new update

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,22 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="Eslint" enabled="true" level="WARNING" enabled_by_default="true" />
+    <inspection_tool class="HtmlUnknownTag" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="myValues">
+        <value>
+          <list size="7">
+            <item index="0" class="java.lang.String" itemvalue="nobr" />
+            <item index="1" class="java.lang.String" itemvalue="noembed" />
+            <item index="2" class="java.lang.String" itemvalue="comment" />
+            <item index="3" class="java.lang.String" itemvalue="noscript" />
+            <item index="4" class="java.lang.String" itemvalue="embed" />
+            <item index="5" class="java.lang.String" itemvalue="script" />
+            <item index="6" class="java.lang.String" itemvalue="style" />
+          </list>
+        </value>
+      </option>
+      <option name="myCustomValuesEnabled" value="true" />
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9 (venv) (14)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/token-level-bias-detector.iml" filepath="$PROJECT_DIR$/.idea/token-level-bias-detector.iml" />
+    </modules>
+  </component>
+</project>

.idea/token-level-bias-detector.iml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

README.md

@@ -1,3 +0,0 @@
----
-license: mit
----

config.json

@@ -41,6 +41,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.30.2",
+  "transformers_version": "4.16.2",
   "vocab_size": 30522
 }

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f3a2ede176455f03fbb391b979ffdae699ee0b6a651038e4d30e81caf24615b
-size 175105008
+oid sha256:4fc301f3565f1f66dcc2f181d9282ed55ed442c52baa544c2581bdc8a61f2953
+size 531014313

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3f43365dd427813db2965cc9f4572fac706b40840d2b76126d8bea971329c1
-size 176815110
+oid sha256:244b8ae0a16e42ca098bf10fcbd969892e6cbcf3e0a7f05a4ec52fb752db3ea1
+size 265517173

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d96600483ff85427d732ec69c81a43227d9090e71ba01297a2070e3b1e7a2276
-size 14575
+oid sha256:c80dcae06b0c0549c4ad1ac0024ccb896e9245726737652c176de5d386a600c8
+size 13547

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3da5120f044f3bc98c066d6f08325e23bfcbf5fa4b3a593c660f74ac4cba240a
-size 627
+oid sha256:4a7307711a3ffe0a038b57c3070c813da888b248e0bbf62ba06ac99ee91aa9d6
+size 623

special_tokens_map.json

@@ -1,7 +1 @@
-{
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
-}
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -1,13 +1 @@
-{
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
-}
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}

trainer_state.json

@@ -1,76 +1,202 @@
 {
-  "best_metric": 0.06264707446098328,
-  "best_model_checkpoint": "token_level_model/best_model/checkpoint-1264",
-  "epoch": 4.0,
-  "global_step": 1264,
+  "best_metric": 0.07052170485258102,
+  "best_model_checkpoint": "token_level_model/best_model/checkpoint-948",
+  "epoch": 12.0,
+  "global_step": 3792,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_balanced accuracy": 0.6290652713011048,
-      "eval_f1": 0.5903625610241477,
-      "eval_loss": 0.08535531163215637,
-      "eval_precision": 0.6673952462175068,
-      "eval_recall": 0.6290652713011048,
-      "eval_runtime": 1.1616,
-      "eval_samples_per_second": 1088.145,
-      "eval_steps_per_second": 68.009,
+      "eval_balanced accuracy": 0.5633085631676005,
+      "eval_f1": 0.5303163390780957,
+      "eval_loss": 0.09163307398557663,
+      "eval_precision": 0.6548165588282941,
+      "eval_recall": 0.5633085631676005,
+      "eval_runtime": 5.3367,
+      "eval_samples_per_second": 236.852,
+      "eval_steps_per_second": 14.803,
       "step": 316
     },
     {
       "epoch": 1.58,
       "learning_rate": 1.7362869198312237e-05,
-      "loss": 0.1826,
+      "loss": 0.1839,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_balanced accuracy": 0.7368620541402373,
-      "eval_f1": 0.7319179038298047,
-      "eval_loss": 0.0663721114397049,
-      "eval_precision": 0.7513664045814622,
-      "eval_recall": 0.7368620541402373,
-      "eval_runtime": 1.1399,
-      "eval_samples_per_second": 1108.902,
-      "eval_steps_per_second": 69.306,
+      "eval_balanced accuracy": 0.7195902052549533,
+      "eval_f1": 0.7255288809894066,
+      "eval_loss": 0.0722324550151825,
+      "eval_precision": 0.7454575741625619,
+      "eval_recall": 0.7195902052549533,
+      "eval_runtime": 5.3534,
+      "eval_samples_per_second": 236.111,
+      "eval_steps_per_second": 14.757,
       "step": 632
     },
     {
       "epoch": 3.0,
-      "eval_balanced accuracy": 0.7154153135735104,
-      "eval_f1": 0.7058619488659976,
-      "eval_loss": 0.0662752017378807,
-      "eval_precision": 0.7270224611135597,
-      "eval_recall": 0.7154153135735104,
-      "eval_runtime": 1.1286,
-      "eval_samples_per_second": 1119.927,
-      "eval_steps_per_second": 69.995,
+      "eval_balanced accuracy": 0.7147400555506803,
+      "eval_f1": 0.7192305114894215,
+      "eval_loss": 0.07052170485258102,
+      "eval_precision": 0.7756273409712318,
+      "eval_recall": 0.7147400555506803,
+      "eval_runtime": 5.4755,
+      "eval_samples_per_second": 230.847,
+      "eval_steps_per_second": 14.428,
       "step": 948
     },
     {
       "epoch": 3.16,
       "learning_rate": 1.4725738396624474e-05,
-      "loss": 0.0568,
+      "loss": 0.0587,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_balanced accuracy": 0.73742506900579,
-      "eval_f1": 0.7367887044772851,
-      "eval_loss": 0.06264707446098328,
-      "eval_precision": 0.7489761641718176,
-      "eval_recall": 0.73742506900579,
-      "eval_runtime": 1.1361,
-      "eval_samples_per_second": 1112.55,
-      "eval_steps_per_second": 69.534,
+      "eval_balanced accuracy": 0.7295185936273012,
+      "eval_f1": 0.7296703416168215,
+      "eval_loss": 0.07182055711746216,
+      "eval_precision": 0.7401045017667032,
+      "eval_recall": 0.7295185936273012,
+      "eval_runtime": 5.3937,
+      "eval_samples_per_second": 234.345,
+      "eval_steps_per_second": 14.647,
       "step": 1264
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 1.208860759493671e-05,
+      "loss": 0.0376,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_balanced accuracy": 0.735330002568732,
+      "eval_f1": 0.743746101471838,
+      "eval_loss": 0.07561135292053223,
+      "eval_precision": 0.758929084908083,
+      "eval_recall": 0.735330002568732,
+      "eval_runtime": 5.5304,
+      "eval_samples_per_second": 228.555,
+      "eval_steps_per_second": 14.285,
+      "step": 1580
+    },
+    {
+      "epoch": 6.0,
+      "eval_balanced accuracy": 0.7487913019838482,
+      "eval_f1": 0.7539294881409199,
+      "eval_loss": 0.08333344757556915,
+      "eval_precision": 0.7640729935139194,
+      "eval_recall": 0.7487913019838482,
+      "eval_runtime": 5.304,
+      "eval_samples_per_second": 238.312,
+      "eval_steps_per_second": 14.894,
+      "step": 1896
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 9.451476793248946e-06,
+      "loss": 0.0239,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_balanced accuracy": 0.7495077050154062,
+      "eval_f1": 0.7547220689413356,
+      "eval_loss": 0.09176070988178253,
+      "eval_precision": 0.7680132999431392,
+      "eval_recall": 0.7495077050154062,
+      "eval_runtime": 5.4894,
+      "eval_samples_per_second": 230.262,
+      "eval_steps_per_second": 14.391,
+      "step": 2212
+    },
+    {
+      "epoch": 7.91,
+      "learning_rate": 6.814345991561182e-06,
+      "loss": 0.0161,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_balanced accuracy": 0.7519480763726148,
+      "eval_f1": 0.7441340002103095,
+      "eval_loss": 0.10090441256761551,
+      "eval_precision": 0.7421918161304624,
+      "eval_recall": 0.7519480763726148,
+      "eval_runtime": 5.4772,
+      "eval_samples_per_second": 230.774,
+      "eval_steps_per_second": 14.423,
+      "step": 2528
+    },
+    {
+      "epoch": 9.0,
+      "eval_balanced accuracy": 0.7372305744818235,
+      "eval_f1": 0.7418663358868686,
+      "eval_loss": 0.10627683997154236,
+      "eval_precision": 0.747694948865169,
+      "eval_recall": 0.7372305744818235,
+      "eval_runtime": 5.673,
+      "eval_samples_per_second": 222.809,
+      "eval_steps_per_second": 13.926,
+      "step": 2844
+    },
+    {
+      "epoch": 9.49,
+      "learning_rate": 4.177215189873418e-06,
+      "loss": 0.0107,
+      "step": 3000
+    },
+    {
+      "epoch": 10.0,
+      "eval_balanced accuracy": 0.7454153105654866,
+      "eval_f1": 0.7532278014935634,
+      "eval_loss": 0.11291743814945221,
+      "eval_precision": 0.7635910633921945,
+      "eval_recall": 0.7454153105654866,
+      "eval_runtime": 5.7497,
+      "eval_samples_per_second": 219.839,
+      "eval_steps_per_second": 13.74,
+      "step": 3160
+    },
+    {
+      "epoch": 11.0,
+      "eval_balanced accuracy": 0.7422514651185799,
+      "eval_f1": 0.7462413455365297,
+      "eval_loss": 0.11802595853805542,
+      "eval_precision": 0.7518280300030182,
+      "eval_recall": 0.7422514651185799,
+      "eval_runtime": 5.6277,
+      "eval_samples_per_second": 224.602,
+      "eval_steps_per_second": 14.038,
+      "step": 3476
+    },
+    {
+      "epoch": 11.08,
+      "learning_rate": 1.5400843881856542e-06,
+      "loss": 0.007,
+      "step": 3500
+    },
+    {
+      "epoch": 12.0,
+      "eval_balanced accuracy": 0.7397630177088332,
+      "eval_f1": 0.7454360643197575,
+      "eval_loss": 0.11985792219638824,
+      "eval_precision": 0.7526407260582226,
+      "eval_recall": 0.7397630177088332,
+      "eval_runtime": 5.7001,
+      "eval_samples_per_second": 221.752,
+      "eval_steps_per_second": 13.859,
+      "step": 3792
     }
   ],
   "max_steps": 3792,
   "num_train_epochs": 12,
-  "total_flos": 100660027447476.0,
+  "total_flos": 302819736843288.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76b8d0f901caec1b204fedf3a32dcc6d45c2a6f05439608359b93e904dccc26c
-size 3963
+oid sha256:da42e7baa76de3c12fa9e7243405605b228d1c4584da43c52ec2fc2947df75f5
+size 3055