Upload folder using huggingface_hub

client_states_fedMultipqfullfreezeB_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:e1406494cc81ecc6645ea66f135fba48b08b852d84e00ed3bf0e64767d6d04ac
+size 184221358

client_states_fedMultipqfullfreezeB_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 sha256:3ea62685819911eed87352c12e84beedd3b7005ff276b52e2daafcae72fe3e72
+size 184221358

client_states_fedMultipqfullfreezeB_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 sha256:63bb105f42d890d7de605ee624cd3d3ea1ed3f3ada6504f43e3496b76ed11477
+size 184221358

client_states_fedMultipqfullfreezeB_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 sha256:112d488d6dd765e22fb60780f08192dbec107d54c3bffee59821f65693bdfcdb
+size 184221358

client_states_fedMultipqfullfreezeB_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:f5aca2c4fbdc327cd5143b8cb5ad4053247b5ab4f9748d40dd5d7537104e1818
+size 184220842

client_states_fedMultipqfullfreezeB_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:abb5598f97f2e908b9dbd8c0a79ec7e0c817cb571f8b75c0814b23a8b59b6571
+size 184221358

client_states_fedMultipqfullfreezeB_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 sha256:5058a6b0ac16ea3df6010fc0ee4b1c177f4258b9bef8d032eb3654d64cc8debe
+size 184220842

client_states_fedMultipqfullfreezeB_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:b17e001b9ce2245203552aeea0089c50dfb58b037215ab9bdc7149147d4fe270
+size 184220842

client_states_fedMultipqfullfreezeB_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": 8.886947631835938,
+      "learning_rate": 2e-05,
+      "loss": 1.0586,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.588067054748535,
+      "learning_rate": 2e-05,
+      "loss": 1.1688,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.8690497875213623,
+      "learning_rate": 2e-05,
+      "loss": 0.2551,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5837838053703308,
+      "learning_rate": 2e-05,
+      "loss": 0.08,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.369279861450195,
+      "learning_rate": 2e-05,
+      "loss": 0.6118,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 9.228706359863281,
+      "learning_rate": 2e-05,
+      "loss": 0.7312,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 4.238631725311279,
+      "learning_rate": 2e-05,
+      "loss": 0.4682,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 10.901687622070312,
+      "learning_rate": 2e-05,
+      "loss": 1.1604,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 13.660758018493652,
+      "learning_rate": 2e-05,
+      "loss": 2.0892,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 7.721104621887207,
+      "learning_rate": 2e-05,
+      "loss": 1.0469,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.844839334487915,
+      "learning_rate": 2e-05,
+      "loss": 0.0317,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 8.220420837402344,
+      "learning_rate": 2e-05,
+      "loss": 0.7715,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 5.426258563995361,
+      "learning_rate": 2e-05,
+      "loss": 0.2142,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.8402196764945984,
+      "learning_rate": 2e-05,
+      "loss": 0.1679,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.16737699508667,
+      "learning_rate": 2e-05,
+      "loss": 0.733,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 15.065016746520996,
+      "learning_rate": 2e-05,
+      "loss": 0.8619,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.412502288818359,
+      "learning_rate": 2e-05,
+      "loss": 0.249,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 10.433276176452637,
+      "learning_rate": 2e-05,
+      "loss": 0.6592,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.079629898071289,
+      "learning_rate": 2e-05,
+      "loss": 0.8352,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.647284984588623,
+      "learning_rate": 2e-05,
+      "loss": 0.3377,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.9022719860076904,
+      "learning_rate": 2e-05,
+      "loss": 0.1098,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 7.464609622955322,
+      "learning_rate": 2e-05,
+      "loss": 1.1977,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5387044548988342,
+      "learning_rate": 2e-05,
+      "loss": 0.3511,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 10.601780891418457,
+      "learning_rate": 2e-05,
+      "loss": 0.9487,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.023946762084961,
+      "learning_rate": 2e-05,
+      "loss": 0.1302,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 11.571028709411621,
+      "learning_rate": 2e-05,
+      "loss": 0.6011,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.87282133102417,
+      "learning_rate": 2e-05,
+      "loss": 0.2818,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.713423490524292,
+      "learning_rate": 2e-05,
+      "loss": 0.1644,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 11.62910270690918,
+      "learning_rate": 2e-05,
+      "loss": 1.9844,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.192251682281494,
+      "learning_rate": 2e-05,
+      "loss": 0.092,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.723055362701416,
+      "learning_rate": 2e-05,
+      "loss": 0.38,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.7932076454162598,
+      "learning_rate": 2e-05,
+      "loss": 0.1944,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.571885883808136,
+      "learning_rate": 2e-05,
+      "loss": 0.2546,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 5.109936714172363,
+      "learning_rate": 2e-05,
+      "loss": 0.7904,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 11.202879905700684,
+      "learning_rate": 2e-05,
+      "loss": 0.7539,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.579624652862549,
+      "learning_rate": 2e-05,
+      "loss": 0.2826,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 11.335589408874512,
+      "learning_rate": 2e-05,
+      "loss": 2.4529,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.759703159332275,
+      "learning_rate": 2e-05,
+      "loss": 0.7191,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.2622716724872589,
+      "learning_rate": 2e-05,
+      "loss": 0.7453,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.5320322513580322,
+      "learning_rate": 2e-05,
+      "loss": 0.9757,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.187987804412842,
+      "learning_rate": 2e-05,
+      "loss": 0.5671,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 12.467034339904785,
+      "learning_rate": 2e-05,
+      "loss": 0.9474,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.5042973756790161,
+      "learning_rate": 2e-05,
+      "loss": 0.1792,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 7.86875057220459,
+      "learning_rate": 2e-05,
+      "loss": 1.0289,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.8946852684020996,
+      "learning_rate": 2e-05,
+      "loss": 0.2982,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.4661802053451538,
+      "learning_rate": 2e-05,
+      "loss": 0.8666,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 9.840381622314453,
+      "learning_rate": 2e-05,
+      "loss": 2.3103,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.418431282043457,
+      "learning_rate": 2e-05,
+      "loss": 1.4225,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 10.213849067687988,
+      "learning_rate": 2e-05,
+      "loss": 1.7524,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9313125014305115,
+      "learning_rate": 2e-05,
+      "loss": 0.2875,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2053257199353856.0,
+      "train_loss": 0.7320353770256043,
+      "train_runtime": 66.905,
+      "train_samples_per_second": 5.979,
+      "train_steps_per_second": 1.495
+    }
+  ],
+  "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_fedMultipqfullfreezeB_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:e9f69b1103c62fa7ae8a22e0e3ccfc2c5e79308e08e508e52b29b119dcf8c9bb
+size 184221358

client_states_fedMultipqfullfreezeB_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 sha256:1b8d2457f80abb108f40c2f3adb097bef93008977810423c0e675ec1ff635ac3
+size 184221358

client_states_fedMultipqfullfreezeB_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 sha256:29e8a6ed78c6837f10bd56236a5e50ec8ab5e8db6e43ce8422ee8628f347d7da
+size 184221358

client_states_fedMultipqfullfreezeB_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:ca0cc677d61964b9e133c65a9ac2dbf43ac29bb3bfea733e5d4b280f6e9d597c
+size 184221358

client_states_fedMultipqfullfreezeB_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 sha256:63a9be8d75b6021bb9d0a8b556780ac78f11a2a7af3eaddf441f7796be24d97e
+size 184220842

client_states_fedMultipqfullfreezeB_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 sha256:2ecf9bfb11ce103a00fe8a8b20ca08c2c959d07deea30618626eea0935996543
+size 184221358

client_states_fedMultipqfullfreezeB_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 sha256:14d3365bf56511c60e5f95d53a32aa9496ac3000c7ede73328414cc27059fe17
+size 184220842

client_states_fedMultipqfullfreezeB_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 sha256:54e9617b10757dbb92359ffbee252fb941dad7087f24c1b2c37cc62e63d0d709
+size 184220842

client_states_fedMultipqfullfreezeB_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": 0.028587516397237778,
+      "learning_rate": 2e-05,
+      "loss": 0.0267,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.029884878545999527,
+      "learning_rate": 2e-05,
+      "loss": 0.0521,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.22514687478542328,
+      "learning_rate": 2e-05,
+      "loss": 0.0093,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.2603912055492401,
+      "learning_rate": 2e-05,
+      "loss": 0.0116,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.01106907706707716,
+      "learning_rate": 2e-05,
+      "loss": 0.0014,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.07203883677721024,
+      "learning_rate": 2e-05,
+      "loss": 0.0136,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.0598430410027504,
+      "learning_rate": 2e-05,
+      "loss": 0.0018,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.4535575211048126,
+      "learning_rate": 2e-05,
+      "loss": 0.0383,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.05992416664958,
+      "learning_rate": 2e-05,
+      "loss": 0.121,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.011320442892611027,
+      "learning_rate": 2e-05,
+      "loss": 0.0011,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.05899134278297424,
+      "learning_rate": 2e-05,
+      "loss": 0.0142,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.031861934810876846,
+      "learning_rate": 2e-05,
+      "loss": 0.0013,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.6744505167007446,
+      "learning_rate": 2e-05,
+      "loss": 0.0483,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.024044731631875038,
+      "learning_rate": 2e-05,
+      "loss": 0.001,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.8456639647483826,
+      "learning_rate": 2e-05,
+      "loss": 0.021,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.27866730093955994,
+      "learning_rate": 2e-05,
+      "loss": 0.0593,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.786769390106201,
+      "learning_rate": 2e-05,
+      "loss": 0.119,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.0027335325721651316,
+      "learning_rate": 2e-05,
+      "loss": 0.0002,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.270172655582428,
+      "learning_rate": 2e-05,
+      "loss": 0.008,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.465975284576416,
+      "learning_rate": 2e-05,
+      "loss": 0.145,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.029022216796875,
+      "learning_rate": 2e-05,
+      "loss": 0.0009,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 6.952610969543457,
+      "learning_rate": 2e-05,
+      "loss": 0.534,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.01336925383657217,
+      "learning_rate": 2e-05,
+      "loss": 0.001,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.02632717974483967,
+      "learning_rate": 2e-05,
+      "loss": 0.0011,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.009850457310676575,
+      "learning_rate": 2e-05,
+      "loss": 0.0011,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.016133064404129982,
+      "learning_rate": 2e-05,
+      "loss": 0.0298,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.6239187717437744,
+      "learning_rate": 2e-05,
+      "loss": 0.0179,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.018147876486182213,
+      "learning_rate": 2e-05,
+      "loss": 0.0043,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.16743789613246918,
+      "learning_rate": 2e-05,
+      "loss": 0.333,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.0029559978283941746,
+      "learning_rate": 2e-05,
+      "loss": 0.0975,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.014169096015393734,
+      "learning_rate": 2e-05,
+      "loss": 0.0007,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.015532419085502625,
+      "learning_rate": 2e-05,
+      "loss": 0.0346,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 8.49161148071289,
+      "learning_rate": 2e-05,
+      "loss": 0.0365,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.4051973819732666,
+      "learning_rate": 2e-05,
+      "loss": 0.0712,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.012287739664316177,
+      "learning_rate": 2e-05,
+      "loss": 0.001,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.317421793937683,
+      "learning_rate": 2e-05,
+      "loss": 0.033,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.141310691833496,
+      "learning_rate": 2e-05,
+      "loss": 0.0516,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.012324603274464607,
+      "learning_rate": 2e-05,
+      "loss": 0.0009,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 7.358309745788574,
+      "learning_rate": 2e-05,
+      "loss": 0.3286,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.0068267700262367725,
+      "learning_rate": 2e-05,
+      "loss": 0.0019,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.027679968625307083,
+      "learning_rate": 2e-05,
+      "loss": 0.0009,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.0038455259054899216,
+      "learning_rate": 2e-05,
+      "loss": 0.0004,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.014652257785201073,
+      "learning_rate": 2e-05,
+      "loss": 0.8248,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.0212117750197649,
+      "learning_rate": 2e-05,
+      "loss": 0.0017,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.9145652651786804,
+      "learning_rate": 2e-05,
+      "loss": 0.0257,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 11.541312217712402,
+      "learning_rate": 2e-05,
+      "loss": 0.1007,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1450074464082718,
+      "learning_rate": 2e-05,
+      "loss": 0.0047,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.7812843322753906,
+      "learning_rate": 2e-05,
+      "loss": 0.0183,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.024971066042780876,
+      "learning_rate": 2e-05,
+      "loss": 0.0041,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.16854286193847656,
+      "learning_rate": 2e-05,
+      "loss": 0.0041,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2069634366832640.0,
+      "train_loss": 0.06520086646080017,
+      "train_runtime": 67.209,
+      "train_samples_per_second": 5.952,
+      "train_steps_per_second": 1.488
+    }
+  ],
+  "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_fedMultipqfullfreezeB_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:a670055415d4880f331eb85740f70ee2cb8f486eab509d8c4166f859eaf436b7
+size 395787774

client_states_fedMultipqfullfreezeB_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:e9cf3334d22adf8bc8d9032fa9838217ea2b3978770784adcbb80142c6b5fec3
+size 395787774

client_states_fedMultipqfullfreezeB_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 sha256:455388704986c44003ba4297c180b4b670acc8e28d55c7f76b1e45185dc8dc23
+size 395787774

client_states_fedMultipqfullfreezeB_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 sha256:1c3571032b0c4bff4b3b6476039fb98dd4f4127eb67fe700d6fbb28e870706f2
+size 395787774

client_states_fedMultipqfullfreezeB_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 sha256:5b93124585d402b5d7320965a6575b46c2453b80c4a8329666426be96a120734
+size 395786922

client_states_fedMultipqfullfreezeB_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 sha256:857252bbf3b233a4e5d00443550447c436ceaa062657d052591fa62a8532bf1a
+size 395787774

client_states_fedMultipqfullfreezeB_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:b82c7f7336b24eb8a6b2d826058b56d3aedc502c0979070fe9934a543156c75b
+size 395786922

client_states_fedMultipqfullfreezeB_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 sha256:88557795e1bea1f7f2a1071a8e8c0297f54ece9a2f511068c1a7cc4c8d6ccce4
+size 395786922

client_states_fedMultipqfullfreezeB_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": 2.105396032333374,
+      "learning_rate": 2e-05,
+      "loss": 0.2033,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.478094577789307,
+      "learning_rate": 2e-05,
+      "loss": 1.3439,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.1515796184539795,
+      "learning_rate": 2e-05,
+      "loss": 0.857,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 5.204065799713135,
+      "learning_rate": 2e-05,
+      "loss": 0.963,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.9221630096435547,
+      "learning_rate": 2e-05,
+      "loss": 0.5015,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.2301812171936035,
+      "learning_rate": 2e-05,
+      "loss": 0.9144,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3219952881336212,
+      "learning_rate": 2e-05,
+      "loss": 0.4334,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.475340366363525,
+      "learning_rate": 2e-05,
+      "loss": 0.6966,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.9704943895339966,
+      "learning_rate": 2e-05,
+      "loss": 0.4297,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.269054412841797,
+      "learning_rate": 2e-05,
+      "loss": 1.1395,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.6645411252975464,
+      "learning_rate": 2e-05,
+      "loss": 0.1644,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.255583763122559,
+      "learning_rate": 2e-05,
+      "loss": 0.4868,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 6.85243034362793,
+      "learning_rate": 2e-05,
+      "loss": 0.8597,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.772141933441162,
+      "learning_rate": 2e-05,
+      "loss": 0.3411,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.2398443222045898,
+      "learning_rate": 2e-05,
+      "loss": 0.1638,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.372430801391602,
+      "learning_rate": 2e-05,
+      "loss": 0.377,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.858203649520874,
+      "learning_rate": 2e-05,
+      "loss": 0.6456,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.7406525611877441,
+      "learning_rate": 2e-05,
+      "loss": 0.118,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.103638648986816,
+      "learning_rate": 2e-05,
+      "loss": 1.1136,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.947889804840088,
+      "learning_rate": 2e-05,
+      "loss": 0.4615,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.2340707778930664,
+      "learning_rate": 2e-05,
+      "loss": 0.7555,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.404001474380493,
+      "learning_rate": 2e-05,
+      "loss": 0.183,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.3455829620361328,
+      "learning_rate": 2e-05,
+      "loss": 0.4547,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6196079850196838,
+      "learning_rate": 2e-05,
+      "loss": 0.4648,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.5915979146957397,
+      "learning_rate": 2e-05,
+      "loss": 0.1563,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 7.3114800453186035,
+      "learning_rate": 2e-05,
+      "loss": 0.6918,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 5.828458786010742,
+      "learning_rate": 2e-05,
+      "loss": 0.6894,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 6.562094688415527,
+      "learning_rate": 2e-05,
+      "loss": 0.5373,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.23714280128479,
+      "learning_rate": 2e-05,
+      "loss": 0.1409,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.15032356977462769,
+      "learning_rate": 2e-05,
+      "loss": 0.1555,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.8144638538360596,
+      "learning_rate": 2e-05,
+      "loss": 0.7566,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.5122342109680176,
+      "learning_rate": 2e-05,
+      "loss": 0.3092,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.330488443374634,
+      "learning_rate": 2e-05,
+      "loss": 0.1339,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.021944761276245,
+      "learning_rate": 2e-05,
+      "loss": 0.3639,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 6.429702281951904,
+      "learning_rate": 2e-05,
+      "loss": 0.859,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.8376978039741516,
+      "learning_rate": 2e-05,
+      "loss": 0.9001,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.4407913088798523,
+      "learning_rate": 2e-05,
+      "loss": 0.0276,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.9633609056472778,
+      "learning_rate": 2e-05,
+      "loss": 0.143,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.6581859588623047,
+      "learning_rate": 2e-05,
+      "loss": 0.102,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 17.37574005126953,
+      "learning_rate": 2e-05,
+      "loss": 1.8274,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 10.83108139038086,
+      "learning_rate": 2e-05,
+      "loss": 2.4245,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.0673346146941185,
+      "learning_rate": 2e-05,
+      "loss": 0.0176,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.964028358459473,
+      "learning_rate": 2e-05,
+      "loss": 0.7041,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.659679651260376,
+      "learning_rate": 2e-05,
+      "loss": 0.4814,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 7.119080066680908,
+      "learning_rate": 2e-05,
+      "loss": 1.6169,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.1464005708694458,
+      "learning_rate": 2e-05,
+      "loss": 0.158,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 5.066743850708008,
+      "learning_rate": 2e-05,
+      "loss": 0.4878,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.149415969848633,
+      "learning_rate": 2e-05,
+      "loss": 0.2938,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 8.900089263916016,
+      "learning_rate": 2e-05,
+      "loss": 1.8197,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.3194432258605957,
+      "learning_rate": 2e-05,
+      "loss": 0.1952,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 4914533793529856.0,
+      "train_loss": 0.601297242641449,
+      "train_runtime": 105.5222,
+      "train_samples_per_second": 3.791,
+      "train_steps_per_second": 0.948
+    }
+  ],
+  "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_fedMultipqfullfreezeB_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 sha256:76d4aa596eabb5159b4d28b74e46910045877aeffa3554b2f997f94bd0da89fa
+size 184221358

client_states_fedMultipqfullfreezeB_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:b11bc00aaa6e08a36cfd6d3b39d0efaa19cf0e4c8754f92d09b14cef53cfdec8
+size 184221358

client_states_fedMultipqfullfreezeB_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:fa072bb30028b47746493c2225cae7f34658e6a00c00fc580645c4737b8d5b77
+size 184221358

client_states_fedMultipqfullfreezeB_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 sha256:9ef4c443dc56a11508dbafa313f5867032aef15767cbcf03ac1df7a277ebce41
+size 184221358

client_states_fedMultipqfullfreezeB_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:e37e23d0ba28984416df0b8e066f2bc68f7673b4aa966520dcbc59528864e563
+size 184220842

client_states_fedMultipqfullfreezeB_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 sha256:60423bc56c7bcb5446e76d5a86804e524694b7b68dd7dcf8db3f84290dac4749
+size 184221358

client_states_fedMultipqfullfreezeB_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 sha256:09e1da4e2387cf65fdb295db6605417ce879f31983d9c7247a67df7c290263d5
+size 184220842

client_states_fedMultipqfullfreezeB_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:f24ee88d145c695c184774afccab251d6d4f137b15f280443f3a09044a30ac7b
+size 184220842

client_states_fedMultipqfullfreezeB_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": 9.15634536743164,
+      "learning_rate": 2e-05,
+      "loss": 0.9397,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.9539599418640137,
+      "learning_rate": 2e-05,
+      "loss": 0.4816,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 7.12010383605957,
+      "learning_rate": 2e-05,
+      "loss": 1.0672,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 11.230935096740723,
+      "learning_rate": 2e-05,
+      "loss": 1.3385,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 12.102299690246582,
+      "learning_rate": 2e-05,
+      "loss": 1.314,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 7.587926387786865,
+      "learning_rate": 2e-05,
+      "loss": 1.5088,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 11.77520751953125,
+      "learning_rate": 2e-05,
+      "loss": 1.5007,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 8.806689262390137,
+      "learning_rate": 2e-05,
+      "loss": 1.0232,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 6.919975280761719,
+      "learning_rate": 2e-05,
+      "loss": 0.5305,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.2757022380828857,
+      "learning_rate": 2e-05,
+      "loss": 0.7843,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 5.029139041900635,
+      "learning_rate": 2e-05,
+      "loss": 0.5721,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.680845260620117,
+      "learning_rate": 2e-05,
+      "loss": 1.0862,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.745439052581787,
+      "learning_rate": 2e-05,
+      "loss": 0.4518,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.786810874938965,
+      "learning_rate": 2e-05,
+      "loss": 0.3724,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 6.002584934234619,
+      "learning_rate": 2e-05,
+      "loss": 0.7648,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 16.67854118347168,
+      "learning_rate": 2e-05,
+      "loss": 1.1352,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.959960699081421,
+      "learning_rate": 2e-05,
+      "loss": 2.1569,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 12.444388389587402,
+      "learning_rate": 2e-05,
+      "loss": 2.0652,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.5506157875061035,
+      "learning_rate": 2e-05,
+      "loss": 0.8247,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.148169994354248,
+      "learning_rate": 2e-05,
+      "loss": 1.1364,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 13.703283309936523,
+      "learning_rate": 2e-05,
+      "loss": 1.249,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 12.692126274108887,
+      "learning_rate": 2e-05,
+      "loss": 1.5431,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.30729341506958,
+      "learning_rate": 2e-05,
+      "loss": 0.6453,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.500507831573486,
+      "learning_rate": 2e-05,
+      "loss": 0.5124,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 5.481895923614502,
+      "learning_rate": 2e-05,
+      "loss": 0.9677,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 9.486720085144043,
+      "learning_rate": 2e-05,
+      "loss": 1.9241,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.8915572762489319,
+      "learning_rate": 2e-05,
+      "loss": 0.875,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.3242287635803223,
+      "learning_rate": 2e-05,
+      "loss": 0.8049,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.5319318771362305,
+      "learning_rate": 2e-05,
+      "loss": 0.8476,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 7.810834884643555,
+      "learning_rate": 2e-05,
+      "loss": 1.4747,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 6.061686992645264,
+      "learning_rate": 2e-05,
+      "loss": 0.8335,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 5.4117021560668945,
+      "learning_rate": 2e-05,
+      "loss": 0.8062,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 5.741265296936035,
+      "learning_rate": 2e-05,
+      "loss": 1.0926,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 5.817255973815918,
+      "learning_rate": 2e-05,
+      "loss": 1.0386,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 6.286365509033203,
+      "learning_rate": 2e-05,
+      "loss": 1.1693,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 7.558319091796875,
+      "learning_rate": 2e-05,
+      "loss": 2.0536,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 4.5277299880981445,
+      "learning_rate": 2e-05,
+      "loss": 1.2765,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 14.435311317443848,
+      "learning_rate": 2e-05,
+      "loss": 1.4086,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 8.644015312194824,
+      "learning_rate": 2e-05,
+      "loss": 0.9196,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 9.145062446594238,
+      "learning_rate": 2e-05,
+      "loss": 0.8797,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.320108652114868,
+      "learning_rate": 2e-05,
+      "loss": 0.2312,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 5.20671272277832,
+      "learning_rate": 2e-05,
+      "loss": 0.6787,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.356175422668457,
+      "learning_rate": 2e-05,
+      "loss": 1.126,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.225734710693359,
+      "learning_rate": 2e-05,
+      "loss": 1.0222,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.531115531921387,
+      "learning_rate": 2e-05,
+      "loss": 0.8512,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 12.393115043640137,
+      "learning_rate": 2e-05,
+      "loss": 0.6987,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 6.147823333740234,
+      "learning_rate": 2e-05,
+      "loss": 0.7845,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.951950788497925,
+      "learning_rate": 2e-05,
+      "loss": 0.3292,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 8.34253978729248,
+      "learning_rate": 2e-05,
+      "loss": 1.201,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.68620777130127,
+      "learning_rate": 2e-05,
+      "loss": 1.0787,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2097655350034432.0,
+      "train_loss": 1.0275479412078858,
+      "train_runtime": 64.3773,
+      "train_samples_per_second": 6.213,
+      "train_steps_per_second": 1.553
+    }
+  ],
+  "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_fedMultipqfullfreezeB_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 sha256:6d4d8713c7ae223db37f74fef11dd2ec4f9c3697a7a18a4fd8fd21981be318f2
+size 395787774

client_states_fedMultipqfullfreezeB_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 sha256:81e320f0ce1133e0ed75393c6cadb957b05f71007fa15b1c85e91fe4977988b0
+size 395787774

client_states_fedMultipqfullfreezeB_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 sha256:2d1c3becb212aaf99877fa63249be60c7ddd78eb66f2af6aeda19fab9b0501cd
+size 395787774

client_states_fedMultipqfullfreezeB_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 sha256:220b21c193eaa514cdc503e0420124f21cdb556570549838224cb0a4b0d1b8b9
+size 395787774

client_states_fedMultipqfullfreezeB_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:c65cf9e5799b751d75d4fec3e33a80a67aaf1f57bd03d2231c084929e9dc7b79
+size 395786922

client_states_fedMultipqfullfreezeB_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 sha256:6f29e653ce3f711cae0a7a108c6ce3b0c3128932d3d79ee2b6b3608d29722c0f
+size 395787774

client_states_fedMultipqfullfreezeB_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:ca3e2c59ac98b5c0412e87b06cf40a54be4437394cb4638fe685ea2c9dfb8d4a
+size 395786922

client_states_fedMultipqfullfreezeB_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 sha256:3cd5928b47c6a13dddd075a64d5151863836a4403bbfa51316ed8b6434cbe791
+size 395786922

client_states_fedMultipqfullfreezeB_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": 1.527263879776001,
+      "learning_rate": 2e-05,
+      "loss": 0.4842,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.760221242904663,
+      "learning_rate": 2e-05,
+      "loss": 0.9147,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.1504747867584229,
+      "learning_rate": 2e-05,
+      "loss": 0.4597,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.06758975982666,
+      "learning_rate": 2e-05,
+      "loss": 0.6667,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.2761497497558594,
+      "learning_rate": 2e-05,
+      "loss": 0.5814,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.6250596046447754,
+      "learning_rate": 2e-05,
+      "loss": 0.3246,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.6377880573272705,
+      "learning_rate": 2e-05,
+      "loss": 0.681,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 9.429349899291992,
+      "learning_rate": 2e-05,
+      "loss": 2.0273,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.9040491580963135,
+      "learning_rate": 2e-05,
+      "loss": 0.425,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.228061199188232,
+      "learning_rate": 2e-05,
+      "loss": 0.4564,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.796684741973877,
+      "learning_rate": 2e-05,
+      "loss": 1.8981,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.6710107326507568,
+      "learning_rate": 2e-05,
+      "loss": 0.9774,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.283553123474121,
+      "learning_rate": 2e-05,
+      "loss": 0.4572,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.7857582569122314,
+      "learning_rate": 2e-05,
+      "loss": 1.0938,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.051619529724121,
+      "learning_rate": 2e-05,
+      "loss": 0.8807,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.345559597015381,
+      "learning_rate": 2e-05,
+      "loss": 0.8728,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.005192756652832,
+      "learning_rate": 2e-05,
+      "loss": 0.4745,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 4.272996425628662,
+      "learning_rate": 2e-05,
+      "loss": 1.1445,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.1995797157287598,
+      "learning_rate": 2e-05,
+      "loss": 0.5203,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.592801094055176,
+      "learning_rate": 2e-05,
+      "loss": 1.1552,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.3184566497802734,
+      "learning_rate": 2e-05,
+      "loss": 0.8856,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.79464054107666,
+      "learning_rate": 2e-05,
+      "loss": 0.5977,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.426015615463257,
+      "learning_rate": 2e-05,
+      "loss": 0.8892,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.772137403488159,
+      "learning_rate": 2e-05,
+      "loss": 0.7512,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.5406640768051147,
+      "learning_rate": 2e-05,
+      "loss": 0.3895,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.195302963256836,
+      "learning_rate": 2e-05,
+      "loss": 1.59,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.618748426437378,
+      "learning_rate": 2e-05,
+      "loss": 0.8087,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.804460048675537,
+      "learning_rate": 2e-05,
+      "loss": 0.2267,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.8953168392181396,
+      "learning_rate": 2e-05,
+      "loss": 0.8058,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.712660551071167,
+      "learning_rate": 2e-05,
+      "loss": 0.841,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.6159372329711914,
+      "learning_rate": 2e-05,
+      "loss": 0.64,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.1374075412750244,
+      "learning_rate": 2e-05,
+      "loss": 1.0344,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 5.049036026000977,
+      "learning_rate": 2e-05,
+      "loss": 1.009,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.3270905017852783,
+      "learning_rate": 2e-05,
+      "loss": 0.6997,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 5.63070821762085,
+      "learning_rate": 2e-05,
+      "loss": 0.8887,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.6345393657684326,
+      "learning_rate": 2e-05,
+      "loss": 0.5349,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.9860789775848389,
+      "learning_rate": 2e-05,
+      "loss": 0.5652,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.1421189308166504,
+      "learning_rate": 2e-05,
+      "loss": 1.3851,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.823781728744507,
+      "learning_rate": 2e-05,
+      "loss": 0.7622,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.986513614654541,
+      "learning_rate": 2e-05,
+      "loss": 0.4424,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.666304111480713,
+      "learning_rate": 2e-05,
+      "loss": 0.5415,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.9997386932373047,
+      "learning_rate": 2e-05,
+      "loss": 0.4661,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.9241174459457397,
+      "learning_rate": 2e-05,
+      "loss": 0.3708,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.7665395736694336,
+      "learning_rate": 2e-05,
+      "loss": 0.55,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.948091983795166,
+      "learning_rate": 2e-05,
+      "loss": 0.8679,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 5.765527248382568,
+      "learning_rate": 2e-05,
+      "loss": 0.7642,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.300235271453857,
+      "learning_rate": 2e-05,
+      "loss": 0.8016,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.0772464275360107,
+      "learning_rate": 2e-05,
+      "loss": 0.6961,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.6090457439422607,
+      "learning_rate": 2e-05,
+      "loss": 0.2739,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.003314018249512,
+      "learning_rate": 2e-05,
+      "loss": 1.1299,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5694661670731776.0,
+      "train_loss": 0.7740931415557861,
+      "train_runtime": 109.547,
+      "train_samples_per_second": 3.651,
+      "train_steps_per_second": 0.913
+    }
+  ],
+  "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_fedMultipqfullfreezeB_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 sha256:4a764a4e8709390732d62e78d72e55d509301d9aa9c718c1011f8b52fa63d8a5
+size 395787774

client_states_fedMultipqfullfreezeB_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 sha256:54b3ab1a6455447fed4f76fcba7124073ea0fe24aac388e398ecf28fc95c214c
+size 395787774

client_states_fedMultipqfullfreezeB_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 sha256:0145c9d4e23a0839b6206582913016c8edf7581075b67b94b9c4c87e1753b746
+size 395787774

client_states_fedMultipqfullfreezeB_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 sha256:7ef935d710f91d11a6434902130857ec1b4970fe68b4327e8f8911fc4be7e1ac
+size 395787774

client_states_fedMultipqfullfreezeB_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:b5d16c10719a5f81175aeea9c96393e87f7f0cd11c784297d0a9155891b8b21c
+size 395786922