Model save

README.md

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [aubmindlab/bert-large-arabertv2](https://huggingface.co/aubmindlab/bert-large-arabertv2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6083
-- Macro F1: 0.6233
-- Accuracy: 0.7756
+- Loss: 0.5849
+- Macro F1: 0.6310
+- Accuracy: 0.7822
 
 ## Model description
 
@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
 - learning_rate: 2e-05
 - train_batch_size: 16
 - eval_batch_size: 128
-- seed: 25
+- seed: 42
 - gradient_accumulation_steps: 2
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -51,8 +51,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
-| No log        | 1.0   | 491  | 0.6442          | 0.5825   | 0.7603   |
-| 0.8094        | 2.0   | 982  | 0.6083          | 0.6233   | 0.7756   |
+| No log        | 1.0   | 497  | 0.6328          | 0.5838   | 0.7719   |
+| 0.7505        | 2.0   | 994  | 0.5849          | 0.6310   | 0.7822   |
 
 
 ### Framework versions

config.json

@@ -9,18 +9,18 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 1024,
   "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3"
+    "0": "Positive",
+    "1": "Negative",
+    "2": "Neutral",
+    "3": "Mixed"
   },
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2,
-    "LABEL_3": 3
+    "Mixed": 3,
+    "Negative": 1,
+    "Neutral": 2,
+    "Positive": 0
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,