Model save

README.md

@@ -0,0 +1,70 @@
+---
+base_model: SI2M-Lab/DarijaBERT
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: darija_test
+  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. -->
+
+# darija_test
+
+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: 0.6520
+- Accuracy: 0.7041
+
+## 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: 0.0003
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.813         | 1.0   | 169  | 0.7390          | 0.2959   |
+| 0.9437        | 2.0   | 338  | 0.6520          | 0.7041   |
+| 0.759         | 3.0   | 507  | 0.6080          | 0.7041   |
+| 0.7936        | 4.0   | 676  | 0.6582          | 0.7041   |
+| 0.8051        | 5.0   | 845  | 0.6452          | 0.7041   |
+| 0.7397        | 6.0   | 1014 | 0.6422          | 0.7041   |
+| 0.5792        | 7.0   | 1183 | 0.6132          | 0.7041   |
+| 0.5339        | 8.0   | 1352 | 0.6095          | 0.7041   |
+| 0.5152        | 9.0   | 1521 | 0.6136          | 0.7041   |
+| 0.4909        | 10.0  | 1690 | 0.6181          | 0.7041   |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,43 @@
+{
+  "_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": 768,
+  "id2label": {
+    "0": "*6",
+    "1": "autre"
+  },
+  "initializer_range": 0.02,
+  "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": 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": "4.42.4",
+  "type_vocab_size": 2,
+  "unk_token": "[UNK]",
+  "use_cache": true,
+  "vocab_size": 80000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5de96ac812ad89bba0cf44537b9d7aed18ec619d2dcdb045ae60fdca01eb1d1
+size 589955072

runs/Jul25_10-44-26_a92422d17f17/events.out.tfevents.1721904271.a92422d17f17.1439.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed8eef827376cd4df139649da3206e8aeea3c3b3c92b08087a4c2b8e553a9932
+size 32428

runs/Jul25_10-49-33_a92422d17f17/events.out.tfevents.1721904582.a92422d17f17.1439.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:603de25afa762e50c3a9bf652d7b7ede2c39548a6bf786152571d005eab3a8a2
+size 44392

runs/Jul25_10-49-33_a92422d17f17/events.out.tfevents.1721905237.a92422d17f17.1439.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5a1cd7171a7f91de57f3706b09e72f422e76b416180d75d6c4f75c570523288
+size 411

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "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

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da60082f53a1dde82f615b7bad02bceaff71098f5ba477a1f20c81d0da2ad06
+size 5112