Upload folder using huggingface_hub

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700e7727cf62cfd19a2076884072dcffbb10ce4b2b1fa43e918ece6b4a52f780
+size 369838470

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4249b386b505e112fadfed2251f23a91116092c0d07bc0462c990953f6422939
+size 369838470

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d34bc48ad7842636f16c2b43b1a316afc71dd01fc740d03ef8687ce1fe38f6bf
+size 369838470

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891b9a80d3aafa1dc39de8451e37e899622190f27d78b07d966b0c5cd5dc111b
+size 369838470

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0e0cefde296b62551bd6ea3d0a38d186186ea80d535eb4a866f6e510cb0811
+size 369837282

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01cabf1f3ad046e3731f2d52f8659a9b4d39ff665bf15a29261d1f946e27d36
+size 369838470

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8615dcab1df208016e96b293e7a0d05e8d1e17d8630cf3412b0d4e8b5f0308b9
+size 369837282

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193da4c2270c794ade78d5290b2fb119462ac21ee08f18e40c23e7f90ac1e38d
+size 369837282

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/0_trainer_state.json

@@ -0,0 +1,378 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 97,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020618556701030927,
+      "grad_norm": 0.9594700932502747,
+      "learning_rate": 2e-05,
+      "loss": 0.8117,
+      "step": 2
+    },
+    {
+      "epoch": 0.041237113402061855,
+      "grad_norm": 1.316869854927063,
+      "learning_rate": 2e-05,
+      "loss": 0.9801,
+      "step": 4
+    },
+    {
+      "epoch": 0.061855670103092786,
+      "grad_norm": 0.9525308609008789,
+      "learning_rate": 2e-05,
+      "loss": 1.0166,
+      "step": 6
+    },
+    {
+      "epoch": 0.08247422680412371,
+      "grad_norm": 2.6361804008483887,
+      "learning_rate": 2e-05,
+      "loss": 1.783,
+      "step": 8
+    },
+    {
+      "epoch": 0.10309278350515463,
+      "grad_norm": 2.6056838035583496,
+      "learning_rate": 2e-05,
+      "loss": 1.3024,
+      "step": 10
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 0.8098453283309937,
+      "learning_rate": 2e-05,
+      "loss": 0.6617,
+      "step": 12
+    },
+    {
+      "epoch": 0.14432989690721648,
+      "grad_norm": 0.7525412440299988,
+      "learning_rate": 2e-05,
+      "loss": 1.1856,
+      "step": 14
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 1.2613378763198853,
+      "learning_rate": 2e-05,
+      "loss": 1.0713,
+      "step": 16
+    },
+    {
+      "epoch": 0.18556701030927836,
+      "grad_norm": 1.3653959035873413,
+      "learning_rate": 2e-05,
+      "loss": 0.5042,
+      "step": 18
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 1.5698071718215942,
+      "learning_rate": 2e-05,
+      "loss": 0.9574,
+      "step": 20
+    },
+    {
+      "epoch": 0.2268041237113402,
+      "grad_norm": 1.4238898754119873,
+      "learning_rate": 2e-05,
+      "loss": 0.5896,
+      "step": 22
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "grad_norm": 1.0638025999069214,
+      "learning_rate": 2e-05,
+      "loss": 0.6436,
+      "step": 24
+    },
+    {
+      "epoch": 0.26804123711340205,
+      "grad_norm": 1.482254981994629,
+      "learning_rate": 2e-05,
+      "loss": 1.116,
+      "step": 26
+    },
+    {
+      "epoch": 0.28865979381443296,
+      "grad_norm": 0.9255651235580444,
+      "learning_rate": 2e-05,
+      "loss": 0.8036,
+      "step": 28
+    },
+    {
+      "epoch": 0.30927835051546393,
+      "grad_norm": 1.4140223264694214,
+      "learning_rate": 2e-05,
+      "loss": 1.2512,
+      "step": 30
+    },
+    {
+      "epoch": 0.32989690721649484,
+      "grad_norm": 1.219704031944275,
+      "learning_rate": 2e-05,
+      "loss": 1.3776,
+      "step": 32
+    },
+    {
+      "epoch": 0.35051546391752575,
+      "grad_norm": 1.07976496219635,
+      "learning_rate": 2e-05,
+      "loss": 0.5591,
+      "step": 34
+    },
+    {
+      "epoch": 0.3711340206185567,
+      "grad_norm": 0.7267152070999146,
+      "learning_rate": 2e-05,
+      "loss": 0.7852,
+      "step": 36
+    },
+    {
+      "epoch": 0.3917525773195876,
+      "grad_norm": 1.143415093421936,
+      "learning_rate": 2e-05,
+      "loss": 0.756,
+      "step": 38
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 1.8038641214370728,
+      "learning_rate": 2e-05,
+      "loss": 0.845,
+      "step": 40
+    },
+    {
+      "epoch": 0.4329896907216495,
+      "grad_norm": 1.0822728872299194,
+      "learning_rate": 2e-05,
+      "loss": 1.519,
+      "step": 42
+    },
+    {
+      "epoch": 0.4536082474226804,
+      "grad_norm": 1.1943228244781494,
+      "learning_rate": 2e-05,
+      "loss": 0.4455,
+      "step": 44
+    },
+    {
+      "epoch": 0.4742268041237113,
+      "grad_norm": 1.8823230266571045,
+      "learning_rate": 2e-05,
+      "loss": 0.96,
+      "step": 46
+    },
+    {
+      "epoch": 0.4948453608247423,
+      "grad_norm": 7.420291423797607,
+      "learning_rate": 2e-05,
+      "loss": 1.452,
+      "step": 48
+    },
+    {
+      "epoch": 0.5154639175257731,
+      "grad_norm": 3.0441153049468994,
+      "learning_rate": 2e-05,
+      "loss": 1.3325,
+      "step": 50
+    },
+    {
+      "epoch": 0.5360824742268041,
+      "grad_norm": 0.5439964532852173,
+      "learning_rate": 2e-05,
+      "loss": 0.1226,
+      "step": 52
+    },
+    {
+      "epoch": 0.5567010309278351,
+      "grad_norm": 1.2239110469818115,
+      "learning_rate": 2e-05,
+      "loss": 1.674,
+      "step": 54
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": 4.072906970977783,
+      "learning_rate": 2e-05,
+      "loss": 1.2365,
+      "step": 56
+    },
+    {
+      "epoch": 0.5979381443298969,
+      "grad_norm": 5.7371134757995605,
+      "learning_rate": 2e-05,
+      "loss": 1.087,
+      "step": 58
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 1.6185969114303589,
+      "learning_rate": 2e-05,
+      "loss": 0.8133,
+      "step": 60
+    },
+    {
+      "epoch": 0.6391752577319587,
+      "grad_norm": 3.079521894454956,
+      "learning_rate": 2e-05,
+      "loss": 0.808,
+      "step": 62
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 6.495431423187256,
+      "learning_rate": 2e-05,
+      "loss": 1.0943,
+      "step": 64
+    },
+    {
+      "epoch": 0.6804123711340206,
+      "grad_norm": 0.8551055788993835,
+      "learning_rate": 2e-05,
+      "loss": 0.1527,
+      "step": 66
+    },
+    {
+      "epoch": 0.7010309278350515,
+      "grad_norm": 1.7763549089431763,
+      "learning_rate": 2e-05,
+      "loss": 0.6739,
+      "step": 68
+    },
+    {
+      "epoch": 0.7216494845360825,
+      "grad_norm": 2.691042423248291,
+      "learning_rate": 2e-05,
+      "loss": 1.1616,
+      "step": 70
+    },
+    {
+      "epoch": 0.7422680412371134,
+      "grad_norm": 4.3141350746154785,
+      "learning_rate": 2e-05,
+      "loss": 1.0808,
+      "step": 72
+    },
+    {
+      "epoch": 0.7628865979381443,
+      "grad_norm": 7.18300724029541,
+      "learning_rate": 2e-05,
+      "loss": 0.9536,
+      "step": 74
+    },
+    {
+      "epoch": 0.7835051546391752,
+      "grad_norm": 1.1671137809753418,
+      "learning_rate": 2e-05,
+      "loss": 1.1202,
+      "step": 76
+    },
+    {
+      "epoch": 0.8041237113402062,
+      "grad_norm": 1.3312162160873413,
+      "learning_rate": 2e-05,
+      "loss": 0.9128,
+      "step": 78
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 4.002167224884033,
+      "learning_rate": 2e-05,
+      "loss": 1.8212,
+      "step": 80
+    },
+    {
+      "epoch": 0.845360824742268,
+      "grad_norm": 0.5520375967025757,
+      "learning_rate": 2e-05,
+      "loss": 0.9018,
+      "step": 82
+    },
+    {
+      "epoch": 0.865979381443299,
+      "grad_norm": 3.623425245285034,
+      "learning_rate": 2e-05,
+      "loss": 1.4031,
+      "step": 84
+    },
+    {
+      "epoch": 0.8865979381443299,
+      "grad_norm": 1.4582457542419434,
+      "learning_rate": 2e-05,
+      "loss": 0.9698,
+      "step": 86
+    },
+    {
+      "epoch": 0.9072164948453608,
+      "grad_norm": 1.663182258605957,
+      "learning_rate": 2e-05,
+      "loss": 0.617,
+      "step": 88
+    },
+    {
+      "epoch": 0.9278350515463918,
+      "grad_norm": 1.543397307395935,
+      "learning_rate": 2e-05,
+      "loss": 0.8184,
+      "step": 90
+    },
+    {
+      "epoch": 0.9484536082474226,
+      "grad_norm": 2.6305606365203857,
+      "learning_rate": 2e-05,
+      "loss": 1.4602,
+      "step": 92
+    },
+    {
+      "epoch": 0.9690721649484536,
+      "grad_norm": 1.8172004222869873,
+      "learning_rate": 2e-05,
+      "loss": 0.6449,
+      "step": 94
+    },
+    {
+      "epoch": 0.9896907216494846,
+      "grad_norm": 0.8449392318725586,
+      "learning_rate": 2e-05,
+      "loss": 0.4998,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "step": 97,
+      "total_flos": 5656240185147392.0,
+      "train_loss": 0.9712527560204575,
+      "train_runtime": 283.4008,
+      "train_samples_per_second": 1.369,
+      "train_steps_per_second": 0.342
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 97,
+  "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": 5656240185147392.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:010cb22f7080862208e90610dcf48f78cec63ba5efdaceee2d112cdbf5d47641
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f204f32e0ac67fe417eaa2bb8d824e8d397b21b56098e393a96c8aaf6edb9e3a
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55d660cc32509b326e396a2bc1bf081350d83ce1bb10fad553dbd51e4040a65
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858bfd490a02d0faf510784d79cc65abb26239811b6932a93c1457def18b1913
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d2f80c6899f8893bf78df5df1051033bd46910dae99ae1f014e25b9fa10001
+size 794706058

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d267dde84c916584c0fd2e2698b726a6fbc2cf6d5ec19fc8c9c1eb29b2af5d
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c9b73bb331974f6c5867f6f3b6415ad39b4f910b7b39f3ffa95b5fa31c2069
+size 794706058

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30850c74cce70f504f4ad301d34a176a7430241e851d3365422877ea2f45e46b
+size 794706058

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/1_trainer_state.json

@@ -0,0 +1,378 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 97,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020618556701030927,
+      "grad_norm": 1.2024366855621338,
+      "learning_rate": 2e-05,
+      "loss": 0.9855,
+      "step": 2
+    },
+    {
+      "epoch": 0.041237113402061855,
+      "grad_norm": 2.8276209831237793,
+      "learning_rate": 2e-05,
+      "loss": 2.0286,
+      "step": 4
+    },
+    {
+      "epoch": 0.061855670103092786,
+      "grad_norm": 0.8268002867698669,
+      "learning_rate": 2e-05,
+      "loss": 0.8436,
+      "step": 6
+    },
+    {
+      "epoch": 0.08247422680412371,
+      "grad_norm": 1.137050747871399,
+      "learning_rate": 2e-05,
+      "loss": 0.6613,
+      "step": 8
+    },
+    {
+      "epoch": 0.10309278350515463,
+      "grad_norm": 0.32624438405036926,
+      "learning_rate": 2e-05,
+      "loss": 0.6151,
+      "step": 10
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 1.5309603214263916,
+      "learning_rate": 2e-05,
+      "loss": 1.2007,
+      "step": 12
+    },
+    {
+      "epoch": 0.14432989690721648,
+      "grad_norm": 0.9214475750923157,
+      "learning_rate": 2e-05,
+      "loss": 0.8164,
+      "step": 14
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 0.8667386770248413,
+      "learning_rate": 2e-05,
+      "loss": 1.3474,
+      "step": 16
+    },
+    {
+      "epoch": 0.18556701030927836,
+      "grad_norm": 1.3758001327514648,
+      "learning_rate": 2e-05,
+      "loss": 0.9568,
+      "step": 18
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 1.6424651145935059,
+      "learning_rate": 2e-05,
+      "loss": 1.734,
+      "step": 20
+    },
+    {
+      "epoch": 0.2268041237113402,
+      "grad_norm": 1.2598588466644287,
+      "learning_rate": 2e-05,
+      "loss": 0.9668,
+      "step": 22
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "grad_norm": 0.4972625970840454,
+      "learning_rate": 2e-05,
+      "loss": 1.0234,
+      "step": 24
+    },
+    {
+      "epoch": 0.26804123711340205,
+      "grad_norm": 1.1207408905029297,
+      "learning_rate": 2e-05,
+      "loss": 0.771,
+      "step": 26
+    },
+    {
+      "epoch": 0.28865979381443296,
+      "grad_norm": 3.0427370071411133,
+      "learning_rate": 2e-05,
+      "loss": 1.5074,
+      "step": 28
+    },
+    {
+      "epoch": 0.30927835051546393,
+      "grad_norm": 2.0376274585723877,
+      "learning_rate": 2e-05,
+      "loss": 1.231,
+      "step": 30
+    },
+    {
+      "epoch": 0.32989690721649484,
+      "grad_norm": 1.4843626022338867,
+      "learning_rate": 2e-05,
+      "loss": 0.5791,
+      "step": 32
+    },
+    {
+      "epoch": 0.35051546391752575,
+      "grad_norm": 1.1146706342697144,
+      "learning_rate": 2e-05,
+      "loss": 0.5438,
+      "step": 34
+    },
+    {
+      "epoch": 0.3711340206185567,
+      "grad_norm": 3.4487464427948,
+      "learning_rate": 2e-05,
+      "loss": 0.6243,
+      "step": 36
+    },
+    {
+      "epoch": 0.3917525773195876,
+      "grad_norm": 1.1361485719680786,
+      "learning_rate": 2e-05,
+      "loss": 0.5469,
+      "step": 38
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 1.1683415174484253,
+      "learning_rate": 2e-05,
+      "loss": 0.7735,
+      "step": 40
+    },
+    {
+      "epoch": 0.4329896907216495,
+      "grad_norm": 1.9458197355270386,
+      "learning_rate": 2e-05,
+      "loss": 0.7973,
+      "step": 42
+    },
+    {
+      "epoch": 0.4536082474226804,
+      "grad_norm": 2.1601526737213135,
+      "learning_rate": 2e-05,
+      "loss": 2.1649,
+      "step": 44
+    },
+    {
+      "epoch": 0.4742268041237113,
+      "grad_norm": 0.644416868686676,
+      "learning_rate": 2e-05,
+      "loss": 0.478,
+      "step": 46
+    },
+    {
+      "epoch": 0.4948453608247423,
+      "grad_norm": 1.2410545349121094,
+      "learning_rate": 2e-05,
+      "loss": 0.9742,
+      "step": 48
+    },
+    {
+      "epoch": 0.5154639175257731,
+      "grad_norm": 1.7227394580841064,
+      "learning_rate": 2e-05,
+      "loss": 0.7909,
+      "step": 50
+    },
+    {
+      "epoch": 0.5360824742268041,
+      "grad_norm": 0.8551867008209229,
+      "learning_rate": 2e-05,
+      "loss": 1.2275,
+      "step": 52
+    },
+    {
+      "epoch": 0.5567010309278351,
+      "grad_norm": 3.663994550704956,
+      "learning_rate": 2e-05,
+      "loss": 1.1619,
+      "step": 54
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": 3.1182751655578613,
+      "learning_rate": 2e-05,
+      "loss": 1.1158,
+      "step": 56
+    },
+    {
+      "epoch": 0.5979381443298969,
+      "grad_norm": 3.4014275074005127,
+      "learning_rate": 2e-05,
+      "loss": 1.5493,
+      "step": 58
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 1.064070701599121,
+      "learning_rate": 2e-05,
+      "loss": 1.0928,
+      "step": 60
+    },
+    {
+      "epoch": 0.6391752577319587,
+      "grad_norm": 2.2249224185943604,
+      "learning_rate": 2e-05,
+      "loss": 1.6255,
+      "step": 62
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 1.1762775182724,
+      "learning_rate": 2e-05,
+      "loss": 0.7151,
+      "step": 64
+    },
+    {
+      "epoch": 0.6804123711340206,
+      "grad_norm": 1.9675991535186768,
+      "learning_rate": 2e-05,
+      "loss": 1.1143,
+      "step": 66
+    },
+    {
+      "epoch": 0.7010309278350515,
+      "grad_norm": 1.0661314725875854,
+      "learning_rate": 2e-05,
+      "loss": 1.0532,
+      "step": 68
+    },
+    {
+      "epoch": 0.7216494845360825,
+      "grad_norm": 1.9606918096542358,
+      "learning_rate": 2e-05,
+      "loss": 1.1101,
+      "step": 70
+    },
+    {
+      "epoch": 0.7422680412371134,
+      "grad_norm": 1.426865577697754,
+      "learning_rate": 2e-05,
+      "loss": 0.7968,
+      "step": 72
+    },
+    {
+      "epoch": 0.7628865979381443,
+      "grad_norm": 2.376742362976074,
+      "learning_rate": 2e-05,
+      "loss": 1.7639,
+      "step": 74
+    },
+    {
+      "epoch": 0.7835051546391752,
+      "grad_norm": 1.166895866394043,
+      "learning_rate": 2e-05,
+      "loss": 0.8135,
+      "step": 76
+    },
+    {
+      "epoch": 0.8041237113402062,
+      "grad_norm": 1.8746273517608643,
+      "learning_rate": 2e-05,
+      "loss": 1.1028,
+      "step": 78
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 0.614515483379364,
+      "learning_rate": 2e-05,
+      "loss": 0.5723,
+      "step": 80
+    },
+    {
+      "epoch": 0.845360824742268,
+      "grad_norm": 1.903074860572815,
+      "learning_rate": 2e-05,
+      "loss": 1.1099,
+      "step": 82
+    },
+    {
+      "epoch": 0.865979381443299,
+      "grad_norm": 2.264801025390625,
+      "learning_rate": 2e-05,
+      "loss": 0.8985,
+      "step": 84
+    },
+    {
+      "epoch": 0.8865979381443299,
+      "grad_norm": 3.2271571159362793,
+      "learning_rate": 2e-05,
+      "loss": 1.4144,
+      "step": 86
+    },
+    {
+      "epoch": 0.9072164948453608,
+      "grad_norm": 1.078228235244751,
+      "learning_rate": 2e-05,
+      "loss": 0.5997,
+      "step": 88
+    },
+    {
+      "epoch": 0.9278350515463918,
+      "grad_norm": 1.2719480991363525,
+      "learning_rate": 2e-05,
+      "loss": 0.7412,
+      "step": 90
+    },
+    {
+      "epoch": 0.9484536082474226,
+      "grad_norm": 0.7247925996780396,
+      "learning_rate": 2e-05,
+      "loss": 0.4561,
+      "step": 92
+    },
+    {
+      "epoch": 0.9690721649484536,
+      "grad_norm": 3.501603364944458,
+      "learning_rate": 2e-05,
+      "loss": 0.9331,
+      "step": 94
+    },
+    {
+      "epoch": 0.9896907216494846,
+      "grad_norm": 1.7136667966842651,
+      "learning_rate": 2e-05,
+      "loss": 1.0366,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "step": 97,
+      "total_flos": 1.3528534647570432e+16,
+      "train_loss": 1.0150119152265726,
+      "train_runtime": 431.5296,
+      "train_samples_per_second": 0.899,
+      "train_steps_per_second": 0.225
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 97,
+  "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": 1.3528534647570432e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deba6b08f202485d96d8396e670eee325d63ffe910dbfb5a0017a987cdc49f75
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fafe0dfb6f69b886eb2742fafb483ebd3c456e4d07784fc1074c7bd71ebadb5
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b33512f44b71784fc12140eeda027975f098331543c06da40a5167fef1bbf2
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d39a3573dc359faeea0b925780cce1542de85c37f581100edb135619bfcb90
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fade7bec581700a545e511f6629d3aaf950e0569037a762dfa724afacf1cb049
+size 794706058

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f31ff76684fe396191026d2704f6e5d3b6a189df85ea2ead48acaa7660c99f8
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ea45f5e41f6fd557342ed0013396a40a87337cdf56818a5a343dd91aea04017
+size 794706058

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b3c5d3a98d86e38347599f9c241683885e6ee4c8794cccb08f15b7e4f56ec99
+size 794706058

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/2_trainer_state.json

@@ -0,0 +1,378 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 97,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020618556701030927,
+      "grad_norm": 2.094592332839966,
+      "learning_rate": 2e-05,
+      "loss": 0.5636,
+      "step": 2
+    },
+    {
+      "epoch": 0.041237113402061855,
+      "grad_norm": 2.9416861534118652,
+      "learning_rate": 2e-05,
+      "loss": 0.6539,
+      "step": 4
+    },
+    {
+      "epoch": 0.061855670103092786,
+      "grad_norm": 2.3152358531951904,
+      "learning_rate": 2e-05,
+      "loss": 2.7326,
+      "step": 6
+    },
+    {
+      "epoch": 0.08247422680412371,
+      "grad_norm": 1.2773842811584473,
+      "learning_rate": 2e-05,
+      "loss": 0.491,
+      "step": 8
+    },
+    {
+      "epoch": 0.10309278350515463,
+      "grad_norm": 2.8158011436462402,
+      "learning_rate": 2e-05,
+      "loss": 1.0919,
+      "step": 10
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 0.3333049714565277,
+      "learning_rate": 2e-05,
+      "loss": 0.4831,
+      "step": 12
+    },
+    {
+      "epoch": 0.14432989690721648,
+      "grad_norm": 2.7883007526397705,
+      "learning_rate": 2e-05,
+      "loss": 1.0931,
+      "step": 14
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 3.233243227005005,
+      "learning_rate": 2e-05,
+      "loss": 0.6956,
+      "step": 16
+    },
+    {
+      "epoch": 0.18556701030927836,
+      "grad_norm": 1.989795207977295,
+      "learning_rate": 2e-05,
+      "loss": 0.7488,
+      "step": 18
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 1.7127903699874878,
+      "learning_rate": 2e-05,
+      "loss": 0.6343,
+      "step": 20
+    },
+    {
+      "epoch": 0.2268041237113402,
+      "grad_norm": 2.0744166374206543,
+      "learning_rate": 2e-05,
+      "loss": 0.8524,
+      "step": 22
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "grad_norm": 0.5908894538879395,
+      "learning_rate": 2e-05,
+      "loss": 0.5006,
+      "step": 24
+    },
+    {
+      "epoch": 0.26804123711340205,
+      "grad_norm": 2.3167927265167236,
+      "learning_rate": 2e-05,
+      "loss": 0.7399,
+      "step": 26
+    },
+    {
+      "epoch": 0.28865979381443296,
+      "grad_norm": 2.3707773685455322,
+      "learning_rate": 2e-05,
+      "loss": 1.7088,
+      "step": 28
+    },
+    {
+      "epoch": 0.30927835051546393,
+      "grad_norm": 1.400090217590332,
+      "learning_rate": 2e-05,
+      "loss": 0.6791,
+      "step": 30
+    },
+    {
+      "epoch": 0.32989690721649484,
+      "grad_norm": 1.3757578134536743,
+      "learning_rate": 2e-05,
+      "loss": 0.2768,
+      "step": 32
+    },
+    {
+      "epoch": 0.35051546391752575,
+      "grad_norm": 1.4865468740463257,
+      "learning_rate": 2e-05,
+      "loss": 0.9843,
+      "step": 34
+    },
+    {
+      "epoch": 0.3711340206185567,
+      "grad_norm": 0.6968898773193359,
+      "learning_rate": 2e-05,
+      "loss": 0.7418,
+      "step": 36
+    },
+    {
+      "epoch": 0.3917525773195876,
+      "grad_norm": 0.8154457211494446,
+      "learning_rate": 2e-05,
+      "loss": 0.3193,
+      "step": 38
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 1.838761329650879,
+      "learning_rate": 2e-05,
+      "loss": 0.9609,
+      "step": 40
+    },
+    {
+      "epoch": 0.4329896907216495,
+      "grad_norm": 13.480488777160645,
+      "learning_rate": 2e-05,
+      "loss": 2.4343,
+      "step": 42
+    },
+    {
+      "epoch": 0.4536082474226804,
+      "grad_norm": 4.987843036651611,
+      "learning_rate": 2e-05,
+      "loss": 0.8691,
+      "step": 44
+    },
+    {
+      "epoch": 0.4742268041237113,
+      "grad_norm": 2.576080322265625,
+      "learning_rate": 2e-05,
+      "loss": 1.5122,
+      "step": 46
+    },
+    {
+      "epoch": 0.4948453608247423,
+      "grad_norm": 2.20375919342041,
+      "learning_rate": 2e-05,
+      "loss": 1.8862,
+      "step": 48
+    },
+    {
+      "epoch": 0.5154639175257731,
+      "grad_norm": 2.071373224258423,
+      "learning_rate": 2e-05,
+      "loss": 1.2672,
+      "step": 50
+    },
+    {
+      "epoch": 0.5360824742268041,
+      "grad_norm": 0.8673601150512695,
+      "learning_rate": 2e-05,
+      "loss": 0.4441,
+      "step": 52
+    },
+    {
+      "epoch": 0.5567010309278351,
+      "grad_norm": 4.185937404632568,
+      "learning_rate": 2e-05,
+      "loss": 0.9008,
+      "step": 54
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": 3.8477606773376465,
+      "learning_rate": 2e-05,
+      "loss": 1.4731,
+      "step": 56
+    },
+    {
+      "epoch": 0.5979381443298969,
+      "grad_norm": 2.552183151245117,
+      "learning_rate": 2e-05,
+      "loss": 0.9716,
+      "step": 58
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 4.546395301818848,
+      "learning_rate": 2e-05,
+      "loss": 0.8568,
+      "step": 60
+    },
+    {
+      "epoch": 0.6391752577319587,
+      "grad_norm": 2.3420331478118896,
+      "learning_rate": 2e-05,
+      "loss": 0.7591,
+      "step": 62
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 2.695547342300415,
+      "learning_rate": 2e-05,
+      "loss": 0.8987,
+      "step": 64
+    },
+    {
+      "epoch": 0.6804123711340206,
+      "grad_norm": 1.2362654209136963,
+      "learning_rate": 2e-05,
+      "loss": 0.5021,
+      "step": 66
+    },
+    {
+      "epoch": 0.7010309278350515,
+      "grad_norm": 1.2740592956542969,
+      "learning_rate": 2e-05,
+      "loss": 0.4018,
+      "step": 68
+    },
+    {
+      "epoch": 0.7216494845360825,
+      "grad_norm": 5.063082695007324,
+      "learning_rate": 2e-05,
+      "loss": 2.1985,
+      "step": 70
+    },
+    {
+      "epoch": 0.7422680412371134,
+      "grad_norm": 2.316474199295044,
+      "learning_rate": 2e-05,
+      "loss": 0.8644,
+      "step": 72
+    },
+    {
+      "epoch": 0.7628865979381443,
+      "grad_norm": 0.6739747524261475,
+      "learning_rate": 2e-05,
+      "loss": 0.307,
+      "step": 74
+    },
+    {
+      "epoch": 0.7835051546391752,
+      "grad_norm": 4.647529125213623,
+      "learning_rate": 2e-05,
+      "loss": 1.7771,
+      "step": 76
+    },
+    {
+      "epoch": 0.8041237113402062,
+      "grad_norm": 3.0259242057800293,
+      "learning_rate": 2e-05,
+      "loss": 1.2311,
+      "step": 78
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 3.602269411087036,
+      "learning_rate": 2e-05,
+      "loss": 0.995,
+      "step": 80
+    },
+    {
+      "epoch": 0.845360824742268,
+      "grad_norm": 4.247006893157959,
+      "learning_rate": 2e-05,
+      "loss": 0.8127,
+      "step": 82
+    },
+    {
+      "epoch": 0.865979381443299,
+      "grad_norm": 0.7156468629837036,
+      "learning_rate": 2e-05,
+      "loss": 0.3186,
+      "step": 84
+    },
+    {
+      "epoch": 0.8865979381443299,
+      "grad_norm": 1.2778359651565552,
+      "learning_rate": 2e-05,
+      "loss": 0.7263,
+      "step": 86
+    },
+    {
+      "epoch": 0.9072164948453608,
+      "grad_norm": 0.9886473417282104,
+      "learning_rate": 2e-05,
+      "loss": 0.4815,
+      "step": 88
+    },
+    {
+      "epoch": 0.9278350515463918,
+      "grad_norm": 1.8476825952529907,
+      "learning_rate": 2e-05,
+      "loss": 0.5218,
+      "step": 90
+    },
+    {
+      "epoch": 0.9484536082474226,
+      "grad_norm": 2.6772751808166504,
+      "learning_rate": 2e-05,
+      "loss": 0.8244,
+      "step": 92
+    },
+    {
+      "epoch": 0.9690721649484536,
+      "grad_norm": 4.056234359741211,
+      "learning_rate": 2e-05,
+      "loss": 0.6775,
+      "step": 94
+    },
+    {
+      "epoch": 0.9896907216494846,
+      "grad_norm": 3.1529552936553955,
+      "learning_rate": 2e-05,
+      "loss": 1.1456,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "step": 97,
+      "total_flos": 1.5335589188468736e+16,
+      "train_loss": 0.9330275279959452,
+      "train_runtime": 477.9415,
+      "train_samples_per_second": 0.812,
+      "train_steps_per_second": 0.203
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 97,
+  "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": 1.5335589188468736e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e61720a5e93ea50f46d08346c0df1394049140d37f0be98aefdbc25d8c977fe8
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836a2a51b5d4cd21f746b2911500ba9905601999cd9b335acc407fd395fe1cb3
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0dd5eecb186e6dcaa58034081295a486373fca823093397cf31e3755191623
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:375f2c180f2e46d00af64d4459b0073410922a9f58f34b26245d662eab7393b6
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd19025a1e446de997e470ce9151125aea2fa376342cac8933d66cadd7ebac8
+size 794706058

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057226ff2ae7762685aceb34cd0a4a78e68705b79c0a199bff2d0ec30309fff0
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a503724b4bc52a4d41d3a106cb2039e5bf468c5869b6a17ab520f99dadf635
+size 794706058

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b3ba1e22afc45f14750f023cf9412deaae7c183e4dabcd7db6c3de26a05a5f
+size 794706058

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/3_trainer_state.json

@@ -0,0 +1,378 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 97,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020618556701030927,
+      "grad_norm": 1.2351635694503784,
+      "learning_rate": 2e-05,
+      "loss": 0.8896,
+      "step": 2
+    },
+    {
+      "epoch": 0.041237113402061855,
+      "grad_norm": 1.028679609298706,
+      "learning_rate": 2e-05,
+      "loss": 1.0489,
+      "step": 4
+    },
+    {
+      "epoch": 0.061855670103092786,
+      "grad_norm": 1.1318262815475464,
+      "learning_rate": 2e-05,
+      "loss": 0.7579,
+      "step": 6
+    },
+    {
+      "epoch": 0.08247422680412371,
+      "grad_norm": 0.7864372134208679,
+      "learning_rate": 2e-05,
+      "loss": 1.0486,
+      "step": 8
+    },
+    {
+      "epoch": 0.10309278350515463,
+      "grad_norm": 1.1569880247116089,
+      "learning_rate": 2e-05,
+      "loss": 1.0792,
+      "step": 10
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 1.2696163654327393,
+      "learning_rate": 2e-05,
+      "loss": 0.9814,
+      "step": 12
+    },
+    {
+      "epoch": 0.14432989690721648,
+      "grad_norm": 0.8696528673171997,
+      "learning_rate": 2e-05,
+      "loss": 0.4638,
+      "step": 14
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 0.5613833069801331,
+      "learning_rate": 2e-05,
+      "loss": 0.4833,
+      "step": 16
+    },
+    {
+      "epoch": 0.18556701030927836,
+      "grad_norm": 1.4101988077163696,
+      "learning_rate": 2e-05,
+      "loss": 1.0988,
+      "step": 18
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 2.2370290756225586,
+      "learning_rate": 2e-05,
+      "loss": 1.4935,
+      "step": 20
+    },
+    {
+      "epoch": 0.2268041237113402,
+      "grad_norm": 0.7359315156936646,
+      "learning_rate": 2e-05,
+      "loss": 0.5316,
+      "step": 22
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "grad_norm": 0.10134891420602798,
+      "learning_rate": 2e-05,
+      "loss": 0.7342,
+      "step": 24
+    },
+    {
+      "epoch": 0.26804123711340205,
+      "grad_norm": 0.458024799823761,
+      "learning_rate": 2e-05,
+      "loss": 0.9999,
+      "step": 26
+    },
+    {
+      "epoch": 0.28865979381443296,
+      "grad_norm": 1.2111563682556152,
+      "learning_rate": 2e-05,
+      "loss": 0.9257,
+      "step": 28
+    },
+    {
+      "epoch": 0.30927835051546393,
+      "grad_norm": 1.0723052024841309,
+      "learning_rate": 2e-05,
+      "loss": 1.3809,
+      "step": 30
+    },
+    {
+      "epoch": 0.32989690721649484,
+      "grad_norm": 1.1956589221954346,
+      "learning_rate": 2e-05,
+      "loss": 0.8152,
+      "step": 32
+    },
+    {
+      "epoch": 0.35051546391752575,
+      "grad_norm": 1.7930861711502075,
+      "learning_rate": 2e-05,
+      "loss": 0.8741,
+      "step": 34
+    },
+    {
+      "epoch": 0.3711340206185567,
+      "grad_norm": 1.2833040952682495,
+      "learning_rate": 2e-05,
+      "loss": 1.1285,
+      "step": 36
+    },
+    {
+      "epoch": 0.3917525773195876,
+      "grad_norm": 1.0580778121948242,
+      "learning_rate": 2e-05,
+      "loss": 1.1266,
+      "step": 38
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 3.55466365814209,
+      "learning_rate": 2e-05,
+      "loss": 1.817,
+      "step": 40
+    },
+    {
+      "epoch": 0.4329896907216495,
+      "grad_norm": 1.2678000926971436,
+      "learning_rate": 2e-05,
+      "loss": 0.7765,
+      "step": 42
+    },
+    {
+      "epoch": 0.4536082474226804,
+      "grad_norm": 0.35197746753692627,
+      "learning_rate": 2e-05,
+      "loss": 0.2773,
+      "step": 44
+    },
+    {
+      "epoch": 0.4742268041237113,
+      "grad_norm": 0.6228245496749878,
+      "learning_rate": 2e-05,
+      "loss": 0.6613,
+      "step": 46
+    },
+    {
+      "epoch": 0.4948453608247423,
+      "grad_norm": 0.8533904552459717,
+      "learning_rate": 2e-05,
+      "loss": 0.838,
+      "step": 48
+    },
+    {
+      "epoch": 0.5154639175257731,
+      "grad_norm": 1.0209187269210815,
+      "learning_rate": 2e-05,
+      "loss": 1.0453,
+      "step": 50
+    },
+    {
+      "epoch": 0.5360824742268041,
+      "grad_norm": 2.189225673675537,
+      "learning_rate": 2e-05,
+      "loss": 0.5933,
+      "step": 52
+    },
+    {
+      "epoch": 0.5567010309278351,
+      "grad_norm": 1.2542327642440796,
+      "learning_rate": 2e-05,
+      "loss": 1.0437,
+      "step": 54
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": 2.0544962882995605,
+      "learning_rate": 2e-05,
+      "loss": 1.1979,
+      "step": 56
+    },
+    {
+      "epoch": 0.5979381443298969,
+      "grad_norm": 1.0727826356887817,
+      "learning_rate": 2e-05,
+      "loss": 0.6359,
+      "step": 58
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 1.5904814004898071,
+      "learning_rate": 2e-05,
+      "loss": 0.7723,
+      "step": 60
+    },
+    {
+      "epoch": 0.6391752577319587,
+      "grad_norm": 1.0151207447052002,
+      "learning_rate": 2e-05,
+      "loss": 0.5503,
+      "step": 62
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 1.441215991973877,
+      "learning_rate": 2e-05,
+      "loss": 1.0698,
+      "step": 64
+    },
+    {
+      "epoch": 0.6804123711340206,
+      "grad_norm": 1.0735455751419067,
+      "learning_rate": 2e-05,
+      "loss": 0.5145,
+      "step": 66
+    },
+    {
+      "epoch": 0.7010309278350515,
+      "grad_norm": 0.10968424379825592,
+      "learning_rate": 2e-05,
+      "loss": 0.3674,
+      "step": 68
+    },
+    {
+      "epoch": 0.7216494845360825,
+      "grad_norm": 0.9318140149116516,
+      "learning_rate": 2e-05,
+      "loss": 0.3887,
+      "step": 70
+    },
+    {
+      "epoch": 0.7422680412371134,
+      "grad_norm": 1.0061886310577393,
+      "learning_rate": 2e-05,
+      "loss": 0.8431,
+      "step": 72
+    },
+    {
+      "epoch": 0.7628865979381443,
+      "grad_norm": 2.2860257625579834,
+      "learning_rate": 2e-05,
+      "loss": 0.9988,
+      "step": 74
+    },
+    {
+      "epoch": 0.7835051546391752,
+      "grad_norm": 1.5457782745361328,
+      "learning_rate": 2e-05,
+      "loss": 0.9536,
+      "step": 76
+    },
+    {
+      "epoch": 0.8041237113402062,
+      "grad_norm": 0.6779859662055969,
+      "learning_rate": 2e-05,
+      "loss": 0.4899,
+      "step": 78
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 0.7183377742767334,
+      "learning_rate": 2e-05,
+      "loss": 0.4293,
+      "step": 80
+    },
+    {
+      "epoch": 0.845360824742268,
+      "grad_norm": 0.36951103806495667,
+      "learning_rate": 2e-05,
+      "loss": 0.1843,
+      "step": 82
+    },
+    {
+      "epoch": 0.865979381443299,
+      "grad_norm": 0.8922227025032043,
+      "learning_rate": 2e-05,
+      "loss": 0.6862,
+      "step": 84
+    },
+    {
+      "epoch": 0.8865979381443299,
+      "grad_norm": 2.8659071922302246,
+      "learning_rate": 2e-05,
+      "loss": 1.1587,
+      "step": 86
+    },
+    {
+      "epoch": 0.9072164948453608,
+      "grad_norm": 1.3875242471694946,
+      "learning_rate": 2e-05,
+      "loss": 0.9098,
+      "step": 88
+    },
+    {
+      "epoch": 0.9278350515463918,
+      "grad_norm": 0.9852328896522522,
+      "learning_rate": 2e-05,
+      "loss": 0.6307,
+      "step": 90
+    },
+    {
+      "epoch": 0.9484536082474226,
+      "grad_norm": 0.5574153661727905,
+      "learning_rate": 2e-05,
+      "loss": 0.5733,
+      "step": 92
+    },
+    {
+      "epoch": 0.9690721649484536,
+      "grad_norm": 1.3713490962982178,
+      "learning_rate": 2e-05,
+      "loss": 0.9024,
+      "step": 94
+    },
+    {
+      "epoch": 0.9896907216494846,
+      "grad_norm": 1.467879295349121,
+      "learning_rate": 2e-05,
+      "loss": 0.8192,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "step": 97,
+      "total_flos": 2.0809997453623296e+16,
+      "train_loss": 0.831003818315329,
+      "train_runtime": 456.3128,
+      "train_samples_per_second": 0.85,
+      "train_steps_per_second": 0.213
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 97,
+  "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": 2.0809997453623296e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc616230c7b9aa7088c203ce58a78ebd04c5d555e8853f4dcb6a0306e0c72479
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0c3f6fb5908711c8f352c77a674a31b0f4b28a1e23a95da23b186be60cc9ca7
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084953bf14eed1659ee09043267c0af0d28b102e0e4b1a1b253698538222957b
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b060a981deaaa4340ad03a4b7bfec93f1aceda46bb115afb99b4fd72d5c93f7d
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:139a3db837cc749cfe3aaba05f566ff9c3c58fbb8ff77bcdbaa97f547d20c6bb
+size 794706058

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6560c4b0dd4fbc06c539a4a4fcf6367317511d4ac417d4ea9665aee62fe22c39
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04e83af490f1a6ac89ab7f83bb7698f86e3dff253cb9e07f10c600ee753a697a
+size 794706058

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a040e7c95ddd984135c170b3f2691fad4f71ef638bf5d975151c8e54a7176d3c
+size 794706058

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/4_trainer_state.json

@@ -0,0 +1,378 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 97,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020618556701030927,
+      "grad_norm": 0.2858644723892212,
+      "learning_rate": 2e-05,
+      "loss": 0.2736,
+      "step": 2
+    },
+    {
+      "epoch": 0.041237113402061855,
+      "grad_norm": 1.1567838191986084,
+      "learning_rate": 2e-05,
+      "loss": 0.8047,
+      "step": 4
+    },
+    {
+      "epoch": 0.061855670103092786,
+      "grad_norm": 1.3844921588897705,
+      "learning_rate": 2e-05,
+      "loss": 0.721,
+      "step": 6
+    },
+    {
+      "epoch": 0.08247422680412371,
+      "grad_norm": 2.228928804397583,
+      "learning_rate": 2e-05,
+      "loss": 0.3891,
+      "step": 8
+    },
+    {
+      "epoch": 0.10309278350515463,
+      "grad_norm": 4.224711894989014,
+      "learning_rate": 2e-05,
+      "loss": 1.6159,
+      "step": 10
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 2.257948398590088,
+      "learning_rate": 2e-05,
+      "loss": 0.6054,
+      "step": 12
+    },
+    {
+      "epoch": 0.14432989690721648,
+      "grad_norm": 0.02765708975493908,
+      "learning_rate": 2e-05,
+      "loss": 0.2752,
+      "step": 14
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 1.5334547758102417,
+      "learning_rate": 2e-05,
+      "loss": 0.9059,
+      "step": 16
+    },
+    {
+      "epoch": 0.18556701030927836,
+      "grad_norm": 1.4655863046646118,
+      "learning_rate": 2e-05,
+      "loss": 1.0014,
+      "step": 18
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 2.4958205223083496,
+      "learning_rate": 2e-05,
+      "loss": 0.912,
+      "step": 20
+    },
+    {
+      "epoch": 0.2268041237113402,
+      "grad_norm": 0.2553260624408722,
+      "learning_rate": 2e-05,
+      "loss": 0.6693,
+      "step": 22
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "grad_norm": 1.1488703489303589,
+      "learning_rate": 2e-05,
+      "loss": 1.4668,
+      "step": 24
+    },
+    {
+      "epoch": 0.26804123711340205,
+      "grad_norm": 2.2296223640441895,
+      "learning_rate": 2e-05,
+      "loss": 1.0992,
+      "step": 26
+    },
+    {
+      "epoch": 0.28865979381443296,
+      "grad_norm": 1.788644790649414,
+      "learning_rate": 2e-05,
+      "loss": 0.5368,
+      "step": 28
+    },
+    {
+      "epoch": 0.30927835051546393,
+      "grad_norm": 2.4774513244628906,
+      "learning_rate": 2e-05,
+      "loss": 1.5951,
+      "step": 30
+    },
+    {
+      "epoch": 0.32989690721649484,
+      "grad_norm": 2.1652729511260986,
+      "learning_rate": 2e-05,
+      "loss": 1.094,
+      "step": 32
+    },
+    {
+      "epoch": 0.35051546391752575,
+      "grad_norm": 2.3260281085968018,
+      "learning_rate": 2e-05,
+      "loss": 1.0952,
+      "step": 34
+    },
+    {
+      "epoch": 0.3711340206185567,
+      "grad_norm": 1.3701273202896118,
+      "learning_rate": 2e-05,
+      "loss": 0.9869,
+      "step": 36
+    },
+    {
+      "epoch": 0.3917525773195876,
+      "grad_norm": 4.809845447540283,
+      "learning_rate": 2e-05,
+      "loss": 1.3194,
+      "step": 38
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 2.351966619491577,
+      "learning_rate": 2e-05,
+      "loss": 0.9726,
+      "step": 40
+    },
+    {
+      "epoch": 0.4329896907216495,
+      "grad_norm": 0.9332682490348816,
+      "learning_rate": 2e-05,
+      "loss": 0.4279,
+      "step": 42
+    },
+    {
+      "epoch": 0.4536082474226804,
+      "grad_norm": 1.890088677406311,
+      "learning_rate": 2e-05,
+      "loss": 1.4647,
+      "step": 44
+    },
+    {
+      "epoch": 0.4742268041237113,
+      "grad_norm": 2.079850435256958,
+      "learning_rate": 2e-05,
+      "loss": 1.2145,
+      "step": 46
+    },
+    {
+      "epoch": 0.4948453608247423,
+      "grad_norm": 1.5987228155136108,
+      "learning_rate": 2e-05,
+      "loss": 0.3709,
+      "step": 48
+    },
+    {
+      "epoch": 0.5154639175257731,
+      "grad_norm": 5.048325538635254,
+      "learning_rate": 2e-05,
+      "loss": 1.5801,
+      "step": 50
+    },
+    {
+      "epoch": 0.5360824742268041,
+      "grad_norm": 1.1632441282272339,
+      "learning_rate": 2e-05,
+      "loss": 1.0393,
+      "step": 52
+    },
+    {
+      "epoch": 0.5567010309278351,
+      "grad_norm": 4.325563430786133,
+      "learning_rate": 2e-05,
+      "loss": 1.1573,
+      "step": 54
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": 0.5468723773956299,
+      "learning_rate": 2e-05,
+      "loss": 0.715,
+      "step": 56
+    },
+    {
+      "epoch": 0.5979381443298969,
+      "grad_norm": 2.392122268676758,
+      "learning_rate": 2e-05,
+      "loss": 1.7613,
+      "step": 58
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 4.436788082122803,
+      "learning_rate": 2e-05,
+      "loss": 1.6617,
+      "step": 60
+    },
+    {
+      "epoch": 0.6391752577319587,
+      "grad_norm": 2.003520965576172,
+      "learning_rate": 2e-05,
+      "loss": 0.7345,
+      "step": 62
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 3.054750919342041,
+      "learning_rate": 2e-05,
+      "loss": 0.8026,
+      "step": 64
+    },
+    {
+      "epoch": 0.6804123711340206,
+      "grad_norm": 1.6678532361984253,
+      "learning_rate": 2e-05,
+      "loss": 1.3865,
+      "step": 66
+    },
+    {
+      "epoch": 0.7010309278350515,
+      "grad_norm": 0.6752498745918274,
+      "learning_rate": 2e-05,
+      "loss": 0.8424,
+      "step": 68
+    },
+    {
+      "epoch": 0.7216494845360825,
+      "grad_norm": 1.077208161354065,
+      "learning_rate": 2e-05,
+      "loss": 1.0379,
+      "step": 70
+    },
+    {
+      "epoch": 0.7422680412371134,
+      "grad_norm": 0.9076808094978333,
+      "learning_rate": 2e-05,
+      "loss": 1.0342,
+      "step": 72
+    },
+    {
+      "epoch": 0.7628865979381443,
+      "grad_norm": 1.4604486227035522,
+      "learning_rate": 2e-05,
+      "loss": 1.1822,
+      "step": 74
+    },
+    {
+      "epoch": 0.7835051546391752,
+      "grad_norm": 1.8128681182861328,
+      "learning_rate": 2e-05,
+      "loss": 0.6584,
+      "step": 76
+    },
+    {
+      "epoch": 0.8041237113402062,
+      "grad_norm": 2.5491185188293457,
+      "learning_rate": 2e-05,
+      "loss": 0.3425,
+      "step": 78
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 1.706129550933838,
+      "learning_rate": 2e-05,
+      "loss": 1.0393,
+      "step": 80
+    },
+    {
+      "epoch": 0.845360824742268,
+      "grad_norm": 2.769246816635132,
+      "learning_rate": 2e-05,
+      "loss": 0.7411,
+      "step": 82
+    },
+    {
+      "epoch": 0.865979381443299,
+      "grad_norm": 1.2856016159057617,
+      "learning_rate": 2e-05,
+      "loss": 0.5905,
+      "step": 84
+    },
+    {
+      "epoch": 0.8865979381443299,
+      "grad_norm": 1.2032272815704346,
+      "learning_rate": 2e-05,
+      "loss": 1.3024,
+      "step": 86
+    },
+    {
+      "epoch": 0.9072164948453608,
+      "grad_norm": 4.467032432556152,
+      "learning_rate": 2e-05,
+      "loss": 1.5643,
+      "step": 88
+    },
+    {
+      "epoch": 0.9278350515463918,
+      "grad_norm": 0.8960971832275391,
+      "learning_rate": 2e-05,
+      "loss": 0.9636,
+      "step": 90
+    },
+    {
+      "epoch": 0.9484536082474226,
+      "grad_norm": 4.481700897216797,
+      "learning_rate": 2e-05,
+      "loss": 0.8844,
+      "step": 92
+    },
+    {
+      "epoch": 0.9690721649484536,
+      "grad_norm": 4.529354095458984,
+      "learning_rate": 2e-05,
+      "loss": 1.6111,
+      "step": 94
+    },
+    {
+      "epoch": 0.9896907216494846,
+      "grad_norm": 1.4919743537902832,
+      "learning_rate": 2e-05,
+      "loss": 1.6889,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "step": 97,
+      "total_flos": 1.9758677338619904e+16,
+      "train_loss": 0.9952088532988558,
+      "train_runtime": 442.3189,
+      "train_samples_per_second": 0.877,
+      "train_steps_per_second": 0.219
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 97,
+  "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": 1.9758677338619904e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc07147185ef7a1116d8cbc4f5855e408ee10ec875b71b6efeecb64b8d71f75
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6bc63415aeffe90bd3ccb05b09889be57a253688c4af1be07d4765b52c7d13a
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cffbedc1a3a3b78b0738584215596619f506b2c16eb245d62eed0cb0335f339c
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8475e2ffae13cd3c88095c8250c4b587b8576722e9978f00e8e1604ea4e754e8
+size 794708086

client_states_feddualMultipqfullfreezeA_homoAgg_moe2_NEWAensureOrth_Bcca_T05_freq10_bs4_saveoptim_lr2e-5_5e-5_sc132_4tasks_5rounds_fixitr97_T0125_decay099/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096ecec406537adc34c8168d271a176cee2901d079bd735e6f7a09e54b4fe23f
+size 794706058