Update model

config.json

@@ -1,5 +1,6 @@
 {
   "_name_or_path": "indobert-lite-base-p2",
+  "_num_labels": 5,
   "architectures": [
     "AlbertForTokenClassification"
   ],
@@ -27,8 +28,9 @@
     "9": "U-QUESTION",
     "10": "UU",
     "11": "UU-COMMA",
-    "12": "UU-PERIOD",
-    "13": "UU-QUESTION"
+    "12": "UU-EXCLAMATION",
+    "13": "UU-PERIOD",
+    "14": "UU-QUESTION"
   },
   "initializer_range": 0.02,
   "inner_group_num": 1,
@@ -46,8 +48,9 @@
     "U-QUESTION": 9,
     "UU": 10,
     "UU-COMMA": 11,
-    "UU-PERIOD": 12,
-    "UU-QUESTION": 13
+    "UU-EXCLAMATION": 12,
+    "UU-PERIOD": 13,
+    "UU-QUESTION": 14
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bb4f4c3abca46a16ae5a5bd681dd64e29ab60739d08b6b158a322d216ce16a9
-size 44427351
+oid sha256:8cc375a9ad426fa46d5d19ae02c80cfe321c94a602c32d66159b8b71af368c54
+size 44430423

trainer_state.json

@@ -1,169 +1,520 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
-  "global_step": 12316,
+  "epoch": 0.8585972156918863,
+  "global_step": 42000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.08,
-      "learning_rate": 4.7978239688210455e-05,
-      "loss": 0.2689,
+      "epoch": 0.01,
+      "learning_rate": 4.983032483594661e-05,
+      "loss": 0.3265,
       "step": 500
     },
     {
-      "epoch": 0.16,
-      "learning_rate": 4.595241961675869e-05,
-      "loss": 0.193,
+      "epoch": 0.02,
+      "learning_rate": 4.965996824553155e-05,
+      "loss": 0.2483,
       "step": 1000
     },
     {
-      "epoch": 0.24,
-      "learning_rate": 4.392253978564469e-05,
-      "loss": 0.183,
+      "epoch": 0.03,
+      "learning_rate": 4.948961165511649e-05,
+      "loss": 0.2357,
       "step": 1500
     },
     {
-      "epoch": 0.32,
-      "learning_rate": 4.189265995453069e-05,
-      "loss": 0.1763,
+      "epoch": 0.04,
+      "learning_rate": 4.9319255064701436e-05,
+      "loss": 0.2285,
       "step": 2000
     },
     {
-      "epoch": 0.41,
-      "learning_rate": 3.986278012341669e-05,
-      "loss": 0.1727,
+      "epoch": 0.05,
+      "learning_rate": 4.7446695422859136e-05,
+      "loss": 0.2259,
       "step": 2500
     },
     {
-      "epoch": 0.49,
-      "learning_rate": 3.7832900292302696e-05,
-      "loss": 0.1702,
+      "epoch": 0.06,
+      "learning_rate": 4.693562565161396e-05,
+      "loss": 0.2204,
       "step": 3000
     },
     {
-      "epoch": 0.57,
-      "learning_rate": 3.5803020461188695e-05,
-      "loss": 0.1678,
+      "epoch": 0.07,
+      "learning_rate": 4.642455588036879e-05,
+      "loss": 0.2183,
       "step": 3500
     },
     {
-      "epoch": 0.65,
-      "learning_rate": 3.37731406300747e-05,
-      "loss": 0.1645,
+      "epoch": 0.08,
+      "learning_rate": 4.591348610912362e-05,
+      "loss": 0.2167,
       "step": 4000
     },
     {
-      "epoch": 0.73,
-      "learning_rate": 3.1743260798960706e-05,
-      "loss": 0.1629,
+      "epoch": 0.09,
+      "learning_rate": 4.540343847742094e-05,
+      "loss": 0.2131,
       "step": 4500
     },
     {
-      "epoch": 0.81,
-      "learning_rate": 2.9713380967846704e-05,
-      "loss": 0.1608,
+      "epoch": 0.1,
+      "learning_rate": 4.489236870617577e-05,
+      "loss": 0.2123,
       "step": 5000
     },
     {
-      "epoch": 0.89,
-      "learning_rate": 2.768350113673271e-05,
-      "loss": 0.1587,
+      "epoch": 0.11,
+      "learning_rate": 4.4381298934930596e-05,
+      "loss": 0.212,
       "step": 5500
     },
     {
-      "epoch": 0.97,
-      "learning_rate": 2.565362130561871e-05,
-      "loss": 0.1561,
+      "epoch": 0.12,
+      "learning_rate": 4.387022916368543e-05,
+      "loss": 0.2075,
       "step": 6000
     },
     {
-      "epoch": 1.06,
-      "learning_rate": 2.362374147450471e-05,
-      "loss": 0.1453,
+      "epoch": 0.13,
+      "learning_rate": 4.336018153198275e-05,
+      "loss": 0.2077,
       "step": 6500
     },
     {
-      "epoch": 1.14,
-      "learning_rate": 2.1593861643390713e-05,
-      "loss": 0.1399,
+      "epoch": 0.14,
+      "learning_rate": 4.2849111760737576e-05,
+      "loss": 0.2061,
       "step": 7000
     },
     {
-      "epoch": 1.22,
-      "learning_rate": 1.9563981812276715e-05,
-      "loss": 0.139,
+      "epoch": 0.15,
+      "learning_rate": 4.23380419894924e-05,
+      "loss": 0.207,
       "step": 7500
     },
     {
-      "epoch": 1.3,
-      "learning_rate": 1.7534101981162717e-05,
-      "loss": 0.139,
+      "epoch": 0.16,
+      "learning_rate": 4.1826972218247236e-05,
+      "loss": 0.2039,
       "step": 8000
     },
     {
-      "epoch": 1.38,
-      "learning_rate": 1.5504222150048715e-05,
-      "loss": 0.1382,
+      "epoch": 0.17,
+      "learning_rate": 4.131590244700207e-05,
+      "loss": 0.2025,
       "step": 8500
     },
     {
-      "epoch": 1.46,
-      "learning_rate": 1.3474342318934719e-05,
-      "loss": 0.1381,
+      "epoch": 0.18,
+      "learning_rate": 4.08048326757569e-05,
+      "loss": 0.2004,
       "step": 9000
     },
     {
-      "epoch": 1.54,
-      "learning_rate": 1.1444462487820721e-05,
-      "loss": 0.1366,
+      "epoch": 0.19,
+      "learning_rate": 4.029376290451173e-05,
+      "loss": 0.2036,
       "step": 9500
     },
     {
-      "epoch": 1.62,
-      "learning_rate": 9.414582656706723e-06,
-      "loss": 0.1365,
+      "epoch": 0.2,
+      "learning_rate": 3.9782693133266555e-05,
+      "loss": 0.1998,
       "step": 10000
     },
     {
-      "epoch": 1.71,
-      "learning_rate": 7.384702825592725e-06,
-      "loss": 0.1348,
+      "epoch": 0.21,
+      "learning_rate": 3.927162336202139e-05,
+      "loss": 0.1995,
       "step": 10500
     },
     {
-      "epoch": 1.79,
-      "learning_rate": 5.358882754140955e-06,
-      "loss": 0.1351,
+      "epoch": 0.22,
+      "learning_rate": 3.876157573031871e-05,
+      "loss": 0.199,
       "step": 11000
     },
     {
-      "epoch": 1.87,
-      "learning_rate": 3.3290029230269568e-06,
-      "loss": 0.1343,
+      "epoch": 0.24,
+      "learning_rate": 3.8250505959073535e-05,
+      "loss": 0.1969,
       "step": 11500
     },
     {
-      "epoch": 1.95,
-      "learning_rate": 1.2991230919129588e-06,
-      "loss": 0.1339,
+      "epoch": 0.25,
+      "learning_rate": 3.773943618782836e-05,
+      "loss": 0.1937,
       "step": 12000
     },
     {
-      "epoch": 2.0,
-      "step": 12316,
-      "total_flos": 4101375688441856.0,
-      "train_loss": 0.15709904239873834,
-      "train_runtime": 1021.7988,
-      "train_samples_per_second": 771.383,
-      "train_steps_per_second": 12.053
+      "epoch": 0.26,
+      "learning_rate": 3.7228366416583195e-05,
+      "loss": 0.1963,
+      "step": 12500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 3.671729664533802e-05,
+      "loss": 0.1961,
+      "step": 13000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.6206226874092855e-05,
+      "loss": 0.1956,
+      "step": 13500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 3.569515710284768e-05,
+      "loss": 0.1953,
+      "step": 14000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.518715375022998e-05,
+      "loss": 0.1936,
+      "step": 14500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.4676083978984816e-05,
+      "loss": 0.1942,
+      "step": 15000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.416501420773964e-05,
+      "loss": 0.192,
+      "step": 15500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.3653944436494475e-05,
+      "loss": 0.1925,
+      "step": 16000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.31428746652493e-05,
+      "loss": 0.1905,
+      "step": 16500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.263180489400413e-05,
+      "loss": 0.1923,
+      "step": 17000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.212073512275896e-05,
+      "loss": 0.1897,
+      "step": 17500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.160966535151379e-05,
+      "loss": 0.1908,
+      "step": 18000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.109859558026862e-05,
+      "loss": 0.1897,
+      "step": 18500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.058752580902345e-05,
+      "loss": 0.189,
+      "step": 19000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.0076456037778278e-05,
+      "loss": 0.1878,
+      "step": 19500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.9566408406075595e-05,
+      "loss": 0.1891,
+      "step": 20000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.9055338634830425e-05,
+      "loss": 0.1881,
+      "step": 20500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.854426886358526e-05,
+      "loss": 0.1871,
+      "step": 21000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.803319909234009e-05,
+      "loss": 0.1871,
+      "step": 21500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.7522129321094918e-05,
+      "loss": 0.1863,
+      "step": 22000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.7011059549849748e-05,
+      "loss": 0.1853,
+      "step": 22500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.6499989778604578e-05,
+      "loss": 0.1867,
+      "step": 23000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.5988920007359408e-05,
+      "loss": 0.1847,
+      "step": 23500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.5478872375656725e-05,
+      "loss": 0.1839,
+      "step": 24000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.4967802604411554e-05,
+      "loss": 0.1825,
+      "step": 24500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.4456732833166384e-05,
+      "loss": 0.1849,
+      "step": 25000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.3945663061921214e-05,
+      "loss": 0.1848,
+      "step": 25500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.3435615430218534e-05,
+      "loss": 0.1829,
+      "step": 26000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.2924545658973364e-05,
+      "loss": 0.1817,
+      "step": 26500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.2413475887728194e-05,
+      "loss": 0.1829,
+      "step": 27000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.1902406116483024e-05,
+      "loss": 0.1826,
+      "step": 27500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.1391336345237854e-05,
+      "loss": 0.1808,
+      "step": 28000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.088026657399268e-05,
+      "loss": 0.1814,
+      "step": 28500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.0370218942290004e-05,
+      "loss": 0.1807,
+      "step": 29000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.9859149171044834e-05,
+      "loss": 0.181,
+      "step": 29500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.934807939979966e-05,
+      "loss": 0.179,
+      "step": 30000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.883803176809698e-05,
+      "loss": 0.1805,
+      "step": 30500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.832696199685181e-05,
+      "loss": 0.1813,
+      "step": 31000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.781589222560664e-05,
+      "loss": 0.1797,
+      "step": 31500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.7304822454361467e-05,
+      "loss": 0.1777,
+      "step": 32000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.67937526831163e-05,
+      "loss": 0.1798,
+      "step": 32500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.628268291187113e-05,
+      "loss": 0.1795,
+      "step": 33000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.577161314062596e-05,
+      "loss": 0.1778,
+      "step": 33500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.526054336938079e-05,
+      "loss": 0.1807,
+      "step": 34000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.4749473598135619e-05,
+      "loss": 0.1763,
+      "step": 34500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.4238403826890448e-05,
+      "loss": 0.1799,
+      "step": 35000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.3727334055645277e-05,
+      "loss": 0.1771,
+      "step": 35500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.3216264284400107e-05,
+      "loss": 0.1772,
+      "step": 36000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.2706216652697429e-05,
+      "loss": 0.1788,
+      "step": 36500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.2195146881452257e-05,
+      "loss": 0.177,
+      "step": 37000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.1684077110207085e-05,
+      "loss": 0.1769,
+      "step": 37500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.1173007338961917e-05,
+      "loss": 0.1753,
+      "step": 38000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.0661937567716745e-05,
+      "loss": 0.1749,
+      "step": 38500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.0152912075556555e-05,
+      "loss": 0.1752,
+      "step": 39000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.641842304311385e-06,
+      "loss": 0.1736,
+      "step": 39500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 9.130772533066215e-06,
+      "loss": 0.1741,
+      "step": 40000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 8.619702761821043e-06,
+      "loss": 0.1741,
+      "step": 40500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.109655130118364e-06,
+      "loss": 0.1739,
+      "step": 41000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.5985853588731936e-06,
+      "loss": 0.1742,
+      "step": 41500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 7.087515587628023e-06,
+      "loss": 0.1726,
+      "step": 42000
     }
   ],
-  "max_steps": 12316,
-  "num_train_epochs": 2,
-  "total_flos": 4101375688441856.0,
+  "max_steps": 48917,
+  "num_train_epochs": 1,
+  "total_flos": 1.4653685132951552e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a6042a8df01e4339fe6824eb7b75d8ce70b25363904b3f22bb80fd4e198d7c0
+oid sha256:7fcecdde9b65524acb717834600f04676101f075ba7466fa4550637dfe768e10
 size 3247