Training complete

README.md

@@ -0,0 +1,85 @@
+---
+license: apache-2.0
+base_model: dslim/distilbert-NER
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: distilbert-finetuned-ner
+  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-finetuned-ner
+
+This model is a fine-tuned version of [dslim/distilbert-NER](https://huggingface.co/dslim/distilbert-NER) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4109
+- Precision: 0.6952
+- Recall: 0.7549
+- F1: 0.7238
+- Accuracy: 0.8724
+
+## 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: 1e-06
+- 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
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 1.647         | 1.0   | 977   | 0.8265          | 0.4918    | 0.5741 | 0.5298 | 0.7793   |
+| 0.7697        | 2.0   | 1954  | 0.6350          | 0.5801    | 0.6567 | 0.6160 | 0.8194   |
+| 0.6089        | 3.0   | 2931  | 0.5591          | 0.6138    | 0.6857 | 0.6478 | 0.8352   |
+| 0.534         | 4.0   | 3908  | 0.5163          | 0.6296    | 0.6955 | 0.6609 | 0.8439   |
+| 0.4911        | 5.0   | 4885  | 0.4885          | 0.6436    | 0.7075 | 0.6740 | 0.8498   |
+| 0.4545        | 6.0   | 5862  | 0.4683          | 0.6526    | 0.7165 | 0.6830 | 0.8557   |
+| 0.4379        | 7.0   | 6839  | 0.4534          | 0.6600    | 0.7231 | 0.6901 | 0.8592   |
+| 0.4124        | 8.0   | 7816  | 0.4441          | 0.6713    | 0.7274 | 0.6982 | 0.8625   |
+| 0.403         | 9.0   | 8793  | 0.4345          | 0.6746    | 0.7359 | 0.7039 | 0.8658   |
+| 0.394         | 10.0  | 9770  | 0.4324          | 0.6835    | 0.7445 | 0.7127 | 0.8667   |
+| 0.3782        | 11.0  | 10747 | 0.4256          | 0.6820    | 0.7465 | 0.7128 | 0.8678   |
+| 0.3706        | 12.0  | 11724 | 0.4213          | 0.6873    | 0.7460 | 0.7155 | 0.8691   |
+| 0.3712        | 13.0  | 12701 | 0.4197          | 0.6873    | 0.7518 | 0.7181 | 0.8703   |
+| 0.3626        | 14.0  | 13678 | 0.4163          | 0.6882    | 0.7523 | 0.7188 | 0.8713   |
+| 0.351         | 15.0  | 14655 | 0.4142          | 0.6905    | 0.7528 | 0.7203 | 0.8717   |
+| 0.3528        | 16.0  | 15632 | 0.4142          | 0.6932    | 0.7538 | 0.7222 | 0.8718   |
+| 0.3523        | 17.0  | 16609 | 0.4123          | 0.6949    | 0.7533 | 0.7229 | 0.8722   |
+| 0.3464        | 18.0  | 17586 | 0.4107          | 0.6936    | 0.7538 | 0.7224 | 0.8727   |
+| 0.342         | 19.0  | 18563 | 0.4115          | 0.6954    | 0.7560 | 0.7244 | 0.8726   |
+| 0.3496        | 20.0  | 19540 | 0.4109          | 0.6952    | 0.7549 | 0.7238 | 0.8724   |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,79 @@
+{
+  "_name_or_path": "dslim/distilbert-NER",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "B-Actor",
+    "1": "I-Actor",
+    "2": "O",
+    "3": "B-Plot",
+    "4": "I-Plot",
+    "5": "B-Opinion",
+    "6": "I-Opinion",
+    "7": "B-Award",
+    "8": "I-Award",
+    "9": "B-Year",
+    "10": "B-Genre",
+    "11": "B-Origin",
+    "12": "I-Origin",
+    "13": "B-Director",
+    "14": "I-Director",
+    "15": "I-Genre",
+    "16": "I-Year",
+    "17": "B-Soundtrack",
+    "18": "I-Soundtrack",
+    "19": "B-Relationship",
+    "20": "I-Relationship",
+    "21": "B-Character_Name",
+    "22": "I-Character_Name",
+    "23": "B-Quote",
+    "24": "I-Quote"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-Actor": 0,
+    "B-Award": 7,
+    "B-Character_Name": 21,
+    "B-Director": 13,
+    "B-Genre": 10,
+    "B-Opinion": 5,
+    "B-Origin": 11,
+    "B-Plot": 3,
+    "B-Quote": 23,
+    "B-Relationship": 19,
+    "B-Soundtrack": 17,
+    "B-Year": 9,
+    "I-Actor": 1,
+    "I-Award": 8,
+    "I-Character_Name": 22,
+    "I-Director": 14,
+    "I-Genre": 15,
+    "I-Opinion": 6,
+    "I-Origin": 12,
+    "I-Plot": 4,
+    "I-Quote": 24,
+    "I-Relationship": 20,
+    "I-Soundtrack": 18,
+    "I-Year": 16,
+    "O": 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": "4.41.1",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b67822b905e1a2549036addb2f40af083414c7cf2e3d448fba7864dbceb61bd
+size 260852884

runs/May29_00-40-55_deda405e21c0/events.out.tfevents.1716943258.deda405e21c0.512.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f9c3a64b68d5a298eac7a40c9d011a550b49ca6aafc9e274d2c19c7658f634
+size 23970

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 +1,59 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9654a2c6d1063cc7ca3416469378cfa04fddd59eb06a3ae4f2fcbfcc6e7231
+size 5112