Upload folder using huggingface_hub

client_states_ditto_NOCONT_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:c803ac2d7df8d3416d277e195b5c429bd7fe4ca71d70c1457334691b77dee74e
+size 778341886

client_states_ditto_NOCONT_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 sha256:334662a46a6b6c6c620a810f6df83b72e2fc02dd4817bbd03d402b35cd145e3a
+size 778341886

client_states_ditto_NOCONT_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 sha256:8886497483ae7c72c6bad712c4c1cae2f488c255d23f1d8e1d9ddfa4be9a6dcd
+size 778341886

client_states_ditto_NOCONT_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:b8620b03c3b778b43c26aa8b6b94d7af38574e540c89eba509f711b140a5ce50
+size 778341886

client_states_ditto_NOCONT_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 sha256:739d3a91e1f18921c094b00b959a571bbce95ad66d10eb85fdd7d0562b75800c
+size 778341034

client_states_ditto_NOCONT_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:c2dbcde1c440af5564dcdeb27f25835d60208d7449965006a01cc6ecfa41b841
+size 778341886

client_states_ditto_NOCONT_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 sha256:0d01e6526959b1fbbcebe2d6b15319de000dc7270b42631865c0543e4adb784c
+size 778341034

client_states_ditto_NOCONT_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 sha256:137a812e74b6fad89835750748176d351c0c4f6a449d9853ecdda130305725f8
+size 778341034

client_states_ditto_NOCONT_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": 0.7667892575263977,
+      "learning_rate": 2e-05,
+      "loss": 0.1179,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.5806317329406738,
+      "learning_rate": 2e-05,
+      "loss": 0.0748,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.9773032665252686,
+      "learning_rate": 2e-05,
+      "loss": 0.161,
+      "step": 6
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 10.056038856506348,
+      "learning_rate": 2e-05,
+      "loss": 0.9856,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.048658847808838,
+      "learning_rate": 2e-05,
+      "loss": 0.2802,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.219111919403076,
+      "learning_rate": 2e-05,
+      "loss": 0.2203,
+      "step": 12
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 11.86638355255127,
+      "learning_rate": 2e-05,
+      "loss": 0.4414,
+      "step": 14
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 8.374286651611328,
+      "learning_rate": 2e-05,
+      "loss": 0.5991,
+      "step": 16
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.21061983704566956,
+      "learning_rate": 2e-05,
+      "loss": 0.3935,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 9.000163078308105,
+      "learning_rate": 2e-05,
+      "loss": 0.3326,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 6.770906925201416,
+      "learning_rate": 2e-05,
+      "loss": 0.1982,
+      "step": 22
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.7530550956726074,
+      "learning_rate": 2e-05,
+      "loss": 0.2769,
+      "step": 24
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.6666361093521118,
+      "learning_rate": 2e-05,
+      "loss": 0.2491,
+      "step": 26
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.6201651096343994,
+      "learning_rate": 2e-05,
+      "loss": 0.1815,
+      "step": 28
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.6012219786643982,
+      "learning_rate": 2e-05,
+      "loss": 0.1345,
+      "step": 30
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 7.640186309814453,
+      "learning_rate": 2e-05,
+      "loss": 0.5771,
+      "step": 32
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 3.2143445014953613,
+      "learning_rate": 2e-05,
+      "loss": 0.1147,
+      "step": 34
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 7.746758460998535,
+      "learning_rate": 2e-05,
+      "loss": 0.78,
+      "step": 36
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.48903387784957886,
+      "learning_rate": 2e-05,
+      "loss": 0.1493,
+      "step": 38
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 3.833240032196045,
+      "learning_rate": 2e-05,
+      "loss": 0.1742,
+      "step": 40
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 2.32177734375,
+      "learning_rate": 2e-05,
+      "loss": 0.1063,
+      "step": 42
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 8.378777503967285,
+      "learning_rate": 2e-05,
+      "loss": 0.4172,
+      "step": 44
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 11.414420127868652,
+      "learning_rate": 2e-05,
+      "loss": 0.5939,
+      "step": 46
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 6.671710968017578,
+      "learning_rate": 2e-05,
+      "loss": 0.232,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5039780139923096,
+      "learning_rate": 2e-05,
+      "loss": 0.2037,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "step": 50,
+      "total_flos": 5262165829222400.0,
+      "train_loss": 0.31980655193328855,
+      "train_runtime": 239.9667,
+      "train_samples_per_second": 0.833,
+      "train_steps_per_second": 0.208
+    }
+  ],
+  "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": 5262165829222400.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_ditto_NOCONT_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 sha256:6489ed9886b89c9ea85e70292d4342a2a716cc8be6ca5a76aa2971d005b437ab
+size 778341886

client_states_ditto_NOCONT_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:f8a07013192dd24753b5c7c55c95900a707d0ceb6304c30525eb2f6f46ea98f3
+size 778341886

client_states_ditto_NOCONT_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 sha256:6750114d435cc8667c82f070a1038bdfd026db427756d4446a63eddfee439c8b
+size 778341886

client_states_ditto_NOCONT_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:d1ebf73ed1505ecf6f8c853da753c6c52c593830ad9bb378889cf0573c786710
+size 778341886

client_states_ditto_NOCONT_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 sha256:6829b71110e91404783fcf920df526232d254e61ccf7209145356193ae7fd467
+size 778341034

client_states_ditto_NOCONT_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 sha256:3f9c2bd1eb8f46ada3ab8ee4637aded3aa4d5fa5290a3f6b771c43eedf33b360
+size 778341886

client_states_ditto_NOCONT_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 sha256:072d36de5c413c031e7ae3e22007260d08480a014acafbaea2d3aebc4f9814a4
+size 778341034

client_states_ditto_NOCONT_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 sha256:042c737efc6df6277e3cc924bb335a9ac8e38e3684d3f6cf497d26e41f5662ad
+size 778341034

client_states_ditto_NOCONT_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": 0.14927105605602264,
+      "learning_rate": 2e-05,
+      "loss": 0.0217,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.12387175112962723,
+      "learning_rate": 2e-05,
+      "loss": 0.0184,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.013222594745457172,
+      "learning_rate": 2e-05,
+      "loss": 0.0217,
+      "step": 6
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.450136423110962,
+      "learning_rate": 2e-05,
+      "loss": 0.0769,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.021984504535794258,
+      "learning_rate": 2e-05,
+      "loss": 0.1508,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.1526262760162354,
+      "learning_rate": 2e-05,
+      "loss": 0.041,
+      "step": 12
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.11113946884870529,
+      "learning_rate": 2e-05,
+      "loss": 0.0182,
+      "step": 14
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.011015263386070728,
+      "learning_rate": 2e-05,
+      "loss": 0.0179,
+      "step": 16
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.09534614533185959,
+      "learning_rate": 2e-05,
+      "loss": 0.0208,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.43175551295280457,
+      "learning_rate": 2e-05,
+      "loss": 0.0249,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.016742650419473648,
+      "learning_rate": 2e-05,
+      "loss": 0.0165,
+      "step": 22
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.033203743398189545,
+      "learning_rate": 2e-05,
+      "loss": 0.1004,
+      "step": 24
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.04871096834540367,
+      "learning_rate": 2e-05,
+      "loss": 0.0177,
+      "step": 26
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 5.269626617431641,
+      "learning_rate": 2e-05,
+      "loss": 0.0943,
+      "step": 28
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.33731862902641296,
+      "learning_rate": 2e-05,
+      "loss": 0.0197,
+      "step": 30
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.05585172027349472,
+      "learning_rate": 2e-05,
+      "loss": 0.7125,
+      "step": 32
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.02681584283709526,
+      "learning_rate": 2e-05,
+      "loss": 0.0495,
+      "step": 34
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.022232314571738243,
+      "learning_rate": 2e-05,
+      "loss": 0.0163,
+      "step": 36
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.782255172729492,
+      "learning_rate": 2e-05,
+      "loss": 0.0773,
+      "step": 38
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.048367224633693695,
+      "learning_rate": 2e-05,
+      "loss": 0.1995,
+      "step": 40
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.01112910732626915,
+      "learning_rate": 2e-05,
+      "loss": 0.018,
+      "step": 42
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.02462596632540226,
+      "learning_rate": 2e-05,
+      "loss": 0.0176,
+      "step": 44
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 4.232011318206787,
+      "learning_rate": 2e-05,
+      "loss": 0.2029,
+      "step": 46
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.059689201414585114,
+      "learning_rate": 2e-05,
+      "loss": 0.0178,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7513514757156372,
+      "learning_rate": 2e-05,
+      "loss": 0.0355,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "step": 50,
+      "total_flos": 5304318332764160.0,
+      "train_loss": 0.08031658798456193,
+      "train_runtime": 238.74,
+      "train_samples_per_second": 0.838,
+      "train_steps_per_second": 0.209
+    }
+  ],
+  "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": 5304318332764160.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_ditto_NOCONT_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 sha256:8fb547dc6739b9763fed5be8fb4fa30cd3e7f8336003c76e755885aa6b782715
+size 778341886

client_states_ditto_NOCONT_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 sha256:8adc01237d9489b6ca3ff7075680ccd5a630a10c3a6af077971c22b13b3788a6
+size 778341886

client_states_ditto_NOCONT_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:cc8d7aeec99792b634bc505737836c991747964b9a862175fd0e18bf2ac5be3d
+size 778341886

client_states_ditto_NOCONT_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 sha256:8e62db05415e2a77393da2f301921cdaac5ea8f3ff533781436cbf34371ea575
+size 778341886

client_states_ditto_NOCONT_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 sha256:5760884bec441f710b95253fef84bfe641a42be3d81d10247ecfbe65ac517e92
+size 778341034

client_states_ditto_NOCONT_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 sha256:1c232c002a1b9d4f6ee5ed306340310000cccd6fbd86f191f5c56fe51b11a6b9
+size 778341886

client_states_ditto_NOCONT_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:d8fb21d4da2f9fe73cdefa91deb0b6742acd8e7b706caddd1b17d58033c13b34
+size 778341034

client_states_ditto_NOCONT_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 sha256:95c1de8e32062c486e66c1cb968d7c5ca7eab1da261ec880d4c0fb09a1c7fc99
+size 778341034

client_states_ditto_NOCONT_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": 3.6483705043792725,
+      "learning_rate": 2e-05,
+      "loss": 0.2636,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.38539457321167,
+      "learning_rate": 2e-05,
+      "loss": 0.2129,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.941530704498291,
+      "learning_rate": 2e-05,
+      "loss": 0.4584,
+      "step": 6
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 8.902280807495117,
+      "learning_rate": 2e-05,
+      "loss": 0.302,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.929030895233154,
+      "learning_rate": 2e-05,
+      "loss": 0.6967,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.339599609375,
+      "learning_rate": 2e-05,
+      "loss": 0.647,
+      "step": 12
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.5364546179771423,
+      "learning_rate": 2e-05,
+      "loss": 0.3199,
+      "step": 14
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.1174445152282715,
+      "learning_rate": 2e-05,
+      "loss": 0.509,
+      "step": 16
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.4249067306518555,
+      "learning_rate": 2e-05,
+      "loss": 0.2703,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 9.164104461669922,
+      "learning_rate": 2e-05,
+      "loss": 0.4174,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.5465577840805054,
+      "learning_rate": 2e-05,
+      "loss": 0.2393,
+      "step": 22
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.968472957611084,
+      "learning_rate": 2e-05,
+      "loss": 0.2272,
+      "step": 24
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.181370735168457,
+      "learning_rate": 2e-05,
+      "loss": 0.4012,
+      "step": 26
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 8.281719207763672,
+      "learning_rate": 2e-05,
+      "loss": 0.4838,
+      "step": 28
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.6046605110168457,
+      "learning_rate": 2e-05,
+      "loss": 0.3552,
+      "step": 30
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 8.130400657653809,
+      "learning_rate": 2e-05,
+      "loss": 0.2694,
+      "step": 32
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 5.307687282562256,
+      "learning_rate": 2e-05,
+      "loss": 0.4507,
+      "step": 34
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.459664225578308,
+      "learning_rate": 2e-05,
+      "loss": 0.2014,
+      "step": 36
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.2293667793273926,
+      "learning_rate": 2e-05,
+      "loss": 0.3504,
+      "step": 38
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 4.12849235534668,
+      "learning_rate": 2e-05,
+      "loss": 0.8053,
+      "step": 40
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 1.7654016017913818,
+      "learning_rate": 2e-05,
+      "loss": 0.2757,
+      "step": 42
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.289141297340393,
+      "learning_rate": 2e-05,
+      "loss": 0.2181,
+      "step": 44
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 5.082073211669922,
+      "learning_rate": 2e-05,
+      "loss": 0.3774,
+      "step": 46
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.6545560359954834,
+      "learning_rate": 2e-05,
+      "loss": 0.1477,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.226861476898193,
+      "learning_rate": 2e-05,
+      "loss": 0.3506,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "step": 50,
+      "total_flos": 5202848019120128.0,
+      "train_loss": 0.37002829074859617,
+      "train_runtime": 239.6987,
+      "train_samples_per_second": 0.834,
+      "train_steps_per_second": 0.209
+    }
+  ],
+  "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": 5202848019120128.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_ditto_NOCONT_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 sha256:193d53610f34e7c99b69eac9f8c43aef7786fd30f4034c789cdbcdeb7d4d747f
+size 778341886

client_states_ditto_NOCONT_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:db099dd13a102389bc94596eb64726fa9238de2baa18ac5fad8254196327ab7c
+size 778341886

client_states_ditto_NOCONT_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 sha256:78b55a730433dcc522268fd7bcd39f6eacd1e21897f15aed08167a07cc96354b
+size 778341886

client_states_ditto_NOCONT_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 sha256:1f2e5966385f8c4f2d8b4e54d5d57f4218780028cc58f145fc684a737f41141d
+size 778341886

client_states_ditto_NOCONT_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:a2dff4fdb3421c783e2ceebc6eb8d768b480bf1580bc0a7dbf729844d872dcaf
+size 778341034

client_states_ditto_NOCONT_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 sha256:52dc234d376b4a5b67ece222e2a20466fa87f930433980b4d2cfa91b3fcd47d2
+size 778341886

client_states_ditto_NOCONT_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:afc8761857f99707fcc05cf67b8ef7d6ed3df9f564dd94ee2a6d3e8b5e7bdda7
+size 778341034

client_states_ditto_NOCONT_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:f817a8fdc6ea9b2eb800c698b8123bc616bc09eab9a2cd968eb31d9cf6806cb0
+size 778341034

client_states_ditto_NOCONT_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": 3.4478659629821777,
+      "learning_rate": 2e-05,
+      "loss": 0.3251,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.3723435401916504,
+      "learning_rate": 2e-05,
+      "loss": 0.2443,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.8664913177490234,
+      "learning_rate": 2e-05,
+      "loss": 0.502,
+      "step": 6
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 13.679643630981445,
+      "learning_rate": 2e-05,
+      "loss": 0.5109,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 16.67136573791504,
+      "learning_rate": 2e-05,
+      "loss": 0.6347,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.277215003967285,
+      "learning_rate": 2e-05,
+      "loss": 0.5943,
+      "step": 12
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.4732996225357056,
+      "learning_rate": 2e-05,
+      "loss": 0.3285,
+      "step": 14
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.1789543628692627,
+      "learning_rate": 2e-05,
+      "loss": 0.5106,
+      "step": 16
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.3657021522521973,
+      "learning_rate": 2e-05,
+      "loss": 0.5294,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 8.679784774780273,
+      "learning_rate": 2e-05,
+      "loss": 0.776,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.163334369659424,
+      "learning_rate": 2e-05,
+      "loss": 0.4622,
+      "step": 22
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.628009080886841,
+      "learning_rate": 2e-05,
+      "loss": 0.1345,
+      "step": 24
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 9.723793983459473,
+      "learning_rate": 2e-05,
+      "loss": 0.7767,
+      "step": 26
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 2.0383365154266357,
+      "learning_rate": 2e-05,
+      "loss": 0.3931,
+      "step": 28
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 15.98172378540039,
+      "learning_rate": 2e-05,
+      "loss": 0.8819,
+      "step": 30
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 5.598606109619141,
+      "learning_rate": 2e-05,
+      "loss": 0.3345,
+      "step": 32
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 13.945756912231445,
+      "learning_rate": 2e-05,
+      "loss": 0.7454,
+      "step": 34
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 4.697895526885986,
+      "learning_rate": 2e-05,
+      "loss": 0.1937,
+      "step": 36
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 3.633106231689453,
+      "learning_rate": 2e-05,
+      "loss": 0.3231,
+      "step": 38
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 7.842234134674072,
+      "learning_rate": 2e-05,
+      "loss": 1.003,
+      "step": 40
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 9.326179504394531,
+      "learning_rate": 2e-05,
+      "loss": 0.8243,
+      "step": 42
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 10.093409538269043,
+      "learning_rate": 2e-05,
+      "loss": 1.0942,
+      "step": 44
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 8.910246849060059,
+      "learning_rate": 2e-05,
+      "loss": 0.7166,
+      "step": 46
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 13.468656539916992,
+      "learning_rate": 2e-05,
+      "loss": 0.7485,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.664309501647949,
+      "learning_rate": 2e-05,
+      "loss": 0.8516,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "step": 50,
+      "total_flos": 5374290547441664.0,
+      "train_loss": 0.5775572681427001,
+      "train_runtime": 238.3272,
+      "train_samples_per_second": 0.839,
+      "train_steps_per_second": 0.21
+    }
+  ],
+  "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": 5374290547441664.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_ditto_NOCONT_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 sha256:555305873003cdd036adb9a510e035efabe73950fd00672e108c8d562fbb3ba6
+size 778341886

client_states_ditto_NOCONT_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:eca7ddf7e79e6d534fc0a16c86edd7bb1e391e76b3509187cb1b8e9e1da63de7
+size 778341886

client_states_ditto_NOCONT_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:e690c80156dc7e1c8d3aae75c5824bd69d62482c9aabda9d14e275cd738ccb99
+size 778341886

client_states_ditto_NOCONT_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:ec5c4a9d8dfb015f7aced084b5665491ff3b47d5612f5f3b9bfa1933008fcbca
+size 778341886

client_states_ditto_NOCONT_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:cf6ede4ac35e887bb1eaca4430ca7f87550c736110fa6e046703f1390348626d
+size 778341034

client_states_ditto_NOCONT_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 sha256:89ca116af1a07707cb9942a76b9f03970398ae45c35c46ce0578a8f353423a63
+size 778341886

client_states_ditto_NOCONT_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:cb162ac16ed798bfb593c93e0e4c529fb0ef36613eb4f9b7b16024030116b05e
+size 778341034

client_states_ditto_NOCONT_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:f7835c10392fe4da896edf502f8f9a6b7337763310d467dd87cc4436575978ff
+size 778341034

client_states_ditto_NOCONT_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": 1.9345431327819824,
+      "learning_rate": 2e-05,
+      "loss": 0.4416,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.169915199279785,
+      "learning_rate": 2e-05,
+      "loss": 0.517,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.80987286567688,
+      "learning_rate": 2e-05,
+      "loss": 0.5113,
+      "step": 6
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.478898525238037,
+      "learning_rate": 2e-05,
+      "loss": 0.3937,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.535274505615234,
+      "learning_rate": 2e-05,
+      "loss": 0.5091,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.092980146408081,
+      "learning_rate": 2e-05,
+      "loss": 0.3117,
+      "step": 12
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.6311594247817993,
+      "learning_rate": 2e-05,
+      "loss": 0.286,
+      "step": 14
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.5908632278442383,
+      "learning_rate": 2e-05,
+      "loss": 0.2972,
+      "step": 16
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.4908201694488525,
+      "learning_rate": 2e-05,
+      "loss": 0.4042,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.47562575340271,
+      "learning_rate": 2e-05,
+      "loss": 0.178,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.692809581756592,
+      "learning_rate": 2e-05,
+      "loss": 0.7429,
+      "step": 22
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 5.989434242248535,
+      "learning_rate": 2e-05,
+      "loss": 0.5588,
+      "step": 24
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 3.6605117321014404,
+      "learning_rate": 2e-05,
+      "loss": 0.54,
+      "step": 26
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 8.406970977783203,
+      "learning_rate": 2e-05,
+      "loss": 0.9017,
+      "step": 28
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 3.413125514984131,
+      "learning_rate": 2e-05,
+      "loss": 0.4279,
+      "step": 30
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 2.7760772705078125,
+      "learning_rate": 2e-05,
+      "loss": 0.2696,
+      "step": 32
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 5.107151031494141,
+      "learning_rate": 2e-05,
+      "loss": 0.354,
+      "step": 34
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.8273810148239136,
+      "learning_rate": 2e-05,
+      "loss": 0.5987,
+      "step": 36
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.8949187994003296,
+      "learning_rate": 2e-05,
+      "loss": 0.4651,
+      "step": 38
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 3.457481861114502,
+      "learning_rate": 2e-05,
+      "loss": 0.4585,
+      "step": 40
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 2.920348644256592,
+      "learning_rate": 2e-05,
+      "loss": 0.39,
+      "step": 42
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.8225722312927246,
+      "learning_rate": 2e-05,
+      "loss": 0.3335,
+      "step": 44
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 3.2992806434631348,
+      "learning_rate": 2e-05,
+      "loss": 0.4695,
+      "step": 46
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.4678384065628052,
+      "learning_rate": 2e-05,
+      "loss": 0.2763,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.645047426223755,
+      "learning_rate": 2e-05,
+      "loss": 0.5516,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "step": 50,
+      "total_flos": 6020445073571840.0,
+      "train_loss": 0.447514705657959,
+      "train_runtime": 239.0376,
+      "train_samples_per_second": 0.837,
+      "train_steps_per_second": 0.209
+    }
+  ],
+  "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": 6020445073571840.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_ditto_NOCONT_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:efd0a4e68e38029a29f2c80ea0243bda838fcedc66e84e6b4c64ce69e5137f6c
+size 778341886

client_states_ditto_NOCONT_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 sha256:90309922d05eef74fe4c07729306909ad87b9a3e01a3df898edde4dfc133ecc9
+size 778341886

client_states_ditto_NOCONT_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:a7b6b2c7d837443d1f4aea83b48e35fec26c944c6ccbf43a7f0084befa778742
+size 778341886

client_states_ditto_NOCONT_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 sha256:58af96c2fd96f7ffe05c717bda957b01d700813634f5cdb2168e99f0c64b6fbf
+size 778341886

client_states_ditto_NOCONT_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:c67f6cbfe8805ca677dd1b8102897b9bea09068cd4c7513fd4e39cfe0f6078c8
+size 778341034