Upload folder using huggingface_hub

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd9b72c102467a54798d17af40216bfda340a47e9c928110d991498f37352fe
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e25c6ccda7c6e331ba742be5fd51d6f69b5f4b378d4f279cbf21631e693c713
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579af869f114095f217068552a0c40d05ebcb9e89cda67b5455ec2d2694a2c20
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f10e15c3e0c6e60298a05d6907c98495e7ada8a1f57764544fd3fe18156250
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7902b8470612bde23149de6ce83d22e0a10cda6fe6527ca93a47cd0c8067afe
+size 389170122

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc6bf0700f807db2c7cbfd1d47510b21c70c0365cb1a5c3a099a7e21ad210582
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a299ef241e8f742ea1657eafa2f0aa5ebbe006a0197111f56758dd2dc6b3499
+size 389170122

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5138f690d9121a2e0460ccffc2733e479cc693db04a3525cce8af64bb024be7a
+size 389170122

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/0_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.894064426422119,
+      "learning_rate": 2e-05,
+      "loss": 0.9085,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.3201831579208374,
+      "learning_rate": 2e-05,
+      "loss": 0.3126,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.121770143508911,
+      "learning_rate": 2e-05,
+      "loss": 0.7891,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.0768280029296875,
+      "learning_rate": 2e-05,
+      "loss": 1.0664,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.1001958847045898,
+      "learning_rate": 2e-05,
+      "loss": 1.078,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.823949098587036,
+      "learning_rate": 2e-05,
+      "loss": 0.3738,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.2138632535934448,
+      "learning_rate": 2e-05,
+      "loss": 0.1228,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.490877628326416,
+      "learning_rate": 2e-05,
+      "loss": 0.6624,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 9.688061714172363,
+      "learning_rate": 2e-05,
+      "loss": 1.0531,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.0712640285491943,
+      "learning_rate": 2e-05,
+      "loss": 2.184,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.8509835004806519,
+      "learning_rate": 2e-05,
+      "loss": 0.1043,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.7280430793762207,
+      "learning_rate": 2e-05,
+      "loss": 0.1391,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.14078085124492645,
+      "learning_rate": 2e-05,
+      "loss": 0.0165,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 9.411897659301758,
+      "learning_rate": 2e-05,
+      "loss": 1.9539,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2108028680086136,
+      "learning_rate": 2e-05,
+      "loss": 0.0312,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.6999951601028442,
+      "learning_rate": 2e-05,
+      "loss": 0.5234,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.3077850341796875,
+      "learning_rate": 2e-05,
+      "loss": 0.8673,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.1280887871980667,
+      "learning_rate": 2e-05,
+      "loss": 0.2362,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.76698637008667,
+      "learning_rate": 2e-05,
+      "loss": 0.1529,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.7104475498199463,
+      "learning_rate": 2e-05,
+      "loss": 0.6142,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.521893322467804,
+      "learning_rate": 2e-05,
+      "loss": 0.1496,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.5190557837486267,
+      "learning_rate": 2e-05,
+      "loss": 0.5708,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.1117076873779297,
+      "learning_rate": 2e-05,
+      "loss": 0.5076,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.133110523223877,
+      "learning_rate": 2e-05,
+      "loss": 0.7732,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.7691269516944885,
+      "learning_rate": 2e-05,
+      "loss": 0.2829,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.188059091567993,
+      "learning_rate": 2e-05,
+      "loss": 0.7398,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.092348575592041,
+      "learning_rate": 2e-05,
+      "loss": 0.299,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.5498709678649902,
+      "learning_rate": 2e-05,
+      "loss": 1.4419,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.921797275543213,
+      "learning_rate": 2e-05,
+      "loss": 0.285,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.740967273712158,
+      "learning_rate": 2e-05,
+      "loss": 0.6471,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.9472544193267822,
+      "learning_rate": 2e-05,
+      "loss": 1.4534,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.546498715877533,
+      "learning_rate": 2e-05,
+      "loss": 0.0518,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 6.151440143585205,
+      "learning_rate": 2e-05,
+      "loss": 1.2357,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.18737871944904327,
+      "learning_rate": 2e-05,
+      "loss": 0.1359,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.142384052276611,
+      "learning_rate": 2e-05,
+      "loss": 0.6293,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.109649419784546,
+      "learning_rate": 2e-05,
+      "loss": 0.0879,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.949535608291626,
+      "learning_rate": 2e-05,
+      "loss": 0.4062,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.329496145248413,
+      "learning_rate": 2e-05,
+      "loss": 1.1151,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.8130714893341064,
+      "learning_rate": 2e-05,
+      "loss": 1.1395,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.4879205226898193,
+      "learning_rate": 2e-05,
+      "loss": 0.167,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.950775384902954,
+      "learning_rate": 2e-05,
+      "loss": 1.5502,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 2.520659923553467,
+      "learning_rate": 2e-05,
+      "loss": 0.4802,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.47688207030296326,
+      "learning_rate": 2e-05,
+      "loss": 0.2397,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.8515924215316772,
+      "learning_rate": 2e-05,
+      "loss": 0.1466,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.2912800312042236,
+      "learning_rate": 2e-05,
+      "loss": 0.1982,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.22282549738883972,
+      "learning_rate": 2e-05,
+      "loss": 0.0881,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.608417272567749,
+      "learning_rate": 2e-05,
+      "loss": 0.3884,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.5378755331039429,
+      "learning_rate": 2e-05,
+      "loss": 0.1059,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.9015717506408691,
+      "learning_rate": 2e-05,
+      "loss": 0.417,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.07535640150308609,
+      "learning_rate": 2e-05,
+      "loss": 0.2791,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 4974012128034816.0,
+      "train_loss": 0.5840333950519562,
+      "train_runtime": 160.7903,
+      "train_samples_per_second": 2.488,
+      "train_steps_per_second": 0.622
+    }
+  ],
+  "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": 4974012128034816.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:040fc1ba02166da25b53124eafd7ab770676f8ae9902cfdaa1fd9419fb975fb8
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66b27e044a5bef36de82e366639214d4b09b43709be6e33cf4e497de1d123f7b
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae2913055c4818c7fd3525c69ed67558d07bfdf1a04928bf20b6e0ec84589bd
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a750a9eaf2737a6051a7e2f44d5637e00df4c42ad6bf3f2cb5efe4548e30071
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b6c4b1a4df16e1fd1d9aaaaa959fb6ccc43c475a8a7642a0a98dcce7ecdf5e
+size 389170122

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa4f8cff476a8ac9e4d7d695aa2237b7ff0a1a1c4f5e21d166ecf80155bcc78
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db54eaad21943935cf7a0ac6fb6e20d00916bf5ebd09fcb20ef845668c17e76
+size 389170122

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d949af7f4e051c441c783d35219de277685e59671951e697ba610a0b6817109
+size 389170122

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/1_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.7926690578460693,
+      "learning_rate": 2e-05,
+      "loss": 0.3634,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6020875573158264,
+      "learning_rate": 2e-05,
+      "loss": 0.5082,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.04904913157224655,
+      "learning_rate": 2e-05,
+      "loss": 0.003,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.08567889034748077,
+      "learning_rate": 2e-05,
+      "loss": 0.0071,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.0006135515286587179,
+      "learning_rate": 2e-05,
+      "loss": 0.0015,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.915755033493042,
+      "learning_rate": 2e-05,
+      "loss": 0.1474,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.04489617794752121,
+      "learning_rate": 2e-05,
+      "loss": 0.0029,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.003059796988964081,
+      "learning_rate": 2e-05,
+      "loss": 0.0024,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.012128287926316261,
+      "learning_rate": 2e-05,
+      "loss": 0.0009,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.003509308211505413,
+      "learning_rate": 2e-05,
+      "loss": 0.0098,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.6594346165657043,
+      "learning_rate": 2e-05,
+      "loss": 0.1193,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.0088326930999756,
+      "learning_rate": 2e-05,
+      "loss": 0.1751,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.003368888283148408,
+      "learning_rate": 2e-05,
+      "loss": 0.0002,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.09144292771816254,
+      "learning_rate": 2e-05,
+      "loss": 0.2113,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.0011707392986863852,
+      "learning_rate": 2e-05,
+      "loss": 0.0006,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.00044834177242591977,
+      "learning_rate": 2e-05,
+      "loss": 0.0001,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.0155986612662673,
+      "learning_rate": 2e-05,
+      "loss": 0.0009,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.008986121974885464,
+      "learning_rate": 2e-05,
+      "loss": 0.0024,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.0013730537611991167,
+      "learning_rate": 2e-05,
+      "loss": 0.0001,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.0022560814395546913,
+      "learning_rate": 2e-05,
+      "loss": 0.1583,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.7707070112228394,
+      "learning_rate": 2e-05,
+      "loss": 0.0477,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.0005886413273401558,
+      "learning_rate": 2e-05,
+      "loss": 0.5489,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.003063227515667677,
+      "learning_rate": 2e-05,
+      "loss": 0.0086,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.0037043734919279814,
+      "learning_rate": 2e-05,
+      "loss": 0.0003,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.0012796800583600998,
+      "learning_rate": 2e-05,
+      "loss": 0.0012,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.010248442180454731,
+      "learning_rate": 2e-05,
+      "loss": 0.0005,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.0034741233102977276,
+      "learning_rate": 2e-05,
+      "loss": 0.0003,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.1743801087141037,
+      "learning_rate": 2e-05,
+      "loss": 0.0068,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.007030021399259567,
+      "learning_rate": 2e-05,
+      "loss": 0.2121,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.19218796491622925,
+      "learning_rate": 2e-05,
+      "loss": 0.0046,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.00157554994802922,
+      "learning_rate": 2e-05,
+      "loss": 0.0013,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.0012670699506998062,
+      "learning_rate": 2e-05,
+      "loss": 0.0001,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.20495271682739258,
+      "learning_rate": 2e-05,
+      "loss": 0.18,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.24123035371303558,
+      "learning_rate": 2e-05,
+      "loss": 0.0098,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.5640333890914917,
+      "learning_rate": 2e-05,
+      "loss": 0.0182,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.00047914290917105973,
+      "learning_rate": 2e-05,
+      "loss": 0.0003,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.05535870045423508,
+      "learning_rate": 2e-05,
+      "loss": 0.0027,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.9184343814849854,
+      "learning_rate": 2e-05,
+      "loss": 0.0988,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.017705975100398064,
+      "learning_rate": 2e-05,
+      "loss": 0.1589,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.9290534257888794,
+      "learning_rate": 2e-05,
+      "loss": 0.0509,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.0019139001378789544,
+      "learning_rate": 2e-05,
+      "loss": 0.0002,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.03513801470398903,
+      "learning_rate": 2e-05,
+      "loss": 0.0049,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.005002826452255249,
+      "learning_rate": 2e-05,
+      "loss": 0.023,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.006781861651688814,
+      "learning_rate": 2e-05,
+      "loss": 0.0004,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.44860827922821045,
+      "learning_rate": 2e-05,
+      "loss": 0.0252,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.0025509921833872795,
+      "learning_rate": 2e-05,
+      "loss": 0.2639,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1632906198501587,
+      "learning_rate": 2e-05,
+      "loss": 0.0047,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.006769334431737661,
+      "learning_rate": 2e-05,
+      "loss": 0.0002,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.008943594060838223,
+      "learning_rate": 2e-05,
+      "loss": 0.0038,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0011910570319741964,
+      "learning_rate": 2e-05,
+      "loss": 0.0005,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5013697617461248.0,
+      "train_loss": 0.06788168847560883,
+      "train_runtime": 159.9459,
+      "train_samples_per_second": 2.501,
+      "train_steps_per_second": 0.625
+    }
+  ],
+  "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": 5013697617461248.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97178d8b4ef002af17e1c1babc854b69d498b28af4f39cce2d0dd39fedbde7ce
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8066065f2acdac23b4511d758ce20c24502ec9ab5def97b2e7bc0b46c963210
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc26b83020d42b0beeabe2c32501098b86237d6c8f2feed8bbe7ab778d51e88
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b988bdabff0eebbb189e63cc27e00dcece2b2ac4230235431dcb0f98f3df503d
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d2e4922163550bfb783bf8cdf258af5a948ad085565b2004a5054284dbaa21
+size 389170122

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9418ec35221a73971914591676bda02aaa4cc416f5bf8770c359c850795549
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fbbcfcb71a48141155ec932e5d4f9d86d306cec4d8589381b8e7d98b2317a5a
+size 389170122

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de2ff3db9a0037bfab3244f817729ff083e6446bb75dd088cd91b89d1bccaf4e
+size 389170122

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/2_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.9014546871185303,
+      "learning_rate": 2e-05,
+      "loss": 0.8479,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.2428691387176514,
+      "learning_rate": 2e-05,
+      "loss": 0.5352,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.7876530289649963,
+      "learning_rate": 2e-05,
+      "loss": 0.197,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.0728108882904053,
+      "learning_rate": 2e-05,
+      "loss": 0.3382,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.316784620285034,
+      "learning_rate": 2e-05,
+      "loss": 0.4009,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.4547951221466064,
+      "learning_rate": 2e-05,
+      "loss": 1.1106,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.191783428192139,
+      "learning_rate": 2e-05,
+      "loss": 1.1847,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.597446918487549,
+      "learning_rate": 2e-05,
+      "loss": 0.5215,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.2228509187698364,
+      "learning_rate": 2e-05,
+      "loss": 0.2476,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.161182880401611,
+      "learning_rate": 2e-05,
+      "loss": 1.322,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.1612755060195923,
+      "learning_rate": 2e-05,
+      "loss": 0.3423,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.0303940773010254,
+      "learning_rate": 2e-05,
+      "loss": 0.3911,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.7589966058731079,
+      "learning_rate": 2e-05,
+      "loss": 0.237,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.836357593536377,
+      "learning_rate": 2e-05,
+      "loss": 1.1011,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.2222888469696045,
+      "learning_rate": 2e-05,
+      "loss": 1.3152,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.079301118850708,
+      "learning_rate": 2e-05,
+      "loss": 0.6851,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 5.449805736541748,
+      "learning_rate": 2e-05,
+      "loss": 1.6285,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.7335667610168457,
+      "learning_rate": 2e-05,
+      "loss": 0.1028,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 5.621280670166016,
+      "learning_rate": 2e-05,
+      "loss": 0.8429,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.6560351848602295,
+      "learning_rate": 2e-05,
+      "loss": 0.3729,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.6034119129180908,
+      "learning_rate": 2e-05,
+      "loss": 0.0629,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.0162291526794434,
+      "learning_rate": 2e-05,
+      "loss": 0.2953,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5169147849082947,
+      "learning_rate": 2e-05,
+      "loss": 0.3583,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.3467202186584473,
+      "learning_rate": 2e-05,
+      "loss": 0.2518,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.08579041063785553,
+      "learning_rate": 2e-05,
+      "loss": 0.1946,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.8094596266746521,
+      "learning_rate": 2e-05,
+      "loss": 0.4245,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.2027623653411865,
+      "learning_rate": 2e-05,
+      "loss": 0.9185,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 6.3284478187561035,
+      "learning_rate": 2e-05,
+      "loss": 1.153,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 5.553554058074951,
+      "learning_rate": 2e-05,
+      "loss": 1.1882,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.07298469543457,
+      "learning_rate": 2e-05,
+      "loss": 0.657,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.5594613552093506,
+      "learning_rate": 2e-05,
+      "loss": 0.1507,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.9592647552490234,
+      "learning_rate": 2e-05,
+      "loss": 0.5403,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.393865704536438,
+      "learning_rate": 2e-05,
+      "loss": 0.214,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.127103567123413,
+      "learning_rate": 2e-05,
+      "loss": 0.578,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.9923616647720337,
+      "learning_rate": 2e-05,
+      "loss": 0.475,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.7169052362442017,
+      "learning_rate": 2e-05,
+      "loss": 0.6912,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.8878061771392822,
+      "learning_rate": 2e-05,
+      "loss": 0.5777,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.5864697098731995,
+      "learning_rate": 2e-05,
+      "loss": 0.3095,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.0971084833145142,
+      "learning_rate": 2e-05,
+      "loss": 0.4023,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.0812549591064453,
+      "learning_rate": 2e-05,
+      "loss": 1.4656,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.087915301322937,
+      "learning_rate": 2e-05,
+      "loss": 0.6259,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.559573233127594,
+      "learning_rate": 2e-05,
+      "loss": 0.2886,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 5.675575256347656,
+      "learning_rate": 2e-05,
+      "loss": 0.8127,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.2897826433181763,
+      "learning_rate": 2e-05,
+      "loss": 0.2609,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.957866668701172,
+      "learning_rate": 2e-05,
+      "loss": 0.2235,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.3432726860046387,
+      "learning_rate": 2e-05,
+      "loss": 0.657,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 5.912756443023682,
+      "learning_rate": 2e-05,
+      "loss": 0.6071,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.4021425247192383,
+      "learning_rate": 2e-05,
+      "loss": 0.6625,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.7503753900527954,
+      "learning_rate": 2e-05,
+      "loss": 0.4068,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.381590366363525,
+      "learning_rate": 2e-05,
+      "loss": 0.9321,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 4913814755606528.0,
+      "train_loss": 0.6022030544281006,
+      "train_runtime": 160.1433,
+      "train_samples_per_second": 2.498,
+      "train_steps_per_second": 0.624
+    }
+  ],
+  "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": 4913814755606528.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12662a115ad2c2c1782b5a4b2a2b9b626b7b21bfffefe471f1cf0884dbc07775
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf633a0b5fb896130a3119571a77f610cee784ce26f06017aa6146af6a1e7291
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0d932a65e55df3cc8f20317dd81eece079e91c19ea65c942cbfd669a3969f3
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6852d881c1f756efb68d80a21cfc2dd501ff10349dfd6fac3517650134d2471
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5a706e5f71613a148a641e094205e1d97e0b4f5776f1715a10269608796e6d
+size 389170122

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ea36682ef1abda8799e6bada7ecdd090db0bcbaf6f371a0cede135e0e44b35
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b171e756d9c7f4c802172c232f513ca798305059851682ff0f5d1c797e99bd0
+size 389170122

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0238c056c8e82b97d019db62946e1d34fc3a8c834ab8cb1bef720927562f6cdb
+size 389170122

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/3_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.097942590713501,
+      "learning_rate": 2e-05,
+      "loss": 0.5807,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.9074313640594482,
+      "learning_rate": 2e-05,
+      "loss": 1.5071,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.6304781436920166,
+      "learning_rate": 2e-05,
+      "loss": 0.4908,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.46525764465332,
+      "learning_rate": 2e-05,
+      "loss": 1.0056,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.3878512382507324,
+      "learning_rate": 2e-05,
+      "loss": 0.3701,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.7448008060455322,
+      "learning_rate": 2e-05,
+      "loss": 1.0356,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.3460839986801147,
+      "learning_rate": 2e-05,
+      "loss": 0.2344,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.188470363616943,
+      "learning_rate": 2e-05,
+      "loss": 0.8728,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.190163612365723,
+      "learning_rate": 2e-05,
+      "loss": 1.6686,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.3317737579345703,
+      "learning_rate": 2e-05,
+      "loss": 1.6924,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.992833137512207,
+      "learning_rate": 2e-05,
+      "loss": 0.6843,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.71842098236084,
+      "learning_rate": 2e-05,
+      "loss": 0.8008,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.7787336111068726,
+      "learning_rate": 2e-05,
+      "loss": 0.4146,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.0199549198150635,
+      "learning_rate": 2e-05,
+      "loss": 0.7224,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.692366123199463,
+      "learning_rate": 2e-05,
+      "loss": 1.0116,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 6.386943340301514,
+      "learning_rate": 2e-05,
+      "loss": 1.5629,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.464090585708618,
+      "learning_rate": 2e-05,
+      "loss": 1.045,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 5.253996849060059,
+      "learning_rate": 2e-05,
+      "loss": 0.8652,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.0147178173065186,
+      "learning_rate": 2e-05,
+      "loss": 0.8926,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.174330234527588,
+      "learning_rate": 2e-05,
+      "loss": 0.5714,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 5.197195053100586,
+      "learning_rate": 2e-05,
+      "loss": 2.0066,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.705170631408691,
+      "learning_rate": 2e-05,
+      "loss": 0.8634,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.936582088470459,
+      "learning_rate": 2e-05,
+      "loss": 0.688,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.3450106382369995,
+      "learning_rate": 2e-05,
+      "loss": 0.8493,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.475832223892212,
+      "learning_rate": 2e-05,
+      "loss": 1.1124,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.734349012374878,
+      "learning_rate": 2e-05,
+      "loss": 0.4247,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 6.65780782699585,
+      "learning_rate": 2e-05,
+      "loss": 1.8004,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.2812113761901855,
+      "learning_rate": 2e-05,
+      "loss": 0.8878,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 6.450176239013672,
+      "learning_rate": 2e-05,
+      "loss": 1.1367,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.53096079826355,
+      "learning_rate": 2e-05,
+      "loss": 1.2302,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.3121376037597656,
+      "learning_rate": 2e-05,
+      "loss": 0.3248,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.2921791076660156,
+      "learning_rate": 2e-05,
+      "loss": 0.9923,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.9732469320297241,
+      "learning_rate": 2e-05,
+      "loss": 0.3496,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 19.43094253540039,
+      "learning_rate": 2e-05,
+      "loss": 1.545,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.824756383895874,
+      "learning_rate": 2e-05,
+      "loss": 1.0909,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.171675205230713,
+      "learning_rate": 2e-05,
+      "loss": 1.377,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 4.2659010887146,
+      "learning_rate": 2e-05,
+      "loss": 0.9467,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.9447065591812134,
+      "learning_rate": 2e-05,
+      "loss": 0.3376,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 4.128762245178223,
+      "learning_rate": 2e-05,
+      "loss": 1.0416,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.5198454856872559,
+      "learning_rate": 2e-05,
+      "loss": 0.495,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.582706093788147,
+      "learning_rate": 2e-05,
+      "loss": 1.2556,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 2.893664836883545,
+      "learning_rate": 2e-05,
+      "loss": 0.3995,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.9730072021484375,
+      "learning_rate": 2e-05,
+      "loss": 1.1895,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.6474361419677734,
+      "learning_rate": 2e-05,
+      "loss": 2.0776,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5.00705623626709,
+      "learning_rate": 2e-05,
+      "loss": 1.5599,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.9408862590789795,
+      "learning_rate": 2e-05,
+      "loss": 0.8146,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.137223958969116,
+      "learning_rate": 2e-05,
+      "loss": 1.1117,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.60581636428833,
+      "learning_rate": 2e-05,
+      "loss": 1.0244,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.505368947982788,
+      "learning_rate": 2e-05,
+      "loss": 0.389,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.0294015407562256,
+      "learning_rate": 2e-05,
+      "loss": 0.345,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5082403345268736.0,
+      "train_loss": 0.9539071077108383,
+      "train_runtime": 160.1565,
+      "train_samples_per_second": 2.498,
+      "train_steps_per_second": 0.624
+    }
+  ],
+  "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": 5082403345268736.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5c4705c320eddc8a7424fda148c8b02e628026e27bcf1434e4f0c6d74e5d138
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a9165cbc5b90d7e2f92b1037f052e1af20ee867c99dae80afc8c384c2a838a3
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d47fa91dd65b087cc768981cdd66f10cf523ee2fca6f9d6215d3fddc164361a
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8799bd379e86ab9d60e4f9d5cc1dad0d3a7db5f0cc8db96502ae0c0cc5153c
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf20522100437eb2f78d58fd3a6f25ec8a70fff9f2a2655f8f213a2b8ef52045
+size 389170122

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f1850bc34be260602927eced981c1f91bb98c31eaf3c265e216c4d225d3ea5
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b28c6aaf6947b5e7f00736d094de8ae17ffa1a505d1c0450dc8bc825e6dae9
+size 389170122

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7141336f1173475c9692c2668fcdbf5a26bad47c86d62f45b5794f9e3d4f0f38
+size 389170122

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/4_trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.7694361209869385,
+      "learning_rate": 2e-05,
+      "loss": 0.6797,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.712048053741455,
+      "learning_rate": 2e-05,
+      "loss": 0.3863,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.2159461975097656,
+      "learning_rate": 2e-05,
+      "loss": 0.8038,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.892475128173828,
+      "learning_rate": 2e-05,
+      "loss": 2.343,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.8474981784820557,
+      "learning_rate": 2e-05,
+      "loss": 0.7891,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.7567367553710938,
+      "learning_rate": 2e-05,
+      "loss": 1.2256,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.1084630489349365,
+      "learning_rate": 2e-05,
+      "loss": 0.5378,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.597458600997925,
+      "learning_rate": 2e-05,
+      "loss": 1.1296,
+      "step": 16
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.7688543796539307,
+      "learning_rate": 2e-05,
+      "loss": 1.6792,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.0053212642669678,
+      "learning_rate": 2e-05,
+      "loss": 0.8291,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.2323999404907227,
+      "learning_rate": 2e-05,
+      "loss": 0.7659,
+      "step": 22
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.9668832421302795,
+      "learning_rate": 2e-05,
+      "loss": 0.4112,
+      "step": 24
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.050217628479004,
+      "learning_rate": 2e-05,
+      "loss": 0.5468,
+      "step": 26
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.0268161296844482,
+      "learning_rate": 2e-05,
+      "loss": 0.7263,
+      "step": 28
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.6333857774734497,
+      "learning_rate": 2e-05,
+      "loss": 1.1593,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.8671631813049316,
+      "learning_rate": 2e-05,
+      "loss": 0.9164,
+      "step": 32
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.747903823852539,
+      "learning_rate": 2e-05,
+      "loss": 0.893,
+      "step": 34
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.8260470628738403,
+      "learning_rate": 2e-05,
+      "loss": 1.0974,
+      "step": 36
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.2476838827133179,
+      "learning_rate": 2e-05,
+      "loss": 0.5784,
+      "step": 38
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.1296557188034058,
+      "learning_rate": 2e-05,
+      "loss": 0.5419,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.772802710533142,
+      "learning_rate": 2e-05,
+      "loss": 0.7333,
+      "step": 42
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.721181631088257,
+      "learning_rate": 2e-05,
+      "loss": 0.7137,
+      "step": 44
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.527193069458008,
+      "learning_rate": 2e-05,
+      "loss": 0.5528,
+      "step": 46
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.12138032913208,
+      "learning_rate": 2e-05,
+      "loss": 1.0548,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.6518544554710388,
+      "learning_rate": 2e-05,
+      "loss": 0.3414,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.018988132476807,
+      "learning_rate": 2e-05,
+      "loss": 1.5555,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.6130986213684082,
+      "learning_rate": 2e-05,
+      "loss": 0.4019,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.33242765069007874,
+      "learning_rate": 2e-05,
+      "loss": 0.2922,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.9729520082473755,
+      "learning_rate": 2e-05,
+      "loss": 0.6715,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.9380380511283875,
+      "learning_rate": 2e-05,
+      "loss": 0.3047,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.6756107807159424,
+      "learning_rate": 2e-05,
+      "loss": 0.7653,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 6.233062744140625,
+      "learning_rate": 2e-05,
+      "loss": 1.116,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.7454715967178345,
+      "learning_rate": 2e-05,
+      "loss": 0.2272,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.9794038534164429,
+      "learning_rate": 2e-05,
+      "loss": 0.9766,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.021594762802124,
+      "learning_rate": 2e-05,
+      "loss": 1.1175,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.5316901206970215,
+      "learning_rate": 2e-05,
+      "loss": 0.7159,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.6453006267547607,
+      "learning_rate": 2e-05,
+      "loss": 1.1686,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.7126204967498779,
+      "learning_rate": 2e-05,
+      "loss": 0.2293,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.6401352882385254,
+      "learning_rate": 2e-05,
+      "loss": 0.4406,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 8.485867500305176,
+      "learning_rate": 2e-05,
+      "loss": 1.04,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.8455100059509277,
+      "learning_rate": 2e-05,
+      "loss": 0.9729,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.618323564529419,
+      "learning_rate": 2e-05,
+      "loss": 0.7559,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.153294563293457,
+      "learning_rate": 2e-05,
+      "loss": 0.9314,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.3631463050842285,
+      "learning_rate": 2e-05,
+      "loss": 1.1333,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.2221667766571045,
+      "learning_rate": 2e-05,
+      "loss": 0.6,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.3827831745147705,
+      "learning_rate": 2e-05,
+      "loss": 0.8038,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.3622207641601562,
+      "learning_rate": 2e-05,
+      "loss": 0.3635,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.6388647556304932,
+      "learning_rate": 2e-05,
+      "loss": 0.7245,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.3859128952026367,
+      "learning_rate": 2e-05,
+      "loss": 0.4281,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.1130776405334473,
+      "learning_rate": 2e-05,
+      "loss": 0.6673,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 5687732361756672.0,
+      "train_loss": 0.7967825222015381,
+      "train_runtime": 161.3161,
+      "train_samples_per_second": 2.48,
+      "train_steps_per_second": 0.62
+    }
+  ],
+  "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": 5687732361756672.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7120f59b3e327f46b7701185d0fbe755cc4c3708b15e42aa9340697ccb63820e
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e27fa87cee19c29aa37b2f4d56a73f5194311c97b396574ee0b5c82b1e2a56e
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f58ccf6396ad783df7ff3e8b5c3d28eefa3b6c37f471ac05e34f0c22d1e05b
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a9e56f3289a41a3ef33f94549b9d9770c5e16eba0b1aa89ba2bf47af5358d83
+size 389170582

client_states_fedavg_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixit100_T0125_decay099_SEED2/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c301bd4f0f805d33e15d5d6ef5bca41d790003760a57770a9d0bec8ce5fa6e
+size 389170122