Training in progress epoch 0

README.md

@@ -1,5 +1,4 @@
 ---
-license: apache-2.0
 tags:
 - generated_from_keras_callback
 model-index:
@@ -12,11 +11,13 @@ probably proofread and complete it, then remove this comment. -->
 
 # AHarbury/debiasNLPFinal
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [d4data/bias-detection-model](https://huggingface.co/d4data/bias-detection-model) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.6933
-- Validation Loss: 0.6933
-- Epoch: 1
+- Train Loss: 0.6113
+- Train Accuracy: 0.6458
+- Validation Loss: 0.5694
+- Validation Accuracy: 0.6902
+- Epoch: 0
 
 ## Model description
 
@@ -35,15 +36,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 0.001, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 40350, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
-| Train Loss | Validation Loss | Epoch |
-|:----------:|:---------------:|:-----:|
-| 0.6947     | 0.6934          | 0     |
-| 0.6933     | 0.6933          | 1     |
+| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
+|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
+| 0.6113     | 0.6458         | 0.5694          | 0.6902              | 0     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "d4data/bias-detection-model",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -8,7 +8,15 @@
   "dim": 768,
   "dropout": 0.1,
   "hidden_dim": 3072,
+  "id2label": {
+    "0": "Non-biased",
+    "1": "Biased"
+  },
   "initializer_range": 0.02,
+  "label2id": {
+    "Biased": 1,
+    "Non-biased": 0
+  },
   "max_position_embeddings": 512,
   "model_type": "distilbert",
   "n_heads": 12,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71070f4d778482370f73a8679baca8367203b2a0e5e257480fc30b3e327c6a1c
-size 267951808
+oid sha256:663ec27dedafbe23d7885a6c50ee7fd2871212ffd48cf55953fee455baad7842
+size 267955144

tokenizer.json

@@ -7,9 +7,7 @@
     "stride": 0
   },
   "padding": {
-    "strategy": {
-      "Fixed": 128
-    },
+    "strategy": "BatchLongest",
     "direction": "Right",
     "pad_to_multiple_of": null,
     "pad_id": 0,

tokenizer_config.json

@@ -1,9 +1,11 @@
 {
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,