Upload folder using huggingface_hub

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f048edeeae0416ad7b7f9f2792337738fc29b8a5b3ea5d0ea8bd65f2aa4a87
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f659985e12bae8ddcb3e2085c76d2fab78ebd016d6b6b42328072004da80bef
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a37d501618e1daaffd7e7dfe10add752fece1b8fa1816fd33517b70445f92ae
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c43b66a035428128328ebe2671d6b3c71616a3b2b3918892d9d6da8f2b6a37a2
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e2676be52628a62f3b8f3f6c07704f6d8b7ebe703d9a0d2ed8a9536cc0bdf7
+size 184220842

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6acb660cb111fc4efdbb99a763250dfe13355017d0368f2751edbc2f602d45e
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6267c048c9cad023c945c6521f9ec58a43f7a09ac53f002702c4adb63ae098c1
+size 184220842

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/0_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.1532974243164062,
+      "learning_rate": 2e-05,
+      "loss": 0.1816,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.5308837890625,
+      "learning_rate": 2e-05,
+      "loss": 0.2659,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.6874430179595947,
+      "learning_rate": 2e-05,
+      "loss": 0.1328,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.168386459350586,
+      "learning_rate": 2e-05,
+      "loss": 0.4946,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.49451756477355957,
+      "learning_rate": 2e-05,
+      "loss": 0.0704,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.3002219200134277,
+      "learning_rate": 2e-05,
+      "loss": 0.134,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.6663122177124023,
+      "learning_rate": 2e-05,
+      "loss": 0.2808,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.072387933731079,
+      "learning_rate": 2e-05,
+      "loss": 0.2126,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 9.23437213897705,
+      "learning_rate": 2e-05,
+      "loss": 0.2095,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.610624074935913,
+      "learning_rate": 2e-05,
+      "loss": 0.189,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.139845371246338,
+      "learning_rate": 2e-05,
+      "loss": 0.1157,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.2783198356628418,
+      "learning_rate": 2e-05,
+      "loss": 0.1091,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.6409637928009033,
+      "learning_rate": 2e-05,
+      "loss": 0.3108,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.5853898525238037,
+      "learning_rate": 2e-05,
+      "loss": 0.1641,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.854699611663818,
+      "learning_rate": 2e-05,
+      "loss": 0.335,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.4038703441619873,
+      "learning_rate": 2e-05,
+      "loss": 0.3679,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.0609790086746216,
+      "learning_rate": 2e-05,
+      "loss": 0.1128,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 6.019529342651367,
+      "learning_rate": 2e-05,
+      "loss": 0.377,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 5.390917778015137,
+      "learning_rate": 2e-05,
+      "loss": 0.5391,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.0058133602142334,
+      "learning_rate": 2e-05,
+      "loss": 0.3828,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.898128032684326,
+      "learning_rate": 2e-05,
+      "loss": 0.2788,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 8.558566093444824,
+      "learning_rate": 2e-05,
+      "loss": 0.2646,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.090677738189697,
+      "learning_rate": 2e-05,
+      "loss": 0.3008,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.0819746255874634,
+      "learning_rate": 2e-05,
+      "loss": 0.1235,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.556148648262024,
+      "learning_rate": 2e-05,
+      "loss": 0.2378,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.5604588985443115,
+      "learning_rate": 2e-05,
+      "loss": 0.1197,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 6.361417293548584,
+      "learning_rate": 2e-05,
+      "loss": 0.5151,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 8.687939643859863,
+      "learning_rate": 2e-05,
+      "loss": 0.4375,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.642131805419922,
+      "learning_rate": 2e-05,
+      "loss": 0.1611,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.859739899635315,
+      "learning_rate": 2e-05,
+      "loss": 0.145,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.98333740234375,
+      "learning_rate": 2e-05,
+      "loss": 0.2485,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.8972673416137695,
+      "learning_rate": 2e-05,
+      "loss": 0.3062,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.5855597257614136,
+      "learning_rate": 2e-05,
+      "loss": 0.0764,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5774495601654053,
+      "learning_rate": 2e-05,
+      "loss": 0.2243,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.549870491027832,
+      "learning_rate": 2e-05,
+      "loss": 0.1746,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.2936458587646484,
+      "learning_rate": 2e-05,
+      "loss": 0.1777,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.4894068241119385,
+      "learning_rate": 2e-05,
+      "loss": 0.2368,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.257445216178894,
+      "learning_rate": 2e-05,
+      "loss": 0.2021,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.4454576969146729,
+      "learning_rate": 2e-05,
+      "loss": 0.2573,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.781729817390442,
+      "learning_rate": 2e-05,
+      "loss": 0.3301,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.1323760747909546,
+      "learning_rate": 2e-05,
+      "loss": 0.2344,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.8015055656433105,
+      "learning_rate": 2e-05,
+      "loss": 0.2842,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.7761592864990234,
+      "learning_rate": 2e-05,
+      "loss": 0.2563,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.44229793548584,
+      "learning_rate": 2e-05,
+      "loss": 0.3269,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.4079943895339966,
+      "learning_rate": 2e-05,
+      "loss": 0.0944,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.248412013053894,
+      "learning_rate": 2e-05,
+      "loss": 0.0981,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.023442029953003,
+      "learning_rate": 2e-05,
+      "loss": 0.2021,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.4544942378997803,
+      "learning_rate": 2e-05,
+      "loss": 0.1582,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.772751808166504,
+      "learning_rate": 2e-05,
+      "loss": 0.3203,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.914933204650879,
+      "learning_rate": 2e-05,
+      "loss": 0.2764,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 7701031911686144.0,
+      "train_loss": 0.2410992431640625,
+      "train_runtime": 131.5542,
+      "train_samples_per_second": 3.041,
+      "train_steps_per_second": 0.76
+    }
+  ],
+  "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": 7701031911686144.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:862e841f586a1c676f224be608aa692b886b7366e91b75fd7f3f323a8a0f91c5
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a47f67299db2d5c43a298b51f3e39d377dc18aef7748c10de43712b98a930f87
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f2cbfd611d51913c4b60f603ee754be14e2bc54d9961b19eedf6ff2a5b1016
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d493f9638fa837605913c7d31467443088dcf2e02f2a3e11a71f91a35e94cb5f
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd09122dbd315f1ebe87e6a37f8f6dc074b417dd38097de08d440ec9d3a2e2d
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81471f5290c52a449ab14b0b65bd543c3895eaa8f69746d8daf31ea97941630
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d518b951cd3a3a93775687e6f0fff685850372c1b9c8012bc70dd66bdfc65e
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/1_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.795502185821533,
+      "learning_rate": 2e-05,
+      "loss": 0.4502,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 7.123850345611572,
+      "learning_rate": 2e-05,
+      "loss": 0.2979,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.156874895095825,
+      "learning_rate": 2e-05,
+      "loss": 0.4004,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.2159154415130615,
+      "learning_rate": 2e-05,
+      "loss": 0.2393,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.0778675079345703,
+      "learning_rate": 2e-05,
+      "loss": 0.2959,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.9174330234527588,
+      "learning_rate": 2e-05,
+      "loss": 0.23,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.9123361110687256,
+      "learning_rate": 2e-05,
+      "loss": 0.2988,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.2561991214752197,
+      "learning_rate": 2e-05,
+      "loss": 0.2856,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.6939635276794434,
+      "learning_rate": 2e-05,
+      "loss": 0.2378,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.499593734741211,
+      "learning_rate": 2e-05,
+      "loss": 0.2441,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.4911894798278809,
+      "learning_rate": 2e-05,
+      "loss": 0.2573,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.8584893941879272,
+      "learning_rate": 2e-05,
+      "loss": 0.2583,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.9822528958320618,
+      "learning_rate": 2e-05,
+      "loss": 0.1914,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.0371787548065186,
+      "learning_rate": 2e-05,
+      "loss": 0.2124,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.5427534580230713,
+      "learning_rate": 2e-05,
+      "loss": 0.3652,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.590794086456299,
+      "learning_rate": 2e-05,
+      "loss": 0.3633,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.0113798379898071,
+      "learning_rate": 2e-05,
+      "loss": 0.2529,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.576972007751465,
+      "learning_rate": 2e-05,
+      "loss": 0.3379,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.8894009590148926,
+      "learning_rate": 2e-05,
+      "loss": 0.1487,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.6677130460739136,
+      "learning_rate": 2e-05,
+      "loss": 0.2422,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.960363507270813,
+      "learning_rate": 2e-05,
+      "loss": 0.23,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.1358486413955688,
+      "learning_rate": 2e-05,
+      "loss": 0.2861,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.0046958923339844,
+      "learning_rate": 2e-05,
+      "loss": 0.2102,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.3224812746047974,
+      "learning_rate": 2e-05,
+      "loss": 0.1543,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.1381001472473145,
+      "learning_rate": 2e-05,
+      "loss": 0.291,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.2688443660736084,
+      "learning_rate": 2e-05,
+      "loss": 0.418,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.68595027923584,
+      "learning_rate": 2e-05,
+      "loss": 0.3213,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.9931286573410034,
+      "learning_rate": 2e-05,
+      "loss": 0.1438,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.6896065473556519,
+      "learning_rate": 2e-05,
+      "loss": 0.1997,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.1000540256500244,
+      "learning_rate": 2e-05,
+      "loss": 0.2114,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.9265353679656982,
+      "learning_rate": 2e-05,
+      "loss": 0.3818,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.8865680694580078,
+      "learning_rate": 2e-05,
+      "loss": 0.1777,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.9666782021522522,
+      "learning_rate": 2e-05,
+      "loss": 0.3721,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.9722671508789062,
+      "learning_rate": 2e-05,
+      "loss": 0.3564,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.222570538520813,
+      "learning_rate": 2e-05,
+      "loss": 0.2876,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.2904052734375,
+      "learning_rate": 2e-05,
+      "loss": 0.2578,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.8825144171714783,
+      "learning_rate": 2e-05,
+      "loss": 0.1953,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.4329357147216797,
+      "learning_rate": 2e-05,
+      "loss": 0.2642,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.1460537910461426,
+      "learning_rate": 2e-05,
+      "loss": 0.2012,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.055041790008545,
+      "learning_rate": 2e-05,
+      "loss": 0.375,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.1837732791900635,
+      "learning_rate": 2e-05,
+      "loss": 0.1755,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5480858683586121,
+      "learning_rate": 2e-05,
+      "loss": 0.2344,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.649846076965332,
+      "learning_rate": 2e-05,
+      "loss": 0.2607,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.002662420272827,
+      "learning_rate": 2e-05,
+      "loss": 0.293,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.9865012168884277,
+      "learning_rate": 2e-05,
+      "loss": 0.2837,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.9601739645004272,
+      "learning_rate": 2e-05,
+      "loss": 0.229,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.8378078937530518,
+      "learning_rate": 2e-05,
+      "loss": 0.2446,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.87432599067688,
+      "learning_rate": 2e-05,
+      "loss": 0.1914,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.0967655181884766,
+      "learning_rate": 2e-05,
+      "loss": 0.2163,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.495866298675537,
+      "learning_rate": 2e-05,
+      "loss": 0.4033,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.831939061317632e+16,
+      "train_loss": 0.26953125,
+      "train_runtime": 299.3537,
+      "train_samples_per_second": 1.336,
+      "train_steps_per_second": 0.334
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.831939061317632e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6800d8fcd8a44b1c01a78c6c6890ecc2956b614b6ba920f4bb87a5f8d8e4c748
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e5a8ce7bc39561a501c60630ae8dafac8338484aacee6b5125323fb9ef9e63
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c19634f1d59ccc9db509bfc651785d9d701b9e1214b28194d1e32130c68942e9
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e5e95996c2f65cbe0260fb0a724fbca36c8a324260c923816549abc2b8066a1
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610a9e886ebc23a684c2556c9c2b8df5aa416eb9e371df693511c0b9decd2ac7
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d9e44c9d7387e5da58daa1b6f726d227c6b35aa9205ac6d9356d4368ac9c43
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5381594d86e32d600599a4a380d04480915dab7c210a74a9324f1f21f1d8602
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/2_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.500993728637695,
+      "learning_rate": 2e-05,
+      "loss": 0.2593,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.6622408628463745,
+      "learning_rate": 2e-05,
+      "loss": 0.1311,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.778311252593994,
+      "learning_rate": 2e-05,
+      "loss": 0.1947,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.542095184326172,
+      "learning_rate": 2e-05,
+      "loss": 0.1447,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.3226494789123535,
+      "learning_rate": 2e-05,
+      "loss": 0.4307,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.877063751220703,
+      "learning_rate": 2e-05,
+      "loss": 0.2231,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.632908821105957,
+      "learning_rate": 2e-05,
+      "loss": 0.271,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.6585263013839722,
+      "learning_rate": 2e-05,
+      "loss": 0.2805,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.8262925148010254,
+      "learning_rate": 2e-05,
+      "loss": 0.2764,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.506618022918701,
+      "learning_rate": 2e-05,
+      "loss": 0.2051,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.5826640129089355,
+      "learning_rate": 2e-05,
+      "loss": 0.2397,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.7919895648956299,
+      "learning_rate": 2e-05,
+      "loss": 0.3066,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.0978145599365234,
+      "learning_rate": 2e-05,
+      "loss": 0.1675,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.73683500289917,
+      "learning_rate": 2e-05,
+      "loss": 0.2996,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.0620052814483643,
+      "learning_rate": 2e-05,
+      "loss": 0.1465,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.346411943435669,
+      "learning_rate": 2e-05,
+      "loss": 0.1645,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 7.4767560958862305,
+      "learning_rate": 2e-05,
+      "loss": 0.2744,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 7.579076766967773,
+      "learning_rate": 2e-05,
+      "loss": 0.2686,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.5238951444625854,
+      "learning_rate": 2e-05,
+      "loss": 0.1636,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.760282039642334,
+      "learning_rate": 2e-05,
+      "loss": 0.1401,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 5.585556983947754,
+      "learning_rate": 2e-05,
+      "loss": 0.2896,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.5539571046829224,
+      "learning_rate": 2e-05,
+      "loss": 0.093,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.4564839601516724,
+      "learning_rate": 2e-05,
+      "loss": 0.2954,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.2913273572921753,
+      "learning_rate": 2e-05,
+      "loss": 0.0901,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 10.594887733459473,
+      "learning_rate": 2e-05,
+      "loss": 0.4326,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.127068519592285,
+      "learning_rate": 2e-05,
+      "loss": 0.2397,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.24247407913208,
+      "learning_rate": 2e-05,
+      "loss": 0.2363,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.8992795944213867,
+      "learning_rate": 2e-05,
+      "loss": 0.1558,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.954968214035034,
+      "learning_rate": 2e-05,
+      "loss": 0.1824,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.740546226501465,
+      "learning_rate": 2e-05,
+      "loss": 0.2222,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 17.958728790283203,
+      "learning_rate": 2e-05,
+      "loss": 0.499,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.034136414527893,
+      "learning_rate": 2e-05,
+      "loss": 0.1609,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.5941245555877686,
+      "learning_rate": 2e-05,
+      "loss": 0.2295,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 4.146021366119385,
+      "learning_rate": 2e-05,
+      "loss": 0.2334,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.400031566619873,
+      "learning_rate": 2e-05,
+      "loss": 0.2266,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.742607593536377,
+      "learning_rate": 2e-05,
+      "loss": 0.147,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.9525485038757324,
+      "learning_rate": 2e-05,
+      "loss": 0.3354,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.062930583953857,
+      "learning_rate": 2e-05,
+      "loss": 0.416,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.0584497451782227,
+      "learning_rate": 2e-05,
+      "loss": 0.0496,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.931713581085205,
+      "learning_rate": 2e-05,
+      "loss": 0.1848,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 6.437009811401367,
+      "learning_rate": 2e-05,
+      "loss": 0.2666,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.580648422241211,
+      "learning_rate": 2e-05,
+      "loss": 0.1194,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.208071708679199,
+      "learning_rate": 2e-05,
+      "loss": 0.1509,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.544546365737915,
+      "learning_rate": 2e-05,
+      "loss": 0.2412,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.1570082902908325,
+      "learning_rate": 2e-05,
+      "loss": 0.1213,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.188741445541382,
+      "learning_rate": 2e-05,
+      "loss": 0.1851,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 6.331286907196045,
+      "learning_rate": 2e-05,
+      "loss": 0.4678,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 6.169668197631836,
+      "learning_rate": 2e-05,
+      "loss": 0.4053,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 6.514842987060547,
+      "learning_rate": 2e-05,
+      "loss": 0.3701,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.544450283050537,
+      "learning_rate": 2e-05,
+      "loss": 0.3462,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2.5000877441941504e+16,
+      "train_loss": 0.2396124267578125,
+      "train_runtime": 418.5446,
+      "train_samples_per_second": 0.956,
+      "train_steps_per_second": 0.239
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.5000877441941504e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c800361006c36cae06345537c17aa1ebe5cd8fa7b63429b8249e2b1ccc24633
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6059d8c192ee065ff92661071237aa6cfea2f02b83455767975c607c6f3649c1
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:935133e0149822c4a34dd759b493a6713664bd5e09d44772092f3222f89ee5aa
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d9c34eb9721154cc0e36769763604db7eea5b8afdc5c8f85bd90bd4bf5dcd1e
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9019999c7aff8abd359ea6e2ac0408ee22f1340a521441c4b015ff79533b4d
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d07f1b1d9a4f315355f5ca5a8032533eec95d13f9f24793cd9aca5f86448c0a
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eacae0fbc3c56a083011c152fbbdaba320c97036c2e5f16c3c2f959e5bdffc1
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/3_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.0025649070739746,
+      "learning_rate": 2e-05,
+      "loss": 0.2485,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.7948851585388184,
+      "learning_rate": 2e-05,
+      "loss": 0.5361,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.8121417760848999,
+      "learning_rate": 2e-05,
+      "loss": 0.2241,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.123253345489502,
+      "learning_rate": 2e-05,
+      "loss": 0.2559,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.336986780166626,
+      "learning_rate": 2e-05,
+      "loss": 0.2471,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.3932501077651978,
+      "learning_rate": 2e-05,
+      "loss": 0.1479,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.0414385795593262,
+      "learning_rate": 2e-05,
+      "loss": 0.1372,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.6982548832893372,
+      "learning_rate": 2e-05,
+      "loss": 0.2161,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.9259173274040222,
+      "learning_rate": 2e-05,
+      "loss": 0.3291,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6017290949821472,
+      "learning_rate": 2e-05,
+      "loss": 0.1797,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.1265554428100586,
+      "learning_rate": 2e-05,
+      "loss": 0.2627,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.754398822784424,
+      "learning_rate": 2e-05,
+      "loss": 0.3145,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.5871934294700623,
+      "learning_rate": 2e-05,
+      "loss": 0.2012,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.5588992834091187,
+      "learning_rate": 2e-05,
+      "loss": 0.3711,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.080377221107483,
+      "learning_rate": 2e-05,
+      "loss": 0.3604,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.06168794631958,
+      "learning_rate": 2e-05,
+      "loss": 0.2402,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.801756739616394,
+      "learning_rate": 2e-05,
+      "loss": 0.1768,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.4924569129943848,
+      "learning_rate": 2e-05,
+      "loss": 0.2217,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.4915250539779663,
+      "learning_rate": 2e-05,
+      "loss": 0.2451,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.8517245054244995,
+      "learning_rate": 2e-05,
+      "loss": 0.207,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.141131639480591,
+      "learning_rate": 2e-05,
+      "loss": 0.2334,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.9605770111083984,
+      "learning_rate": 2e-05,
+      "loss": 0.3008,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.275175929069519,
+      "learning_rate": 2e-05,
+      "loss": 0.2686,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.7505128383636475,
+      "learning_rate": 2e-05,
+      "loss": 0.1169,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.3512696027755737,
+      "learning_rate": 2e-05,
+      "loss": 0.2925,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.6239995956420898,
+      "learning_rate": 2e-05,
+      "loss": 0.0778,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 8.274873733520508,
+      "learning_rate": 2e-05,
+      "loss": 0.3345,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.730467677116394,
+      "learning_rate": 2e-05,
+      "loss": 0.2661,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.204479217529297,
+      "learning_rate": 2e-05,
+      "loss": 0.1787,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.446319580078125,
+      "learning_rate": 2e-05,
+      "loss": 0.1968,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.5213268995285034,
+      "learning_rate": 2e-05,
+      "loss": 0.1399,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.9250975251197815,
+      "learning_rate": 2e-05,
+      "loss": 0.3188,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.3367539644241333,
+      "learning_rate": 2e-05,
+      "loss": 0.251,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 5.409438133239746,
+      "learning_rate": 2e-05,
+      "loss": 0.1094,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.181166172027588,
+      "learning_rate": 2e-05,
+      "loss": 0.1948,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.0822051763534546,
+      "learning_rate": 2e-05,
+      "loss": 0.1116,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 10.998620986938477,
+      "learning_rate": 2e-05,
+      "loss": 0.2512,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.5456011295318604,
+      "learning_rate": 2e-05,
+      "loss": 0.2617,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.227940797805786,
+      "learning_rate": 2e-05,
+      "loss": 0.269,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7067040801048279,
+      "learning_rate": 2e-05,
+      "loss": 0.1675,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.563961982727051,
+      "learning_rate": 2e-05,
+      "loss": 0.1489,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 12.330256462097168,
+      "learning_rate": 2e-05,
+      "loss": 0.2734,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.1151248216629028,
+      "learning_rate": 2e-05,
+      "loss": 0.3262,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.372849225997925,
+      "learning_rate": 2e-05,
+      "loss": 0.251,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.5705537796020508,
+      "learning_rate": 2e-05,
+      "loss": 0.187,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.64632511138916,
+      "learning_rate": 2e-05,
+      "loss": 0.2095,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.7962813973426819,
+      "learning_rate": 2e-05,
+      "loss": 0.1699,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.290016174316406,
+      "learning_rate": 2e-05,
+      "loss": 0.2295,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.72586989402771,
+      "learning_rate": 2e-05,
+      "loss": 0.1671,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6375048160552979,
+      "learning_rate": 2e-05,
+      "loss": 0.0822,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2.703806282334208e+16,
+      "train_loss": 0.230157470703125,
+      "train_runtime": 442.335,
+      "train_samples_per_second": 0.904,
+      "train_steps_per_second": 0.226
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.703806282334208e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874a0a2c0ac827b4eaf45ccddd3873af0e615dbbbf08df114a3ad58e829a146e
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12da84ffc55a8a548e476fcd520c03411a2d7b6e6b2622aa9aed6f3db764db4c
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aed93444b1374e9e94fbc40b6f6a40e43eeb8e18eafb7b783ceedf346829d30
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd1fb6feb80eb728f88abbfe63c5446cbbfd716b0e764a07f0417059ea7a0b0
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a59d4ff5fbbbb420881bf7d931967b88b54cce8e9b8f40815c7126074125511
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a41a550d740cb0f8a7ea2d46d715303cdde79c13a4fdcfcac36ad5ccfed1e982
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:509e77e3a5f04635b7a2f37e0b504792e39ab5f027ccd67faa80c0105d2b4fbc
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/4_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.7979049682617188,
+      "learning_rate": 2e-05,
+      "loss": 0.2332,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.8530945181846619,
+      "learning_rate": 2e-05,
+      "loss": 0.0725,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.4376585483551025,
+      "learning_rate": 2e-05,
+      "loss": 0.1489,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.372811198234558,
+      "learning_rate": 2e-05,
+      "loss": 0.0916,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.194847583770752,
+      "learning_rate": 2e-05,
+      "loss": 0.2046,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.073252558708191,
+      "learning_rate": 2e-05,
+      "loss": 0.1852,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.2176636904478073,
+      "learning_rate": 2e-05,
+      "loss": 0.0349,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.995069980621338,
+      "learning_rate": 2e-05,
+      "loss": 0.2549,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.7777777314186096,
+      "learning_rate": 2e-05,
+      "loss": 0.1458,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.9153635501861572,
+      "learning_rate": 2e-05,
+      "loss": 0.0589,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.5894811153411865,
+      "learning_rate": 2e-05,
+      "loss": 0.189,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.8403184413909912,
+      "learning_rate": 2e-05,
+      "loss": 0.3677,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 6.922029972076416,
+      "learning_rate": 2e-05,
+      "loss": 0.7754,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.2179768085479736,
+      "learning_rate": 2e-05,
+      "loss": 0.4561,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.006457328796387,
+      "learning_rate": 2e-05,
+      "loss": 0.4551,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.419265031814575,
+      "learning_rate": 2e-05,
+      "loss": 0.1953,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.8707253336906433,
+      "learning_rate": 2e-05,
+      "loss": 0.1899,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.0631970167160034,
+      "learning_rate": 2e-05,
+      "loss": 0.3623,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.6909946203231812,
+      "learning_rate": 2e-05,
+      "loss": 0.0984,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.8037109375,
+      "learning_rate": 2e-05,
+      "loss": 0.2969,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.13729023933410645,
+      "learning_rate": 2e-05,
+      "loss": 0.0875,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.0968855619430542,
+      "learning_rate": 2e-05,
+      "loss": 0.2334,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.9539963006973267,
+      "learning_rate": 2e-05,
+      "loss": 0.1895,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.4654781818389893,
+      "learning_rate": 2e-05,
+      "loss": 0.1545,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.7956494092941284,
+      "learning_rate": 2e-05,
+      "loss": 0.2256,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.6221271753311157,
+      "learning_rate": 2e-05,
+      "loss": 0.4038,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.8657891154289246,
+      "learning_rate": 2e-05,
+      "loss": 0.1365,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.6475398540496826,
+      "learning_rate": 2e-05,
+      "loss": 0.0962,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.2849177122116089,
+      "learning_rate": 2e-05,
+      "loss": 0.1753,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.8204646110534668,
+      "learning_rate": 2e-05,
+      "loss": 0.075,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.6790094375610352,
+      "learning_rate": 2e-05,
+      "loss": 0.1567,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 6.28656530380249,
+      "learning_rate": 2e-05,
+      "loss": 0.3691,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.1709206104278564,
+      "learning_rate": 2e-05,
+      "loss": 0.3486,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.12063116580247879,
+      "learning_rate": 2e-05,
+      "loss": 0.0579,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.6891348361968994,
+      "learning_rate": 2e-05,
+      "loss": 0.179,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.5351128578186035,
+      "learning_rate": 2e-05,
+      "loss": 0.2651,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.48907238245010376,
+      "learning_rate": 2e-05,
+      "loss": 0.2495,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.253840923309326,
+      "learning_rate": 2e-05,
+      "loss": 0.2278,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.225708484649658,
+      "learning_rate": 2e-05,
+      "loss": 0.1725,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.755949020385742,
+      "learning_rate": 2e-05,
+      "loss": 0.3335,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.792585372924805,
+      "learning_rate": 2e-05,
+      "loss": 0.229,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 8.50632095336914,
+      "learning_rate": 2e-05,
+      "loss": 0.5068,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.2268624305725098,
+      "learning_rate": 2e-05,
+      "loss": 0.1063,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.5307092666625977,
+      "learning_rate": 2e-05,
+      "loss": 0.3721,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.4677900075912476,
+      "learning_rate": 2e-05,
+      "loss": 0.058,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.4051296710968018,
+      "learning_rate": 2e-05,
+      "loss": 0.333,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.5520013570785522,
+      "learning_rate": 2e-05,
+      "loss": 0.0959,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.343193769454956,
+      "learning_rate": 2e-05,
+      "loss": 0.2673,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 8.007261276245117,
+      "learning_rate": 2e-05,
+      "loss": 0.2444,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1382752656936646,
+      "learning_rate": 2e-05,
+      "loss": 0.1812,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2.66822049857536e+16,
+      "train_loss": 0.226947021484375,
+      "train_runtime": 436.2411,
+      "train_samples_per_second": 0.917,
+      "train_steps_per_second": 0.229
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.66822049857536e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:571fd547f051f9af584566a2ddbe2e2394a44a00d743bb703279f3dbec5bb5a6
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b4cb9408427d40d220cc237ffe852eb3c96a58f271e2a503eebed3d6686c57
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:180d44335e1bda32c8d2feadaf08b1ec61d2aa1905c171f0e7febe4697bee9c1
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0d5ed7fc203ff982c04f189803c1f553cfc3575ee07cffea85a56eb0496781
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:799e3a37371b8beb19d4fb570cdc1673a48839d26180c40712d0b17432009cab
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a26dbc47705491d3a713c9daccad7308bdbf423af4a48163c9c0e19d4e4628
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddb891917158aee8803a1b70e15b4c47473c94bdda5c2de9d43be7ec9b4448e3
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/5_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": 2.549835443496704,
+      "learning_rate": 2e-05,
+      "loss": 0.4492,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.4158651828765869,
+      "learning_rate": 2e-05,
+      "loss": 0.0829,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 5.307398319244385,
+      "learning_rate": 2e-05,
+      "loss": 0.2295,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3566608726978302,
+      "learning_rate": 2e-05,
+      "loss": 0.0897,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.9706152081489563,
+      "learning_rate": 2e-05,
+      "loss": 0.2598,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.9534002542495728,
+      "learning_rate": 2e-05,
+      "loss": 0.3379,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.8293063640594482,
+      "learning_rate": 2e-05,
+      "loss": 0.0673,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.4109033346176147,
+      "learning_rate": 2e-05,
+      "loss": 0.188,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.8552109003067017,
+      "learning_rate": 2e-05,
+      "loss": 0.134,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.48601436614990234,
+      "learning_rate": 2e-05,
+      "loss": 0.1133,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.806236505508423,
+      "learning_rate": 2e-05,
+      "loss": 0.2446,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.574978828430176,
+      "learning_rate": 2e-05,
+      "loss": 0.2157,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.5801928639411926,
+      "learning_rate": 2e-05,
+      "loss": 0.2695,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.201779305934906,
+      "learning_rate": 2e-05,
+      "loss": 0.055,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.1705542653799057,
+      "learning_rate": 2e-05,
+      "loss": 0.0763,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.5239601731300354,
+      "learning_rate": 2e-05,
+      "loss": 0.0891,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.7213793396949768,
+      "learning_rate": 2e-05,
+      "loss": 0.1084,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 8.098418235778809,
+      "learning_rate": 2e-05,
+      "loss": 0.2583,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.6241951584815979,
+      "learning_rate": 2e-05,
+      "loss": 0.0559,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5840942859649658,
+      "learning_rate": 2e-05,
+      "loss": 0.0742,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.7002200484275818,
+      "learning_rate": 2e-05,
+      "loss": 0.098,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.7152146100997925,
+      "learning_rate": 2e-05,
+      "loss": 0.3774,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.125622510910034,
+      "learning_rate": 2e-05,
+      "loss": 0.215,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.45262452960014343,
+      "learning_rate": 2e-05,
+      "loss": 0.0374,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.5261863470077515,
+      "learning_rate": 2e-05,
+      "loss": 0.0385,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.1815991401672363,
+      "learning_rate": 2e-05,
+      "loss": 0.1992,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.572287380695343,
+      "learning_rate": 2e-05,
+      "loss": 0.0801,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6819407939910889,
+      "learning_rate": 2e-05,
+      "loss": 0.0903,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 5.11102819442749,
+      "learning_rate": 2e-05,
+      "loss": 0.1851,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.898163318634033,
+      "learning_rate": 2e-05,
+      "loss": 0.3965,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.501598060131073,
+      "learning_rate": 2e-05,
+      "loss": 0.0896,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.2187391519546509,
+      "learning_rate": 2e-05,
+      "loss": 0.3701,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.4092749357223511,
+      "learning_rate": 2e-05,
+      "loss": 0.0815,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.0137696266174316,
+      "learning_rate": 2e-05,
+      "loss": 0.2798,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.4367271363735199,
+      "learning_rate": 2e-05,
+      "loss": 0.1514,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.6051576733589172,
+      "learning_rate": 2e-05,
+      "loss": 0.0551,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.48240211606025696,
+      "learning_rate": 2e-05,
+      "loss": 0.1748,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.7057625651359558,
+      "learning_rate": 2e-05,
+      "loss": 0.127,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.536785125732422,
+      "learning_rate": 2e-05,
+      "loss": 0.2402,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.3254449367523193,
+      "learning_rate": 2e-05,
+      "loss": 0.2876,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.7100874781608582,
+      "learning_rate": 2e-05,
+      "loss": 0.0833,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.474085807800293,
+      "learning_rate": 2e-05,
+      "loss": 0.1663,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.025565659627318382,
+      "learning_rate": 2e-05,
+      "loss": 0.0882,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.122403144836426,
+      "learning_rate": 2e-05,
+      "loss": 0.0574,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.5345476269721985,
+      "learning_rate": 2e-05,
+      "loss": 0.1709,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.4158120155334473,
+      "learning_rate": 2e-05,
+      "loss": 0.1973,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.47550350427627563,
+      "learning_rate": 2e-05,
+      "loss": 0.1047,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.016447901725769,
+      "learning_rate": 2e-05,
+      "loss": 0.1031,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.8785897493362427,
+      "learning_rate": 2e-05,
+      "loss": 0.1536,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.1417903900146484,
+      "learning_rate": 2e-05,
+      "loss": 0.2004,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 3.162254698610688e+16,
+      "train_loss": 0.16597122192382813,
+      "train_runtime": 519.5813,
+      "train_samples_per_second": 0.77,
+      "train_steps_per_second": 0.192
+    }
+  ],
+  "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": 3.162254698610688e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1325415a5a8db5d42448c71fd3e2153ad55cc0e4ab5239ad88031fea5a24d078
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046d4ed192e5add6d134d4f682449a7f24ce73380119dbc179d0a7c75a7d389c
+size 184221358