Upload folder using huggingface_hub

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dac7b6bce352f6c975f0f5656beef509afdab382bc722b932595b99bf50090c
+size 180440142

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dcab448066a13c1f03938d764d26279e454333c8dc6923a707bf1cf0dc2f833
+size 180440142

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c7d3453a23565008a42c4dccd1749cabfbf9ec23ea912014a4d4209943520d8
+size 180440142

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56c05502646862715dc27c5584e6a3e60191712121cfc7f969a9461170eadbe9
+size 180440142

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:513aba8649167d639d7183da473d0eb85bdf76970b10f7d12d4d47d0bfa8f4f6
+size 180439850

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:269ac2ed7bfedd0bec7453eff915764e747247d28030f63f1ac848a7ed018c9f
+size 180440142

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027f4e35e64efb5d494d33d46953933ce8bdb4a518cb33cecc238cfdbe8c1b84
+size 180439850

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72abb5953c3d401fe841ebfb21c15bdd99db0975371868aa0aff2121d5510e50
+size 180439850

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/0_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.185389757156372,
+      "learning_rate": 2e-05,
+      "loss": 0.5313,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.462697148323059,
+      "learning_rate": 2e-05,
+      "loss": 2.1023,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.06314225494861603,
+      "learning_rate": 2e-05,
+      "loss": 0.0065,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 8.08350658416748,
+      "learning_rate": 2e-05,
+      "loss": 0.7299,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.8942979574203491,
+      "learning_rate": 2e-05,
+      "loss": 0.4338,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 7.397281646728516,
+      "learning_rate": 2e-05,
+      "loss": 0.9851,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.0156924724578857,
+      "learning_rate": 2e-05,
+      "loss": 0.1971,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 9.138948440551758,
+      "learning_rate": 2e-05,
+      "loss": 0.6213,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 8.548439979553223,
+      "learning_rate": 2e-05,
+      "loss": 0.8961,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.227810859680176,
+      "learning_rate": 2e-05,
+      "loss": 1.4456,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 4.551537990570068,
+      "learning_rate": 2e-05,
+      "loss": 1.636,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 6.477214336395264,
+      "learning_rate": 2e-05,
+      "loss": 1.0221,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.2676788866519928,
+      "learning_rate": 2e-05,
+      "loss": 0.2403,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 14.42641830444336,
+      "learning_rate": 2e-05,
+      "loss": 1.108,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.8010652661323547,
+      "learning_rate": 2e-05,
+      "loss": 0.3901,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 9.867847442626953,
+      "learning_rate": 2e-05,
+      "loss": 1.073,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.5489710569381714,
+      "learning_rate": 2e-05,
+      "loss": 0.1765,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.8706305027008057,
+      "learning_rate": 2e-05,
+      "loss": 0.8621,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.2662458419799805,
+      "learning_rate": 2e-05,
+      "loss": 0.1863,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 10.825136184692383,
+      "learning_rate": 2e-05,
+      "loss": 1.1348,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.9670252799987793,
+      "learning_rate": 2e-05,
+      "loss": 0.6283,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.5218558311462402,
+      "learning_rate": 2e-05,
+      "loss": 0.8367,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.4162901639938354,
+      "learning_rate": 2e-05,
+      "loss": 0.4749,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.961083889007568,
+      "learning_rate": 2e-05,
+      "loss": 0.3601,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 7.117353439331055,
+      "learning_rate": 2e-05,
+      "loss": 0.6846,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 6.346409797668457,
+      "learning_rate": 2e-05,
+      "loss": 1.0359,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.3846776485443115,
+      "learning_rate": 2e-05,
+      "loss": 0.2492,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.2677325904369354,
+      "learning_rate": 2e-05,
+      "loss": 1.0758,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.839362621307373,
+      "learning_rate": 2e-05,
+      "loss": 0.7528,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 15.682966232299805,
+      "learning_rate": 2e-05,
+      "loss": 0.9388,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 9.203821182250977,
+      "learning_rate": 2e-05,
+      "loss": 1.9389,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 10.753218650817871,
+      "learning_rate": 2e-05,
+      "loss": 1.8481,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.960542678833008,
+      "learning_rate": 2e-05,
+      "loss": 0.9183,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.8610289096832275,
+      "learning_rate": 2e-05,
+      "loss": 0.4862,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.5907980799674988,
+      "learning_rate": 2e-05,
+      "loss": 0.0323,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.849497318267822,
+      "learning_rate": 2e-05,
+      "loss": 0.5046,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.7647833824157715,
+      "learning_rate": 2e-05,
+      "loss": 0.9464,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.2242050170898438,
+      "learning_rate": 2e-05,
+      "loss": 1.0414,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.43988850712776184,
+      "learning_rate": 2e-05,
+      "loss": 0.0393,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 7.581626892089844,
+      "learning_rate": 2e-05,
+      "loss": 0.914,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 8.071428298950195,
+      "learning_rate": 2e-05,
+      "loss": 0.5456,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 9.775481224060059,
+      "learning_rate": 2e-05,
+      "loss": 1.1202,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.938329219818115,
+      "learning_rate": 2e-05,
+      "loss": 0.4349,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.7860143184661865,
+      "learning_rate": 2e-05,
+      "loss": 0.3314,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.644363522529602,
+      "learning_rate": 2e-05,
+      "loss": 0.2175,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.6504173278808594,
+      "learning_rate": 2e-05,
+      "loss": 0.2242,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.1692447662353516,
+      "learning_rate": 2e-05,
+      "loss": 0.3253,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 7.509362697601318,
+      "learning_rate": 2e-05,
+      "loss": 0.9171,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.7557180523872375,
+      "learning_rate": 2e-05,
+      "loss": 0.0612,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4876616597175598,
+      "learning_rate": 2e-05,
+      "loss": 0.054,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2050008522162176.0,
+      "train_loss": 0.714327917098999,
+      "train_runtime": 101.3941,
+      "train_samples_per_second": 3.945,
+      "train_steps_per_second": 0.986
+    }
+  ],
+  "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": 2050008522162176.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d4c4d89bdb3f350e2518ed150ec2a0b791fe39b81f2e0f62a2f5cc4ba7666e
+size 180440142

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459f79aed03d2ed8311a89bfc1543de0307289da1e03e5b61b17859497bd7b94
+size 180440142

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d025fa1d64446f3b8d8480477c7c2366e1dc17c670e582008dc6b3d3ebdae8eb
+size 180440142

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88310f262c4da1aa92e63114b5417a63139a526b4adffa1eb7585320a682b4cf
+size 180440142

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6940d88337600557f8ef5224d94bee18273ca815983d5753451f7393f3ae082
+size 180439850

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f2718fac6eeee5d8a92ba8245e122b5832a37a9c8d03f18654502259c52e93e
+size 180440142

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c5ed776c37af82da7e7c990f70a018ca7465e1c03abbf9f8e50c2450e301235
+size 180439850

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e310e436e59b58a8b51ebb8bfeeadcd4c23607edc7a36a702c0ef8a1d8775b51
+size 180439850

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/1_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.0033269652631133795,
+      "learning_rate": 2e-05,
+      "loss": 0.0085,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.041157741099596024,
+      "learning_rate": 2e-05,
+      "loss": 0.0008,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.9592494368553162,
+      "learning_rate": 2e-05,
+      "loss": 0.0262,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.6419932246208191,
+      "learning_rate": 2e-05,
+      "loss": 0.0282,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.6463303565979,
+      "learning_rate": 2e-05,
+      "loss": 0.6913,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.000999588519334793,
+      "learning_rate": 2e-05,
+      "loss": 0.0004,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.2222857028245926,
+      "learning_rate": 2e-05,
+      "loss": 0.0397,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.16892485320568085,
+      "learning_rate": 2e-05,
+      "loss": 0.0769,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.009978498332202435,
+      "learning_rate": 2e-05,
+      "loss": 0.0012,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.3538615703582764,
+      "learning_rate": 2e-05,
+      "loss": 0.4112,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.0049792262725532055,
+      "learning_rate": 2e-05,
+      "loss": 0.0009,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.9717739820480347,
+      "learning_rate": 2e-05,
+      "loss": 0.0344,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.007954389788210392,
+      "learning_rate": 2e-05,
+      "loss": 0.0886,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.15055210888385773,
+      "learning_rate": 2e-05,
+      "loss": 0.982,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.05759048089385033,
+      "learning_rate": 2e-05,
+      "loss": 0.5327,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.051013048738241196,
+      "learning_rate": 2e-05,
+      "loss": 0.0034,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.027761617675423622,
+      "learning_rate": 2e-05,
+      "loss": 0.0036,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.010388568975031376,
+      "learning_rate": 2e-05,
+      "loss": 0.0009,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.01740710809826851,
+      "learning_rate": 2e-05,
+      "loss": 0.2172,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.017691656947135925,
+      "learning_rate": 2e-05,
+      "loss": 0.0017,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.31259411573410034,
+      "learning_rate": 2e-05,
+      "loss": 0.0131,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.02895217575132847,
+      "learning_rate": 2e-05,
+      "loss": 0.0063,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.009466350078582764,
+      "learning_rate": 2e-05,
+      "loss": 0.0024,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.41093146800994873,
+      "learning_rate": 2e-05,
+      "loss": 0.018,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.006547864992171526,
+      "learning_rate": 2e-05,
+      "loss": 0.0008,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.009852895513176918,
+      "learning_rate": 2e-05,
+      "loss": 0.0273,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.0796719342470169,
+      "learning_rate": 2e-05,
+      "loss": 0.0066,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.17664939165115356,
+      "learning_rate": 2e-05,
+      "loss": 0.0089,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.03962412849068642,
+      "learning_rate": 2e-05,
+      "loss": 0.0023,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.23390346765518188,
+      "learning_rate": 2e-05,
+      "loss": 0.0101,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.035884492099285126,
+      "learning_rate": 2e-05,
+      "loss": 0.0022,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.006772290449589491,
+      "learning_rate": 2e-05,
+      "loss": 0.0014,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.13574518263339996,
+      "learning_rate": 2e-05,
+      "loss": 0.0098,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 17.729595184326172,
+      "learning_rate": 2e-05,
+      "loss": 1.8484,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.05980616807937622,
+      "learning_rate": 2e-05,
+      "loss": 0.0085,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.1025233268737793,
+      "learning_rate": 2e-05,
+      "loss": 1.0268,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.00824617501348257,
+      "learning_rate": 2e-05,
+      "loss": 0.0033,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.188517093658447,
+      "learning_rate": 2e-05,
+      "loss": 0.38,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.014042158611118793,
+      "learning_rate": 2e-05,
+      "loss": 0.0017,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.04890606924891472,
+      "learning_rate": 2e-05,
+      "loss": 0.1103,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.023772185668349266,
+      "learning_rate": 2e-05,
+      "loss": 0.0018,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.432652473449707,
+      "learning_rate": 2e-05,
+      "loss": 0.3927,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.6805059909820557,
+      "learning_rate": 2e-05,
+      "loss": 0.0469,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.975512146949768,
+      "learning_rate": 2e-05,
+      "loss": 0.2212,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.9377481937408447,
+      "learning_rate": 2e-05,
+      "loss": 0.4155,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.2486044466495514,
+      "learning_rate": 2e-05,
+      "loss": 0.0152,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.015230941586196423,
+      "learning_rate": 2e-05,
+      "loss": 0.0133,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.1053871437907219,
+      "learning_rate": 2e-05,
+      "loss": 0.0693,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.023564128205180168,
+      "learning_rate": 2e-05,
+      "loss": 0.0031,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.015611840412020683,
+      "learning_rate": 2e-05,
+      "loss": 0.025,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2066355427737600.0,
+      "train_loss": 0.1568439483642578,
+      "train_runtime": 99.9893,
+      "train_samples_per_second": 4.0,
+      "train_steps_per_second": 1.0
+    }
+  ],
+  "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": 2066355427737600.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de2a14f0034bf1a514488a2a3c3dd156f6cd9486176464301efb43f273eeaa69
+size 389170582

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2995ff2139b05e73dd687bf519c8a8de7d3e2ada63a7ff7c04c34ae1853fd2
+size 389170582

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b71a7bf9a66fe1dfe1482aa1d0d500b7ebfd0950d854e6159f8c7f469e5a0c2
+size 389170582

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7db80190dcd29b88d459a63955e96ddfe0d6783a855674d557761b674e3e07e
+size 389170582

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b28230a69be1080fce36c0aa88635abdbef0bee9461b7e7f17386ee963856aa
+size 389170122

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fc05025bf8c8f9ceebe415e6840941b0c064ff4afe2125e74ae593b3c6d5b48
+size 389170582

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49fc6d328f225665d42987b8a4bba2cd04fdf3ee8634fe9e9699f73ffb9ea04e
+size 389170122

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3acfe893b0c739503151ea961300cc6c25f8f270719d005c1737ae4d31e60eca
+size 389170122

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/2_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.806666374206543,
+      "learning_rate": 2e-05,
+      "loss": 0.3127,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.772969961166382,
+      "learning_rate": 2e-05,
+      "loss": 0.6935,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 5.492923736572266,
+      "learning_rate": 2e-05,
+      "loss": 1.7379,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.6056976318359375,
+      "learning_rate": 2e-05,
+      "loss": 0.8991,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.7061705589294434,
+      "learning_rate": 2e-05,
+      "loss": 0.5627,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.2979965209960938,
+      "learning_rate": 2e-05,
+      "loss": 0.3267,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.3533953428268433,
+      "learning_rate": 2e-05,
+      "loss": 0.3217,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.877424716949463,
+      "learning_rate": 2e-05,
+      "loss": 0.2856,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.0798438787460327,
+      "learning_rate": 2e-05,
+      "loss": 0.4367,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.245316982269287,
+      "learning_rate": 2e-05,
+      "loss": 0.5249,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.5087791681289673,
+      "learning_rate": 2e-05,
+      "loss": 0.3091,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.263746500015259,
+      "learning_rate": 2e-05,
+      "loss": 1.0143,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.557353138923645,
+      "learning_rate": 2e-05,
+      "loss": 0.1558,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.3562333583831787,
+      "learning_rate": 2e-05,
+      "loss": 0.55,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.261547088623047,
+      "learning_rate": 2e-05,
+      "loss": 0.8929,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.1925289630889893,
+      "learning_rate": 2e-05,
+      "loss": 0.4653,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.4827537536621094,
+      "learning_rate": 2e-05,
+      "loss": 0.4744,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.6158387660980225,
+      "learning_rate": 2e-05,
+      "loss": 0.1999,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.348236560821533,
+      "learning_rate": 2e-05,
+      "loss": 0.5648,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5702676177024841,
+      "learning_rate": 2e-05,
+      "loss": 0.5624,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.970848321914673,
+      "learning_rate": 2e-05,
+      "loss": 1.4146,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.26162052154541,
+      "learning_rate": 2e-05,
+      "loss": 1.5653,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 5.289398193359375,
+      "learning_rate": 2e-05,
+      "loss": 1.6653,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.84953498840332,
+      "learning_rate": 2e-05,
+      "loss": 0.9846,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.963735103607178,
+      "learning_rate": 2e-05,
+      "loss": 1.5258,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.125373601913452,
+      "learning_rate": 2e-05,
+      "loss": 0.5031,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.5217068195343018,
+      "learning_rate": 2e-05,
+      "loss": 0.3672,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.5323041677474976,
+      "learning_rate": 2e-05,
+      "loss": 0.6326,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.9375790357589722,
+      "learning_rate": 2e-05,
+      "loss": 0.236,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.5400359630584717,
+      "learning_rate": 2e-05,
+      "loss": 1.02,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.9115395545959473,
+      "learning_rate": 2e-05,
+      "loss": 0.3253,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.119795322418213,
+      "learning_rate": 2e-05,
+      "loss": 0.7132,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.27884840965271,
+      "learning_rate": 2e-05,
+      "loss": 1.2836,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.7405014038085938,
+      "learning_rate": 2e-05,
+      "loss": 0.3597,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.0723375082015991,
+      "learning_rate": 2e-05,
+      "loss": 1.1792,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.9426579475402832,
+      "learning_rate": 2e-05,
+      "loss": 0.2904,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.871702194213867,
+      "learning_rate": 2e-05,
+      "loss": 1.4492,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.5469585657119751,
+      "learning_rate": 2e-05,
+      "loss": 0.1543,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 5.215576648712158,
+      "learning_rate": 2e-05,
+      "loss": 1.2247,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.197208881378174,
+      "learning_rate": 2e-05,
+      "loss": 0.7877,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.622382402420044,
+      "learning_rate": 2e-05,
+      "loss": 0.6431,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.4372755289077759,
+      "learning_rate": 2e-05,
+      "loss": 0.543,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.7911620140075684,
+      "learning_rate": 2e-05,
+      "loss": 0.3779,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.9083788394927979,
+      "learning_rate": 2e-05,
+      "loss": 0.315,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.12868903577327728,
+      "learning_rate": 2e-05,
+      "loss": 0.1472,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.37657198309898376,
+      "learning_rate": 2e-05,
+      "loss": 0.344,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.369081735610962,
+      "learning_rate": 2e-05,
+      "loss": 0.9474,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.9848467707633972,
+      "learning_rate": 2e-05,
+      "loss": 0.1981,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.4741188883781433,
+      "learning_rate": 2e-05,
+      "loss": 0.1882,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.421746730804443,
+      "learning_rate": 2e-05,
+      "loss": 1.1065,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 4911038537400320.0,
+      "train_loss": 0.6756564712524414,
+      "train_runtime": 161.515,
+      "train_samples_per_second": 2.477,
+      "train_steps_per_second": 0.619
+    }
+  ],
+  "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": 4911038537400320.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:925e02bab65a8c21b13961b7c1c2504de2854c66f54cb1db5c5db095445d9dfb
+size 180440142

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dfe2459c0ed9a99de2b5da1cc8c1a3d564a7665992fe018017fad9a0eea2b55
+size 180440142

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a21077d8411c069fc73ccf68c83a8476cf01f5314a1c6eba65d534185182233
+size 180440142

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f92d68232d50118aa91f6cd58d30ddcbc66f1a3de7a10fb77f8a0c9b3c5bc168
+size 180440142

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f59030679d64456e72c0ef422af79b028f254ee3a6b11793905566e90314704
+size 180439850

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:133dc402d125ddaafc27f06bc1e6410077a9202486323d7f05f062dee2fd8afe
+size 180440142

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb1c71ea609345555a1aa2ed7e222ce23f61a50458542ffa87292b16afd3cda
+size 180439850

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62cd085080e075ce63299e262c2c23ff7573f2d1ac1354c18f23e91751e8647
+size 180439850

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/3_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.710101127624512,
+      "learning_rate": 2e-05,
+      "loss": 1.4172,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.9397523403167725,
+      "learning_rate": 2e-05,
+      "loss": 0.8797,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.1615402698516846,
+      "learning_rate": 2e-05,
+      "loss": 1.0671,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 13.820159912109375,
+      "learning_rate": 2e-05,
+      "loss": 3.6283,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 11.3993501663208,
+      "learning_rate": 2e-05,
+      "loss": 2.2113,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 13.748973846435547,
+      "learning_rate": 2e-05,
+      "loss": 2.2509,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 10.254955291748047,
+      "learning_rate": 2e-05,
+      "loss": 1.3235,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.2683303356170654,
+      "learning_rate": 2e-05,
+      "loss": 0.3648,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 7.850968837738037,
+      "learning_rate": 2e-05,
+      "loss": 1.1944,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.817758560180664,
+      "learning_rate": 2e-05,
+      "loss": 1.5678,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.871739625930786,
+      "learning_rate": 2e-05,
+      "loss": 1.3073,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 8.361922264099121,
+      "learning_rate": 2e-05,
+      "loss": 0.9962,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.391210079193115,
+      "learning_rate": 2e-05,
+      "loss": 1.3205,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 6.039274215698242,
+      "learning_rate": 2e-05,
+      "loss": 1.9638,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.7958240509033203,
+      "learning_rate": 2e-05,
+      "loss": 0.46,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 7.391857147216797,
+      "learning_rate": 2e-05,
+      "loss": 1.1388,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 8.654966354370117,
+      "learning_rate": 2e-05,
+      "loss": 1.5172,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 10.035390853881836,
+      "learning_rate": 2e-05,
+      "loss": 1.7336,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.6513237953186035,
+      "learning_rate": 2e-05,
+      "loss": 1.2339,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.69884991645813,
+      "learning_rate": 2e-05,
+      "loss": 0.4367,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.5067331790924072,
+      "learning_rate": 2e-05,
+      "loss": 0.7892,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 8.914396286010742,
+      "learning_rate": 2e-05,
+      "loss": 1.5515,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 6.865166187286377,
+      "learning_rate": 2e-05,
+      "loss": 1.689,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.9471137523651123,
+      "learning_rate": 2e-05,
+      "loss": 0.9443,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.263576030731201,
+      "learning_rate": 2e-05,
+      "loss": 0.3431,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.667490243911743,
+      "learning_rate": 2e-05,
+      "loss": 1.6956,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 10.96878433227539,
+      "learning_rate": 2e-05,
+      "loss": 1.092,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.746389865875244,
+      "learning_rate": 2e-05,
+      "loss": 0.7459,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 6.84367561340332,
+      "learning_rate": 2e-05,
+      "loss": 0.8944,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.7791221141815186,
+      "learning_rate": 2e-05,
+      "loss": 1.3167,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 4.828078746795654,
+      "learning_rate": 2e-05,
+      "loss": 1.8402,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 13.462433815002441,
+      "learning_rate": 2e-05,
+      "loss": 1.1954,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 9.061487197875977,
+      "learning_rate": 2e-05,
+      "loss": 1.31,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.7035795450210571,
+      "learning_rate": 2e-05,
+      "loss": 0.6877,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 7.510168075561523,
+      "learning_rate": 2e-05,
+      "loss": 1.5226,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.2935638427734375,
+      "learning_rate": 2e-05,
+      "loss": 1.5661,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 4.344234466552734,
+      "learning_rate": 2e-05,
+      "loss": 1.6382,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.743943691253662,
+      "learning_rate": 2e-05,
+      "loss": 0.713,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 8.068772315979004,
+      "learning_rate": 2e-05,
+      "loss": 1.1778,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.1857481002807617,
+      "learning_rate": 2e-05,
+      "loss": 0.9007,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 5.7237138748168945,
+      "learning_rate": 2e-05,
+      "loss": 2.0638,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 6.149637699127197,
+      "learning_rate": 2e-05,
+      "loss": 0.9916,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.0919957160949707,
+      "learning_rate": 2e-05,
+      "loss": 0.6464,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.3683154582977295,
+      "learning_rate": 2e-05,
+      "loss": 0.6144,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.998460292816162,
+      "learning_rate": 2e-05,
+      "loss": 0.8671,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.805094003677368,
+      "learning_rate": 2e-05,
+      "loss": 0.6894,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.4422361850738525,
+      "learning_rate": 2e-05,
+      "loss": 0.3568,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.961075782775879,
+      "learning_rate": 2e-05,
+      "loss": 0.8177,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 9.63961124420166,
+      "learning_rate": 2e-05,
+      "loss": 2.5556,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.2371578216552734,
+      "learning_rate": 2e-05,
+      "loss": 0.4797,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2094816317931520.0,
+      "train_loss": 1.2341706466674804,
+      "train_runtime": 100.7881,
+      "train_samples_per_second": 3.969,
+      "train_steps_per_second": 0.992
+    }
+  ],
+  "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": 2094816317931520.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b7d2e033a4b3d1dd6203f1de7275223b49ea702986d1bcc4bc023f61efac5c
+size 389170582

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:448423352706cc1f24e4a54a1813344e0787aa887633b802cf0e89e39d7b71b4
+size 389170582

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb4840eadbd7ef1db67e9ceca295cc87f0fe1a605516db0cb6646e53aada077a
+size 389170582

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22187ed7cdb78ce527269fc7896018eb44dd8bd197e63cb13b6dd630c05aac58
+size 389170582

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a3056867ad1c4ca79975c0c9bace7ffb0bbb72c2de8042a61fdba76ee6983f
+size 389170122

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:491ed5be2cd16c68c92a753673103ac5a7d180f35c90e218b096fcd9390e8090
+size 389170582

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a8b283879be4d8ee9c79c7127666354510b854e5227bb598eb78c61238b9f4b
+size 389170122

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000d4f0e9c4b4d86561759eb13ba6397ea829bb5be2c694c51bacc84bfcb746f
+size 389170122

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/4_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.1811344623565674,
+      "learning_rate": 2e-05,
+      "loss": 0.9004,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.057499885559082,
+      "learning_rate": 2e-05,
+      "loss": 0.4477,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.4118136167526245,
+      "learning_rate": 2e-05,
+      "loss": 0.4494,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.3802590370178223,
+      "learning_rate": 2e-05,
+      "loss": 0.5171,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.8723020553588867,
+      "learning_rate": 2e-05,
+      "loss": 0.2846,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.808058738708496,
+      "learning_rate": 2e-05,
+      "loss": 0.7729,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.9369915127754211,
+      "learning_rate": 2e-05,
+      "loss": 0.4847,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.7796673774719238,
+      "learning_rate": 2e-05,
+      "loss": 0.7306,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.8881521224975586,
+      "learning_rate": 2e-05,
+      "loss": 0.7441,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.4085545539855957,
+      "learning_rate": 2e-05,
+      "loss": 0.6283,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.587538719177246,
+      "learning_rate": 2e-05,
+      "loss": 1.1968,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.6639175415039062,
+      "learning_rate": 2e-05,
+      "loss": 0.7579,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.090292453765869,
+      "learning_rate": 2e-05,
+      "loss": 1.3047,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.301203966140747,
+      "learning_rate": 2e-05,
+      "loss": 0.2738,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.2021005153656006,
+      "learning_rate": 2e-05,
+      "loss": 0.3979,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 6.288852691650391,
+      "learning_rate": 2e-05,
+      "loss": 1.585,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.023402214050293,
+      "learning_rate": 2e-05,
+      "loss": 1.1474,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.4434189796447754,
+      "learning_rate": 2e-05,
+      "loss": 0.2991,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.773408055305481,
+      "learning_rate": 2e-05,
+      "loss": 0.6277,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.1902174949645996,
+      "learning_rate": 2e-05,
+      "loss": 0.5112,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.60333251953125,
+      "learning_rate": 2e-05,
+      "loss": 0.2128,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.51239013671875,
+      "learning_rate": 2e-05,
+      "loss": 1.3767,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.47873491048812866,
+      "learning_rate": 2e-05,
+      "loss": 0.1478,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.3050646781921387,
+      "learning_rate": 2e-05,
+      "loss": 0.4301,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.4680174589157104,
+      "learning_rate": 2e-05,
+      "loss": 0.4868,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 5.060284614562988,
+      "learning_rate": 2e-05,
+      "loss": 1.4766,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.9290950298309326,
+      "learning_rate": 2e-05,
+      "loss": 0.521,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.033177614212036,
+      "learning_rate": 2e-05,
+      "loss": 0.8623,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.6711596250534058,
+      "learning_rate": 2e-05,
+      "loss": 0.6449,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.6369800567626953,
+      "learning_rate": 2e-05,
+      "loss": 0.7327,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.0031280517578125,
+      "learning_rate": 2e-05,
+      "loss": 0.5193,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.3499245643615723,
+      "learning_rate": 2e-05,
+      "loss": 0.4866,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.0874881744384766,
+      "learning_rate": 2e-05,
+      "loss": 0.8739,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.215085506439209,
+      "learning_rate": 2e-05,
+      "loss": 1.1589,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.7898951768875122,
+      "learning_rate": 2e-05,
+      "loss": 0.2845,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.463358163833618,
+      "learning_rate": 2e-05,
+      "loss": 0.3765,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.7925405502319336,
+      "learning_rate": 2e-05,
+      "loss": 0.3446,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.6757383346557617,
+      "learning_rate": 2e-05,
+      "loss": 0.7917,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.5198004245758057,
+      "learning_rate": 2e-05,
+      "loss": 0.3082,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.186577081680298,
+      "learning_rate": 2e-05,
+      "loss": 0.6401,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.8060414791107178,
+      "learning_rate": 2e-05,
+      "loss": 0.0603,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 2.0299384593963623,
+      "learning_rate": 2e-05,
+      "loss": 0.4283,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.539688229560852,
+      "learning_rate": 2e-05,
+      "loss": 0.2565,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.5283581018447876,
+      "learning_rate": 2e-05,
+      "loss": 0.1788,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.6798237562179565,
+      "learning_rate": 2e-05,
+      "loss": 0.7287,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.418360471725464,
+      "learning_rate": 2e-05,
+      "loss": 0.3788,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.48986631631851196,
+      "learning_rate": 2e-05,
+      "loss": 2.0909,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.2811102271080017,
+      "learning_rate": 2e-05,
+      "loss": 0.0683,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.9367895126342773,
+      "learning_rate": 2e-05,
+      "loss": 0.4261,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.887495279312134,
+      "learning_rate": 2e-05,
+      "loss": 0.4067,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5689210367377408.0,
+      "train_loss": 0.6352152729034424,
+      "train_runtime": 162.5562,
+      "train_samples_per_second": 2.461,
+      "train_steps_per_second": 0.615
+    }
+  ],
+  "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": 5689210367377408.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07f03b0ba909c845d5b5b49c2c076935f837f2786c99faff543722d4798bbed1
+size 389170582

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e00c2c325bfc7ee21add5d449c752326a25edbf3d18251963cb643297bb9ae
+size 389170582

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fbba7266a66e0096e2065265be474ac545ee8600fc54ed14af585a8031e9726
+size 389170582

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6756fbbfec598b27becfb99f39fdd78b7398d2e636031e0b73a8e62aa614ad2b
+size 389170582

client_states_fedavg_hetero_NOCONT_bs4_saveoptim_lr2e-5_5e-5_sc315_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc2aa4f97bd4e09072b338e21a46703e6b339f7d3a0baa7ac9633d09088b73b
+size 389170122