french_names_detector

README.md

@@ -0,0 +1,76 @@
+---
+library_name: transformers
+license: mit
+base_model: camembert-base
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: my_awesome_wnut_model
+  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. -->
+
+# my_awesome_wnut_model
+
+This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0033
+- Precision: 0.0
+- Recall: 0.0
+- F1: 0.0
+- Accuracy: 0.9990
+
+## 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-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1  | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:---:|:--------:|
+| 0.0136        | 1.0   | 1559  | 0.0085          | 0.0       | 0.0    | 0.0 | 0.9983   |
+| 0.0087        | 2.0   | 3118  | 0.0056          | 0.0       | 0.0    | 0.0 | 0.9986   |
+| 0.0061        | 3.0   | 4677  | 0.0046          | 0.0       | 0.0    | 0.0 | 0.9987   |
+| 0.0061        | 4.0   | 6236  | 0.0040          | 0.0       | 0.0    | 0.0 | 0.9988   |
+| 0.005         | 5.0   | 7795  | 0.0038          | 0.0       | 0.0    | 0.0 | 0.9988   |
+| 0.0049        | 6.0   | 9354  | 0.0035          | 0.0       | 0.0    | 0.0 | 0.9989   |
+| 0.0044        | 7.0   | 10913 | 0.0034          | 0.0       | 0.0    | 0.0 | 0.9989   |
+| 0.004         | 8.0   | 12472 | 0.0036          | 0.0       | 0.0    | 0.0 | 0.9988   |
+| 0.004         | 9.0   | 14031 | 0.0034          | 0.0       | 0.0    | 0.0 | 0.9990   |
+| 0.0044        | 10.0  | 15590 | 0.0033          | 0.0       | 0.0    | 0.0 | 0.9990   |
+
+
+### Framework versions
+
+- Transformers 4.46.2
+- Pytorch 2.5.1
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "camembert-base",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bec9a9d5a6c8205f96eb8fbdc58958cf267523e17c2dc6b383919549f17236da
+size 440155504

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<unk>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<unk>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<unk>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28226c1b70e899c61ac969dfed2363de9a7e92518ee348172294ed0b822cbccc
+size 5304