Upload folder using huggingface_hub

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/0_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7683bb4ea2a24dff622304d61701404a0684195b95f9250e01e70995b9f33b60
+size 84049390

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/0_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a8f21d51f1d852500947c6f6cd4ac3c7bf8d2f78ca632e5da650501051a821
+size 84049390

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/0_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efdf8d36d0c485c31fabbec778c518ab69e13effb160d8b75bb54118131f4672
+size 84049390

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/0_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8f4ea3a7bdefd00087f485fc726583cd3cbd85b917881387e5ea2b95ab34a8
+size 84049390

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/0_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9d462b48368e9cad91c2ccf4c5c05c7752edba6bf41e12f73d3f1df82bed250
+size 84048874

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/0_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b61eac975c6482170877e9be8e10a3dda12ff6115f7e0a496a95fb736de87791
+size 84049390

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/0_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c83ade3092b38a35d67cde82a2166da52dae0f76f25a41889628aa13c76631
+size 84048874

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/0_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe15bd6d2f28b6947c6a677d0cf05b69240312e24e89c89412d82c828f62ee00
+size 84048874

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/0_trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.24416396021842957,
+      "learning_rate": 0.0003,
+      "loss": 0.4589,
+      "step": 2
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.2861782908439636,
+      "learning_rate": 0.0003,
+      "loss": 0.5497,
+      "step": 4
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.28807416558265686,
+      "learning_rate": 0.0003,
+      "loss": 0.5351,
+      "step": 6
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.3524809181690216,
+      "learning_rate": 0.0003,
+      "loss": 0.6347,
+      "step": 8
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.21695467829704285,
+      "learning_rate": 0.0003,
+      "loss": 0.5836,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.26244187355041504,
+      "learning_rate": 0.0003,
+      "loss": 0.7104,
+      "step": 12
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.1886732578277588,
+      "learning_rate": 0.0003,
+      "loss": 0.3353,
+      "step": 14
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.3749811351299286,
+      "learning_rate": 0.0003,
+      "loss": 0.6642,
+      "step": 16
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.3102177083492279,
+      "learning_rate": 0.0003,
+      "loss": 0.6082,
+      "step": 18
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.3232249319553375,
+      "learning_rate": 0.0003,
+      "loss": 0.6706,
+      "step": 20
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.3113941550254822,
+      "learning_rate": 0.0003,
+      "loss": 0.4988,
+      "step": 22
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.31279242038726807,
+      "learning_rate": 0.0003,
+      "loss": 0.6155,
+      "step": 24
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.28257760405540466,
+      "learning_rate": 0.0003,
+      "loss": 0.529,
+      "step": 26
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.29951271414756775,
+      "learning_rate": 0.0003,
+      "loss": 0.6252,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.28102612495422363,
+      "learning_rate": 0.0003,
+      "loss": 0.6261,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "step": 30,
+      "total_flos": 1196511245369344.0,
+      "train_loss": 0.5763573904832204,
+      "train_runtime": 48.5145,
+      "train_samples_per_second": 2.473,
+      "train_steps_per_second": 0.618
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 30,
+  "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": 1196511245369344.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/1_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31500f229e4dede815dc1cc073235b4910c5640d3f9f99749e4f72e32ca3db44
+size 48770134

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/1_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94cf1f2ddc94b0d84d41afde7e24759d2211a03e0fab68e0542bb7cbae44d24c
+size 48770134

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/1_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8231a23a9e887e103a1bea2b34e07dbdd7b32d3e9a3ce6cacb38f9c7d8a84352
+size 48770134

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/1_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4632dc38995fd9058cb3bb3a74a7a3f0acdd96f2a1da229c53116be8290d5f9
+size 48770134

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/1_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0374a33829e21756f1c74170b81a6df936c7af2f9da602333c5674eac242a81
+size 48769674

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/1_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce872529f7431f71b64e45c64eeb5e1968e51ef863244a28fdd348e9286a1f8
+size 48770134

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/1_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:648dc41a6d4e798c5adf00f42548fcf41d160761046cc2999039fca354944806
+size 48769674

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/1_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e02abd240d532114b52e1ec2eb1b26449b496cf245448e44f8e802929895f22
+size 48769674

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/1_trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.9023004770278931,
+      "learning_rate": 0.0003,
+      "loss": 1.5571,
+      "step": 2
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.5817632675170898,
+      "learning_rate": 0.0003,
+      "loss": 1.7767,
+      "step": 4
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.4354921579360962,
+      "learning_rate": 0.0003,
+      "loss": 1.731,
+      "step": 6
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.3641677498817444,
+      "learning_rate": 0.0003,
+      "loss": 1.6872,
+      "step": 8
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.28223559260368347,
+      "learning_rate": 0.0003,
+      "loss": 0.7443,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2681761384010315,
+      "learning_rate": 0.0003,
+      "loss": 1.2404,
+      "step": 12
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.44366130232810974,
+      "learning_rate": 0.0003,
+      "loss": 1.9958,
+      "step": 14
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.39765021204948425,
+      "learning_rate": 0.0003,
+      "loss": 1.4386,
+      "step": 16
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.6642311811447144,
+      "learning_rate": 0.0003,
+      "loss": 2.1369,
+      "step": 18
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.5510743260383606,
+      "learning_rate": 0.0003,
+      "loss": 2.0597,
+      "step": 20
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.45161959528923035,
+      "learning_rate": 0.0003,
+      "loss": 1.6513,
+      "step": 22
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.3321634531021118,
+      "learning_rate": 0.0003,
+      "loss": 1.605,
+      "step": 24
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.6213057041168213,
+      "learning_rate": 0.0003,
+      "loss": 1.7325,
+      "step": 26
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.43713563680648804,
+      "learning_rate": 0.0003,
+      "loss": 1.4591,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5952392816543579,
+      "learning_rate": 0.0003,
+      "loss": 2.0974,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "step": 30,
+      "total_flos": 305071842656256.0,
+      "train_loss": 1.6608658949534099,
+      "train_runtime": 42.0423,
+      "train_samples_per_second": 2.854,
+      "train_steps_per_second": 0.714
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 30,
+  "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": 305071842656256.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/2_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963fba097065a142c0541ce9526facbeae65ff78898ef02a1e2f0f723a862a06
+size 48770134

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/2_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863dee3962c380286ef4c7b450cb2510f759d0df1cee2bd79ba770ca703d6b5a
+size 48770134

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/2_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92c6a552dd3b85e4e36855e303c5cb57a0388d4632a3acaa5302ca646fbda017
+size 48770134

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/2_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec4da88e12a570b8176e33d4e833ca9833197f98837cc27f9094df7bcc1d9f47
+size 48770134

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/2_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c7085f793d1434518d9aed118ee8850b6a55de0a894e9edc95302a13baee13
+size 48769674

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/2_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eacf61ef3b77cdb6df02a9c2cb07c1947dcd233aa080c00ee541a7eca6dccc6a
+size 48770134

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/2_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1628f05f6b832066328946babf7025e77f425acfea9ad0713a1499422297c91
+size 48769674

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/2_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b0b5bad83b2738ad513afc4ac7711f67c12fafcf1c1ed2cce2aaf637865825
+size 48769674

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/2_trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.3037028908729553,
+      "learning_rate": 0.0003,
+      "loss": 0.9116,
+      "step": 2
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.3489552140235901,
+      "learning_rate": 0.0003,
+      "loss": 1.6459,
+      "step": 4
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.3942304253578186,
+      "learning_rate": 0.0003,
+      "loss": 1.0189,
+      "step": 6
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.29892203211784363,
+      "learning_rate": 0.0003,
+      "loss": 1.8188,
+      "step": 8
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.5498002171516418,
+      "learning_rate": 0.0003,
+      "loss": 1.3308,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.42956435680389404,
+      "learning_rate": 0.0003,
+      "loss": 2.4234,
+      "step": 12
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.29204803705215454,
+      "learning_rate": 0.0003,
+      "loss": 1.2476,
+      "step": 14
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.45598259568214417,
+      "learning_rate": 0.0003,
+      "loss": 1.6462,
+      "step": 16
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2771050035953522,
+      "learning_rate": 0.0003,
+      "loss": 0.8,
+      "step": 18
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.23567508161067963,
+      "learning_rate": 0.0003,
+      "loss": 1.3243,
+      "step": 20
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.4404710829257965,
+      "learning_rate": 0.0003,
+      "loss": 2.0618,
+      "step": 22
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.475818395614624,
+      "learning_rate": 0.0003,
+      "loss": 1.9837,
+      "step": 24
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.3802916705608368,
+      "learning_rate": 0.0003,
+      "loss": 1.8485,
+      "step": 26
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.43724003434181213,
+      "learning_rate": 0.0003,
+      "loss": 0.9082,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.21405752003192902,
+      "learning_rate": 0.0003,
+      "loss": 1.7006,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "step": 30,
+      "total_flos": 580445060202496.0,
+      "train_loss": 1.5113671978314718,
+      "train_runtime": 42.5765,
+      "train_samples_per_second": 2.818,
+      "train_steps_per_second": 0.705
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 30,
+  "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": 580445060202496.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/3_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f9ba92d85e161ddac50cbfa1376def41b8d564876d86da5bb0a73e5f5897e0
+size 48770134

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/3_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56c1e2ede2ef52e0ce5b80fe084164ea027a24dbe02b6ae7084ab4163e7f138
+size 48770134

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/3_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000cbfb5eb0df3a6772db4a5ba76965417e97dbcfd6f80c20db43fbc1cca7919
+size 48770134

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/3_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10851f6148ba1adf32ead3d827ee058c411fbcc5543de63f040822768e553348
+size 48770134

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/3_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a5f9ae6d49abe626a408ff3516e35c481686287266a07609307499f1f3b923
+size 48769674

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/3_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c2abfadebda687c435c856c4927a4b71c9168b9d47cc07b81c30c07f39f6053
+size 48770134

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/3_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f19790a399e75267ef51f23d3c69e581779159e150dbc269ab6b30502c96556
+size 48769674

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/3_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec671844c9cd52814d46ea7a6c890dcb81f2f45a04c140372af16e38bbebdd9f
+size 48769674

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/3_trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.16276100277900696,
+      "learning_rate": 0.0003,
+      "loss": 0.833,
+      "step": 2
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.251880019903183,
+      "learning_rate": 0.0003,
+      "loss": 0.883,
+      "step": 4
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.2255876660346985,
+      "learning_rate": 0.0003,
+      "loss": 0.6912,
+      "step": 6
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.2852807641029358,
+      "learning_rate": 0.0003,
+      "loss": 0.9001,
+      "step": 8
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.21784625947475433,
+      "learning_rate": 0.0003,
+      "loss": 0.8835,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.19225150346755981,
+      "learning_rate": 0.0003,
+      "loss": 0.5988,
+      "step": 12
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.14822231233119965,
+      "learning_rate": 0.0003,
+      "loss": 0.5905,
+      "step": 14
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.1591639667749405,
+      "learning_rate": 0.0003,
+      "loss": 0.4959,
+      "step": 16
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.12191551923751831,
+      "learning_rate": 0.0003,
+      "loss": 0.6851,
+      "step": 18
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.31107524037361145,
+      "learning_rate": 0.0003,
+      "loss": 0.6968,
+      "step": 20
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.18976068496704102,
+      "learning_rate": 0.0003,
+      "loss": 0.9054,
+      "step": 22
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.23062096536159515,
+      "learning_rate": 0.0003,
+      "loss": 0.4708,
+      "step": 24
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.3150513470172882,
+      "learning_rate": 0.0003,
+      "loss": 0.6063,
+      "step": 26
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.15745581686496735,
+      "learning_rate": 0.0003,
+      "loss": 0.4576,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.20806829631328583,
+      "learning_rate": 0.0003,
+      "loss": 0.6251,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "step": 30,
+      "total_flos": 1809773389414400.0,
+      "train_loss": 0.6882031063238779,
+      "train_runtime": 53.2716,
+      "train_samples_per_second": 2.253,
+      "train_steps_per_second": 0.563
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 30,
+  "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": 1809773389414400.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/4_client_model_round10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad083f2e642a767d5504eb2dd2e2c1ffeacb9765251550c355fcc0d1dc61199
+size 84049390

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/4_client_model_round12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be02dbb2f9a3dc8edf5df8d3606692c50f06f2c89b23f8b6daf92f966649b22d
+size 84049390

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/4_client_model_round15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5ff7e1f593d4b3a29a210026ea5b2b0154e90f2a5832bbbb5067e40eda2bda8
+size 84049390

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/4_client_model_round17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a0f9fe0829a1607a5e1f12053abf5062647afeb1fbccc13457f8f449c6dd3ca
+size 84049390

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/4_client_model_round2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffcbd8292ac0a7ac227c08a272e9b49049d3f1828668e5f5686a29eae4683bee
+size 84048874

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/4_client_model_round20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8347c82a60d5d8cff43f998c24f471d16985a6bad1652d26e48cdcfa9ba022e2
+size 84049390

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/4_client_model_round5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5efa904dfdf8aeafd4ae597f530c9125b89c869b8cb43f650a3651f701b43189
+size 84048874

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/4_client_model_round7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bce00e87548e396505aee69f7ff404d99885432c726eff94ff85f2596d467302
+size 84048874

client_states_NEW_fedavg_NOCONT_bs4_saveoptim_r16_32_lr3e-4_sc74_4tasks_5rounds_fixtir30_T0125_decay099/4_trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.2867070138454437,
+      "learning_rate": 0.0003,
+      "loss": 0.5952,
+      "step": 2
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.33537670969963074,
+      "learning_rate": 0.0003,
+      "loss": 0.9564,
+      "step": 4
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.3584403991699219,
+      "learning_rate": 0.0003,
+      "loss": 0.9349,
+      "step": 6
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.3439081907272339,
+      "learning_rate": 0.0003,
+      "loss": 0.8646,
+      "step": 8
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.44978123903274536,
+      "learning_rate": 0.0003,
+      "loss": 0.9359,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.3586316704750061,
+      "learning_rate": 0.0003,
+      "loss": 0.8132,
+      "step": 12
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.26364096999168396,
+      "learning_rate": 0.0003,
+      "loss": 0.5523,
+      "step": 14
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.31966859102249146,
+      "learning_rate": 0.0003,
+      "loss": 0.9114,
+      "step": 16
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.35554757714271545,
+      "learning_rate": 0.0003,
+      "loss": 1.3788,
+      "step": 18
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.258931964635849,
+      "learning_rate": 0.0003,
+      "loss": 0.6495,
+      "step": 20
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.2897098660469055,
+      "learning_rate": 0.0003,
+      "loss": 1.0337,
+      "step": 22
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.2801041007041931,
+      "learning_rate": 0.0003,
+      "loss": 0.8032,
+      "step": 24
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.3492525815963745,
+      "learning_rate": 0.0003,
+      "loss": 0.7369,
+      "step": 26
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.44734007120132446,
+      "learning_rate": 0.0003,
+      "loss": 0.8824,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.29203251004219055,
+      "learning_rate": 0.0003,
+      "loss": 0.7433,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "step": 30,
+      "total_flos": 3616159123374080.0,
+      "train_loss": 0.8527638713518778,
+      "train_runtime": 68.1295,
+      "train_samples_per_second": 1.761,
+      "train_steps_per_second": 0.44
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 30,
+  "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": 3616159123374080.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}