msperka/bert-finetuned-ner

.gitattributes

@@ -33,3 +33,4 @@ 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
+vocab.txt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,92 @@
+---
+license: cc-by-4.0
+base_model: dicta-il/dictabert
+tags:
+- generated_from_trainer
+datasets:
+- nemo_corpus
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: bert-finetuned-ner
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: nemo_corpus
+      type: nemo_corpus
+      config: flat_token
+      split: validation
+      args: flat_token
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.8606811145510835
+    - name: Recall
+      type: recall
+      value: 0.852760736196319
+    - name: F1
+      type: f1
+      value: 0.8567026194144837
+    - name: Accuracy
+      type: accuracy
+      value: 0.9786301369863014
+---
+
+<!-- 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. -->
+
+# bert-finetuned-ner
+
+This model is a fine-tuned version of [dicta-il/dictabert](https://huggingface.co/dicta-il/dictabert) on the nemo_corpus dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1102
+- Precision: 0.8607
+- Recall: 0.8528
+- F1: 0.8567
+- Accuracy: 0.9786
+
+## 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: 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.2884        | 1.0   | 618  | 0.1202          | 0.8182    | 0.8006 | 0.8093 | 0.9733   |
+| 0.0896        | 2.0   | 1236 | 0.1081          | 0.8298    | 0.8374 | 0.8336 | 0.9771   |
+| 0.0548        | 3.0   | 1854 | 0.1102          | 0.8607    | 0.8528 | 0.8567 | 0.9786   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.1+cpu
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,105 @@
+{
+  "_name_or_path": "dicta-il/dictabert",
+  "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": "S-ANG",
+    "1": "B-ANG",
+    "2": "I-ANG",
+    "3": "E-ANG",
+    "4": "S-DUC",
+    "5": "B-DUC",
+    "6": "I-DUC",
+    "7": "E-DUC",
+    "8": "B-EVE",
+    "9": "E-EVE",
+    "10": "S-EVE",
+    "11": "I-EVE",
+    "12": "S-FAC",
+    "13": "B-FAC",
+    "14": "E-FAC",
+    "15": "I-FAC",
+    "16": "S-GPE",
+    "17": "B-GPE",
+    "18": "E-GPE",
+    "19": "I-GPE",
+    "20": "S-LOC",
+    "21": "B-LOC",
+    "22": "E-LOC",
+    "23": "I-LOC",
+    "24": "O",
+    "25": "S-ORG",
+    "26": "B-ORG",
+    "27": "E-ORG",
+    "28": "I-ORG",
+    "29": "B-PER",
+    "30": "I-PER",
+    "31": "E-PER",
+    "32": "S-PER",
+    "33": "B-WOA",
+    "34": "E-WOA",
+    "35": "I-WOA",
+    "36": "S-WOA"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ANG": 1,
+    "B-DUC": 5,
+    "B-EVE": 8,
+    "B-FAC": 13,
+    "B-GPE": 17,
+    "B-LOC": 21,
+    "B-ORG": 26,
+    "B-PER": 29,
+    "B-WOA": 33,
+    "E-ANG": 3,
+    "E-DUC": 7,
+    "E-EVE": 9,
+    "E-FAC": 14,
+    "E-GPE": 18,
+    "E-LOC": 22,
+    "E-ORG": 27,
+    "E-PER": 31,
+    "E-WOA": 34,
+    "I-ANG": 2,
+    "I-DUC": 6,
+    "I-EVE": 11,
+    "I-FAC": 15,
+    "I-GPE": 19,
+    "I-LOC": 23,
+    "I-ORG": 28,
+    "I-PER": 30,
+    "I-WOA": 35,
+    "O": 24,
+    "S-ANG": 0,
+    "S-DUC": 4,
+    "S-EVE": 10,
+    "S-FAC": 12,
+    "S-GPE": 16,
+    "S-LOC": 20,
+    "S-ORG": 25,
+    "S-PER": 32,
+    "S-WOA": 36
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "newmodern": true,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 128000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c6fdaa2c8139cf8edd9b04d6928b148edfd6f1531847632c4b4f6fc0d6703a
+size 735156180

runs/Dec11_13-50-37_soc-5CG223442L/events.out.tfevents.1702295442.soc-5CG223442L

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63530312253fffc1a5bafbaf6f69ab8ee0e286139e8ba0b2b8987bf39370df05
+size 5530

runs/Dec11_13-53-45_soc-5CG223442L/events.out.tfevents.1702295627.soc-5CG223442L

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d338cd27b32fb200868bba9a3db4efc9462d3e909e7ee86c5cc231d35ffe60a0
+size 7771

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 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[BLANK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "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 sha256:7716b4262e7277768a15f42fafae42546d45f3ea9b2d67763866d55fb693d279
+size 4155

vocab.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fb90bfa35244d26f0065d1fcd0b5becc3da3d44d616a7e2aacaf6320b9fa2d0
+size 1500244