End of training

README.md

@@ -0,0 +1,73 @@
+---
+base_model: aubmindlab/bert-base-arabertv02-twitter
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: Improved-Arabert-twitter-sentiment-No-dropout-Twitter
+  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. -->
+
+# Improved-Arabert-twitter-sentiment-No-dropout-Twitter
+
+This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02-twitter](https://huggingface.co/aubmindlab/bert-base-arabertv02-twitter) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6342
+- Accuracy: 0.89
+
+## 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:
+- learning_rate: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.5264        | 0.55  | 50   | 0.5252          | 0.71     |
+| 0.3041        | 1.1   | 100  | 0.4085          | 0.81     |
+| 0.2205        | 1.65  | 150  | 0.3303          | 0.88     |
+| 0.1476        | 2.2   | 200  | 0.3890          | 0.87     |
+| 0.1219        | 2.75  | 250  | 0.3775          | 0.87     |
+| 0.0972        | 3.3   | 300  | 0.3930          | 0.88     |
+| 0.0917        | 3.85  | 350  | 0.4728          | 0.86     |
+| 0.0596        | 4.4   | 400  | 0.4406          | 0.89     |
+| 0.0556        | 4.95  | 450  | 0.4949          | 0.89     |
+| 0.0375        | 5.49  | 500  | 0.4935          | 0.9      |
+| 0.0269        | 6.04  | 550  | 0.5977          | 0.88     |
+| 0.0235        | 6.59  | 600  | 0.5543          | 0.89     |
+| 0.0191        | 7.14  | 650  | 0.5941          | 0.88     |
+| 0.0109        | 7.69  | 700  | 0.6562          | 0.89     |
+| 0.0198        | 8.24  | 750  | 0.6342          | 0.89     |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.7
+- Tokenizers 0.14.1

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "aubmindlab/bert-base-arabertv02-twitter",
   "architectures": [
-    "BertForMaskedLM"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
@@ -9,16 +9,8 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
-  "id2label": {
-    "0": "Negative",
-    "1": "Positive"
-  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "label2id": {
-    "Negative": 0,
-    "Positive": 1
-  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
@@ -26,6 +18,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.34.1",
   "type_vocab_size": 2,