Upload folder using huggingface_hub

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:272d152a867ab41665ff4b14bd2664cbe439281aac4ce8b200d7b718307b126b
+size 360880622

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d76b1907e562d7be4b4d8c05be01e4cda31f7db1d20626ea7dfd1af12033ad00
+size 360880622

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccce5a80eebb1205c033e472b86c672bc6d13cd4c190227bd7e348128e47d581
+size 360880622

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c645bb754c2ce02ce91f973e5140f29977b468544be656eb2bc6d527d6bec808
+size 360880622

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c7476432e61646d8e60716a84e633c89b0e944b2cb4ebac0ec4841daee1cde2
+size 360880106

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c1a84dc752dd6efa6cc783b662d254ed587ca2b9cf76496d9992ff3deb58ee9
+size 360880622

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10cc54c34e7cd9c8ffe66d0ab7036d02f9ddc8b7839553f6fa9d9fe022abca00
+size 360880106

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aff43e0efa5d50dda0f87da98d075db9b26ea5d9c7fb5dee923a0c32e15f4a1c
+size 360880106

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 11.468276023864746,
+      "learning_rate": 2e-05,
+      "loss": 1.668,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 13.013179779052734,
+      "learning_rate": 2e-05,
+      "loss": 0.6551,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.899092674255371,
+      "learning_rate": 2e-05,
+      "loss": 1.4227,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 10.417702674865723,
+      "learning_rate": 2e-05,
+      "loss": 1.2854,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.4957451820373535,
+      "learning_rate": 2e-05,
+      "loss": 1.076,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 11.509440422058105,
+      "learning_rate": 2e-05,
+      "loss": 0.6792,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.03311014175415,
+      "learning_rate": 2e-05,
+      "loss": 0.2549,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.364517688751221,
+      "learning_rate": 2e-05,
+      "loss": 1.4782,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.390167236328125,
+      "learning_rate": 2e-05,
+      "loss": 0.49,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 6.741970062255859,
+      "learning_rate": 2e-05,
+      "loss": 3.6953,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.631387948989868,
+      "learning_rate": 2e-05,
+      "loss": 0.2798,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 7.609371185302734,
+      "learning_rate": 2e-05,
+      "loss": 0.4919,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.3606047630310059,
+      "learning_rate": 2e-05,
+      "loss": 0.1068,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 15.077208518981934,
+      "learning_rate": 2e-05,
+      "loss": 1.6368,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.3899340629577637,
+      "learning_rate": 2e-05,
+      "loss": 0.274,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.730544090270996,
+      "learning_rate": 2e-05,
+      "loss": 0.5332,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.338137149810791,
+      "learning_rate": 2e-05,
+      "loss": 0.5818,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.47265109419822693,
+      "learning_rate": 2e-05,
+      "loss": 0.3511,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.583622455596924,
+      "learning_rate": 2e-05,
+      "loss": 0.1571,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.760534763336182,
+      "learning_rate": 2e-05,
+      "loss": 0.3887,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.149841547012329,
+      "learning_rate": 2e-05,
+      "loss": 0.4415,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4094676077365875,
+      "learning_rate": 2e-05,
+      "loss": 0.858,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.535027503967285,
+      "learning_rate": 2e-05,
+      "loss": 0.4825,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 6.963266372680664,
+      "learning_rate": 2e-05,
+      "loss": 0.542,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.2709807753562927,
+      "learning_rate": 2e-05,
+      "loss": 0.4804,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.4240652322769165,
+      "learning_rate": 2e-05,
+      "loss": 0.4452,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.6048128604888916,
+      "learning_rate": 2e-05,
+      "loss": 0.6762,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.263965129852295,
+      "learning_rate": 2e-05,
+      "loss": 1.3549,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 5.906020164489746,
+      "learning_rate": 2e-05,
+      "loss": 0.7348,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.632805824279785,
+      "learning_rate": 2e-05,
+      "loss": 0.7929,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.760554552078247,
+      "learning_rate": 2e-05,
+      "loss": 1.0124,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.37708696722984314,
+      "learning_rate": 2e-05,
+      "loss": 0.036,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 5.953865051269531,
+      "learning_rate": 2e-05,
+      "loss": 1.0636,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.12408101558685303,
+      "learning_rate": 2e-05,
+      "loss": 0.2447,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.6159584522247314,
+      "learning_rate": 2e-05,
+      "loss": 1.5753,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.123723268508911,
+      "learning_rate": 2e-05,
+      "loss": 0.3181,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.158083200454712,
+      "learning_rate": 2e-05,
+      "loss": 0.255,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.0079448223114014,
+      "learning_rate": 2e-05,
+      "loss": 1.3879,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.4162845611572266,
+      "learning_rate": 2e-05,
+      "loss": 1.2661,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.42022573947906494,
+      "learning_rate": 2e-05,
+      "loss": 0.4624,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.4718551635742188,
+      "learning_rate": 2e-05,
+      "loss": 2.6513,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.038799285888672,
+      "learning_rate": 2e-05,
+      "loss": 0.6602,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.767530620098114,
+      "learning_rate": 2e-05,
+      "loss": 0.2701,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.633103847503662,
+      "learning_rate": 2e-05,
+      "loss": 0.2863,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.8834018707275391,
+      "learning_rate": 2e-05,
+      "loss": 0.0962,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.8029925227165222,
+      "learning_rate": 2e-05,
+      "loss": 0.151,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.0458297729492188,
+      "learning_rate": 2e-05,
+      "loss": 0.6086,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.42579904198646545,
+      "learning_rate": 2e-05,
+      "loss": 0.1379,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.0101704597473145,
+      "learning_rate": 2e-05,
+      "loss": 0.7558,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.33978980779647827,
+      "learning_rate": 2e-05,
+      "loss": 0.0732,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2185662354685952.0,
+      "train_loss": 0.7525365662574768,
+      "train_runtime": 150.9129,
+      "train_samples_per_second": 2.651,
+      "train_steps_per_second": 0.663
+    }
+  ],
+  "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": 2185662354685952.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb4a49b439c28d8d190448191d2491c8f2d9d9381a33bc569753df77b93d107
+size 360880622

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5262adbeb60ccffc1323f73831539fe624c2aed741f137c58f49b119e4fdedae
+size 360880622

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77cba52695feb8bc4b3ca31a58e5f6683e9fa65f1fb92adb455e7a928e1d7340
+size 360880622

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58e7cfddf57ab23e40048ac3f369a966ab3599bf543f7d45ca359409a21019f8
+size 360880622

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f03b72475b164bdca0088703374303e8763eb107dee5edc11c880e977d38854
+size 360880106

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da1f49acd8f0189d516ddc07a8795e024cda908579a6359e0b0c7660404fca3
+size 360880622

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa895286be91de8a6e0f37351e38c8e427030e99aff09b52daf580349c09642a
+size 360880106

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1bec964f18c50fe82a94a345b89e64ae93b437a2d60349a8bf20f2331b2cfbc
+size 360880106

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.9418780207633972,
+      "learning_rate": 2e-05,
+      "loss": 0.3668,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.7834081053733826,
+      "learning_rate": 2e-05,
+      "loss": 0.2299,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.570934772491455,
+      "learning_rate": 2e-05,
+      "loss": 0.5088,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.852219581604004,
+      "learning_rate": 2e-05,
+      "loss": 0.3404,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.046853017061948776,
+      "learning_rate": 2e-05,
+      "loss": 0.0053,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.4755373001098633,
+      "learning_rate": 2e-05,
+      "loss": 0.2663,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.413883239030838,
+      "learning_rate": 2e-05,
+      "loss": 1.0055,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.07382853329181671,
+      "learning_rate": 2e-05,
+      "loss": 0.3183,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.10246730595827103,
+      "learning_rate": 2e-05,
+      "loss": 0.0289,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.03177673742175102,
+      "learning_rate": 2e-05,
+      "loss": 0.0242,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.1593880653381348,
+      "learning_rate": 2e-05,
+      "loss": 0.4398,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.9290744066238403,
+      "learning_rate": 2e-05,
+      "loss": 0.0844,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.05123985931277275,
+      "learning_rate": 2e-05,
+      "loss": 0.0085,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.8998264074325562,
+      "learning_rate": 2e-05,
+      "loss": 0.527,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.13683098554611206,
+      "learning_rate": 2e-05,
+      "loss": 0.1605,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.09497078508138657,
+      "learning_rate": 2e-05,
+      "loss": 0.0061,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.39149010181427,
+      "learning_rate": 2e-05,
+      "loss": 0.0452,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.549695372581482,
+      "learning_rate": 2e-05,
+      "loss": 0.1289,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.633894145488739,
+      "learning_rate": 2e-05,
+      "loss": 0.0119,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.8946341276168823,
+      "learning_rate": 2e-05,
+      "loss": 0.6402,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 7.587536811828613,
+      "learning_rate": 2e-05,
+      "loss": 0.8406,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.09829995036125183,
+      "learning_rate": 2e-05,
+      "loss": 0.4789,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.1041155681014061,
+      "learning_rate": 2e-05,
+      "loss": 0.0109,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.195893332362175,
+      "learning_rate": 2e-05,
+      "loss": 0.0113,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.05048517510294914,
+      "learning_rate": 2e-05,
+      "loss": 0.0089,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.13715337216854095,
+      "learning_rate": 2e-05,
+      "loss": 0.0143,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.015534869395196438,
+      "learning_rate": 2e-05,
+      "loss": 0.0036,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.8198376893997192,
+      "learning_rate": 2e-05,
+      "loss": 0.1497,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.195146560668945,
+      "learning_rate": 2e-05,
+      "loss": 0.4006,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5402289628982544,
+      "learning_rate": 2e-05,
+      "loss": 0.0427,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.02903779409825802,
+      "learning_rate": 2e-05,
+      "loss": 0.0064,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.12855856120586395,
+      "learning_rate": 2e-05,
+      "loss": 0.0144,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.7946436405181885,
+      "learning_rate": 2e-05,
+      "loss": 0.7804,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.8190321326255798,
+      "learning_rate": 2e-05,
+      "loss": 0.0701,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.7014371156692505,
+      "learning_rate": 2e-05,
+      "loss": 0.0854,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.01210495363920927,
+      "learning_rate": 2e-05,
+      "loss": 0.0023,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.47593849897384644,
+      "learning_rate": 2e-05,
+      "loss": 0.059,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.3410400152206421,
+      "learning_rate": 2e-05,
+      "loss": 0.0698,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.10963509231805801,
+      "learning_rate": 2e-05,
+      "loss": 0.3811,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.2575267553329468,
+      "learning_rate": 2e-05,
+      "loss": 0.0941,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.0267863273620605,
+      "learning_rate": 2e-05,
+      "loss": 0.098,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.1581244319677353,
+      "learning_rate": 2e-05,
+      "loss": 0.0377,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.07940375804901123,
+      "learning_rate": 2e-05,
+      "loss": 0.0357,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.023072313517332077,
+      "learning_rate": 2e-05,
+      "loss": 0.0188,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.7455753087997437,
+      "learning_rate": 2e-05,
+      "loss": 0.0823,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.048216842114925385,
+      "learning_rate": 2e-05,
+      "loss": 0.1018,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.0343430042266846,
+      "learning_rate": 2e-05,
+      "loss": 0.176,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.007752849720418453,
+      "learning_rate": 2e-05,
+      "loss": 0.0009,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.03207560256123543,
+      "learning_rate": 2e-05,
+      "loss": 0.003,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.009924360550940037,
+      "learning_rate": 2e-05,
+      "loss": 0.0046,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2203100823683072.0,
+      "train_loss": 0.18460362195968627,
+      "train_runtime": 149.7722,
+      "train_samples_per_second": 2.671,
+      "train_steps_per_second": 0.668
+    }
+  ],
+  "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": 2203100823683072.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a019c92267ae5e335d1fc8ff84c7bc54d54e96aba66854e764ac80751b6f099d
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6242ea4cc9a3597dc8837aaecf93606e3398073b2c82117d2a6a0ce78f98e8f9
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f55720eb65ef087919dc1066498f361c45fc3eddb2c5e4e5dabc94a09b7e9d9
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a41aa0790261c9acffea762697a87338db5625da24eb92c86311cc1d1f6e6e3
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3db03128dae4ecfbb360db76f763c5031af8aca8d8151ea474128fe2c4143c3
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0989773b3a23802284d1201822033ed34046005735930e560fed0be9b06a3f4
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6040888c80e53df52e617b46f5db4f3d546eacccbf52b2d80a692324698721
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f29dd2aaaa2d2887d9ddd03c9ec0218e80c11ab8e26af8c70b5e443345dac2df
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.7772328853607178,
+      "learning_rate": 2e-05,
+      "loss": 1.0009,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.870094060897827,
+      "learning_rate": 2e-05,
+      "loss": 0.7007,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.33457279205322266,
+      "learning_rate": 2e-05,
+      "loss": 0.0473,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.4138612747192383,
+      "learning_rate": 2e-05,
+      "loss": 0.2522,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.5410336256027222,
+      "learning_rate": 2e-05,
+      "loss": 0.2067,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.8038370609283447,
+      "learning_rate": 2e-05,
+      "loss": 0.6918,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 6.221210479736328,
+      "learning_rate": 2e-05,
+      "loss": 1.1887,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.4460601806640625,
+      "learning_rate": 2e-05,
+      "loss": 0.7211,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.6152211427688599,
+      "learning_rate": 2e-05,
+      "loss": 0.3936,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.758711338043213,
+      "learning_rate": 2e-05,
+      "loss": 1.348,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.9407858848571777,
+      "learning_rate": 2e-05,
+      "loss": 0.4284,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.8231184482574463,
+      "learning_rate": 2e-05,
+      "loss": 0.289,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.1073336601257324,
+      "learning_rate": 2e-05,
+      "loss": 0.1379,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.671870708465576,
+      "learning_rate": 2e-05,
+      "loss": 1.0666,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.4478886127471924,
+      "learning_rate": 2e-05,
+      "loss": 1.5288,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.0650575160980225,
+      "learning_rate": 2e-05,
+      "loss": 0.6413,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.9534478187561035,
+      "learning_rate": 2e-05,
+      "loss": 1.518,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.6580589413642883,
+      "learning_rate": 2e-05,
+      "loss": 0.0963,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.114241600036621,
+      "learning_rate": 2e-05,
+      "loss": 0.5737,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5105870366096497,
+      "learning_rate": 2e-05,
+      "loss": 0.5189,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.34910497069358826,
+      "learning_rate": 2e-05,
+      "loss": 0.0478,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.300654411315918,
+      "learning_rate": 2e-05,
+      "loss": 0.3245,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.8640389442443848,
+      "learning_rate": 2e-05,
+      "loss": 0.2942,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.876298725605011,
+      "learning_rate": 2e-05,
+      "loss": 0.3075,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.08325261622667313,
+      "learning_rate": 2e-05,
+      "loss": 0.2153,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.11174854636192322,
+      "learning_rate": 2e-05,
+      "loss": 0.4341,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.753587245941162,
+      "learning_rate": 2e-05,
+      "loss": 0.8374,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.9684956073760986,
+      "learning_rate": 2e-05,
+      "loss": 1.4496,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.8988077640533447,
+      "learning_rate": 2e-05,
+      "loss": 1.2955,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.069868564605713,
+      "learning_rate": 2e-05,
+      "loss": 0.4547,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.5531668663024902,
+      "learning_rate": 2e-05,
+      "loss": 0.1617,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0127068758010864,
+      "learning_rate": 2e-05,
+      "loss": 0.5601,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.7856873273849487,
+      "learning_rate": 2e-05,
+      "loss": 0.3769,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.4297077655792236,
+      "learning_rate": 2e-05,
+      "loss": 0.5413,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.4274978041648865,
+      "learning_rate": 2e-05,
+      "loss": 0.2912,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.011972427368164,
+      "learning_rate": 2e-05,
+      "loss": 0.6817,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.2338765859603882,
+      "learning_rate": 2e-05,
+      "loss": 0.5988,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.7795504331588745,
+      "learning_rate": 2e-05,
+      "loss": 0.4102,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.6567718982696533,
+      "learning_rate": 2e-05,
+      "loss": 0.4535,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.0618244409561157,
+      "learning_rate": 2e-05,
+      "loss": 1.3002,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.8827853798866272,
+      "learning_rate": 2e-05,
+      "loss": 0.7112,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.621549129486084,
+      "learning_rate": 2e-05,
+      "loss": 0.414,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.6500234603881836,
+      "learning_rate": 2e-05,
+      "loss": 1.0575,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.41276150941848755,
+      "learning_rate": 2e-05,
+      "loss": 0.1767,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.3679842948913574,
+      "learning_rate": 2e-05,
+      "loss": 0.2918,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.2793606519699097,
+      "learning_rate": 2e-05,
+      "loss": 0.8175,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.083470106124878,
+      "learning_rate": 2e-05,
+      "loss": 0.6887,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6317909955978394,
+      "learning_rate": 2e-05,
+      "loss": 0.6057,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.9122306108474731,
+      "learning_rate": 2e-05,
+      "loss": 0.6412,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.5604162216186523,
+      "learning_rate": 2e-05,
+      "loss": 0.7647,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5200945432494080.0,
+      "train_loss": 0.6110978984832763,
+      "train_runtime": 254.1782,
+      "train_samples_per_second": 1.574,
+      "train_steps_per_second": 0.393
+    }
+  ],
+  "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": 5200945432494080.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09dc85a329ffdfcb332f4a210c4251b86b95e5d6dc5312a63f5a569f098b29a
+size 360880622

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67938ab6eeb915d73a553f80721eb8e49fa1ec3af8c756286e61bb00fba2b40c
+size 360880622

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9d648dd6669c20a5b07d0a810eabe043d67ec4ebc16d7bb2a7ca44fdea0a05
+size 360880622

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:412e5c6b8d09bafb8dfffb4e470a1accfa6670ee17d7894b972774a99b001990
+size 360880622

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e372c275a65c800dee474024b429c87baefb6e713548d7392a255d0299246ca5
+size 360880106

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0353c976d6a405c39434e2fbfead24f4396b1945cd0c74ea8e3025c308dd6b53
+size 360880622

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b44cf92c0b4f0c4f48eeb4c53de6cf30bce271873da0250b2baee6543caf7605
+size 360880106

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b9cb7fdf91a5d699f2b4ec2b6cd3c5fe3e4859c5e09da3ab2c6d489b753783
+size 360880106

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 7.792142391204834,
+      "learning_rate": 2e-05,
+      "loss": 1.2916,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.023014545440674,
+      "learning_rate": 2e-05,
+      "loss": 3.5714,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 6.57926082611084,
+      "learning_rate": 2e-05,
+      "loss": 1.5864,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 10.789443016052246,
+      "learning_rate": 2e-05,
+      "loss": 2.7961,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.5799789428710938,
+      "learning_rate": 2e-05,
+      "loss": 0.5679,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.088947772979736,
+      "learning_rate": 2e-05,
+      "loss": 1.5752,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.1460089683532715,
+      "learning_rate": 2e-05,
+      "loss": 0.9169,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.7856991291046143,
+      "learning_rate": 2e-05,
+      "loss": 0.8518,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.619609832763672,
+      "learning_rate": 2e-05,
+      "loss": 1.3801,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.50746488571167,
+      "learning_rate": 2e-05,
+      "loss": 1.2587,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 8.305500030517578,
+      "learning_rate": 2e-05,
+      "loss": 1.0734,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.19241189956665,
+      "learning_rate": 2e-05,
+      "loss": 0.7836,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.3395862579345703,
+      "learning_rate": 2e-05,
+      "loss": 0.6475,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 7.040569305419922,
+      "learning_rate": 2e-05,
+      "loss": 1.2521,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.001715660095215,
+      "learning_rate": 2e-05,
+      "loss": 1.1543,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 8.984875679016113,
+      "learning_rate": 2e-05,
+      "loss": 2.0586,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.349306583404541,
+      "learning_rate": 2e-05,
+      "loss": 1.0413,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 5.427790641784668,
+      "learning_rate": 2e-05,
+      "loss": 1.6563,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.6137840747833252,
+      "learning_rate": 2e-05,
+      "loss": 1.1592,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.16748309135437,
+      "learning_rate": 2e-05,
+      "loss": 0.5156,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 8.764156341552734,
+      "learning_rate": 2e-05,
+      "loss": 2.4003,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 9.373359680175781,
+      "learning_rate": 2e-05,
+      "loss": 1.6908,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.3396241664886475,
+      "learning_rate": 2e-05,
+      "loss": 0.7827,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.254624128341675,
+      "learning_rate": 2e-05,
+      "loss": 0.5496,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.849947929382324,
+      "learning_rate": 2e-05,
+      "loss": 1.1958,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.5219838619232178,
+      "learning_rate": 2e-05,
+      "loss": 0.9757,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.996366262435913,
+      "learning_rate": 2e-05,
+      "loss": 0.8615,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.0587832927703857,
+      "learning_rate": 2e-05,
+      "loss": 0.9333,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 8.328261375427246,
+      "learning_rate": 2e-05,
+      "loss": 2.0392,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.4318846464157104,
+      "learning_rate": 2e-05,
+      "loss": 1.6461,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.621255874633789,
+      "learning_rate": 2e-05,
+      "loss": 0.4382,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 5.432891845703125,
+      "learning_rate": 2e-05,
+      "loss": 1.6557,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.570347785949707,
+      "learning_rate": 2e-05,
+      "loss": 0.5628,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 6.035056114196777,
+      "learning_rate": 2e-05,
+      "loss": 0.8242,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.1205101013183594,
+      "learning_rate": 2e-05,
+      "loss": 0.9068,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.7536263465881348,
+      "learning_rate": 2e-05,
+      "loss": 1.7733,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 5.084173679351807,
+      "learning_rate": 2e-05,
+      "loss": 1.139,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.9449111819267273,
+      "learning_rate": 2e-05,
+      "loss": 0.5757,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.6127724647521973,
+      "learning_rate": 2e-05,
+      "loss": 1.3481,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.3057523965835571,
+      "learning_rate": 2e-05,
+      "loss": 0.705,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.5335392951965332,
+      "learning_rate": 2e-05,
+      "loss": 0.9568,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 2.186148166656494,
+      "learning_rate": 2e-05,
+      "loss": 0.5098,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.127236843109131,
+      "learning_rate": 2e-05,
+      "loss": 2.0965,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.2698607444763184,
+      "learning_rate": 2e-05,
+      "loss": 1.8116,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 7.15731143951416,
+      "learning_rate": 2e-05,
+      "loss": 2.0281,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.700381875038147,
+      "learning_rate": 2e-05,
+      "loss": 1.3664,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.8054038286209106,
+      "learning_rate": 2e-05,
+      "loss": 1.0307,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.1921820640563965,
+      "learning_rate": 2e-05,
+      "loss": 1.1617,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.8828494548797607,
+      "learning_rate": 2e-05,
+      "loss": 0.7795,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.916834831237793,
+      "learning_rate": 2e-05,
+      "loss": 0.7422,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2233291239325696.0,
+      "train_loss": 1.2525035691261293,
+      "train_runtime": 160.8169,
+      "train_samples_per_second": 2.487,
+      "train_steps_per_second": 0.622
+    }
+  ],
+  "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": 2233291239325696.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c88bcdbcef96f0cc9f10b056f032824471bf31525402a1888c54d6a5bd93ddf6
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78f69654677d277697dcf550b91d3448ea03a05c37dfd28e0723874e20adc908
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b29534740cdf69dfee373ef8bc9c0749923bde13b5208006fbc18916f3ca0a
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86cfeae9f0b9a252446507106e41bbcc13e74bcb4cc11f9f5e173506fd0dda79
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef777dc711277e61509e50d38a953a057667fa139be8faeac789ba5c2698a3f
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb30030ae9a34e79c71b04a8f44f1913824dc261d37d6b9c6c53b09aa4fe5d70
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec26c19913afffba6c0fd3585819787a6c533aa5c831d9a9daef84aba1bcc71
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:723a4d97f24e5c1a311901f6621474755cd35e8326fff914074f1a7e1f399beb
+size 778341034

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.3815970420837402,
+      "learning_rate": 2e-05,
+      "loss": 0.5863,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.8185386657714844,
+      "learning_rate": 2e-05,
+      "loss": 1.2971,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.8948168754577637,
+      "learning_rate": 2e-05,
+      "loss": 0.9846,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.101174831390381,
+      "learning_rate": 2e-05,
+      "loss": 1.688,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.688793897628784,
+      "learning_rate": 2e-05,
+      "loss": 0.6859,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.47356915473938,
+      "learning_rate": 2e-05,
+      "loss": 1.0135,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.2694878578186035,
+      "learning_rate": 2e-05,
+      "loss": 0.9047,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.625256061553955,
+      "learning_rate": 2e-05,
+      "loss": 1.125,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.0847363471984863,
+      "learning_rate": 2e-05,
+      "loss": 1.2551,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.9543544054031372,
+      "learning_rate": 2e-05,
+      "loss": 0.7905,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.1540379524230957,
+      "learning_rate": 2e-05,
+      "loss": 0.7426,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.8286647200584412,
+      "learning_rate": 2e-05,
+      "loss": 0.3257,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.9040488004684448,
+      "learning_rate": 2e-05,
+      "loss": 0.5483,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.71846342086792,
+      "learning_rate": 2e-05,
+      "loss": 0.7243,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.20640230178833,
+      "learning_rate": 2e-05,
+      "loss": 1.1453,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.0493052005767822,
+      "learning_rate": 2e-05,
+      "loss": 1.1843,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.9781206846237183,
+      "learning_rate": 2e-05,
+      "loss": 0.8867,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.0017993450164795,
+      "learning_rate": 2e-05,
+      "loss": 1.3522,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.269047737121582,
+      "learning_rate": 2e-05,
+      "loss": 0.6205,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.3758752346038818,
+      "learning_rate": 2e-05,
+      "loss": 0.6778,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.46341073513031,
+      "learning_rate": 2e-05,
+      "loss": 0.8367,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.903554916381836,
+      "learning_rate": 2e-05,
+      "loss": 1.1299,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.7048883438110352,
+      "learning_rate": 2e-05,
+      "loss": 0.388,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.586846947669983,
+      "learning_rate": 2e-05,
+      "loss": 1.0262,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.801108956336975,
+      "learning_rate": 2e-05,
+      "loss": 0.4058,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.518892765045166,
+      "learning_rate": 2e-05,
+      "loss": 1.8573,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.9927799701690674,
+      "learning_rate": 2e-05,
+      "loss": 0.8552,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.25938358902931213,
+      "learning_rate": 2e-05,
+      "loss": 0.5029,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.1329509019851685,
+      "learning_rate": 2e-05,
+      "loss": 0.6975,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.3482877016067505,
+      "learning_rate": 2e-05,
+      "loss": 0.269,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.7116028070449829,
+      "learning_rate": 2e-05,
+      "loss": 0.6903,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.584398031234741,
+      "learning_rate": 2e-05,
+      "loss": 1.0017,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.240759015083313,
+      "learning_rate": 2e-05,
+      "loss": 0.2974,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.373422622680664,
+      "learning_rate": 2e-05,
+      "loss": 0.9894,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.4504565000534058,
+      "learning_rate": 2e-05,
+      "loss": 1.0746,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.392308235168457,
+      "learning_rate": 2e-05,
+      "loss": 0.6376,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.5228718519210815,
+      "learning_rate": 2e-05,
+      "loss": 1.0094,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.7216625213623047,
+      "learning_rate": 2e-05,
+      "loss": 0.2343,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.6243200302124023,
+      "learning_rate": 2e-05,
+      "loss": 0.308,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.7099385261535645,
+      "learning_rate": 2e-05,
+      "loss": 1.2533,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.371478796005249,
+      "learning_rate": 2e-05,
+      "loss": 1.7963,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 2.473755121231079,
+      "learning_rate": 2e-05,
+      "loss": 0.7662,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.194167137145996,
+      "learning_rate": 2e-05,
+      "loss": 1.0925,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.4907443523406982,
+      "learning_rate": 2e-05,
+      "loss": 1.1646,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.6863021850585938,
+      "learning_rate": 2e-05,
+      "loss": 0.6589,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.869765043258667,
+      "learning_rate": 2e-05,
+      "loss": 0.9901,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.8603519201278687,
+      "learning_rate": 2e-05,
+      "loss": 0.4007,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.9052290320396423,
+      "learning_rate": 2e-05,
+      "loss": 0.6978,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.2907326221466064,
+      "learning_rate": 2e-05,
+      "loss": 0.4787,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4034663438796997,
+      "learning_rate": 2e-05,
+      "loss": 0.6854,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 6020085697216512.0,
+      "train_loss": 0.8546864128112793,
+      "train_runtime": 255.754,
+      "train_samples_per_second": 1.564,
+      "train_steps_per_second": 0.391
+    }
+  ],
+  "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": 6020085697216512.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c3a1b765d8bd5932df4956901960360e5b4e813af8c4fd48a911511d54f299
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a002bd6bd961d702a9f40536b342cae52b650251facf614e81064f85fe5901
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:774bae98e390e5a37e10de5e0db1f24e9e86a534077998f010879dc7d6b6e3d3
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e7450aea0bcdceccc04163ce77df3ae35350518486063118edac379c7c8470
+size 778341886

client_states_feddpa_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d61d2ee984ad9bac2c3a63e62f83964d12a7d10eec8862dfafbca85f8505c03b
+size 778341034