Upload folder using huggingface_hub

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71e59d68bc050c8c245682070738d377c3e19f040f75d17d0cfd0f2999cc4e1
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1fef668f0d7cf020371a9037ed6532b000024009a6fd648fe97d5aee857e2f
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5a73244e27070c923af720d74f42921bdf06863edcf77edc1c033af617cda87
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35723c0677349a5aaddebc202ac67a3c0b3bb9044bbb603b52832cda8a4c52eb
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9411d9ca803dc1af4a0b4a7e38b589fca56cee664bdc423e13ce4c9757d15bb2
+size 389170122

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43bc8607d28473ee78beb1b794c124640ae310f711e81d454732f9c4d9055f7
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2640c2d9044d425e897e23f28e9dee9f8c785ab88291f30b9b1eb6b28b005438
+size 389170122

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f83827f00382f1eb6ff6e2111384a1d8504a47732551b96e6f614a09650b77cb
+size 389170122

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.38719627261161804,
+      "learning_rate": 2e-05,
+      "loss": 0.9495,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.077051639556885,
+      "learning_rate": 2e-05,
+      "loss": 1.1149,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.647763729095459,
+      "learning_rate": 2e-05,
+      "loss": 0.469,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.861011028289795,
+      "learning_rate": 2e-05,
+      "loss": 0.5863,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.731424808502197,
+      "learning_rate": 2e-05,
+      "loss": 0.9636,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.3729605674743652,
+      "learning_rate": 2e-05,
+      "loss": 0.3736,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.4353901147842407,
+      "learning_rate": 2e-05,
+      "loss": 0.1299,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5314454436302185,
+      "learning_rate": 2e-05,
+      "loss": 0.6239,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 8.169297218322754,
+      "learning_rate": 2e-05,
+      "loss": 0.6807,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.6590330600738525,
+      "learning_rate": 2e-05,
+      "loss": 0.5854,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 5.28508996963501,
+      "learning_rate": 2e-05,
+      "loss": 2.7898,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.721231460571289,
+      "learning_rate": 2e-05,
+      "loss": 0.8212,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.1040432453155518,
+      "learning_rate": 2e-05,
+      "loss": 0.5053,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.9020832180976868,
+      "learning_rate": 2e-05,
+      "loss": 0.6259,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.40765118598938,
+      "learning_rate": 2e-05,
+      "loss": 1.1208,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.6171839237213135,
+      "learning_rate": 2e-05,
+      "loss": 0.9921,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.896834135055542,
+      "learning_rate": 2e-05,
+      "loss": 2.3071,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 5.1378374099731445,
+      "learning_rate": 2e-05,
+      "loss": 1.0913,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.00353741645813,
+      "learning_rate": 2e-05,
+      "loss": 1.2155,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.643733024597168,
+      "learning_rate": 2e-05,
+      "loss": 0.6208,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.8098461031913757,
+      "learning_rate": 2e-05,
+      "loss": 0.7776,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.4461122751235962,
+      "learning_rate": 2e-05,
+      "loss": 0.5236,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.9179946184158325,
+      "learning_rate": 2e-05,
+      "loss": 0.7537,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.2779043912887573,
+      "learning_rate": 2e-05,
+      "loss": 0.1594,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.877365231513977,
+      "learning_rate": 2e-05,
+      "loss": 0.9093,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.1748464107513428,
+      "learning_rate": 2e-05,
+      "loss": 1.39,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.7928354740142822,
+      "learning_rate": 2e-05,
+      "loss": 1.5579,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.500996708869934,
+      "learning_rate": 2e-05,
+      "loss": 0.2921,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.890474557876587,
+      "learning_rate": 2e-05,
+      "loss": 1.9559,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.7665313482284546,
+      "learning_rate": 2e-05,
+      "loss": 1.1142,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.2902581691741943,
+      "learning_rate": 2e-05,
+      "loss": 1.1461,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.8201829791069031,
+      "learning_rate": 2e-05,
+      "loss": 0.319,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.8217755556106567,
+      "learning_rate": 2e-05,
+      "loss": 0.7143,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 5.381126880645752,
+      "learning_rate": 2e-05,
+      "loss": 1.4243,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.4853060245513916,
+      "learning_rate": 2e-05,
+      "loss": 1.332,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.8426356315612793,
+      "learning_rate": 2e-05,
+      "loss": 1.1019,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.0112955570220947,
+      "learning_rate": 2e-05,
+      "loss": 1.0745,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 6.144918441772461,
+      "learning_rate": 2e-05,
+      "loss": 1.3628,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.4487675428390503,
+      "learning_rate": 2e-05,
+      "loss": 1.2708,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.009932029992341995,
+      "learning_rate": 2e-05,
+      "loss": 0.0021,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.9352052211761475,
+      "learning_rate": 2e-05,
+      "loss": 0.8146,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.740455627441406,
+      "learning_rate": 2e-05,
+      "loss": 0.712,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.8824151754379272,
+      "learning_rate": 2e-05,
+      "loss": 0.8197,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.143326997756958,
+      "learning_rate": 2e-05,
+      "loss": 0.4786,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 7.9439568519592285,
+      "learning_rate": 2e-05,
+      "loss": 1.4635,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.9261692762374878,
+      "learning_rate": 2e-05,
+      "loss": 0.1459,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.15097160637378693,
+      "learning_rate": 2e-05,
+      "loss": 0.357,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.4769234657287598,
+      "learning_rate": 2e-05,
+      "loss": 0.5221,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.9160871505737305,
+      "learning_rate": 2e-05,
+      "loss": 0.1567,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9476838111877441,
+      "learning_rate": 2e-05,
+      "loss": 0.8606,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.3383727962914816e+16,
+      "train_loss": 0.8815823143720627,
+      "train_runtime": 221.7164,
+      "train_samples_per_second": 1.804,
+      "train_steps_per_second": 0.451
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3383727962914816e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58aaffed59004af9db8ee186338a182d816d24d018a3166bdf4eb7f1178a86d6
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ba967cee68443f977a541e7e6ffcf44f3901ad6dabf69afbff4c8f439a6511
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:573ef4116a3152205a6bf0ca45fe0a34a7d57b71e621638f1f6a794c1fd092cd
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816025eb8d9c6f058c150890efb65dca6b1a72f9df0812c68c6c8e63e058f451
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6af229c16becf87bc79bc110fb9a49b852561f49ecdaefc5e7100dcedf857ac7
+size 389170122

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4753f5eedaf424f5ada3f33644bf095beffad6aec1037a5ae25bf34d3e8dd81
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f030325fc05fcc7c9e7554a76118c3d401c19a0b676f9ce15ffa238c6942fbbd
+size 389170122

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28e7a35d588e96a688dfe0ecca58f08511efb23a0d8f10407c642f08720a78b1
+size 389170122

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.8179876804351807,
+      "learning_rate": 2e-05,
+      "loss": 1.0491,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.41719651222229,
+      "learning_rate": 2e-05,
+      "loss": 1.2026,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.7802327871322632,
+      "learning_rate": 2e-05,
+      "loss": 0.7165,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.2552599906921387,
+      "learning_rate": 2e-05,
+      "loss": 0.9459,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.9657232761383057,
+      "learning_rate": 2e-05,
+      "loss": 1.2008,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.42064094543457,
+      "learning_rate": 2e-05,
+      "loss": 0.6898,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.853833198547363,
+      "learning_rate": 2e-05,
+      "loss": 1.3398,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.1425490379333496,
+      "learning_rate": 2e-05,
+      "loss": 1.1606,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.079017400741577,
+      "learning_rate": 2e-05,
+      "loss": 0.628,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.0045346021652222,
+      "learning_rate": 2e-05,
+      "loss": 0.6254,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 5.308418273925781,
+      "learning_rate": 2e-05,
+      "loss": 1.7184,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.9791314601898193,
+      "learning_rate": 2e-05,
+      "loss": 1.8596,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.9890248775482178,
+      "learning_rate": 2e-05,
+      "loss": 1.8337,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.7617010474205017,
+      "learning_rate": 2e-05,
+      "loss": 0.9499,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.3277595043182373,
+      "learning_rate": 2e-05,
+      "loss": 0.6863,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.103001832962036,
+      "learning_rate": 2e-05,
+      "loss": 1.4148,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.023189067840576,
+      "learning_rate": 2e-05,
+      "loss": 1.3982,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.5112829208374023,
+      "learning_rate": 2e-05,
+      "loss": 1.4246,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.2516484260559082,
+      "learning_rate": 2e-05,
+      "loss": 0.7055,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.5040652751922607,
+      "learning_rate": 2e-05,
+      "loss": 0.8877,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.1845147609710693,
+      "learning_rate": 2e-05,
+      "loss": 1.1816,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.596839427947998,
+      "learning_rate": 2e-05,
+      "loss": 0.6533,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.4578452110290527,
+      "learning_rate": 2e-05,
+      "loss": 1.3431,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.6840025186538696,
+      "learning_rate": 2e-05,
+      "loss": 0.8367,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.492110252380371,
+      "learning_rate": 2e-05,
+      "loss": 1.0867,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.0508782863616943,
+      "learning_rate": 2e-05,
+      "loss": 0.9977,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 5.697988033294678,
+      "learning_rate": 2e-05,
+      "loss": 1.5868,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.7626290321350098,
+      "learning_rate": 2e-05,
+      "loss": 0.9999,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.180218458175659,
+      "learning_rate": 2e-05,
+      "loss": 0.8487,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.1971452236175537,
+      "learning_rate": 2e-05,
+      "loss": 0.8921,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.7069987058639526,
+      "learning_rate": 2e-05,
+      "loss": 0.8564,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.4899487495422363,
+      "learning_rate": 2e-05,
+      "loss": 0.931,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.0761315822601318,
+      "learning_rate": 2e-05,
+      "loss": 0.7449,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.789404273033142,
+      "learning_rate": 2e-05,
+      "loss": 0.8726,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.981410264968872,
+      "learning_rate": 2e-05,
+      "loss": 0.4085,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.762418746948242,
+      "learning_rate": 2e-05,
+      "loss": 1.2914,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.9814112186431885,
+      "learning_rate": 2e-05,
+      "loss": 1.1581,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.3890533447265625,
+      "learning_rate": 2e-05,
+      "loss": 0.8834,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.0549677610397339,
+      "learning_rate": 2e-05,
+      "loss": 0.646,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.3273770809173584,
+      "learning_rate": 2e-05,
+      "loss": 1.3475,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.1365349292755127,
+      "learning_rate": 2e-05,
+      "loss": 1.1026,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.8358497619628906,
+      "learning_rate": 2e-05,
+      "loss": 1.3143,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.3015081882476807,
+      "learning_rate": 2e-05,
+      "loss": 1.3413,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.632488965988159,
+      "learning_rate": 2e-05,
+      "loss": 1.1476,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.0986149311065674,
+      "learning_rate": 2e-05,
+      "loss": 0.7337,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.7485151290893555,
+      "learning_rate": 2e-05,
+      "loss": 1.3003,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.1127849817276,
+      "learning_rate": 2e-05,
+      "loss": 0.5595,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.18037748336792,
+      "learning_rate": 2e-05,
+      "loss": 0.8242,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.708859443664551,
+      "learning_rate": 2e-05,
+      "loss": 1.6295,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.884798288345337,
+      "learning_rate": 2e-05,
+      "loss": 1.0589,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.3139463274233856e+16,
+      "train_loss": 1.0603120422363281,
+      "train_runtime": 216.4261,
+      "train_samples_per_second": 1.848,
+      "train_steps_per_second": 0.462
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3139463274233856e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa4ad41be462d3a5e1b7a04ddc5426f6fce993e6b7fabb3fd5d18e1e4e4129b
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e40697f6089ace79725387184f234781741956d518ec7c3e6e046da097c5d425
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32751fd91bd74287c810dc3ce7384f0ec4310b3dd86ac9801654472296bb2049
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c4eb84b78f4202cd088f5c6fb69b2d4c31eb0cb82c93691984a69824b147d0
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed09505540a40497eabb3b09e335838d1d521d05c42a498ad4c67b4922b65a66
+size 389170122

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac30bb490173b7d4300047924aa2aa75d82711d35414c5c2792c9497ce852a0
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce743102f5cfa2a5094a34d74e24cb10a981722f58f5f95cb3f9f7046440363f
+size 389170122

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:340aef991091efdf641ca7ef21415ca4a7e6361e0ce54d330fb7b41f2456f326
+size 389170122

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.9490151405334473,
+      "learning_rate": 2e-05,
+      "loss": 1.4567,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.8499606251716614,
+      "learning_rate": 2e-05,
+      "loss": 1.7778,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.46522098779678345,
+      "learning_rate": 2e-05,
+      "loss": 0.3968,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.8376254439353943,
+      "learning_rate": 2e-05,
+      "loss": 0.4488,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.22391676902771,
+      "learning_rate": 2e-05,
+      "loss": 0.8374,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.033006191253662,
+      "learning_rate": 2e-05,
+      "loss": 1.3004,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 4.817259311676025,
+      "learning_rate": 2e-05,
+      "loss": 0.5057,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.756402611732483,
+      "learning_rate": 2e-05,
+      "loss": 0.9344,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.656694173812866,
+      "learning_rate": 2e-05,
+      "loss": 1.2954,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.356359958648682,
+      "learning_rate": 2e-05,
+      "loss": 0.4394,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.1422009468078613,
+      "learning_rate": 2e-05,
+      "loss": 0.2635,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.291994571685791,
+      "learning_rate": 2e-05,
+      "loss": 1.4222,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.210984706878662,
+      "learning_rate": 2e-05,
+      "loss": 0.4962,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.3874601125717163,
+      "learning_rate": 2e-05,
+      "loss": 0.2592,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 6.824109077453613,
+      "learning_rate": 2e-05,
+      "loss": 1.3853,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.2160550206899643,
+      "learning_rate": 2e-05,
+      "loss": 0.2748,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 8.029728889465332,
+      "learning_rate": 2e-05,
+      "loss": 0.7844,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.261617660522461,
+      "learning_rate": 2e-05,
+      "loss": 1.2363,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 6.283971786499023,
+      "learning_rate": 2e-05,
+      "loss": 0.9562,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.48956239223480225,
+      "learning_rate": 2e-05,
+      "loss": 0.398,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.1637802124023438,
+      "learning_rate": 2e-05,
+      "loss": 1.4373,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.5024800300598145,
+      "learning_rate": 2e-05,
+      "loss": 0.9499,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 6.166162967681885,
+      "learning_rate": 2e-05,
+      "loss": 0.3982,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.1384220123291016,
+      "learning_rate": 2e-05,
+      "loss": 0.5947,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.627658367156982,
+      "learning_rate": 2e-05,
+      "loss": 1.6234,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 9.658411026000977,
+      "learning_rate": 2e-05,
+      "loss": 1.5451,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.6504881381988525,
+      "learning_rate": 2e-05,
+      "loss": 0.6826,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 6.26855993270874,
+      "learning_rate": 2e-05,
+      "loss": 0.7033,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.2874207496643066,
+      "learning_rate": 2e-05,
+      "loss": 0.6535,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.7567996978759766,
+      "learning_rate": 2e-05,
+      "loss": 0.5392,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 4.708986282348633,
+      "learning_rate": 2e-05,
+      "loss": 1.6334,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.634983539581299,
+      "learning_rate": 2e-05,
+      "loss": 0.7382,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.82580304145813,
+      "learning_rate": 2e-05,
+      "loss": 0.6029,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.219573974609375,
+      "learning_rate": 2e-05,
+      "loss": 0.6639,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 6.9499101638793945,
+      "learning_rate": 2e-05,
+      "loss": 1.1658,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.107332229614258,
+      "learning_rate": 2e-05,
+      "loss": 0.5946,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.9869490265846252,
+      "learning_rate": 2e-05,
+      "loss": 0.3319,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.773704528808594,
+      "learning_rate": 2e-05,
+      "loss": 0.8904,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 5.0077009201049805,
+      "learning_rate": 2e-05,
+      "loss": 0.8231,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.703085422515869,
+      "learning_rate": 2e-05,
+      "loss": 0.5793,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.477120876312256,
+      "learning_rate": 2e-05,
+      "loss": 0.6928,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 6.5172858238220215,
+      "learning_rate": 2e-05,
+      "loss": 1.0894,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.759190320968628,
+      "learning_rate": 2e-05,
+      "loss": 0.3536,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.939716339111328,
+      "learning_rate": 2e-05,
+      "loss": 0.7504,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5.724381446838379,
+      "learning_rate": 2e-05,
+      "loss": 1.3589,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 5.820595741271973,
+      "learning_rate": 2e-05,
+      "loss": 2.8232,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.7025810480117798,
+      "learning_rate": 2e-05,
+      "loss": 1.3651,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.008639335632324,
+      "learning_rate": 2e-05,
+      "loss": 1.8883,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.462066173553467,
+      "learning_rate": 2e-05,
+      "loss": 0.7482,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.429091930389404,
+      "learning_rate": 2e-05,
+      "loss": 1.5025,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.6070859319934976e+16,
+      "train_loss": 0.9318349838256836,
+      "train_runtime": 245.4173,
+      "train_samples_per_second": 1.63,
+      "train_steps_per_second": 0.407
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6070859319934976e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07d8690a0c0bc7f7659aa7e3345d561cc5b583740443e8911e37f0f00d3023a5
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a46d6d61def086cf51e0001fb5e3bf9019639e228833ee12afc2cc4951504c
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbdd6a7bc88b020c6797a91bcacd48c83170eb43b5b9f80dd4cef884c019c110
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a2708b750d00a8aa59682609c5fe107bd86bfae07e0576736bb8b86465a387c
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c362abe0ee0c4e4e64cf49e85865ec5afb70edf82872564ed58c360f9a7f9422
+size 389170122

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e909226669dbb1c5cce1749e57a7cbf572ffe75e8cd0ff8a9596cd9f1b4e2b5
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4ce182216e59b966509d34c00c76e4cdb9fc64300ec6f6f5acb0823ba4df683
+size 389170122

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41079dc3921a1e286f5271d74cf02fc0c741d564222df4b295df6e5e9203f238
+size 389170122

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.5392704010009766,
+      "learning_rate": 2e-05,
+      "loss": 0.9512,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.5443292260169983,
+      "learning_rate": 2e-05,
+      "loss": 0.5493,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.7276273965835571,
+      "learning_rate": 2e-05,
+      "loss": 0.7195,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.6282225251197815,
+      "learning_rate": 2e-05,
+      "loss": 0.4978,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.8995158672332764,
+      "learning_rate": 2e-05,
+      "loss": 0.7806,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.3764248788356781,
+      "learning_rate": 2e-05,
+      "loss": 0.1982,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 4.37995719909668,
+      "learning_rate": 2e-05,
+      "loss": 0.9697,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.6920167207717896,
+      "learning_rate": 2e-05,
+      "loss": 1.3309,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.3924529552459717,
+      "learning_rate": 2e-05,
+      "loss": 1.364,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.6065640449523926,
+      "learning_rate": 2e-05,
+      "loss": 0.9799,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.2157273292541504,
+      "learning_rate": 2e-05,
+      "loss": 0.7581,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.9669651985168457,
+      "learning_rate": 2e-05,
+      "loss": 0.2652,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.5557457208633423,
+      "learning_rate": 2e-05,
+      "loss": 0.5342,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.6205579042434692,
+      "learning_rate": 2e-05,
+      "loss": 0.3555,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.9040493965148926,
+      "learning_rate": 2e-05,
+      "loss": 0.7911,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.4295775592327118,
+      "learning_rate": 2e-05,
+      "loss": 0.3723,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.5853860378265381,
+      "learning_rate": 2e-05,
+      "loss": 0.4382,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.7423451542854309,
+      "learning_rate": 2e-05,
+      "loss": 0.3345,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.3415956497192383,
+      "learning_rate": 2e-05,
+      "loss": 0.3874,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.9895901083946228,
+      "learning_rate": 2e-05,
+      "loss": 0.8562,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.759679079055786,
+      "learning_rate": 2e-05,
+      "loss": 0.6649,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.449832916259766,
+      "learning_rate": 2e-05,
+      "loss": 1.0138,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.4374058246612549,
+      "learning_rate": 2e-05,
+      "loss": 1.1579,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.2519681453704834,
+      "learning_rate": 2e-05,
+      "loss": 0.4247,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.183549165725708,
+      "learning_rate": 2e-05,
+      "loss": 1.0477,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.453892469406128,
+      "learning_rate": 2e-05,
+      "loss": 1.1864,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.9186144471168518,
+      "learning_rate": 2e-05,
+      "loss": 0.6686,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.9324042797088623,
+      "learning_rate": 2e-05,
+      "loss": 0.8158,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.215837478637695,
+      "learning_rate": 2e-05,
+      "loss": 0.4595,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.3837835788726807,
+      "learning_rate": 2e-05,
+      "loss": 0.6181,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.1491609811782837,
+      "learning_rate": 2e-05,
+      "loss": 0.6926,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.070747971534729,
+      "learning_rate": 2e-05,
+      "loss": 1.2385,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.3820966482162476,
+      "learning_rate": 2e-05,
+      "loss": 0.5424,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.3940738439559937,
+      "learning_rate": 2e-05,
+      "loss": 0.4959,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.6330006718635559,
+      "learning_rate": 2e-05,
+      "loss": 0.7177,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.8667371273040771,
+      "learning_rate": 2e-05,
+      "loss": 0.8641,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.0052789449691772,
+      "learning_rate": 2e-05,
+      "loss": 0.2287,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.4756717681884766,
+      "learning_rate": 2e-05,
+      "loss": 0.5842,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.0159566402435303,
+      "learning_rate": 2e-05,
+      "loss": 0.2617,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 12.710314750671387,
+      "learning_rate": 2e-05,
+      "loss": 0.9227,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.747962713241577,
+      "learning_rate": 2e-05,
+      "loss": 0.5271,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.5851404666900635,
+      "learning_rate": 2e-05,
+      "loss": 0.9902,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.607115387916565,
+      "learning_rate": 2e-05,
+      "loss": 1.7817,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.76336407661438,
+      "learning_rate": 2e-05,
+      "loss": 1.7342,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.5464903116226196,
+      "learning_rate": 2e-05,
+      "loss": 0.8454,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.81872034072876,
+      "learning_rate": 2e-05,
+      "loss": 1.9256,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.795423686504364,
+      "learning_rate": 2e-05,
+      "loss": 0.6289,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.5372910499572754,
+      "learning_rate": 2e-05,
+      "loss": 0.3388,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.8624018430709839,
+      "learning_rate": 2e-05,
+      "loss": 0.2551,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.973138451576233,
+      "learning_rate": 2e-05,
+      "loss": 0.2702,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2.021057658408141e+16,
+      "train_loss": 0.7467445921897888,
+      "train_runtime": 242.3455,
+      "train_samples_per_second": 1.651,
+      "train_steps_per_second": 0.413
+    }
+  ],
+  "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": 2.021057658408141e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b05fdb0625dd7daf03c1884255c1b225df5f13421d25aa2095a9001c69e69a7
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb29b18b30c98588fa090d902d9d4918bf240299d4bdcc5a275b4464a81c901f
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ef1cd1f9958cf47952b757fb59c0d5103b3408d0fa285c3e33c039c200795a
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7467e0cd8409dfa38e6aedf41b3266b2be12c259399453ee324b67591880aa2d
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfd34ec4cf9983f81667a7ad3ab1cd9aadb6b6c14eea6c794075d14c09b1a90
+size 389170122

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f50f9af5c299f47818aa61372f2ce2ea76e4725e33ae2edd1ae1424a8732e1a
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc752cadc06caa429e65eb54be6f161292c501ce8ec00a8490623a8cf7f233c
+size 389170122

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c31240f805ac9ed4f810089d2593e9e7846793e9bc418086b508372c6bdea097
+size 389170122

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.433440208435059,
+      "learning_rate": 2e-05,
+      "loss": 1.1102,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.6188807487487793,
+      "learning_rate": 2e-05,
+      "loss": 0.7672,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.3638596534729004,
+      "learning_rate": 2e-05,
+      "loss": 0.3702,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 7.427084445953369,
+      "learning_rate": 2e-05,
+      "loss": 1.312,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.3429694175720215,
+      "learning_rate": 2e-05,
+      "loss": 0.5379,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.051405191421509,
+      "learning_rate": 2e-05,
+      "loss": 0.6165,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.7151682376861572,
+      "learning_rate": 2e-05,
+      "loss": 0.6384,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.0302693843841553,
+      "learning_rate": 2e-05,
+      "loss": 0.388,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.345546245574951,
+      "learning_rate": 2e-05,
+      "loss": 0.5916,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.9489526748657227,
+      "learning_rate": 2e-05,
+      "loss": 0.6976,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.725450038909912,
+      "learning_rate": 2e-05,
+      "loss": 1.4011,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.639797687530518,
+      "learning_rate": 2e-05,
+      "loss": 0.9098,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 5.01195764541626,
+      "learning_rate": 2e-05,
+      "loss": 1.1458,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.973168134689331,
+      "learning_rate": 2e-05,
+      "loss": 0.5898,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 5.872989654541016,
+      "learning_rate": 2e-05,
+      "loss": 1.9116,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 6.089108467102051,
+      "learning_rate": 2e-05,
+      "loss": 1.9043,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.4458413124084473,
+      "learning_rate": 2e-05,
+      "loss": 1.2772,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.9035794734954834,
+      "learning_rate": 2e-05,
+      "loss": 0.431,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.9877755641937256,
+      "learning_rate": 2e-05,
+      "loss": 0.9434,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.707182884216309,
+      "learning_rate": 2e-05,
+      "loss": 0.8015,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 9.478857040405273,
+      "learning_rate": 2e-05,
+      "loss": 1.6909,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.994309425354004,
+      "learning_rate": 2e-05,
+      "loss": 1.0641,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.126333713531494,
+      "learning_rate": 2e-05,
+      "loss": 0.5798,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.5265707969665527,
+      "learning_rate": 2e-05,
+      "loss": 1.2152,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.8720102310180664,
+      "learning_rate": 2e-05,
+      "loss": 0.8986,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.4834368228912354,
+      "learning_rate": 2e-05,
+      "loss": 1.0198,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.769567489624023,
+      "learning_rate": 2e-05,
+      "loss": 1.3574,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.097980976104736,
+      "learning_rate": 2e-05,
+      "loss": 1.0021,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.1415047645568848,
+      "learning_rate": 2e-05,
+      "loss": 0.8902,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.144840240478516,
+      "learning_rate": 2e-05,
+      "loss": 2.0223,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 5.529412269592285,
+      "learning_rate": 2e-05,
+      "loss": 1.1244,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.0263214111328125,
+      "learning_rate": 2e-05,
+      "loss": 0.536,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.7067674398422241,
+      "learning_rate": 2e-05,
+      "loss": 0.4865,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 6.090213775634766,
+      "learning_rate": 2e-05,
+      "loss": 0.8405,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.867413520812988,
+      "learning_rate": 2e-05,
+      "loss": 1.5321,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.3090170621871948,
+      "learning_rate": 2e-05,
+      "loss": 1.3437,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.0951173305511475,
+      "learning_rate": 2e-05,
+      "loss": 0.9251,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.5101104974746704,
+      "learning_rate": 2e-05,
+      "loss": 0.3047,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.95428729057312,
+      "learning_rate": 2e-05,
+      "loss": 2.1858,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.568641185760498,
+      "learning_rate": 2e-05,
+      "loss": 0.7705,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.8518729209899902,
+      "learning_rate": 2e-05,
+      "loss": 1.5554,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.1477725505828857,
+      "learning_rate": 2e-05,
+      "loss": 0.2965,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.384981632232666,
+      "learning_rate": 2e-05,
+      "loss": 2.0754,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.6094033122062683,
+      "learning_rate": 2e-05,
+      "loss": 0.2383,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.6929229497909546,
+      "learning_rate": 2e-05,
+      "loss": 0.75,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.472173690795898,
+      "learning_rate": 2e-05,
+      "loss": 0.8645,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 6.539391994476318,
+      "learning_rate": 2e-05,
+      "loss": 1.0788,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.824303150177002,
+      "learning_rate": 2e-05,
+      "loss": 1.4423,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.012169361114502,
+      "learning_rate": 2e-05,
+      "loss": 1.2461,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.046121597290039,
+      "learning_rate": 2e-05,
+      "loss": 0.3551,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.947256978669568e+16,
+      "train_loss": 1.000740842819214,
+      "train_runtime": 242.7394,
+      "train_samples_per_second": 1.648,
+      "train_steps_per_second": 0.412
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.947256978669568e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99ac70de5b7db1a0657b03cb5003368d1b8a8dfaaa6fd88ef8a62e2f51191ebb
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10192f3c768a1512e89983cd03a7eafaac980556a4e5ee9a4b3c41975609b791
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c19c5ca0b36e4566d727bbe6b3a39a359a9da403c1f33aff0681ff4c17a17ba
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:183093727dd11ba7c501e411aefa6887e6dfd520cbf6f0180de584569983c90b
+size 389170582

client_states_fedavg_NOCONT_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c972eedd0bd6b3d91f8d5ed067551079cb2d9b5f2a0e5653dc7aad5222c7844
+size 389170122