Upload folder using huggingface_hub

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a1d84be2f0637a8002b5b3af874484cae552c6280e756bce7dde0cbb13145d
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6248e7080bad36002d932fc329308efbb58cbc3c9469304dbba71b7938a84367
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90882c6daa75109703f69cb50d7e04c460d1f4344bc438823391eea9d7bd6754
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc2d6265491807df8fd3b6c3b15674150d5a5ffb36cf28b2227763ed5136aaa
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16e675f4c1968626339279cb96325491c6cc8cae380d71c43f5777f66a255e95
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9991679d96f74ba5990f64b8d121ee2d97b23b8e200fcb2e00dd9db511b1ae6
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d4e51792a645233c4a482e675f35b643ef77eb473a05f905ca1b8726622f34f
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669e7eac935aedc38163869e1bd4f9b80fa7ed24e298d5b712c724ce59b9eb6c
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/0_trainer_state.json

@@ -0,0 +1,217 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.47488170862197876,
+      "learning_rate": 2e-05,
+      "loss": 0.0866,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.9166059494018555,
+      "learning_rate": 2e-05,
+      "loss": 0.2647,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.567215085029602,
+      "learning_rate": 2e-05,
+      "loss": 0.1872,
+      "step": 6
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.5392768383026123,
+      "learning_rate": 2e-05,
+      "loss": 0.2264,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.43878668546676636,
+      "learning_rate": 2e-05,
+      "loss": 0.0416,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.8712286949157715,
+      "learning_rate": 2e-05,
+      "loss": 0.3169,
+      "step": 12
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.626501202583313,
+      "learning_rate": 2e-05,
+      "loss": 0.027,
+      "step": 14
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.570056676864624,
+      "learning_rate": 2e-05,
+      "loss": 0.0335,
+      "step": 16
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.9959315061569214,
+      "learning_rate": 2e-05,
+      "loss": 0.2356,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.9875115752220154,
+      "learning_rate": 2e-05,
+      "loss": 0.0379,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.563103973865509,
+      "learning_rate": 2e-05,
+      "loss": 0.0213,
+      "step": 22
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.232426643371582,
+      "learning_rate": 2e-05,
+      "loss": 0.216,
+      "step": 24
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 2.3981211185455322,
+      "learning_rate": 2e-05,
+      "loss": 0.0729,
+      "step": 26
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.0411518812179565,
+      "learning_rate": 2e-05,
+      "loss": 0.0328,
+      "step": 28
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.5252733826637268,
+      "learning_rate": 2e-05,
+      "loss": 0.3069,
+      "step": 30
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.7728747129440308,
+      "learning_rate": 2e-05,
+      "loss": 0.0693,
+      "step": 32
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 1.3379911184310913,
+      "learning_rate": 2e-05,
+      "loss": 0.1159,
+      "step": 34
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 2.592834949493408,
+      "learning_rate": 2e-05,
+      "loss": 0.1534,
+      "step": 36
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.610074520111084,
+      "learning_rate": 2e-05,
+      "loss": 0.1051,
+      "step": 38
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.4380384385585785,
+      "learning_rate": 2e-05,
+      "loss": 0.1043,
+      "step": 40
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 1.5626729726791382,
+      "learning_rate": 2e-05,
+      "loss": 0.2938,
+      "step": 42
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.40467581152915955,
+      "learning_rate": 2e-05,
+      "loss": 0.0479,
+      "step": 44
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 1.2873458862304688,
+      "learning_rate": 2e-05,
+      "loss": 0.2392,
+      "step": 46
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.608442783355713,
+      "learning_rate": 2e-05,
+      "loss": 0.0982,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.45398300886154175,
+      "learning_rate": 2e-05,
+      "loss": 0.0287,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "step": 50,
+      "total_flos": 5557405387587584.0,
+      "train_loss": 0.13453627586364747,
+      "train_runtime": 250.9273,
+      "train_samples_per_second": 0.797,
+      "train_steps_per_second": 0.199
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 50,
+  "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": 5557405387587584.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4245025adbb4ba892c81e432826e975168b3ec8383bdede0fcceb79870619bf
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e0dd549fa9834746df684ac37929c7a95d637624e23ad474b2dff4204fde527
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9e0cbaadad63f4557adbd3ea5cd1c9365bb01eabd7522200419dbc59ff601c
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c2663e5856636050b16fce836516ee7bc4fd7b09276c4d22e55ab746de5bf9c
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec459ecf2f10078d738357b93e8272ac5a65be27fa5014237fa6258d67df5a9
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed18be924b7d8fb8ea8d8d4e4b91a44fce9170e1b6fd48f58ac873e51f01586
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc6bcfef6dd11b739da5d24b81cdef29d3aa96064e324c31dda33bba35c29860
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41222190a5e0175394253c867cf8607218ae331b1e6679a68f8edca8afd60735
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/1_trainer_state.json

@@ -0,0 +1,217 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.46819382905960083,
+      "learning_rate": 2e-05,
+      "loss": 0.2447,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.0340005159378052,
+      "learning_rate": 2e-05,
+      "loss": 0.071,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.917952299118042,
+      "learning_rate": 2e-05,
+      "loss": 0.1966,
+      "step": 6
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.3073928952217102,
+      "learning_rate": 2e-05,
+      "loss": 0.0277,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.6226162910461426,
+      "learning_rate": 2e-05,
+      "loss": 0.1002,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.4787392020225525,
+      "learning_rate": 2e-05,
+      "loss": 0.0788,
+      "step": 12
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.5545408725738525,
+      "learning_rate": 2e-05,
+      "loss": 0.0277,
+      "step": 14
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.3709498941898346,
+      "learning_rate": 2e-05,
+      "loss": 0.0334,
+      "step": 16
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.895387649536133,
+      "learning_rate": 2e-05,
+      "loss": 0.2151,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.8211622834205627,
+      "learning_rate": 2e-05,
+      "loss": 0.0471,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.7779847383499146,
+      "learning_rate": 2e-05,
+      "loss": 0.1101,
+      "step": 22
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.0119048357009888,
+      "learning_rate": 2e-05,
+      "loss": 0.0509,
+      "step": 24
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.7551224827766418,
+      "learning_rate": 2e-05,
+      "loss": 0.061,
+      "step": 26
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.1288940906524658,
+      "learning_rate": 2e-05,
+      "loss": 0.0847,
+      "step": 28
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 3.3638179302215576,
+      "learning_rate": 2e-05,
+      "loss": 0.2176,
+      "step": 30
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.2910892367362976,
+      "learning_rate": 2e-05,
+      "loss": 0.0181,
+      "step": 32
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.6550900340080261,
+      "learning_rate": 2e-05,
+      "loss": 0.0268,
+      "step": 34
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.7145023345947266,
+      "learning_rate": 2e-05,
+      "loss": 0.0648,
+      "step": 36
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.2834157943725586,
+      "learning_rate": 2e-05,
+      "loss": 0.2366,
+      "step": 38
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.8662907481193542,
+      "learning_rate": 2e-05,
+      "loss": 0.0295,
+      "step": 40
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.6141842603683472,
+      "learning_rate": 2e-05,
+      "loss": 0.0423,
+      "step": 42
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.8501439094543457,
+      "learning_rate": 2e-05,
+      "loss": 0.0458,
+      "step": 44
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 1.9633840322494507,
+      "learning_rate": 2e-05,
+      "loss": 0.0736,
+      "step": 46
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.34262603521347046,
+      "learning_rate": 2e-05,
+      "loss": 0.0152,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3050743341445923,
+      "learning_rate": 2e-05,
+      "loss": 0.0163,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "step": 50,
+      "total_flos": 5596219090927616.0,
+      "train_loss": 0.08542263984680176,
+      "train_runtime": 248.9867,
+      "train_samples_per_second": 0.803,
+      "train_steps_per_second": 0.201
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 50,
+  "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": 5596219090927616.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7bfcf82c883429cb22818be001c1cc587a0b98ea5fdcbf7d3be831b374052a4
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5b21ec19732b48f7037a15443898d61f0d0b0f3cfb78e1b8c537b033c6a47a4
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a365a4d93e2e6d8ddbb99a6189015d6e682ac40c0a5499a2b8d8344b75555ecb
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b1e12e6843f9f48fa60001056847936749611862bb47a9ba7c4470d3ca532a
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7fc3def105651c26cc37ac4a34fe29a73f9f6a11d10d7091a84bbe187224f6f
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3691084a0a3dd43e3b392dfa4106d3d2a8acac102c57215ccab318e38fc0838f
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6af87464154ee1f7f447c689fc8deac6df53736d5ee0eeb164b1257fb55b5020
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc3932b2cd6c354eef4b1d8a5c59b9b29569a60008e399dab6614eee185794df
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/2_trainer_state.json

@@ -0,0 +1,217 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.3417752981185913,
+      "learning_rate": 2e-05,
+      "loss": 0.1006,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.6572253108024597,
+      "learning_rate": 2e-05,
+      "loss": 0.0886,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.1601297855377197,
+      "learning_rate": 2e-05,
+      "loss": 0.3825,
+      "step": 6
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.5155367851257324,
+      "learning_rate": 2e-05,
+      "loss": 0.8629,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.19246768951416,
+      "learning_rate": 2e-05,
+      "loss": 0.3246,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.0038927793502808,
+      "learning_rate": 2e-05,
+      "loss": 0.1555,
+      "step": 12
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 5.269669532775879,
+      "learning_rate": 2e-05,
+      "loss": 0.0864,
+      "step": 14
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0328688621520996,
+      "learning_rate": 2e-05,
+      "loss": 0.1792,
+      "step": 16
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.8982062935829163,
+      "learning_rate": 2e-05,
+      "loss": 0.1407,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.5086755752563477,
+      "learning_rate": 2e-05,
+      "loss": 0.1533,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.2126076221466064,
+      "learning_rate": 2e-05,
+      "loss": 0.1508,
+      "step": 22
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.6549688577651978,
+      "learning_rate": 2e-05,
+      "loss": 0.2418,
+      "step": 24
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 3.2237186431884766,
+      "learning_rate": 2e-05,
+      "loss": 0.2407,
+      "step": 26
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.624603033065796,
+      "learning_rate": 2e-05,
+      "loss": 0.1989,
+      "step": 28
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.289777159690857,
+      "learning_rate": 2e-05,
+      "loss": 0.0911,
+      "step": 30
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5119551420211792,
+      "learning_rate": 2e-05,
+      "loss": 0.0293,
+      "step": 32
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 1.698155164718628,
+      "learning_rate": 2e-05,
+      "loss": 0.2148,
+      "step": 34
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.7996082305908203,
+      "learning_rate": 2e-05,
+      "loss": 0.2261,
+      "step": 36
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.48896124958992004,
+      "learning_rate": 2e-05,
+      "loss": 0.3192,
+      "step": 38
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.537122368812561,
+      "learning_rate": 2e-05,
+      "loss": 0.0526,
+      "step": 40
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 2.135448455810547,
+      "learning_rate": 2e-05,
+      "loss": 0.1417,
+      "step": 42
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.1811649799346924,
+      "learning_rate": 2e-05,
+      "loss": 0.1384,
+      "step": 44
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 2.414937734603882,
+      "learning_rate": 2e-05,
+      "loss": 0.1008,
+      "step": 46
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 3.2851128578186035,
+      "learning_rate": 2e-05,
+      "loss": 0.2202,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.5515780448913574,
+      "learning_rate": 2e-05,
+      "loss": 0.1151,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "step": 50,
+      "total_flos": 5482320970645504.0,
+      "train_loss": 0.19822086334228517,
+      "train_runtime": 248.7984,
+      "train_samples_per_second": 0.804,
+      "train_steps_per_second": 0.201
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 50,
+  "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": 5482320970645504.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c14b217787ea7ae817cb3f8b2f4f5e637d74864386d99a4f37982ebf2d124be
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ff1d0fd3a7664e105ec96c5d81ef97579f149b1d607142f982f5a6ad1ebccf6
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e665491ab85a1d6a2aacbde93a87d790eb63f0025ead836eb3052d4a0f37a9
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39965412854e8ab9d2b39b2e4c0a54c77fc5208158bbbd4eb325eab68359642
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a1a0cec0272eba07433f0dcea21da0c0980c297940976e2a3af4f2c6df1da97
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f663db034a9b94866914bcd51580375ba7f402eeebd01cfa621255d92d4225da
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee65fc133a6cb7b7315c4efc73d0249be8971ed59b278b1f23d9feae1949b73
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d879b0671c7101fc956f8b05a51c8916e22bb1e2bd31c2af450b2508d52c94b
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/3_trainer_state.json

@@ -0,0 +1,217 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.911635637283325,
+      "learning_rate": 2e-05,
+      "loss": 0.3981,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5911923050880432,
+      "learning_rate": 2e-05,
+      "loss": 0.2374,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.1119353771209717,
+      "learning_rate": 2e-05,
+      "loss": 0.1946,
+      "step": 6
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.107414484024048,
+      "learning_rate": 2e-05,
+      "loss": 0.2211,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.076481580734253,
+      "learning_rate": 2e-05,
+      "loss": 0.3442,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.9608561992645264,
+      "learning_rate": 2e-05,
+      "loss": 0.387,
+      "step": 12
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.599261999130249,
+      "learning_rate": 2e-05,
+      "loss": 0.1272,
+      "step": 14
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.731563150882721,
+      "learning_rate": 2e-05,
+      "loss": 0.092,
+      "step": 16
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.21544075012207,
+      "learning_rate": 2e-05,
+      "loss": 0.5217,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.667925477027893,
+      "learning_rate": 2e-05,
+      "loss": 0.0901,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.7500098943710327,
+      "learning_rate": 2e-05,
+      "loss": 0.3038,
+      "step": 22
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.87495493888855,
+      "learning_rate": 2e-05,
+      "loss": 0.27,
+      "step": 24
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 5.719139099121094,
+      "learning_rate": 2e-05,
+      "loss": 0.8637,
+      "step": 26
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 3.9575798511505127,
+      "learning_rate": 2e-05,
+      "loss": 0.2241,
+      "step": 28
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 3.180509090423584,
+      "learning_rate": 2e-05,
+      "loss": 0.2912,
+      "step": 30
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 3.4659345149993896,
+      "learning_rate": 2e-05,
+      "loss": 0.4136,
+      "step": 32
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 5.336747646331787,
+      "learning_rate": 2e-05,
+      "loss": 0.3516,
+      "step": 34
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.7263541221618652,
+      "learning_rate": 2e-05,
+      "loss": 0.0987,
+      "step": 36
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.231567621231079,
+      "learning_rate": 2e-05,
+      "loss": 0.3073,
+      "step": 38
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.5393335819244385,
+      "learning_rate": 2e-05,
+      "loss": 0.331,
+      "step": 40
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 6.146248817443848,
+      "learning_rate": 2e-05,
+      "loss": 0.585,
+      "step": 42
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.6960240602493286,
+      "learning_rate": 2e-05,
+      "loss": 0.1809,
+      "step": 44
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 1.0312891006469727,
+      "learning_rate": 2e-05,
+      "loss": 0.213,
+      "step": 46
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.6583869457244873,
+      "learning_rate": 2e-05,
+      "loss": 0.5143,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.2781920433044434,
+      "learning_rate": 2e-05,
+      "loss": 0.1894,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "step": 50,
+      "total_flos": 5673132543180800.0,
+      "train_loss": 0.3100400161743164,
+      "train_runtime": 247.9097,
+      "train_samples_per_second": 0.807,
+      "train_steps_per_second": 0.202
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 50,
+  "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": 5673132543180800.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d33c91a5f48e47e093054ca5ea2eaf9736af79442e0516e57a0f41c0146f3ceb
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a370bf90c623e3fdc2b46f736270265d5ee116a3535512b775de363feb4fde02
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b26b2eaf8fd7cfc4c60cd119648df240d927a295f9bfa5bb17c4086470d8ca48
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e5fe838295293ecf035ce5db3510c31d207103e17cbfb107c2870e09d43a61
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc3632fc93600a7982ac68490dbb2ebfb77903fd3b7e050faebfd652c67dab1
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09dac0b9dfd4a1b7e3efe7a6e1d9d1bd65a9a70bd9d311fc2ecdb594e943d938
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c88ed8abf53a12d4bba898eb3fe04164eacaee747dc6953d03e75267b99de6f4
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b394665feb33db3aa2884ce08cc02cad6dccd97cb5e3c8dae14515fbd64e625
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/4_trainer_state.json

@@ -0,0 +1,217 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.8551050424575806,
+      "learning_rate": 2e-05,
+      "loss": 0.2176,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.4949532747268677,
+      "learning_rate": 2e-05,
+      "loss": 0.3246,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.8867964148521423,
+      "learning_rate": 2e-05,
+      "loss": 0.1527,
+      "step": 6
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.1332507133483887,
+      "learning_rate": 2e-05,
+      "loss": 0.1606,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.1229583024978638,
+      "learning_rate": 2e-05,
+      "loss": 0.1485,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.5596634149551392,
+      "learning_rate": 2e-05,
+      "loss": 0.1656,
+      "step": 12
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.693656325340271,
+      "learning_rate": 2e-05,
+      "loss": 0.1749,
+      "step": 14
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.1607701778411865,
+      "learning_rate": 2e-05,
+      "loss": 0.1646,
+      "step": 16
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.7262656688690186,
+      "learning_rate": 2e-05,
+      "loss": 0.2236,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.5488182306289673,
+      "learning_rate": 2e-05,
+      "loss": 0.1973,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.2641401290893555,
+      "learning_rate": 2e-05,
+      "loss": 0.154,
+      "step": 22
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.8307248950004578,
+      "learning_rate": 2e-05,
+      "loss": 0.2771,
+      "step": 24
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.2456833124160767,
+      "learning_rate": 2e-05,
+      "loss": 0.2396,
+      "step": 26
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.3302162289619446,
+      "learning_rate": 2e-05,
+      "loss": 0.1226,
+      "step": 28
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.5295584201812744,
+      "learning_rate": 2e-05,
+      "loss": 0.2166,
+      "step": 30
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.6318351030349731,
+      "learning_rate": 2e-05,
+      "loss": 0.1125,
+      "step": 32
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 1.4376343488693237,
+      "learning_rate": 2e-05,
+      "loss": 0.3601,
+      "step": 34
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.818044900894165,
+      "learning_rate": 2e-05,
+      "loss": 0.1704,
+      "step": 36
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.8872388601303101,
+      "learning_rate": 2e-05,
+      "loss": 0.1346,
+      "step": 38
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.1370484828948975,
+      "learning_rate": 2e-05,
+      "loss": 0.1651,
+      "step": 40
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 2.046491861343384,
+      "learning_rate": 2e-05,
+      "loss": 0.1531,
+      "step": 42
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 2.7971935272216797,
+      "learning_rate": 2e-05,
+      "loss": 0.305,
+      "step": 44
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 1.2505499124526978,
+      "learning_rate": 2e-05,
+      "loss": 0.1415,
+      "step": 46
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.0299497842788696,
+      "learning_rate": 2e-05,
+      "loss": 0.0801,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3772761821746826,
+      "learning_rate": 2e-05,
+      "loss": 0.2148,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "step": 50,
+      "total_flos": 6353755020722176.0,
+      "train_loss": 0.19108272552490235,
+      "train_runtime": 250.9701,
+      "train_samples_per_second": 0.797,
+      "train_steps_per_second": 0.199
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 50,
+  "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": 6353755020722176.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa371cc628332dd87a25e51e5195c8e030170b45afaed687b775d7a900aa238
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccabd25c60cf78d22479fb05029d6373408c726fb72e8c353e364dcf41d94058
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c78158bd76652abc30395caba8b8cc5bc770a1271cada0423a6a1a69779accd
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5edcb8aa0a0d1f3e5b75e2c71e3ad1ff8a9183f302307e2547594096bff67497
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc310_4tasks_5rounds_fixitr50_T0125_decay099/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dcd8cc59e6b9a48bef1ea7f506fd8ce5c936a443f551367167297a9fa7ac939
+size 1167511866