Model save

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: transformers
-base_model: asafaya/bert-large-arabic
+base_model: SI2M-Lab/DarijaBERT
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # darija_test8
 
-This model is a fine-tuned version of [asafaya/bert-large-arabic](https://huggingface.co/asafaya/bert-large-arabic) on the None dataset.
+This model is a fine-tuned version of [SI2M-Lab/DarijaBERT](https://huggingface.co/SI2M-Lab/DarijaBERT) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0000
-- Accuracy: 1.0
+- Loss: 0.0106
+- Accuracy: 0.9982
 
 ## Model description
 
@@ -49,12 +49,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 281  | 0.0390          | 0.9929   |
-| 0.0967        | 2.0   | 562  | 0.0139          | 0.9982   |
-| 0.0967        | 3.0   | 843  | 0.0008          | 1.0      |
-| 0.0216        | 4.0   | 1124 | 0.0000          | 1.0      |
-| 0.0216        | 5.0   | 1405 | 0.0000          | 1.0      |
-| 0.0032        | 6.0   | 1686 | 0.0000          | 1.0      |
+| No log        | 1.0   | 281  | 0.0242          | 0.9947   |
+| 0.0937        | 2.0   | 562  | 0.0167          | 0.9982   |
+| 0.0937        | 3.0   | 843  | 0.0245          | 0.9947   |
+| 0.0022        | 4.0   | 1124 | 0.0239          | 0.9964   |
+| 0.0022        | 5.0   | 1405 | 0.0181          | 0.9982   |
+| 0.0003        | 6.0   | 1686 | 0.0106          | 0.9982   |
 
 
 ### Framework versions

config.json

@@ -1,37 +1,43 @@
 {
-  "_name_or_path": "asafaya/bert-large-arabic",
-  "_num_labels": 2,
+  "_name_or_path": "SI2M-Lab/DarijaBERT",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "*6",
     "1": "autre"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "*6": 0,
     "autre": 1
   },
   "layer_norm_eps": 1e-12,
+  "mask_token": "[MASK]",
+  "max_len": 128,
   "max_position_embeddings": 512,
+  "model_max_length": 128,
   "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "output_past": true,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token": "[PAD]",
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "sep_token": "[SEP]",
   "torch_dtype": "float32",
   "transformers_version": "4.44.2",
   "type_vocab_size": 2,
+  "unk_token": "[UNK]",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 80000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc44c255d329cb60a88bd40957805804d721d611e29d8f973dba65a7d146822c
-size 1346676656
+oid sha256:8cedc757f7ee16bc187a86d3d8a932c04a1aa572a1da43d5aa5fbc9a1e20e3e5
+size 589955072

runs/Sep12_10-44-45_16cf65176a0f/events.out.tfevents.1726137886.16cf65176a0f.2037.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83e13182b241e5eaf7388a3e2ec307d83fab7305ad3595b9a08aced807a83b2c
+size 8109

runs/Sep12_10-44-45_16cf65176a0f/events.out.tfevents.1726138277.16cf65176a0f.2037.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daea50217d727c5c5ec1df68a8750d8cafdbc64bd4bdd54927a15e4dac750b98
+size 411

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -45,7 +45,6 @@
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
-  "full_tokenizer_file": null,
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "never_split": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:848e1b0697766f97ae43902e8bd1b7663261e83fc17fa9c6dced7665058abc08
+oid sha256:6df38197662ca5ddd415754ac8ebc6a93e899e6465f25524d1298ff0a04dd1f6
 size 5176