Upload folder using huggingface_hub

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b66a32e0ff8138602d6e73189b81eb799f08a5d1cd260bc527d56a85f6421d0
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624deb837fd30945a68870268738bcb64bb31f78b9588e60f9d518e35c2e902b
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb7237020948b2f8d4372a2898ce6eca6c774d9874f2a617a6bb9c00967bfe75
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4def8fb25d7ebb11c9cec43bf316781f3250ca1a6ddf09785dc96210cdd1d2f
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ee4b44a74b75edcd213a8102bdc22bacec527fc6307a1fbe9f07ea0f3881cb8
+size 778341034

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8baee951380ee4a586fb91f79ffce0ff27e6a6e93a57e1f87fbecc3e10c9252e
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37912ffb5b4f17a8aaa74c30e3a06eec4ad63aebf4604b55da8d5e72807cc17e
+size 778341034

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a3d64c6ac41caa81187e6c367c21b0864301381d4e8fdccf98fe623bad110b
+size 778341034

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_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": 5.029373645782471,
+      "learning_rate": 2e-05,
+      "loss": 0.3899,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.111943483352661,
+      "learning_rate": 2e-05,
+      "loss": 0.2725,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.640967845916748,
+      "learning_rate": 2e-05,
+      "loss": 1.5895,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 8.661733627319336,
+      "learning_rate": 2e-05,
+      "loss": 1.819,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.9770549535751343,
+      "learning_rate": 2e-05,
+      "loss": 0.7534,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 10.830841064453125,
+      "learning_rate": 2e-05,
+      "loss": 1.6526,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.2293946743011475,
+      "learning_rate": 2e-05,
+      "loss": 0.1848,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.2187273502349854,
+      "learning_rate": 2e-05,
+      "loss": 0.558,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.0363123416900635,
+      "learning_rate": 2e-05,
+      "loss": 0.2754,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.232224464416504,
+      "learning_rate": 2e-05,
+      "loss": 2.7864,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.9394012689590454,
+      "learning_rate": 2e-05,
+      "loss": 0.3288,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.2453362941741943,
+      "learning_rate": 2e-05,
+      "loss": 0.1595,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.42229607701301575,
+      "learning_rate": 2e-05,
+      "loss": 0.0334,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 9.027763366699219,
+      "learning_rate": 2e-05,
+      "loss": 2.0246,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.302832841873169,
+      "learning_rate": 2e-05,
+      "loss": 0.21,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.746319055557251,
+      "learning_rate": 2e-05,
+      "loss": 0.4778,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.8785818815231323,
+      "learning_rate": 2e-05,
+      "loss": 0.3394,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.0920899361371994,
+      "learning_rate": 2e-05,
+      "loss": 0.4768,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.953840494155884,
+      "learning_rate": 2e-05,
+      "loss": 0.265,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.795336961746216,
+      "learning_rate": 2e-05,
+      "loss": 0.6555,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.5175550580024719,
+      "learning_rate": 2e-05,
+      "loss": 0.1091,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.2004595547914505,
+      "learning_rate": 2e-05,
+      "loss": 0.3236,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.516871452331543,
+      "learning_rate": 2e-05,
+      "loss": 0.3721,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 6.682279586791992,
+      "learning_rate": 2e-05,
+      "loss": 1.2178,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 7.205321311950684,
+      "learning_rate": 2e-05,
+      "loss": 0.9481,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.1038731336593628,
+      "learning_rate": 2e-05,
+      "loss": 0.4632,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.3550664186477661,
+      "learning_rate": 2e-05,
+      "loss": 0.2686,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.616992712020874,
+      "learning_rate": 2e-05,
+      "loss": 1.3902,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.2277296781539917,
+      "learning_rate": 2e-05,
+      "loss": 0.2487,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.6558258533477783,
+      "learning_rate": 2e-05,
+      "loss": 0.5365,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.477752685546875,
+      "learning_rate": 2e-05,
+      "loss": 1.1109,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.6273409128189087,
+      "learning_rate": 2e-05,
+      "loss": 0.0915,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.3226382732391357,
+      "learning_rate": 2e-05,
+      "loss": 1.134,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.06056645140051842,
+      "learning_rate": 2e-05,
+      "loss": 0.1094,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.7548142671585083,
+      "learning_rate": 2e-05,
+      "loss": 1.2667,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.7575669884681702,
+      "learning_rate": 2e-05,
+      "loss": 0.131,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.8603719472885132,
+      "learning_rate": 2e-05,
+      "loss": 0.2251,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.216780424118042,
+      "learning_rate": 2e-05,
+      "loss": 1.6178,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.1145668029785156,
+      "learning_rate": 2e-05,
+      "loss": 1.2492,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.8439353704452515,
+      "learning_rate": 2e-05,
+      "loss": 0.2072,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.43707671761512756,
+      "learning_rate": 2e-05,
+      "loss": 1.7812,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.1235876083374023,
+      "learning_rate": 2e-05,
+      "loss": 0.5426,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.10454016178846359,
+      "learning_rate": 2e-05,
+      "loss": 0.3795,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.1258776187896729,
+      "learning_rate": 2e-05,
+      "loss": 0.1479,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.4155058860778809,
+      "learning_rate": 2e-05,
+      "loss": 0.3084,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.3539073169231415,
+      "learning_rate": 2e-05,
+      "loss": 0.1655,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.3305696249008179,
+      "learning_rate": 2e-05,
+      "loss": 0.2958,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.2774284780025482,
+      "learning_rate": 2e-05,
+      "loss": 0.1842,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.6683800220489502,
+      "learning_rate": 2e-05,
+      "loss": 0.6587,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.36092549562454224,
+      "learning_rate": 2e-05,
+      "loss": 0.3554,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5264660366360576.0,
+      "train_loss": 0.6618465614318848,
+      "train_runtime": 199.071,
+      "train_samples_per_second": 2.009,
+      "train_steps_per_second": 0.502
+    }
+  ],
+  "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": 5264660366360576.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6022ae4659a11a1170113a1e56c7c94546c3888e43d97d2d12a9e5885267570c
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:243f0f9765404aca68817dabc40e8949739c6a2832dd1b30cdaa4b0b364eed91
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:815140967fd9c3e419e9c8acf514517f5518696e943620410cc23a42a0f6e1de
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819a9022aa005a5202fabab916d6a48ce2baa548d517f19665c7871aefe55e90
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48c29b18e0b6236c0fa39fbd069cd1e6a0abb6462879634f4b8a32b94c8c50f4
+size 778341034

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb270204c0d5c01b9ae55c6a0dd967ea385c33352dacd0fbb957f981d034fa34
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9551063dc775f6f75f41036694b4b70c60267f2c680c93568569428fef894af0
+size 778341034

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87b106ff5130a7a1c106d5f13f6f818631646adb5d10096bb078ca37a8333845
+size 778341034

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_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": 0.7360143065452576,
+      "learning_rate": 2e-05,
+      "loss": 0.2715,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.2964683175086975,
+      "learning_rate": 2e-05,
+      "loss": 0.2327,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.1277915984392166,
+      "learning_rate": 2e-05,
+      "loss": 0.0108,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.08108308166265488,
+      "learning_rate": 2e-05,
+      "loss": 0.076,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.009317649528384209,
+      "learning_rate": 2e-05,
+      "loss": 0.0054,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.1490423679351807,
+      "learning_rate": 2e-05,
+      "loss": 0.0842,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.7548104524612427,
+      "learning_rate": 2e-05,
+      "loss": 0.8254,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.007570192217826843,
+      "learning_rate": 2e-05,
+      "loss": 0.1302,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.07496156543493271,
+      "learning_rate": 2e-05,
+      "loss": 0.0063,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.03207743540406227,
+      "learning_rate": 2e-05,
+      "loss": 0.0034,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.9136055111885071,
+      "learning_rate": 2e-05,
+      "loss": 0.1465,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 12.220712661743164,
+      "learning_rate": 2e-05,
+      "loss": 1.1015,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.005785540211945772,
+      "learning_rate": 2e-05,
+      "loss": 0.0011,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.3816988170146942,
+      "learning_rate": 2e-05,
+      "loss": 0.06,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.02641678787767887,
+      "learning_rate": 2e-05,
+      "loss": 0.008,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.02070285752415657,
+      "learning_rate": 2e-05,
+      "loss": 0.0015,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.7145651578903198,
+      "learning_rate": 2e-05,
+      "loss": 0.07,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.238328456878662,
+      "learning_rate": 2e-05,
+      "loss": 0.036,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.4018346965312958,
+      "learning_rate": 2e-05,
+      "loss": 0.0139,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.11333867907524109,
+      "learning_rate": 2e-05,
+      "loss": 0.2545,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.5644049048423767,
+      "learning_rate": 2e-05,
+      "loss": 0.0408,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.17072898149490356,
+      "learning_rate": 2e-05,
+      "loss": 0.5839,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.009764144197106361,
+      "learning_rate": 2e-05,
+      "loss": 0.0056,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.1741126924753189,
+      "learning_rate": 2e-05,
+      "loss": 0.0106,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.09493707120418549,
+      "learning_rate": 2e-05,
+      "loss": 0.0041,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.07839623093605042,
+      "learning_rate": 2e-05,
+      "loss": 0.0078,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.007820292375981808,
+      "learning_rate": 2e-05,
+      "loss": 0.0013,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.46173766255378723,
+      "learning_rate": 2e-05,
+      "loss": 0.0382,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 7.137088298797607,
+      "learning_rate": 2e-05,
+      "loss": 1.1429,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5940173268318176,
+      "learning_rate": 2e-05,
+      "loss": 0.0647,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.040866173803806305,
+      "learning_rate": 2e-05,
+      "loss": 0.0035,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.010234386660158634,
+      "learning_rate": 2e-05,
+      "loss": 0.0019,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.847973108291626,
+      "learning_rate": 2e-05,
+      "loss": 0.5856,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.18223556876182556,
+      "learning_rate": 2e-05,
+      "loss": 0.0231,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.17391642928123474,
+      "learning_rate": 2e-05,
+      "loss": 0.0156,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.0007022529025562108,
+      "learning_rate": 2e-05,
+      "loss": 0.0022,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.07573020458221436,
+      "learning_rate": 2e-05,
+      "loss": 0.0131,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.8579408526420593,
+      "learning_rate": 2e-05,
+      "loss": 0.1139,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.10402293503284454,
+      "learning_rate": 2e-05,
+      "loss": 0.2166,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.8201993703842163,
+      "learning_rate": 2e-05,
+      "loss": 0.199,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.017804984003305435,
+      "learning_rate": 2e-05,
+      "loss": 0.002,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.07739057391881943,
+      "learning_rate": 2e-05,
+      "loss": 0.0153,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.024365084245800972,
+      "learning_rate": 2e-05,
+      "loss": 0.1982,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.020023249089717865,
+      "learning_rate": 2e-05,
+      "loss": 0.0034,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.4256666600704193,
+      "learning_rate": 2e-05,
+      "loss": 0.0573,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.002212060382589698,
+      "learning_rate": 2e-05,
+      "loss": 0.1752,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.17573536932468414,
+      "learning_rate": 2e-05,
+      "loss": 0.0257,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.7300965785980225,
+      "learning_rate": 2e-05,
+      "loss": 0.0318,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.01184467226266861,
+      "learning_rate": 2e-05,
+      "loss": 0.0084,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0024825653526932,
+      "learning_rate": 2e-05,
+      "loss": 0.0007,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5306664827748352.0,
+      "train_loss": 0.13863192200660707,
+      "train_runtime": 198.1536,
+      "train_samples_per_second": 2.019,
+      "train_steps_per_second": 0.505
+    }
+  ],
+  "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": 5306664827748352.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:886eb25665ee7cbdc4b7eaac7705de2df4074da6834b0acc8d87254bc5d30f51
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e5ac228a0abd3974e794710241e57f3533880f4f02da362cbffd2e9aaa283c
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3c99bc6f9f4873ec87b583acc7a7d6d4eda91fe452b88ae0b875d0b54c9fe2d
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b98c87151efd491550c2073eb69549916982ea2084f1ae31a57a59005bfb2de4
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3715690b3f68f0a64459123023df01a2b87c44f29466abe8c216755a67cc79e5
+size 778341034

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20abbeae79fc1b5404bd8a9d3683f79a28fde83c8d506c86c954fd533d184925
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb007a9010e5b2a08ca23e7cdc78a4bad4c53033d7a88dffc4d1149e62acd25
+size 778341034

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66852556ae03dc13b69d0cf6840c79ba88509e4a9298416e5bf55c618a6cb12
+size 778341034

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_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": 2.7820990085601807,
+      "learning_rate": 2e-05,
+      "loss": 0.9436,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.5394349098205566,
+      "learning_rate": 2e-05,
+      "loss": 0.586,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.6744922995567322,
+      "learning_rate": 2e-05,
+      "loss": 0.0724,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.854970693588257,
+      "learning_rate": 2e-05,
+      "loss": 0.3357,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.9946097135543823,
+      "learning_rate": 2e-05,
+      "loss": 0.24,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.7899529933929443,
+      "learning_rate": 2e-05,
+      "loss": 0.7613,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 6.388876438140869,
+      "learning_rate": 2e-05,
+      "loss": 1.2136,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.7646965980529785,
+      "learning_rate": 2e-05,
+      "loss": 0.7847,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.5144887566566467,
+      "learning_rate": 2e-05,
+      "loss": 0.3545,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.091771602630615,
+      "learning_rate": 2e-05,
+      "loss": 1.3558,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.5789737701416016,
+      "learning_rate": 2e-05,
+      "loss": 0.5201,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.9908242225646973,
+      "learning_rate": 2e-05,
+      "loss": 0.3306,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.9906637072563171,
+      "learning_rate": 2e-05,
+      "loss": 0.1251,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.419766664505005,
+      "learning_rate": 2e-05,
+      "loss": 0.9497,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.0049045085906982,
+      "learning_rate": 2e-05,
+      "loss": 1.617,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.5235016345977783,
+      "learning_rate": 2e-05,
+      "loss": 0.7302,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.045655727386475,
+      "learning_rate": 2e-05,
+      "loss": 1.3329,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.661603569984436,
+      "learning_rate": 2e-05,
+      "loss": 0.1179,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.7658913135528564,
+      "learning_rate": 2e-05,
+      "loss": 0.6136,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.4761198163032532,
+      "learning_rate": 2e-05,
+      "loss": 0.5293,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.7399206161499023,
+      "learning_rate": 2e-05,
+      "loss": 0.0578,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.876828908920288,
+      "learning_rate": 2e-05,
+      "loss": 0.3066,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.6885768175125122,
+      "learning_rate": 2e-05,
+      "loss": 0.3174,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.8192023038864136,
+      "learning_rate": 2e-05,
+      "loss": 0.2879,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.07490100711584091,
+      "learning_rate": 2e-05,
+      "loss": 0.2212,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.11679685115814209,
+      "learning_rate": 2e-05,
+      "loss": 0.4335,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.7333829402923584,
+      "learning_rate": 2e-05,
+      "loss": 0.8517,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.754225015640259,
+      "learning_rate": 2e-05,
+      "loss": 1.4939,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.8190817832946777,
+      "learning_rate": 2e-05,
+      "loss": 1.1906,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.2269262075424194,
+      "learning_rate": 2e-05,
+      "loss": 0.4379,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.6373017430305481,
+      "learning_rate": 2e-05,
+      "loss": 0.1766,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.8057060241699219,
+      "learning_rate": 2e-05,
+      "loss": 0.5919,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.8550773859024048,
+      "learning_rate": 2e-05,
+      "loss": 0.3959,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.2275999784469604,
+      "learning_rate": 2e-05,
+      "loss": 0.4892,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.5185688734054565,
+      "learning_rate": 2e-05,
+      "loss": 0.3365,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.8324384093284607,
+      "learning_rate": 2e-05,
+      "loss": 0.6932,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.1002087593078613,
+      "learning_rate": 2e-05,
+      "loss": 0.5546,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.6600869297981262,
+      "learning_rate": 2e-05,
+      "loss": 0.4065,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.651470422744751,
+      "learning_rate": 2e-05,
+      "loss": 0.4323,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.225136160850525,
+      "learning_rate": 2e-05,
+      "loss": 1.3342,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.6928401589393616,
+      "learning_rate": 2e-05,
+      "loss": 0.6781,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5778830647468567,
+      "learning_rate": 2e-05,
+      "loss": 0.4015,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.666121006011963,
+      "learning_rate": 2e-05,
+      "loss": 0.9837,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.39838707447052,
+      "learning_rate": 2e-05,
+      "loss": 0.181,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.752300977706909,
+      "learning_rate": 2e-05,
+      "loss": 0.2926,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.3149762153625488,
+      "learning_rate": 2e-05,
+      "loss": 0.8986,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.1806201934814453,
+      "learning_rate": 2e-05,
+      "loss": 0.6732,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.5404461026191711,
+      "learning_rate": 2e-05,
+      "loss": 0.65,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.236466884613037,
+      "learning_rate": 2e-05,
+      "loss": 0.4907,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.8161308765411377,
+      "learning_rate": 2e-05,
+      "loss": 0.7615,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5200945432494080.0,
+      "train_loss": 0.6106836557388305,
+      "train_runtime": 197.7531,
+      "train_samples_per_second": 2.023,
+      "train_steps_per_second": 0.506
+    }
+  ],
+  "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_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a924635a5b76cbb5be392d72a1294ac13869b33002eff61683f3bd2c1c882da2
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd0fb97c922a6004b6c82cfd0b55987cb7c9a81ba9db0380c64239964f7dfd32
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e18abce138a7431c8803828f52c9819bfe211f3c5978216847d4be33c355e69
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0480348c40411a3b73c75e6c0325d3e643da504a0c9e15a6d6848ce498c93eb7
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4e1c95d2ff10340593386f39aaa5f25c0dea6b15de52d1e8705c75e08afd85
+size 778341034

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f3dbd2ab23f35b0ef2e12dd36b09493753bb7e77de6c62147b99aa1be1032cd
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b94bd7a8a35ca7a6c482d19d548afde224717848a3c05f56742a571f0125f1
+size 778341034

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea191fafb514bbb05bd4e487d069c9cd3b688468088283e5e93d13ac7a574f35
+size 778341034

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_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": 10.930863380432129,
+      "learning_rate": 2e-05,
+      "loss": 1.6507,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.929012298583984,
+      "learning_rate": 2e-05,
+      "loss": 3.0733,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.590864896774292,
+      "learning_rate": 2e-05,
+      "loss": 1.0931,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.397353172302246,
+      "learning_rate": 2e-05,
+      "loss": 1.1,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.288862228393555,
+      "learning_rate": 2e-05,
+      "loss": 0.5711,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.7472829818725586,
+      "learning_rate": 2e-05,
+      "loss": 1.6572,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.885960340499878,
+      "learning_rate": 2e-05,
+      "loss": 0.7,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 6.131839275360107,
+      "learning_rate": 2e-05,
+      "loss": 0.9751,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 4.516921520233154,
+      "learning_rate": 2e-05,
+      "loss": 1.5208,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.126148223876953,
+      "learning_rate": 2e-05,
+      "loss": 1.3799,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.76863169670105,
+      "learning_rate": 2e-05,
+      "loss": 0.3688,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.348143458366394,
+      "learning_rate": 2e-05,
+      "loss": 0.4706,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.4673678874969482,
+      "learning_rate": 2e-05,
+      "loss": 0.7827,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.895928859710693,
+      "learning_rate": 2e-05,
+      "loss": 1.3299,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.4925365447998047,
+      "learning_rate": 2e-05,
+      "loss": 0.7627,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 6.011823654174805,
+      "learning_rate": 2e-05,
+      "loss": 1.5433,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.3401705026626587,
+      "learning_rate": 2e-05,
+      "loss": 0.8334,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 6.880156993865967,
+      "learning_rate": 2e-05,
+      "loss": 1.525,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.098840594291687,
+      "learning_rate": 2e-05,
+      "loss": 1.142,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.713680744171143,
+      "learning_rate": 2e-05,
+      "loss": 0.5681,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.662692546844482,
+      "learning_rate": 2e-05,
+      "loss": 1.9439,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 9.783991813659668,
+      "learning_rate": 2e-05,
+      "loss": 2.0982,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.130922317504883,
+      "learning_rate": 2e-05,
+      "loss": 1.0598,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.703055500984192,
+      "learning_rate": 2e-05,
+      "loss": 0.4514,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7805418968200684,
+      "learning_rate": 2e-05,
+      "loss": 1.1067,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.3128750324249268,
+      "learning_rate": 2e-05,
+      "loss": 0.3608,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.0405678749084473,
+      "learning_rate": 2e-05,
+      "loss": 0.9832,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.436537027359009,
+      "learning_rate": 2e-05,
+      "loss": 1.0532,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.396934747695923,
+      "learning_rate": 2e-05,
+      "loss": 1.4396,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.4227089881896973,
+      "learning_rate": 2e-05,
+      "loss": 1.1572,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.0701757669448853,
+      "learning_rate": 2e-05,
+      "loss": 0.5118,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.405320405960083,
+      "learning_rate": 2e-05,
+      "loss": 1.3809,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.297457695007324,
+      "learning_rate": 2e-05,
+      "loss": 0.8793,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 6.075654029846191,
+      "learning_rate": 2e-05,
+      "loss": 0.7679,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.6562526226043701,
+      "learning_rate": 2e-05,
+      "loss": 1.1942,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.7227914333343506,
+      "learning_rate": 2e-05,
+      "loss": 1.3111,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.8359243869781494,
+      "learning_rate": 2e-05,
+      "loss": 1.1813,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.5864817500114441,
+      "learning_rate": 2e-05,
+      "loss": 0.4636,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.185802459716797,
+      "learning_rate": 2e-05,
+      "loss": 0.9803,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.9854297041893005,
+      "learning_rate": 2e-05,
+      "loss": 0.6373,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.092267394065857,
+      "learning_rate": 2e-05,
+      "loss": 1.3163,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.7934210300445557,
+      "learning_rate": 2e-05,
+      "loss": 0.3073,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.9273383617401123,
+      "learning_rate": 2e-05,
+      "loss": 1.149,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.9544419646263123,
+      "learning_rate": 2e-05,
+      "loss": 2.3232,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.9544155597686768,
+      "learning_rate": 2e-05,
+      "loss": 1.5575,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.278726100921631,
+      "learning_rate": 2e-05,
+      "loss": 1.2604,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.9203688502311707,
+      "learning_rate": 2e-05,
+      "loss": 0.9193,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.1436952352523804,
+      "learning_rate": 2e-05,
+      "loss": 1.1761,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.3480257987976074,
+      "learning_rate": 2e-05,
+      "loss": 0.7385,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9458126425743103,
+      "learning_rate": 2e-05,
+      "loss": 0.3745,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5379385225904128.0,
+      "train_loss": 1.1026222538948058,
+      "train_runtime": 196.9701,
+      "train_samples_per_second": 2.031,
+      "train_steps_per_second": 0.508
+    }
+  ],
+  "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": 5379385225904128.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc61a1fa3ad35c1867f623c04414aed9fe2734d51a58996e7bd27d9f7693304
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d325e7a85c3a7a717e49c50280dc6684e4bde308ea6c101a50b469a9f789c290
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80bbca4e9aec8bb0ec14488774a796623ce127ff3cded382b395fe3ad066e73b
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0f7280bf69624478d87e53862b4da8da6e5533abe8252997066c6f2fa4aaf2c
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2abaa4d0ffa93a38e2ac514105322f7a5f19cbf6890b05fa2f8ac491b1c1a1b9
+size 778341034

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a0605ffb7a338872b8f55b33376c4ebc82d1d61ac0b511daf20d944cacde37
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06eb849b86ead067e03bda1d14ae7ad23a0760ef9e96842f7b1d95bea2acb6bb
+size 778341034

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6883d63a18ba4bc7ed6114a78d6b0a78f365aa062eaa1f4da5b4201122340a40
+size 778341034

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_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": 1.357893466949463,
+      "learning_rate": 2e-05,
+      "loss": 0.67,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.940321922302246,
+      "learning_rate": 2e-05,
+      "loss": 1.2823,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.14263916015625,
+      "learning_rate": 2e-05,
+      "loss": 0.9153,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.899571418762207,
+      "learning_rate": 2e-05,
+      "loss": 1.6568,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.9886393547058105,
+      "learning_rate": 2e-05,
+      "loss": 0.7204,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.842442750930786,
+      "learning_rate": 2e-05,
+      "loss": 1.1273,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.7368173599243164,
+      "learning_rate": 2e-05,
+      "loss": 0.949,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.2248767614364624,
+      "learning_rate": 2e-05,
+      "loss": 0.9882,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.9518104791641235,
+      "learning_rate": 2e-05,
+      "loss": 1.3088,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.9377427101135254,
+      "learning_rate": 2e-05,
+      "loss": 0.7789,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.3922064304351807,
+      "learning_rate": 2e-05,
+      "loss": 0.826,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.965751051902771,
+      "learning_rate": 2e-05,
+      "loss": 0.3058,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.8510717153549194,
+      "learning_rate": 2e-05,
+      "loss": 0.5588,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.8657582998275757,
+      "learning_rate": 2e-05,
+      "loss": 0.7137,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.801306128501892,
+      "learning_rate": 2e-05,
+      "loss": 1.0616,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.223435401916504,
+      "learning_rate": 2e-05,
+      "loss": 1.1613,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.837424635887146,
+      "learning_rate": 2e-05,
+      "loss": 0.9025,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.0163207054138184,
+      "learning_rate": 2e-05,
+      "loss": 1.1511,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.6024384498596191,
+      "learning_rate": 2e-05,
+      "loss": 0.7246,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.3062243461608887,
+      "learning_rate": 2e-05,
+      "loss": 0.6299,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.6857709884643555,
+      "learning_rate": 2e-05,
+      "loss": 0.8251,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.9923744201660156,
+      "learning_rate": 2e-05,
+      "loss": 1.1456,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.9148615598678589,
+      "learning_rate": 2e-05,
+      "loss": 0.3444,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.7506935596466064,
+      "learning_rate": 2e-05,
+      "loss": 0.9631,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.5837172269821167,
+      "learning_rate": 2e-05,
+      "loss": 0.3699,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.410757303237915,
+      "learning_rate": 2e-05,
+      "loss": 1.6722,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.7994933128356934,
+      "learning_rate": 2e-05,
+      "loss": 0.7047,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.2838125228881836,
+      "learning_rate": 2e-05,
+      "loss": 0.4519,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.2547208070755005,
+      "learning_rate": 2e-05,
+      "loss": 0.7873,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.45123398303985596,
+      "learning_rate": 2e-05,
+      "loss": 0.3131,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.6631761193275452,
+      "learning_rate": 2e-05,
+      "loss": 0.6959,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.915126323699951,
+      "learning_rate": 2e-05,
+      "loss": 1.0301,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.2797094583511353,
+      "learning_rate": 2e-05,
+      "loss": 0.2926,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.2585256099700928,
+      "learning_rate": 2e-05,
+      "loss": 0.8461,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.5185467004776,
+      "learning_rate": 2e-05,
+      "loss": 1.153,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.5300116539001465,
+      "learning_rate": 2e-05,
+      "loss": 0.6098,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.5738203525543213,
+      "learning_rate": 2e-05,
+      "loss": 0.9635,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.5161136984825134,
+      "learning_rate": 2e-05,
+      "loss": 0.1756,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.5103969573974609,
+      "learning_rate": 2e-05,
+      "loss": 0.2725,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 7.511044025421143,
+      "learning_rate": 2e-05,
+      "loss": 1.5605,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.57822847366333,
+      "learning_rate": 2e-05,
+      "loss": 1.744,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 2.341519355773926,
+      "learning_rate": 2e-05,
+      "loss": 0.8056,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.882524847984314,
+      "learning_rate": 2e-05,
+      "loss": 0.9453,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.7270419597625732,
+      "learning_rate": 2e-05,
+      "loss": 1.269,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.9677159786224365,
+      "learning_rate": 2e-05,
+      "loss": 0.6482,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.6180154085159302,
+      "learning_rate": 2e-05,
+      "loss": 0.8784,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.7344378232955933,
+      "learning_rate": 2e-05,
+      "loss": 0.4053,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.8181297779083252,
+      "learning_rate": 2e-05,
+      "loss": 0.6965,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.3030812740325928,
+      "learning_rate": 2e-05,
+      "loss": 0.5235,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.348716139793396,
+      "learning_rate": 2e-05,
+      "loss": 0.6765,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 6020085697216512.0,
+      "train_loss": 0.8440377378463745,
+      "train_runtime": 199.4757,
+      "train_samples_per_second": 2.005,
+      "train_steps_per_second": 0.501
+    }
+  ],
+  "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_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca4fa03a0502aff4817e12605f19597321b107149c52e04c9db1a8a031fb68e
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77df6aaa259b373ce97151fe98af91309ace52c53f89a9607e1f4a5af2fe56f0
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a191fdd6da6dc58e2381afc9c81c7ab672c77214454612cf8d4cd3b7176793d
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bcc241034c804a813756aa09f643b01c20fa338b795f0eac331c37a313a42af
+size 778341886

client_states_feddpa_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a3de53bcf639438abda8678e5d6df5afd28c9b8b5912edc4963b031d6b7de2
+size 778341034