Model save

README.md

@@ -0,0 +1,70 @@
+---
+base_model: SI2M-Lab/DarijaBERT
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: darija_test5
+  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_test5
+
+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: 1.1195
+- Accuracy: 0.8508
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0554        | 1.0   | 214  | 1.1195          | 0.8508   |
+| 0.5871        | 2.0   | 428  | 0.6734          | 0.6131   |
+| 0.7418        | 3.0   | 642  | 0.7144          | 0.6131   |
+| 0.7406        | 4.0   | 856  | 0.7020          | 0.6131   |
+| 0.6984        | 5.0   | 1070 | 0.6787          | 0.6131   |
+| 0.7168        | 6.0   | 1284 | 0.6678          | 0.6131   |
+| 0.6719        | 7.0   | 1498 | 0.6676          | 0.6131   |
+| 0.72          | 8.0   | 1712 | 0.6701          | 0.6131   |
+| 0.5586        | 9.0   | 1926 | 0.6686          | 0.6131   |
+| 0.7321        | 10.0  | 2140 | 0.6693          | 0.6131   |
+
+
+### 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 sha256:4ee030f977a9651a93b1d4a7870ae73ee7d99cff73f9ab2d9c8b584d501fe898
+size 589955072

runs/Aug29_13-39-29_0b1055bdc6cf/events.out.tfevents.1724938774.0b1055bdc6cf.735.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05dfbfbadca60758f810890bb9aea4ab006f2012d61319b656b8f31a89384d78
+size 100165

runs/Aug29_13-39-29_0b1055bdc6cf/events.out.tfevents.1724939550.0b1055bdc6cf.735.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c74cf5f36524f4ba0a0a950388d70f514a443050e3f7e1810f21563717ac7e
+size 411

runs/Aug29_14-20-30_0b1055bdc6cf/events.out.tfevents.1724941236.0b1055bdc6cf.735.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c40cc01212198136db4f2d9b3ee3e84512521f13246f98c73af39549311b6432
+size 53800

runs/Aug29_14-20-30_0b1055bdc6cf/events.out.tfevents.1724941629.0b1055bdc6cf.735.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7bfeb01b4f1f3cbc29c13f57aa570c0a5a1c4c6a28236f20f0847e3c708138
+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 sha256:466690ee87f00ee16f190f67de21fe29f6355b753591bef4e785a45432c5349e
+size 5112