Update spaCy pipeline

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+textcat_multilabel/model filter=lfs diff=lfs merge=lfs -text
+transformer/model filter=lfs diff=lfs merge=lfs -text
+zh_Overall_Layer_Classifier-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,48 @@
+---
+tags:
+- spacy
+- text-classification
+language:
+- zh
+model-index:
+- name: zh_Overall_Layer_Classifier
+  results: []
+---
+| Feature | Description |
+| --- | --- |
+| **Name** | `zh_Overall_Layer_Classifier` |
+| **Version** | `0.0.0` |
+| **spaCy** | `>=3.6.1,<3.7.0` |
+| **Default Pipeline** | `transformer`, `textcat_multilabel` |
+| **Components** | `transformer`, `textcat_multilabel` |
+| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
+| **Sources** | n/a |
+| **License** | n/a |
+| **Author** | [n/a]() |
+
+### Label Scheme
+
+<details>
+
+<summary>View label scheme (4 labels for 1 components)</summary>
+
+| Component | Labels |
+| --- | --- |
+| **`textcat_multilabel`** | `比賽`, `加油`, `轉播`, `閒聊` |
+
+</details>
+
+### Accuracy
+
+| Type | Score |
+| --- | --- |
+| `CATS_SCORE` | 99.55 |
+| `CATS_MICRO_P` | 97.83 |
+| `CATS_MICRO_R` | 96.92 |
+| `CATS_MICRO_F` | 97.37 |
+| `CATS_MACRO_P` | 97.85 |
+| `CATS_MACRO_R` | 96.77 |
+| `CATS_MACRO_F` | 97.28 |
+| `CATS_MACRO_AUC` | 99.55 |
+| `TRANSFORMER_LOSS` | 4021.60 |
+| `TEXTCAT_MULTILABEL_LOSS` | 930.96 |

config.cfg

@@ -0,0 +1,157 @@
+[paths]
+train = "./data/train.spacy"
+dev = "./data/valid.spacy"
+vectors = null
+init_tok2vec = null
+
+[system]
+gpu_allocator = "pytorch"
+seed = 0
+
+[nlp]
+lang = "zh"
+pipeline = ["transformer","textcat_multilabel"]
+batch_size = 128
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+
+[nlp.tokenizer]
+@tokenizers = "spacy.zh.ChineseTokenizer"
+segmenter = "char"
+
+[components]
+
+[components.textcat_multilabel]
+factory = "textcat_multilabel"
+scorer = {"@scorers":"spacy.textcat_multilabel_scorer.v2"}
+threshold = 0.5
+
+[components.textcat_multilabel.model]
+@architectures = "spacy.TextCatEnsemble.v2"
+nO = null
+
+[components.textcat_multilabel.model.linear_model]
+@architectures = "spacy.TextCatBOW.v2"
+exclusive_classes = false
+ngram_size = 1
+no_output_layer = false
+nO = null
+
+[components.textcat_multilabel.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+pooling = {"@layers":"reduce_mean.v1"}
+upstream = "*"
+
+[components.transformer]
+factory = "transformer"
+max_batch_items = 4096
+set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
+
+[components.transformer.model]
+@architectures = "spacy-transformers.TransformerModel.v3"
+name = "bert-base-chinese"
+mixed_precision = false
+
+[components.transformer.model.get_spans]
+@span_getters = "spacy-transformers.strided_spans.v1"
+window = 128
+stride = 96
+
+[components.transformer.model.grad_scaler_config]
+
+[components.transformer.model.tokenizer_config]
+use_fast = true
+
+[components.transformer.model.transformer_config]
+
+[corpora]
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[training]
+accumulate_gradient = 3
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+patience = 1600
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+annotating_components = []
+before_to_disk = null
+before_update = null
+
+[training.batcher]
+@batchers = "spacy.batch_by_padded.v1"
+discard_oversize = true
+size = 2000
+buffer = 256
+get_length = null
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = false
+
+[training.optimizer]
+@optimizers = "Adam.v1"
+beta1 = 0.9
+beta2 = 0.999
+L2_is_weight_decay = true
+L2 = 0.01
+grad_clip = 1.0
+use_averages = false
+eps = 0.00000001
+
+[training.optimizer.learn_rate]
+@schedules = "warmup_linear.v1"
+warmup_steps = 250
+total_steps = 20000
+initial_rate = 0.00005
+
+[training.score_weights]
+cats_score = 1.0
+cats_score_desc = null
+cats_micro_p = null
+cats_micro_r = null
+cats_micro_f = null
+cats_macro_p = null
+cats_macro_r = null
+cats_macro_f = null
+cats_macro_auc = null
+cats_f_per_type = null
+
+[pretraining]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.tokenizer]
+pkuseg_model = null
+pkuseg_user_dict = "default"

meta.json

@@ -0,0 +1,78 @@
+{
+  "lang":"zh",
+  "name":"Overall_Layer_Classifier",
+  "version":"0.0.0",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_version":">=3.6.1,<3.7.0",
+  "spacy_git_version":"458bc5f45",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null
+  },
+  "labels":{
+    "transformer":[
+
+    ],
+    "textcat_multilabel":[
+      "\u6bd4\u8cfd",
+      "\u52a0\u6cb9",
+      "\u8f49\u64ad",
+      "\u9592\u804a"
+    ]
+  },
+  "pipeline":[
+    "transformer",
+    "textcat_multilabel"
+  ],
+  "components":[
+    "transformer",
+    "textcat_multilabel"
+  ],
+  "disabled":[
+
+  ],
+  "performance":{
+    "cats_score":0.9955167645,
+    "cats_score_desc":"macro AUC",
+    "cats_micro_p":0.978286011,
+    "cats_micro_r":0.9691818458,
+    "cats_micro_f":0.973712648,
+    "cats_macro_p":0.9784797905,
+    "cats_macro_r":0.9677062023,
+    "cats_macro_f":0.9728313633,
+    "cats_macro_auc":0.9955167645,
+    "cats_f_per_type":{
+      "\u6bd4\u8cfd":{
+        "p":0.9677419355,
+        "r":0.9914762328,
+        "f":0.9794653235
+      },
+      "\u52a0\u6cb9":{
+        "p":0.9884738088,
+        "r":0.9394561815,
+        "f":0.9633418585
+      },
+      "\u8f49\u64ad":{
+        "p":0.9693795326,
+        "r":0.9820408163,
+        "f":0.9756690998
+      },
+      "\u9592\u804a":{
+        "p":0.9883238853,
+        "r":0.9578515785,
+        "f":0.9728491713
+      }
+    },
+    "transformer_loss":40.2160341321,
+    "textcat_multilabel_loss":9.3095552224
+  },
+  "requirements":[
+    "spacy-transformers>=1.2.5,<1.3.0"
+  ]
+}

textcat_multilabel/cfg

@@ -0,0 +1,9 @@
+{
+  "labels":[
+    "\u6bd4\u8cfd",
+    "\u52a0\u6cb9",
+    "\u8f49\u64ad",
+    "\u9592\u804a"
+  ],
+  "threshold":0.5
+}

textcat_multilabel/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d77b22bcf400cf35703cb3e18322617a16f2c02ebfabc6cc6be4ce2e701385
+size 11305871

tokenizer/cfg

@@ -0,0 +1,3 @@
+{
+  "segmenter":"char"
+}

transformer/cfg

@@ -0,0 +1,3 @@
+{
+  "max_batch_items":4096
+}

transformer/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50d8abca024a3ed0b9fe2b2c8f985ee6f5d19538f58066303cca6ba8c7066015
+size 409704459

vocab/key2row

@@ -0,0 +1 @@
+�

vocab/lookups.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
+size 1

vocab/vectors.cfg

@@ -0,0 +1,3 @@
+{
+  "mode":"default"
+}

zh_Overall_Layer_Classifier-any-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf2d62746dfe12a7278c1423dbf3e6b0d0b63352485d10ecbc31c188faac5148
+size 386871385