Training in progress epoch 0

README.md

@@ -1,38 +1,23 @@
 ---
 license: apache-2.0
 tags:
-- generated_from_trainer
-datasets:
-- glue
-metrics:
-- matthews_correlation
+- generated_from_keras_callback
 model-index:
-- name: distilbert-base-uncased-finetuned-cola
-  results:
-  - task:
-      name: Text Classification
-      type: text-classification
-    dataset:
-      name: glue
-      type: glue
-      config: cola
-      split: validation
-      args: cola
-    metrics:
-    - name: Matthews Correlation
-      type: matthews_correlation
-      value: 0.5468655257933821
+- name: CMacD12/distilbert-base-uncased-finetuned-cola
+  results: []
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
 
-# distilbert-base-uncased-finetuned-cola
+# CMacD12/distilbert-base-uncased-finetuned-cola
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8215
-- Matthews Correlation: 0.5469
+- Train Loss: 0.5145
+- Validation Loss: 0.4719
+- Train Matthews Correlation: 0.4496
+- Epoch: 0
 
 ## Model description
 
@@ -51,28 +36,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 5
+- optimizer: {'name': 'Adam', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1602, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- training_precision: float32
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
-|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5219        | 1.0   | 535  | 0.5513          | 0.3860               |
-| 0.3434        | 2.0   | 1070 | 0.4889          | 0.5060               |
-| 0.232         | 3.0   | 1605 | 0.5794          | 0.5309               |
-| 0.1692        | 4.0   | 2140 | 0.7830          | 0.5380               |
-| 0.1266        | 5.0   | 2675 | 0.8215          | 0.5469               |
+| Train Loss | Validation Loss | Train Matthews Correlation | Epoch |
+|:----------:|:---------------:|:--------------------------:|:-----:|
+| 0.5145     | 0.4719          | 0.4496                     | 0     |
 
 
 ### Framework versions
 
 - Transformers 4.29.2
-- Pytorch 2.0.1
+- TensorFlow 2.13.0-rc1
 - Datasets 2.12.0
 - Tokenizers 0.13.3

config.json

@@ -8,18 +8,24 @@
   "dim": 768,
   "dropout": 0.1,
   "hidden_dim": 3072,
+  "id2label": {
+    "0": "Invalid",
+    "1": "Valid"
+  },
   "initializer_range": 0.02,
+  "label2id": {
+    "Invalid": 0,
+    "Valid": 1
+  },
   "max_position_embeddings": 512,
   "model_type": "distilbert",
   "n_heads": 12,
   "n_layers": 6,
   "pad_token_id": 0,
-  "problem_type": "single_label_classification",
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "torch_dtype": "float32",
   "transformers_version": "4.29.2",
   "vocab_size": 30522
 }

logs/train/events.out.tfevents.1687472656.Coles-MBP.ad.stfx.ca.18611.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e3dd9677ee5f873b1343dadc25efcc35ae450ef274b4668d5c4bb6ce26e3dd
+size 1559149

logs/validation/events.out.tfevents.1687472819.Coles-MBP.ad.stfx.ca.18611.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3887924ea8e485e724367ab4a1ca20767dd2b54ee92e9d88361bee8baedac57b
+size 232

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ba08dadfec1ed9e0a26db297cbfeded383311eda31cec85da9208a719a29e06
+size 267951808

tokenizer.json

@@ -1,12 +1,14 @@
 {
   "version": "1.0",
-  "truncation": {
+  "truncation": null,
+  "padding": {
+    "strategy": "BatchLongest",
     "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
   },
-  "padding": null,
   "added_tokens": [
     {
       "id": 0,