End of training

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+base_model: distilbert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: distilbert-base-cased-gmb-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. -->
+
+# distilbert-base-cased-gmb-ner
+
+This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0907
+- F1: 0.8453
+
+## 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: 5e-05
+- train_batch_size: 24
+- eval_batch_size: 24
+- 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 | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.1287        | 1.0   | 1402 | 0.0948          | 0.8283 |
+| 0.0732        | 2.0   | 2804 | 0.0867          | 0.8409 |
+| 0.0498        | 3.0   | 4206 | 0.0907          | 0.8453 |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,64 @@
+{
+  "_name_or_path": "distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "-100": "IGN",
+    "0": "B-art",
+    "1": "I-art",
+    "2": "B-eve",
+    "3": "I-eve",
+    "4": "B-geo",
+    "5": "I-geo",
+    "6": "B-gpe",
+    "7": "I-gpe",
+    "8": "B-nat",
+    "9": "I-nat",
+    "10": "B-org",
+    "11": "I-org",
+    "12": "B-per",
+    "13": "I-per",
+    "14": "B-tim",
+    "15": "I-tim",
+    "16": "O"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-art": 0,
+    "B-eve": 2,
+    "B-geo": 4,
+    "B-gpe": 6,
+    "B-nat": 8,
+    "B-org": 10,
+    "B-per": 12,
+    "B-tim": 14,
+    "I-art": 1,
+    "I-eve": 3,
+    "I-geo": 5,
+    "I-gpe": 7,
+    "I-nat": 9,
+    "I-org": 11,
+    "I-per": 13,
+    "I-tim": 15,
+    "O": 16
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc57d4ebf326c792c90c0e393958ace01220e44273d49b245340275507e311e6
+size 260851298

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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cdc4b83b4090beef83ade570359346075b7d1339d43f0ded0bcb8e9c7040ed1
+size 4536