Upload TFDistilBertForSequenceClassification

README.md

@@ -14,7 +14,13 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [giogenna16/pretrained-distilbert-tim-alarms-clusters-ord](https://huggingface.co/giogenna16/pretrained-distilbert-tim-alarms-clusters-ord) on an unknown dataset.
 It achieves the following results on the evaluation set:
-
+- Train Loss: 0.1970
+- Train Categorical Accuracy: 0.9058
+- Train Categorical True Positives: 6890.0
+- Train Categorical False Negatives: 588.0
+- Train Categorical False Positives: 573.0
+- Train Categorical True Negatives: 4269.0
+- Epoch: 2
 
 ## Model description
 
@@ -33,15 +39,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamW', 'weight_decay': 0.05, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PiecewiseConstantDecay', 'config': {'boundaries': [45, 90, 135, 180, 225, 270, 315, 360, 405, 450, 495, 540, 585, 630, 675, 720, 765, 810, 855], 'values': [3e-05, 2.8499999999999998e-05, 2.7075e-05, 2.5721249999999997e-05, 2.44351875e-05, 2.3213428124999993e-05, 2.2052756718749993e-05, 2.0950118882812494e-05, 1.9902612938671867e-05, 1.890748229173827e-05, 1.796210817715136e-05, 1.706400276829379e-05, 1.62108026298791e-05, 1.5400262498385145e-05, 1.4630249373465886e-05, 1.3898736904792591e-05, 1.3203800059552961e-05, 1.2543610056575313e-05, 1.1916429553746547e-05, 1.1320608076059218e-05], 'name': None}, 'registered_name': None}, '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': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
+| Train Loss | Train Categorical Accuracy | Train Categorical True Positives | Train Categorical False Negatives | Train Categorical False Positives | Train Categorical True Negatives | Epoch |
+|:----------:|:--------------------------:|:--------------------------------:|:---------------------------------:|:---------------------------------:|:--------------------------------:|:-----:|
+| 0.5356     | 0.7289                     | 6327.0                           | 1151.0                            | 2189.0                            | 2653.0                           | 0     |
+| 0.2885     | 0.8661                     | 6664.0                           | 814.0                             | 836.0                             | 4006.0                           | 1     |
+| 0.1970     | 0.9058                     | 6890.0                           | 588.0                             | 573.0                             | 4269.0                           | 2     |
 
 
 ### Framework versions
 
-- Transformers 4.37.2
+- Transformers 4.38.2
 - TensorFlow 2.15.0
 - Tokenizers 0.15.2

config.json

@@ -18,6 +18,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.38.2",
   "vocab_size": 30522
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2bb1af5ce573fec974bd86e58df64913c474a898b3575db64bc3997a19a0907
+oid sha256:d4fb26ce57da7c568924a38fd1fd1a28453acf8b79993ee83ae4a554bcd81e36
 size 267951808