Upload folder using huggingface_hub

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fb926652ce35e0a05312b5494eddf9964db8020f8cdac05956cd89021dbd5b6
+size 184221358

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7caae9977c113301ce074be4b1020f4c3a5bd3ba40df7a141e6f7c8c4a39a667
+size 184221358

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7114005e2a035f4fa3174c7f27375b4c823f9a0ad9618622fc9c2089edf820e
+size 184221358

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8995b091a50fa5748c96ae6966e37a63d6cccd78fd8e361be409252664e8025d
+size 184221358

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b468782bd8bdef139b6ee7bf3c59295cdc227920073907511be9c15fcb17ca9
+size 184220842

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df1e79c8ee8273ad82921275ca1df74ff6aa36480e981f94029713bd96785d02
+size 184221358

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:758d5975539362897379095e1f4985215f7c32318ae9e9d654eb865a74191c2f
+size 184220842

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94daf02adf121f22d56ae58bf5890b8b97d15cfe7434381426c0c7fb39daf360
+size 184220842

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_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": 17.057233810424805,
+      "learning_rate": 2e-05,
+      "loss": 1.429,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 16.035552978515625,
+      "learning_rate": 2e-05,
+      "loss": 1.279,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 17.284889221191406,
+      "learning_rate": 2e-05,
+      "loss": 0.3961,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.228580474853516,
+      "learning_rate": 2e-05,
+      "loss": 0.1003,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 9.274914741516113,
+      "learning_rate": 2e-05,
+      "loss": 0.4737,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 17.14118194580078,
+      "learning_rate": 2e-05,
+      "loss": 0.7475,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 11.042923927307129,
+      "learning_rate": 2e-05,
+      "loss": 0.3686,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 27.170347213745117,
+      "learning_rate": 2e-05,
+      "loss": 1.1992,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 24.550939559936523,
+      "learning_rate": 2e-05,
+      "loss": 1.9915,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 22.20884895324707,
+      "learning_rate": 2e-05,
+      "loss": 1.3349,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.0631847381591797,
+      "learning_rate": 2e-05,
+      "loss": 0.0348,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 18.128084182739258,
+      "learning_rate": 2e-05,
+      "loss": 0.7203,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.3488261699676514,
+      "learning_rate": 2e-05,
+      "loss": 0.2416,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.432104110717773,
+      "learning_rate": 2e-05,
+      "loss": 0.2479,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.3399593830108643,
+      "learning_rate": 2e-05,
+      "loss": 0.5576,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 30.939563751220703,
+      "learning_rate": 2e-05,
+      "loss": 1.0148,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 6.3796162605285645,
+      "learning_rate": 2e-05,
+      "loss": 0.1672,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 19.28791046142578,
+      "learning_rate": 2e-05,
+      "loss": 0.502,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 6.22046422958374,
+      "learning_rate": 2e-05,
+      "loss": 1.6969,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 7.716579437255859,
+      "learning_rate": 2e-05,
+      "loss": 0.1707,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.418802499771118,
+      "learning_rate": 2e-05,
+      "loss": 0.0486,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 17.938234329223633,
+      "learning_rate": 2e-05,
+      "loss": 1.3497,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5611051321029663,
+      "learning_rate": 2e-05,
+      "loss": 0.3303,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 19.7348690032959,
+      "learning_rate": 2e-05,
+      "loss": 2.2087,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.4957550764083862,
+      "learning_rate": 2e-05,
+      "loss": 0.1454,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 24.74273109436035,
+      "learning_rate": 2e-05,
+      "loss": 0.5816,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 7.927778720855713,
+      "learning_rate": 2e-05,
+      "loss": 0.8075,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 9.316579818725586,
+      "learning_rate": 2e-05,
+      "loss": 0.2555,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 23.200603485107422,
+      "learning_rate": 2e-05,
+      "loss": 1.7893,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 9.340189933776855,
+      "learning_rate": 2e-05,
+      "loss": 0.2063,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.1941299438476562,
+      "learning_rate": 2e-05,
+      "loss": 0.383,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.817136287689209,
+      "learning_rate": 2e-05,
+      "loss": 0.1845,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.088149309158325,
+      "learning_rate": 2e-05,
+      "loss": 0.4042,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 18.703197479248047,
+      "learning_rate": 2e-05,
+      "loss": 1.7414,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 27.611318588256836,
+      "learning_rate": 2e-05,
+      "loss": 1.1281,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 12.825926780700684,
+      "learning_rate": 2e-05,
+      "loss": 0.247,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 23.934783935546875,
+      "learning_rate": 2e-05,
+      "loss": 2.9569,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 22.396121978759766,
+      "learning_rate": 2e-05,
+      "loss": 0.9961,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.7141060829162598,
+      "learning_rate": 2e-05,
+      "loss": 0.8012,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 9.97252368927002,
+      "learning_rate": 2e-05,
+      "loss": 0.9497,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 9.308930397033691,
+      "learning_rate": 2e-05,
+      "loss": 0.8887,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 24.823070526123047,
+      "learning_rate": 2e-05,
+      "loss": 0.7886,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 9.218820571899414,
+      "learning_rate": 2e-05,
+      "loss": 0.3562,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 18.449987411499023,
+      "learning_rate": 2e-05,
+      "loss": 1.541,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 16.013731002807617,
+      "learning_rate": 2e-05,
+      "loss": 0.6323,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.9226857423782349,
+      "learning_rate": 2e-05,
+      "loss": 0.7785,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 20.768098831176758,
+      "learning_rate": 2e-05,
+      "loss": 2.1707,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 15.813720703125,
+      "learning_rate": 2e-05,
+      "loss": 2.0121,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 10.63700008392334,
+      "learning_rate": 2e-05,
+      "loss": 1.3873,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.4819769859313965,
+      "learning_rate": 2e-05,
+      "loss": 0.3152,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2053257199353856.0,
+      "train_loss": 0.8611783313751221,
+      "train_runtime": 68.6543,
+      "train_samples_per_second": 5.826,
+      "train_steps_per_second": 1.457
+    }
+  ],
+  "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": 2053257199353856.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca74ac08c1abd68b9d1290bfe17da61a2be5f55590d9ee9059ad0d3402be3dca
+size 184221358

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e601ae3c4d027e754440222794168a4e6deee2e5df34449ff791b2b7ad939fd2
+size 184221358

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:324bdc75d945d4ad9e421699d04315516875c461dde7f278d13774d5d7499b37
+size 184221358

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85533acb939799e62a366afae327de2848a4d6797c8a06d7e9f31db464521bc
+size 184221358

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:390fb7105b816027c14f1a3608907ae0fa81d694b1e5f5fcfd9fafdcd70aa039
+size 184220842

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bdb2027dfc6b74f50a639dfe00e9cd95eed0769b7c9663ced68be53d0f546cf
+size 184221358

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8bea59d5bceb723869881b1bd19e43450378ac497817227fc22c25226466ec
+size 184220842

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66fae50b48e525cdd9d3ed60711b6874b0edd3168b215621a61867f4b091488
+size 184220842

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_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": 0.044703781604766846,
+      "learning_rate": 2e-05,
+      "loss": 0.0018,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.21178390085697174,
+      "learning_rate": 2e-05,
+      "loss": 0.0487,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.3870941400527954,
+      "learning_rate": 2e-05,
+      "loss": 0.0198,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.3502098321914673,
+      "learning_rate": 2e-05,
+      "loss": 0.0183,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.034831710159778595,
+      "learning_rate": 2e-05,
+      "loss": 0.0011,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.03862101957201958,
+      "learning_rate": 2e-05,
+      "loss": 0.0207,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.032296374440193176,
+      "learning_rate": 2e-05,
+      "loss": 0.0012,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.4266643524169922,
+      "learning_rate": 2e-05,
+      "loss": 0.0253,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.08606778085231781,
+      "learning_rate": 2e-05,
+      "loss": 0.072,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.06966991722583771,
+      "learning_rate": 2e-05,
+      "loss": 0.0017,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.03714023157954216,
+      "learning_rate": 2e-05,
+      "loss": 0.0019,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.02337123453617096,
+      "learning_rate": 2e-05,
+      "loss": 0.0006,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.5694215297698975,
+      "learning_rate": 2e-05,
+      "loss": 0.0298,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.07775002717971802,
+      "learning_rate": 2e-05,
+      "loss": 0.0013,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.19765383005142212,
+      "learning_rate": 2e-05,
+      "loss": 0.0035,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.5510034561157227,
+      "learning_rate": 2e-05,
+      "loss": 0.0073,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 13.539923667907715,
+      "learning_rate": 2e-05,
+      "loss": 0.145,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.01147350762039423,
+      "learning_rate": 2e-05,
+      "loss": 0.0003,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.164375901222229,
+      "learning_rate": 2e-05,
+      "loss": 0.0139,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.3746843934059143,
+      "learning_rate": 2e-05,
+      "loss": 0.0043,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.7776218056678772,
+      "learning_rate": 2e-05,
+      "loss": 0.0087,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 8.505824089050293,
+      "learning_rate": 2e-05,
+      "loss": 0.1081,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.033780287951231,
+      "learning_rate": 2e-05,
+      "loss": 0.0011,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.06528189778327942,
+      "learning_rate": 2e-05,
+      "loss": 0.0012,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.014482088387012482,
+      "learning_rate": 2e-05,
+      "loss": 0.0009,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.011595295742154121,
+      "learning_rate": 2e-05,
+      "loss": 0.0204,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.080960988998413,
+      "learning_rate": 2e-05,
+      "loss": 0.0326,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.01212055329233408,
+      "learning_rate": 2e-05,
+      "loss": 0.0035,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.06828805804252625,
+      "learning_rate": 2e-05,
+      "loss": 1.158,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.109000563621521,
+      "learning_rate": 2e-05,
+      "loss": 0.56,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.07980120927095413,
+      "learning_rate": 2e-05,
+      "loss": 0.0018,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.03460214287042618,
+      "learning_rate": 2e-05,
+      "loss": 0.0016,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.26421451568603516,
+      "learning_rate": 2e-05,
+      "loss": 0.0039,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.6567984819412231,
+      "learning_rate": 2e-05,
+      "loss": 0.014,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.27901744842529297,
+      "learning_rate": 2e-05,
+      "loss": 0.005,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.11144458502531052,
+      "learning_rate": 2e-05,
+      "loss": 0.0021,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.48066651821136475,
+      "learning_rate": 2e-05,
+      "loss": 0.0092,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.11648140102624893,
+      "learning_rate": 2e-05,
+      "loss": 0.002,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 20.70526885986328,
+      "learning_rate": 2e-05,
+      "loss": 0.7939,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.033763304352760315,
+      "learning_rate": 2e-05,
+      "loss": 0.0039,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.23296765983104706,
+      "learning_rate": 2e-05,
+      "loss": 0.0037,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.014723770320415497,
+      "learning_rate": 2e-05,
+      "loss": 0.0013,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.04044659435749054,
+      "learning_rate": 2e-05,
+      "loss": 1.072,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.08691377937793732,
+      "learning_rate": 2e-05,
+      "loss": 0.0027,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.193515419960022,
+      "learning_rate": 2e-05,
+      "loss": 0.0172,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.8346377015113831,
+      "learning_rate": 2e-05,
+      "loss": 0.0163,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1634865552186966,
+      "learning_rate": 2e-05,
+      "loss": 0.0247,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.09125829488039017,
+      "learning_rate": 2e-05,
+      "loss": 0.0022,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.31049448251724243,
+      "learning_rate": 2e-05,
+      "loss": 0.0063,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.11262838542461395,
+      "learning_rate": 2e-05,
+      "loss": 0.0034,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2069634366832640.0,
+      "train_loss": 0.08600348770618439,
+      "train_runtime": 66.1485,
+      "train_samples_per_second": 6.047,
+      "train_steps_per_second": 1.512
+    }
+  ],
+  "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": 2069634366832640.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d47000144da5957274573349c513aa2bbc44407569c05785a90459f5ac3f0c0e
+size 395787774

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a881a1167e05f4bb1c28b078b87e77968acbc8c56db1bf928c726a04964e7e
+size 395787774

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a537003728ce427afb053e9a6a069d6e7d1c0aa1bdcff963a187625d58e33f86
+size 395787774

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c5bd0b86de9567e4237d6aa335cf9796f736f1c766222ad824d129eaec1177c
+size 395787774

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b3aa9d567bb1ab42a91635afd35fca8d6ecb703aa49c5b847d5e73f57ecba48
+size 395786922

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a880648c69088bd3ef5d7a6c5fbf12b01fec1b8e2655935c9224f785ae6083f
+size 395787774

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e31f3e427d90bc0f398147e7d418d4276737ef3705c826ccbd35bb5f7b2e6d9
+size 395786922

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e046fc5467181d81dda8a921ea4ea3e4e661d09a6e7f9ead4ea35bb1610d83
+size 395786922

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_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": 1.7190805673599243,
+      "learning_rate": 2e-05,
+      "loss": 0.1468,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 8.977873802185059,
+      "learning_rate": 2e-05,
+      "loss": 1.2143,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.756490468978882,
+      "learning_rate": 2e-05,
+      "loss": 1.3066,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 5.235644340515137,
+      "learning_rate": 2e-05,
+      "loss": 1.1405,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 7.524799823760986,
+      "learning_rate": 2e-05,
+      "loss": 0.6738,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 9.593109130859375,
+      "learning_rate": 2e-05,
+      "loss": 1.0312,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.5453864932060242,
+      "learning_rate": 2e-05,
+      "loss": 0.3309,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.725948333740234,
+      "learning_rate": 2e-05,
+      "loss": 0.4419,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.698237419128418,
+      "learning_rate": 2e-05,
+      "loss": 0.4275,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 8.3702392578125,
+      "learning_rate": 2e-05,
+      "loss": 1.8615,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.290210008621216,
+      "learning_rate": 2e-05,
+      "loss": 0.2323,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 9.233611106872559,
+      "learning_rate": 2e-05,
+      "loss": 0.3407,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 10.91540813446045,
+      "learning_rate": 2e-05,
+      "loss": 0.9,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 11.868660926818848,
+      "learning_rate": 2e-05,
+      "loss": 0.6023,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.7284384965896606,
+      "learning_rate": 2e-05,
+      "loss": 0.1738,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 6.5820417404174805,
+      "learning_rate": 2e-05,
+      "loss": 0.6303,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.786893844604492,
+      "learning_rate": 2e-05,
+      "loss": 0.6713,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.7642679214477539,
+      "learning_rate": 2e-05,
+      "loss": 0.1098,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 5.1546454429626465,
+      "learning_rate": 2e-05,
+      "loss": 1.1471,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 11.79127311706543,
+      "learning_rate": 2e-05,
+      "loss": 0.8145,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.426208019256592,
+      "learning_rate": 2e-05,
+      "loss": 0.4472,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 11.041153907775879,
+      "learning_rate": 2e-05,
+      "loss": 0.4632,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.071969985961914,
+      "learning_rate": 2e-05,
+      "loss": 0.5037,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.2244842052459717,
+      "learning_rate": 2e-05,
+      "loss": 0.5435,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.0249276161193848,
+      "learning_rate": 2e-05,
+      "loss": 0.1149,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 8.494997024536133,
+      "learning_rate": 2e-05,
+      "loss": 0.5543,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 14.141156196594238,
+      "learning_rate": 2e-05,
+      "loss": 0.9018,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 19.998416900634766,
+      "learning_rate": 2e-05,
+      "loss": 1.1294,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 5.338615894317627,
+      "learning_rate": 2e-05,
+      "loss": 0.1798,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.16664651036262512,
+      "learning_rate": 2e-05,
+      "loss": 0.1008,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 7.190863132476807,
+      "learning_rate": 2e-05,
+      "loss": 0.8715,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 5.1638407707214355,
+      "learning_rate": 2e-05,
+      "loss": 0.6667,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.6446938514709473,
+      "learning_rate": 2e-05,
+      "loss": 0.1582,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 4.495665073394775,
+      "learning_rate": 2e-05,
+      "loss": 0.2294,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 10.644786834716797,
+      "learning_rate": 2e-05,
+      "loss": 0.7821,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 4.212159156799316,
+      "learning_rate": 2e-05,
+      "loss": 0.7759,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.807500422000885,
+      "learning_rate": 2e-05,
+      "loss": 0.0511,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.9650363922119141,
+      "learning_rate": 2e-05,
+      "loss": 0.1146,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.2229278087615967,
+      "learning_rate": 2e-05,
+      "loss": 0.1406,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 22.622486114501953,
+      "learning_rate": 2e-05,
+      "loss": 2.1986,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 21.340667724609375,
+      "learning_rate": 2e-05,
+      "loss": 2.6584,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.6434290409088135,
+      "learning_rate": 2e-05,
+      "loss": 0.0414,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 9.894030570983887,
+      "learning_rate": 2e-05,
+      "loss": 0.7128,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.1998186111450195,
+      "learning_rate": 2e-05,
+      "loss": 0.4012,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 14.06959056854248,
+      "learning_rate": 2e-05,
+      "loss": 1.6564,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.18601089715957642,
+      "learning_rate": 2e-05,
+      "loss": 0.275,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 14.611976623535156,
+      "learning_rate": 2e-05,
+      "loss": 1.0607,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 5.8440375328063965,
+      "learning_rate": 2e-05,
+      "loss": 0.3328,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 15.99650764465332,
+      "learning_rate": 2e-05,
+      "loss": 2.204,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.640856981277466,
+      "learning_rate": 2e-05,
+      "loss": 0.1978,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 4914533793529856.0,
+      "train_loss": 0.6932883739471436,
+      "train_runtime": 106.5324,
+      "train_samples_per_second": 3.755,
+      "train_steps_per_second": 0.939
+    }
+  ],
+  "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": 4914533793529856.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e30e7dab2afe1029a26670fd024074a5573f81eb4efba1300c83f4c2073cb7
+size 184221358

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ff1d5b792ed10e7e39a944fcd521cfe7795d2646c29841b1c8df39d6ac57243
+size 184221358

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc655e89cddbcf602f9e444dd1cd583e55d8429d9485dabca545026a78a55bdc
+size 184221358

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:563ebc31ce1b575d8efed0d346927577e92508e6136f0887fe179f1e8bc84534
+size 184221358

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d94fb06130aac74718e8ccba0adc662dc1fdf9713fa963d23c50f9d94a959979
+size 184220842

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a192eadebade4b4b253e1824e47ab1da91ad2380909fa6cfb81816b7bc2517
+size 184221358

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f97ddfaf7a0a8e1d1a43b2c9d45e90a48527bf384d1dd3b36eeec2aad84ff4d
+size 184220842

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:379d34a161b6b7c4369aa16980314ab5f3ca1b020e7073f4372eeae3fd85e05c
+size 184220842

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_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": 17.728961944580078,
+      "learning_rate": 2e-05,
+      "loss": 1.3401,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.184070587158203,
+      "learning_rate": 2e-05,
+      "loss": 0.6049,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 20.953231811523438,
+      "learning_rate": 2e-05,
+      "loss": 1.3572,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 16.717697143554688,
+      "learning_rate": 2e-05,
+      "loss": 0.9823,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 31.81471824645996,
+      "learning_rate": 2e-05,
+      "loss": 1.7014,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 21.207393646240234,
+      "learning_rate": 2e-05,
+      "loss": 1.9672,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 21.250038146972656,
+      "learning_rate": 2e-05,
+      "loss": 1.1579,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 16.170562744140625,
+      "learning_rate": 2e-05,
+      "loss": 0.8864,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 18.03732681274414,
+      "learning_rate": 2e-05,
+      "loss": 0.4625,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 11.003514289855957,
+      "learning_rate": 2e-05,
+      "loss": 0.8025,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 9.46671199798584,
+      "learning_rate": 2e-05,
+      "loss": 0.7005,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 17.09604263305664,
+      "learning_rate": 2e-05,
+      "loss": 1.5089,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 5.776289463043213,
+      "learning_rate": 2e-05,
+      "loss": 0.5325,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 14.779522895812988,
+      "learning_rate": 2e-05,
+      "loss": 0.537,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 12.744089126586914,
+      "learning_rate": 2e-05,
+      "loss": 0.7497,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 31.664012908935547,
+      "learning_rate": 2e-05,
+      "loss": 0.9688,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.644858360290527,
+      "learning_rate": 2e-05,
+      "loss": 1.9609,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 29.535329818725586,
+      "learning_rate": 2e-05,
+      "loss": 2.5261,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 16.49091911315918,
+      "learning_rate": 2e-05,
+      "loss": 1.8476,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 13.428852081298828,
+      "learning_rate": 2e-05,
+      "loss": 1.1375,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 29.579025268554688,
+      "learning_rate": 2e-05,
+      "loss": 1.8553,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 27.436153411865234,
+      "learning_rate": 2e-05,
+      "loss": 1.7611,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 16.608835220336914,
+      "learning_rate": 2e-05,
+      "loss": 0.8257,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 8.383333206176758,
+      "learning_rate": 2e-05,
+      "loss": 0.2477,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 16.611234664916992,
+      "learning_rate": 2e-05,
+      "loss": 0.7533,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 12.93441104888916,
+      "learning_rate": 2e-05,
+      "loss": 1.7095,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.626491665840149,
+      "learning_rate": 2e-05,
+      "loss": 1.4653,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 12.2285737991333,
+      "learning_rate": 2e-05,
+      "loss": 0.894,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 12.543736457824707,
+      "learning_rate": 2e-05,
+      "loss": 0.9093,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 22.99381446838379,
+      "learning_rate": 2e-05,
+      "loss": 1.8475,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 18.157413482666016,
+      "learning_rate": 2e-05,
+      "loss": 1.1089,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 19.753389358520508,
+      "learning_rate": 2e-05,
+      "loss": 1.2159,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 12.126591682434082,
+      "learning_rate": 2e-05,
+      "loss": 0.8489,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 10.849102973937988,
+      "learning_rate": 2e-05,
+      "loss": 1.3116,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 11.539202690124512,
+      "learning_rate": 2e-05,
+      "loss": 0.9028,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 21.75928497314453,
+      "learning_rate": 2e-05,
+      "loss": 1.9344,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 4.046775817871094,
+      "learning_rate": 2e-05,
+      "loss": 1.0286,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 35.8420524597168,
+      "learning_rate": 2e-05,
+      "loss": 2.3075,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 5.226153373718262,
+      "learning_rate": 2e-05,
+      "loss": 0.5298,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 22.450458526611328,
+      "learning_rate": 2e-05,
+      "loss": 0.9573,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 7.684447765350342,
+      "learning_rate": 2e-05,
+      "loss": 0.2319,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 6.0478339195251465,
+      "learning_rate": 2e-05,
+      "loss": 0.5947,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 11.66108512878418,
+      "learning_rate": 2e-05,
+      "loss": 1.2579,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 9.50322151184082,
+      "learning_rate": 2e-05,
+      "loss": 0.9388,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 14.719149589538574,
+      "learning_rate": 2e-05,
+      "loss": 1.1785,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 17.723316192626953,
+      "learning_rate": 2e-05,
+      "loss": 0.5481,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 15.078863143920898,
+      "learning_rate": 2e-05,
+      "loss": 0.8471,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 5.520349025726318,
+      "learning_rate": 2e-05,
+      "loss": 0.3668,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 19.787466049194336,
+      "learning_rate": 2e-05,
+      "loss": 1.3677,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 19.332462310791016,
+      "learning_rate": 2e-05,
+      "loss": 1.8359,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2097655350034432.0,
+      "train_loss": 1.1462754821777343,
+      "train_runtime": 62.501,
+      "train_samples_per_second": 6.4,
+      "train_steps_per_second": 1.6
+    }
+  ],
+  "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": 2097655350034432.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc513e258fb7428a8bf8a6963825106eeb222456a34fde07853820822408ef4d
+size 395787774

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:509c84c42aa206837b71054b1ec03a80868698caa97ab4cca37fc8cdd1b90e38
+size 395787774

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c045719d046d40332a3ae661f02f61086a92b17942dcf417008e96f1d86e921
+size 395787774

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:effab8263b2ce39dbbf8b10bd4d79075a445765bfb2728e50054964420d1db3f
+size 395787774

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a1e932f6f3ecce4516880c69f50249bb2820676923d79cd22cbfd4c65ba3b1
+size 395786922

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05ca863a31381e13ced2d178a9d6824eecbd9b945a06390e68c8afc7f67fe21
+size 395787774

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:447b680274d98310bc1e2181992b388c0c2a55807a1a90d0b4623e59ae8f3078
+size 395786922

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63872411d205b83f6bd9ae6e4ebce2b5625373531b8e9e0326a94de7c6b831b4
+size 395786922

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_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": 3.4695563316345215,
+      "learning_rate": 2e-05,
+      "loss": 0.7117,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.528818130493164,
+      "learning_rate": 2e-05,
+      "loss": 0.9443,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.8286404609680176,
+      "learning_rate": 2e-05,
+      "loss": 0.4758,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.220069408416748,
+      "learning_rate": 2e-05,
+      "loss": 0.6582,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.49510383605957,
+      "learning_rate": 2e-05,
+      "loss": 0.5969,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.685155868530273,
+      "learning_rate": 2e-05,
+      "loss": 0.2637,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 6.694015026092529,
+      "learning_rate": 2e-05,
+      "loss": 0.6274,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 12.9075345993042,
+      "learning_rate": 2e-05,
+      "loss": 2.0231,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.817466735839844,
+      "learning_rate": 2e-05,
+      "loss": 0.4885,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 9.82458782196045,
+      "learning_rate": 2e-05,
+      "loss": 0.3874,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 7.341700553894043,
+      "learning_rate": 2e-05,
+      "loss": 1.7604,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.500534772872925,
+      "learning_rate": 2e-05,
+      "loss": 0.933,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.8060784339904785,
+      "learning_rate": 2e-05,
+      "loss": 0.4489,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 7.633967876434326,
+      "learning_rate": 2e-05,
+      "loss": 1.2498,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 6.188253402709961,
+      "learning_rate": 2e-05,
+      "loss": 1.0066,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 11.749099731445312,
+      "learning_rate": 2e-05,
+      "loss": 1.0057,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.9198079109191895,
+      "learning_rate": 2e-05,
+      "loss": 0.4555,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 10.411748886108398,
+      "learning_rate": 2e-05,
+      "loss": 1.2595,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 5.9154181480407715,
+      "learning_rate": 2e-05,
+      "loss": 0.7594,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 11.50054931640625,
+      "learning_rate": 2e-05,
+      "loss": 1.1038,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 7.356972694396973,
+      "learning_rate": 2e-05,
+      "loss": 0.9607,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 6.648898601531982,
+      "learning_rate": 2e-05,
+      "loss": 0.6124,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 7.777207374572754,
+      "learning_rate": 2e-05,
+      "loss": 0.9619,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 7.531315326690674,
+      "learning_rate": 2e-05,
+      "loss": 0.7908,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7036921977996826,
+      "learning_rate": 2e-05,
+      "loss": 0.4484,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 7.062431335449219,
+      "learning_rate": 2e-05,
+      "loss": 1.4581,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 7.804239273071289,
+      "learning_rate": 2e-05,
+      "loss": 0.8044,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.930359363555908,
+      "learning_rate": 2e-05,
+      "loss": 0.2664,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 7.491869926452637,
+      "learning_rate": 2e-05,
+      "loss": 0.909,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.822236061096191,
+      "learning_rate": 2e-05,
+      "loss": 0.8031,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 6.403017520904541,
+      "learning_rate": 2e-05,
+      "loss": 0.7448,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 6.305790901184082,
+      "learning_rate": 2e-05,
+      "loss": 1.1824,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 10.106334686279297,
+      "learning_rate": 2e-05,
+      "loss": 0.9054,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.6661808490753174,
+      "learning_rate": 2e-05,
+      "loss": 0.7058,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 11.230613708496094,
+      "learning_rate": 2e-05,
+      "loss": 0.8219,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.552886009216309,
+      "learning_rate": 2e-05,
+      "loss": 0.5434,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.033714532852173,
+      "learning_rate": 2e-05,
+      "loss": 0.7006,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.972300052642822,
+      "learning_rate": 2e-05,
+      "loss": 1.4068,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 8.233331680297852,
+      "learning_rate": 2e-05,
+      "loss": 0.8651,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.377525806427002,
+      "learning_rate": 2e-05,
+      "loss": 0.4299,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.237364292144775,
+      "learning_rate": 2e-05,
+      "loss": 0.6223,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.02529239654541,
+      "learning_rate": 2e-05,
+      "loss": 0.5242,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.8147952556610107,
+      "learning_rate": 2e-05,
+      "loss": 0.3852,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 8.175802230834961,
+      "learning_rate": 2e-05,
+      "loss": 0.4779,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 6.911006450653076,
+      "learning_rate": 2e-05,
+      "loss": 0.9153,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 11.411774635314941,
+      "learning_rate": 2e-05,
+      "loss": 0.807,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 6.6330132484436035,
+      "learning_rate": 2e-05,
+      "loss": 0.7153,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 7.924644470214844,
+      "learning_rate": 2e-05,
+      "loss": 0.8148,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.888672828674316,
+      "learning_rate": 2e-05,
+      "loss": 0.2964,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 18.131637573242188,
+      "learning_rate": 2e-05,
+      "loss": 1.1981,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5694661670731776.0,
+      "train_loss": 0.8047478008270263,
+      "train_runtime": 105.1787,
+      "train_samples_per_second": 3.803,
+      "train_steps_per_second": 0.951
+    }
+  ],
+  "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": 5694661670731776.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5881120267f886f18996e394e55022af5e9203f98f017c3b6fd8b9e48447d337
+size 395787774

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1425520ae344c2ed7af236991fdd9729d75dea8bba8340683dc24411df28f619
+size 395787774

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d498ce2a6477a3ea9861a62cd8098377d2f16e7245bdd354692d90944dfa8bd0
+size 395787774

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9bb07f98dace569c1b3aaca9f1deefee4b8d37b4f70b834153ff5d2254e381
+size 395787774

client_states_fedMultipqfullfreezeA_sft_pca_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063d6402dfa6abcfb9ed3f0cc9e319cc70cbc613857b7a03dab74743b3203172
+size 395786922