Upload folder using huggingface_hub

client_states_fedMulti05pqfullfreeze_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 sha256:0d45b60c3377d2b233fb79150e4c6377564419264b3e0dd37b143f4dea3eeaca
+size 184221358

client_states_fedMulti05pqfullfreeze_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:d914723f4cff80df3e933a3d63ed043f08536b104877dd055d63014f403de212
+size 184221358

client_states_fedMulti05pqfullfreeze_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:af842a7f9e95aa8f8e6a126bead7c15243b1d3dd91e7dd5062278c436136c8d6
+size 184221358

client_states_fedMulti05pqfullfreeze_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:b7608843e5153961ba8c3edc1f197c34164f0867a809f0207e1008fecf20a06a
+size 184221358

client_states_fedMulti05pqfullfreeze_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 sha256:44243ca3716547c0c21a27577345ceaeb9e623be86ced11e1044d7ab6fa8a7e7
+size 184220842

client_states_fedMulti05pqfullfreeze_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:ea2112c3636246412e69c2fcd14b814cd7b68334b9c3f8bbddb5b8208429e04a
+size 184221358

client_states_fedMulti05pqfullfreeze_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 sha256:1b8c7efe671d91efab26d3fbdc245783660112915cbb1d22a44ed154e94e2748
+size 184220842

client_states_fedMulti05pqfullfreeze_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 sha256:291f338c17fa2a84cb07d5db8619e1333d6e2f8944c902a3261c101b354ba731
+size 184220842

client_states_fedMulti05pqfullfreeze_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": 10.044001579284668,
+      "learning_rate": 2e-05,
+      "loss": 1.0811,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.708449363708496,
+      "learning_rate": 2e-05,
+      "loss": 1.0935,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 6.164332389831543,
+      "learning_rate": 2e-05,
+      "loss": 0.2887,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.7329395413398743,
+      "learning_rate": 2e-05,
+      "loss": 0.0654,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.7981791496276855,
+      "learning_rate": 2e-05,
+      "loss": 0.5255,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 10.993570327758789,
+      "learning_rate": 2e-05,
+      "loss": 0.7257,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 6.135924816131592,
+      "learning_rate": 2e-05,
+      "loss": 0.3716,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 10.345540046691895,
+      "learning_rate": 2e-05,
+      "loss": 1.132,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 15.495490074157715,
+      "learning_rate": 2e-05,
+      "loss": 1.7626,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 9.968962669372559,
+      "learning_rate": 2e-05,
+      "loss": 1.0484,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.6021881103515625,
+      "learning_rate": 2e-05,
+      "loss": 0.0195,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 10.388916015625,
+      "learning_rate": 2e-05,
+      "loss": 0.813,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 6.319398880004883,
+      "learning_rate": 2e-05,
+      "loss": 0.2256,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.6123639345169067,
+      "learning_rate": 2e-05,
+      "loss": 0.1623,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.0997838973999023,
+      "learning_rate": 2e-05,
+      "loss": 0.8552,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 17.500144958496094,
+      "learning_rate": 2e-05,
+      "loss": 1.1279,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 5.181461334228516,
+      "learning_rate": 2e-05,
+      "loss": 0.2672,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 10.427047729492188,
+      "learning_rate": 2e-05,
+      "loss": 0.5116,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.001834392547607,
+      "learning_rate": 2e-05,
+      "loss": 0.8254,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.918587684631348,
+      "learning_rate": 2e-05,
+      "loss": 0.2577,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.5070538520812988,
+      "learning_rate": 2e-05,
+      "loss": 0.0786,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 8.23068904876709,
+      "learning_rate": 2e-05,
+      "loss": 1.336,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.4960165321826935,
+      "learning_rate": 2e-05,
+      "loss": 0.2786,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 14.814494132995605,
+      "learning_rate": 2e-05,
+      "loss": 1.3887,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.1397197246551514,
+      "learning_rate": 2e-05,
+      "loss": 0.1331,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 11.526412963867188,
+      "learning_rate": 2e-05,
+      "loss": 0.4426,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.414958953857422,
+      "learning_rate": 2e-05,
+      "loss": 0.2413,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.718291282653809,
+      "learning_rate": 2e-05,
+      "loss": 0.1895,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 12.340472221374512,
+      "learning_rate": 2e-05,
+      "loss": 1.9869,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.813292503356934,
+      "learning_rate": 2e-05,
+      "loss": 0.1454,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.3212244510650635,
+      "learning_rate": 2e-05,
+      "loss": 0.4304,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.7471375465393066,
+      "learning_rate": 2e-05,
+      "loss": 0.1793,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.6779154539108276,
+      "learning_rate": 2e-05,
+      "loss": 0.1912,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 5.2416229248046875,
+      "learning_rate": 2e-05,
+      "loss": 0.7198,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 12.138299942016602,
+      "learning_rate": 2e-05,
+      "loss": 0.6979,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 8.756268501281738,
+      "learning_rate": 2e-05,
+      "loss": 0.3211,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 12.594830513000488,
+      "learning_rate": 2e-05,
+      "loss": 2.7682,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.925561904907227,
+      "learning_rate": 2e-05,
+      "loss": 0.7106,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.4183579981327057,
+      "learning_rate": 2e-05,
+      "loss": 0.9514,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.107239246368408,
+      "learning_rate": 2e-05,
+      "loss": 1.1018,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 6.866254806518555,
+      "learning_rate": 2e-05,
+      "loss": 0.6412,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 13.476661682128906,
+      "learning_rate": 2e-05,
+      "loss": 0.9713,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.8483925461769104,
+      "learning_rate": 2e-05,
+      "loss": 0.1767,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 9.308485984802246,
+      "learning_rate": 2e-05,
+      "loss": 1.2229,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.227640151977539,
+      "learning_rate": 2e-05,
+      "loss": 0.4012,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.6228331923484802,
+      "learning_rate": 2e-05,
+      "loss": 0.9619,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 9.9182767868042,
+      "learning_rate": 2e-05,
+      "loss": 2.1173,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.4465816020965576,
+      "learning_rate": 2e-05,
+      "loss": 1.605,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 12.18694019317627,
+      "learning_rate": 2e-05,
+      "loss": 2.0198,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0387413501739502,
+      "learning_rate": 2e-05,
+      "loss": 0.2066,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2053257199353856.0,
+      "train_loss": 0.755521228313446,
+      "train_runtime": 101.7028,
+      "train_samples_per_second": 3.933,
+      "train_steps_per_second": 0.983
+    }
+  ],
+  "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_fedMulti05pqfullfreeze_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:bf0af71fd4d6dc12cffd01523df4bbc58a571c0978ca4c7d7571aa24bdeb8ee5
+size 184221358

client_states_fedMulti05pqfullfreeze_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 sha256:1744e2ae1501079d9883e05d012fe5bf1d7a4f72884671f31cc3a124d304ec02
+size 184221358

client_states_fedMulti05pqfullfreeze_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:c105cc5e4f96671ece69b8f9d708aa9a805d9a65a48b0865cc54c7d7fc57fdbf
+size 184221358

client_states_fedMulti05pqfullfreeze_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:ff0a15058359453e6d079b47f6e618fcf9720db11d691877dbe2140c6a15be3c
+size 184221358

client_states_fedMulti05pqfullfreeze_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 sha256:1ec3b7d6ad6a720fb656550c2f62665f56860a6f8a8288ff1f826b9dceaed89e
+size 184220842

client_states_fedMulti05pqfullfreeze_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 sha256:59993217d193880b0fc5548c04f04df882e9949136543c7bbede6e4dcfb2687c
+size 184221358

client_states_fedMulti05pqfullfreeze_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 sha256:009defbeb3403fee4f1ed358ade2be16ece2a7c97a4f95464240ea4cf6c2e3d8
+size 184220842

client_states_fedMulti05pqfullfreeze_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:c0be9e6109694003abb07f24a9bb7b03b63669d481039c2e19e40b6296e98501
+size 184220842

client_states_fedMulti05pqfullfreeze_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": 0.02960115671157837,
+      "learning_rate": 2e-05,
+      "loss": 0.0045,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.09186350554227829,
+      "learning_rate": 2e-05,
+      "loss": 0.0653,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.16298067569732666,
+      "learning_rate": 2e-05,
+      "loss": 0.0063,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.09170705080032349,
+      "learning_rate": 2e-05,
+      "loss": 0.0034,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.06864725798368454,
+      "learning_rate": 2e-05,
+      "loss": 0.0031,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.19071757793426514,
+      "learning_rate": 2e-05,
+      "loss": 0.0287,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.17343077063560486,
+      "learning_rate": 2e-05,
+      "loss": 0.0038,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.2856125235557556,
+      "learning_rate": 2e-05,
+      "loss": 0.0591,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.04609253257513046,
+      "learning_rate": 2e-05,
+      "loss": 0.024,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.01641538180410862,
+      "learning_rate": 2e-05,
+      "loss": 0.001,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.07860966771841049,
+      "learning_rate": 2e-05,
+      "loss": 0.0113,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.027962295338511467,
+      "learning_rate": 2e-05,
+      "loss": 0.0011,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.3819764852523804,
+      "learning_rate": 2e-05,
+      "loss": 0.0356,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.01595745049417019,
+      "learning_rate": 2e-05,
+      "loss": 0.0008,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.12123987823724747,
+      "learning_rate": 2e-05,
+      "loss": 0.004,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.7385960221290588,
+      "learning_rate": 2e-05,
+      "loss": 0.1151,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 5.604942798614502,
+      "learning_rate": 2e-05,
+      "loss": 0.1588,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.005619928240776062,
+      "learning_rate": 2e-05,
+      "loss": 0.0003,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.027213625609874725,
+      "learning_rate": 2e-05,
+      "loss": 0.0016,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.135501384735107,
+      "learning_rate": 2e-05,
+      "loss": 0.0975,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.00542866624891758,
+      "learning_rate": 2e-05,
+      "loss": 0.0006,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 7.716265678405762,
+      "learning_rate": 2e-05,
+      "loss": 0.3077,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.01432905811816454,
+      "learning_rate": 2e-05,
+      "loss": 0.0009,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.3185250163078308,
+      "learning_rate": 2e-05,
+      "loss": 0.004,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.00824733730405569,
+      "learning_rate": 2e-05,
+      "loss": 0.0022,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.006523216143250465,
+      "learning_rate": 2e-05,
+      "loss": 0.0265,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.3274787664413452,
+      "learning_rate": 2e-05,
+      "loss": 0.0094,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.012340985238552094,
+      "learning_rate": 2e-05,
+      "loss": 0.0011,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.01708126626908779,
+      "learning_rate": 2e-05,
+      "loss": 0.6785,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.005370909348130226,
+      "learning_rate": 2e-05,
+      "loss": 0.2075,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.009917240589857101,
+      "learning_rate": 2e-05,
+      "loss": 0.0011,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.015617340803146362,
+      "learning_rate": 2e-05,
+      "loss": 0.0178,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.04841961711645126,
+      "learning_rate": 2e-05,
+      "loss": 0.0013,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.055001735687256,
+      "learning_rate": 2e-05,
+      "loss": 0.0487,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.010724334977567196,
+      "learning_rate": 2e-05,
+      "loss": 0.0007,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.1112007200717926,
+      "learning_rate": 2e-05,
+      "loss": 0.0032,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.5635241270065308,
+      "learning_rate": 2e-05,
+      "loss": 0.0103,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.024422986432909966,
+      "learning_rate": 2e-05,
+      "loss": 0.0009,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 9.877224922180176,
+      "learning_rate": 2e-05,
+      "loss": 0.4788,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.025433897972106934,
+      "learning_rate": 2e-05,
+      "loss": 0.0017,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.07279513031244278,
+      "learning_rate": 2e-05,
+      "loss": 0.0021,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.003639621427282691,
+      "learning_rate": 2e-05,
+      "loss": 0.0004,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.021531013771891594,
+      "learning_rate": 2e-05,
+      "loss": 1.1024,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.041703518480062485,
+      "learning_rate": 2e-05,
+      "loss": 0.0053,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.0306504964828491,
+      "learning_rate": 2e-05,
+      "loss": 0.0258,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.19764401018619537,
+      "learning_rate": 2e-05,
+      "loss": 0.0066,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1398591846227646,
+      "learning_rate": 2e-05,
+      "loss": 0.0036,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.9593293070793152,
+      "learning_rate": 2e-05,
+      "loss": 0.0234,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.013573438860476017,
+      "learning_rate": 2e-05,
+      "loss": 0.0012,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.1273522675037384,
+      "learning_rate": 2e-05,
+      "loss": 0.003,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2069634366832640.0,
+      "train_loss": 0.07204394578933716,
+      "train_runtime": 101.8827,
+      "train_samples_per_second": 3.926,
+      "train_steps_per_second": 0.982
+    }
+  ],
+  "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_fedMulti05pqfullfreeze_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 sha256:2cd1af5c7ca40ed6a79af8c9cb6555f78589b0a624a98c6483565f76f8b3c61d
+size 395787774

client_states_fedMulti05pqfullfreeze_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 sha256:8e8db792016ac55ff57bd23f8349e5df6ceb14624e1d9a29105c81ed7d7ed4ed
+size 395787774

client_states_fedMulti05pqfullfreeze_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 sha256:19524fc38015f33290f292a4f522b4d36c1adcb621ac578bb561050e13fefe91
+size 395787774

client_states_fedMulti05pqfullfreeze_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 sha256:3a874d7d599aad5817e884d0953977542823faf1f01d25101400d3430928ff9c
+size 395787774

client_states_fedMulti05pqfullfreeze_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 sha256:33baa7cb694bc7b9f9162330827005d81631575ea2e90cd715b6d42b50f475da
+size 395786922

client_states_fedMulti05pqfullfreeze_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:cb3be0c563957173b91a7ec86c8723fdb23acdadf722cf602bc3483c5d0b11ae
+size 395787774

client_states_fedMulti05pqfullfreeze_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 sha256:698b9afe0148feecdd937cdc3624b381dfe48c2a3a8083e2dfa29bfedd728c42
+size 395786922

client_states_fedMulti05pqfullfreeze_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 sha256:633deab3c32fa4046bc1e4c0691c368ae244561291e78cbdba6062fdf7b77f16
+size 395786922

client_states_fedMulti05pqfullfreeze_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": 1.765663981437683,
+      "learning_rate": 2e-05,
+      "loss": 0.1386,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.676456928253174,
+      "learning_rate": 2e-05,
+      "loss": 1.1946,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.184738874435425,
+      "learning_rate": 2e-05,
+      "loss": 0.9233,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.627042770385742,
+      "learning_rate": 2e-05,
+      "loss": 1.1015,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.915734767913818,
+      "learning_rate": 2e-05,
+      "loss": 0.663,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 6.462231636047363,
+      "learning_rate": 2e-05,
+      "loss": 1.0081,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.35552021861076355,
+      "learning_rate": 2e-05,
+      "loss": 0.3945,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.338579177856445,
+      "learning_rate": 2e-05,
+      "loss": 0.6744,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.783922791481018,
+      "learning_rate": 2e-05,
+      "loss": 0.4461,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.711841106414795,
+      "learning_rate": 2e-05,
+      "loss": 1.4118,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.9069531559944153,
+      "learning_rate": 2e-05,
+      "loss": 0.176,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 7.7085490226745605,
+      "learning_rate": 2e-05,
+      "loss": 0.5315,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 10.80366039276123,
+      "learning_rate": 2e-05,
+      "loss": 1.0346,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 6.07086181640625,
+      "learning_rate": 2e-05,
+      "loss": 0.3799,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.8229091167449951,
+      "learning_rate": 2e-05,
+      "loss": 0.1932,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.323653697967529,
+      "learning_rate": 2e-05,
+      "loss": 0.3793,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.461909770965576,
+      "learning_rate": 2e-05,
+      "loss": 0.6431,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.6867424249649048,
+      "learning_rate": 2e-05,
+      "loss": 0.1087,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.3799192905426025,
+      "learning_rate": 2e-05,
+      "loss": 0.6874,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 7.544458389282227,
+      "learning_rate": 2e-05,
+      "loss": 0.6817,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.379153251647949,
+      "learning_rate": 2e-05,
+      "loss": 0.6136,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.67325758934021,
+      "learning_rate": 2e-05,
+      "loss": 0.1987,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.6791194677352905,
+      "learning_rate": 2e-05,
+      "loss": 0.3694,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.7336940169334412,
+      "learning_rate": 2e-05,
+      "loss": 0.3386,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.389741897583008,
+      "learning_rate": 2e-05,
+      "loss": 0.1778,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 7.384143829345703,
+      "learning_rate": 2e-05,
+      "loss": 0.7985,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 7.0400872230529785,
+      "learning_rate": 2e-05,
+      "loss": 0.6097,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 8.808256149291992,
+      "learning_rate": 2e-05,
+      "loss": 0.7863,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.6529507637023926,
+      "learning_rate": 2e-05,
+      "loss": 0.1368,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.17764848470687866,
+      "learning_rate": 2e-05,
+      "loss": 0.1653,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.8120052814483643,
+      "learning_rate": 2e-05,
+      "loss": 0.7154,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.756453037261963,
+      "learning_rate": 2e-05,
+      "loss": 0.5272,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.120513677597046,
+      "learning_rate": 2e-05,
+      "loss": 0.1667,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 4.981636047363281,
+      "learning_rate": 2e-05,
+      "loss": 0.3927,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 5.101208209991455,
+      "learning_rate": 2e-05,
+      "loss": 0.6766,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.0963003635406494,
+      "learning_rate": 2e-05,
+      "loss": 0.7616,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.7717503905296326,
+      "learning_rate": 2e-05,
+      "loss": 0.0356,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.8139798641204834,
+      "learning_rate": 2e-05,
+      "loss": 0.1705,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.033977746963501,
+      "learning_rate": 2e-05,
+      "loss": 0.1349,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 13.496634483337402,
+      "learning_rate": 2e-05,
+      "loss": 1.6624,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 13.66792106628418,
+      "learning_rate": 2e-05,
+      "loss": 2.9498,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.06267403066158295,
+      "learning_rate": 2e-05,
+      "loss": 0.0111,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 5.407293319702148,
+      "learning_rate": 2e-05,
+      "loss": 0.5322,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 6.728641510009766,
+      "learning_rate": 2e-05,
+      "loss": 0.6077,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5.393722057342529,
+      "learning_rate": 2e-05,
+      "loss": 1.6041,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.15307481586933136,
+      "learning_rate": 2e-05,
+      "loss": 0.3262,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 6.039478302001953,
+      "learning_rate": 2e-05,
+      "loss": 0.491,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.6059703826904297,
+      "learning_rate": 2e-05,
+      "loss": 0.2965,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 10.516265869140625,
+      "learning_rate": 2e-05,
+      "loss": 1.887,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.030522584915161,
+      "learning_rate": 2e-05,
+      "loss": 0.1721,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 4914533793529856.0,
+      "train_loss": 0.6217503023147583,
+      "train_runtime": 169.8273,
+      "train_samples_per_second": 2.355,
+      "train_steps_per_second": 0.589
+    }
+  ],
+  "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_fedMulti05pqfullfreeze_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 sha256:386840b3ff94a28b7c83212829e6accfe75f2e328a9057cab81f329994fef0f1
+size 184221358

client_states_fedMulti05pqfullfreeze_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 sha256:99fe6a5d31215c1d0c764a74fdc4ec5918e52a0db960e55f5fdd3fe51f8dc2d2
+size 184221358

client_states_fedMulti05pqfullfreeze_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 sha256:924e12ae251af8a13eb6310668a2e9dbdc07b477f9b1ade3564b97b41171fb39
+size 184221358

client_states_fedMulti05pqfullfreeze_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:dc65366e8dea534e149ce7cd583b6319994ed35ecc39582525344b753aeb1858
+size 184221358

client_states_fedMulti05pqfullfreeze_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 sha256:92099a5ace36a30279e1cc431967135db0772dc3159d7b8d231675dfd4cf88c0
+size 184220842

client_states_fedMulti05pqfullfreeze_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:d874d9cb32ec1bddc888cfd18e4b414cf20eff538ba46baccd8b8d0b89bc4fbd
+size 184221358

client_states_fedMulti05pqfullfreeze_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 sha256:85cba7e8c401b0d413e0b2a269065ccf0c313caf14e5148232105b7da2d2fa8f
+size 184220842

client_states_fedMulti05pqfullfreeze_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:b6a290cb3bf0eb2e5195b515d1ca2991a50522ba0f05ad0956cc52b0f6922957
+size 184220842

client_states_fedMulti05pqfullfreeze_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": 11.693649291992188,
+      "learning_rate": 2e-05,
+      "loss": 1.0507,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.9311091899871826,
+      "learning_rate": 2e-05,
+      "loss": 0.4164,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 8.45428466796875,
+      "learning_rate": 2e-05,
+      "loss": 1.1758,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 14.28290843963623,
+      "learning_rate": 2e-05,
+      "loss": 1.3931,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 15.484107971191406,
+      "learning_rate": 2e-05,
+      "loss": 1.6668,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 9.924738883972168,
+      "learning_rate": 2e-05,
+      "loss": 1.5835,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 8.884476661682129,
+      "learning_rate": 2e-05,
+      "loss": 1.1145,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 9.459785461425781,
+      "learning_rate": 2e-05,
+      "loss": 0.9232,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 9.546226501464844,
+      "learning_rate": 2e-05,
+      "loss": 0.5492,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.949314594268799,
+      "learning_rate": 2e-05,
+      "loss": 0.744,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 5.894227027893066,
+      "learning_rate": 2e-05,
+      "loss": 0.6446,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.924652099609375,
+      "learning_rate": 2e-05,
+      "loss": 0.8909,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.6994128227233887,
+      "learning_rate": 2e-05,
+      "loss": 0.4439,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 8.177955627441406,
+      "learning_rate": 2e-05,
+      "loss": 0.4963,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 9.719780921936035,
+      "learning_rate": 2e-05,
+      "loss": 0.8525,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 22.681800842285156,
+      "learning_rate": 2e-05,
+      "loss": 1.8416,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.0644638538360596,
+      "learning_rate": 2e-05,
+      "loss": 2.1517,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 14.563640594482422,
+      "learning_rate": 2e-05,
+      "loss": 2.4433,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 7.03754186630249,
+      "learning_rate": 2e-05,
+      "loss": 1.3491,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.36046838760376,
+      "learning_rate": 2e-05,
+      "loss": 1.1212,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 18.849185943603516,
+      "learning_rate": 2e-05,
+      "loss": 1.6678,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 14.333285331726074,
+      "learning_rate": 2e-05,
+      "loss": 1.6081,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 6.0595269203186035,
+      "learning_rate": 2e-05,
+      "loss": 0.6205,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.74971342086792,
+      "learning_rate": 2e-05,
+      "loss": 0.4097,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 7.75990104675293,
+      "learning_rate": 2e-05,
+      "loss": 1.074,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 9.010882377624512,
+      "learning_rate": 2e-05,
+      "loss": 2.1047,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.1840580701828003,
+      "learning_rate": 2e-05,
+      "loss": 0.8681,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.5251049995422363,
+      "learning_rate": 2e-05,
+      "loss": 0.7495,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 6.284056186676025,
+      "learning_rate": 2e-05,
+      "loss": 0.8752,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 8.168758392333984,
+      "learning_rate": 2e-05,
+      "loss": 1.3925,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 6.6547770500183105,
+      "learning_rate": 2e-05,
+      "loss": 0.7414,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.461399078369141,
+      "learning_rate": 2e-05,
+      "loss": 0.8258,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 6.963188648223877,
+      "learning_rate": 2e-05,
+      "loss": 1.218,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 5.871964454650879,
+      "learning_rate": 2e-05,
+      "loss": 1.1124,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 7.110522747039795,
+      "learning_rate": 2e-05,
+      "loss": 1.2579,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 8.83693790435791,
+      "learning_rate": 2e-05,
+      "loss": 2.2598,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 7.1040520668029785,
+      "learning_rate": 2e-05,
+      "loss": 1.2506,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 17.06218719482422,
+      "learning_rate": 2e-05,
+      "loss": 1.4432,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 7.473016262054443,
+      "learning_rate": 2e-05,
+      "loss": 0.784,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 8.905854225158691,
+      "learning_rate": 2e-05,
+      "loss": 0.8411,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.500631332397461,
+      "learning_rate": 2e-05,
+      "loss": 0.2397,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.327226638793945,
+      "learning_rate": 2e-05,
+      "loss": 0.4464,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.575321674346924,
+      "learning_rate": 2e-05,
+      "loss": 1.1319,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.218846321105957,
+      "learning_rate": 2e-05,
+      "loss": 0.8927,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 7.213256359100342,
+      "learning_rate": 2e-05,
+      "loss": 0.9017,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 10.291433334350586,
+      "learning_rate": 2e-05,
+      "loss": 0.6296,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 6.705934524536133,
+      "learning_rate": 2e-05,
+      "loss": 0.6399,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.8862531185150146,
+      "learning_rate": 2e-05,
+      "loss": 0.3221,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 9.070793151855469,
+      "learning_rate": 2e-05,
+      "loss": 1.1441,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.29675006866455,
+      "learning_rate": 2e-05,
+      "loss": 1.2231,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2097655350034432.0,
+      "train_loss": 1.0705613040924071,
+      "train_runtime": 102.5888,
+      "train_samples_per_second": 3.899,
+      "train_steps_per_second": 0.975
+    }
+  ],
+  "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_fedMulti05pqfullfreeze_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 sha256:63c020f0e9a8f0c812148e6b98c897be1fbf16e0e6bdf9c1cb855bd2fb184967
+size 395787774

client_states_fedMulti05pqfullfreeze_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:a576f6efc9cbd3bb8a501153bc3e085ec89a15902ad8cfe10bc4b974f03e4fcd
+size 395787774

client_states_fedMulti05pqfullfreeze_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 sha256:5db05f3d3601799e1fc60bea63f67d5557eee27fabad09326273c4391caa1f03
+size 395787774

client_states_fedMulti05pqfullfreeze_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 sha256:7b1615aeafa8813c4d2376f2ae7a14b957139e2e63d429b39c3fb322e8bde63a
+size 395787774

client_states_fedMulti05pqfullfreeze_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 sha256:6ba947d6751d0af4d240a2ac8b103cec9438b64bef846a3c69fd34bf8554f5df
+size 395786922

client_states_fedMulti05pqfullfreeze_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 sha256:56fa94a36ca7fe11a494c594eb9b640dd6ee9b47daeee27e2fee4d62575c6f43
+size 395787774

client_states_fedMulti05pqfullfreeze_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:ac555e618f6ec228443d7e19fcd469b8ef8e5bea20f651ef5cde9cdf85221ad9
+size 395786922

client_states_fedMulti05pqfullfreeze_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 sha256:9e7a27691ec0a074141418aadc3a9c16e25bbeb6a18c82bc76883e6acb92cb24
+size 395786922

client_states_fedMulti05pqfullfreeze_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": 2.637403726577759,
+      "learning_rate": 2e-05,
+      "loss": 0.5614,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.73873233795166,
+      "learning_rate": 2e-05,
+      "loss": 0.9697,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.6665256023406982,
+      "learning_rate": 2e-05,
+      "loss": 0.4683,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.0230000019073486,
+      "learning_rate": 2e-05,
+      "loss": 0.6475,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.887681245803833,
+      "learning_rate": 2e-05,
+      "loss": 0.5517,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.429380416870117,
+      "learning_rate": 2e-05,
+      "loss": 0.2907,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 4.610021114349365,
+      "learning_rate": 2e-05,
+      "loss": 0.6544,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 8.516341209411621,
+      "learning_rate": 2e-05,
+      "loss": 1.9958,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.5461740493774414,
+      "learning_rate": 2e-05,
+      "loss": 0.3917,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.2099456787109375,
+      "learning_rate": 2e-05,
+      "loss": 0.4288,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 4.585675239562988,
+      "learning_rate": 2e-05,
+      "loss": 1.801,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.1597061157226562,
+      "learning_rate": 2e-05,
+      "loss": 1.0035,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.1741673946380615,
+      "learning_rate": 2e-05,
+      "loss": 0.4851,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.476759433746338,
+      "learning_rate": 2e-05,
+      "loss": 1.1165,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.2731804847717285,
+      "learning_rate": 2e-05,
+      "loss": 0.9401,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 6.725061893463135,
+      "learning_rate": 2e-05,
+      "loss": 0.7967,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.4326884746551514,
+      "learning_rate": 2e-05,
+      "loss": 0.4525,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 4.693164348602295,
+      "learning_rate": 2e-05,
+      "loss": 1.2137,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.8988044261932373,
+      "learning_rate": 2e-05,
+      "loss": 0.5093,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.970594882965088,
+      "learning_rate": 2e-05,
+      "loss": 1.0991,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.4238510131835938,
+      "learning_rate": 2e-05,
+      "loss": 0.8502,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.9824445247650146,
+      "learning_rate": 2e-05,
+      "loss": 0.6589,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.8126678466796875,
+      "learning_rate": 2e-05,
+      "loss": 0.8948,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.100122451782227,
+      "learning_rate": 2e-05,
+      "loss": 0.8117,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.1359190940856934,
+      "learning_rate": 2e-05,
+      "loss": 0.4148,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 5.385488033294678,
+      "learning_rate": 2e-05,
+      "loss": 1.6419,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.634507656097412,
+      "learning_rate": 2e-05,
+      "loss": 0.8469,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.4589309692382812,
+      "learning_rate": 2e-05,
+      "loss": 0.2448,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.612209796905518,
+      "learning_rate": 2e-05,
+      "loss": 0.836,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2502317428588867,
+      "learning_rate": 2e-05,
+      "loss": 0.8215,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.3926491737365723,
+      "learning_rate": 2e-05,
+      "loss": 0.6394,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.6580755710601807,
+      "learning_rate": 2e-05,
+      "loss": 1.1433,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 7.191780090332031,
+      "learning_rate": 2e-05,
+      "loss": 1.0154,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.0875039100646973,
+      "learning_rate": 2e-05,
+      "loss": 0.6591,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 7.09459114074707,
+      "learning_rate": 2e-05,
+      "loss": 0.8218,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.325845241546631,
+      "learning_rate": 2e-05,
+      "loss": 0.6073,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.3921314477920532,
+      "learning_rate": 2e-05,
+      "loss": 0.5865,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.6516613960266113,
+      "learning_rate": 2e-05,
+      "loss": 1.4063,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 4.696588039398193,
+      "learning_rate": 2e-05,
+      "loss": 0.7179,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.545356512069702,
+      "learning_rate": 2e-05,
+      "loss": 0.4085,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.8088479042053223,
+      "learning_rate": 2e-05,
+      "loss": 0.5266,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 5.2242326736450195,
+      "learning_rate": 2e-05,
+      "loss": 0.6016,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.499507427215576,
+      "learning_rate": 2e-05,
+      "loss": 0.3916,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.5232198238372803,
+      "learning_rate": 2e-05,
+      "loss": 0.5096,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.562027931213379,
+      "learning_rate": 2e-05,
+      "loss": 0.7677,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 6.415626525878906,
+      "learning_rate": 2e-05,
+      "loss": 0.7187,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 5.6967644691467285,
+      "learning_rate": 2e-05,
+      "loss": 0.7985,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.2610225677490234,
+      "learning_rate": 2e-05,
+      "loss": 0.6187,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.403749942779541,
+      "learning_rate": 2e-05,
+      "loss": 0.2896,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.633613586425781,
+      "learning_rate": 2e-05,
+      "loss": 1.1527,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5694661670731776.0,
+      "train_loss": 0.7755919742584229,
+      "train_runtime": 170.0795,
+      "train_samples_per_second": 2.352,
+      "train_steps_per_second": 0.588
+    }
+  ],
+  "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_fedMulti05pqfullfreeze_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 sha256:75fce352d5052d2b03312c457b9d07a3c2045a3c1d82fa169cde815ffac140a0
+size 395787774

client_states_fedMulti05pqfullfreeze_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 sha256:51efd3d761dbc6a85da1d36fd13afc6913e8f35c7c18b9825c9a03ebd8725119
+size 395787774

client_states_fedMulti05pqfullfreeze_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 sha256:04acc4730d61aa5cab2b5961a914144dea9077c80a98ea800ef7b634fb202740
+size 395787774

client_states_fedMulti05pqfullfreeze_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:c21f2c0bf74b5e28d521eff1cae89902767d9acad0a560a77818c53885c72763
+size 395787774

client_states_fedMulti05pqfullfreeze_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:cf27c9f6c67ee9af8765ac0ea5533f11f5d1e729b6e3d53daf4b640cb3853670
+size 395786922