Training in progress, epoch 1

README.md

@@ -0,0 +1,76 @@
+---
+library_name: transformers
+base_model: UBC-NLP/MARBERT
+tags:
+- generated_from_trainer
+model-index:
+- name: offres_classification_UBC-NLP_MARBERT_promo_classification_new_train_data_v1
+  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. -->
+
+# offres_classification_UBC-NLP_MARBERT_promo_classification_new_train_data_v1
+
+This model is a fine-tuned version of [UBC-NLP/MARBERT](https://huggingface.co/UBC-NLP/MARBERT) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0640
+
+## 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: 2e-06
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 211  | 1.4751          |
+| No log        | 2.0   | 422  | 0.8215          |
+| 1.4542        | 3.0   | 633  | 0.4444          |
+| 1.4542        | 4.0   | 844  | 0.2632          |
+| 0.4504        | 5.0   | 1055 | 0.1727          |
+| 0.4504        | 6.0   | 1266 | 0.1351          |
+| 0.4504        | 7.0   | 1477 | 0.0994          |
+| 0.1381        | 8.0   | 1688 | 0.0911          |
+| 0.1381        | 9.0   | 1899 | 0.0767          |
+| 0.0581        | 10.0  | 2110 | 0.0790          |
+| 0.0581        | 11.0  | 2321 | 0.0726          |
+| 0.0383        | 12.0  | 2532 | 0.0691          |
+| 0.0383        | 13.0  | 2743 | 0.0654          |
+| 0.0383        | 14.0  | 2954 | 0.0669          |
+| 0.0262        | 15.0  | 3165 | 0.0643          |
+| 0.0262        | 16.0  | 3376 | 0.0653          |
+| 0.0231        | 17.0  | 3587 | 0.0669          |
+| 0.0231        | 18.0  | 3798 | 0.0647          |
+| 0.0177        | 19.0  | 4009 | 0.0636          |
+| 0.0177        | 20.0  | 4220 | 0.0640          |
+
+
+### Framework versions
+
+- Transformers 4.50.3
+- Pytorch 2.6.0+cu124
+- Datasets 2.21.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "*1",
+    "1": "*2",
+    "2": "*3",
+    "3": "*4",
+    "4": "*5",
+    "5": "*6",
+    "6": "*8",
+    "7": "Recharge normale",
+    "8": "autre"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "*1": 0,
+    "*2": 1,
+    "*3": 2,
+    "*4": 3,
+    "*5": 4,
+    "*6": 5,
+    "*8": 6,
+    "Recharge normale": 7,
+    "autre": 8
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 64000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c7366274b50abbe7043063ab6d8b5272b2907c667b01fbfe4e9673099c6ff0
+size 540824604

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 +1,87 @@
+{
+  "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
+    },
+    "5": {
+      "content": "[رابط]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "6": {
+      "content": "[بريد]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "7": {
+      "content": "[مستخدم]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": [
+    "[بريد]",
+    "[مستخدم]",
+    "[رابط]"
+  ],
+  "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:f84254d7c145bf2ad1507d777d6c37472bdb500e38e1e7f0a53a902711fc0545
+size 5432