Model save

README.md

@@ -1,13 +1,8 @@
 ---
 license: mit
-base_model: surrey-nlp/roberta-base-finetuned-abbr
+base_model: dslim/bert-base-NER
 tags:
 - generated_from_trainer
-metrics:
-- precision
-- recall
-- f1
-- accuracy
 model-index:
 - name: bert-base-NER-finetuned-ner
   results: []
@@ -18,13 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-NER-finetuned-ner
 
-This model is a fine-tuned version of [surrey-nlp/roberta-base-finetuned-abbr](https://huggingface.co/surrey-nlp/roberta-base-finetuned-abbr) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.4944
-- Precision: 0.8197
-- Recall: 0.8510
-- F1: 0.8350
-- Accuracy: 0.8172
+This model is a fine-tuned version of [dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER) on an unknown dataset.
 
 ## Model description
 
@@ -44,23 +33,19 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
+- train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 32
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 20
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
-- Transformers 4.37.2
+- Transformers 4.39.3
 - Pytorch 2.2.2+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.1
+- Datasets 2.19.0
+- Tokenizers 0.15.2

config.json

@@ -1,41 +1,49 @@
 {
-  "_name_or_path": "surrey-nlp/roberta-base-finetuned-abbr",
+  "_name_or_path": "dslim/bert-base-NER",
+  "_num_labels": 9,
   "architectures": [
-    "RobertaForTokenClassification"
+    "BertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
     "0": "O",
-    "1": "B-AC",
-    "2": "I-AC",
-    "3": "B-LF",
-    "4": "I-LF"
+    "1": "B-MISC",
+    "2": "I-MISC",
+    "3": "B-PER",
+    "4": "I-PER",
+    "5": "B-ORG",
+    "6": "I-ORG",
+    "7": "B-LOC",
+    "8": "I-LOC"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "B-AC": 1,
-    "B-LF": 3,
-    "I-AC": 2,
-    "I-LF": 4,
+    "B-LOC": 7,
+    "B-MISC": 1,
+    "B-ORG": 5,
+    "B-PER": 3,
+    "I-LOC": 8,
+    "I-MISC": 2,
+    "I-ORG": 6,
+    "I-PER": 4,
     "O": 0
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 1,
+  "output_past": true,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
-  "type_vocab_size": 1,
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a527ab00033365c6f135308a22aaac4a0ba4c6b2ff0bf9d83074f11bfdb6935d
-size 430918012
+oid sha256:2dd88b8e7c886a2a5ea8256b5437abca02bf43fc29ffd4c01f8f4afc2187d62f
+size 430929740

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6da4aff15c405ff227cf5b6c522356efc6e52c3eea8f325f99b3b07dde60d3c2
-size 4728
+oid sha256:88341f584804370faac7368449ebd73697f8116ec22eb7e1723c9f70624b0556
+size 4920