Upload folder using huggingface_hub

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20a2cfa32a281784795db634cd58040e0099dfb3a6b461f3e2811690aed270d4
+size 295585110

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:164b99db199f8c1afc330ed8c4d413297e461263d6c0d531ef9471b84e72e5fa
+size 295585110

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ac471bdb0a23646a4b729abc1bddddff87a0202bf5fc658f8eff46c613af93
+size 295585110

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddce9ffe75535dd2ce3951b60de8b30f69eca1122d14aa68bce2d74012e20d92
+size 295585110

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8940422daafc8acb84347ba4f766e1cb543eb670aa45b0420a9a5227c22ba7e6
+size 295584650

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1884b1ce6eb419994414bec53db3f25c876be84c73dd4b6bac19b279a37ae199
+size 295585110

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba57bcea505e8a5c94f327f555ddca8d1ae8fa1037bae98cdcc235d5c2709b5
+size 295584650

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ea8ab72fae35f37e9ace071574cc20c4fbfc4c0f331de08fd89db0ec7fd1c0
+size 295584650

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/0_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": 1.4357949495315552,
+      "learning_rate": 2e-05,
+      "loss": 0.9752,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 7.484304904937744,
+      "learning_rate": 2e-05,
+      "loss": 0.3921,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.0805540084838867,
+      "learning_rate": 2e-05,
+      "loss": 0.766,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.26295432448387146,
+      "learning_rate": 2e-05,
+      "loss": 0.2986,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.8822102546691895,
+      "learning_rate": 2e-05,
+      "loss": 0.3405,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.02680317871272564,
+      "learning_rate": 2e-05,
+      "loss": 0.3358,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.1298555135726929,
+      "learning_rate": 2e-05,
+      "loss": 0.6812,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.079339027404785,
+      "learning_rate": 2e-05,
+      "loss": 0.6571,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.0236611366271973,
+      "learning_rate": 2e-05,
+      "loss": 0.4357,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.0701911449432373,
+      "learning_rate": 2e-05,
+      "loss": 0.5624,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.1642799377441406,
+      "learning_rate": 2e-05,
+      "loss": 0.4102,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.8954672813415527,
+      "learning_rate": 2e-05,
+      "loss": 1.296,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 5.15814208984375,
+      "learning_rate": 2e-05,
+      "loss": 1.2499,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.06376051902771,
+      "learning_rate": 2e-05,
+      "loss": 0.6663,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.37149399518966675,
+      "learning_rate": 2e-05,
+      "loss": 0.1357,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.2507413625717163,
+      "learning_rate": 2e-05,
+      "loss": 0.1487,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.1001901626586914,
+      "learning_rate": 2e-05,
+      "loss": 0.9658,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.733464002609253,
+      "learning_rate": 2e-05,
+      "loss": 0.9133,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.3771137595176697,
+      "learning_rate": 2e-05,
+      "loss": 0.2268,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.6037631034851074,
+      "learning_rate": 2e-05,
+      "loss": 0.3637,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.1135358810424805,
+      "learning_rate": 2e-05,
+      "loss": 0.5037,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 12.166988372802734,
+      "learning_rate": 2e-05,
+      "loss": 1.5196,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.188719391822815,
+      "learning_rate": 2e-05,
+      "loss": 0.7123,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.858033299446106,
+      "learning_rate": 2e-05,
+      "loss": 0.3241,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.1797194480895996,
+      "learning_rate": 2e-05,
+      "loss": 0.3886,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.2527966499328613,
+      "learning_rate": 2e-05,
+      "loss": 0.3365,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 5.527441024780273,
+      "learning_rate": 2e-05,
+      "loss": 1.4229,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.6085422039031982,
+      "learning_rate": 2e-05,
+      "loss": 0.4734,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.661068320274353,
+      "learning_rate": 2e-05,
+      "loss": 0.3244,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.1758453845977783,
+      "learning_rate": 2e-05,
+      "loss": 0.4436,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.1051682233810425,
+      "learning_rate": 2e-05,
+      "loss": 0.4639,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.56185245513916,
+      "learning_rate": 2e-05,
+      "loss": 0.7811,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.042705774307251,
+      "learning_rate": 2e-05,
+      "loss": 2.9756,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 7.160967826843262,
+      "learning_rate": 2e-05,
+      "loss": 0.8687,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.546377658843994,
+      "learning_rate": 2e-05,
+      "loss": 0.9039,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.3272593021392822,
+      "learning_rate": 2e-05,
+      "loss": 0.4634,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.9541059732437134,
+      "learning_rate": 2e-05,
+      "loss": 0.4152,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 7.0820465087890625,
+      "learning_rate": 2e-05,
+      "loss": 0.7858,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.81209659576416,
+      "learning_rate": 2e-05,
+      "loss": 0.7721,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.922970771789551,
+      "learning_rate": 2e-05,
+      "loss": 0.4672,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.5200783014297485,
+      "learning_rate": 2e-05,
+      "loss": 0.4998,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 8.176060676574707,
+      "learning_rate": 2e-05,
+      "loss": 1.6471,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 10.166783332824707,
+      "learning_rate": 2e-05,
+      "loss": 0.9579,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.09095903486013412,
+      "learning_rate": 2e-05,
+      "loss": 0.2736,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.8619403839111328,
+      "learning_rate": 2e-05,
+      "loss": 0.5136,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.9814728498458862,
+      "learning_rate": 2e-05,
+      "loss": 0.6869,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.469095230102539,
+      "learning_rate": 2e-05,
+      "loss": 0.4635,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 5.562348365783691,
+      "learning_rate": 2e-05,
+      "loss": 1.7081,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.774053931236267,
+      "learning_rate": 2e-05,
+      "loss": 1.1335,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.8918042182922363,
+      "learning_rate": 2e-05,
+      "loss": 0.3731,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 7197827847421952.0,
+      "train_loss": 0.7084918451309205,
+      "train_runtime": 296.0647,
+      "train_samples_per_second": 1.351,
+      "train_steps_per_second": 0.338
+    }
+  ],
+  "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": 7197827847421952.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a302188073e933752c00de25e2203101e658a30dec07fdab4bd426265d5f2e
+size 140898814

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d64dd65a260b5d8ba3a2efe7eece417e0404a651245f61ff8b0c983786841f6
+size 140898814

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e07a0c4b4a5ae5e4161e9cef8f4d38901e2a913350ba5522a1d29d4212e1ffb1
+size 140898814

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c4254a77f1aa1f047303e2aeaf86752a06c02eb5e52ec452b7fcc782f52b52d
+size 140898814

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:219c8d3bd85819db008faa389480875901a7069c993bae6623244671878646de
+size 140898410

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7063fbc35cc60e6bed46affd0034dc1ed7b58aff7ad80d34b2a8a99308364ea6
+size 140898814

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:585947acf8c75eb8dde19ac6a1ed4cdbcb9a0d357157898aa9255c927d7c62ea
+size 140898410

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b2c2bf6e18599c6416fab5f06330502ca9308ae9865311ebc522ed87568e55
+size 140898410

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/1_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": 2.9427311420440674,
+      "learning_rate": 2e-05,
+      "loss": 1.0288,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.741145610809326,
+      "learning_rate": 2e-05,
+      "loss": 1.4761,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.015233039855957,
+      "learning_rate": 2e-05,
+      "loss": 1.5796,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.0968964099884033,
+      "learning_rate": 2e-05,
+      "loss": 1.0918,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.706130027770996,
+      "learning_rate": 2e-05,
+      "loss": 1.0278,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.9777791500091553,
+      "learning_rate": 2e-05,
+      "loss": 1.8856,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.209172487258911,
+      "learning_rate": 2e-05,
+      "loss": 1.3796,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.455867052078247,
+      "learning_rate": 2e-05,
+      "loss": 1.2993,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.4126646518707275,
+      "learning_rate": 2e-05,
+      "loss": 1.2639,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.840634346008301,
+      "learning_rate": 2e-05,
+      "loss": 1.4814,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.0498416423797607,
+      "learning_rate": 2e-05,
+      "loss": 1.6443,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.3178482055664062,
+      "learning_rate": 2e-05,
+      "loss": 1.3003,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.242715358734131,
+      "learning_rate": 2e-05,
+      "loss": 1.4062,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.3701682090759277,
+      "learning_rate": 2e-05,
+      "loss": 1.5181,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.3877534866333008,
+      "learning_rate": 2e-05,
+      "loss": 1.5938,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.308324933052063,
+      "learning_rate": 2e-05,
+      "loss": 1.5723,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.3145534992218018,
+      "learning_rate": 2e-05,
+      "loss": 1.3368,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 4.586231231689453,
+      "learning_rate": 2e-05,
+      "loss": 1.3999,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 5.7817888259887695,
+      "learning_rate": 2e-05,
+      "loss": 1.4358,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.2060853242874146,
+      "learning_rate": 2e-05,
+      "loss": 0.9374,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.4397454261779785,
+      "learning_rate": 2e-05,
+      "loss": 1.1576,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.8089556694030762,
+      "learning_rate": 2e-05,
+      "loss": 1.2778,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.1753023862838745,
+      "learning_rate": 2e-05,
+      "loss": 1.3643,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.98372483253479,
+      "learning_rate": 2e-05,
+      "loss": 1.4053,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.529714584350586,
+      "learning_rate": 2e-05,
+      "loss": 1.4272,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.703952312469482,
+      "learning_rate": 2e-05,
+      "loss": 1.6426,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.705620527267456,
+      "learning_rate": 2e-05,
+      "loss": 1.5771,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.1030988693237305,
+      "learning_rate": 2e-05,
+      "loss": 1.2424,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.4728143215179443,
+      "learning_rate": 2e-05,
+      "loss": 1.2578,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.7469069957733154,
+      "learning_rate": 2e-05,
+      "loss": 1.2402,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.4544708728790283,
+      "learning_rate": 2e-05,
+      "loss": 1.4639,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.6641395092010498,
+      "learning_rate": 2e-05,
+      "loss": 1.1909,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.0484120845794678,
+      "learning_rate": 2e-05,
+      "loss": 1.4282,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.478560447692871,
+      "learning_rate": 2e-05,
+      "loss": 1.3979,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.1397147178649902,
+      "learning_rate": 2e-05,
+      "loss": 1.5562,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.3987221717834473,
+      "learning_rate": 2e-05,
+      "loss": 1.4531,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.8414459228515625,
+      "learning_rate": 2e-05,
+      "loss": 1.4473,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.1021289825439453,
+      "learning_rate": 2e-05,
+      "loss": 1.3472,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.8407915830612183,
+      "learning_rate": 2e-05,
+      "loss": 1.2642,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.4831814765930176,
+      "learning_rate": 2e-05,
+      "loss": 1.3237,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.4579954147338867,
+      "learning_rate": 2e-05,
+      "loss": 1.1968,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.551758289337158,
+      "learning_rate": 2e-05,
+      "loss": 1.5654,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.751859188079834,
+      "learning_rate": 2e-05,
+      "loss": 1.2002,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.306459903717041,
+      "learning_rate": 2e-05,
+      "loss": 1.3477,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.63804292678833,
+      "learning_rate": 2e-05,
+      "loss": 1.4023,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.2834153175354004,
+      "learning_rate": 2e-05,
+      "loss": 1.3506,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.944771766662598,
+      "learning_rate": 2e-05,
+      "loss": 1.627,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.705222249031067,
+      "learning_rate": 2e-05,
+      "loss": 1.2178,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.038778305053711,
+      "learning_rate": 2e-05,
+      "loss": 1.3418,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.250809907913208,
+      "learning_rate": 2e-05,
+      "loss": 1.2407,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2949501438394368.0,
+      "train_loss": 1.3722802734375,
+      "train_runtime": 245.4499,
+      "train_samples_per_second": 1.63,
+      "train_steps_per_second": 0.407
+    }
+  ],
+  "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": 2949501438394368.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7862e641bae9b1c1ff58cceb03a83630ad7cf69a12c1166502c070f23b2d02d9
+size 479128390

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e894638477fe4d5df5e29deebcb475380243f8770751c46fc8c27c5353930445
+size 479128390

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5feb2ae3f928072c4ee2154140d7034edc181a88544b9fd3e627d79ddbd1807e
+size 479128390

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b772019cbba5031146eb8804cb175b47ef30a03774f0dd273bfd862b6c5ba52
+size 479128390

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:785ce1c8ffeb43b8dee5b41dd20edbb058f523c2db0ed6b8af8ffda877b8b1e6
+size 479127818

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06ba3ab83896fcaa00d07ee5061d394d33a34434d3f42e173b68f0a154d8472a
+size 479128390

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef05687dd4b30bcee4fdd616997a10b003f3ef39210a5ac61b153007d271fd50
+size 479127818

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f8c6de60f28ae04a762180348c698a8c16fccd95e77755909e614b573f4117
+size 479127818

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/2_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": 3.2558865547180176,
+      "learning_rate": 2e-05,
+      "loss": 0.9064,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.991973340511322,
+      "learning_rate": 2e-05,
+      "loss": 0.1233,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 6.5367913246154785,
+      "learning_rate": 2e-05,
+      "loss": 1.9525,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 5.972145080566406,
+      "learning_rate": 2e-05,
+      "loss": 1.1308,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.799992561340332,
+      "learning_rate": 2e-05,
+      "loss": 0.7781,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.8599284887313843,
+      "learning_rate": 2e-05,
+      "loss": 0.2985,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.0901894569396973,
+      "learning_rate": 2e-05,
+      "loss": 1.287,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.8889167308807373,
+      "learning_rate": 2e-05,
+      "loss": 0.7026,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.7417221069335938,
+      "learning_rate": 2e-05,
+      "loss": 0.2317,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.34332019090652466,
+      "learning_rate": 2e-05,
+      "loss": 0.3007,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.8413283824920654,
+      "learning_rate": 2e-05,
+      "loss": 0.5139,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.948110103607178,
+      "learning_rate": 2e-05,
+      "loss": 1.0095,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.9708259105682373,
+      "learning_rate": 2e-05,
+      "loss": 1.0875,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 6.128609657287598,
+      "learning_rate": 2e-05,
+      "loss": 1.1535,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.5443027019500732,
+      "learning_rate": 2e-05,
+      "loss": 0.2954,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.782371997833252,
+      "learning_rate": 2e-05,
+      "loss": 0.2122,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.9455428123474121,
+      "learning_rate": 2e-05,
+      "loss": 0.4753,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 5.72688627243042,
+      "learning_rate": 2e-05,
+      "loss": 0.8696,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.12677001953125,
+      "learning_rate": 2e-05,
+      "loss": 0.4472,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.0864536762237549,
+      "learning_rate": 2e-05,
+      "loss": 0.2052,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.737551212310791,
+      "learning_rate": 2e-05,
+      "loss": 0.422,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.5829198360443115,
+      "learning_rate": 2e-05,
+      "loss": 0.5197,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.83404278755188,
+      "learning_rate": 2e-05,
+      "loss": 0.3223,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.3315060138702393,
+      "learning_rate": 2e-05,
+      "loss": 0.5508,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.9215158224105835,
+      "learning_rate": 2e-05,
+      "loss": 0.1513,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 5.178053379058838,
+      "learning_rate": 2e-05,
+      "loss": 0.7244,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 6.672908782958984,
+      "learning_rate": 2e-05,
+      "loss": 0.8517,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 6.269854545593262,
+      "learning_rate": 2e-05,
+      "loss": 2.2648,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 8.046138763427734,
+      "learning_rate": 2e-05,
+      "loss": 1.1398,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.5552077293396,
+      "learning_rate": 2e-05,
+      "loss": 1.1731,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 8.006683349609375,
+      "learning_rate": 2e-05,
+      "loss": 0.9849,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 9.458540916442871,
+      "learning_rate": 2e-05,
+      "loss": 0.6968,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.7672533988952637,
+      "learning_rate": 2e-05,
+      "loss": 1.579,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.504437208175659,
+      "learning_rate": 2e-05,
+      "loss": 0.4301,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 5.53498649597168,
+      "learning_rate": 2e-05,
+      "loss": 0.7245,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.9111721515655518,
+      "learning_rate": 2e-05,
+      "loss": 0.7371,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 8.062969207763672,
+      "learning_rate": 2e-05,
+      "loss": 0.7654,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 7.899918079376221,
+      "learning_rate": 2e-05,
+      "loss": 1.6479,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.5469361543655396,
+      "learning_rate": 2e-05,
+      "loss": 0.7988,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 11.664484024047852,
+      "learning_rate": 2e-05,
+      "loss": 1.4557,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.4525814354419708,
+      "learning_rate": 2e-05,
+      "loss": 0.4412,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 5.048192977905273,
+      "learning_rate": 2e-05,
+      "loss": 0.5993,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.5683045387268066,
+      "learning_rate": 2e-05,
+      "loss": 0.6205,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.712682723999023,
+      "learning_rate": 2e-05,
+      "loss": 0.4364,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 9.933538436889648,
+      "learning_rate": 2e-05,
+      "loss": 1.3851,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.783173084259033,
+      "learning_rate": 2e-05,
+      "loss": 0.4456,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.395021915435791,
+      "learning_rate": 2e-05,
+      "loss": 0.7315,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.892876148223877,
+      "learning_rate": 2e-05,
+      "loss": 0.8238,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.3703393936157227,
+      "learning_rate": 2e-05,
+      "loss": 0.3309,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7113988995552063,
+      "learning_rate": 2e-05,
+      "loss": 0.8155,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.570782887018496e+16,
+      "train_loss": 0.7710115814208984,
+      "train_runtime": 425.933,
+      "train_samples_per_second": 0.939,
+      "train_steps_per_second": 0.235
+    }
+  ],
+  "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": 1.570782887018496e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b930dbca6b179a5bc29fc350fc47779afbb1a26cac6de123dcc4a530f9c5359
+size 479128390

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e03e5d95385f51204779d8e410237239d9cd5c50011063fc3ce4a6655e6982
+size 479128390

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6496615d1b538df97655e76e86eeec11e6de6e8a873239cc7fa24813a095cc1b
+size 479128390

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7407557f6cbc453acb51d7a5b78c207e88530b905b32608fadf4aa968eb6181e
+size 479128390

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04c1c3f23467e3dfff4f5e902e3447f7cee591eb9358914edfa4c90bfc14e000
+size 479127818

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b41a2866ab605fe35c2c230b5f3194131b98959bd35153dd1faf39913ad83748
+size 479128390

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050b3b536ac4f0a5278377639ee83e7c7523c352c429c8f76b48c25936aacd69
+size 479127818

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f060f4423b7a30f309ab6cc75bfa0e53766a36e5cba4d26b68665a17c4879ac
+size 479127818

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/3_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": 0.6915289759635925,
+      "learning_rate": 2e-05,
+      "loss": 0.803,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.5236664414405823,
+      "learning_rate": 2e-05,
+      "loss": 0.3719,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.7289407849311829,
+      "learning_rate": 2e-05,
+      "loss": 0.6735,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.04733162373304367,
+      "learning_rate": 2e-05,
+      "loss": 0.3086,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.7653596997261047,
+      "learning_rate": 2e-05,
+      "loss": 0.2241,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.275763511657715,
+      "learning_rate": 2e-05,
+      "loss": 0.8208,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.8538552522659302,
+      "learning_rate": 2e-05,
+      "loss": 0.806,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.4601213932037354,
+      "learning_rate": 2e-05,
+      "loss": 0.7453,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.620142936706543,
+      "learning_rate": 2e-05,
+      "loss": 0.3818,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.4771318435668945,
+      "learning_rate": 2e-05,
+      "loss": 0.7292,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.6303713321685791,
+      "learning_rate": 2e-05,
+      "loss": 0.3592,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.111276865005493,
+      "learning_rate": 2e-05,
+      "loss": 0.8449,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.3116923570632935,
+      "learning_rate": 2e-05,
+      "loss": 0.7724,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 7.254108428955078,
+      "learning_rate": 2e-05,
+      "loss": 0.6019,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.0935317277908325,
+      "learning_rate": 2e-05,
+      "loss": 0.3723,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.6438285708427429,
+      "learning_rate": 2e-05,
+      "loss": 0.4673,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 9.997159957885742,
+      "learning_rate": 2e-05,
+      "loss": 1.4406,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.574639916419983,
+      "learning_rate": 2e-05,
+      "loss": 0.8156,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.7990269660949707,
+      "learning_rate": 2e-05,
+      "loss": 0.9997,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.4288394451141357,
+      "learning_rate": 2e-05,
+      "loss": 1.0895,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.751030445098877,
+      "learning_rate": 2e-05,
+      "loss": 0.5163,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.5789567232131958,
+      "learning_rate": 2e-05,
+      "loss": 0.4597,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.716470718383789,
+      "learning_rate": 2e-05,
+      "loss": 0.5985,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.0268652439117432,
+      "learning_rate": 2e-05,
+      "loss": 0.8839,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.183387041091919,
+      "learning_rate": 2e-05,
+      "loss": 0.635,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.6883171796798706,
+      "learning_rate": 2e-05,
+      "loss": 0.8253,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 6.081538677215576,
+      "learning_rate": 2e-05,
+      "loss": 1.7804,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.235260963439941,
+      "learning_rate": 2e-05,
+      "loss": 0.5859,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.297282695770264,
+      "learning_rate": 2e-05,
+      "loss": 1.0606,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.6412908434867859,
+      "learning_rate": 2e-05,
+      "loss": 0.2726,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.3413950204849243,
+      "learning_rate": 2e-05,
+      "loss": 0.3853,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 6.513116836547852,
+      "learning_rate": 2e-05,
+      "loss": 0.7348,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.7780243158340454,
+      "learning_rate": 2e-05,
+      "loss": 0.8995,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.6931712031364441,
+      "learning_rate": 2e-05,
+      "loss": 0.6984,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 5.796865940093994,
+      "learning_rate": 2e-05,
+      "loss": 0.6069,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.1728687286376953,
+      "learning_rate": 2e-05,
+      "loss": 0.7387,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.4009567201137543,
+      "learning_rate": 2e-05,
+      "loss": 0.5621,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.6604442596435547,
+      "learning_rate": 2e-05,
+      "loss": 0.8287,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.2604601383209229,
+      "learning_rate": 2e-05,
+      "loss": 0.7813,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5949382185935974,
+      "learning_rate": 2e-05,
+      "loss": 0.2305,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.986330986022949,
+      "learning_rate": 2e-05,
+      "loss": 1.0291,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.1950682401657104,
+      "learning_rate": 2e-05,
+      "loss": 0.5847,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.359482526779175,
+      "learning_rate": 2e-05,
+      "loss": 0.4699,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.38797926902770996,
+      "learning_rate": 2e-05,
+      "loss": 0.3318,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.0094640254974365,
+      "learning_rate": 2e-05,
+      "loss": 0.7107,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 10.679686546325684,
+      "learning_rate": 2e-05,
+      "loss": 1.1031,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.3764183521270752,
+      "learning_rate": 2e-05,
+      "loss": 0.2138,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 17.799694061279297,
+      "learning_rate": 2e-05,
+      "loss": 0.6659,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.7701702117919922,
+      "learning_rate": 2e-05,
+      "loss": 0.6446,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.7060821056365967,
+      "learning_rate": 2e-05,
+      "loss": 0.7716,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2.014860909792461e+16,
+      "train_loss": 0.6847475278377533,
+      "train_runtime": 438.6106,
+      "train_samples_per_second": 0.912,
+      "train_steps_per_second": 0.228
+    }
+  ],
+  "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": 2.014860909792461e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ae1dcfb75d581b07865f7e719852e53c0313715a95546499deeb3abd5356736
+size 479128390

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff62f62346aae26510c829ce3a4dae85ad0d6a1845876f1ce707c7a9bcdc04bb
+size 479128390

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fed039615c8f70ef8fb5cdfb55d6628f5a5e1f903d0fe2965d9f5130ec00013
+size 479128390

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a09338731636e04d275069a3942e655fb868bcc9839f6cd926e930e422aa74
+size 479128390

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2bc2093a3f74d5610009eeb3c573f6e2a18d53c23f42b5915b97aa22cefeb78
+size 479127818

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8527a6d3e15d2942d59d56a7e75275cef893892fbdfc47601bb38b5e5ae5e0d4
+size 479128390

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270f1fed8bb31676ab501726cee5078fbbff91f34854f365ab9545ffe56e3177
+size 479127818

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d09f687a822b4962a11c0546b789db3d0b1e2d02fb5fa81437bb1c01f7181e
+size 479127818

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/4_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": 0.9225918054580688,
+      "learning_rate": 2e-05,
+      "loss": 0.991,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.8597076535224915,
+      "learning_rate": 2e-05,
+      "loss": 0.3758,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.3333783745765686,
+      "learning_rate": 2e-05,
+      "loss": 0.5362,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5292944312095642,
+      "learning_rate": 2e-05,
+      "loss": 0.7394,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.7009687423706055,
+      "learning_rate": 2e-05,
+      "loss": 1.8573,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.600105881690979,
+      "learning_rate": 2e-05,
+      "loss": 0.8488,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.5355629920959473,
+      "learning_rate": 2e-05,
+      "loss": 0.4846,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.030879259109497,
+      "learning_rate": 2e-05,
+      "loss": 0.5453,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.8978800177574158,
+      "learning_rate": 2e-05,
+      "loss": 0.4633,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.1896603107452393,
+      "learning_rate": 2e-05,
+      "loss": 0.7015,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.6468939781188965,
+      "learning_rate": 2e-05,
+      "loss": 0.4669,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.17122745513916,
+      "learning_rate": 2e-05,
+      "loss": 1.0091,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.072269439697266,
+      "learning_rate": 2e-05,
+      "loss": 2.0015,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.218262195587158,
+      "learning_rate": 2e-05,
+      "loss": 0.7374,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.5141124725341797,
+      "learning_rate": 2e-05,
+      "loss": 1.726,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.6296266317367554,
+      "learning_rate": 2e-05,
+      "loss": 0.5757,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.733184337615967,
+      "learning_rate": 2e-05,
+      "loss": 0.3487,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.812718391418457,
+      "learning_rate": 2e-05,
+      "loss": 0.2033,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.641838788986206,
+      "learning_rate": 2e-05,
+      "loss": 1.0014,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.547071933746338,
+      "learning_rate": 2e-05,
+      "loss": 0.6443,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 5.26523494720459,
+      "learning_rate": 2e-05,
+      "loss": 1.9649,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.6201882362365723,
+      "learning_rate": 2e-05,
+      "loss": 0.479,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.8259027004241943,
+      "learning_rate": 2e-05,
+      "loss": 0.6319,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 7.226994037628174,
+      "learning_rate": 2e-05,
+      "loss": 0.7662,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.9887053966522217,
+      "learning_rate": 2e-05,
+      "loss": 1.0707,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.292367696762085,
+      "learning_rate": 2e-05,
+      "loss": 0.4642,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 5.1545867919921875,
+      "learning_rate": 2e-05,
+      "loss": 0.9666,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.924346685409546,
+      "learning_rate": 2e-05,
+      "loss": 1.8803,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.1195952892303467,
+      "learning_rate": 2e-05,
+      "loss": 1.1754,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.6606249809265137,
+      "learning_rate": 2e-05,
+      "loss": 1.0212,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.3416082859039307,
+      "learning_rate": 2e-05,
+      "loss": 0.8757,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.2015907764434814,
+      "learning_rate": 2e-05,
+      "loss": 0.4014,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.0905282497406006,
+      "learning_rate": 2e-05,
+      "loss": 0.3452,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 7.018588542938232,
+      "learning_rate": 2e-05,
+      "loss": 1.2981,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.384774684906006,
+      "learning_rate": 2e-05,
+      "loss": 0.7799,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 4.2297210693359375,
+      "learning_rate": 2e-05,
+      "loss": 0.4246,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.036142349243164,
+      "learning_rate": 2e-05,
+      "loss": 0.1518,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.1399793028831482,
+      "learning_rate": 2e-05,
+      "loss": 0.1056,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 9.0904541015625,
+      "learning_rate": 2e-05,
+      "loss": 1.3569,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.4876017570495605,
+      "learning_rate": 2e-05,
+      "loss": 1.7918,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.1255276203155518,
+      "learning_rate": 2e-05,
+      "loss": 0.279,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 5.206053256988525,
+      "learning_rate": 2e-05,
+      "loss": 1.561,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.1543315351009369,
+      "learning_rate": 2e-05,
+      "loss": 0.0126,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.7004189491271973,
+      "learning_rate": 2e-05,
+      "loss": 0.7089,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.0638126134872437,
+      "learning_rate": 2e-05,
+      "loss": 0.5882,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.7447102069854736,
+      "learning_rate": 2e-05,
+      "loss": 0.5941,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.824549674987793,
+      "learning_rate": 2e-05,
+      "loss": 1.5416,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.7135050296783447,
+      "learning_rate": 2e-05,
+      "loss": 0.5581,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.0467679500579834,
+      "learning_rate": 2e-05,
+      "loss": 0.6242,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.1278626918792725,
+      "learning_rate": 2e-05,
+      "loss": 0.4743,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2.015594703277261e+16,
+      "train_loss": 0.8230290794372559,
+      "train_runtime": 469.2451,
+      "train_samples_per_second": 0.852,
+      "train_steps_per_second": 0.213
+    }
+  ],
+  "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": 2.015594703277261e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c511c59b784a0f74f1dde51e0b2080a498cdc8e50966b14aa71fbae0f831686
+size 295585110

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57e78f755ed86c7ee2e85264e01afa0586b716855ee8452edb1ca788b22bf283
+size 295585110

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e717534fafe38840fb8c361d11d64541821aebf3cdd6f39e1f77013437871306
+size 295585110

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac8da32902dca181676ea7e5c2f04894bf057c516027b502d39bce2e20e08b2
+size 295585110

client_states_NEW_fedavg_bs4_saveoptim_lr2e-5_5e-5_sc103_4tasks_5rounds_fixtir100_T0125_decay099_SEED2/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b5157aa89baeeacaabdfccd8363baebbaf64e31b05696aa6d88d8bc57449b07
+size 295584650