End of training

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert-base-cased
+tags:
+- generated_from_trainer
+model-index:
+- name: distilbert-base-cased-finetuned-ner-eng
+  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. -->
+
+# distilbert-base-cased-finetuned-ner-eng
+
+This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2012
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 84   | 0.2498          |
+| No log        | 2.0   | 168  | 0.2110          |
+| No log        | 3.0   | 252  | 0.2012          |
+
+
+### Framework versions
+
+- Transformers 4.45.1
+- Pytorch 2.4.0
+- Datasets 3.0.1
+- Tokenizers 0.20.0

config.json

@@ -0,0 +1,85 @@
+{
+  "_name_or_path": "distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O\"",
+    "1": "B-MED\"",
+    "2": "C-B-VIP",
+    "3": "B-MTG",
+    "4": "I-LEG",
+    "5": "B-EVENT",
+    "6": "I-ORG\"",
+    "7": "0",
+    "8": "I-PER",
+    "9": "B-ORG",
+    "10": "I-MED",
+    "11": "B-MED",
+    "12": "I-ORG",
+    "13": "B-PER",
+    "14": "B-POS",
+    "15": "O",
+    "16": "I-LOC",
+    "17": "B-O",
+    "18": "B-LEG",
+    "19": "B-VIP",
+    "20": "B-DOC",
+    "21": "B-TITLE",
+    "22": "B- VIP",
+    "23": "MICHAEL B-VIP",
+    "24": "B-LOC",
+    "25": "I-VIP",
+    "26": "B-PROD",
+    "27": "I-DOC"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": 7,
+    "B- VIP": 22,
+    "B-DOC": 20,
+    "B-EVENT": 5,
+    "B-LEG": 18,
+    "B-LOC": 24,
+    "B-MED": 11,
+    "B-MED\"": 1,
+    "B-MTG": 3,
+    "B-O": 17,
+    "B-ORG": 9,
+    "B-PER": 13,
+    "B-POS": 14,
+    "B-PROD": 26,
+    "B-TITLE": 21,
+    "B-VIP": 19,
+    "C-B-VIP": 2,
+    "I-DOC": 27,
+    "I-LEG": 4,
+    "I-LOC": 16,
+    "I-MED": 10,
+    "I-ORG": 12,
+    "I-ORG\"": 6,
+    "I-PER": 8,
+    "I-VIP": 25,
+    "MICHAEL B-VIP": 23,
+    "O": 15,
+    "O\"": 0
+  },
+  "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": "4.45.1",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc736936f1d47e2a2422d5ec9ef5b93a37d0c9905370e95061e4465afe3f416
+size 260862112

runs/Nov19_08-19-22_f770c02d8443/events.out.tfevents.1732004711.f770c02d8443.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18b5cc8849dbf30dd506475280362c87e2cbe5c6b05be7e5eedbe8cbac757310
+size 7124

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 +1,55 @@
+{
+  "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,
+  "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:f937ca4176924add505da51e72d0f14c457d01333d3d72e55cacc0060d53b5ae
+size 5240