Model save

README.md

@@ -0,0 +1,70 @@
+---
+base_model: SI2M-Lab/DarijaBERT
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: darija_test4
+  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_test4
+
+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: 0.2337
+- Accuracy: 0.9402
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.691         | 1.0   | 209  | 0.6551          | 0.6388   |
+| 0.48          | 2.0   | 418  | 0.5391          | 0.8086   |
+| 0.7983        | 3.0   | 627  | 0.6059          | 0.7105   |
+| 0.7509        | 4.0   | 836  | 0.5645          | 0.7201   |
+| 0.6031        | 5.0   | 1045 | 0.5616          | 0.7249   |
+| 0.4155        | 6.0   | 1254 | 0.5425          | 0.8062   |
+| 0.5307        | 7.0   | 1463 | 0.5160          | 0.7943   |
+| 0.4064        | 8.0   | 1672 | 0.4301          | 0.8469   |
+| 0.3983        | 9.0   | 1881 | 0.3789          | 0.8971   |
+| 0.4016        | 10.0  | 2090 | 0.2337          | 0.9402   |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- 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:a995be96ce9f3c99a6d06ba5d005e45667122ed811a2185057600f111bf9b338
+size 589955072

runs/Aug29_13-28-50_0b1055bdc6cf/events.out.tfevents.1724938139.0b1055bdc6cf.735.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ed3039dd45eb83e4bd7a8e9aca5018a2dc2eb1d0b6b583c8dc1d8508f644b84
+size 52745

runs/Aug29_13-28-50_0b1055bdc6cf/events.out.tfevents.1724938519.0b1055bdc6cf.735.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ff7fe17cbb9a921df92b9996265102bf0d3c53cfa26f6f06427f3f36b9145d
+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:fd9b471186e31452080d85043025a5b4a887c2612f2452545dead5d8b703dcac
+size 5112