End of training

README.md

@@ -0,0 +1,84 @@
+---
+base_model: google-bert/bert-base-chinese
+tags:
+- generated_from_trainer
+datasets:
+- generator
+metrics:
+- precision
+- recall
+- f1
+model-index:
+- name: NERBorder
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: generator
+      type: generator
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.6153846153498767
+    - name: Recall
+      type: recall
+      value: 0.804091266599492
+    - name: F1
+      type: f1
+      value: 0.6971945083321585
+---
+
+<!-- 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. -->
+
+# NERBorder
+
+This model is a fine-tuned version of [google-bert/bert-base-chinese](https://huggingface.co/google-bert/bert-base-chinese) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1990
+- Precision: 0.6154
+- Recall: 0.8041
+- F1: 0.6972
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
+| 0.2157        | 1.0   | 416  | 0.1990          | 0.6154    | 0.8041 | 0.6972 |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.0.1
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "google-bert/bert-base-chinese",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b723e13ec07df97483a0b641e084364bed29a7fa2e3209840b2449c4b4f697
+size 406740756

runs/Mar20_15-06-46_supermicro/events.out.tfevents.1710918408.supermicro.2660342.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:986b24e0de9049599c3528f011520aff22c3b38245a20b09a7af486a03ef5c98
+size 6060

runs/Mar20_15-10-29_supermicro/events.out.tfevents.1710918632.supermicro.2661526.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ed66928de04a3147cf445bf31585f3c6c1dd77045dc660fc657d391cfac63d0
+size 6060

runs/Mar20_15-17-51_supermicro/events.out.tfevents.1710919073.supermicro.2662640.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b55607742bb7f3588b46ce2b6ca8dbfc520523f3bccaf81bbbf51ab6f5e6bdba
+size 6060

runs/Mar20_15-19-53_supermicro/events.out.tfevents.1710919196.supermicro.2663303.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f4fd6af247fab429eb001388481a3ba9b63d2425fe579cc456fb687c7fae7b3
+size 6060

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": true,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:570d20239598d150a8bdbcd3499fdf848353350942d86069d1db832c8c52e109
+size 4283