Upload folder using huggingface_hub

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7546fc4f1e9ad7913732bbac8f36c358f4bc57b5ccdd0209ecb823e88eef64ae
+size 360880622

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b3692bc1eaca37a4b7c56ad571b626ce99dbfe4464f973b73e1513df2d17fd2
+size 360880622

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c1afc9e7075b2f6e9345942d3f664b6785d1646b84fbadbc41e1ea445fb7f9
+size 360880622

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787291ff7f546a56bf69b79282d993192f739b755f27bc1a6a0b48d0b0941ff5
+size 360880622

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc050a3945b1411266694eab273360b72f13c1563b4bd1d1bd460179bf50f9ab
+size 360880106

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0988ed7f186292c41f64edf248ae75f7d65914c3a963891ff2f457a923988df5
+size 360880622

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b77dabf5d164dfd38481a3c55ac86c2388ceccec9c81758ed8e83a498db17fe
+size 360880106

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7baca178c3bce56809cd463fd1534af32f44e08d517f585843e4b95ea578b340
+size 360880106

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_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": 3.168569326400757,
+      "learning_rate": 2e-05,
+      "loss": 0.6893,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.9174137115478516,
+      "learning_rate": 2e-05,
+      "loss": 0.4755,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.3625084161758423,
+      "learning_rate": 2e-05,
+      "loss": 0.0357,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.177082538604736,
+      "learning_rate": 2e-05,
+      "loss": 0.5867,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 6.442203998565674,
+      "learning_rate": 2e-05,
+      "loss": 0.9335,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 8.964068412780762,
+      "learning_rate": 2e-05,
+      "loss": 1.1723,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.881713390350342,
+      "learning_rate": 2e-05,
+      "loss": 0.1933,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.157293319702148,
+      "learning_rate": 2e-05,
+      "loss": 0.3247,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 7.916150093078613,
+      "learning_rate": 2e-05,
+      "loss": 1.1029,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.8996070623397827,
+      "learning_rate": 2e-05,
+      "loss": 0.1545,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 7.651811599731445,
+      "learning_rate": 2e-05,
+      "loss": 1.4526,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 9.129485130310059,
+      "learning_rate": 2e-05,
+      "loss": 1.4704,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.2082066684961319,
+      "learning_rate": 2e-05,
+      "loss": 0.1436,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 13.400495529174805,
+      "learning_rate": 2e-05,
+      "loss": 1.1374,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.703688621520996,
+      "learning_rate": 2e-05,
+      "loss": 1.4414,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 10.852417945861816,
+      "learning_rate": 2e-05,
+      "loss": 1.195,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.962532639503479,
+      "learning_rate": 2e-05,
+      "loss": 0.3736,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 4.2005534172058105,
+      "learning_rate": 2e-05,
+      "loss": 0.6136,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.7884447574615479,
+      "learning_rate": 2e-05,
+      "loss": 0.1229,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 9.23675537109375,
+      "learning_rate": 2e-05,
+      "loss": 0.893,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.7615028023719788,
+      "learning_rate": 2e-05,
+      "loss": 0.6928,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.6696066856384277,
+      "learning_rate": 2e-05,
+      "loss": 0.7411,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.5730092525482178,
+      "learning_rate": 2e-05,
+      "loss": 1.2715,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 9.454010963439941,
+      "learning_rate": 2e-05,
+      "loss": 0.5399,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 8.564720153808594,
+      "learning_rate": 2e-05,
+      "loss": 1.5553,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.2727251052856445,
+      "learning_rate": 2e-05,
+      "loss": 1.3705,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.7668354511260986,
+      "learning_rate": 2e-05,
+      "loss": 0.5318,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.1835460215806961,
+      "learning_rate": 2e-05,
+      "loss": 0.6833,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.27826184034347534,
+      "learning_rate": 2e-05,
+      "loss": 0.8111,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 7.857359409332275,
+      "learning_rate": 2e-05,
+      "loss": 1.3904,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.6023170948028564,
+      "learning_rate": 2e-05,
+      "loss": 0.8659,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 5.245106220245361,
+      "learning_rate": 2e-05,
+      "loss": 1.4542,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.9230977296829224,
+      "learning_rate": 2e-05,
+      "loss": 1.0524,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.41410088539123535,
+      "learning_rate": 2e-05,
+      "loss": 0.5411,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.13429969549179077,
+      "learning_rate": 2e-05,
+      "loss": 0.0238,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.6073343753814697,
+      "learning_rate": 2e-05,
+      "loss": 0.3158,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.4870729446411133,
+      "learning_rate": 2e-05,
+      "loss": 0.8523,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.3943371772766113,
+      "learning_rate": 2e-05,
+      "loss": 1.0344,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.19015595316886902,
+      "learning_rate": 2e-05,
+      "loss": 0.023,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.408768177032471,
+      "learning_rate": 2e-05,
+      "loss": 0.5619,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 6.211584091186523,
+      "learning_rate": 2e-05,
+      "loss": 0.9297,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.473548412322998,
+      "learning_rate": 2e-05,
+      "loss": 1.1034,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.3540263175964355,
+      "learning_rate": 2e-05,
+      "loss": 0.496,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.8121440410614014,
+      "learning_rate": 2e-05,
+      "loss": 0.4946,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.1282097101211548,
+      "learning_rate": 2e-05,
+      "loss": 0.2981,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.8578763008117676,
+      "learning_rate": 2e-05,
+      "loss": 0.4562,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.614463448524475,
+      "learning_rate": 2e-05,
+      "loss": 0.2898,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.689039945602417,
+      "learning_rate": 2e-05,
+      "loss": 0.8306,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.5519903302192688,
+      "learning_rate": 2e-05,
+      "loss": 0.0559,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6827519536018372,
+      "learning_rate": 2e-05,
+      "loss": 0.0948,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2184696968511488.0,
+      "train_loss": 0.7174666833877563,
+      "train_runtime": 198.3012,
+      "train_samples_per_second": 2.017,
+      "train_steps_per_second": 0.504
+    }
+  ],
+  "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": 2184696968511488.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce55dbea5aa307d12bc0ced5f84983ab08f2091a8e4a95c18c96566f2681d36
+size 360880622

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aa6cd98747c2bf91d55f47f977ae06f1832f852937acdc43d3b2bb0390d4bb6
+size 360880622

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56534b902dca2ae72d612a20b66fe3fc996f3b21bf3a2b7e2cf16c0ef5fa6537
+size 360880622

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9d53e9fa92e5fc2d83fb7d73d7ba33279e12c729ba964b17912ea3e2c567f76
+size 360880622

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dcbed81728b3d67b5f92eb4ffec08ffb4e53127144e3c0b24f65d63d0f34147
+size 360880106

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f085a0f44e5da2f242213a1be131073b88f17a8d701d31172bc98fb9f43feb34
+size 360880622

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5414bbef48473343b0b7dc228ff982948ec87c9b6874c98bb5076280d965c91
+size 360880106

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16332d8c4686b4e074d4d7e096cea27434416ae0fa043785a01d0ae448848bdd
+size 360880106

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_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": 0.011207446455955505,
+      "learning_rate": 2e-05,
+      "loss": 0.0135,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.01147475466132164,
+      "learning_rate": 2e-05,
+      "loss": 0.0012,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.596205234527588,
+      "learning_rate": 2e-05,
+      "loss": 0.0964,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.28634506464004517,
+      "learning_rate": 2e-05,
+      "loss": 0.0108,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.7038493156433105,
+      "learning_rate": 2e-05,
+      "loss": 0.2892,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.002277372870594263,
+      "learning_rate": 2e-05,
+      "loss": 0.0007,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.0801393911242485,
+      "learning_rate": 2e-05,
+      "loss": 0.007,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.04304589703679085,
+      "learning_rate": 2e-05,
+      "loss": 0.0017,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.005371824372559786,
+      "learning_rate": 2e-05,
+      "loss": 0.0005,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.11802884191274643,
+      "learning_rate": 2e-05,
+      "loss": 0.0246,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.014701750129461288,
+      "learning_rate": 2e-05,
+      "loss": 0.0012,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.13001033663749695,
+      "learning_rate": 2e-05,
+      "loss": 0.011,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.0053694406524300575,
+      "learning_rate": 2e-05,
+      "loss": 0.0058,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.5377350449562073,
+      "learning_rate": 2e-05,
+      "loss": 0.6586,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.02019331231713295,
+      "learning_rate": 2e-05,
+      "loss": 0.6455,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.21001771092414856,
+      "learning_rate": 2e-05,
+      "loss": 0.0102,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.13548670709133148,
+      "learning_rate": 2e-05,
+      "loss": 0.1406,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.00781962275505066,
+      "learning_rate": 2e-05,
+      "loss": 0.0013,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.014647940173745155,
+      "learning_rate": 2e-05,
+      "loss": 0.0238,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.040587376803159714,
+      "learning_rate": 2e-05,
+      "loss": 0.0017,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.31018340587615967,
+      "learning_rate": 2e-05,
+      "loss": 0.0183,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.004495964851230383,
+      "learning_rate": 2e-05,
+      "loss": 0.0007,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.08285064995288849,
+      "learning_rate": 2e-05,
+      "loss": 0.0158,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 7.0068359375,
+      "learning_rate": 2e-05,
+      "loss": 0.4812,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.09830096364021301,
+      "learning_rate": 2e-05,
+      "loss": 0.0039,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.00431413296610117,
+      "learning_rate": 2e-05,
+      "loss": 0.5317,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.007897529751062393,
+      "learning_rate": 2e-05,
+      "loss": 0.0081,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.26051226258277893,
+      "learning_rate": 2e-05,
+      "loss": 0.1901,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.009529797360301018,
+      "learning_rate": 2e-05,
+      "loss": 0.0034,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.679503440856934,
+      "learning_rate": 2e-05,
+      "loss": 0.9803,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.01950022205710411,
+      "learning_rate": 2e-05,
+      "loss": 0.0021,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.010863760486245155,
+      "learning_rate": 2e-05,
+      "loss": 0.0022,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.3716355562210083,
+      "learning_rate": 2e-05,
+      "loss": 0.1011,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 6.969474792480469,
+      "learning_rate": 2e-05,
+      "loss": 1.1201,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.01342960074543953,
+      "learning_rate": 2e-05,
+      "loss": 0.0042,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.062052078545093536,
+      "learning_rate": 2e-05,
+      "loss": 0.1595,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.0028084074147045612,
+      "learning_rate": 2e-05,
+      "loss": 0.0052,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.4721274375915527,
+      "learning_rate": 2e-05,
+      "loss": 0.7356,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.002178875496610999,
+      "learning_rate": 2e-05,
+      "loss": 0.0008,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.003153095953166485,
+      "learning_rate": 2e-05,
+      "loss": 0.1196,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.0015531632816419005,
+      "learning_rate": 2e-05,
+      "loss": 0.0017,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.7809462547302246,
+      "learning_rate": 2e-05,
+      "loss": 0.7962,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.1522572785615921,
+      "learning_rate": 2e-05,
+      "loss": 0.0142,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.4365298748016357,
+      "learning_rate": 2e-05,
+      "loss": 0.2214,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.8702583909034729,
+      "learning_rate": 2e-05,
+      "loss": 0.6717,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.10574907809495926,
+      "learning_rate": 2e-05,
+      "loss": 0.0158,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.007073584012687206,
+      "learning_rate": 2e-05,
+      "loss": 0.0117,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.09635786712169647,
+      "learning_rate": 2e-05,
+      "loss": 0.0842,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.025972407311201096,
+      "learning_rate": 2e-05,
+      "loss": 0.0032,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.03356132283806801,
+      "learning_rate": 2e-05,
+      "loss": 0.0614,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2202117888540672.0,
+      "train_loss": 0.16621231228113176,
+      "train_runtime": 195.4115,
+      "train_samples_per_second": 2.047,
+      "train_steps_per_second": 0.512
+    }
+  ],
+  "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": 2202117888540672.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad05e513dda4c8e022e1374f0407dd6d6443ea4647952b939b957e33f12d09c
+size 778341886

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df19f77ccd84778e59287d2f0a4e1c1eb74022985104e195fe5a6d1704457dbe
+size 778341886

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bd2174d078d759747b45f2f37e746dae6521de9cde14ad9c976110ca4994bef
+size 778341886

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b9f0f37f4f725020bbba93c6b90f20d9c785c8b01a7da526723ff8e43569fa9
+size 778341886

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84fd56d36d8f689a4441e37fcabbaa3c2485f2c503e6f7cea4259c2a7b5b1708
+size 778341034

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd493958f623644eb6e10987b5df70e4fd8277697a8988403b8433063ac386e
+size 778341886

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc49b586c01ccc573f1dbf3e8a17cb4666d8de29ec9d16786f9e46c0903ba214
+size 778341034

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e658c5d70604d6e93790515311d4a64591fd81159d7ff50feb44c274026150e
+size 778341034

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_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": 0.5404447317123413,
+      "learning_rate": 2e-05,
+      "loss": 0.2464,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.234242916107178,
+      "learning_rate": 2e-05,
+      "loss": 0.8502,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.310257911682129,
+      "learning_rate": 2e-05,
+      "loss": 1.9313,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.2035372257232666,
+      "learning_rate": 2e-05,
+      "loss": 0.2283,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.818188428878784,
+      "learning_rate": 2e-05,
+      "loss": 0.7593,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.656116247177124,
+      "learning_rate": 2e-05,
+      "loss": 0.5119,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.843384027481079,
+      "learning_rate": 2e-05,
+      "loss": 0.4628,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.174237012863159,
+      "learning_rate": 2e-05,
+      "loss": 0.3806,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.7489578127861023,
+      "learning_rate": 2e-05,
+      "loss": 0.518,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.409237861633301,
+      "learning_rate": 2e-05,
+      "loss": 0.2752,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.8066983222961426,
+      "learning_rate": 2e-05,
+      "loss": 0.4498,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 9.522912979125977,
+      "learning_rate": 2e-05,
+      "loss": 1.5513,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.8413701057434082,
+      "learning_rate": 2e-05,
+      "loss": 0.1162,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.7504090666770935,
+      "learning_rate": 2e-05,
+      "loss": 0.2894,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.5619468688964844,
+      "learning_rate": 2e-05,
+      "loss": 0.2309,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.712264060974121,
+      "learning_rate": 2e-05,
+      "loss": 1.0148,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.8456515073776245,
+      "learning_rate": 2e-05,
+      "loss": 1.2941,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.6516411304473877,
+      "learning_rate": 2e-05,
+      "loss": 0.3304,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.230163097381592,
+      "learning_rate": 2e-05,
+      "loss": 0.6982,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.8181395530700684,
+      "learning_rate": 2e-05,
+      "loss": 0.5174,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.769617080688477,
+      "learning_rate": 2e-05,
+      "loss": 1.7706,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.622427940368652,
+      "learning_rate": 2e-05,
+      "loss": 1.1796,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 6.225355625152588,
+      "learning_rate": 2e-05,
+      "loss": 3.0296,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.1429452896118164,
+      "learning_rate": 2e-05,
+      "loss": 0.6984,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7007458209991455,
+      "learning_rate": 2e-05,
+      "loss": 1.251,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.2813233137130737,
+      "learning_rate": 2e-05,
+      "loss": 0.6892,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.1559221744537354,
+      "learning_rate": 2e-05,
+      "loss": 0.5884,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.0968915224075317,
+      "learning_rate": 2e-05,
+      "loss": 0.8697,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.7630658149719238,
+      "learning_rate": 2e-05,
+      "loss": 0.2812,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.268714427947998,
+      "learning_rate": 2e-05,
+      "loss": 0.7784,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.6064919829368591,
+      "learning_rate": 2e-05,
+      "loss": 0.2061,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.786159336566925,
+      "learning_rate": 2e-05,
+      "loss": 0.7694,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.6141662001609802,
+      "learning_rate": 2e-05,
+      "loss": 0.9531,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.2273752689361572,
+      "learning_rate": 2e-05,
+      "loss": 0.3643,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.34563758969306946,
+      "learning_rate": 2e-05,
+      "loss": 1.2121,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.1070133447647095,
+      "learning_rate": 2e-05,
+      "loss": 0.3763,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.701382875442505,
+      "learning_rate": 2e-05,
+      "loss": 1.6308,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.2998264729976654,
+      "learning_rate": 2e-05,
+      "loss": 0.1903,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8566079139709473,
+      "learning_rate": 2e-05,
+      "loss": 1.3346,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.1532411575317383,
+      "learning_rate": 2e-05,
+      "loss": 0.8968,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.2786032557487488,
+      "learning_rate": 2e-05,
+      "loss": 0.7812,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.8800046443939209,
+      "learning_rate": 2e-05,
+      "loss": 0.5602,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.8316788077354431,
+      "learning_rate": 2e-05,
+      "loss": 0.328,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.9697389006614685,
+      "learning_rate": 2e-05,
+      "loss": 0.3522,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.05534057691693306,
+      "learning_rate": 2e-05,
+      "loss": 0.1543,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.3023179769515991,
+      "learning_rate": 2e-05,
+      "loss": 0.3407,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.4678339958190918,
+      "learning_rate": 2e-05,
+      "loss": 1.1556,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.5633058547973633,
+      "learning_rate": 2e-05,
+      "loss": 0.481,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.2930028736591339,
+      "learning_rate": 2e-05,
+      "loss": 0.224,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.328813076019287,
+      "learning_rate": 2e-05,
+      "loss": 1.4674,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5198007012163584.0,
+      "train_loss": 0.7514226150512695,
+      "train_runtime": 325.028,
+      "train_samples_per_second": 1.231,
+      "train_steps_per_second": 0.308
+    }
+  ],
+  "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": 5198007012163584.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9e4d3519e47481fe5f1a17aa5c590c46a4e41cea6c0863d623c7142eef2962
+size 360880622

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0cc3078c10ceb9c3f2d77b51f34bc74ea4a48e98ac2ad25eba81e9cc1814268
+size 360880622

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c0f9ad3aacb0387511bf31cdd66785140ab8067f2f47e562cd323ab4305672
+size 360880622

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be47670175f5ed9c8d6b67a807aa6f31c5df67ec86eac2dcfc6b4157285d77d6
+size 360880622

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf22a626e9612d791d2634d516356546a5c86b15a85e4c0be40edaed7ce3412
+size 360880106

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9ffe60cde3a8f5e874bba3c2d480c89150f973d3cef46ab1dc1aa6ed8ed61b0
+size 360880622

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd01ed462ed040c9bae208b7d149fec5676a85c6bcd1e82c6387670f9442345a
+size 360880106

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d9b0bcd874b41c488a2a2313c0834141e9103fce99018e40601e7e006e618bc
+size 360880106

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/3_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.651209354400635,
+      "learning_rate": 2e-05,
+      "loss": 1.5799,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.4673378467559814,
+      "learning_rate": 2e-05,
+      "loss": 1.2502,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 8.588323593139648,
+      "learning_rate": 2e-05,
+      "loss": 1.2586,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 14.28863525390625,
+      "learning_rate": 2e-05,
+      "loss": 5.0681,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 12.881756782531738,
+      "learning_rate": 2e-05,
+      "loss": 3.1508,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 8.44861888885498,
+      "learning_rate": 2e-05,
+      "loss": 0.9047,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 11.289327621459961,
+      "learning_rate": 2e-05,
+      "loss": 2.482,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.8942275047302246,
+      "learning_rate": 2e-05,
+      "loss": 0.694,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.9555184841156006,
+      "learning_rate": 2e-05,
+      "loss": 1.0708,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.645041465759277,
+      "learning_rate": 2e-05,
+      "loss": 1.9126,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.385215997695923,
+      "learning_rate": 2e-05,
+      "loss": 1.2057,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 11.083643913269043,
+      "learning_rate": 2e-05,
+      "loss": 1.4454,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 5.367053508758545,
+      "learning_rate": 2e-05,
+      "loss": 1.483,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.883023262023926,
+      "learning_rate": 2e-05,
+      "loss": 1.5338,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.5808935165405273,
+      "learning_rate": 2e-05,
+      "loss": 0.5527,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 7.009443759918213,
+      "learning_rate": 2e-05,
+      "loss": 1.2703,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 7.639594078063965,
+      "learning_rate": 2e-05,
+      "loss": 1.6407,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 10.748512268066406,
+      "learning_rate": 2e-05,
+      "loss": 2.7119,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.931131362915039,
+      "learning_rate": 2e-05,
+      "loss": 1.332,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.751891613006592,
+      "learning_rate": 2e-05,
+      "loss": 0.5565,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.8544440269470215,
+      "learning_rate": 2e-05,
+      "loss": 1.1039,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 7.867600440979004,
+      "learning_rate": 2e-05,
+      "loss": 1.7485,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.696001052856445,
+      "learning_rate": 2e-05,
+      "loss": 1.4325,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.3621315956115723,
+      "learning_rate": 2e-05,
+      "loss": 0.9735,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 6.720008850097656,
+      "learning_rate": 2e-05,
+      "loss": 0.9182,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.451417088508606,
+      "learning_rate": 2e-05,
+      "loss": 1.4714,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.894761562347412,
+      "learning_rate": 2e-05,
+      "loss": 0.9466,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.2837414741516113,
+      "learning_rate": 2e-05,
+      "loss": 1.0579,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.35042667388916,
+      "learning_rate": 2e-05,
+      "loss": 0.5301,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.1204663515090942,
+      "learning_rate": 2e-05,
+      "loss": 1.0299,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 4.040454864501953,
+      "learning_rate": 2e-05,
+      "loss": 1.7987,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 6.976199626922607,
+      "learning_rate": 2e-05,
+      "loss": 0.8811,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 5.038837909698486,
+      "learning_rate": 2e-05,
+      "loss": 1.3469,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.1533371210098267,
+      "learning_rate": 2e-05,
+      "loss": 0.8213,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.484751224517822,
+      "learning_rate": 2e-05,
+      "loss": 1.5949,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.307978391647339,
+      "learning_rate": 2e-05,
+      "loss": 1.561,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.5336391925811768,
+      "learning_rate": 2e-05,
+      "loss": 1.5742,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.477813243865967,
+      "learning_rate": 2e-05,
+      "loss": 0.778,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 4.3487443923950195,
+      "learning_rate": 2e-05,
+      "loss": 1.0323,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.038912534713745,
+      "learning_rate": 2e-05,
+      "loss": 1.2723,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.805425643920898,
+      "learning_rate": 2e-05,
+      "loss": 1.6786,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.4529948234558105,
+      "learning_rate": 2e-05,
+      "loss": 1.044,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.10660982131958,
+      "learning_rate": 2e-05,
+      "loss": 0.5032,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.402340292930603,
+      "learning_rate": 2e-05,
+      "loss": 0.4542,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.467075824737549,
+      "learning_rate": 2e-05,
+      "loss": 0.5911,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.6482043266296387,
+      "learning_rate": 2e-05,
+      "loss": 0.5791,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.8936263918876648,
+      "learning_rate": 2e-05,
+      "loss": 0.5246,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.2066774368286133,
+      "learning_rate": 2e-05,
+      "loss": 0.9112,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 5.093555450439453,
+      "learning_rate": 2e-05,
+      "loss": 2.6101,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8295354247093201,
+      "learning_rate": 2e-05,
+      "loss": 0.3223,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2232448700121088.0,
+      "train_loss": 1.3239105606079102,
+      "train_runtime": 200.6918,
+      "train_samples_per_second": 1.993,
+      "train_steps_per_second": 0.498
+    }
+  ],
+  "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": 2232448700121088.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5261f95100c0c51812337c38912cb7860120fa221dcf5b707a32a68e5def55
+size 778341886

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d477fa569979d03ea3532fbf689df0a7034e70687dffc582e3cfea71ff1c152e
+size 778341886

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca069f5d4ff088206f9e7f08bb0231ee8a26716aa0bf53e94c3046a3fb274732
+size 778341886

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd7a70db8f3d2ed0c1b30c6b2f2284a84dc34dad7951573ca2c2313eaebd655
+size 778341886

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97cf3be13624527100e90e693ee0f5b4dd42a7c9b884c429ba7ba63ac9a1ea31
+size 778341034

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc117b47e62c496a56ada7b6259ba2334e03ebe99d3c871decc3e026e9bf68c4
+size 778341886

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f00abd1910b0ce9aa851ea534bd3e7b45c7d124628b8d237ce47a8fb020c55
+size 778341034

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:910fb780fdf2f4f33d77ac5ab299c2e1531eac8bbcc3501d491390540820e395
+size 778341034

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_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": 2.135240077972412,
+      "learning_rate": 2e-05,
+      "loss": 1.0894,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.9615914821624756,
+      "learning_rate": 2e-05,
+      "loss": 1.1041,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.6545370221138,
+      "learning_rate": 2e-05,
+      "loss": 0.8112,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.5365221500396729,
+      "learning_rate": 2e-05,
+      "loss": 0.6786,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.4570178985595703,
+      "learning_rate": 2e-05,
+      "loss": 0.5305,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.0226900577545166,
+      "learning_rate": 2e-05,
+      "loss": 1.0511,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.8617432713508606,
+      "learning_rate": 2e-05,
+      "loss": 0.5836,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.024794578552246,
+      "learning_rate": 2e-05,
+      "loss": 1.1538,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.498765707015991,
+      "learning_rate": 2e-05,
+      "loss": 1.1043,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.5931302309036255,
+      "learning_rate": 2e-05,
+      "loss": 0.8382,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.6691994667053223,
+      "learning_rate": 2e-05,
+      "loss": 1.172,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.5918915271759033,
+      "learning_rate": 2e-05,
+      "loss": 1.1233,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.495661973953247,
+      "learning_rate": 2e-05,
+      "loss": 1.1864,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.3097240924835205,
+      "learning_rate": 2e-05,
+      "loss": 0.6324,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.8678293228149414,
+      "learning_rate": 2e-05,
+      "loss": 0.7137,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.0660629272460938,
+      "learning_rate": 2e-05,
+      "loss": 0.9321,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.8471760749816895,
+      "learning_rate": 2e-05,
+      "loss": 1.0355,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.508430242538452,
+      "learning_rate": 2e-05,
+      "loss": 0.5002,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.8722703456878662,
+      "learning_rate": 2e-05,
+      "loss": 0.7212,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.5722665786743164,
+      "learning_rate": 2e-05,
+      "loss": 0.8498,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.9076077938079834,
+      "learning_rate": 2e-05,
+      "loss": 0.7296,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.572580575942993,
+      "learning_rate": 2e-05,
+      "loss": 1.3611,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.44332531094551086,
+      "learning_rate": 2e-05,
+      "loss": 0.2498,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.1259448528289795,
+      "learning_rate": 2e-05,
+      "loss": 0.7585,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.0389528274536133,
+      "learning_rate": 2e-05,
+      "loss": 0.6054,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.683242082595825,
+      "learning_rate": 2e-05,
+      "loss": 1.4809,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.6899000406265259,
+      "learning_rate": 2e-05,
+      "loss": 0.8846,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.9556215405464172,
+      "learning_rate": 2e-05,
+      "loss": 0.6845,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.7650007605552673,
+      "learning_rate": 2e-05,
+      "loss": 0.8277,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.223469853401184,
+      "learning_rate": 2e-05,
+      "loss": 0.6027,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.3763542175292969,
+      "learning_rate": 2e-05,
+      "loss": 0.4406,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.8908870220184326,
+      "learning_rate": 2e-05,
+      "loss": 0.4679,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.5750905275344849,
+      "learning_rate": 2e-05,
+      "loss": 1.1326,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.523346185684204,
+      "learning_rate": 2e-05,
+      "loss": 1.1717,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.8685157299041748,
+      "learning_rate": 2e-05,
+      "loss": 0.3642,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.6070201396942139,
+      "learning_rate": 2e-05,
+      "loss": 0.2661,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.4007425308227539,
+      "learning_rate": 2e-05,
+      "loss": 0.3317,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.8447000980377197,
+      "learning_rate": 2e-05,
+      "loss": 0.7384,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.9502848386764526,
+      "learning_rate": 2e-05,
+      "loss": 0.5064,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.8948686718940735,
+      "learning_rate": 2e-05,
+      "loss": 0.6011,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.3797571063041687,
+      "learning_rate": 2e-05,
+      "loss": 0.0635,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.7227259874343872,
+      "learning_rate": 2e-05,
+      "loss": 0.3671,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.8156260848045349,
+      "learning_rate": 2e-05,
+      "loss": 0.3524,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.4789669513702393,
+      "learning_rate": 2e-05,
+      "loss": 0.2621,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.2756178677082062,
+      "learning_rate": 2e-05,
+      "loss": 0.8211,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.6193075776100159,
+      "learning_rate": 2e-05,
+      "loss": 0.2295,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.6215288043022156,
+      "learning_rate": 2e-05,
+      "loss": 1.6611,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.10143130272626877,
+      "learning_rate": 2e-05,
+      "loss": 0.0809,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.530308723449707,
+      "learning_rate": 2e-05,
+      "loss": 0.3437,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9788203835487366,
+      "learning_rate": 2e-05,
+      "loss": 0.4016,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 6021650063556608.0,
+      "train_loss": 0.7320010375976562,
+      "train_runtime": 329.014,
+      "train_samples_per_second": 1.216,
+      "train_steps_per_second": 0.304
+    }
+  ],
+  "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": 6021650063556608.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fbfaefa8c867086bb2d17e11c798ab563fd4e0fcf8a4a601a5ae690d9ada118
+size 778341886

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d916acd5ef982141ea4a8ecb0542d6561472df83b8b01ce63b3edbf0477d89
+size 778341886

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0b950eafe3f401e3ed5106e0607a05074eb7df4476b642768746e23f6ff993
+size 778341886

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d63d20e41cc50ae1113a13946050e4bd86d293b4596c6c12248ade0edd93177d
+size 778341886

client_states_feddpa_NOCONT_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixit100_T0125_decay099/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9bece4e78ec943c8a8cb5f81f3751d2090e73fcec3865837e6d4bb28f6f655
+size 778341034