Upload folder using huggingface_hub

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4dbd7b57117ebc0e92f840772e7b8d9326ec963af97ee7c8ed8f5b4ee5a16c
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da9f5258d69f82613d56ddb767feca00d546a6022909992b29e3e4bfa2387dfb
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb29437e912422ee086e5c8e7522fa85e62c7cd132f24649d8c01ae226142003
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad3cfb989f0199c40ada0bf07b6861730ad35c59050da0ad718530ab4d7bbaa
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2f4127fb143b2ffa86130e606a7d9aa32b52faedb673e200e7ce733eb83b521
+size 389170122

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abc0687c29d3aea2e03a80a0b7b8b996288fbd8cdeb741b7c2bae13fb5d4268d
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad22cdcb5a353bd143900ef12f0b22ba7bbdffab96c7bc1a0a252b43d8e736cf
+size 389170122

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f082d8ba919fb52b4c5c6ca1498321a6fe472fbfc9ea29e8eaea4c30e8b2a987
+size 389170122

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_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": 0.7681789398193359,
+      "learning_rate": 2e-05,
+      "loss": 0.1667,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.9858031272888184,
+      "learning_rate": 2e-05,
+      "loss": 0.1653,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 7.460695266723633,
+      "learning_rate": 2e-05,
+      "loss": 0.1575,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.774257183074951,
+      "learning_rate": 2e-05,
+      "loss": 0.3906,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.697665274143219,
+      "learning_rate": 2e-05,
+      "loss": 0.0591,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.0891075134277344,
+      "learning_rate": 2e-05,
+      "loss": 0.1472,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.9881222248077393,
+      "learning_rate": 2e-05,
+      "loss": 0.3101,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.5707805156707764,
+      "learning_rate": 2e-05,
+      "loss": 0.1572,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 4.1817803382873535,
+      "learning_rate": 2e-05,
+      "loss": 0.2539,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.0925190448760986,
+      "learning_rate": 2e-05,
+      "loss": 0.1567,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.5714080333709717,
+      "learning_rate": 2e-05,
+      "loss": 0.1296,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.7355799674987793,
+      "learning_rate": 2e-05,
+      "loss": 0.0603,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.4088470935821533,
+      "learning_rate": 2e-05,
+      "loss": 0.1611,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.11065936088562,
+      "learning_rate": 2e-05,
+      "loss": 0.1589,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.533633708953857,
+      "learning_rate": 2e-05,
+      "loss": 0.2048,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.762478828430176,
+      "learning_rate": 2e-05,
+      "loss": 0.2603,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.6360326409339905,
+      "learning_rate": 2e-05,
+      "loss": 0.073,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.446553945541382,
+      "learning_rate": 2e-05,
+      "loss": 0.1926,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.585399150848389,
+      "learning_rate": 2e-05,
+      "loss": 0.3315,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.1877154111862183,
+      "learning_rate": 2e-05,
+      "loss": 0.2788,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.592831611633301,
+      "learning_rate": 2e-05,
+      "loss": 0.1753,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.399947166442871,
+      "learning_rate": 2e-05,
+      "loss": 0.1438,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.7166435718536377,
+      "learning_rate": 2e-05,
+      "loss": 0.1648,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.6287264823913574,
+      "learning_rate": 2e-05,
+      "loss": 0.0942,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.5515120029449463,
+      "learning_rate": 2e-05,
+      "loss": 0.2102,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.0096092224121094,
+      "learning_rate": 2e-05,
+      "loss": 0.087,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 9.327820777893066,
+      "learning_rate": 2e-05,
+      "loss": 0.4895,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.359659194946289,
+      "learning_rate": 2e-05,
+      "loss": 0.2271,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.62618088722229,
+      "learning_rate": 2e-05,
+      "loss": 0.0863,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.553459167480469,
+      "learning_rate": 2e-05,
+      "loss": 0.2427,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.9122878313064575,
+      "learning_rate": 2e-05,
+      "loss": 0.0432,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.588026762008667,
+      "learning_rate": 2e-05,
+      "loss": 0.2168,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.6846867203712463,
+      "learning_rate": 2e-05,
+      "loss": 0.0696,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.5343677997589111,
+      "learning_rate": 2e-05,
+      "loss": 0.0789,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.9839800596237183,
+      "learning_rate": 2e-05,
+      "loss": 0.106,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.914919376373291,
+      "learning_rate": 2e-05,
+      "loss": 0.1992,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 7.914262294769287,
+      "learning_rate": 2e-05,
+      "loss": 0.1443,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.7149121761322021,
+      "learning_rate": 2e-05,
+      "loss": 0.2246,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.287249803543091,
+      "learning_rate": 2e-05,
+      "loss": 0.3584,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.400071620941162,
+      "learning_rate": 2e-05,
+      "loss": 0.4287,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.0164868831634521,
+      "learning_rate": 2e-05,
+      "loss": 0.166,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.102115154266357,
+      "learning_rate": 2e-05,
+      "loss": 0.2234,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 5.070318222045898,
+      "learning_rate": 2e-05,
+      "loss": 0.23,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.395050525665283,
+      "learning_rate": 2e-05,
+      "loss": 0.3926,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.2536754608154297,
+      "learning_rate": 2e-05,
+      "loss": 0.0894,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.3888511061668396,
+      "learning_rate": 2e-05,
+      "loss": 0.0743,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.8675658106803894,
+      "learning_rate": 2e-05,
+      "loss": 0.0897,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.6503221988677979,
+      "learning_rate": 2e-05,
+      "loss": 0.1399,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.524456739425659,
+      "learning_rate": 2e-05,
+      "loss": 0.2627,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.795688152313232,
+      "learning_rate": 2e-05,
+      "loss": 0.2783,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.865191632614195e+16,
+      "train_loss": 0.191044921875,
+      "train_runtime": 303.6413,
+      "train_samples_per_second": 1.317,
+      "train_steps_per_second": 0.329
+    }
+  ],
+  "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": 1.865191632614195e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1945623050c0fbfa439f0308b407f01c192adfb55deb3d8ece723ddf3073b4
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a50beb931d0b17c7f4fecc51a4111e38d003d51b6f524091fb9c128c20d16cf7
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4900b6a620fb460d7eebe63c32a1d3aa7021f1a82ce189ece2e75b654f84b387
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a35103139b2719bf6cd82156594ec03e472045e38a8abacec5730171b5dea7
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525c0ed366ae1187d55a0c12c194b102495917c4e7ca13dc617503c27c2a30a0
+size 389170122

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c43ffd9200389e0fb5e68ee38e6c992bbbdd068e4e3147f32fd334c58ee995bc
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82afcf2e9815bc492277eaf9b495d2f112933333b7c813eb4516c0c4f743c580
+size 389170122

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9315733ea4fc115f4683a83e8591a02c6aa572df2cb21342457ed0dd7e41408f
+size 389170122

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_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": 5.162927150726318,
+      "learning_rate": 2e-05,
+      "loss": 0.3672,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.8139963150024414,
+      "learning_rate": 2e-05,
+      "loss": 0.2764,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.4045088291168213,
+      "learning_rate": 2e-05,
+      "loss": 0.2886,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.0921738147735596,
+      "learning_rate": 2e-05,
+      "loss": 0.2959,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.3632135391235352,
+      "learning_rate": 2e-05,
+      "loss": 0.2969,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.172605276107788,
+      "learning_rate": 2e-05,
+      "loss": 0.2148,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.9686121940612793,
+      "learning_rate": 2e-05,
+      "loss": 0.2988,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.4601385593414307,
+      "learning_rate": 2e-05,
+      "loss": 0.2915,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.6114205121994019,
+      "learning_rate": 2e-05,
+      "loss": 0.2109,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.0597972869873047,
+      "learning_rate": 2e-05,
+      "loss": 0.249,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.3526787757873535,
+      "learning_rate": 2e-05,
+      "loss": 0.2544,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.1127853393554688,
+      "learning_rate": 2e-05,
+      "loss": 0.2817,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.1098952293395996,
+      "learning_rate": 2e-05,
+      "loss": 0.1846,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.701572895050049,
+      "learning_rate": 2e-05,
+      "loss": 0.1963,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.284106492996216,
+      "learning_rate": 2e-05,
+      "loss": 0.3916,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.42879056930542,
+      "learning_rate": 2e-05,
+      "loss": 0.2969,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.040755271911621,
+      "learning_rate": 2e-05,
+      "loss": 0.3027,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.8482613563537598,
+      "learning_rate": 2e-05,
+      "loss": 0.3052,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.358405351638794,
+      "learning_rate": 2e-05,
+      "loss": 0.1365,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.249178647994995,
+      "learning_rate": 2e-05,
+      "loss": 0.2383,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.7586663961410522,
+      "learning_rate": 2e-05,
+      "loss": 0.187,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.6459927558898926,
+      "learning_rate": 2e-05,
+      "loss": 0.2646,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.9291881322860718,
+      "learning_rate": 2e-05,
+      "loss": 0.168,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.067496418952942,
+      "learning_rate": 2e-05,
+      "loss": 0.1135,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.1252028942108154,
+      "learning_rate": 2e-05,
+      "loss": 0.3447,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.299633979797363,
+      "learning_rate": 2e-05,
+      "loss": 0.4619,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.607396602630615,
+      "learning_rate": 2e-05,
+      "loss": 0.2954,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.2473145723342896,
+      "learning_rate": 2e-05,
+      "loss": 0.1025,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.085881233215332,
+      "learning_rate": 2e-05,
+      "loss": 0.2085,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.942441701889038,
+      "learning_rate": 2e-05,
+      "loss": 0.209,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.026491403579712,
+      "learning_rate": 2e-05,
+      "loss": 0.4785,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.2812161445617676,
+      "learning_rate": 2e-05,
+      "loss": 0.1526,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.2541882991790771,
+      "learning_rate": 2e-05,
+      "loss": 0.4092,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.7665891647338867,
+      "learning_rate": 2e-05,
+      "loss": 0.3896,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.1083252429962158,
+      "learning_rate": 2e-05,
+      "loss": 0.2983,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.9806040525436401,
+      "learning_rate": 2e-05,
+      "loss": 0.2466,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.943515419960022,
+      "learning_rate": 2e-05,
+      "loss": 0.2144,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.462261199951172,
+      "learning_rate": 2e-05,
+      "loss": 0.2729,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.1030101776123047,
+      "learning_rate": 2e-05,
+      "loss": 0.2119,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.973886013031006,
+      "learning_rate": 2e-05,
+      "loss": 0.3633,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.9282856583595276,
+      "learning_rate": 2e-05,
+      "loss": 0.1824,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.6491354703903198,
+      "learning_rate": 2e-05,
+      "loss": 0.2366,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.987030267715454,
+      "learning_rate": 2e-05,
+      "loss": 0.2979,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.5676429271697998,
+      "learning_rate": 2e-05,
+      "loss": 0.2666,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.862716555595398,
+      "learning_rate": 2e-05,
+      "loss": 0.2744,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.8054755926132202,
+      "learning_rate": 2e-05,
+      "loss": 0.2358,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.7789947986602783,
+      "learning_rate": 2e-05,
+      "loss": 0.2129,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.808908224105835,
+      "learning_rate": 2e-05,
+      "loss": 0.1958,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.9118070602416992,
+      "learning_rate": 2e-05,
+      "loss": 0.2136,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.6127201318740845,
+      "learning_rate": 2e-05,
+      "loss": 0.4141,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.8301597519970304e+16,
+      "train_loss": 0.266015625,
+      "train_runtime": 299.9026,
+      "train_samples_per_second": 1.334,
+      "train_steps_per_second": 0.333
+    }
+  ],
+  "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": 1.8301597519970304e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:861a370e45b2f9f01d78fc016f5bad3765cca6c978c9af9f30a409756bc51e97
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a80e9571fc8680486ede0be802ca180741169727a4799492afe1064e86697ce6
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed788184c46a51da9d846cb49e541da4a2e3303c5ad0cee622ee01f3f188086
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d00e2ab2a81a40f620636edb349d89c1e7ef19e79aa22e78e9100ffffc93ca8
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be877f0fc2f11753b74dbcea075c70433b27c2d4d4b1a5154dff3c1cb51d1cb0
+size 389170122

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f0172c9ac94f65a75ec956194f5bce1600b80ab128bf0da604a63c6213e9f3d
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e10edfea7280d36f28e2b9a0afe06770f40903159e887924c4e6121a7b1969bc
+size 389170122

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3c446267413329156d5148c0ba8a8d04c49d5c62a923ab6551c659c2d06ff7
+size 389170122

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_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": 5.92473030090332,
+      "learning_rate": 2e-05,
+      "loss": 0.2788,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.1622978448867798,
+      "learning_rate": 2e-05,
+      "loss": 0.082,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.6461238861083984,
+      "learning_rate": 2e-05,
+      "loss": 0.1726,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.0796098709106445,
+      "learning_rate": 2e-05,
+      "loss": 0.0748,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.907897710800171,
+      "learning_rate": 2e-05,
+      "loss": 0.1819,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 11.616080284118652,
+      "learning_rate": 2e-05,
+      "loss": 0.2549,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 6.870760440826416,
+      "learning_rate": 2e-05,
+      "loss": 0.5967,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.469508171081543,
+      "learning_rate": 2e-05,
+      "loss": 0.3545,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.4311599731445312,
+      "learning_rate": 2e-05,
+      "loss": 0.3042,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.9978313446044922,
+      "learning_rate": 2e-05,
+      "loss": 0.1797,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.14152193069458,
+      "learning_rate": 2e-05,
+      "loss": 0.2578,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.08518648147583,
+      "learning_rate": 2e-05,
+      "loss": 0.1743,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.6409809589385986,
+      "learning_rate": 2e-05,
+      "loss": 0.2168,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.836951732635498,
+      "learning_rate": 2e-05,
+      "loss": 0.2664,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.8253288865089417,
+      "learning_rate": 2e-05,
+      "loss": 0.193,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.445699691772461,
+      "learning_rate": 2e-05,
+      "loss": 0.1362,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.3368934392929077,
+      "learning_rate": 2e-05,
+      "loss": 0.1948,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 7.334422588348389,
+      "learning_rate": 2e-05,
+      "loss": 0.27,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.5522675514221191,
+      "learning_rate": 2e-05,
+      "loss": 0.1226,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.0696229934692383,
+      "learning_rate": 2e-05,
+      "loss": 0.1794,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.5367555618286133,
+      "learning_rate": 2e-05,
+      "loss": 0.2666,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.771532654762268,
+      "learning_rate": 2e-05,
+      "loss": 0.1055,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.6121385097503662,
+      "learning_rate": 2e-05,
+      "loss": 0.1382,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.840958297252655,
+      "learning_rate": 2e-05,
+      "loss": 0.1956,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 9.105291366577148,
+      "learning_rate": 2e-05,
+      "loss": 0.3271,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.591594934463501,
+      "learning_rate": 2e-05,
+      "loss": 0.2515,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.4830551147460938,
+      "learning_rate": 2e-05,
+      "loss": 0.2068,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.9077150225639343,
+      "learning_rate": 2e-05,
+      "loss": 0.1003,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.9782874584198,
+      "learning_rate": 2e-05,
+      "loss": 0.1656,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.8825637102127075,
+      "learning_rate": 2e-05,
+      "loss": 0.1685,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 7.019435405731201,
+      "learning_rate": 2e-05,
+      "loss": 0.3867,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.12417733669281,
+      "learning_rate": 2e-05,
+      "loss": 0.21,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.1205978393554688,
+      "learning_rate": 2e-05,
+      "loss": 0.2744,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.8004539012908936,
+      "learning_rate": 2e-05,
+      "loss": 0.1589,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.7644095420837402,
+      "learning_rate": 2e-05,
+      "loss": 0.2217,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.4835090637207031,
+      "learning_rate": 2e-05,
+      "loss": 0.1443,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.9295995235443115,
+      "learning_rate": 2e-05,
+      "loss": 0.3276,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.166787624359131,
+      "learning_rate": 2e-05,
+      "loss": 0.373,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.4152839183807373,
+      "learning_rate": 2e-05,
+      "loss": 0.0529,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.817052960395813,
+      "learning_rate": 2e-05,
+      "loss": 0.1982,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 6.036396503448486,
+      "learning_rate": 2e-05,
+      "loss": 0.2522,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.7961066961288452,
+      "learning_rate": 2e-05,
+      "loss": 0.104,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.2944209575653076,
+      "learning_rate": 2e-05,
+      "loss": 0.1484,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 6.894327163696289,
+      "learning_rate": 2e-05,
+      "loss": 0.3477,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.9235769510269165,
+      "learning_rate": 2e-05,
+      "loss": 0.0969,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.7430696487426758,
+      "learning_rate": 2e-05,
+      "loss": 0.1968,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 5.987889289855957,
+      "learning_rate": 2e-05,
+      "loss": 0.5039,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 8.167346000671387,
+      "learning_rate": 2e-05,
+      "loss": 0.3647,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 7.413778781890869,
+      "learning_rate": 2e-05,
+      "loss": 0.3555,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.16605806350708,
+      "learning_rate": 2e-05,
+      "loss": 0.3892,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2.497659436793856e+16,
+      "train_loss": 0.23048248291015624,
+      "train_runtime": 395.796,
+      "train_samples_per_second": 1.011,
+      "train_steps_per_second": 0.253
+    }
+  ],
+  "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": 2.497659436793856e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf003a0715646d51d7d8dd69d21438f861fcc6bf462e5aa8b8d7752680923ad4
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c20bbb50c4867bd9ab7a8e7ba989ef137b20f09819a143823d4696a7bd86314
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a24d0cd89ede47f27ec36b49824613b974b1ad1d6f2ce20319ec7de50d1912d3
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:961c2839e9016d39e6c46226ca8319aff4d60ffa6c4c139c293d6bb9555fd5a3
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55a9ba8f67f33396c7161c03dd5de4bae4441d29685ab799357ff0caffb33145
+size 389170122

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a294262ae2a18fa9aaaeba2a89bf8e85512f01dc73429613b0ed7525403875
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8af1304b56ea2a178b1a623e04cbc466952d93a3685d3735b8f66ca282a1cb2e
+size 389170122

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:724fe45e0487e8d17e203794b8410bfaba92fc29067f298af8ed9447274c1f86
+size 389170122

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_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": 5.450788974761963,
+      "learning_rate": 2e-05,
+      "loss": 0.4023,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.3735480308532715,
+      "learning_rate": 2e-05,
+      "loss": 0.8789,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.179641008377075,
+      "learning_rate": 2e-05,
+      "loss": 0.2146,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.3362727165222168,
+      "learning_rate": 2e-05,
+      "loss": 0.2378,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.5938769578933716,
+      "learning_rate": 2e-05,
+      "loss": 0.2266,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.8245390057563782,
+      "learning_rate": 2e-05,
+      "loss": 0.113,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.9300125241279602,
+      "learning_rate": 2e-05,
+      "loss": 0.1543,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.7108556032180786,
+      "learning_rate": 2e-05,
+      "loss": 0.1973,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.0650441646575928,
+      "learning_rate": 2e-05,
+      "loss": 0.3037,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.7739357352256775,
+      "learning_rate": 2e-05,
+      "loss": 0.1987,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.9206535816192627,
+      "learning_rate": 2e-05,
+      "loss": 0.293,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 6.544978618621826,
+      "learning_rate": 2e-05,
+      "loss": 0.5303,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.8539941906929016,
+      "learning_rate": 2e-05,
+      "loss": 0.1707,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.50163733959198,
+      "learning_rate": 2e-05,
+      "loss": 0.3721,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.9231382012367249,
+      "learning_rate": 2e-05,
+      "loss": 0.3438,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.4241496324539185,
+      "learning_rate": 2e-05,
+      "loss": 0.2148,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.346113681793213,
+      "learning_rate": 2e-05,
+      "loss": 0.249,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.622445821762085,
+      "learning_rate": 2e-05,
+      "loss": 0.2319,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.527666449546814,
+      "learning_rate": 2e-05,
+      "loss": 0.2397,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.2725470066070557,
+      "learning_rate": 2e-05,
+      "loss": 0.2456,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.2991366386413574,
+      "learning_rate": 2e-05,
+      "loss": 0.2217,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.7729849815368652,
+      "learning_rate": 2e-05,
+      "loss": 0.2349,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.2132370471954346,
+      "learning_rate": 2e-05,
+      "loss": 0.3203,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.9868631958961487,
+      "learning_rate": 2e-05,
+      "loss": 0.1399,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.8213165998458862,
+      "learning_rate": 2e-05,
+      "loss": 0.3296,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.6022188663482666,
+      "learning_rate": 2e-05,
+      "loss": 0.1272,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 5.657681465148926,
+      "learning_rate": 2e-05,
+      "loss": 0.3325,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.7171556949615479,
+      "learning_rate": 2e-05,
+      "loss": 0.2881,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.9206146001815796,
+      "learning_rate": 2e-05,
+      "loss": 0.2173,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.2901687622070312,
+      "learning_rate": 2e-05,
+      "loss": 0.1465,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.38545823097229,
+      "learning_rate": 2e-05,
+      "loss": 0.1621,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.096327543258667,
+      "learning_rate": 2e-05,
+      "loss": 0.2964,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.434394359588623,
+      "learning_rate": 2e-05,
+      "loss": 0.3135,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.6365418434143066,
+      "learning_rate": 2e-05,
+      "loss": 0.085,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.9778931736946106,
+      "learning_rate": 2e-05,
+      "loss": 0.1101,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.0804357528686523,
+      "learning_rate": 2e-05,
+      "loss": 0.1011,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 8.342849731445312,
+      "learning_rate": 2e-05,
+      "loss": 0.0988,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.158697128295898,
+      "learning_rate": 2e-05,
+      "loss": 0.231,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.9794576168060303,
+      "learning_rate": 2e-05,
+      "loss": 0.3228,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.1897964477539062,
+      "learning_rate": 2e-05,
+      "loss": 0.0883,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.8258769512176514,
+      "learning_rate": 2e-05,
+      "loss": 0.2031,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 5.6181559562683105,
+      "learning_rate": 2e-05,
+      "loss": 0.3669,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.9324073791503906,
+      "learning_rate": 2e-05,
+      "loss": 0.2578,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 5.12706995010376,
+      "learning_rate": 2e-05,
+      "loss": 0.3032,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 6.049209117889404,
+      "learning_rate": 2e-05,
+      "loss": 0.3042,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.761207342147827,
+      "learning_rate": 2e-05,
+      "loss": 0.2314,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.6125823259353638,
+      "learning_rate": 2e-05,
+      "loss": 0.1582,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.5384273529052734,
+      "learning_rate": 2e-05,
+      "loss": 0.1904,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.4318525791168213,
+      "learning_rate": 2e-05,
+      "loss": 0.0905,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.46588173508644104,
+      "learning_rate": 2e-05,
+      "loss": 0.064,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2.7011800205623296e+16,
+      "train_loss": 0.24309326171875,
+      "train_runtime": 440.2463,
+      "train_samples_per_second": 0.909,
+      "train_steps_per_second": 0.227
+    }
+  ],
+  "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": 2.7011800205623296e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4179fd368b67028dd973f7abd88a2d2a03025f61ef13e87a1e8cbd6ce4fd382f
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff94ef4c83754c6ad4c8211c740a6727c24bc4aef38665e83b9de6338c9ea17
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3642f0c9dce5029bac42c5a27aff3ea37fd82a4c917ab8b4e7dcd5064a1e619c
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a0adbad2f5a8aa264d7936fdaff6b05707fe37b556aacd726bccddaca735b6d
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b8d8d8d43b5ceb413dcecdc8d13b620986f13fb0c744be8a6a62135b83a4f30
+size 389170122

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:729f2bc8bd697b0e8bd9dec495b719b3075d07b956bd6345027f7bc2031ce56f
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1b40d85f0086ea0f070724cf28d56f500cfd32f8102720ced8eef38895822c4
+size 389170122

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b179b032ff4cd4a2bcd2f9207e0ce04655651fdf93d07cf79590154002a5bd7
+size 389170122

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_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": 1.2775617837905884,
+      "learning_rate": 2e-05,
+      "loss": 0.0959,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6514262557029724,
+      "learning_rate": 2e-05,
+      "loss": 0.0951,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.4927728176116943,
+      "learning_rate": 2e-05,
+      "loss": 0.1514,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.7910555601119995,
+      "learning_rate": 2e-05,
+      "loss": 0.0729,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.8304953575134277,
+      "learning_rate": 2e-05,
+      "loss": 0.2334,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.3381283283233643,
+      "learning_rate": 2e-05,
+      "loss": 0.2092,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.2959333658218384,
+      "learning_rate": 2e-05,
+      "loss": 0.0399,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.57353138923645,
+      "learning_rate": 2e-05,
+      "loss": 0.3037,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.645243763923645,
+      "learning_rate": 2e-05,
+      "loss": 0.1586,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.9823670387268066,
+      "learning_rate": 2e-05,
+      "loss": 0.0765,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.530198812484741,
+      "learning_rate": 2e-05,
+      "loss": 0.1733,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.9225659966468811,
+      "learning_rate": 2e-05,
+      "loss": 0.2864,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 5.3893327713012695,
+      "learning_rate": 2e-05,
+      "loss": 0.8496,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.3154380321502686,
+      "learning_rate": 2e-05,
+      "loss": 0.4512,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.843571186065674,
+      "learning_rate": 2e-05,
+      "loss": 0.3457,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.980067729949951,
+      "learning_rate": 2e-05,
+      "loss": 0.2661,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.548189401626587,
+      "learning_rate": 2e-05,
+      "loss": 0.2275,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.518248438835144,
+      "learning_rate": 2e-05,
+      "loss": 0.3413,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.61312735080719,
+      "learning_rate": 2e-05,
+      "loss": 0.0928,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.421812534332275,
+      "learning_rate": 2e-05,
+      "loss": 0.293,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.13254289329051971,
+      "learning_rate": 2e-05,
+      "loss": 0.0839,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.1233917474746704,
+      "learning_rate": 2e-05,
+      "loss": 0.2109,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.286293864250183,
+      "learning_rate": 2e-05,
+      "loss": 0.2073,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5999717116355896,
+      "learning_rate": 2e-05,
+      "loss": 0.1538,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.8072141408920288,
+      "learning_rate": 2e-05,
+      "loss": 0.1875,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.4119832515716553,
+      "learning_rate": 2e-05,
+      "loss": 0.3901,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.0136523246765137,
+      "learning_rate": 2e-05,
+      "loss": 0.1553,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.5950088500976562,
+      "learning_rate": 2e-05,
+      "loss": 0.0686,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.3284698724746704,
+      "learning_rate": 2e-05,
+      "loss": 0.2051,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.8365779519081116,
+      "learning_rate": 2e-05,
+      "loss": 0.0698,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.1531637907028198,
+      "learning_rate": 2e-05,
+      "loss": 0.1392,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 5.157987117767334,
+      "learning_rate": 2e-05,
+      "loss": 0.3096,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.6640563011169434,
+      "learning_rate": 2e-05,
+      "loss": 0.3555,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.3148294985294342,
+      "learning_rate": 2e-05,
+      "loss": 0.0494,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.636918067932129,
+      "learning_rate": 2e-05,
+      "loss": 0.1895,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 4.029793739318848,
+      "learning_rate": 2e-05,
+      "loss": 0.2573,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.7756206393241882,
+      "learning_rate": 2e-05,
+      "loss": 0.2483,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.137673377990723,
+      "learning_rate": 2e-05,
+      "loss": 0.2288,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.653560161590576,
+      "learning_rate": 2e-05,
+      "loss": 0.1887,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.49356746673584,
+      "learning_rate": 2e-05,
+      "loss": 0.4987,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 6.035229682922363,
+      "learning_rate": 2e-05,
+      "loss": 0.2783,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 9.805408477783203,
+      "learning_rate": 2e-05,
+      "loss": 0.3604,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.5182745456695557,
+      "learning_rate": 2e-05,
+      "loss": 0.1099,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.8968892097473145,
+      "learning_rate": 2e-05,
+      "loss": 0.4873,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.410318374633789,
+      "learning_rate": 2e-05,
+      "loss": 0.0804,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.7177977561950684,
+      "learning_rate": 2e-05,
+      "loss": 0.3599,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.3571261167526245,
+      "learning_rate": 2e-05,
+      "loss": 0.1086,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.055740475654602,
+      "learning_rate": 2e-05,
+      "loss": 0.2812,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 5.602509498596191,
+      "learning_rate": 2e-05,
+      "loss": 0.1919,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4338890314102173,
+      "learning_rate": 2e-05,
+      "loss": 0.1665,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2.665628858266419e+16,
+      "train_loss": 0.2277008819580078,
+      "train_runtime": 433.6026,
+      "train_samples_per_second": 0.923,
+      "train_steps_per_second": 0.231
+    }
+  ],
+  "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": 2.665628858266419e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73c55ae4da4a9eb5ba0b74a710c4c1c538dade95131d4a7f43aa44f9a7150680
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eae3d7d81ae40241aa37d662628362786ee3bc318cdabd4056f28ec4a7325fe
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a813877ea30a92cea3df1dd7dbb8e79a464957ec3606ba43c7cb03e9cda613fe
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:773d23a64f72f59916f4e934e34309aef4352c3c691c1155a420f14d8248d7f6
+size 389170582

client_states_fedavg_bs4_saveoptim_lr2e-5_sc135_4tasks_5rounds_fixitr100_T0125_decay099/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c29d0e9bd3f3eac817566ff565c02b48193ff1a6f317b541b7b307a3fd8309c
+size 389170122