Training in progress, epoch 1

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+base_model: bert-base-multilingual-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: custom_BERT_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. -->
+
+# custom_BERT_NER
+
+This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2288
+- Perf P: 0.8211
+- Perf R: 0.9398
+- Inst P: 0.9444
+- Inst R: 0.8095
+- Comp P: 0.7717
+- Comp R: 0.7474
+- Precision: 0.8182
+- Recall: 0.8270
+- F1: 0.8226
+- Accuracy: 0.9412
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Perf P | Perf R | Inst P | Inst R | Comp P | Comp R | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:------:|:------:|:------:|:---------:|:------:|:------:|:--------:|
+| 1.1177        | 1.0   | 68   | 0.5451          | 0.5033 | 0.9277 | 0.7377 | 0.7143 | 0.4333 | 0.2737 | 0.5762    | 0.4973 | 0.5338 | 0.8295   |
+| 0.4079        | 2.0   | 136  | 0.3157          | 0.8021 | 0.9277 | 0.7742 | 0.7619 | 0.7701 | 0.7053 | 0.7542    | 0.7297 | 0.7418 | 0.9097   |
+| 0.2188        | 3.0   | 204  | 0.2725          | 0.7143 | 0.9036 | 0.7    | 0.7778 | 0.74   | 0.7789 | 0.7391    | 0.7351 | 0.7371 | 0.9164   |
+| 0.1484        | 4.0   | 272  | 0.2467          | 0.79   | 0.9518 | 0.7681 | 0.8413 | 0.7692 | 0.7368 | 0.7838    | 0.8036 | 0.7936 | 0.9290   |
+| 0.0914        | 5.0   | 340  | 0.2059          | 0.8488 | 0.8795 | 0.8571 | 0.8571 | 0.8370 | 0.8105 | 0.8312    | 0.8252 | 0.8282 | 0.9374   |
+| 0.0656        | 6.0   | 408  | 0.2090          | 0.8247 | 0.9639 | 0.8194 | 0.9365 | 0.8636 | 0.8    | 0.8406    | 0.8360 | 0.8383 | 0.9406   |
+| 0.0541        | 7.0   | 476  | 0.2066          | 0.7692 | 0.9639 | 0.8254 | 0.8254 | 0.8506 | 0.7789 | 0.8259    | 0.8288 | 0.8273 | 0.9432   |
+| 0.0345        | 8.0   | 544  | 0.2288          | 0.8211 | 0.9398 | 0.9444 | 0.8095 | 0.7717 | 0.7474 | 0.8182    | 0.8270 | 0.8226 | 0.9412   |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,77 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "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": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC",
+    "9": "B-PERF",
+    "10": "I-PERF",
+    "11": "B-COMP",
+    "12": "I-COMP",
+    "13": "B-INST",
+    "14": "I-INST",
+    "15": "B-OTH",
+    "16": "I-OTH",
+    "17": "B-MUSIC",
+    "18": "I-MUSIC",
+    "19": "B-OTHP",
+    "20": "I-OTHP"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-COMP": 11,
+    "B-INST": 13,
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-MUSIC": 17,
+    "B-ORG": 3,
+    "B-OTH": 15,
+    "B-OTHP": 19,
+    "B-PER": 1,
+    "B-PERF": 9,
+    "I-COMP": 12,
+    "I-INST": 14,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-MUSIC": 18,
+    "I-ORG": 4,
+    "I-OTH": 16,
+    "I-OTHP": 20,
+    "I-PER": 2,
+    "I-PERF": 10,
+    "O": 0
+  },
+  "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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c3ead9f2cea63531155eafac5d78b4b75051a71b92c6c211a58b43b3046dde3
+size 709139348

runs/Apr29_02-28-17_a88bf9f1af5f/events.out.tfevents.1714357698.a88bf9f1af5f.1337.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2f4af87d2cb277377b76896005251d7c67fb10ebdd7a6ec79b91e0347cb2e0
+size 13845

runs/Apr29_02-38-49_a88bf9f1af5f/events.out.tfevents.1714358330.a88bf9f1af5f.1337.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:607a97a26cd5cb6b3d205a5a671aadc7d1077dd9f4f41aab615ee9f06adc22ba
+size 16717

runs/Apr29_02-51-00_a88bf9f1af5f/events.out.tfevents.1714359061.a88bf9f1af5f.1337.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae817d67a0d8ef71f3b96837e6fa29c297089da308237c09f15ab8c30fe1f28a
+size 13806

runs/Apr29_03-02-32_a88bf9f1af5f/events.out.tfevents.1714359753.a88bf9f1af5f.1337.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b47a1300015d2ac7d7d49259899c8171f0c4facebb615c7e9eaabacbf859913b
+size 13825

runs/Apr29_03-15-19_a88bf9f1af5f/events.out.tfevents.1714360521.a88bf9f1af5f.13227.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82381c9c44f3fd8f8b1c8763fa4caf922bf9ce2b9ca7c6d3c9208f9d84d0a83f
+size 6610

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 sha256:15578840aabc4db66fd8724fe8a4ab4cdafff576a0f90066569c482cb68b8f2c
+size 4984