en_names_detection

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert/distilbert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: my_awesome_wnut_model_2
+  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_2
+
+This model is a fine-tuned version of [distilbert/distilbert-base-cased](https://huggingface.co/distilbert/distilbert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0982
+- Precision: 0.0
+- Recall: 0.0
+- F1: 0.0
+- Accuracy: 0.9814
+
+## 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 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: 13
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1  | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
+| No log        | 1.0   | 118  | 0.0915          | 0.0       | 0.0    | 0.0 | 0.9808   |
+| No log        | 2.0   | 236  | 0.0942          | 0.0       | 0.0    | 0.0 | 0.9812   |
+| No log        | 3.0   | 354  | 0.1112          | 0.0       | 0.0    | 0.0 | 0.9786   |
+| No log        | 4.0   | 472  | 0.0931          | 0.0       | 0.0    | 0.0 | 0.9806   |
+| 0.0017        | 5.0   | 590  | 0.1000          | 0.0       | 0.0    | 0.0 | 0.9810   |
+| 0.0017        | 6.0   | 708  | 0.0925          | 0.0       | 0.0    | 0.0 | 0.9810   |
+| 0.0017        | 7.0   | 826  | 0.0976          | 0.0       | 0.0    | 0.0 | 0.9815   |
+| 0.0017        | 8.0   | 944  | 0.0930          | 0.0       | 0.0    | 0.0 | 0.9815   |
+| 0.0012        | 9.0   | 1062 | 0.1012          | 0.0       | 0.0    | 0.0 | 0.9810   |
+| 0.0012        | 10.0  | 1180 | 0.0993          | 0.0       | 0.0    | 0.0 | 0.9814   |
+| 0.0012        | 11.0  | 1298 | 0.0995          | 0.0       | 0.0    | 0.0 | 0.9812   |
+| 0.0012        | 12.0  | 1416 | 0.0975          | 0.0       | 0.0    | 0.0 | 0.9814   |
+| 0.0006        | 13.0  | 1534 | 0.0982          | 0.0       | 0.0    | 0.0 | 0.9814   |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu121
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350cecaed4ff3661a66c7caf933fe0d4c4f1235c385a82916b0b1f538651c9fc
+size 260785212

runs/Jan13_18-39-45_ea43fe1769f5/events.out.tfevents.1736793586.ea43fe1769f5.594.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ed0a8c0faf2b40f5c7991be8539062fa05cce82cb13dea0cda28fb073fd34a8
+size 12261

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20dcc2f65496b08f5b2b98f5ced26f1b73433c59a49e66dc0e7af5cf5c3c4347
+size 5368