Upload folder using huggingface_hub

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be795e425a5d7075f02bcfe4fdba702b3f4a3e2e6a3d24568b5ecb7742b9be4
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:887e60b457a7171a821e7871a0ac1e3d1f6b636237460b3a009dca4517d16002
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78830ea00219f3ab8d7def684eaf76650219e7485e437546e1063cb641384b16
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd7c02543def5cda3ee658b2596dfe8f19dad3f233f2edc88a7ad60838375445
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42460728f6212b8e84faeae4fb69f1132392c13071247a6520899c51c0794157
+size 184220842

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0566cecd95b8cfd97288a78a54d0276b978b8e14bc10a02dc4e3acde077ca9
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a5bda513396bb15e9746b4c13c779f4a11be27581445b4712425b479007d3a
+size 184220842

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef6a46f1defc563a93d9ae0e0aa84ce4dd35f623f57c366a21b7e660cbe9c90
+size 184220842

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_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": 4.8568243980407715,
+      "learning_rate": 2e-05,
+      "loss": 0.9372,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.345067977905273,
+      "learning_rate": 2e-05,
+      "loss": 0.9044,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 12.120655059814453,
+      "learning_rate": 2e-05,
+      "loss": 1.2838,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 5.687979698181152,
+      "learning_rate": 2e-05,
+      "loss": 2.4326,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.3347970247268677,
+      "learning_rate": 2e-05,
+      "loss": 0.3054,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.94572114944458,
+      "learning_rate": 2e-05,
+      "loss": 0.476,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 8.041915893554688,
+      "learning_rate": 2e-05,
+      "loss": 2.3675,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.2988779544830322,
+      "learning_rate": 2e-05,
+      "loss": 0.8773,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 10.082386016845703,
+      "learning_rate": 2e-05,
+      "loss": 1.2354,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.044953346252441,
+      "learning_rate": 2e-05,
+      "loss": 1.0228,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 5.216516494750977,
+      "learning_rate": 2e-05,
+      "loss": 0.8611,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.001774311065674,
+      "learning_rate": 2e-05,
+      "loss": 0.7416,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 5.1101155281066895,
+      "learning_rate": 2e-05,
+      "loss": 1.0476,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 6.11592960357666,
+      "learning_rate": 2e-05,
+      "loss": 0.9232,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 6.683459281921387,
+      "learning_rate": 2e-05,
+      "loss": 1.203,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.920234203338623,
+      "learning_rate": 2e-05,
+      "loss": 1.3295,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.9107036590576172,
+      "learning_rate": 2e-05,
+      "loss": 0.492,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 7.40504264831543,
+      "learning_rate": 2e-05,
+      "loss": 1.6457,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 8.718831062316895,
+      "learning_rate": 2e-05,
+      "loss": 2.8188,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.62222146987915,
+      "learning_rate": 2e-05,
+      "loss": 1.4451,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 7.5993452072143555,
+      "learning_rate": 2e-05,
+      "loss": 1.1404,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 11.086434364318848,
+      "learning_rate": 2e-05,
+      "loss": 0.7555,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.652540683746338,
+      "learning_rate": 2e-05,
+      "loss": 1.1318,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.010275363922119,
+      "learning_rate": 2e-05,
+      "loss": 0.5329,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 7.997224807739258,
+      "learning_rate": 2e-05,
+      "loss": 1.2541,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.179985284805298,
+      "learning_rate": 2e-05,
+      "loss": 0.4904,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 10.767970085144043,
+      "learning_rate": 2e-05,
+      "loss": 2.2404,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 5.549088001251221,
+      "learning_rate": 2e-05,
+      "loss": 1.4976,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 11.436861991882324,
+      "learning_rate": 2e-05,
+      "loss": 1.1036,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 7.861836910247803,
+      "learning_rate": 2e-05,
+      "loss": 0.8495,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 8.143918991088867,
+      "learning_rate": 2e-05,
+      "loss": 1.3565,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.367578029632568,
+      "learning_rate": 2e-05,
+      "loss": 1.9117,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.4422531127929688,
+      "learning_rate": 2e-05,
+      "loss": 0.2458,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.6072515845298767,
+      "learning_rate": 2e-05,
+      "loss": 0.4135,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.17832612991333,
+      "learning_rate": 2e-05,
+      "loss": 0.5555,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 4.957637786865234,
+      "learning_rate": 2e-05,
+      "loss": 0.7625,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 5.490946292877197,
+      "learning_rate": 2e-05,
+      "loss": 1.3255,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.61025071144104,
+      "learning_rate": 2e-05,
+      "loss": 0.7288,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.5497350692749023,
+      "learning_rate": 2e-05,
+      "loss": 1.277,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.070952892303467,
+      "learning_rate": 2e-05,
+      "loss": 1.5686,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.195366382598877,
+      "learning_rate": 2e-05,
+      "loss": 1.1058,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.0397443771362305,
+      "learning_rate": 2e-05,
+      "loss": 1.0513,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.9195706844329834,
+      "learning_rate": 2e-05,
+      "loss": 1.0052,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 6.697042465209961,
+      "learning_rate": 2e-05,
+      "loss": 1.3321,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.519200325012207,
+      "learning_rate": 2e-05,
+      "loss": 0.4151,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.2042155265808105,
+      "learning_rate": 2e-05,
+      "loss": 0.4957,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.8642756938934326,
+      "learning_rate": 2e-05,
+      "loss": 0.8047,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.016802787780762,
+      "learning_rate": 2e-05,
+      "loss": 0.7323,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 5.384059429168701,
+      "learning_rate": 2e-05,
+      "loss": 1.413,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.8328022956848145,
+      "learning_rate": 2e-05,
+      "loss": 1.0836,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5462826382524416.0,
+      "train_loss": 1.0986122703552246,
+      "train_runtime": 130.3604,
+      "train_samples_per_second": 3.068,
+      "train_steps_per_second": 0.767
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5462826382524416.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4edbe0cbb17d2990d159c0027f168bc857cbfb1a6bb449af22e6962cd89679f
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d6877435499f1e92528d26dbe10cb4c00a6fdc4fbf7631f55f64f0aaff855c
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90db85b5c464796d6a8bf43529e6b677026cc1a1c7b6ff1728a14708ac21f19a
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecfa816282c26cd8f9f71d7a2b6905d6343a7a07b564523e6ecc2a0da324ee0f
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b63e55b69b38ac055d7be4a13a4cdcb92abb460717b45b7b24d7405f9ab8c21
+size 184220842

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d83d0d78759cce8c50907c09cc9983be8eb443ec79b7712eb373aba07ca8a0
+size 184221358

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bd6627e16a20f099893f0d485c73a444e4df4ef3ca9cad9a95eadcfb6d943dd
+size 184220842

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13ccc291e872fe938a37933a665286eface4e5c9a0b4d14f9dfd930dccac439
+size 184220842

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_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": 11.147574424743652,
+      "learning_rate": 2e-05,
+      "loss": 1.3265,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.276861190795898,
+      "learning_rate": 2e-05,
+      "loss": 1.1753,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 7.431264400482178,
+      "learning_rate": 2e-05,
+      "loss": 1.4501,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.3549540042877197,
+      "learning_rate": 2e-05,
+      "loss": 0.7166,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.00397253036499,
+      "learning_rate": 2e-05,
+      "loss": 1.1938,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.596293926239014,
+      "learning_rate": 2e-05,
+      "loss": 0.983,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 8.429619789123535,
+      "learning_rate": 2e-05,
+      "loss": 1.1644,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.940812110900879,
+      "learning_rate": 2e-05,
+      "loss": 1.3457,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.7962863445281982,
+      "learning_rate": 2e-05,
+      "loss": 1.1819,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 8.068099975585938,
+      "learning_rate": 2e-05,
+      "loss": 1.009,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.047276258468628,
+      "learning_rate": 2e-05,
+      "loss": 0.9596,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 7.590549945831299,
+      "learning_rate": 2e-05,
+      "loss": 1.3425,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.109409809112549,
+      "learning_rate": 2e-05,
+      "loss": 0.9021,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 6.835687637329102,
+      "learning_rate": 2e-05,
+      "loss": 0.9056,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.146049976348877,
+      "learning_rate": 2e-05,
+      "loss": 1.2231,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.957376956939697,
+      "learning_rate": 2e-05,
+      "loss": 1.4825,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.7589638233184814,
+      "learning_rate": 2e-05,
+      "loss": 1.3005,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 12.209796905517578,
+      "learning_rate": 2e-05,
+      "loss": 1.1377,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 6.60794734954834,
+      "learning_rate": 2e-05,
+      "loss": 1.1643,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.360702991485596,
+      "learning_rate": 2e-05,
+      "loss": 1.1243,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 7.058619022369385,
+      "learning_rate": 2e-05,
+      "loss": 1.0932,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.354834794998169,
+      "learning_rate": 2e-05,
+      "loss": 1.4331,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.1146738529205322,
+      "learning_rate": 2e-05,
+      "loss": 1.3581,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.396064758300781,
+      "learning_rate": 2e-05,
+      "loss": 0.9706,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.462273597717285,
+      "learning_rate": 2e-05,
+      "loss": 1.08,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 7.432363510131836,
+      "learning_rate": 2e-05,
+      "loss": 1.8945,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.282905578613281,
+      "learning_rate": 2e-05,
+      "loss": 1.153,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.7390224933624268,
+      "learning_rate": 2e-05,
+      "loss": 0.6751,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 8.883049011230469,
+      "learning_rate": 2e-05,
+      "loss": 0.9915,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.453659534454346,
+      "learning_rate": 2e-05,
+      "loss": 0.9824,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 4.341336250305176,
+      "learning_rate": 2e-05,
+      "loss": 1.8174,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.2057862281799316,
+      "learning_rate": 2e-05,
+      "loss": 0.6967,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 5.3489861488342285,
+      "learning_rate": 2e-05,
+      "loss": 1.48,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 12.532249450683594,
+      "learning_rate": 2e-05,
+      "loss": 1.4761,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.928640365600586,
+      "learning_rate": 2e-05,
+      "loss": 1.1903,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 4.719779968261719,
+      "learning_rate": 2e-05,
+      "loss": 1.3064,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.3434858322143555,
+      "learning_rate": 2e-05,
+      "loss": 0.9087,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 8.262925148010254,
+      "learning_rate": 2e-05,
+      "loss": 1.1738,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.6751790046691895,
+      "learning_rate": 2e-05,
+      "loss": 0.9931,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 9.4998197555542,
+      "learning_rate": 2e-05,
+      "loss": 1.3631,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.2977250814437866,
+      "learning_rate": 2e-05,
+      "loss": 0.9746,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 7.485049724578857,
+      "learning_rate": 2e-05,
+      "loss": 1.0304,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 8.568105697631836,
+      "learning_rate": 2e-05,
+      "loss": 1.1331,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.983133316040039,
+      "learning_rate": 2e-05,
+      "loss": 1.3687,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 10.139394760131836,
+      "learning_rate": 2e-05,
+      "loss": 1.2744,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 8.025995254516602,
+      "learning_rate": 2e-05,
+      "loss": 1.285,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 14.446391105651855,
+      "learning_rate": 2e-05,
+      "loss": 1.0137,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.424881935119629,
+      "learning_rate": 2e-05,
+      "loss": 1.3005,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.0400640964508057,
+      "learning_rate": 2e-05,
+      "loss": 0.9536,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.7732696533203125,
+      "learning_rate": 2e-05,
+      "loss": 1.5835,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5436726839345152.0,
+      "train_loss": 1.1808644104003907,
+      "train_runtime": 130.6818,
+      "train_samples_per_second": 3.061,
+      "train_steps_per_second": 0.765
+    }
+  ],
+  "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": 5436726839345152.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dc4aafd5bfdf57ef9aad42de2e74a7ac673e61cf2c722f0c95701bfa756cfa8
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46edfaafcc538df7834bdf30131ba6a4bb123364e6dde600b7ef807a23ed65af
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe659fe724a0abd4f054f1ac7d2f5e441f32774d6c9232934e3c1d25d94edc8f
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c74d2e3920345856a13f9560ef7c49a1f452c76a757e6d685064411180785d4e
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193ef6ece51f6f5e122228060eb01453e17b76c19aec098941c5a36ab4cf05e2
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc33b8640d27b19a6e368461705556e6fc7a941e186befb2177025b283d6b87
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f44c40d282adf3fa4c7e8ab2c068b365fead07fb46193b2f764fb1d09b5c64a9
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef20b42802c8eb5161ff1f26d33dcc91a0b3f544c3183f0505a9ff3ab6b03953
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_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": 7.4485626220703125,
+      "learning_rate": 2e-05,
+      "loss": 0.9813,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.9862580299377441,
+      "learning_rate": 2e-05,
+      "loss": 0.3618,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 5.480435848236084,
+      "learning_rate": 2e-05,
+      "loss": 0.7232,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.3666605949401855,
+      "learning_rate": 2e-05,
+      "loss": 0.5558,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 8.656007766723633,
+      "learning_rate": 2e-05,
+      "loss": 1.5084,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.521378040313721,
+      "learning_rate": 2e-05,
+      "loss": 1.0171,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 7.8770294189453125,
+      "learning_rate": 2e-05,
+      "loss": 1.1928,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.125856876373291,
+      "learning_rate": 2e-05,
+      "loss": 0.9306,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.606194496154785,
+      "learning_rate": 2e-05,
+      "loss": 1.0293,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 6.488819599151611,
+      "learning_rate": 2e-05,
+      "loss": 0.7309,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 5.991289138793945,
+      "learning_rate": 2e-05,
+      "loss": 0.8452,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.130293607711792,
+      "learning_rate": 2e-05,
+      "loss": 1.3333,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.767559766769409,
+      "learning_rate": 2e-05,
+      "loss": 0.6951,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 7.329335689544678,
+      "learning_rate": 2e-05,
+      "loss": 1.1264,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.395749092102051,
+      "learning_rate": 2e-05,
+      "loss": 0.8407,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.593240737915039,
+      "learning_rate": 2e-05,
+      "loss": 0.6638,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 5.472085475921631,
+      "learning_rate": 2e-05,
+      "loss": 0.7324,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 7.004269123077393,
+      "learning_rate": 2e-05,
+      "loss": 1.0726,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.786731243133545,
+      "learning_rate": 2e-05,
+      "loss": 0.6328,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.682612419128418,
+      "learning_rate": 2e-05,
+      "loss": 0.6289,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 7.152703762054443,
+      "learning_rate": 2e-05,
+      "loss": 1.2498,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.1759555339813232,
+      "learning_rate": 2e-05,
+      "loss": 0.3251,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.7986321449279785,
+      "learning_rate": 2e-05,
+      "loss": 0.9933,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.8032745122909546,
+      "learning_rate": 2e-05,
+      "loss": 0.5448,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.621896982192993,
+      "learning_rate": 2e-05,
+      "loss": 1.1534,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 5.912569046020508,
+      "learning_rate": 2e-05,
+      "loss": 0.8669,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.9287352561950684,
+      "learning_rate": 2e-05,
+      "loss": 0.7631,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.8568964004516602,
+      "learning_rate": 2e-05,
+      "loss": 0.4661,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.823870897293091,
+      "learning_rate": 2e-05,
+      "loss": 0.6656,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.9624710083007812,
+      "learning_rate": 2e-05,
+      "loss": 1.1263,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 18.075254440307617,
+      "learning_rate": 2e-05,
+      "loss": 2.0835,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.5604605674743652,
+      "learning_rate": 2e-05,
+      "loss": 0.6604,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 5.896483898162842,
+      "learning_rate": 2e-05,
+      "loss": 1.2012,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 7.719961166381836,
+      "learning_rate": 2e-05,
+      "loss": 0.7057,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 7.1494951248168945,
+      "learning_rate": 2e-05,
+      "loss": 0.8958,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.3935749530792236,
+      "learning_rate": 2e-05,
+      "loss": 0.5964,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.0517525672912598,
+      "learning_rate": 2e-05,
+      "loss": 1.0687,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.149694919586182,
+      "learning_rate": 2e-05,
+      "loss": 1.4968,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.5019639730453491,
+      "learning_rate": 2e-05,
+      "loss": 0.1589,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.0508153438568115,
+      "learning_rate": 2e-05,
+      "loss": 0.7247,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 7.231861114501953,
+      "learning_rate": 2e-05,
+      "loss": 0.732,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.0040225982666016,
+      "learning_rate": 2e-05,
+      "loss": 0.4023,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.380476951599121,
+      "learning_rate": 2e-05,
+      "loss": 0.5608,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 9.996171951293945,
+      "learning_rate": 2e-05,
+      "loss": 1.1683,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.28837251663208,
+      "learning_rate": 2e-05,
+      "loss": 0.4167,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.0701327323913574,
+      "learning_rate": 2e-05,
+      "loss": 0.7562,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 6.403076648712158,
+      "learning_rate": 2e-05,
+      "loss": 2.0225,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 7.473080635070801,
+      "learning_rate": 2e-05,
+      "loss": 1.862,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 7.931491851806641,
+      "learning_rate": 2e-05,
+      "loss": 1.4611,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.673038482666016,
+      "learning_rate": 2e-05,
+      "loss": 1.4778,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.4596800069500928e+16,
+      "train_loss": 0.9241710472106933,
+      "train_runtime": 285.2412,
+      "train_samples_per_second": 1.402,
+      "train_steps_per_second": 0.351
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4596800069500928e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e8987f26740c7009f1f5f56057fbc4b5f96a85ae20b53dfa1e18194705f022
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba53466426b547d1aec2ccf59cc6308fee74e0f8fb734a2954d3034d3ce2a281
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:439bd1eb80adb68fbcc840c96bcacf823288cbaf730476808fb3394ff6ad1df3
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c86ab622fe1feb23b59fb83cf5e472ee71c79dfd4f20eb96701f7393919679e6
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2f5547d82e18f42b23227f391bcddd915c066de4230694981cada509211d187
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:879aa734b796b610505a95fc544fd8d2e58f5306fd4ff0b9e059b542dca1fcc8
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36db059cda41bca570abcc3af1cb8b8a3a686963511afb00352aa80ecfa4d6cd
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca8e5d8dd79a4cab3e6cc3b4f9b2ad4b29b3e9129607c8bbb7680422d6cce54f
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_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": 5.035049915313721,
+      "learning_rate": 2e-05,
+      "loss": 1.1652,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.3497910499572754,
+      "learning_rate": 2e-05,
+      "loss": 1.6484,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.469871997833252,
+      "learning_rate": 2e-05,
+      "loss": 0.737,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.721245288848877,
+      "learning_rate": 2e-05,
+      "loss": 1.0691,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.207581996917725,
+      "learning_rate": 2e-05,
+      "loss": 1.1694,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.003703594207764,
+      "learning_rate": 2e-05,
+      "loss": 0.6077,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.2081942558288574,
+      "learning_rate": 2e-05,
+      "loss": 0.6724,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.170851230621338,
+      "learning_rate": 2e-05,
+      "loss": 1.0347,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.2809324264526367,
+      "learning_rate": 2e-05,
+      "loss": 1.4614,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.2174735069274902,
+      "learning_rate": 2e-05,
+      "loss": 0.9074,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 6.532240867614746,
+      "learning_rate": 2e-05,
+      "loss": 0.824,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 9.217572212219238,
+      "learning_rate": 2e-05,
+      "loss": 2.1938,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.5741959810256958,
+      "learning_rate": 2e-05,
+      "loss": 0.8184,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.815344333648682,
+      "learning_rate": 2e-05,
+      "loss": 1.5176,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.7724013328552246,
+      "learning_rate": 2e-05,
+      "loss": 1.5767,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.960803747177124,
+      "learning_rate": 2e-05,
+      "loss": 1.0888,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.7917325496673584,
+      "learning_rate": 2e-05,
+      "loss": 0.983,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 7.79496431350708,
+      "learning_rate": 2e-05,
+      "loss": 1.0458,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 8.211302757263184,
+      "learning_rate": 2e-05,
+      "loss": 1.1427,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.298877239227295,
+      "learning_rate": 2e-05,
+      "loss": 1.0652,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 6.475459098815918,
+      "learning_rate": 2e-05,
+      "loss": 0.7741,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.8340888023376465,
+      "learning_rate": 2e-05,
+      "loss": 1.1124,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.417236804962158,
+      "learning_rate": 2e-05,
+      "loss": 1.0009,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.54665470123291,
+      "learning_rate": 2e-05,
+      "loss": 0.6321,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.6683158874511719,
+      "learning_rate": 2e-05,
+      "loss": 1.3171,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.7134782671928406,
+      "learning_rate": 2e-05,
+      "loss": 0.3386,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.1631276607513428,
+      "learning_rate": 2e-05,
+      "loss": 0.9637,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.5291998386383057,
+      "learning_rate": 2e-05,
+      "loss": 1.1431,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.054178237915039,
+      "learning_rate": 2e-05,
+      "loss": 0.7363,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.6544301509857178,
+      "learning_rate": 2e-05,
+      "loss": 0.7261,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.754007339477539,
+      "learning_rate": 2e-05,
+      "loss": 0.8795,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.406623601913452,
+      "learning_rate": 2e-05,
+      "loss": 1.0624,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.3705132007598877,
+      "learning_rate": 2e-05,
+      "loss": 1.2757,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 15.125097274780273,
+      "learning_rate": 2e-05,
+      "loss": 1.0644,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.651677131652832,
+      "learning_rate": 2e-05,
+      "loss": 0.6554,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.574554920196533,
+      "learning_rate": 2e-05,
+      "loss": 0.7245,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 6.320649147033691,
+      "learning_rate": 2e-05,
+      "loss": 0.7212,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 7.0648016929626465,
+      "learning_rate": 2e-05,
+      "loss": 1.2978,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.5221383571624756,
+      "learning_rate": 2e-05,
+      "loss": 1.1599,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.474943995475769,
+      "learning_rate": 2e-05,
+      "loss": 0.5594,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.3496599197387695,
+      "learning_rate": 2e-05,
+      "loss": 0.9978,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.546678066253662,
+      "learning_rate": 2e-05,
+      "loss": 1.222,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.939904689788818,
+      "learning_rate": 2e-05,
+      "loss": 1.1428,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 6.095272064208984,
+      "learning_rate": 2e-05,
+      "loss": 1.1364,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.423612117767334,
+      "learning_rate": 2e-05,
+      "loss": 1.5325,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 5.676146984100342,
+      "learning_rate": 2e-05,
+      "loss": 0.8407,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.8238693475723267,
+      "learning_rate": 2e-05,
+      "loss": 0.8097,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.0705935955047607,
+      "learning_rate": 2e-05,
+      "loss": 0.8379,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.3262546062469482,
+      "learning_rate": 2e-05,
+      "loss": 0.5019,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.406374454498291,
+      "learning_rate": 2e-05,
+      "loss": 0.4392,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2.037956633375539e+16,
+      "train_loss": 1.0066848659515382,
+      "train_runtime": 374.3247,
+      "train_samples_per_second": 1.069,
+      "train_steps_per_second": 0.267
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.037956633375539e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b77fab24eb8b332cd18fd8c613d655a23e63cbef32b593244d37b471987aac31
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e5894f1f2391d28f0a2518e63ae6d7ae31cf51cdc672da5551adbb73951be3
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6d983c539ab6a47bd8c88d749b581aea3e7b30e4e7a24eeaa1beac037fc01c2
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa14bb8ccd78b4e38f462af106f27d59d2d84d7a6fe27f505e77f91ee4cc3a64
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b607ca226260ff2c5836d568daf269f77c26d3177e0d05b353360338b82fb2b
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84cf7a57d19cfa7b4eea900c6474a8680b4807fdda2008ecdf5df80fcb3ee27c
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d518f368b997bbe01a591d170363aba7dd9aa337cb40fea2050fbc3a8f66c08a
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0bcb452a6784fbb73d3479cde29cf4c15f889dc79f087ad04d73d0b2bfc6633
+size 395786922

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_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": 1.189469814300537,
+      "learning_rate": 2e-05,
+      "loss": 0.31,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.8435537815093994,
+      "learning_rate": 2e-05,
+      "loss": 0.5298,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 5.566661834716797,
+      "learning_rate": 2e-05,
+      "loss": 1.2779,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.0178768634796143,
+      "learning_rate": 2e-05,
+      "loss": 0.4592,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 9.928922653198242,
+      "learning_rate": 2e-05,
+      "loss": 1.2289,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.7801988124847412,
+      "learning_rate": 2e-05,
+      "loss": 1.1655,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.27690789103507996,
+      "learning_rate": 2e-05,
+      "loss": 0.2859,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.786653995513916,
+      "learning_rate": 2e-05,
+      "loss": 1.0218,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.004693627357483,
+      "learning_rate": 2e-05,
+      "loss": 1.154,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.915676593780518,
+      "learning_rate": 2e-05,
+      "loss": 0.2657,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 6.210068225860596,
+      "learning_rate": 2e-05,
+      "loss": 0.7747,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.257296085357666,
+      "learning_rate": 2e-05,
+      "loss": 1.6313,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 7.215267181396484,
+      "learning_rate": 2e-05,
+      "loss": 3.7582,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 7.644487380981445,
+      "learning_rate": 2e-05,
+      "loss": 2.2401,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 5.116546630859375,
+      "learning_rate": 2e-05,
+      "loss": 1.995,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.723872184753418,
+      "learning_rate": 2e-05,
+      "loss": 0.8439,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.7276716232299805,
+      "learning_rate": 2e-05,
+      "loss": 1.0697,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.0036442279815674,
+      "learning_rate": 2e-05,
+      "loss": 1.7633,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.7193286418914795,
+      "learning_rate": 2e-05,
+      "loss": 0.5447,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.585648059844971,
+      "learning_rate": 2e-05,
+      "loss": 1.3138,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.06341306120157242,
+      "learning_rate": 2e-05,
+      "loss": 0.5346,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.21247935295105,
+      "learning_rate": 2e-05,
+      "loss": 1.5504,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.877152442932129,
+      "learning_rate": 2e-05,
+      "loss": 1.1479,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.434115171432495,
+      "learning_rate": 2e-05,
+      "loss": 0.7492,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.6888427734375,
+      "learning_rate": 2e-05,
+      "loss": 1.0197,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.457335948944092,
+      "learning_rate": 2e-05,
+      "loss": 1.9108,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.416705459356308,
+      "learning_rate": 2e-05,
+      "loss": 0.7948,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.0772849321365356,
+      "learning_rate": 2e-05,
+      "loss": 0.4287,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.1008191108703613,
+      "learning_rate": 2e-05,
+      "loss": 1.094,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.63857102394104,
+      "learning_rate": 2e-05,
+      "loss": 0.7174,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.9035606384277344,
+      "learning_rate": 2e-05,
+      "loss": 0.814,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 6.539764881134033,
+      "learning_rate": 2e-05,
+      "loss": 1.699,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.706289529800415,
+      "learning_rate": 2e-05,
+      "loss": 1.649,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.7016932368278503,
+      "learning_rate": 2e-05,
+      "loss": 0.2642,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.280506134033203,
+      "learning_rate": 2e-05,
+      "loss": 1.2083,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 7.748496055603027,
+      "learning_rate": 2e-05,
+      "loss": 1.104,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.6094746589660645,
+      "learning_rate": 2e-05,
+      "loss": 1.2405,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.584652900695801,
+      "learning_rate": 2e-05,
+      "loss": 0.9338,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 6.3299102783203125,
+      "learning_rate": 2e-05,
+      "loss": 1.2104,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.807102203369141,
+      "learning_rate": 2e-05,
+      "loss": 1.6096,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.525906562805176,
+      "learning_rate": 2e-05,
+      "loss": 1.0336,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 8.219979286193848,
+      "learning_rate": 2e-05,
+      "loss": 2.3766,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.3661632537841797,
+      "learning_rate": 2e-05,
+      "loss": 0.4931,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 8.628079414367676,
+      "learning_rate": 2e-05,
+      "loss": 1.5695,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.711212635040283,
+      "learning_rate": 2e-05,
+      "loss": 0.7535,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 8.135887145996094,
+      "learning_rate": 2e-05,
+      "loss": 1.7705,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.585470676422119,
+      "learning_rate": 2e-05,
+      "loss": 0.6988,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.6448802947998047,
+      "learning_rate": 2e-05,
+      "loss": 1.502,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.504702568054199,
+      "learning_rate": 2e-05,
+      "loss": 0.5163,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.5633938312530518,
+      "learning_rate": 2e-05,
+      "loss": 0.9534,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.920155780330291e+16,
+      "train_loss": 1.1396221828460693,
+      "train_runtime": 369.8727,
+      "train_samples_per_second": 1.081,
+      "train_steps_per_second": 0.27
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.920155780330291e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f65d8e8208f1f43a118be2af13f6c0657768c6cf2f6a6c8821826f6c08f45ac9
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e793cff570be69867002683a9ef9c4425eda39e30bec1773d52551340007a66f
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8857a69c6f759d8234f7d396fc37cb7e39d7bde1d4083fbff4994ba63e14f244
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363dce9b6bbff794e49f733aaea7a3d6287dd7fb30dea5cec0bb128abe809134
+size 395787774

client_states_fedMultipqfullfreeze_sft_bs4_saveoptim_lr2e-5_sc137_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1d5c7a96bf536e66bd688162ae2f559b164db041a290865bc5a303e90040fb9
+size 395786922