diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round10.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..98029c6b68a40d7e56a6cd6f621c6a0475570e0d
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa789cff960ae4ee81fa9ac6a075adcf63e56a3ec6c3ecd5699d4f789f3c213
+size 360880622
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round12.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..da2a8c080d75155e6322c1d86da86a9b6b08d2cb
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432f8736e99ab8b1e39223df1d48f017f6fd4f4f9643ca359d4b99141e4f4d74
+size 360880622
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round15.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e5b5d70bd627767deadda7b80f80031225e2974c
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c8fc312b07e6987f1125962ff398f8861f24936ce222a149189568327cac67
+size 360880622
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round17.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..859f1811f20825130944a49081f9c70f0bf7331a
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:051032624bbe04510f16be6fdc206a54f23b25aa871002ca00fef79182e7c513
+size 360880622
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round2.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6ce47a67ceb29441bd19346a44e4ab6a86d91d34
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d675c4b87e3db30f58b3688f502ecdfd3b852d0a28b2d067cc72ca763b08cd5a
+size 360880106
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round20.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b00c4e1f9af87c04e2e9a3d3e12477087e4176f3
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:381ce3ba71ec63c166839e10280a43a1e9f31dc4d7fa46bef9e6fa158c302e49
+size 360880622
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round5.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1c24b7b8ac9b71e8143bb43f775ed25a051eda3d
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e8733bb21c24aa296509cc99e8f4f9b3259d52e55bf918ee4c9f835985258f
+size 360880106
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round7.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5ef9be35a080e5a0cae4fd64a2b89da9aacb94bf
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89fe3d8b4f7d27dbc7e4251a76c701fd44c4ad0c7fadf149e72d9c82c2e77db3
+size 360880106
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_trainer_state.json b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..729e0266cfb79a8e5fd95ef8eff5b5252786cf19
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_trainer_state.json
@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 9.423497200012207,
+      "learning_rate": 2e-05,
+      "loss": 0.9426,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.242947101593018,
+      "learning_rate": 2e-05,
+      "loss": 0.4941,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.23292511701583862,
+      "learning_rate": 2e-05,
+      "loss": 0.0161,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.2664003372192383,
+      "learning_rate": 2e-05,
+      "loss": 0.0807,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 16.083553314208984,
+      "learning_rate": 2e-05,
+      "loss": 1.5403,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 13.203125,
+      "learning_rate": 2e-05,
+      "loss": 1.3032,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 9.931619644165039,
+      "learning_rate": 2e-05,
+      "loss": 0.4531,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 12.197830200195312,
+      "learning_rate": 2e-05,
+      "loss": 2.0777,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 13.418411254882812,
+      "learning_rate": 2e-05,
+      "loss": 2.5869,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 7.835398197174072,
+      "learning_rate": 2e-05,
+      "loss": 1.2992,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.8039246201515198,
+      "learning_rate": 2e-05,
+      "loss": 0.0811,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 7.014680862426758,
+      "learning_rate": 2e-05,
+      "loss": 1.1046,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 8.817255973815918,
+      "learning_rate": 2e-05,
+      "loss": 0.8185,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.18149733543396,
+      "learning_rate": 2e-05,
+      "loss": 0.1982,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.396234154701233,
+      "learning_rate": 2e-05,
+      "loss": 0.7965,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 9.15268325805664,
+      "learning_rate": 2e-05,
+      "loss": 0.5244,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 5.599765777587891,
+      "learning_rate": 2e-05,
+      "loss": 0.686,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 11.052386283874512,
+      "learning_rate": 2e-05,
+      "loss": 1.5529,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.8186702728271484,
+      "learning_rate": 2e-05,
+      "loss": 0.6692,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.434682846069336,
+      "learning_rate": 2e-05,
+      "loss": 0.5903,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.227272033691406,
+      "learning_rate": 2e-05,
+      "loss": 0.2824,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.939194679260254,
+      "learning_rate": 2e-05,
+      "loss": 1.3968,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5867003798484802,
+      "learning_rate": 2e-05,
+      "loss": 0.393,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 6.319277763366699,
+      "learning_rate": 2e-05,
+      "loss": 0.6232,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.46071195602417,
+      "learning_rate": 2e-05,
+      "loss": 0.2416,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.9734086990356445,
+      "learning_rate": 2e-05,
+      "loss": 0.6859,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.4034255743026733,
+      "learning_rate": 2e-05,
+      "loss": 0.5754,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.3656154870986938,
+      "learning_rate": 2e-05,
+      "loss": 0.1789,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.575096130371094,
+      "learning_rate": 2e-05,
+      "loss": 2.5298,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.9366658329963684,
+      "learning_rate": 2e-05,
+      "loss": 0.1539,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.2089002132415771,
+      "learning_rate": 2e-05,
+      "loss": 0.5569,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.383746862411499,
+      "learning_rate": 2e-05,
+      "loss": 0.3214,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.41840168833732605,
+      "learning_rate": 2e-05,
+      "loss": 0.2939,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.619239330291748,
+      "learning_rate": 2e-05,
+      "loss": 0.6163,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.0113186836242676,
+      "learning_rate": 2e-05,
+      "loss": 0.5063,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.8169399499893188,
+      "learning_rate": 2e-05,
+      "loss": 0.3002,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 4.200991630554199,
+      "learning_rate": 2e-05,
+      "loss": 1.5329,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.631651520729065,
+      "learning_rate": 2e-05,
+      "loss": 0.6569,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.40286803245544434,
+      "learning_rate": 2e-05,
+      "loss": 1.0856,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.7753989696502686,
+      "learning_rate": 2e-05,
+      "loss": 0.9605,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.5652052164077759,
+      "learning_rate": 2e-05,
+      "loss": 0.3553,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 5.572319984436035,
+      "learning_rate": 2e-05,
+      "loss": 1.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.4662155210971832,
+      "learning_rate": 2e-05,
+      "loss": 0.1469,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.5111005306243896,
+      "learning_rate": 2e-05,
+      "loss": 0.9844,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.1454522609710693,
+      "learning_rate": 2e-05,
+      "loss": 0.3873,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.0339059829711914,
+      "learning_rate": 2e-05,
+      "loss": 1.2139,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.232385158538818,
+      "learning_rate": 2e-05,
+      "loss": 2.1749,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.8107025623321533,
+      "learning_rate": 2e-05,
+      "loss": 1.4807,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.099456787109375,
+      "learning_rate": 2e-05,
+      "loss": 1.5927,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4381089210510254,
+      "learning_rate": 2e-05,
+      "loss": 0.2756,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2185214759534592.0,
+      "train_loss": 0.8263820886611939,
+      "train_runtime": 70.7407,
+      "train_samples_per_second": 5.654,
+      "train_steps_per_second": 1.414
+    }
+  ],
+  "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": 2185214759534592.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round10.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..950f4affb232fdce12a68bf978d70e2a68f10994
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca00ad56c9180596acb64d02ed1c2c93b5167313f4ddacae17fe6151ab9c155
+size 360880622
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round12.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ca45c768b5d00f5a854442a17df48b76da338c0a
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5292459abad60fd048050fb5779edeaa54e68fd64f6d8f672e54415ffd378568
+size 360880622
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round15.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a199b5e32a5713dddde1f9ac1fc688aecc104975
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c51878f3c0c54cdc54eb26bf35a2757735003b92f7da1689081ec193e89b87b
+size 360880622
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round17.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f4fde7107a633a74720faac4e487814b8f68b607
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95a9f87437d27a76a6cac22a0d23d1b90a201e43d7c601b4f2178ea763b5880d
+size 360880622
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round2.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7704541746d7d8731a76427b7d12b85e42da0194
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d126b766b20e0cad09d67d67cb29db4c25a011f24be748b251d8b5cf6288b90a
+size 360880106
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round20.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5425b60fe66a997284f33ff9096efc3a3aa0c93c
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ad85bffca2bf517e6a2294ecc419a949579749fae404a75f6f3de58d5c4be5
+size 360880622
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round5.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..aee22c7209952ca7028548a8e9a405c899d7260b
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1e47d59fb16d75680a1f95491ce48c1a01605d42bde715afab635cd1fd4fc4
+size 360880106
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round7.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..02a5a84cfc612d83536c01a7d64b37738a0ab758
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8eb669eede9faee34f088d7edbeb9c774a119de291ab6f2ebf3c071d1346dc1
+size 360880106
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_trainer_state.json b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..d2e6450f9ef9640b208ea514896b20a608322d3c
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_trainer_state.json
@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.06926380842924118,
+      "learning_rate": 2e-05,
+      "loss": 0.0983,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.14224855601787567,
+      "learning_rate": 2e-05,
+      "loss": 0.5132,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.1999995708465576,
+      "learning_rate": 2e-05,
+      "loss": 0.3034,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.366185188293457,
+      "learning_rate": 2e-05,
+      "loss": 0.0975,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.047930456697940826,
+      "learning_rate": 2e-05,
+      "loss": 0.0054,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.5389022827148438,
+      "learning_rate": 2e-05,
+      "loss": 0.1265,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 4.9087395668029785,
+      "learning_rate": 2e-05,
+      "loss": 0.3968,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5400022864341736,
+      "learning_rate": 2e-05,
+      "loss": 0.2126,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.17520087957382202,
+      "learning_rate": 2e-05,
+      "loss": 0.0546,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.15257954597473145,
+      "learning_rate": 2e-05,
+      "loss": 0.0091,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.7264464497566223,
+      "learning_rate": 2e-05,
+      "loss": 0.1006,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.2980533242225647,
+      "learning_rate": 2e-05,
+      "loss": 0.0133,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.862314760684967,
+      "learning_rate": 2e-05,
+      "loss": 0.0667,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.18892519176006317,
+      "learning_rate": 2e-05,
+      "loss": 0.0091,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.21099655330181122,
+      "learning_rate": 2e-05,
+      "loss": 0.0126,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.5386524200439453,
+      "learning_rate": 2e-05,
+      "loss": 0.0495,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.457860946655273,
+      "learning_rate": 2e-05,
+      "loss": 0.2528,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.006588024087250233,
+      "learning_rate": 2e-05,
+      "loss": 0.0005,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.25489550828933716,
+      "learning_rate": 2e-05,
+      "loss": 0.0122,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.0599042177200317,
+      "learning_rate": 2e-05,
+      "loss": 0.0402,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.65377950668335,
+      "learning_rate": 2e-05,
+      "loss": 0.1825,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.81795072555542,
+      "learning_rate": 2e-05,
+      "loss": 0.5606,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.06573299318552017,
+      "learning_rate": 2e-05,
+      "loss": 0.0047,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.15902456641197205,
+      "learning_rate": 2e-05,
+      "loss": 0.0069,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.09095041453838348,
+      "learning_rate": 2e-05,
+      "loss": 0.0076,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.03288710489869118,
+      "learning_rate": 2e-05,
+      "loss": 0.1018,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.8101238012313843,
+      "learning_rate": 2e-05,
+      "loss": 0.0885,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.018732983618974686,
+      "learning_rate": 2e-05,
+      "loss": 0.0025,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.014856848865747452,
+      "learning_rate": 2e-05,
+      "loss": 0.177,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.006819794420152903,
+      "learning_rate": 2e-05,
+      "loss": 0.0792,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.015503552742302418,
+      "learning_rate": 2e-05,
+      "loss": 0.0177,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.02056262083351612,
+      "learning_rate": 2e-05,
+      "loss": 0.0141,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.32354819774627686,
+      "learning_rate": 2e-05,
+      "loss": 0.0082,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.28828832507133484,
+      "learning_rate": 2e-05,
+      "loss": 0.0255,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.011394195258617401,
+      "learning_rate": 2e-05,
+      "loss": 0.002,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.08238676935434341,
+      "learning_rate": 2e-05,
+      "loss": 0.004,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.0231951475143433,
+      "learning_rate": 2e-05,
+      "loss": 0.0829,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.0049722520634531975,
+      "learning_rate": 2e-05,
+      "loss": 0.0011,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.5577210187911987,
+      "learning_rate": 2e-05,
+      "loss": 0.1744,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.060515161603689194,
+      "learning_rate": 2e-05,
+      "loss": 0.0044,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.24229663610458374,
+      "learning_rate": 2e-05,
+      "loss": 0.0266,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.003239632351323962,
+      "learning_rate": 2e-05,
+      "loss": 0.0009,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.019305258989334106,
+      "learning_rate": 2e-05,
+      "loss": 0.5092,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.03198835998773575,
+      "learning_rate": 2e-05,
+      "loss": 0.0061,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.4420487582683563,
+      "learning_rate": 2e-05,
+      "loss": 0.0412,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 8.323692321777344,
+      "learning_rate": 2e-05,
+      "loss": 0.6126,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.013138143345713615,
+      "learning_rate": 2e-05,
+      "loss": 0.0034,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.41053083539009094,
+      "learning_rate": 2e-05,
+      "loss": 0.0296,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.00738116167485714,
+      "learning_rate": 2e-05,
+      "loss": 0.0008,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.04163911193609238,
+      "learning_rate": 2e-05,
+      "loss": 0.0028,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2202644449853440.0,
+      "train_loss": 0.10307437002658844,
+      "train_runtime": 69.5445,
+      "train_samples_per_second": 5.752,
+      "train_steps_per_second": 1.438
+    }
+  ],
+  "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": 2202644449853440.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round10.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..10269639f15a0f55481f14c2c9f6185573559287
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475ad4672ec3aaec5117fffb04c560d3ac5d8223d0494c2bc0036bf8aeeb4787
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round12.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..af017954e28b5fe80013fa5546b3b12000ad768f
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2073eda13fa87d39360d6fd49065146220dc0190e1004c319eb392aee6a48546
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round15.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b37ec1c70b4515e2ba3990c2ba0c63dc67ae229f
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd0388c3619655d1858ead432f4146aae463cdfad671f284a6b5fdff3e9e119e
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round17.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..dd3879010f4177dd3a1cace678d19aa65210875f
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57bc54c8c645bd8a7a7d98994d2b745350a66ffc36b63c1b3485be984ab5a62c
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round2.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ad9b9367eaab27f48be2a7e06929d96877ac42ea
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53ef0ae39d317134427d6d59afb8c58f3a573b7b4c9b00a837033c99411b1a27
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round20.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d8bb6056478e2148099069dce6ab8cbe3e9f080c
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:333195ee6334bf482e3581bf003c5a1b2bdfbda17a5bce80a1c5e88263b3d4a6
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round5.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..be1d9bbac15fe5b223384d5df3c78154c7d5ed05
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:309ab816121588cffe22b87774005c82c50e3940c8226ade89e6c6edc2ed71f9
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round7.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7299ba6265f74e7dce77ddc2cc8ac200c0ae0105
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4706bf42b3020bbe7065ab079de8559f0a6a271f8b90c7dc1a72ba00aaed5e7e
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_trainer_state.json b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..f0bffb1b868acc9d7fd967bca15a64dfb3b13cb2
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_trainer_state.json
@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.42672601342201233,
+      "learning_rate": 2e-05,
+      "loss": 0.1273,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.3164169788360596,
+      "learning_rate": 2e-05,
+      "loss": 1.0253,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.0701144933700562,
+      "learning_rate": 2e-05,
+      "loss": 1.1081,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.5641934871673584,
+      "learning_rate": 2e-05,
+      "loss": 0.917,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.482414960861206,
+      "learning_rate": 2e-05,
+      "loss": 0.4307,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.699124336242676,
+      "learning_rate": 2e-05,
+      "loss": 1.2775,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.19477766752243042,
+      "learning_rate": 2e-05,
+      "loss": 0.2769,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.49098673462867737,
+      "learning_rate": 2e-05,
+      "loss": 0.227,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 4.419643402099609,
+      "learning_rate": 2e-05,
+      "loss": 0.6207,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.067509412765503,
+      "learning_rate": 2e-05,
+      "loss": 1.6495,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.7661958336830139,
+      "learning_rate": 2e-05,
+      "loss": 0.1506,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.098026752471924,
+      "learning_rate": 2e-05,
+      "loss": 0.6787,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.8598406314849854,
+      "learning_rate": 2e-05,
+      "loss": 1.2822,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.6059610843658447,
+      "learning_rate": 2e-05,
+      "loss": 0.4346,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.4412726163864136,
+      "learning_rate": 2e-05,
+      "loss": 0.2262,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.919790506362915,
+      "learning_rate": 2e-05,
+      "loss": 0.3238,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.1158552169799805,
+      "learning_rate": 2e-05,
+      "loss": 0.7178,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.9022879600524902,
+      "learning_rate": 2e-05,
+      "loss": 0.2602,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.8349590301513672,
+      "learning_rate": 2e-05,
+      "loss": 0.679,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.065424919128418,
+      "learning_rate": 2e-05,
+      "loss": 1.0498,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.6241636276245117,
+      "learning_rate": 2e-05,
+      "loss": 0.824,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.375793218612671,
+      "learning_rate": 2e-05,
+      "loss": 0.1406,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.631248950958252,
+      "learning_rate": 2e-05,
+      "loss": 0.9059,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.9230762124061584,
+      "learning_rate": 2e-05,
+      "loss": 0.3381,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.146935224533081,
+      "learning_rate": 2e-05,
+      "loss": 0.3658,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.643314242362976,
+      "learning_rate": 2e-05,
+      "loss": 0.4425,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.577388048171997,
+      "learning_rate": 2e-05,
+      "loss": 0.6525,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.5418776273727417,
+      "learning_rate": 2e-05,
+      "loss": 0.545,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.3298715353012085,
+      "learning_rate": 2e-05,
+      "loss": 0.2741,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.20194341242313385,
+      "learning_rate": 2e-05,
+      "loss": 0.5407,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.6116507053375244,
+      "learning_rate": 2e-05,
+      "loss": 0.6341,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.1075984239578247,
+      "learning_rate": 2e-05,
+      "loss": 0.5064,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.6221591234207153,
+      "learning_rate": 2e-05,
+      "loss": 0.2389,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.730831503868103,
+      "learning_rate": 2e-05,
+      "loss": 0.353,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.8647536039352417,
+      "learning_rate": 2e-05,
+      "loss": 0.9568,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.6666922569274902,
+      "learning_rate": 2e-05,
+      "loss": 0.9053,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.4998483657836914,
+      "learning_rate": 2e-05,
+      "loss": 0.0881,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.8337864279747009,
+      "learning_rate": 2e-05,
+      "loss": 0.3308,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.7664095759391785,
+      "learning_rate": 2e-05,
+      "loss": 0.144,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.212735176086426,
+      "learning_rate": 2e-05,
+      "loss": 0.9583,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.194940567016602,
+      "learning_rate": 2e-05,
+      "loss": 2.3249,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.21294273436069489,
+      "learning_rate": 2e-05,
+      "loss": 0.0391,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.9137557744979858,
+      "learning_rate": 2e-05,
+      "loss": 0.6782,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.2017444372177124,
+      "learning_rate": 2e-05,
+      "loss": 0.5466,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.704470157623291,
+      "learning_rate": 2e-05,
+      "loss": 1.9585,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.09351445734500885,
+      "learning_rate": 2e-05,
+      "loss": 0.1403,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.1362736225128174,
+      "learning_rate": 2e-05,
+      "loss": 0.4254,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6755289435386658,
+      "learning_rate": 2e-05,
+      "loss": 0.2894,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.5850534439086914,
+      "learning_rate": 2e-05,
+      "loss": 1.7788,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5499467849731445,
+      "learning_rate": 2e-05,
+      "loss": 0.16,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5196654105853952.0,
+      "train_loss": 0.6389807415008545,
+      "train_runtime": 132.4801,
+      "train_samples_per_second": 3.019,
+      "train_steps_per_second": 0.755
+    }
+  ],
+  "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
+}
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round10.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e13ae3cd894c66790fa0ca0ab617307f10d786ab
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3137dc1711718282da550f4845cd36baab7c46bbf11b76105eef0fead3e874c1
+size 360880622
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round12.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f6a024a75605676d2d53a31918c0598ab68291d3
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:defed3f7caba8d08a8444293265279252bac754f91960c09be90e83e3f42290f
+size 360880622
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round15.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c5a4b34f9532e0b091ad639160f14e609120da97
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10e379d1ddbbac4869c911e4aa2261e7e062f1759e7a20a5e7ffe738d3b4ece2
+size 360880622
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round17.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..08b784797d69ff9eef2755deb95a74f9ad8fd204
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611b55b9aafd1b4e11c27bcf80a22e33756eef1bb1c1de102cf91676dd074463
+size 360880622
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round2.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..dd390d04025d28c5f70bec049e4d29bf5444acb3
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5576200561a80efa43148ce2e7831d31afb0e4696dd074723a8f63eea37962a3
+size 360880106
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round20.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0580d002b11a21b028e2a79dd50f6ad1546388e9
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5b02587ad1dd9f38df651a6f97486fbd2a5654af5e637c8fcaba6350c37ba07
+size 360880622
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round5.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ee259a500592640c6587ec6cde6913decbabc080
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:594714875d0223582d0341af340f41258ef6b01e6633ed2f1b31835f1fbcb28f
+size 360880106
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round7.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d814258fcdfef3ef2b6aefde68259e6e83f7d3de
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9acc6f735922a0d67535d40544015c6d4cd1d2d4a9d1702e6bd5541a29358dce
+size 360880106
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_trainer_state.json b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d5365ec073d2fe1c9cc953f4e62cb8b353fded2
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_trainer_state.json
@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 11.701602935791016,
+      "learning_rate": 2e-05,
+      "loss": 3.2041,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.8877856731414795,
+      "learning_rate": 2e-05,
+      "loss": 0.8482,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.9416866302490234,
+      "learning_rate": 2e-05,
+      "loss": 0.9832,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 8.076401710510254,
+      "learning_rate": 2e-05,
+      "loss": 1.7619,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 9.02495288848877,
+      "learning_rate": 2e-05,
+      "loss": 1.1751,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 6.70341682434082,
+      "learning_rate": 2e-05,
+      "loss": 1.7742,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 9.935924530029297,
+      "learning_rate": 2e-05,
+      "loss": 2.1147,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 6.356525421142578,
+      "learning_rate": 2e-05,
+      "loss": 0.8387,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 4.266024112701416,
+      "learning_rate": 2e-05,
+      "loss": 0.4111,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 9.628840446472168,
+      "learning_rate": 2e-05,
+      "loss": 1.1686,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 6.305365562438965,
+      "learning_rate": 2e-05,
+      "loss": 0.5419,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.4979939460754395,
+      "learning_rate": 2e-05,
+      "loss": 1.4611,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.904814600944519,
+      "learning_rate": 2e-05,
+      "loss": 0.5461,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.557872772216797,
+      "learning_rate": 2e-05,
+      "loss": 0.4092,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.297398567199707,
+      "learning_rate": 2e-05,
+      "loss": 0.5477,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.574881553649902,
+      "learning_rate": 2e-05,
+      "loss": 1.0394,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.348663806915283,
+      "learning_rate": 2e-05,
+      "loss": 2.8679,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 8.440045356750488,
+      "learning_rate": 2e-05,
+      "loss": 2.2365,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 6.058783531188965,
+      "learning_rate": 2e-05,
+      "loss": 0.8523,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.3567728996276855,
+      "learning_rate": 2e-05,
+      "loss": 1.1006,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 15.160209655761719,
+      "learning_rate": 2e-05,
+      "loss": 1.5179,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 10.718804359436035,
+      "learning_rate": 2e-05,
+      "loss": 1.9688,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.9706368446350098,
+      "learning_rate": 2e-05,
+      "loss": 0.554,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.072225093841553,
+      "learning_rate": 2e-05,
+      "loss": 1.1259,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.832661151885986,
+      "learning_rate": 2e-05,
+      "loss": 1.2787,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.9963531494140625,
+      "learning_rate": 2e-05,
+      "loss": 2.5343,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.30591192841529846,
+      "learning_rate": 2e-05,
+      "loss": 0.7795,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.4619483947753906,
+      "learning_rate": 2e-05,
+      "loss": 0.957,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.5531309843063354,
+      "learning_rate": 2e-05,
+      "loss": 0.753,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.0114293098449707,
+      "learning_rate": 2e-05,
+      "loss": 1.3273,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.4710679054260254,
+      "learning_rate": 2e-05,
+      "loss": 0.9157,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.4386227130889893,
+      "learning_rate": 2e-05,
+      "loss": 1.0244,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.135855197906494,
+      "learning_rate": 2e-05,
+      "loss": 0.8826,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.907819986343384,
+      "learning_rate": 2e-05,
+      "loss": 1.173,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.032712459564209,
+      "learning_rate": 2e-05,
+      "loss": 0.9032,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.388005495071411,
+      "learning_rate": 2e-05,
+      "loss": 1.9712,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.9849488735198975,
+      "learning_rate": 2e-05,
+      "loss": 1.2745,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 7.177330493927002,
+      "learning_rate": 2e-05,
+      "loss": 1.5408,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.1500422954559326,
+      "learning_rate": 2e-05,
+      "loss": 0.589,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.8292155265808105,
+      "learning_rate": 2e-05,
+      "loss": 0.8088,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.9888606667518616,
+      "learning_rate": 2e-05,
+      "loss": 0.1827,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 2.494753122329712,
+      "learning_rate": 2e-05,
+      "loss": 1.0098,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.3061927556991577,
+      "learning_rate": 2e-05,
+      "loss": 1.1736,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.5556581020355225,
+      "learning_rate": 2e-05,
+      "loss": 0.6252,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.5772370100021362,
+      "learning_rate": 2e-05,
+      "loss": 0.7691,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.533968448638916,
+      "learning_rate": 2e-05,
+      "loss": 0.5719,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.4935195446014404,
+      "learning_rate": 2e-05,
+      "loss": 0.7637,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.4782304763793945,
+      "learning_rate": 2e-05,
+      "loss": 0.3888,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.847276210784912,
+      "learning_rate": 2e-05,
+      "loss": 1.1708,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.366889715194702,
+      "learning_rate": 2e-05,
+      "loss": 1.3215,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2232466265866240.0,
+      "train_loss": 1.15478422164917,
+      "train_runtime": 72.3437,
+      "train_samples_per_second": 5.529,
+      "train_steps_per_second": 1.382
+    }
+  ],
+  "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": 2232466265866240.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round10.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..430ef2fd9d6d3a5064361937238b67fcbbdf2bec
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93f65beb7bbd25136510c6187fc11e9ca55eaedcabba3b14033692495c02899c
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round12.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2b14628aa3324e6b12bffae404cef73adbac7259
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaeba29721fb62a98ac7f919a031d53e300c961e5a7541ddce722693348166e5
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round15.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f9536816dccfa1cb22a022f2e98a733ad57ba63d
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec7698a9fcb5af2885504255c07c54acce127c28f1a81ddf7f9850673e0719ef
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round17.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6fe215b5ecc9587b200230dc658c37ac59a3367f
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d090f3e1e20b1615cc8945e72b93472544277b7189ef83362446f27ba8a0c30
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round2.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3fb6da24fef2527ef78ad5a4cd39b2e16defbc75
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:591958c16e67ee2f5bf6f1fd0f51c4455c7585e8e45468af114daff5756e3268
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round20.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0015bcca4754f313b1a981d35af34db48734ab2f
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f300b973c4d938700cfca9fae9a52cf471ee38d054e0060f6d88b1dc551cfa20
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round5.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f5e1b6981b1db066bea59153dcbc448e9aff4d90
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db0a6df166d5e9f5df8f18244a5ccc530772bebf1d2da9d366e863e05f2618d
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round7.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0c05fe9bd1aa6a92f62f35c17aaf2425d47a6218
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8104378821d6474f3a6c351716ffb4f1db29be362a71d37564a8be300b60419
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_trainer_state.json b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6b9fa912e89a99d2582bf658f35022f819271a1
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_trainer_state.json
@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.5440601110458374,
+      "learning_rate": 2e-05,
+      "loss": 0.3859,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.486060380935669,
+      "learning_rate": 2e-05,
+      "loss": 0.8744,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.5172414779663086,
+      "learning_rate": 2e-05,
+      "loss": 1.0364,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.87302565574646,
+      "learning_rate": 2e-05,
+      "loss": 0.6833,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.2508922815322876,
+      "learning_rate": 2e-05,
+      "loss": 0.5988,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.049877643585205,
+      "learning_rate": 2e-05,
+      "loss": 0.2546,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.000075101852417,
+      "learning_rate": 2e-05,
+      "loss": 1.0645,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.159180641174316,
+      "learning_rate": 2e-05,
+      "loss": 1.0189,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.9412723779678345,
+      "learning_rate": 2e-05,
+      "loss": 0.5621,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.991361141204834,
+      "learning_rate": 2e-05,
+      "loss": 0.406,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.989998698234558,
+      "learning_rate": 2e-05,
+      "loss": 2.1827,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.5404460430145264,
+      "learning_rate": 2e-05,
+      "loss": 0.9485,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.243625521659851,
+      "learning_rate": 2e-05,
+      "loss": 0.4014,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.017669200897217,
+      "learning_rate": 2e-05,
+      "loss": 1.1306,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.773820638656616,
+      "learning_rate": 2e-05,
+      "loss": 0.9518,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.3499462604522705,
+      "learning_rate": 2e-05,
+      "loss": 0.8406,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.1517057418823242,
+      "learning_rate": 2e-05,
+      "loss": 0.5119,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.779822826385498,
+      "learning_rate": 2e-05,
+      "loss": 1.2535,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.4071242809295654,
+      "learning_rate": 2e-05,
+      "loss": 0.6125,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.478247880935669,
+      "learning_rate": 2e-05,
+      "loss": 1.1099,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.338315725326538,
+      "learning_rate": 2e-05,
+      "loss": 1.0911,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.6824209690093994,
+      "learning_rate": 2e-05,
+      "loss": 0.7209,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.2349324226379395,
+      "learning_rate": 2e-05,
+      "loss": 0.9425,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.572331666946411,
+      "learning_rate": 2e-05,
+      "loss": 0.6688,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.569999933242798,
+      "learning_rate": 2e-05,
+      "loss": 0.6548,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.5937522053718567,
+      "learning_rate": 2e-05,
+      "loss": 1.0816,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.9653764367103577,
+      "learning_rate": 2e-05,
+      "loss": 0.4465,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6579816937446594,
+      "learning_rate": 2e-05,
+      "loss": 0.2058,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.3638180494308472,
+      "learning_rate": 2e-05,
+      "loss": 0.7284,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.4289367198944092,
+      "learning_rate": 2e-05,
+      "loss": 0.8351,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.7946614027023315,
+      "learning_rate": 2e-05,
+      "loss": 0.6298,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.661765694618225,
+      "learning_rate": 2e-05,
+      "loss": 0.8354,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.3677399158477783,
+      "learning_rate": 2e-05,
+      "loss": 1.0779,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.8689314723014832,
+      "learning_rate": 2e-05,
+      "loss": 0.532,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.7545336484909058,
+      "learning_rate": 2e-05,
+      "loss": 0.8644,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.1046079397201538,
+      "learning_rate": 2e-05,
+      "loss": 0.4699,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.21095605194568634,
+      "learning_rate": 2e-05,
+      "loss": 0.593,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.4656115770339966,
+      "learning_rate": 2e-05,
+      "loss": 1.3938,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.224704384803772,
+      "learning_rate": 2e-05,
+      "loss": 0.7324,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.486828088760376,
+      "learning_rate": 2e-05,
+      "loss": 0.5396,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.9084728956222534,
+      "learning_rate": 2e-05,
+      "loss": 0.554,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.9191360473632812,
+      "learning_rate": 2e-05,
+      "loss": 0.6183,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.7869934439659119,
+      "learning_rate": 2e-05,
+      "loss": 0.3396,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.42631539702415466,
+      "learning_rate": 2e-05,
+      "loss": 0.401,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.4716026782989502,
+      "learning_rate": 2e-05,
+      "loss": 0.8724,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.6058681011199951,
+      "learning_rate": 2e-05,
+      "loss": 0.5681,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.3189148902893066,
+      "learning_rate": 2e-05,
+      "loss": 0.7323,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.9830902814865112,
+      "learning_rate": 2e-05,
+      "loss": 0.6886,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.8136429190635681,
+      "learning_rate": 2e-05,
+      "loss": 0.2411,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.1793293952941895,
+      "learning_rate": 2e-05,
+      "loss": 1.0366,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 6021565481222144.0,
+      "train_loss": 0.7584884357452393,
+      "train_runtime": 150.4749,
+      "train_samples_per_second": 2.658,
+      "train_steps_per_second": 0.665
+    }
+  ],
+  "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
+}
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round10.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b071a4ac8295ecb71a2097d792d61a9582e1afaa
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b224a628b3734d5758dbf6796aed6dd04a1b1d0d81b99063131a5f87f032729
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round12.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fb9f8b9ae4118163b075beaa01ce5009a4dac809
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0b171c9c908292b73b092761beef17fde357b8526a9689a4c1a431bef82d5b
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round15.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fe170f73455de51ff04dc72665cffad8bc4a1f9f
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef71ba45a93d892d931909dd81bac80459da02b0bf561f2c594f640c6c01992a
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round17.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..147130c1ea84857559c9663da742fd9ff86d5f0b
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b990fbebb884361e12c185520abbd6ce9ae62e5e4f4903c4863f11b8a265cc
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round2.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e21c9d2022bb48ddf10a5ba443fbcda05890439f
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc9b6db8edd59dbbd02b347056aa744f332dd711a32e98dd04fd3259d4cf4c56
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round20.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..da88ad8d3ca1831bed2deb7e5242b1cb312e02a9
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f05d80db8399a4a1250713230b29541914dcb088b5446d959b93ada40c7d47
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round5.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..693bfec74f0b4d079aa25142760e12c8ed0ed8aa
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060dded9a5d5f758e0194e7fdd9d56e114fd2c4bbbe4727efce45fe2fc10b2f4
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round7.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a30ee215a54ac703ba301124ab3081c79b02dab1
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c9659d713254e2eb528b418d6d8825d8b43b22e80eb87236e5d0837b4de123e
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_trainer_state.json b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..4804f5dcc74c11bf5feb5f4ae7b0f78c4c96f292
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_trainer_state.json
@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.08982393145561218,
+      "learning_rate": 2e-05,
+      "loss": 0.2328,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.3573379516601562,
+      "learning_rate": 2e-05,
+      "loss": 0.4617,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.2133311629295349,
+      "learning_rate": 2e-05,
+      "loss": 0.0153,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.07882347702980042,
+      "learning_rate": 2e-05,
+      "loss": 0.1774,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.0131030082702637,
+      "learning_rate": 2e-05,
+      "loss": 0.2952,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.09988859295845032,
+      "learning_rate": 2e-05,
+      "loss": 0.0046,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.001691152574494481,
+      "learning_rate": 2e-05,
+      "loss": 0.2014,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.6652685403823853,
+      "learning_rate": 2e-05,
+      "loss": 0.0564,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.2490081638097763,
+      "learning_rate": 2e-05,
+      "loss": 0.0634,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.2552433013916016,
+      "learning_rate": 2e-05,
+      "loss": 0.0471,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 9.787774085998535,
+      "learning_rate": 2e-05,
+      "loss": 1.072,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.691402435302734,
+      "learning_rate": 2e-05,
+      "loss": 0.2304,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.8329142332077026,
+      "learning_rate": 2e-05,
+      "loss": 0.9169,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.139729022979736,
+      "learning_rate": 2e-05,
+      "loss": 2.4264,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.07531707733869553,
+      "learning_rate": 2e-05,
+      "loss": 0.1021,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.0397722721099854,
+      "learning_rate": 2e-05,
+      "loss": 0.1805,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.4966022968292236,
+      "learning_rate": 2e-05,
+      "loss": 0.2218,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.2320594787597656,
+      "learning_rate": 2e-05,
+      "loss": 0.1348,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.4888699054718018,
+      "learning_rate": 2e-05,
+      "loss": 0.0962,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 8.161986351013184,
+      "learning_rate": 2e-05,
+      "loss": 0.7422,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.842879593372345,
+      "learning_rate": 2e-05,
+      "loss": 2.4898,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.469893455505371,
+      "learning_rate": 2e-05,
+      "loss": 0.4676,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5714770555496216,
+      "learning_rate": 2e-05,
+      "loss": 0.1859,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.0934393405914307,
+      "learning_rate": 2e-05,
+      "loss": 1.6918,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 7.387649059295654,
+      "learning_rate": 2e-05,
+      "loss": 1.0815,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.6136128902435303,
+      "learning_rate": 2e-05,
+      "loss": 0.7097,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.7184696197509766,
+      "learning_rate": 2e-05,
+      "loss": 0.3055,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.8947840929031372,
+      "learning_rate": 2e-05,
+      "loss": 0.3352,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.6567164063453674,
+      "learning_rate": 2e-05,
+      "loss": 0.148,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.479931116104126,
+      "learning_rate": 2e-05,
+      "loss": 0.1525,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.5562218427658081,
+      "learning_rate": 2e-05,
+      "loss": 0.2389,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.9559447765350342,
+      "learning_rate": 2e-05,
+      "loss": 1.074,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.5000556707382202,
+      "learning_rate": 2e-05,
+      "loss": 0.2175,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.17561589181423187,
+      "learning_rate": 2e-05,
+      "loss": 0.1933,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.763090193271637,
+      "learning_rate": 2e-05,
+      "loss": 0.4763,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.8020315170288086,
+      "learning_rate": 2e-05,
+      "loss": 0.6349,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.07478474080562592,
+      "learning_rate": 2e-05,
+      "loss": 0.3866,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.3866560459136963,
+      "learning_rate": 2e-05,
+      "loss": 0.0755,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.14689640700817108,
+      "learning_rate": 2e-05,
+      "loss": 0.7847,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5186038017272949,
+      "learning_rate": 2e-05,
+      "loss": 0.2711,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.4922601282596588,
+      "learning_rate": 2e-05,
+      "loss": 0.2955,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.14919228851795197,
+      "learning_rate": 2e-05,
+      "loss": 0.2082,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.2567432224750519,
+      "learning_rate": 2e-05,
+      "loss": 0.1574,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.3054035902023315,
+      "learning_rate": 2e-05,
+      "loss": 0.2232,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.16678793728351593,
+      "learning_rate": 2e-05,
+      "loss": 0.0266,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.688411712646484,
+      "learning_rate": 2e-05,
+      "loss": 0.4672,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.2463907152414322,
+      "learning_rate": 2e-05,
+      "loss": 0.0527,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.7890900373458862,
+      "learning_rate": 2e-05,
+      "loss": 0.4185,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.016967343166470528,
+      "learning_rate": 2e-05,
+      "loss": 0.6785,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.782930850982666,
+      "learning_rate": 2e-05,
+      "loss": 1.87,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5262504125005824.0,
+      "train_loss": 0.4799409031867981,
+      "train_runtime": 134.5856,
+      "train_samples_per_second": 2.972,
+      "train_steps_per_second": 0.743
+    }
+  ],
+  "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": 5262504125005824.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round10.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ba4183ca0d1314acaff889cf437c704a8b074452
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cee0252fa5b54de5eb2c1d6f8a7b3abc755b5988c43a1d13d0150df97e88036
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round12.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..db3b85e629fe68142f4b5869341d8f1c0189db24
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf593f0689d0d5485fd1af977e64810da0180283cca8b57148f72cf0386b5d83
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round15.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4e7d57ac608c53614b9ce9038944bc5a5ba4affa
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76578d1ecf85948c56625c4ff0f5fa0134fae9f1d67ed21376e233b75c4bc561
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round17.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ab65314513289c42728ceb464194f244cefa4162
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a949989d5c755f0d240dc138fe0fa17ff9b73b676659b754d4c15d9ecafb0325
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round2.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..07d4743dabc4395661c271dfe94bfd21ef89741c
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e57f3f3e39f073f1cfd1d7a380c51d6201d19fc2b263665c1a53f6d4c6f05362
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round20.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1c3ab5370ccb7274f522bfa47dd6751faba1a626
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d414b7d30f407e459e7c86c1e6ea9783fd6b831937cb4193ab92505225dff56
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round5.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d3daa3c98feec9071c6a570c465b76dbfe50cf7a
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7486c433c80d238bd58ef72b02c7183faef41a3138d3fce6a742c411de5640b0
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round7.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..add151028111d1e6f805e0970a5020ddf1ebd34f
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_client_model_round7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda871767ad67efa14b1a5751adaf2d568f0dd08c4dd1f93683b89fb8a57ee60
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_trainer_state.json b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e61f6e79497414d1538dd42c560312114cb06ae9
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/6_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": 2.5641870498657227,
+      "learning_rate": 2e-05,
+      "loss": 0.9117,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 7.3367838859558105,
+      "learning_rate": 2e-05,
+      "loss": 1.3484,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.435872793197632,
+      "learning_rate": 2e-05,
+      "loss": 1.1888,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.8724123239517212,
+      "learning_rate": 2e-05,
+      "loss": 0.7479,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.045788764953613,
+      "learning_rate": 2e-05,
+      "loss": 1.0021,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.3941988945007324,
+      "learning_rate": 2e-05,
+      "loss": 0.2292,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.4898414611816406,
+      "learning_rate": 2e-05,
+      "loss": 0.6638,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 6.991770267486572,
+      "learning_rate": 2e-05,
+      "loss": 1.9517,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.0541462898254395,
+      "learning_rate": 2e-05,
+      "loss": 1.7256,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.647504448890686,
+      "learning_rate": 2e-05,
+      "loss": 0.8528,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.6307902336120605,
+      "learning_rate": 2e-05,
+      "loss": 0.4915,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.8431178331375122,
+      "learning_rate": 2e-05,
+      "loss": 0.8148,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.761594533920288,
+      "learning_rate": 2e-05,
+      "loss": 0.9241,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.7404680252075195,
+      "learning_rate": 2e-05,
+      "loss": 0.9169,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.715890645980835,
+      "learning_rate": 2e-05,
+      "loss": 1.9023,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.2809853553771973,
+      "learning_rate": 2e-05,
+      "loss": 0.8091,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.321066975593567,
+      "learning_rate": 2e-05,
+      "loss": 0.977,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.0830439329147339,
+      "learning_rate": 2e-05,
+      "loss": 0.8662,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.58846378326416,
+      "learning_rate": 2e-05,
+      "loss": 0.825,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.2277541160583496,
+      "learning_rate": 2e-05,
+      "loss": 0.814,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.486735224723816,
+      "learning_rate": 2e-05,
+      "loss": 1.0742,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.8081094026565552,
+      "learning_rate": 2e-05,
+      "loss": 0.8131,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.604997158050537,
+      "learning_rate": 2e-05,
+      "loss": 0.5868,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.016016483306885,
+      "learning_rate": 2e-05,
+      "loss": 0.8185,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.8881778717041016,
+      "learning_rate": 2e-05,
+      "loss": 0.7617,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.8280321359634399,
+      "learning_rate": 2e-05,
+      "loss": 0.6892,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.1922149658203125,
+      "learning_rate": 2e-05,
+      "loss": 0.7572,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.8428804874420166,
+      "learning_rate": 2e-05,
+      "loss": 1.4743,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.307338237762451,
+      "learning_rate": 2e-05,
+      "loss": 1.0949,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.005655288696289,
+      "learning_rate": 2e-05,
+      "loss": 1.1342,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 6.022993087768555,
+      "learning_rate": 2e-05,
+      "loss": 1.4705,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.2536320686340332,
+      "learning_rate": 2e-05,
+      "loss": 1.0303,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.0175987482070923,
+      "learning_rate": 2e-05,
+      "loss": 1.0798,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.417553663253784,
+      "learning_rate": 2e-05,
+      "loss": 0.9361,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.2720513343811035,
+      "learning_rate": 2e-05,
+      "loss": 1.0747,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.8921431303024292,
+      "learning_rate": 2e-05,
+      "loss": 0.9569,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.949774980545044,
+      "learning_rate": 2e-05,
+      "loss": 1.2076,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.8719704151153564,
+      "learning_rate": 2e-05,
+      "loss": 1.0281,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.7995576858520508,
+      "learning_rate": 2e-05,
+      "loss": 0.6605,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.1909035444259644,
+      "learning_rate": 2e-05,
+      "loss": 0.4333,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.7953910827636719,
+      "learning_rate": 2e-05,
+      "loss": 0.9653,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.8923394680023193,
+      "learning_rate": 2e-05,
+      "loss": 1.1519,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.6500399708747864,
+      "learning_rate": 2e-05,
+      "loss": 0.5326,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.9078047871589661,
+      "learning_rate": 2e-05,
+      "loss": 0.8246,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.2340238094329834,
+      "learning_rate": 2e-05,
+      "loss": 0.6124,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.590685248374939,
+      "learning_rate": 2e-05,
+      "loss": 2.2126,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.4105197191238403,
+      "learning_rate": 2e-05,
+      "loss": 0.6126,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.10088849067688,
+      "learning_rate": 2e-05,
+      "loss": 0.8313,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.816298484802246,
+      "learning_rate": 2e-05,
+      "loss": 1.2018,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.9328625202178955,
+      "learning_rate": 2e-05,
+      "loss": 1.8354,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.0412693227831296e+16,
+      "train_loss": 0.9965047836303711,
+      "train_runtime": 220.6689,
+      "train_samples_per_second": 1.813,
+      "train_steps_per_second": 0.453
+    }
+  ],
+  "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": 1.0412693227831296e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round10.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9362121da36f81d9de2297c75119a157d83a6b45
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b335ba8a2e7688024dbd46c0b9bb397a073e9c2eb15b3eb037a32a5eadb6012
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round12.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0a7b169656a5a8825222692fd81be97ec8436f40
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97039c2ea390dcfa4b5c7659468bf70c47c724e3be1dee504fbc4df47e322be7
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round15.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ab3fb26fcca44884542efc2bf649ad271eeaacc9
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5808e6333c7cb64a69cb68140934cdb9c06a177e4ca83c5b0bcb147a35cd1b2
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round17.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ee8a5904991e67f1472c32c4ba02eaf1027a8542
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ecb2e96850cf95fabea258a9ccf5d0172b1a5f3434e744468797c3f660df82
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round2.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0deaad3f1487819ee5d065eaa05944d76fee68bf
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac25f56656ebfa3c517af704dcd053fe6b48701852765108715bd1a7225ff1f
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round20.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b321fb121eab3e47500d1b800184da203fbc1f1c
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ba00a41f1fae5d48885f1556bdbbd47f8f0b8a1b9c6a35047841dfb02a2bcf
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round5.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ee9b3fb5f6679684f25a613a2615a02d15c37ede
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c58b1a0f41a7fe55b7e85f29e34c7970de01825e2ab0df0d8ccd007d49de4a
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round7.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..74b8c7959825c56c54f32dfdccc4e2b55c470733
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_client_model_round7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d884a664313d36bec7bd03e21ccec80dacded9eea3aa9cbd328cf30bc4ec70a
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_trainer_state.json b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..92358007ad7269b78586babfa47b2924106a00ad
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/7_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": 2.9860033988952637,
+      "learning_rate": 2e-05,
+      "loss": 0.327,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.423563003540039,
+      "learning_rate": 2e-05,
+      "loss": 1.0884,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.9696483612060547,
+      "learning_rate": 2e-05,
+      "loss": 0.2785,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.6474837064743042,
+      "learning_rate": 2e-05,
+      "loss": 0.6156,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.743607997894287,
+      "learning_rate": 2e-05,
+      "loss": 0.9266,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.090904474258423,
+      "learning_rate": 2e-05,
+      "loss": 0.6268,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.2828066051006317,
+      "learning_rate": 2e-05,
+      "loss": 0.1825,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.0163958072662354,
+      "learning_rate": 2e-05,
+      "loss": 0.8978,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 4.475520610809326,
+      "learning_rate": 2e-05,
+      "loss": 0.5604,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 6.505922317504883,
+      "learning_rate": 2e-05,
+      "loss": 0.7148,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.19619496166706085,
+      "learning_rate": 2e-05,
+      "loss": 0.6846,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.3026323318481445,
+      "learning_rate": 2e-05,
+      "loss": 0.9959,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.5132761001586914,
+      "learning_rate": 2e-05,
+      "loss": 0.1066,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.5363874435424805,
+      "learning_rate": 2e-05,
+      "loss": 0.807,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.0056349039077759,
+      "learning_rate": 2e-05,
+      "loss": 1.1092,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.985927700996399,
+      "learning_rate": 2e-05,
+      "loss": 0.7923,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.3938846588134766,
+      "learning_rate": 2e-05,
+      "loss": 0.1412,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.9086544513702393,
+      "learning_rate": 2e-05,
+      "loss": 0.5865,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.148262619972229,
+      "learning_rate": 2e-05,
+      "loss": 0.1361,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 8.180176734924316,
+      "learning_rate": 2e-05,
+      "loss": 1.714,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.437209963798523,
+      "learning_rate": 2e-05,
+      "loss": 1.8034,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.6405125856399536,
+      "learning_rate": 2e-05,
+      "loss": 0.1931,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.302958011627197,
+      "learning_rate": 2e-05,
+      "loss": 1.1724,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.3256847858428955,
+      "learning_rate": 2e-05,
+      "loss": 0.1326,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.8101141452789307,
+      "learning_rate": 2e-05,
+      "loss": 1.3805,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.6622437238693237,
+      "learning_rate": 2e-05,
+      "loss": 0.4884,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.12145165354013443,
+      "learning_rate": 2e-05,
+      "loss": 0.7347,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6513306498527527,
+      "learning_rate": 2e-05,
+      "loss": 0.1554,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.1421395093202591,
+      "learning_rate": 2e-05,
+      "loss": 0.1763,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.034487247467041,
+      "learning_rate": 2e-05,
+      "loss": 2.4693,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.23729735612869263,
+      "learning_rate": 2e-05,
+      "loss": 0.062,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.698179244995117,
+      "learning_rate": 2e-05,
+      "loss": 1.453,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.8955222368240356,
+      "learning_rate": 2e-05,
+      "loss": 0.3351,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.7866859436035156,
+      "learning_rate": 2e-05,
+      "loss": 0.3985,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.4781858921051025,
+      "learning_rate": 2e-05,
+      "loss": 0.9798,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.6539032459259033,
+      "learning_rate": 2e-05,
+      "loss": 0.8767,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.6716035604476929,
+      "learning_rate": 2e-05,
+      "loss": 0.7938,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.32660794258117676,
+      "learning_rate": 2e-05,
+      "loss": 0.8565,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.9017077684402466,
+      "learning_rate": 2e-05,
+      "loss": 0.797,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.2260944843292236,
+      "learning_rate": 2e-05,
+      "loss": 1.521,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.2876487970352173,
+      "learning_rate": 2e-05,
+      "loss": 0.3754,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.8568190932273865,
+      "learning_rate": 2e-05,
+      "loss": 0.2203,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.4791165590286255,
+      "learning_rate": 2e-05,
+      "loss": 1.2707,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.127885580062866,
+      "learning_rate": 2e-05,
+      "loss": 0.9114,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.0902236700057983,
+      "learning_rate": 2e-05,
+      "loss": 0.8005,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.36327800154685974,
+      "learning_rate": 2e-05,
+      "loss": 0.3284,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.36818528175354,
+      "learning_rate": 2e-05,
+      "loss": 0.5004,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.21333810687065125,
+      "learning_rate": 2e-05,
+      "loss": 0.2709,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.2604660987854004,
+      "learning_rate": 2e-05,
+      "loss": 0.6217,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3066768646240234,
+      "learning_rate": 2e-05,
+      "loss": 0.303,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5454346405806080.0,
+      "train_loss": 0.7134788227081299,
+      "train_runtime": 143.6135,
+      "train_samples_per_second": 2.785,
+      "train_steps_per_second": 0.696
+    }
+  ],
+  "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": 5454346405806080.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round10.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..72742766fcb3f7662888d9fbc0c809811bb48b5a
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eacdfcf71ea44194eb00074114f9870b6c89e10c75fa118f8f2e35bb954e2e8c
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round12.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..23e849c5ede2a590cdce41feb0451cd1212208bf
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2c88652e70a9afad16f1e9a4842a0a788962ded189adf89069ed48d4274712
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round15.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7bcb58bcc7e8465354ee841b745a4eb089c96183
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf37397eeed92207cdc3dd96f6455cee565379adee808c6dcfc3870363148c3
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round17.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round17.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f9d39d4862ac8f67d805c9f62fa2c165ae76b1b1
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round17.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21f4f7d3169b7ad60543e51d04f200e4012a154a36a8e18b43090df79b7a64ab
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round2.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..da25958d5101e8dbcf3bab8c3d8a4ce663e4b9a9
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725ac25187616e9b47ce5d9f7877fa6b581bfaafdd0d471b071f933c91ad6b08
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round20.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round20.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5dd34b5a7c66f107b52e57136bb0b0be45291cbf
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round20.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3fa309d01a45805f581f1d0bd78476a5041d3c83fe80bc72b0654546f91bb30
+size 778341886
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round5.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..63998e189c5781b1549c2b8c81274a58b489c505
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed907485521355ca45ed255c1d6c05aa22c758a43bf209b80644008c3ade42f
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round7.pth b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f1c0655efdabe8a249ff8cd4bf9cae900c51b5b8
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_client_model_round7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1904df9c957424455733e844735fa2e920280491f7fa504464cf22cad86e40b
+size 778341034
diff --git a/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_trainer_state.json b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..9b71cf81839a804c2cd5c1f7f5c9d401662bbf9a
--- /dev/null
+++ b/client_states_feddpa_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/8_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": 0.3082524240016937,
+      "learning_rate": 2e-05,
+      "loss": 0.6482,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.20196011662483215,
+      "learning_rate": 2e-05,
+      "loss": 0.3392,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.12239228934049606,
+      "learning_rate": 2e-05,
+      "loss": 0.1658,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.2035088539123535,
+      "learning_rate": 2e-05,
+      "loss": 0.0952,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.1327526867389679,
+      "learning_rate": 2e-05,
+      "loss": 0.0091,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.7317419052124023,
+      "learning_rate": 2e-05,
+      "loss": 0.4195,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.08746431022882462,
+      "learning_rate": 2e-05,
+      "loss": 0.7528,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.947171211242676,
+      "learning_rate": 2e-05,
+      "loss": 0.6166,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.436347246170044,
+      "learning_rate": 2e-05,
+      "loss": 0.4109,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.7922656536102295,
+      "learning_rate": 2e-05,
+      "loss": 5.073,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 6.673124313354492,
+      "learning_rate": 2e-05,
+      "loss": 2.471,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.4746553897857666,
+      "learning_rate": 2e-05,
+      "loss": 0.3446,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.6311354637146,
+      "learning_rate": 2e-05,
+      "loss": 0.8753,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 6.73305606842041,
+      "learning_rate": 2e-05,
+      "loss": 0.9431,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.6246132850646973,
+      "learning_rate": 2e-05,
+      "loss": 0.0616,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.1175317764282227,
+      "learning_rate": 2e-05,
+      "loss": 0.1549,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.971907377243042,
+      "learning_rate": 2e-05,
+      "loss": 2.1001,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.170811176300049,
+      "learning_rate": 2e-05,
+      "loss": 1.278,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.33163595199585,
+      "learning_rate": 2e-05,
+      "loss": 1.2597,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.0930659770965576,
+      "learning_rate": 2e-05,
+      "loss": 0.3472,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.445111274719238,
+      "learning_rate": 2e-05,
+      "loss": 0.8923,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.008833651430904865,
+      "learning_rate": 2e-05,
+      "loss": 0.282,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.986541509628296,
+      "learning_rate": 2e-05,
+      "loss": 0.7108,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.189093589782715,
+      "learning_rate": 2e-05,
+      "loss": 1.1752,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.4901527762413025,
+      "learning_rate": 2e-05,
+      "loss": 0.4185,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.2659938633441925,
+      "learning_rate": 2e-05,
+      "loss": 0.3296,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.550976037979126,
+      "learning_rate": 2e-05,
+      "loss": 0.4602,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.26266545057296753,
+      "learning_rate": 2e-05,
+      "loss": 0.477,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.0469081401824951,
+      "learning_rate": 2e-05,
+      "loss": 0.2115,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.0375242605805397,
+      "learning_rate": 2e-05,
+      "loss": 0.0109,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.9784115552902222,
+      "learning_rate": 2e-05,
+      "loss": 0.508,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.2599825859069824,
+      "learning_rate": 2e-05,
+      "loss": 1.3798,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.2077398300170898,
+      "learning_rate": 2e-05,
+      "loss": 0.1684,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5861782431602478,
+      "learning_rate": 2e-05,
+      "loss": 0.0761,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.10536394268274307,
+      "learning_rate": 2e-05,
+      "loss": 0.0163,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.3317738771438599,
+      "learning_rate": 2e-05,
+      "loss": 0.2937,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.141127109527588,
+      "learning_rate": 2e-05,
+      "loss": 0.1432,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.5267685055732727,
+      "learning_rate": 2e-05,
+      "loss": 0.1033,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.5539693236351013,
+      "learning_rate": 2e-05,
+      "loss": 0.2652,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.15677958726882935,
+      "learning_rate": 2e-05,
+      "loss": 0.0412,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.541965961456299,
+      "learning_rate": 2e-05,
+      "loss": 0.9765,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.20113620162010193,
+      "learning_rate": 2e-05,
+      "loss": 0.042,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.1557822972536087,
+      "learning_rate": 2e-05,
+      "loss": 0.0232,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.5913605690002441,
+      "learning_rate": 2e-05,
+      "loss": 0.1017,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.2243813276290894,
+      "learning_rate": 2e-05,
+      "loss": 0.5208,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 5.133846282958984,
+      "learning_rate": 2e-05,
+      "loss": 1.4791,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.5330513119697571,
+      "learning_rate": 2e-05,
+      "loss": 0.0408,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.9799649715423584,
+      "learning_rate": 2e-05,
+      "loss": 1.0588,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.08848804980516434,
+      "learning_rate": 2e-05,
+      "loss": 0.0274,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0476655960083008,
+      "learning_rate": 2e-05,
+      "loss": 0.1449,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5308334865383424.0,
+      "train_loss": 0.6148797327280044,
+      "train_runtime": 134.9522,
+      "train_samples_per_second": 2.964,
+      "train_steps_per_second": 0.741
+    }
+  ],
+  "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": 5308334865383424.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}