Upload folder using huggingface_hub

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:728d6ba4c5b19080b714b1012b9adf932eb4d18e3c5074ec3ddb7b43bfa23d55
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa61c283d43f29bf129422368ce4888725b1c89de4df0adb636e36ad09945a83
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017f1b169c8c71390683efd712f3e5a8bb415020045c0fcd00f826e57bdf6a30
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0bceb5008fb2040cb06c09f35eb15e9782bfc7a7203d141c26710db8cf577ba
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2518c89d8178c64b6b50ffe557713f3f361198d2ae3bda48f5344facf4a16e7
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da468699be8d5dc24b362a71167e7f3255b0bbdd342ba8a897073123e4353e1b
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f766d5adcabd02e5e5cbce88879a6f0f20eee530dae3ec9a7ef6dc0d6b16cc0
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:919d983e2dff1839f8453d5fe5421a9d66c5c6436fb2ed9c7c1a5630c04e8865
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_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": 4.488297939300537,
+      "learning_rate": 2e-05,
+      "loss": 0.8213,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.2015602588653564,
+      "learning_rate": 2e-05,
+      "loss": 0.3233,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.10709953308105469,
+      "learning_rate": 2e-05,
+      "loss": 0.0326,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5322740077972412,
+      "learning_rate": 2e-05,
+      "loss": 0.046,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.848097801208496,
+      "learning_rate": 2e-05,
+      "loss": 0.5195,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 7.241242408752441,
+      "learning_rate": 2e-05,
+      "loss": 1.0108,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.5567567348480225,
+      "learning_rate": 2e-05,
+      "loss": 0.2803,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 8.982904434204102,
+      "learning_rate": 2e-05,
+      "loss": 1.6695,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 7.282568454742432,
+      "learning_rate": 2e-05,
+      "loss": 2.0625,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.1677680015563965,
+      "learning_rate": 2e-05,
+      "loss": 1.1116,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.5743522644042969,
+      "learning_rate": 2e-05,
+      "loss": 0.1125,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.533093452453613,
+      "learning_rate": 2e-05,
+      "loss": 0.6137,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.3698212802410126,
+      "learning_rate": 2e-05,
+      "loss": 0.5115,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.12430024147033691,
+      "learning_rate": 2e-05,
+      "loss": 0.4586,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.9602198600769043,
+      "learning_rate": 2e-05,
+      "loss": 0.5641,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.13387736678123474,
+      "learning_rate": 2e-05,
+      "loss": 0.0578,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.6813492178916931,
+      "learning_rate": 2e-05,
+      "loss": 0.1239,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 6.66446590423584,
+      "learning_rate": 2e-05,
+      "loss": 0.5516,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.5657436847686768,
+      "learning_rate": 2e-05,
+      "loss": 0.3398,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.1527981758117676,
+      "learning_rate": 2e-05,
+      "loss": 0.2944,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.614070415496826,
+      "learning_rate": 2e-05,
+      "loss": 0.1658,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.45530366897583,
+      "learning_rate": 2e-05,
+      "loss": 0.5164,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.26953551173210144,
+      "learning_rate": 2e-05,
+      "loss": 0.4748,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.090765357017517,
+      "learning_rate": 2e-05,
+      "loss": 0.7685,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.2699200510978699,
+      "learning_rate": 2e-05,
+      "loss": 0.1514,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.6171990633010864,
+      "learning_rate": 2e-05,
+      "loss": 0.2485,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.15912304818630219,
+      "learning_rate": 2e-05,
+      "loss": 0.0779,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.3092189431190491,
+      "learning_rate": 2e-05,
+      "loss": 0.05,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.4640393257141113,
+      "learning_rate": 2e-05,
+      "loss": 1.5109,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.20263293385505676,
+      "learning_rate": 2e-05,
+      "loss": 0.0228,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.5835360288619995,
+      "learning_rate": 2e-05,
+      "loss": 0.3195,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.5622631907463074,
+      "learning_rate": 2e-05,
+      "loss": 0.3646,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.5297622680664062,
+      "learning_rate": 2e-05,
+      "loss": 0.0998,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.649733781814575,
+      "learning_rate": 2e-05,
+      "loss": 0.4615,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.102297067642212,
+      "learning_rate": 2e-05,
+      "loss": 0.7252,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.8365728855133057,
+      "learning_rate": 2e-05,
+      "loss": 0.1145,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.753603219985962,
+      "learning_rate": 2e-05,
+      "loss": 1.8487,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.4691812992095947,
+      "learning_rate": 2e-05,
+      "loss": 0.6427,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.433463990688324,
+      "learning_rate": 2e-05,
+      "loss": 0.4312,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.9315136075019836,
+      "learning_rate": 2e-05,
+      "loss": 0.7201,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.47460275888442993,
+      "learning_rate": 2e-05,
+      "loss": 0.2802,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 2.672191858291626,
+      "learning_rate": 2e-05,
+      "loss": 0.4495,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.11207932233810425,
+      "learning_rate": 2e-05,
+      "loss": 0.0541,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.3238513469696045,
+      "learning_rate": 2e-05,
+      "loss": 0.4426,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5.984368801116943,
+      "learning_rate": 2e-05,
+      "loss": 0.6007,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.550984263420105,
+      "learning_rate": 2e-05,
+      "loss": 0.5361,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.4784111976623535,
+      "learning_rate": 2e-05,
+      "loss": 2.0455,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.2885706424713135,
+      "learning_rate": 2e-05,
+      "loss": 1.0766,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.1742780208587646,
+      "learning_rate": 2e-05,
+      "loss": 0.6709,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.15040038526058197,
+      "learning_rate": 2e-05,
+      "loss": 0.1122,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5263582228905984.0,
+      "train_loss": 0.5497678864002228,
+      "train_runtime": 133.53,
+      "train_samples_per_second": 2.996,
+      "train_steps_per_second": 0.749
+    }
+  ],
+  "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": 5263582228905984.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9032d90f34cef39fa6e4bf627afae6f29950b13b086b63656488b788df1db35
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33dd8077a31a7c6275623b56a2005200e2e102a1351991f4fa5ad30eb361283e
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2bb8ffef6b7c0dd134789ce18680c101d920fe42fbf475e19ad67f548cac81f
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:003c0311ada693e0dbaa5fd375cc055b7ee26ed20a75fa08ef75ffd121321755
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a564bdea8fc88a44c66774524393c200c1d634baf5c5e83c4c3cb988c0efd489
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5275bc541a33aacc7ce239bedd4a002e9f75e6e0c4cc63f9ac17ee1ac409aa13
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89c8e7f6501ef0bc6dc42428018c180694374c22a371d31dac48126b0caebf14
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef770e12c109d4ae06f167d9867505c28b1006119a4767e4b2c94a0e232f01c
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/1_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.004004059359431267,
+      "learning_rate": 2e-05,
+      "loss": 0.3447,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.6166858673095703,
+      "learning_rate": 2e-05,
+      "loss": 0.1358,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.05047175660729408,
+      "learning_rate": 2e-05,
+      "loss": 0.0837,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.025049692019820213,
+      "learning_rate": 2e-05,
+      "loss": 0.0053,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.004746309015899897,
+      "learning_rate": 2e-05,
+      "loss": 0.0005,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 13.424479484558105,
+      "learning_rate": 2e-05,
+      "loss": 0.4725,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.037212975323200226,
+      "learning_rate": 2e-05,
+      "loss": 0.0015,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.1019517108798027,
+      "learning_rate": 2e-05,
+      "loss": 0.0244,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.5367830395698547,
+      "learning_rate": 2e-05,
+      "loss": 0.8817,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.3478948473930359,
+      "learning_rate": 2e-05,
+      "loss": 0.0171,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.02469763346016407,
+      "learning_rate": 2e-05,
+      "loss": 0.0477,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.1854998618364334,
+      "learning_rate": 2e-05,
+      "loss": 0.008,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.43639543652534485,
+      "learning_rate": 2e-05,
+      "loss": 0.0286,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.5476244688034058,
+      "learning_rate": 2e-05,
+      "loss": 0.0065,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.25762972235679626,
+      "learning_rate": 2e-05,
+      "loss": 0.012,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.06379427760839462,
+      "learning_rate": 2e-05,
+      "loss": 0.0028,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.1136415004730225,
+      "learning_rate": 2e-05,
+      "loss": 0.2595,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.006398867815732956,
+      "learning_rate": 2e-05,
+      "loss": 0.0006,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.07445599883794785,
+      "learning_rate": 2e-05,
+      "loss": 0.0034,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.44294989109039307,
+      "learning_rate": 2e-05,
+      "loss": 0.0494,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 9.519878387451172,
+      "learning_rate": 2e-05,
+      "loss": 0.7374,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.6144859790802,
+      "learning_rate": 2e-05,
+      "loss": 0.362,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.006623577326536179,
+      "learning_rate": 2e-05,
+      "loss": 0.0026,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.050278618931770325,
+      "learning_rate": 2e-05,
+      "loss": 0.0036,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.005851195193827152,
+      "learning_rate": 2e-05,
+      "loss": 0.0022,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.014566048979759216,
+      "learning_rate": 2e-05,
+      "loss": 0.0738,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.3747220039367676,
+      "learning_rate": 2e-05,
+      "loss": 0.0717,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.02883150428533554,
+      "learning_rate": 2e-05,
+      "loss": 0.0487,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.03793926164507866,
+      "learning_rate": 2e-05,
+      "loss": 0.1382,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.05449283495545387,
+      "learning_rate": 2e-05,
+      "loss": 0.0845,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.013709462247788906,
+      "learning_rate": 2e-05,
+      "loss": 0.0027,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.02217160537838936,
+      "learning_rate": 2e-05,
+      "loss": 0.0028,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.032236699014902115,
+      "learning_rate": 2e-05,
+      "loss": 0.0032,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.3997226357460022,
+      "learning_rate": 2e-05,
+      "loss": 0.0456,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.0048163337633013725,
+      "learning_rate": 2e-05,
+      "loss": 0.0017,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.0273527093231678,
+      "learning_rate": 2e-05,
+      "loss": 0.0031,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.17575235664844513,
+      "learning_rate": 2e-05,
+      "loss": 0.0314,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.004614345263689756,
+      "learning_rate": 2e-05,
+      "loss": 0.0008,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.5244370102882385,
+      "learning_rate": 2e-05,
+      "loss": 0.0669,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.0037669800221920013,
+      "learning_rate": 2e-05,
+      "loss": 0.0017,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.00268436293117702,
+      "learning_rate": 2e-05,
+      "loss": 0.0156,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.0031300033442676067,
+      "learning_rate": 2e-05,
+      "loss": 0.0007,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.2447715997695923,
+      "learning_rate": 2e-05,
+      "loss": 0.0761,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.005236513447016478,
+      "learning_rate": 2e-05,
+      "loss": 0.0027,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.09511196613311768,
+      "learning_rate": 2e-05,
+      "loss": 0.0065,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.9401309490203857,
+      "learning_rate": 2e-05,
+      "loss": 0.0501,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.001948182238265872,
+      "learning_rate": 2e-05,
+      "loss": 0.0201,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.027201630175113678,
+      "learning_rate": 2e-05,
+      "loss": 0.0024,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.0009806285379454494,
+      "learning_rate": 2e-05,
+      "loss": 0.0005,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.03273758664727211,
+      "learning_rate": 2e-05,
+      "loss": 0.0024,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5305565551001600.0,
+      "train_loss": 0.08494877636432648,
+      "train_runtime": 132.8331,
+      "train_samples_per_second": 3.011,
+      "train_steps_per_second": 0.753
+    }
+  ],
+  "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": 5305565551001600.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1d28f087efe120b414df4924b261ccd31dd6ee6b2b30a91f69e7f89244f980
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8273181a2e629f86cf2658c387ec2640d3deea1a393a2c1bd34bd71988179822
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da5003f6e0dd4795d51015f108dc44943ae2b41c19e3609b466d09235b694a8d
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40039a0518caaebed21eab55982ac128d6834de3894ee5d633a3a10584a59db8
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc62556ab1a7891aa14633926470eff42d30a8bfb39a6f572659050744b3e561
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16e4e2d8e35484f3eb693a3f87b9f047e010198f9971bb4627e7d22b76a8ec88
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7e89a8fe2c344f35939b58efc8464e0d014bb2f494eda8659cd792ab4fe16fd
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9cc8240e39eac6fdf55c3ec730e34b31c5505801ab276f219c706e8f3b2b6e7
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_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": 0.5714724659919739,
+      "learning_rate": 2e-05,
+      "loss": 0.1571,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2446060180664062,
+      "learning_rate": 2e-05,
+      "loss": 1.0388,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.3332496881484985,
+      "learning_rate": 2e-05,
+      "loss": 1.0596,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.8514249324798584,
+      "learning_rate": 2e-05,
+      "loss": 0.9033,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.338616132736206,
+      "learning_rate": 2e-05,
+      "loss": 0.3997,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.713435411453247,
+      "learning_rate": 2e-05,
+      "loss": 1.2887,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.17629539966583252,
+      "learning_rate": 2e-05,
+      "loss": 0.2615,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.6102802157402039,
+      "learning_rate": 2e-05,
+      "loss": 0.2273,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 4.298458576202393,
+      "learning_rate": 2e-05,
+      "loss": 0.6318,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.091003894805908,
+      "learning_rate": 2e-05,
+      "loss": 1.5592,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.8855243921279907,
+      "learning_rate": 2e-05,
+      "loss": 0.1756,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.281097412109375,
+      "learning_rate": 2e-05,
+      "loss": 0.6557,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.874906301498413,
+      "learning_rate": 2e-05,
+      "loss": 1.1984,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.6696105003356934,
+      "learning_rate": 2e-05,
+      "loss": 0.4452,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.47936731576919556,
+      "learning_rate": 2e-05,
+      "loss": 0.239,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.7706718444824219,
+      "learning_rate": 2e-05,
+      "loss": 0.28,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.2293989658355713,
+      "learning_rate": 2e-05,
+      "loss": 0.784,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.089874744415283,
+      "learning_rate": 2e-05,
+      "loss": 0.2619,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.9052956104278564,
+      "learning_rate": 2e-05,
+      "loss": 0.7359,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.9239583015441895,
+      "learning_rate": 2e-05,
+      "loss": 1.1067,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.5744247436523438,
+      "learning_rate": 2e-05,
+      "loss": 0.7893,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.3776748180389404,
+      "learning_rate": 2e-05,
+      "loss": 0.1343,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.573690891265869,
+      "learning_rate": 2e-05,
+      "loss": 0.9003,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.9480522274971008,
+      "learning_rate": 2e-05,
+      "loss": 0.3198,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.3368165493011475,
+      "learning_rate": 2e-05,
+      "loss": 0.3361,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.9095264673233032,
+      "learning_rate": 2e-05,
+      "loss": 0.4017,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.4821699857711792,
+      "learning_rate": 2e-05,
+      "loss": 0.6252,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.4606550931930542,
+      "learning_rate": 2e-05,
+      "loss": 0.5357,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.1136282682418823,
+      "learning_rate": 2e-05,
+      "loss": 0.2463,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2054370790719986,
+      "learning_rate": 2e-05,
+      "loss": 0.487,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.599104881286621,
+      "learning_rate": 2e-05,
+      "loss": 0.6095,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.3351110219955444,
+      "learning_rate": 2e-05,
+      "loss": 0.5283,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.6148331165313721,
+      "learning_rate": 2e-05,
+      "loss": 0.2094,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.5133107900619507,
+      "learning_rate": 2e-05,
+      "loss": 0.3358,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.8088291883468628,
+      "learning_rate": 2e-05,
+      "loss": 0.9817,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.7727972269058228,
+      "learning_rate": 2e-05,
+      "loss": 0.926,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.41457489132881165,
+      "learning_rate": 2e-05,
+      "loss": 0.0731,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.7710464000701904,
+      "learning_rate": 2e-05,
+      "loss": 0.3228,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.558899998664856,
+      "learning_rate": 2e-05,
+      "loss": 0.1278,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.154862880706787,
+      "learning_rate": 2e-05,
+      "loss": 0.882,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.9989376068115234,
+      "learning_rate": 2e-05,
+      "loss": 2.3649,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.19704104959964752,
+      "learning_rate": 2e-05,
+      "loss": 0.0322,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.101407289505005,
+      "learning_rate": 2e-05,
+      "loss": 0.6594,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.1198782920837402,
+      "learning_rate": 2e-05,
+      "loss": 0.5204,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.034351348876953,
+      "learning_rate": 2e-05,
+      "loss": 2.131,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.07952385395765305,
+      "learning_rate": 2e-05,
+      "loss": 0.1322,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.250375509262085,
+      "learning_rate": 2e-05,
+      "loss": 0.464,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.643530547618866,
+      "learning_rate": 2e-05,
+      "loss": 0.2473,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.6983582973480225,
+      "learning_rate": 2e-05,
+      "loss": 1.8322,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.44969141483306885,
+      "learning_rate": 2e-05,
+      "loss": 0.1492,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5196654105853952.0,
+      "train_loss": 0.6342864322662354,
+      "train_runtime": 132.2335,
+      "train_samples_per_second": 3.025,
+      "train_steps_per_second": 0.756
+    }
+  ],
+  "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": 5196654105853952.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb003799857a383df7314d25d02e962cdf3e2c890804f22b2c1e4a3f011cc7f
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca24c50759ed3eb88f7963dedde1e4a8576ca247efd25e225758ea244af6e28
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:421cf5e2a9784540e893ab22103155f6d62ee22f44d9f6d0b9e339dd2e4e16fc
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd3faece660cdd46a6fa9e2598eeb69b0985458745699d032753ae6bd8d77655
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f737d9eb3f2bdab007289c6b39b184114bba9b98c6593ced73147eb10ab5fd
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db7097cd0df61101c7e114310f111ac37317d5014ceb0b15593e2e6d770dea1
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e1d945bdb21f7ecce54afab5d6db5b9aeea64e8d0255ebaca0f7ab6c62dc28
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ed27e9bd4bb126a53cbbb21d85bbd301c2c043673f3f4d896624aa303699994
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_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": 6.829958438873291,
+      "learning_rate": 2e-05,
+      "loss": 2.5042,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.7837774753570557,
+      "learning_rate": 2e-05,
+      "loss": 0.9837,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.7576625347137451,
+      "learning_rate": 2e-05,
+      "loss": 0.8931,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 8.202378273010254,
+      "learning_rate": 2e-05,
+      "loss": 2.0876,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.5554375648498535,
+      "learning_rate": 2e-05,
+      "loss": 1.0562,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.540701866149902,
+      "learning_rate": 2e-05,
+      "loss": 1.7771,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 6.276415824890137,
+      "learning_rate": 2e-05,
+      "loss": 1.9002,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.344941139221191,
+      "learning_rate": 2e-05,
+      "loss": 1.0422,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.9381601810455322,
+      "learning_rate": 2e-05,
+      "loss": 0.4009,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.276778221130371,
+      "learning_rate": 2e-05,
+      "loss": 1.1137,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.5656118392944336,
+      "learning_rate": 2e-05,
+      "loss": 0.5251,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.265941619873047,
+      "learning_rate": 2e-05,
+      "loss": 1.0292,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.6971996426582336,
+      "learning_rate": 2e-05,
+      "loss": 0.6931,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.231698036193848,
+      "learning_rate": 2e-05,
+      "loss": 0.6691,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.6015894412994385,
+      "learning_rate": 2e-05,
+      "loss": 0.7389,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.6058948040008545,
+      "learning_rate": 2e-05,
+      "loss": 0.5077,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.4528666734695435,
+      "learning_rate": 2e-05,
+      "loss": 1.8561,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 9.451675415039062,
+      "learning_rate": 2e-05,
+      "loss": 2.4665,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.3950164318084717,
+      "learning_rate": 2e-05,
+      "loss": 0.7929,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.098973512649536,
+      "learning_rate": 2e-05,
+      "loss": 0.8046,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 6.233034610748291,
+      "learning_rate": 2e-05,
+      "loss": 1.3336,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.796836853027344,
+      "learning_rate": 2e-05,
+      "loss": 1.5306,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.2648861408233643,
+      "learning_rate": 2e-05,
+      "loss": 0.4912,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.7729060649871826,
+      "learning_rate": 2e-05,
+      "loss": 0.2507,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.1913087368011475,
+      "learning_rate": 2e-05,
+      "loss": 1.6815,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.8567243814468384,
+      "learning_rate": 2e-05,
+      "loss": 1.3694,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.24950291216373444,
+      "learning_rate": 2e-05,
+      "loss": 0.655,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.5070067644119263,
+      "learning_rate": 2e-05,
+      "loss": 0.7996,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.0526025295257568,
+      "learning_rate": 2e-05,
+      "loss": 0.6737,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.1971511840820312,
+      "learning_rate": 2e-05,
+      "loss": 1.0914,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.7395142316818237,
+      "learning_rate": 2e-05,
+      "loss": 0.9404,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.535018801689148,
+      "learning_rate": 2e-05,
+      "loss": 0.8744,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.6441831588745117,
+      "learning_rate": 2e-05,
+      "loss": 0.8961,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.7198731899261475,
+      "learning_rate": 2e-05,
+      "loss": 1.5688,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.4028687477111816,
+      "learning_rate": 2e-05,
+      "loss": 0.8631,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.438341498374939,
+      "learning_rate": 2e-05,
+      "loss": 1.3883,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.202860116958618,
+      "learning_rate": 2e-05,
+      "loss": 1.6366,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.288334846496582,
+      "learning_rate": 2e-05,
+      "loss": 0.6058,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.9990512728691101,
+      "learning_rate": 2e-05,
+      "loss": 0.7013,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.8788294792175293,
+      "learning_rate": 2e-05,
+      "loss": 0.2433,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.201095700263977,
+      "learning_rate": 2e-05,
+      "loss": 0.2564,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.8276937007904053,
+      "learning_rate": 2e-05,
+      "loss": 0.4318,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.879300594329834,
+      "learning_rate": 2e-05,
+      "loss": 1.2925,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.9571355581283569,
+      "learning_rate": 2e-05,
+      "loss": 0.3857,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.6863470077514648,
+      "learning_rate": 2e-05,
+      "loss": 1.2266,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.439926862716675,
+      "learning_rate": 2e-05,
+      "loss": 0.6477,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.6964446306228638,
+      "learning_rate": 2e-05,
+      "loss": 0.7348,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.6687580347061157,
+      "learning_rate": 2e-05,
+      "loss": 0.4901,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.4010913372039795,
+      "learning_rate": 2e-05,
+      "loss": 0.6664,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8191789984703064,
+      "learning_rate": 2e-05,
+      "loss": 0.6277,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5377398090498048.0,
+      "train_loss": 1.003931999206543,
+      "train_runtime": 135.7651,
+      "train_samples_per_second": 2.946,
+      "train_steps_per_second": 0.737
+    }
+  ],
+  "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": 5377398090498048.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32b3a5ba3a6d1dafd38b6f0715b4b0dc0decc7d64a950617dc80b54c7708bb7e
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:256079d30a10b740628769d73f6a5019e2ba62ea4f7f536388d5a5ef929235c0
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca6a46bdefbdee9531c8d29c0bf58b4ceeee160bed76cde4737882f8e3b4cc6
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:760a8875be98d6d514447274671bdc52c2aa3464b80a4875dadd162ef9b2c688
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a4dd094992fcec1ef064969e90f7650d0500304b011143bfcd4eb20deaae72
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0cfafac6c768974632a02e6efbfd1f63096c619db44590c225e4bb0a0d4a51
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec841516a4a347605608f8fe502a97f278b3a6ef940db8f9facbea73b4337b93
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f354f23d1a571c3b3872c399589ffc1bb71f941025ca1e7e3eedf1668145ae
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_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": 0.5834111571311951,
+      "learning_rate": 2e-05,
+      "loss": 0.4239,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.5508387088775635,
+      "learning_rate": 2e-05,
+      "loss": 0.8509,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.6101821660995483,
+      "learning_rate": 2e-05,
+      "loss": 0.8783,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.7012138366699219,
+      "learning_rate": 2e-05,
+      "loss": 0.6616,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.0544990301132202,
+      "learning_rate": 2e-05,
+      "loss": 0.594,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.8790334463119507,
+      "learning_rate": 2e-05,
+      "loss": 0.1706,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.99387788772583,
+      "learning_rate": 2e-05,
+      "loss": 1.0906,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.062889337539673,
+      "learning_rate": 2e-05,
+      "loss": 0.9158,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.20981502532959,
+      "learning_rate": 2e-05,
+      "loss": 0.5364,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.117920398712158,
+      "learning_rate": 2e-05,
+      "loss": 0.3741,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.020120620727539,
+      "learning_rate": 2e-05,
+      "loss": 2.053,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.6177252531051636,
+      "learning_rate": 2e-05,
+      "loss": 0.793,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.2334187030792236,
+      "learning_rate": 2e-05,
+      "loss": 0.3458,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.138347625732422,
+      "learning_rate": 2e-05,
+      "loss": 1.125,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.481730937957764,
+      "learning_rate": 2e-05,
+      "loss": 1.0882,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.1140084266662598,
+      "learning_rate": 2e-05,
+      "loss": 0.8222,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.2080310583114624,
+      "learning_rate": 2e-05,
+      "loss": 0.5059,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 4.3568034172058105,
+      "learning_rate": 2e-05,
+      "loss": 1.2988,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.2587180137634277,
+      "learning_rate": 2e-05,
+      "loss": 0.5841,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.744922161102295,
+      "learning_rate": 2e-05,
+      "loss": 1.2025,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.104158878326416,
+      "learning_rate": 2e-05,
+      "loss": 1.2596,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.9659993648529053,
+      "learning_rate": 2e-05,
+      "loss": 0.7183,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.192279815673828,
+      "learning_rate": 2e-05,
+      "loss": 0.9789,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.752039909362793,
+      "learning_rate": 2e-05,
+      "loss": 0.6117,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.540257692337036,
+      "learning_rate": 2e-05,
+      "loss": 0.6501,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.6760121583938599,
+      "learning_rate": 2e-05,
+      "loss": 1.2218,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.0214837789535522,
+      "learning_rate": 2e-05,
+      "loss": 0.48,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.62760990858078,
+      "learning_rate": 2e-05,
+      "loss": 0.1959,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.3719955682754517,
+      "learning_rate": 2e-05,
+      "loss": 0.6898,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.215210199356079,
+      "learning_rate": 2e-05,
+      "loss": 0.8142,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.002267837524414,
+      "learning_rate": 2e-05,
+      "loss": 0.6765,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.5476014614105225,
+      "learning_rate": 2e-05,
+      "loss": 0.8481,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.1041159629821777,
+      "learning_rate": 2e-05,
+      "loss": 1.1137,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.9381476044654846,
+      "learning_rate": 2e-05,
+      "loss": 0.5496,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.7756975889205933,
+      "learning_rate": 2e-05,
+      "loss": 0.8465,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.1665791273117065,
+      "learning_rate": 2e-05,
+      "loss": 0.5091,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.244778111577034,
+      "learning_rate": 2e-05,
+      "loss": 0.6248,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.372105598449707,
+      "learning_rate": 2e-05,
+      "loss": 1.4099,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.1838430166244507,
+      "learning_rate": 2e-05,
+      "loss": 0.702,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.4739941358566284,
+      "learning_rate": 2e-05,
+      "loss": 0.4792,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.9360646605491638,
+      "learning_rate": 2e-05,
+      "loss": 0.5658,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.7926190495491028,
+      "learning_rate": 2e-05,
+      "loss": 0.5865,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.8734688758850098,
+      "learning_rate": 2e-05,
+      "loss": 0.3024,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.43634670972824097,
+      "learning_rate": 2e-05,
+      "loss": 0.4245,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.4523383378982544,
+      "learning_rate": 2e-05,
+      "loss": 0.9024,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.3738402128219604,
+      "learning_rate": 2e-05,
+      "loss": 0.5415,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.3416821956634521,
+      "learning_rate": 2e-05,
+      "loss": 0.7211,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.8769800662994385,
+      "learning_rate": 2e-05,
+      "loss": 0.6781,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.8396403789520264,
+      "learning_rate": 2e-05,
+      "loss": 0.259,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.1549229621887207,
+      "learning_rate": 2e-05,
+      "loss": 1.0028,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 6021565481222144.0,
+      "train_loss": 0.7535763168334961,
+      "train_runtime": 149.217,
+      "train_samples_per_second": 2.681,
+      "train_steps_per_second": 0.67
+    }
+  ],
+  "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": 6021565481222144.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1363cb1494b81bacaea5a463fbe19042b003c5d208a076338268e02939ff43
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:284d050900e95a109a18edaa7a4b4a1f99a53b3ca416375c7b54f769a0b6a639
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beb2e32839b6bedfffffa2a0190dcd537427f909fbb2ffd24049743f0e546646
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40418bc488bd5b45c0066f91e0f3944c8fb17aa66bf2bf99cdbd3e870cca460a
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc310_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7dbe5fe5dc3ed8c770a83a2527f0dabcd7d9dc80f8d9b0866055ad108d05c6a
+size 778341034