Training in progress epoch 0

README.md

@@ -0,0 +1,53 @@
+---
+tags:
+- generated_from_keras_callback
+model-index:
+- name: negfir/distilbert-base-uncased-finetuned-cola
+  results: []
+---
+
+<!-- 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. -->
+
+# negfir/distilbert-base-uncased-finetuned-cola
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.6171
+- Validation Loss: 0.6188
+- Train Matthews Correlation: 0.0
+- Epoch: 0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2670, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Train Matthews Correlation | Epoch |
+|:----------:|:---------------:|:--------------------------:|:-----:|
+| 0.6171     | 0.6188          | 0.0                        | 0     |
+
+
+### Framework versions
+
+- Transformers 4.17.0
+- TensorFlow 2.8.0
+- Datasets 2.0.0
+- Tokenizers 0.11.6

config.json

@@ -1,25 +1,23 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
   "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 4,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
   "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",
+  "position_embedding_type": "absolute",
   "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 30522
 }

logs/train/events.out.tfevents.1648059800.8e925dbfab71.74.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b42815c3740efe96338afcc16135a550b4c93a991c15d90553503dd4a0825194
+size 559364

logs/validation/events.out.tfevents.1648059822.8e925dbfab71.74.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c514c43b2278ee6c911643186a8fa2323ad009c2159a69047eb0143489fa72
+size 194

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5127be69ac8f86587182289194fba26127fd013ac916eeed8ac2a8b5ffd6e29c
+size 17612160