5195,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 7.169552326202393,
+      "learning_rate": 2e-05,
+      "loss": 2.4595,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.279779076576233,
+      "learning_rate": 2e-05,
+      "loss": 0.3294,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.4748551845550537,
+      "learning_rate": 2e-05,
+      "loss": 0.4323,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.671616077423096,
+      "learning_rate": 2e-05,
+      "loss": 1.8652,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.7232145071029663,
+      "learning_rate": 2e-05,
+      "loss": 0.8714,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 6.445220470428467,
+      "learning_rate": 2e-05,
+      "loss": 0.8018,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.07907772064209,
+      "learning_rate": 2e-05,
+      "loss": 0.967,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.7406017780303955,
+      "learning_rate": 2e-05,
+      "loss": 0.5634,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.080334186553955,
+      "learning_rate": 2e-05,
+      "loss": 0.6188,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.12415885925293,
+      "learning_rate": 2e-05,
+      "loss": 1.1352,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.55212140083313,
+      "learning_rate": 2e-05,
+      "loss": 0.8936,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 6.542572498321533,
+      "learning_rate": 2e-05,
+      "loss": 1.3127,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.529738664627075,
+      "learning_rate": 2e-05,
+      "loss": 1.1697,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.4671977758407593,
+      "learning_rate": 2e-05,
+      "loss": 0.4724,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 4.34552001953125,
+      "learning_rate": 2e-05,
+      "loss": 1.4995,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 7.253231525421143,
+      "learning_rate": 2e-05,
+      "loss": 2.2877,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.232438802719116,
+      "learning_rate": 2e-05,
+      "loss": 1.4542,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.561795711517334,
+      "learning_rate": 2e-05,
+      "loss": 1.1743,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 18.807527542114258,
+      "learning_rate": 2e-05,
+      "loss": 1.192,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.2783002853393555,
+      "learning_rate": 2e-05,
+      "loss": 1.1392,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.0869314670562744,
+      "learning_rate": 2e-05,
+      "loss": 0.6687,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.1220808029174805,
+      "learning_rate": 2e-05,
+      "loss": 1.0115,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.2457854747772217,
+      "learning_rate": 2e-05,
+      "loss": 0.2398,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 8.409690856933594,
+      "learning_rate": 2e-05,
+      "loss": 2.2658,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.42133903503418,
+      "learning_rate": 2e-05,
+      "loss": 1.4105,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 26.248132705688477,
+      "learning_rate": 2e-05,
+      "loss": 1.6689,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.969575881958008,
+      "learning_rate": 2e-05,
+      "loss": 0.7785,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 7.6601243019104,
+      "learning_rate": 2e-05,
+      "loss": 1.3301,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.324950218200684,
+      "learning_rate": 2e-05,
+      "loss": 1.7731,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.2903269529342651,
+      "learning_rate": 2e-05,
+      "loss": 0.3627,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.8038797378540039,
+      "learning_rate": 2e-05,
+      "loss": 0.5118,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 9.203289985656738,
+      "learning_rate": 2e-05,
+      "loss": 1.121,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.5917932987213135,
+      "learning_rate": 2e-05,
+      "loss": 1.019,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.494030237197876,
+      "learning_rate": 2e-05,
+      "loss": 1.101,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.3323720693588257,
+      "learning_rate": 2e-05,
+      "loss": 0.8482,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.9421757459640503,
+      "learning_rate": 2e-05,
+      "loss": 1.2405,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.792178153991699,
+      "learning_rate": 2e-05,
+      "loss": 1.7825,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.410064935684204,
+      "learning_rate": 2e-05,
+      "loss": 1.1688,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.0299370288848877,
+      "learning_rate": 2e-05,
+      "loss": 1.198,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.611098051071167,
+      "learning_rate": 2e-05,
+      "loss": 1.0608,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.5845489501953125,
+      "learning_rate": 2e-05,
+      "loss": 1.2554,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.4315638542175293,
+      "learning_rate": 2e-05,
+      "loss": 0.4646,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.039827585220337,
+      "learning_rate": 2e-05,
+      "loss": 0.5792,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.686455011367798,
+      "learning_rate": 2e-05,
+      "loss": 0.8329,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.963765859603882,
+      "learning_rate": 2e-05,
+      "loss": 0.6777,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.584656715393066,
+      "learning_rate": 2e-05,
+      "loss": 1.3402,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.1249115467071533,
+      "learning_rate": 2e-05,
+      "loss": 0.6403,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5462826382524416.0,
+      "train_loss": 1.0929461765289306,
+      "train_runtime": 82.5201,
+      "train_samples_per_second": 4.847,
+      "train_steps_per_second": 1.212
+    }
+  ],
+  "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": 5462826382524416.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6569eba4caceacadc3ca94b7e39ef7477ca00b0e7076fc54acb0d4a35ca2333
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5559642c89410067723ebc2011d19f1b2fdf0e12f78a9f6077ac7c43a6d4bd65
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0670c35fd74a617b056f0e96441f736c6fb1450b3c5defcd190f6382d6e59032
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af884c6fb360f0c5b2653db2d2e96e1c4fb5c75c389f9c9633a01824235240e
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07572251387dd131249494d4e93caf05735d82c5692218bce3c9d22cb610bc97
+size 395786922

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c17bcdd12306796eb51cbed93dcd7440034d93bd85b9fe62197306db3e1b824
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf19f4a6d4ca8ad9ac748b121e4b5cb5b30dd70a9a6bf7c7200a4675dafafab
+size 395786922

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8f679a86d169855790bded159b2f975b55457b775e9212c15ff0d8a05f1c4f
+size 395786922

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_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": 6.6822428703308105,
+      "learning_rate": 2e-05,
+      "loss": 2.0218,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.877102375030518,
+      "learning_rate": 2e-05,
+      "loss": 1.2054,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.041037082672119,
+      "learning_rate": 2e-05,
+      "loss": 1.8849,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.418424367904663,
+      "learning_rate": 2e-05,
+      "loss": 0.9506,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.0498836040496826,
+      "learning_rate": 2e-05,
+      "loss": 1.2728,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.7078460454940796,
+      "learning_rate": 2e-05,
+      "loss": 0.9739,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.0234792232513428,
+      "learning_rate": 2e-05,
+      "loss": 1.1223,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.3307180404663086,
+      "learning_rate": 2e-05,
+      "loss": 1.2568,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.3364156484603882,
+      "learning_rate": 2e-05,
+      "loss": 0.8994,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.4729753732681274,
+      "learning_rate": 2e-05,
+      "loss": 1.1303,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.8265987634658813,
+      "learning_rate": 2e-05,
+      "loss": 1.0775,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.7694627046585083,
+      "learning_rate": 2e-05,
+      "loss": 1.0759,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.9681388139724731,
+      "learning_rate": 2e-05,
+      "loss": 0.9653,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.9351750612258911,
+      "learning_rate": 2e-05,
+      "loss": 0.8383,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.452039361000061,
+      "learning_rate": 2e-05,
+      "loss": 1.3589,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.3911502361297607,
+      "learning_rate": 2e-05,
+      "loss": 1.1124,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.0069334506988525,
+      "learning_rate": 2e-05,
+      "loss": 0.9875,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.940441608428955,
+      "learning_rate": 2e-05,
+      "loss": 1.2242,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.189831018447876,
+      "learning_rate": 2e-05,
+      "loss": 0.7673,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.779162883758545,
+      "learning_rate": 2e-05,
+      "loss": 0.9361,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.3907397985458374,
+      "learning_rate": 2e-05,
+      "loss": 1.0623,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.3832685947418213,
+      "learning_rate": 2e-05,
+      "loss": 1.1743,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.9638045430183411,
+      "learning_rate": 2e-05,
+      "loss": 0.9272,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.3544044494628906,
+      "learning_rate": 2e-05,
+      "loss": 0.6406,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.9859771728515625,
+      "learning_rate": 2e-05,
+      "loss": 1.2044,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.8015904426574707,
+      "learning_rate": 2e-05,
+      "loss": 1.7158,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.1716017723083496,
+      "learning_rate": 2e-05,
+      "loss": 1.2462,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.1024158000946045,
+      "learning_rate": 2e-05,
+      "loss": 0.5833,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.125066041946411,
+      "learning_rate": 2e-05,
+      "loss": 0.834,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.281691312789917,
+      "learning_rate": 2e-05,
+      "loss": 0.7629,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.6285910606384277,
+      "learning_rate": 2e-05,
+      "loss": 1.6069,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.122559070587158,
+      "learning_rate": 2e-05,
+      "loss": 0.734,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.352406620979309,
+      "learning_rate": 2e-05,
+      "loss": 1.3968,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.0700297355651855,
+      "learning_rate": 2e-05,
+      "loss": 1.4426,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.5523048639297485,
+      "learning_rate": 2e-05,
+      "loss": 1.1194,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.1062090396881104,
+      "learning_rate": 2e-05,
+      "loss": 1.0994,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.9081668257713318,
+      "learning_rate": 2e-05,
+      "loss": 0.8165,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.4344611167907715,
+      "learning_rate": 2e-05,
+      "loss": 1.0179,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.473633289337158,
+      "learning_rate": 2e-05,
+      "loss": 0.9443,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.998819351196289,
+      "learning_rate": 2e-05,
+      "loss": 1.4675,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.3815733194351196,
+      "learning_rate": 2e-05,
+      "loss": 0.6615,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.8155826926231384,
+      "learning_rate": 2e-05,
+      "loss": 0.9048,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.156865358352661,
+      "learning_rate": 2e-05,
+      "loss": 1.096,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.0479371547698975,
+      "learning_rate": 2e-05,
+      "loss": 1.0649,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.5641653537750244,
+      "learning_rate": 2e-05,
+      "loss": 1.158,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.1641392707824707,
+      "learning_rate": 2e-05,
+      "loss": 0.9491,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.590826988220215,
+      "learning_rate": 2e-05,
+      "loss": 0.9922,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.219031810760498,
+      "learning_rate": 2e-05,
+      "loss": 0.9005,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.3779208660125732,
+      "learning_rate": 2e-05,
+      "loss": 0.9138,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.2598304748535156,
+      "learning_rate": 2e-05,
+      "loss": 1.5983,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.3180566698459136e+16,
+      "train_loss": 1.1019461822509766,
+      "train_runtime": 178.6133,
+      "train_samples_per_second": 2.239,
+      "train_steps_per_second": 0.56
+    }
+  ],
+  "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": 1.3180566698459136e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36ab37f964f87f5d413c5d8d8ef72efebc51eb7f115e5d5a68a6659a9689b111
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e4fedce8bb052c09c44e585b9250c18eb915087161d3b58e0ef97b35dc501fc
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00a3f4e3a99e19fda64e4f418ab5cb2181744f4aa2f1e5fe41f58abe1409a6bb
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4b21205e6ebaa14cc1a6fd37a48919e1e46fea8fd2ac25dd0de35170b7bd53
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a68ebf09d80e1800c5605a5939ab6118e7d90b75af0e229b5e9f6b50438a535
+size 395786922

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a3a050fa017fce52d4ef3e8e95ee1d647bf51950d630754ad371425440f126
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0442f7a0096239d39f2410988da66f3190d005463ac11dc935d7df2075d53000
+size 395786922

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4ee85f082da48767836c11433a044025214a61215a6a9829537d3ebcf8ab28a
+size 395786922

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_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": 6.870771408081055,
+      "learning_rate": 2e-05,
+      "loss": 1.1654,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.3432737588882446,
+      "learning_rate": 2e-05,
+      "loss": 0.3689,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.0168616771698,
+      "learning_rate": 2e-05,
+      "loss": 0.6014,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.9527008533477783,
+      "learning_rate": 2e-05,
+      "loss": 0.5146,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.516590595245361,
+      "learning_rate": 2e-05,
+      "loss": 1.2873,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.016819477081299,
+      "learning_rate": 2e-05,
+      "loss": 1.1231,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 4.7131667137146,
+      "learning_rate": 2e-05,
+      "loss": 1.3733,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.375880241394043,
+      "learning_rate": 2e-05,
+      "loss": 1.113,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.5119330883026123,
+      "learning_rate": 2e-05,
+      "loss": 1.1057,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.607441782951355,
+      "learning_rate": 2e-05,
+      "loss": 0.9519,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.930934190750122,
+      "learning_rate": 2e-05,
+      "loss": 1.3872,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.963341474533081,
+      "learning_rate": 2e-05,
+      "loss": 1.1208,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.2240748405456543,
+      "learning_rate": 2e-05,
+      "loss": 1.2998,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.161014556884766,
+      "learning_rate": 2e-05,
+      "loss": 1.1577,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.3142142295837402,
+      "learning_rate": 2e-05,
+      "loss": 0.6747,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.635556221008301,
+      "learning_rate": 2e-05,
+      "loss": 0.6059,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.6338635683059692,
+      "learning_rate": 2e-05,
+      "loss": 0.7202,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 6.789937496185303,
+      "learning_rate": 2e-05,
+      "loss": 1.0048,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.1352427005767822,
+      "learning_rate": 2e-05,
+      "loss": 0.555,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.8702523708343506,
+      "learning_rate": 2e-05,
+      "loss": 0.7508,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.3762640953063965,
+      "learning_rate": 2e-05,
+      "loss": 0.9208,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.6130523681640625,
+      "learning_rate": 2e-05,
+      "loss": 0.3937,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.936488389968872,
+      "learning_rate": 2e-05,
+      "loss": 0.7048,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.49044668674469,
+      "learning_rate": 2e-05,
+      "loss": 0.6971,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 5.2073540687561035,
+      "learning_rate": 2e-05,
+      "loss": 1.0757,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.5597954988479614,
+      "learning_rate": 2e-05,
+      "loss": 0.6179,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.703416347503662,
+      "learning_rate": 2e-05,
+      "loss": 1.0074,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.0945237874984741,
+      "learning_rate": 2e-05,
+      "loss": 0.4657,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.552534341812134,
+      "learning_rate": 2e-05,
+      "loss": 0.6798,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.3692915439605713,
+      "learning_rate": 2e-05,
+      "loss": 0.8334,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 11.139009475708008,
+      "learning_rate": 2e-05,
+      "loss": 2.1337,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.4873778820037842,
+      "learning_rate": 2e-05,
+      "loss": 0.928,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.482325315475464,
+      "learning_rate": 2e-05,
+      "loss": 1.2874,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.16709566116333,
+      "learning_rate": 2e-05,
+      "loss": 1.3439,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.6613510847091675,
+      "learning_rate": 2e-05,
+      "loss": 0.7644,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.898678183555603,
+      "learning_rate": 2e-05,
+      "loss": 0.7386,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.513575553894043,
+      "learning_rate": 2e-05,
+      "loss": 1.1844,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.258788108825684,
+      "learning_rate": 2e-05,
+      "loss": 1.5245,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.4021708965301514,
+      "learning_rate": 2e-05,
+      "loss": 0.3279,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.6789686679840088,
+      "learning_rate": 2e-05,
+      "loss": 0.875,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 6.114107131958008,
+      "learning_rate": 2e-05,
+      "loss": 0.8719,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.4944007396697998,
+      "learning_rate": 2e-05,
+      "loss": 0.4226,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.7887576818466187,
+      "learning_rate": 2e-05,
+      "loss": 0.6338,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.184706687927246,
+      "learning_rate": 2e-05,
+      "loss": 0.9749,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.630242943763733,
+      "learning_rate": 2e-05,
+      "loss": 0.5934,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.0497238636016846,
+      "learning_rate": 2e-05,
+      "loss": 0.7355,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.646782159805298,
+      "learning_rate": 2e-05,
+      "loss": 1.2263,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 6.876937389373779,
+      "learning_rate": 2e-05,
+      "loss": 1.7028,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.737856388092041,
+      "learning_rate": 2e-05,
+      "loss": 1.6059,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.019500255584717,
+      "learning_rate": 2e-05,
+      "loss": 1.5219,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.4596800069500928e+16,
+      "train_loss": 0.9534926033020019,
+      "train_runtime": 189.5869,
+      "train_samples_per_second": 2.11,
+      "train_steps_per_second": 0.527
+    }
+  ],
+  "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": 1.4596800069500928e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7122c199f1685bb1a74025dcf2a16493cb1292b7a8d075725d60cde86d3870
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f172cfe0be8188d745d41b5b0fc3f11eecc304d89505d8f228da66ec3eed1834
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac125b586496530fd8e4cf04392dd9cc5085ed188cab4305e9509aa7fe889b8a
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c275561a21146dc01e148f0f759f776d44dc0edaaefa22d090d45a5d95be37
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc62ff818f1b82e0661b2e93a440c072bf11e0dbc954613d6773e441debe91c2
+size 395786922

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:368ab73062cd440e97ca0c043938f57550e6e5c743360d21b6214adfc29f2934
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1157bed0195c6b0aeab9f8253ca1857539e444df686b4a20c7f1411e0978f42f
+size 395786922

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0d8d764ab44699b83b162e89f42eba1f395d4531ed75f820a2bbd83f38716ab
+size 395786922

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_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": 4.745977401733398,
+      "learning_rate": 2e-05,
+      "loss": 1.3564,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.718540668487549,
+      "learning_rate": 2e-05,
+      "loss": 1.8232,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.8267402648925781,
+      "learning_rate": 2e-05,
+      "loss": 0.9686,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 8.296893119812012,
+      "learning_rate": 2e-05,
+      "loss": 1.3076,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.6323120594024658,
+      "learning_rate": 2e-05,
+      "loss": 0.8773,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.4877943992614746,
+      "learning_rate": 2e-05,
+      "loss": 0.5634,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.0363566875457764,
+      "learning_rate": 2e-05,
+      "loss": 0.7835,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.1087441444396973,
+      "learning_rate": 2e-05,
+      "loss": 1.201,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.4909172058105469,
+      "learning_rate": 2e-05,
+      "loss": 1.0469,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.946487307548523,
+      "learning_rate": 2e-05,
+      "loss": 0.678,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 5.958488464355469,
+      "learning_rate": 2e-05,
+      "loss": 0.9224,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 7.257498264312744,
+      "learning_rate": 2e-05,
+      "loss": 2.0242,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.5010510683059692,
+      "learning_rate": 2e-05,
+      "loss": 0.4853,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.8962352275848389,
+      "learning_rate": 2e-05,
+      "loss": 1.5902,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.3464363813400269,
+      "learning_rate": 2e-05,
+      "loss": 1.78,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.3457775115966797,
+      "learning_rate": 2e-05,
+      "loss": 0.8797,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.346909761428833,
+      "learning_rate": 2e-05,
+      "loss": 1.3902,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.441206932067871,
+      "learning_rate": 2e-05,
+      "loss": 1.1876,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.8529553413391113,
+      "learning_rate": 2e-05,
+      "loss": 1.4603,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.2910548448562622,
+      "learning_rate": 2e-05,
+      "loss": 1.0059,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.868272542953491,
+      "learning_rate": 2e-05,
+      "loss": 0.9323,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.067530393600464,
+      "learning_rate": 2e-05,
+      "loss": 1.0432,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.5052028894424438,
+      "learning_rate": 2e-05,
+      "loss": 1.0481,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.7457492351531982,
+      "learning_rate": 2e-05,
+      "loss": 1.0176,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.292689561843872,
+      "learning_rate": 2e-05,
+      "loss": 1.4312,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.9708192348480225,
+      "learning_rate": 2e-05,
+      "loss": 0.5481,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.5880157947540283,
+      "learning_rate": 2e-05,
+      "loss": 1.3568,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.6197189092636108,
+      "learning_rate": 2e-05,
+      "loss": 1.1299,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.0218310356140137,
+      "learning_rate": 2e-05,
+      "loss": 1.0411,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.4867467880249023,
+      "learning_rate": 2e-05,
+      "loss": 0.7482,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.555323600769043,
+      "learning_rate": 2e-05,
+      "loss": 0.7469,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.1048567295074463,
+      "learning_rate": 2e-05,
+      "loss": 1.1579,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.328464150428772,
+      "learning_rate": 2e-05,
+      "loss": 0.99,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 7.819065093994141,
+      "learning_rate": 2e-05,
+      "loss": 1.2058,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.0296525955200195,
+      "learning_rate": 2e-05,
+      "loss": 0.8083,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.6068267822265625,
+      "learning_rate": 2e-05,
+      "loss": 0.8039,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 6.394163608551025,
+      "learning_rate": 2e-05,
+      "loss": 0.6218,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.4921457767486572,
+      "learning_rate": 2e-05,
+      "loss": 1.1248,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.759273648262024,
+      "learning_rate": 2e-05,
+      "loss": 1.4136,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.1382907629013062,
+      "learning_rate": 2e-05,
+      "loss": 0.5686,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.056369304656982,
+      "learning_rate": 2e-05,
+      "loss": 1.5137,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.4470815658569336,
+      "learning_rate": 2e-05,
+      "loss": 1.7578,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.2486741542816162,
+      "learning_rate": 2e-05,
+      "loss": 1.5913,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.3589069843292236,
+      "learning_rate": 2e-05,
+      "loss": 1.1481,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.026803731918335,
+      "learning_rate": 2e-05,
+      "loss": 0.8436,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.013026475906372,
+      "learning_rate": 2e-05,
+      "loss": 0.8821,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.4985859394073486,
+      "learning_rate": 2e-05,
+      "loss": 0.9763,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.2695242166519165,
+      "learning_rate": 2e-05,
+      "loss": 0.7675,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.2971454858779907,
+      "learning_rate": 2e-05,
+      "loss": 0.5018,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9557787775993347,
+      "learning_rate": 2e-05,
+      "loss": 0.356,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2.037956633375539e+16,
+      "train_loss": 1.0681575393676759,
+      "train_runtime": 255.3992,
+      "train_samples_per_second": 1.566,
+      "train_steps_per_second": 0.392
+    }
+  ],
+  "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": 2.037956633375539e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da4efbf8561fa16b07dd93ceed8bbdfce661a9623cfab93215b871bc4f452f55
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9076ccaa700add0e367f330c40e245ffce262b97e5e27b08574818bbc56248
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2643640e33c16d508ac52c97c466efcb912273f978e83c381c15253f9d845879
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e8e9ac1dfd70c0bc3e06390b003d2e51a809fab567bfd1227e15bc5d70d94e6
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ec345f36df14b551141b1490f28ded2c25ee81d46cd5ac725576250eb4c73c
+size 395786922

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b999b0b3bb375163b5c76fec2a7819f40d039d1ea8499787f09e4160f2c6321
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b228eba0cf76cb2c13223cce56c70a16ec43bb0f9c2f99b288f3f7d79289ca
+size 395786922

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386bb6df7b10275e59bf638d5b90174dc6cc84570dcd69e553effe6d25f3971a
+size 395786922

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_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": 0.9645354151725769,
+      "learning_rate": 2e-05,
+      "loss": 0.298,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.9610158801078796,
+      "learning_rate": 2e-05,
+      "loss": 0.5154,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 5.084799289703369,
+      "learning_rate": 2e-05,
+      "loss": 1.4171,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.795111358165741,
+      "learning_rate": 2e-05,
+      "loss": 0.378,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.510159969329834,
+      "learning_rate": 2e-05,
+      "loss": 1.0449,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.3363721370697021,
+      "learning_rate": 2e-05,
+      "loss": 1.1503,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3838180601596832,
+      "learning_rate": 2e-05,
+      "loss": 0.4465,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.380025863647461,
+      "learning_rate": 2e-05,
+      "loss": 1.0334,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.82670658826828,
+      "learning_rate": 2e-05,
+      "loss": 0.948,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.81815242767334,
+      "learning_rate": 2e-05,
+      "loss": 0.4274,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 6.099972724914551,
+      "learning_rate": 2e-05,
+      "loss": 1.4633,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.6731679439544678,
+      "learning_rate": 2e-05,
+      "loss": 1.7556,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 7.249082088470459,
+      "learning_rate": 2e-05,
+      "loss": 2.2839,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.642025947570801,
+      "learning_rate": 2e-05,
+      "loss": 2.106,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.9788825511932373,
+      "learning_rate": 2e-05,
+      "loss": 1.9205,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.3716607093811035,
+      "learning_rate": 2e-05,
+      "loss": 0.8155,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.929107904434204,
+      "learning_rate": 2e-05,
+      "loss": 1.0665,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.3469587564468384,
+      "learning_rate": 2e-05,
+      "loss": 1.8441,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.9391975402832031,
+      "learning_rate": 2e-05,
+      "loss": 0.5247,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.4839298725128174,
+      "learning_rate": 2e-05,
+      "loss": 1.1509,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.07216771692037582,
+      "learning_rate": 2e-05,
+      "loss": 0.4862,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.357652187347412,
+      "learning_rate": 2e-05,
+      "loss": 1.6776,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.6733430624008179,
+      "learning_rate": 2e-05,
+      "loss": 1.0793,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.3932052850723267,
+      "learning_rate": 2e-05,
+      "loss": 0.8717,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.1675429344177246,
+      "learning_rate": 2e-05,
+      "loss": 0.9573,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.872215747833252,
+      "learning_rate": 2e-05,
+      "loss": 1.9359,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.6550145745277405,
+      "learning_rate": 2e-05,
+      "loss": 0.7791,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.2394981384277344,
+      "learning_rate": 2e-05,
+      "loss": 0.4135,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.0308785438537598,
+      "learning_rate": 2e-05,
+      "loss": 1.1602,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.5475999116897583,
+      "learning_rate": 2e-05,
+      "loss": 0.7825,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.8651981353759766,
+      "learning_rate": 2e-05,
+      "loss": 0.7453,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.137701511383057,
+      "learning_rate": 2e-05,
+      "loss": 1.671,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.767425060272217,
+      "learning_rate": 2e-05,
+      "loss": 1.8104,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.6192474365234375,
+      "learning_rate": 2e-05,
+      "loss": 0.2963,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.698683738708496,
+      "learning_rate": 2e-05,
+      "loss": 1.2459,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.881882429122925,
+      "learning_rate": 2e-05,
+      "loss": 1.1608,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.1753883361816406,
+      "learning_rate": 2e-05,
+      "loss": 1.1475,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.591700792312622,
+      "learning_rate": 2e-05,
+      "loss": 1.2196,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.664095878601074,
+      "learning_rate": 2e-05,
+      "loss": 1.1802,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.098962306976318,
+      "learning_rate": 2e-05,
+      "loss": 1.1402,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 5.9037041664123535,
+      "learning_rate": 2e-05,
+      "loss": 1.6653,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 8.761261940002441,
+      "learning_rate": 2e-05,
+      "loss": 2.4346,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.132128953933716,
+      "learning_rate": 2e-05,
+      "loss": 0.6303,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.608686447143555,
+      "learning_rate": 2e-05,
+      "loss": 1.6204,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.784377098083496,
+      "learning_rate": 2e-05,
+      "loss": 0.7977,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.5807340145111084,
+      "learning_rate": 2e-05,
+      "loss": 1.4101,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.2921392917633057,
+      "learning_rate": 2e-05,
+      "loss": 0.602,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.1056969165802,
+      "learning_rate": 2e-05,
+      "loss": 1.529,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.264127254486084,
+      "learning_rate": 2e-05,
+      "loss": 0.6878,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.0558204650878906,
+      "learning_rate": 2e-05,
+      "loss": 1.177,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.920155780330291e+16,
+      "train_loss": 1.1381040620803833,
+      "train_runtime": 251.4298,
+      "train_samples_per_second": 1.591,
+      "train_steps_per_second": 0.398
+    }
+  ],
+  "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": 1.920155780330291e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b64ad395307586cb119abd8241f2ee156970c97c52dddc477846547188f3166
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b4ec9bed5a971ab8fb4b12852cbd0a03ab61ad6650b4d6d81b8782fe7d2be2
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccbfa3998fb1ca7adc59e7d6b29054e70affbc6a1e7d5e5998f68ea4397ba293
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b24774acfa6131248395c91b176a2fe460b9fbd5351a2f835b22ea927444c2d9
+size 395787774

client_states_fedMultipqfull_sft2_pca_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85abe8da232a71fc77906728939cba0a5e17162c26792432cd12088091885c08
+size 395786922