distilbert-ner-person-content

README.md

@@ -0,0 +1,76 @@
+---
+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
+  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 [distilbert/distilbert-base-cased](https://huggingface.co/distilbert/distilbert-base-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1117
+- Precision: 0.0
+- Recall: 0.0
+- F1: 0.0
+- Accuracy: 0.9592
+
+## 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_FUSED 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
+| No log        | 1.0   | 147  | 0.2772          | 0.0       | 0.0    | 0.0 | 0.9110   |
+| No log        | 2.0   | 294  | 0.1972          | 0.0       | 0.0    | 0.0 | 0.9223   |
+| No log        | 3.0   | 441  | 0.1520          | 0.0       | 0.0    | 0.0 | 0.9420   |
+| 0.2425        | 4.0   | 588  | 0.1341          | 0.0       | 0.0    | 0.0 | 0.9511   |
+| 0.2425        | 5.0   | 735  | 0.1241          | 0.0       | 0.0    | 0.0 | 0.9538   |
+| 0.2425        | 6.0   | 882  | 0.1184          | 0.0       | 0.0    | 0.0 | 0.9572   |
+| 0.1179        | 7.0   | 1029 | 0.1154          | 0.0       | 0.0    | 0.0 | 0.9574   |
+| 0.1179        | 8.0   | 1176 | 0.1131          | 0.0       | 0.0    | 0.0 | 0.9583   |
+| 0.1179        | 9.0   | 1323 | 0.1120          | 0.0       | 0.0    | 0.0 | 0.9594   |
+| 0.1179        | 10.0  | 1470 | 0.1117          | 0.0       | 0.0    | 0.0 | 0.9592   |
+
+
+### Framework versions
+
+- Transformers 4.56.0
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.0

config.json

@@ -0,0 +1,34 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "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,
+  "transformers_version": "4.56.0",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9a236d88ec9528b881d0cf0d63f546620fb73186598a72d60538246fbfcebb
+size 260785212

runs/Oct10_17-44-11_bao-ThinkPad-P16v-Gen-1/events.out.tfevents.1760111061.bao-ThinkPad-P16v-Gen-1.1882686.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3320c471ca31ab660494499990d6ebac45ed3050a6ad274bb99e9e933a564aed
+size 4868

runs/Oct10_17-53-04_bao-ThinkPad-P16v-Gen-1/events.out.tfevents.1760111586.bao-ThinkPad-P16v-Gen-1.1882686.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b137e9afed571906e02d0e05bb9bb4334fd344539b34d6b9b09c3a168843eb4
+size 4868

runs/Oct10_18-04-32_bao-ThinkPad-P16v-Gen-1/events.out.tfevents.1760112274.bao-ThinkPad-P16v-Gen-1.1882686.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff546d6c60438827b1b0fd44b9040dea3eec7cd0f4ec0acdaa6844fbae33bcce
+size 4868

runs/Oct10_18-05-12_bao-ThinkPad-P16v-Gen-1/events.out.tfevents.1760112314.bao-ThinkPad-P16v-Gen-1.1882686.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b1bc05e824091acbdc8af17f7e45f6a7c4b014d26926acab225a3d97596f6de
+size 4868

runs/Oct10_18-05-52_bao-ThinkPad-P16v-Gen-1/events.out.tfevents.1760112353.bao-ThinkPad-P16v-Gen-1.1882686.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73f6783ec51aaca3c3c76fec755c01adc2b676db8a779ab156c96266752b3665
+size 4868

runs/Oct10_18-09-14_bao-ThinkPad-P16v-Gen-1/events.out.tfevents.1760112555.bao-ThinkPad-P16v-Gen-1.1882686.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daad4f9d7742afb45f835130a06bca651fb1df9165ce3f4ec0db7db484bb3051
+size 4868

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 sha256:0dcd29423376424b9735cf3d9ce2f81a9a954c80c0f3a0f6da63fc8e7576f527
+size 5777