Upload folder using huggingface_hub

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2286f95b00921d1876ae9ac87fd9f4baff8ff2721a64e5531942b83186680499
+size 541320910

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a67a4a479132d5b595ba65570f8bcda71ac49ecf710cc3a6027b221900818c
+size 541320910

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc3f3a7327d5072281a95cbe83fe77066d11f1e5401b543ec78228aeebe62d23
+size 541320910

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a14f2fbceb48462f6f045437cd0fad073a017b4167c89de184b2a75c5d607d95
+size 541320910

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d84765f9df5158b2e2de9eeba9083efd978765f974eaa379aa31445011e291f1
+size 541320170

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56635372bfd22ee582f81492582e2973c1ed135acc6d203772e3a15f92e7ab05
+size 541320910

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5786d5f3b71c86ab18cf6f8dd3e56b24d79dc543eeceb52ca2c2b4fa6e0b85b4
+size 541320170

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab2e45a79bb70887cd714b94738fec6fe5af1499a1b525dc4ef5118c3e8e4b5
+size 541320170

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_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": 1.809485912322998,
+      "learning_rate": 2e-05,
+      "loss": 0.0812,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.920042037963867,
+      "learning_rate": 2e-05,
+      "loss": 0.2132,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.8735634684562683,
+      "learning_rate": 2e-05,
+      "loss": 0.1088,
+      "step": 6
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.701018810272217,
+      "learning_rate": 2e-05,
+      "loss": 0.3933,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.7481457591056824,
+      "learning_rate": 2e-05,
+      "loss": 0.1008,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.366037368774414,
+      "learning_rate": 2e-05,
+      "loss": 0.4121,
+      "step": 12
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.8869410753250122,
+      "learning_rate": 2e-05,
+      "loss": 0.0932,
+      "step": 14
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 6.612318515777588,
+      "learning_rate": 2e-05,
+      "loss": 0.2421,
+      "step": 16
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.380836248397827,
+      "learning_rate": 2e-05,
+      "loss": 0.2747,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 7.218313217163086,
+      "learning_rate": 2e-05,
+      "loss": 0.3023,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.9762125015258789,
+      "learning_rate": 2e-05,
+      "loss": 0.0261,
+      "step": 22
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 6.916683673858643,
+      "learning_rate": 2e-05,
+      "loss": 0.2974,
+      "step": 24
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 2.883701801300049,
+      "learning_rate": 2e-05,
+      "loss": 0.0691,
+      "step": 26
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 2.3749592304229736,
+      "learning_rate": 2e-05,
+      "loss": 0.0539,
+      "step": 28
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.4792490005493164,
+      "learning_rate": 2e-05,
+      "loss": 0.2182,
+      "step": 30
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.626264214515686,
+      "learning_rate": 2e-05,
+      "loss": 0.1567,
+      "step": 32
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 2.045509099960327,
+      "learning_rate": 2e-05,
+      "loss": 0.088,
+      "step": 34
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 5.292479515075684,
+      "learning_rate": 2e-05,
+      "loss": 0.2708,
+      "step": 36
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 3.301262378692627,
+      "learning_rate": 2e-05,
+      "loss": 0.1084,
+      "step": 38
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.7496870756149292,
+      "learning_rate": 2e-05,
+      "loss": 0.0622,
+      "step": 40
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 4.937453746795654,
+      "learning_rate": 2e-05,
+      "loss": 0.4291,
+      "step": 42
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.663676142692566,
+      "learning_rate": 2e-05,
+      "loss": 0.1355,
+      "step": 44
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 3.5852761268615723,
+      "learning_rate": 2e-05,
+      "loss": 0.4167,
+      "step": 46
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.524660587310791,
+      "learning_rate": 2e-05,
+      "loss": 0.0941,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.2302050590515137,
+      "learning_rate": 2e-05,
+      "loss": 0.0578,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "step": 50,
+      "total_flos": 2321286118244352.0,
+      "train_loss": 0.18821813583374022,
+      "train_runtime": 154.3783,
+      "train_samples_per_second": 1.296,
+      "train_steps_per_second": 0.324
+    }
+  ],
+  "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": 2321286118244352.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35507947eace9e8d9960d9b68e71386f2fc8c904d1ea318c587fdb74aeda4242
+size 541320910

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee14bcb1a027ebc38c71591a786e56993ee69fe7022a0e920bafadbe80f2607
+size 541320910

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5df99803f1db529badf7adce5d775945a21d8b08872d651884864534dc72b90
+size 541320910

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a4d481cc41be380b4d8e2e256387234a0408fa174b38b26cc97c3ed84d7cc86
+size 541320910

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54328b8cce6e0dc310a2001b36d1f6ec7efcdb2b08322d1c5cbd81d6c5d040a3
+size 541320170

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e9fd95c2421c558b275bae0f05dc44333ca0285053358836ed3a1659ddf60d
+size 541320910

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c97520f21302b6689b6cd952a17aee09ffa740c7b5045f97f88416887ff30f6c
+size 541320170

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d0df64f4071b9efbc17ee1248042f95a4ac7031e03ea568153903681e08b0f
+size 541320170

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_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": 3.0698935985565186,
+      "learning_rate": 2e-05,
+      "loss": 0.1942,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.9258705377578735,
+      "learning_rate": 2e-05,
+      "loss": 0.0843,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.686681866645813,
+      "learning_rate": 2e-05,
+      "loss": 0.241,
+      "step": 6
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.0136128664016724,
+      "learning_rate": 2e-05,
+      "loss": 0.0556,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.6502270698547363,
+      "learning_rate": 2e-05,
+      "loss": 0.0696,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.585745096206665,
+      "learning_rate": 2e-05,
+      "loss": 0.04,
+      "step": 12
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.1424528360366821,
+      "learning_rate": 2e-05,
+      "loss": 0.1483,
+      "step": 14
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.9371734857559204,
+      "learning_rate": 2e-05,
+      "loss": 0.038,
+      "step": 16
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.2085820436477661,
+      "learning_rate": 2e-05,
+      "loss": 0.0601,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.7588016986846924,
+      "learning_rate": 2e-05,
+      "loss": 0.0408,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.1975241899490356,
+      "learning_rate": 2e-05,
+      "loss": 0.0454,
+      "step": 22
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.0584468841552734,
+      "learning_rate": 2e-05,
+      "loss": 0.0406,
+      "step": 24
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 2.3347041606903076,
+      "learning_rate": 2e-05,
+      "loss": 0.1155,
+      "step": 26
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.578382134437561,
+      "learning_rate": 2e-05,
+      "loss": 0.0437,
+      "step": 28
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.00313663482666,
+      "learning_rate": 2e-05,
+      "loss": 0.0712,
+      "step": 30
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.022796392440796,
+      "learning_rate": 2e-05,
+      "loss": 0.0274,
+      "step": 32
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 1.1539667844772339,
+      "learning_rate": 2e-05,
+      "loss": 0.0279,
+      "step": 34
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.4522186517715454,
+      "learning_rate": 2e-05,
+      "loss": 0.0737,
+      "step": 36
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 4.5453996658325195,
+      "learning_rate": 2e-05,
+      "loss": 0.314,
+      "step": 38
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.5239720940589905,
+      "learning_rate": 2e-05,
+      "loss": 0.0215,
+      "step": 40
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 1.0342298746109009,
+      "learning_rate": 2e-05,
+      "loss": 0.0255,
+      "step": 42
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.0581754446029663,
+      "learning_rate": 2e-05,
+      "loss": 0.0256,
+      "step": 44
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.7539445161819458,
+      "learning_rate": 2e-05,
+      "loss": 0.0193,
+      "step": 46
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.662580668926239,
+      "learning_rate": 2e-05,
+      "loss": 0.0203,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8039494156837463,
+      "learning_rate": 2e-05,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "step": 50,
+      "total_flos": 2337498319552512.0,
+      "train_loss": 0.07481922149658203,
+      "train_runtime": 154.6604,
+      "train_samples_per_second": 1.293,
+      "train_steps_per_second": 0.323
+    }
+  ],
+  "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": 2337498319552512.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece549b5d6842a9a737eb926e8c9ad704a9f3b226ee48bee5a7a8e387eafed8f
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bcbce12098a775fbe5826ccbf488646f2bde20140a355bf996676925da477fa
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172d5cf229278b61ef085e4fdd62b8725281640b6e224ae1c5c4a10c1d75ee3a
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bbbb3e20a3faa3ad711d4d1c83f372a21dc984c5399752341c70768eac94c50
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:986b599a6fa8d7f90f77b8f73f0c38bf1802060af4921e40478d0206b5fdfeea
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:503b3def87f384014a340619be5283688e62fc40d6860a79ecb370fae075af4d
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d98b28557dfe09a57fd9893894a32cc8403ca0ba5f7d32135b076562ba16d0d
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:968592a6567677cf354b73d73f802d5eb7ebaa8e28722bcf2443cd5137071ddb
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_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": 1.6217052936553955,
+      "learning_rate": 2e-05,
+      "loss": 0.0899,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.40015384554862976,
+      "learning_rate": 2e-05,
+      "loss": 0.0986,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.083724021911621,
+      "learning_rate": 2e-05,
+      "loss": 0.374,
+      "step": 6
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.4223287105560303,
+      "learning_rate": 2e-05,
+      "loss": 0.8721,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.2518584728240967,
+      "learning_rate": 2e-05,
+      "loss": 0.3268,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.8573708534240723,
+      "learning_rate": 2e-05,
+      "loss": 0.1537,
+      "step": 12
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.007382869720459,
+      "learning_rate": 2e-05,
+      "loss": 0.0738,
+      "step": 14
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.963921308517456,
+      "learning_rate": 2e-05,
+      "loss": 0.1965,
+      "step": 16
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.843093991279602,
+      "learning_rate": 2e-05,
+      "loss": 0.1411,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.4933370351791382,
+      "learning_rate": 2e-05,
+      "loss": 0.1643,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.0871645212173462,
+      "learning_rate": 2e-05,
+      "loss": 0.1414,
+      "step": 22
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.6620066165924072,
+      "learning_rate": 2e-05,
+      "loss": 0.2243,
+      "step": 24
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 2.9521846771240234,
+      "learning_rate": 2e-05,
+      "loss": 0.2429,
+      "step": 26
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.639235019683838,
+      "learning_rate": 2e-05,
+      "loss": 0.2129,
+      "step": 28
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.291696310043335,
+      "learning_rate": 2e-05,
+      "loss": 0.0955,
+      "step": 30
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.4152330458164215,
+      "learning_rate": 2e-05,
+      "loss": 0.0401,
+      "step": 32
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 1.5247786045074463,
+      "learning_rate": 2e-05,
+      "loss": 0.2212,
+      "step": 34
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.539447784423828,
+      "learning_rate": 2e-05,
+      "loss": 0.2224,
+      "step": 36
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.4657011032104492,
+      "learning_rate": 2e-05,
+      "loss": 0.3438,
+      "step": 38
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.40261077880859375,
+      "learning_rate": 2e-05,
+      "loss": 0.0533,
+      "step": 40
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 2.395925521850586,
+      "learning_rate": 2e-05,
+      "loss": 0.1601,
+      "step": 42
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.1181901693344116,
+      "learning_rate": 2e-05,
+      "loss": 0.1358,
+      "step": 44
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 2.107515573501587,
+      "learning_rate": 2e-05,
+      "loss": 0.1083,
+      "step": 46
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.8709938526153564,
+      "learning_rate": 2e-05,
+      "loss": 0.2125,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.597744941711426,
+      "learning_rate": 2e-05,
+      "loss": 0.1081,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "step": 50,
+      "total_flos": 5482320970645504.0,
+      "train_loss": 0.20053319931030272,
+      "train_runtime": 250.9428,
+      "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": 5482320970645504.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0760bbedf6d1154a0daa5f27e9de04bc206cf349728066699154d31fe898aa8
+size 541320910

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27daa99df9cf8105c87fe02faf59df27973beae20a6c3531ab2cba7e8cb671c1
+size 541320910

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c697c13d182a04f0ad837813b2488bbf470bbbd1a4ab2de47d841ab01c0b2950
+size 541320910

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c97f33ba9c0a8411ac5dc48c9077c7084cb015e76ba825762effc9f827d353
+size 541320910

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c2ae5dc4c806d470db6c99cdc0b802a5eb00d79b3670470429433e342ed6f2
+size 541320170

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4897dc9e7e8f652650caa6e381abf36b8e44fff6245a418224ed8b2254b15a9
+size 541320910

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea7467675666c00bd79cb446911b03ff64817ab29ffe3fc8c1797cd05473ff4
+size 541320170

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36cc593f767110f5c41711c4839341bf8942174c45fb29cb9852c150a7502060
+size 541320170

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_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": 3.8343071937561035,
+      "learning_rate": 2e-05,
+      "loss": 0.3821,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.627742052078247,
+      "learning_rate": 2e-05,
+      "loss": 0.3509,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.7913460731506348,
+      "learning_rate": 2e-05,
+      "loss": 0.1982,
+      "step": 6
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.3273074626922607,
+      "learning_rate": 2e-05,
+      "loss": 0.333,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.7180984020233154,
+      "learning_rate": 2e-05,
+      "loss": 0.3994,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.879027843475342,
+      "learning_rate": 2e-05,
+      "loss": 0.3653,
+      "step": 12
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.5970039367675781,
+      "learning_rate": 2e-05,
+      "loss": 0.1159,
+      "step": 14
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.7551569938659668,
+      "learning_rate": 2e-05,
+      "loss": 0.1514,
+      "step": 16
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 7.370809555053711,
+      "learning_rate": 2e-05,
+      "loss": 0.555,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.195746898651123,
+      "learning_rate": 2e-05,
+      "loss": 0.1747,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.975414276123047,
+      "learning_rate": 2e-05,
+      "loss": 0.4369,
+      "step": 22
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.256625652313232,
+      "learning_rate": 2e-05,
+      "loss": 0.4799,
+      "step": 24
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 6.363062858581543,
+      "learning_rate": 2e-05,
+      "loss": 0.6253,
+      "step": 26
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 7.18313455581665,
+      "learning_rate": 2e-05,
+      "loss": 0.3445,
+      "step": 28
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 3.444873571395874,
+      "learning_rate": 2e-05,
+      "loss": 0.3388,
+      "step": 30
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 10.54517936706543,
+      "learning_rate": 2e-05,
+      "loss": 0.6635,
+      "step": 32
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 6.50941801071167,
+      "learning_rate": 2e-05,
+      "loss": 0.3597,
+      "step": 34
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.259827136993408,
+      "learning_rate": 2e-05,
+      "loss": 0.1364,
+      "step": 36
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 5.450165748596191,
+      "learning_rate": 2e-05,
+      "loss": 0.3065,
+      "step": 38
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.3496806621551514,
+      "learning_rate": 2e-05,
+      "loss": 0.3616,
+      "step": 40
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 5.643587112426758,
+      "learning_rate": 2e-05,
+      "loss": 0.4374,
+      "step": 42
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 6.12489652633667,
+      "learning_rate": 2e-05,
+      "loss": 0.2922,
+      "step": 44
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 2.0486600399017334,
+      "learning_rate": 2e-05,
+      "loss": 0.2478,
+      "step": 46
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 4.529411792755127,
+      "learning_rate": 2e-05,
+      "loss": 0.4061,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.211538553237915,
+      "learning_rate": 2e-05,
+      "loss": 0.2573,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "step": 50,
+      "total_flos": 2369624523931648.0,
+      "train_loss": 0.34879604339599607,
+      "train_runtime": 151.6346,
+      "train_samples_per_second": 1.319,
+      "train_steps_per_second": 0.33
+    }
+  ],
+  "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": 2369624523931648.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1070226eaaced9ba7217b6e74a66b82dbcb556e0275f5ae3729f4d34dfbe153d
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659cbf56d5f266a48f74c768a7e171ef7ca3409f2559c42fea454969cac11ef9
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77f50038368cd4f83465a4f821d05ec2e39801da19c01ed9f169b34a789b478
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc38c55ca53e499566c5a6510ac2bb14002f044d3825bc787b6fee5e345e9b26
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a65d5afcf7ff97dc1af6c600ad82956e294d39a73b37fd2456e47d56b344d7b
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c9c0aa559582c451a2e86b72718f06e883f0352bfaa819d85fb8fa09b9b176
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc97475933a047823bbb68c6a8315fb88ba592e0d03562beb7c8f623a75af85
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d08fbeedc51e4984f61d3ecf6b306ff07c451f85c89e53f161cfe101e74b29
+size 1167511866

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_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": 1.800782322883606,
+      "learning_rate": 2e-05,
+      "loss": 0.2007,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.441855788230896,
+      "learning_rate": 2e-05,
+      "loss": 0.3218,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.8594323396682739,
+      "learning_rate": 2e-05,
+      "loss": 0.1535,
+      "step": 6
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.0576399564743042,
+      "learning_rate": 2e-05,
+      "loss": 0.1581,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.1399861574172974,
+      "learning_rate": 2e-05,
+      "loss": 0.1523,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.5218842029571533,
+      "learning_rate": 2e-05,
+      "loss": 0.1663,
+      "step": 12
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.6733721494674683,
+      "learning_rate": 2e-05,
+      "loss": 0.1708,
+      "step": 14
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.129305124282837,
+      "learning_rate": 2e-05,
+      "loss": 0.169,
+      "step": 16
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.7069323062896729,
+      "learning_rate": 2e-05,
+      "loss": 0.2259,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.6732808351516724,
+      "learning_rate": 2e-05,
+      "loss": 0.1896,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.37410569190979,
+      "learning_rate": 2e-05,
+      "loss": 0.1716,
+      "step": 22
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.9175829291343689,
+      "learning_rate": 2e-05,
+      "loss": 0.2634,
+      "step": 24
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.203636884689331,
+      "learning_rate": 2e-05,
+      "loss": 0.2341,
+      "step": 26
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.40644341707229614,
+      "learning_rate": 2e-05,
+      "loss": 0.1233,
+      "step": 28
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.542734980583191,
+      "learning_rate": 2e-05,
+      "loss": 0.2145,
+      "step": 30
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.6000750064849854,
+      "learning_rate": 2e-05,
+      "loss": 0.1029,
+      "step": 32
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 1.792385220527649,
+      "learning_rate": 2e-05,
+      "loss": 0.3384,
+      "step": 34
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.7753247022628784,
+      "learning_rate": 2e-05,
+      "loss": 0.1732,
+      "step": 36
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.9580908417701721,
+      "learning_rate": 2e-05,
+      "loss": 0.1356,
+      "step": 38
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.3093552589416504,
+      "learning_rate": 2e-05,
+      "loss": 0.1695,
+      "step": 40
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 2.1371774673461914,
+      "learning_rate": 2e-05,
+      "loss": 0.1387,
+      "step": 42
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 2.778670310974121,
+      "learning_rate": 2e-05,
+      "loss": 0.2994,
+      "step": 44
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.966310977935791,
+      "learning_rate": 2e-05,
+      "loss": 0.1486,
+      "step": 46
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.992647111415863,
+      "learning_rate": 2e-05,
+      "loss": 0.0735,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.4049288034439087,
+      "learning_rate": 2e-05,
+      "loss": 0.2206,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "step": 50,
+      "total_flos": 6353755020722176.0,
+      "train_loss": 0.18861881256103516,
+      "train_runtime": 249.9395,
+      "train_samples_per_second": 0.8,
+      "train_steps_per_second": 0.2
+    }
+  ],
+  "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_sc315_4tasks_5rounds_fixitr50_T0125_decay099/5_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfef2d9c4b2e00fa69679102482306a6ba8e018b93d7b2dfbc276c2162ef4208
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/5_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1657b71a7d3aa37048a3a54abedc3f0ef167fdbde7a3cadc2cf7751d56971aa
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/5_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e97d03cad0cfa40f1148060e85da1f5ee057d4ece186f760b67a46767fec21ee
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/5_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0377a78adc6312193fd97b5718bfd65baa9b634fc2f00f183b7cbfa86f7b00b8
+size 1167513110

client_states_feddat_bs4_saveoptim_lr2e-5_sc315_4tasks_5rounds_fixitr50_T0125_decay099/5_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63516fc26fd2840bd87c376adb0421d4dd687ee73cd6c1a8641855bb43013e66
+size 1167511866