copy pase

README.md

@@ -0,0 +1,65 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: unified_skill_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. -->
+
+# unified_skill_ner
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.0048
+- eval_Profession-B-f1: 0.9781
+- eval_Profession-I-f1: 0.9798
+- eval_Loc-B-f1: 0.9792
+- eval_Loc-I-f1: 0.9804
+- eval_AreaSkill-B-f1: 0.9625
+- eval_AreaSkill-I-f1: 0.9264
+- eval_Language-B-f1: 0.9976
+- eval_Language-I-f1: 0
+- eval_CertificatesLicense-B-f1: 0.9818
+- eval_CertificatesLicense-I-f1: 1.0
+- eval_Driverslicense-B-f1: 0.9912
+- eval_Driverslicense-I-f1: 1.0
+- eval_f1: 0.9409
+- eval_runtime: 10.5223
+- eval_samples_per_second: 490.958
+- eval_steps_per_second: 61.394
+- step: 0
+
+## 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: 4e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 123
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Framework versions
+
+- Transformers 4.26.1
+- Pytorch 1.13.1+cu116
+- Datasets 2.10.1
+- Tokenizers 0.13.2

added_tokens.json

@@ -0,0 +1,8 @@
+{
+  ".N": 50327,
+  ".n": 50328,
+  "C#": 50330,
+  "C++": 50325,
+  "c#": 50329,
+  "c++": 50326
+}

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "/home/jovyan/work/MatrixProject/ledigajobb-matrix-inputs/input/unified_skill_ner/model/",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50331
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463022270eb9d9cd2c6b97fe59a13c7df7dc2de7884574277d453beb15101a1e
+size 496531949

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 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "/home/jovyan/work/MatrixProject/ledigajobb-matrix-inputs/input/unified_skill_ner/tokenizer/",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/home/jovyan/.cache/huggingface/hub/models--KB--bert-base-swedish-cased/snapshots/81c7baa04742a30cb6732c181e678721868cb42e/special_tokens_map.json",
+  "strip_accents": false,
+  "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 sha256:1915b86e62b86411d47ac1bacbb698c43e6e91c81594e2e31739bb0449db2554
+size 3643