Upload folder using huggingface_hub

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:f1cca839a6000b85230580c3cb523ef92e5c03763db124a522f8c7bb88607aee
+size 180440142

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:bf9d18350e055b39ca5dad52b58bbf3e7c2e287f14d70e917e7236648c476bec
+size 180440142

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:ae408b7c41f30c80ee1fdb5b0728cf48ec831c3a1ffb082daa7de7338f7d2ed8
+size 180440142

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:c2b76e87a2e9700efdac5da11b74c0c5349915ee378939e6d874b3fc61e7f228
+size 180440142

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c6df8106ca65abe1a8e70c8407eae8785cb85b71893fb30c5d069e67caf712
+size 180439850

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:176ad4bfd417145e4051f4fe7c203ce4e8f31c86cda2fcc22bace0468d88ca88
+size 180440142

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3d0619b2b3932156534630bc25b07904f9a6a8df4429d822954a3ef0c473a7
+size 180439850

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86ced7aa854b5dd6d72d4d0e3390d1a2c64bb342a1b3b8efd632c6be6e8504b0
+size 180439850

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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": 5.389871120452881,
+      "learning_rate": 2e-05,
+      "loss": 1.837,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 7.913750648498535,
+      "learning_rate": 2e-05,
+      "loss": 1.5072,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.8081469535827637,
+      "learning_rate": 2e-05,
+      "loss": 1.9628,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.1584787368774414,
+      "learning_rate": 2e-05,
+      "loss": 1.2402,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.2553013563156128,
+      "learning_rate": 2e-05,
+      "loss": 0.4137,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.07167795300483704,
+      "learning_rate": 2e-05,
+      "loss": 0.5048,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.2355425357818604,
+      "learning_rate": 2e-05,
+      "loss": 1.1466,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.243406295776367,
+      "learning_rate": 2e-05,
+      "loss": 1.3616,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.1192171573638916,
+      "learning_rate": 2e-05,
+      "loss": 0.5938,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.964920163154602,
+      "learning_rate": 2e-05,
+      "loss": 0.6115,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.7399609088897705,
+      "learning_rate": 2e-05,
+      "loss": 0.3877,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.4627339839935303,
+      "learning_rate": 2e-05,
+      "loss": 3.434,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.5779869556427,
+      "learning_rate": 2e-05,
+      "loss": 1.3658,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.113224506378174,
+      "learning_rate": 2e-05,
+      "loss": 1.119,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.6840742826461792,
+      "learning_rate": 2e-05,
+      "loss": 0.4981,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.0056612491607666,
+      "learning_rate": 2e-05,
+      "loss": 0.9441,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.881331443786621,
+      "learning_rate": 2e-05,
+      "loss": 1.1007,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.5827242136001587,
+      "learning_rate": 2e-05,
+      "loss": 1.3904,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.0497872829437256,
+      "learning_rate": 2e-05,
+      "loss": 0.8498,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.5571120977401733,
+      "learning_rate": 2e-05,
+      "loss": 0.7427,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.50515615940094,
+      "learning_rate": 2e-05,
+      "loss": 0.5954,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.690471649169922,
+      "learning_rate": 2e-05,
+      "loss": 1.8239,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.0426018238067627,
+      "learning_rate": 2e-05,
+      "loss": 0.8085,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.374183654785156,
+      "learning_rate": 2e-05,
+      "loss": 1.0815,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.9751304388046265,
+      "learning_rate": 2e-05,
+      "loss": 0.4038,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.5408687591552734,
+      "learning_rate": 2e-05,
+      "loss": 0.8188,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.9847683906555176,
+      "learning_rate": 2e-05,
+      "loss": 1.5515,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.9399210214614868,
+      "learning_rate": 2e-05,
+      "loss": 0.516,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.8243143558502197,
+      "learning_rate": 2e-05,
+      "loss": 0.4914,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.0096545219421387,
+      "learning_rate": 2e-05,
+      "loss": 0.5824,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.177213191986084,
+      "learning_rate": 2e-05,
+      "loss": 0.8273,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.069615125656128,
+      "learning_rate": 2e-05,
+      "loss": 1.262,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.477707862854004,
+      "learning_rate": 2e-05,
+      "loss": 3.1642,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 4.157680034637451,
+      "learning_rate": 2e-05,
+      "loss": 1.7826,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.135859489440918,
+      "learning_rate": 2e-05,
+      "loss": 1.3506,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.74435293674469,
+      "learning_rate": 2e-05,
+      "loss": 0.9626,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.8117738962173462,
+      "learning_rate": 2e-05,
+      "loss": 0.748,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.52223801612854,
+      "learning_rate": 2e-05,
+      "loss": 1.0564,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.414597988128662,
+      "learning_rate": 2e-05,
+      "loss": 0.9622,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.8665771484375,
+      "learning_rate": 2e-05,
+      "loss": 0.3819,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.227982997894287,
+      "learning_rate": 2e-05,
+      "loss": 0.6077,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 2.479780912399292,
+      "learning_rate": 2e-05,
+      "loss": 1.1214,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 5.932579040527344,
+      "learning_rate": 2e-05,
+      "loss": 1.2493,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.6842375993728638,
+      "learning_rate": 2e-05,
+      "loss": 0.3546,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.6105072498321533,
+      "learning_rate": 2e-05,
+      "loss": 0.8795,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.8480112552642822,
+      "learning_rate": 2e-05,
+      "loss": 1.2564,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.4740058183670044,
+      "learning_rate": 2e-05,
+      "loss": 0.6387,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.9073842763900757,
+      "learning_rate": 2e-05,
+      "loss": 0.783,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.1106702089309692,
+      "learning_rate": 2e-05,
+      "loss": 1.1876,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.465167045593262,
+      "learning_rate": 2e-05,
+      "loss": 0.9835,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5535011444883456.0,
+      "train_loss": 1.0648856735229493,
+      "train_runtime": 136.9082,
+      "train_samples_per_second": 2.922,
+      "train_steps_per_second": 0.73
+    }
+  ],
+  "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": 5535011444883456.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426a6fa480cdee236f57ad8bd1e64f82ae6c8c08c336b37b68885bc020cf05c2
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:126b9ea9185472b6148b1009458028b25ed07a4225a36abfa17c2617a5119942
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da09528db24d62a6dbf1d13ea3571fec5c829ccf44e39bed0bfabcdfdb9d8f9
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:a3ec9b28b108540f69369acb8d9b021d5b8f731e686adee24e49aeb093b302b8
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561ae01465e3ce055e411d57a2566ab2a931b524238634f089ba5fec3d6db363
+size 389170122

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:fa6d2fc7920ad0af27cbfb4b5f3e1727671352e109fa655686b445ad69003e4c
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b59509bdbe736d456e7bbffe8c5fb030bb0cb522fbe269f3c9323dacc7fa89a
+size 389170122

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:371f56537c6cc23dcda83f899a38b9bd947cb7c0755f14c1deac18a9b9b2f68d
+size 389170122

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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": 1.2099864482879639,
+      "learning_rate": 2e-05,
+      "loss": 0.7102,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.4037203788757324,
+      "learning_rate": 2e-05,
+      "loss": 1.1519,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.8102778196334839,
+      "learning_rate": 2e-05,
+      "loss": 0.9684,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.821050763130188,
+      "learning_rate": 2e-05,
+      "loss": 0.5301,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.580217957496643,
+      "learning_rate": 2e-05,
+      "loss": 0.9518,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.8814568519592285,
+      "learning_rate": 2e-05,
+      "loss": 1.8458,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.3938233852386475,
+      "learning_rate": 2e-05,
+      "loss": 0.9475,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.641783356666565,
+      "learning_rate": 2e-05,
+      "loss": 1.1361,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.12887442111969,
+      "learning_rate": 2e-05,
+      "loss": 0.7893,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.1026272773742676,
+      "learning_rate": 2e-05,
+      "loss": 0.9656,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.3817358016967773,
+      "learning_rate": 2e-05,
+      "loss": 1.5276,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.19884991645813,
+      "learning_rate": 2e-05,
+      "loss": 0.8887,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.272486925125122,
+      "learning_rate": 2e-05,
+      "loss": 0.9409,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.282609701156616,
+      "learning_rate": 2e-05,
+      "loss": 1.4966,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.1684859991073608,
+      "learning_rate": 2e-05,
+      "loss": 1.2735,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.7757588028907776,
+      "learning_rate": 2e-05,
+      "loss": 2.7099,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.7310632467269897,
+      "learning_rate": 2e-05,
+      "loss": 0.8871,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.0317158699035645,
+      "learning_rate": 2e-05,
+      "loss": 0.9895,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.5124049186706543,
+      "learning_rate": 2e-05,
+      "loss": 1.317,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.9667242169380188,
+      "learning_rate": 2e-05,
+      "loss": 0.6481,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.8257367610931396,
+      "learning_rate": 2e-05,
+      "loss": 0.8701,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.1212313175201416,
+      "learning_rate": 2e-05,
+      "loss": 1.1708,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.276118040084839,
+      "learning_rate": 2e-05,
+      "loss": 1.0044,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.457052707672119,
+      "learning_rate": 2e-05,
+      "loss": 1.0235,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.5500776767730713,
+      "learning_rate": 2e-05,
+      "loss": 1.582,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.4070324897766113,
+      "learning_rate": 2e-05,
+      "loss": 1.9971,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.191951274871826,
+      "learning_rate": 2e-05,
+      "loss": 1.2354,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.1881375312805176,
+      "learning_rate": 2e-05,
+      "loss": 0.9124,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.418442964553833,
+      "learning_rate": 2e-05,
+      "loss": 1.196,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.8029783964157104,
+      "learning_rate": 2e-05,
+      "loss": 1.01,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.943813443183899,
+      "learning_rate": 2e-05,
+      "loss": 1.3572,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0548287630081177,
+      "learning_rate": 2e-05,
+      "loss": 0.9924,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 5.823477745056152,
+      "learning_rate": 2e-05,
+      "loss": 1.3245,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.152376413345337,
+      "learning_rate": 2e-05,
+      "loss": 1.3052,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.3831217288970947,
+      "learning_rate": 2e-05,
+      "loss": 1.1949,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.091294050216675,
+      "learning_rate": 2e-05,
+      "loss": 1.1667,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.1181700229644775,
+      "learning_rate": 2e-05,
+      "loss": 0.9937,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.2995938062667847,
+      "learning_rate": 2e-05,
+      "loss": 0.7476,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.4761587381362915,
+      "learning_rate": 2e-05,
+      "loss": 0.6168,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.78084135055542,
+      "learning_rate": 2e-05,
+      "loss": 1.0055,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.6266769170761108,
+      "learning_rate": 2e-05,
+      "loss": 1.4055,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 5.890852451324463,
+      "learning_rate": 2e-05,
+      "loss": 1.3506,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.300797939300537,
+      "learning_rate": 2e-05,
+      "loss": 0.9899,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.9619410037994385,
+      "learning_rate": 2e-05,
+      "loss": 1.158,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.9490997791290283,
+      "learning_rate": 2e-05,
+      "loss": 0.9689,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.6852408647537231,
+      "learning_rate": 2e-05,
+      "loss": 1.0103,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 5.842019557952881,
+      "learning_rate": 2e-05,
+      "loss": 1.546,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.3952200412750244,
+      "learning_rate": 2e-05,
+      "loss": 0.8511,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.604957103729248,
+      "learning_rate": 2e-05,
+      "loss": 0.7199,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.6361178159713745,
+      "learning_rate": 2e-05,
+      "loss": 1.0714,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.3244159611633664e+16,
+      "train_loss": 1.1290626525878906,
+      "train_runtime": 225.692,
+      "train_samples_per_second": 1.772,
+      "train_steps_per_second": 0.443
+    }
+  ],
+  "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": 1.3244159611633664e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0807db4338ab7a7d474fa8f7262b4fd4fe1cea1d99a5f168bf18ecec9ef12c
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f4a9a494715a8be98248261e6efb61e0724a29fa8dbd251bb1618ac5e66098
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:622c64fd65d2677a6ff472f9c1179ea6ee26f41e360fc66f96fe527557ad8b45
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:b10223f228633d93c35e78140b4e8e5379be4d4a5fe2c77de1bff27ce78e45aa
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:fa6e93b7a9598502f5c770e2e2311166fe22644f01d92a98ed0820e2e9631995
+size 389170122

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dad6c74c66eca0f729db8dd76453595a8ce5b3a051f531a2d02bae39d9644f8
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270cec05ffc3f2513dda5349f491335f377213b98445b828103e6e8eacf2e5d3
+size 389170122

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:a0721b69261ec658126151d66332e80e1dd8b0698ab1ea907ce713f11e8611af
+size 389170122

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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": 1.0289795398712158,
+      "learning_rate": 2e-05,
+      "loss": 0.5335,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6102533936500549,
+      "learning_rate": 2e-05,
+      "loss": 0.4069,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.9161092042922974,
+      "learning_rate": 2e-05,
+      "loss": 0.8354,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.4946720600128174,
+      "learning_rate": 2e-05,
+      "loss": 0.7206,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.380189418792725,
+      "learning_rate": 2e-05,
+      "loss": 1.1956,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.4468796253204346,
+      "learning_rate": 2e-05,
+      "loss": 0.4622,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.1074416637420654,
+      "learning_rate": 2e-05,
+      "loss": 1.6658,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.196979284286499,
+      "learning_rate": 2e-05,
+      "loss": 0.9451,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.555473566055298,
+      "learning_rate": 2e-05,
+      "loss": 0.4677,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.8904308676719666,
+      "learning_rate": 2e-05,
+      "loss": 0.6847,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.3065459728240967,
+      "learning_rate": 2e-05,
+      "loss": 0.3474,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.23778772354126,
+      "learning_rate": 2e-05,
+      "loss": 1.6669,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.0633652210235596,
+      "learning_rate": 2e-05,
+      "loss": 1.0448,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.159832715988159,
+      "learning_rate": 2e-05,
+      "loss": 1.2574,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 5.983434200286865,
+      "learning_rate": 2e-05,
+      "loss": 0.8387,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.2606232166290283,
+      "learning_rate": 2e-05,
+      "loss": 0.433,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.855712652206421,
+      "learning_rate": 2e-05,
+      "loss": 0.7482,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 6.815300941467285,
+      "learning_rate": 2e-05,
+      "loss": 0.6416,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.802886724472046,
+      "learning_rate": 2e-05,
+      "loss": 0.7273,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.7808118462562561,
+      "learning_rate": 2e-05,
+      "loss": 0.1985,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.313674211502075,
+      "learning_rate": 2e-05,
+      "loss": 0.6364,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 7.197145462036133,
+      "learning_rate": 2e-05,
+      "loss": 1.1568,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.7081199884414673,
+      "learning_rate": 2e-05,
+      "loss": 0.937,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.9655914306640625,
+      "learning_rate": 2e-05,
+      "loss": 0.5069,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.5406389236450195,
+      "learning_rate": 2e-05,
+      "loss": 0.6002,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 10.869454383850098,
+      "learning_rate": 2e-05,
+      "loss": 0.7676,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 10.128218650817871,
+      "learning_rate": 2e-05,
+      "loss": 2.3426,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 5.551089763641357,
+      "learning_rate": 2e-05,
+      "loss": 2.5984,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.7278666496276855,
+      "learning_rate": 2e-05,
+      "loss": 0.4457,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.7146732807159424,
+      "learning_rate": 2e-05,
+      "loss": 0.6715,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 5.558541297912598,
+      "learning_rate": 2e-05,
+      "loss": 1.3482,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.7671058177948,
+      "learning_rate": 2e-05,
+      "loss": 0.8286,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.145376205444336,
+      "learning_rate": 2e-05,
+      "loss": 1.6906,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.8701162338256836,
+      "learning_rate": 2e-05,
+      "loss": 0.7684,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 6.557702541351318,
+      "learning_rate": 2e-05,
+      "loss": 1.433,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.7119065523147583,
+      "learning_rate": 2e-05,
+      "loss": 0.5752,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.7837646007537842,
+      "learning_rate": 2e-05,
+      "loss": 0.6808,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 8.07896900177002,
+      "learning_rate": 2e-05,
+      "loss": 1.8413,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 5.091773509979248,
+      "learning_rate": 2e-05,
+      "loss": 1.1644,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.6711478233337402,
+      "learning_rate": 2e-05,
+      "loss": 0.8726,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.857771396636963,
+      "learning_rate": 2e-05,
+      "loss": 0.8909,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.943341016769409,
+      "learning_rate": 2e-05,
+      "loss": 0.5204,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.16873300075531,
+      "learning_rate": 2e-05,
+      "loss": 0.9623,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.725329399108887,
+      "learning_rate": 2e-05,
+      "loss": 1.1609,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5.48153018951416,
+      "learning_rate": 2e-05,
+      "loss": 1.1443,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.6034471988677979,
+      "learning_rate": 2e-05,
+      "loss": 0.762,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.3010993003845215,
+      "learning_rate": 2e-05,
+      "loss": 1.1309,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.12829327583313,
+      "learning_rate": 2e-05,
+      "loss": 0.6846,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.9714277982711792,
+      "learning_rate": 2e-05,
+      "loss": 0.5588,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1446884870529175,
+      "learning_rate": 2e-05,
+      "loss": 0.8131,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.5581131495702528e+16,
+      "train_loss": 0.926310920715332,
+      "train_runtime": 248.2955,
+      "train_samples_per_second": 1.611,
+      "train_steps_per_second": 0.403
+    }
+  ],
+  "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": 1.5581131495702528e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:e36f60212361bbfccbcad493cdc07f58f903cc5b26ec97b01cc2c7fe9d10af7b
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cc0950ab05e4bd2ff91260af512e1d3bcb386c17aaf1967c29cbdecadf496d1
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61075455fa883e80d3f5e40eb23b6ec9dbd7b323024842c8818e6d6bddca99ae
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:c218d2b1ddd8fbda4ebbc02cdfc52e08c2cf0d833b40cb79a554c84f8b2cf8bf
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:dc226c37298b921ad72a709271c310cb1853200d5329083c1b0c9edba8173603
+size 389170122

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1285b641c8c20c1a627caaa4e080366067fcabb4ede00871a43c9048756082ee
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:bd4cf7b9470bc33a1b208726dd61d3fb16469f17d2275782c2314eb069aee0f9
+size 389170122

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:a277d042f2f6279ba75231cfe7a4f10a02e921a1271b1670a3b114699366b7da
+size 389170122

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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": 1.3390214443206787,
+      "learning_rate": 2e-05,
+      "loss": 0.8941,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.9163679480552673,
+      "learning_rate": 2e-05,
+      "loss": 0.9235,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.5888918042182922,
+      "learning_rate": 2e-05,
+      "loss": 0.6486,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.30081573128700256,
+      "learning_rate": 2e-05,
+      "loss": 0.2813,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.4009698629379272,
+      "learning_rate": 2e-05,
+      "loss": 0.4144,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.2374634742736816,
+      "learning_rate": 2e-05,
+      "loss": 0.627,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.923579692840576,
+      "learning_rate": 2e-05,
+      "loss": 1.1054,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.857440710067749,
+      "learning_rate": 2e-05,
+      "loss": 0.9148,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.8682881593704224,
+      "learning_rate": 2e-05,
+      "loss": 0.3867,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.028822422027588,
+      "learning_rate": 2e-05,
+      "loss": 0.9991,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.2788021564483643,
+      "learning_rate": 2e-05,
+      "loss": 0.5667,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.953608989715576,
+      "learning_rate": 2e-05,
+      "loss": 0.9328,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.444178581237793,
+      "learning_rate": 2e-05,
+      "loss": 0.8467,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.8711784482002258,
+      "learning_rate": 2e-05,
+      "loss": 0.343,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.8109800815582275,
+      "learning_rate": 2e-05,
+      "loss": 0.3157,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.3886260986328125,
+      "learning_rate": 2e-05,
+      "loss": 0.7694,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.8276898860931396,
+      "learning_rate": 2e-05,
+      "loss": 1.0568,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.259130597114563,
+      "learning_rate": 2e-05,
+      "loss": 0.9007,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.4246671199798584,
+      "learning_rate": 2e-05,
+      "loss": 1.2372,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.6753697395324707,
+      "learning_rate": 2e-05,
+      "loss": 1.0153,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.6607201099395752,
+      "learning_rate": 2e-05,
+      "loss": 0.2803,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.2931270599365234,
+      "learning_rate": 2e-05,
+      "loss": 0.7531,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.034201741218567,
+      "learning_rate": 2e-05,
+      "loss": 0.5761,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.261017084121704,
+      "learning_rate": 2e-05,
+      "loss": 0.9825,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.7095365524291992,
+      "learning_rate": 2e-05,
+      "loss": 0.6045,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.2309482097625732,
+      "learning_rate": 2e-05,
+      "loss": 1.0364,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.170400381088257,
+      "learning_rate": 2e-05,
+      "loss": 2.1252,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.2634927034378052,
+      "learning_rate": 2e-05,
+      "loss": 0.1779,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.0210254192352295,
+      "learning_rate": 2e-05,
+      "loss": 0.7033,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.7227587103843689,
+      "learning_rate": 2e-05,
+      "loss": 0.3596,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.5512145757675171,
+      "learning_rate": 2e-05,
+      "loss": 0.2827,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.8612607717514038,
+      "learning_rate": 2e-05,
+      "loss": 0.3879,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.9014844298362732,
+      "learning_rate": 2e-05,
+      "loss": 0.8704,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5804516673088074,
+      "learning_rate": 2e-05,
+      "loss": 0.7523,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.9667078852653503,
+      "learning_rate": 2e-05,
+      "loss": 0.5082,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.913699150085449,
+      "learning_rate": 2e-05,
+      "loss": 0.8653,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.9874722957611084,
+      "learning_rate": 2e-05,
+      "loss": 0.5091,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.7036550045013428,
+      "learning_rate": 2e-05,
+      "loss": 0.6436,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.1027770042419434,
+      "learning_rate": 2e-05,
+      "loss": 0.7771,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.8439675569534302,
+      "learning_rate": 2e-05,
+      "loss": 0.2235,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 8.07174301147461,
+      "learning_rate": 2e-05,
+      "loss": 0.4817,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.4386396408081055,
+      "learning_rate": 2e-05,
+      "loss": 0.725,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.713127851486206,
+      "learning_rate": 2e-05,
+      "loss": 1.1037,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.2775169014930725,
+      "learning_rate": 2e-05,
+      "loss": 0.2505,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.276524543762207,
+      "learning_rate": 2e-05,
+      "loss": 1.7761,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 6.455582618713379,
+      "learning_rate": 2e-05,
+      "loss": 0.8323,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.1010710000991821,
+      "learning_rate": 2e-05,
+      "loss": 0.3133,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.4408540725708008,
+      "learning_rate": 2e-05,
+      "loss": 0.2172,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.2367064505815506,
+      "learning_rate": 2e-05,
+      "loss": 0.996,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.8455318212509155,
+      "learning_rate": 2e-05,
+      "loss": 0.4503,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2.002019803149107e+16,
+      "train_loss": 0.714879515171051,
+      "train_runtime": 248.3761,
+      "train_samples_per_second": 1.61,
+      "train_steps_per_second": 0.403
+    }
+  ],
+  "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": 2.002019803149107e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8083c948c51172cb731618e51b90a12546b054bf8762835f1d8f32c30904a0d5
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a0d9ba06d1bf534d64476ca8183bf94a7cdc5e70ec3d07c42837d157c9a4a0b
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e305ef4e1ba0d2ce1eabaa6f27d363d493e0800b1743aa78433ec86ed049f78
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:f6f79c8369cf454e0f47a9171dc1cabedfb911e727f8a2cc2373df780aae495e
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:b279129dda29d997289d3ed732f3f71df77a02625d140feb5553a9b77a65f530
+size 389170122

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:c1115eb7ff110cda959261def5f6bb34bd3f6074286ec6891c811e4b5fb3fab9
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:886257f645888c835465772d39b989f229623bd4da1529f6b28ef14ae2ffd167
+size 389170122

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:da72acd2878f27d6054be52695e145be79f4f1ed7b1fc8ce778cc5ef3ea2220c
+size 389170122

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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": 2.3232831954956055,
+      "learning_rate": 2e-05,
+      "loss": 1.0249,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.5343315601348877,
+      "learning_rate": 2e-05,
+      "loss": 0.8533,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.305483341217041,
+      "learning_rate": 2e-05,
+      "loss": 0.3197,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.517935037612915,
+      "learning_rate": 2e-05,
+      "loss": 1.1904,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.153202533721924,
+      "learning_rate": 2e-05,
+      "loss": 2.3176,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.158588171005249,
+      "learning_rate": 2e-05,
+      "loss": 0.7701,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.5296018719673157,
+      "learning_rate": 2e-05,
+      "loss": 0.5261,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.1179733276367188,
+      "learning_rate": 2e-05,
+      "loss": 0.5498,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.0289561748504639,
+      "learning_rate": 2e-05,
+      "loss": 0.4771,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.6146349906921387,
+      "learning_rate": 2e-05,
+      "loss": 0.9022,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.7544004917144775,
+      "learning_rate": 2e-05,
+      "loss": 0.9887,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.7699713706970215,
+      "learning_rate": 2e-05,
+      "loss": 1.5863,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 6.096447944641113,
+      "learning_rate": 2e-05,
+      "loss": 1.7896,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.786501169204712,
+      "learning_rate": 2e-05,
+      "loss": 0.9298,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.055405616760254,
+      "learning_rate": 2e-05,
+      "loss": 1.8627,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.4495849609375,
+      "learning_rate": 2e-05,
+      "loss": 0.5812,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.9012460708618164,
+      "learning_rate": 2e-05,
+      "loss": 0.2027,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.7602607011795044,
+      "learning_rate": 2e-05,
+      "loss": 0.5884,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.8072483539581299,
+      "learning_rate": 2e-05,
+      "loss": 1.1502,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.375112295150757,
+      "learning_rate": 2e-05,
+      "loss": 0.7885,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.289775371551514,
+      "learning_rate": 2e-05,
+      "loss": 2.5796,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.5001745223999023,
+      "learning_rate": 2e-05,
+      "loss": 0.6879,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.169258952140808,
+      "learning_rate": 2e-05,
+      "loss": 0.8135,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.9684996604919434,
+      "learning_rate": 2e-05,
+      "loss": 0.9738,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.281973361968994,
+      "learning_rate": 2e-05,
+      "loss": 1.1334,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.8545925617218018,
+      "learning_rate": 2e-05,
+      "loss": 0.7442,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 6.913942337036133,
+      "learning_rate": 2e-05,
+      "loss": 1.2487,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.960796356201172,
+      "learning_rate": 2e-05,
+      "loss": 2.6527,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.8161797523498535,
+      "learning_rate": 2e-05,
+      "loss": 1.2346,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.4226303100585938,
+      "learning_rate": 2e-05,
+      "loss": 1.4142,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.7144083976745605,
+      "learning_rate": 2e-05,
+      "loss": 0.6787,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.2450892925262451,
+      "learning_rate": 2e-05,
+      "loss": 0.6321,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.3646719455718994,
+      "learning_rate": 2e-05,
+      "loss": 0.6567,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.297370195388794,
+      "learning_rate": 2e-05,
+      "loss": 1.6927,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.9890066385269165,
+      "learning_rate": 2e-05,
+      "loss": 1.2573,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 4.081875801086426,
+      "learning_rate": 2e-05,
+      "loss": 1.2384,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.1986734867095947,
+      "learning_rate": 2e-05,
+      "loss": 0.3413,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.6766782402992249,
+      "learning_rate": 2e-05,
+      "loss": 0.3358,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.628237724304199,
+      "learning_rate": 2e-05,
+      "loss": 0.882,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.969377040863037,
+      "learning_rate": 2e-05,
+      "loss": 1.4629,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.985935688018799,
+      "learning_rate": 2e-05,
+      "loss": 0.8891,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.395092010498047,
+      "learning_rate": 2e-05,
+      "loss": 0.2739,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.5362117290496826,
+      "learning_rate": 2e-05,
+      "loss": 0.0327,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.663097858428955,
+      "learning_rate": 2e-05,
+      "loss": 1.3678,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 8.288853645324707,
+      "learning_rate": 2e-05,
+      "loss": 0.8778,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.423278570175171,
+      "learning_rate": 2e-05,
+      "loss": 0.9577,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.7824862003326416,
+      "learning_rate": 2e-05,
+      "loss": 1.774,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.8134786486625671,
+      "learning_rate": 2e-05,
+      "loss": 0.3738,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.9615880250930786,
+      "learning_rate": 2e-05,
+      "loss": 0.6358,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.486088752746582,
+      "learning_rate": 2e-05,
+      "loss": 0.4703,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 2.0033979121926144e+16,
+      "train_loss": 0.9942560279369355,
+      "train_runtime": 250.7882,
+      "train_samples_per_second": 1.595,
+      "train_steps_per_second": 0.399
+    }
+  ],
+  "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": 2.0033979121926144e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6337f27b607152eee0d1b4ea2358cf08126147b4914b73bd5a8c8903c1ab0ced
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_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:fc2c476c9efb2d640b2d4693eb7ca33ed8a81427598a6ce8616fa53381917a31
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932993b3ff1dc5e604696e5e767669c7c0b93343ea098462f7627f54cd9eba93
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c75322d52cd772b2db81ae2fa8c3c26dadfd35e55af48985ff630b2144b0af6
+size 389170582

client_states_fedavg_hetero_bs4_saveoptim_lr2e-5_sc132_4tasks_5rounds_fixitr100_T0125_decay099_SEED2/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56d327dca77c8944915eddac9b6933354e5d84bce5c15992ac927cdd1e864ad3
+size 389170122