End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: google/muril-base-cased
+base_model: bert-base-multilingual-cased
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # uner-muril-ner
 
-This model is a fine-tuned version of [google/muril-base-cased](https://huggingface.co/google/muril-base-cased) on an unknown dataset.
+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: 0.9988
-- Precision: 0.7540
-- Recall: 0.5065
-- F1: 0.6060
-- Accuracy: 0.9354
+- Loss: 0.8124
+- Precision: 0.0
+- Recall: 0.0
+- F1: 0.0
+- Accuracy: 0.8061
 
 ## Model description
 
@@ -43,7 +43,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 0.002
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -53,18 +53,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 144  | 1.3197          | 0.7598    | 0.2537 | 0.3804 | 0.8836   |
-| No log        | 2.0   | 288  | 1.1787          | 0.8185    | 0.5131 | 0.6308 | 0.9316   |
-| No log        | 3.0   | 432  | 1.0772          | 0.7754    | 0.5115 | 0.6164 | 0.9340   |
-| 1.2357        | 4.0   | 576  | 1.0183          | 0.7512    | 0.5090 | 0.6068 | 0.9356   |
-| 1.2357        | 5.0   | 720  | 0.9988          | 0.7540    | 0.5065 | 0.6060 | 0.9354   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1  | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
+| No log        | 1.0   | 144  | 0.9153          | 0.0       | 0.0    | 0.0 | 0.8061   |
+| No log        | 2.0   | 288  | 0.8211          | 0.0       | 0.0    | 0.0 | 0.8061   |
+| No log        | 3.0   | 432  | 0.8449          | 0.0       | 0.0    | 0.0 | 0.8061   |
+| 0.8505        | 4.0   | 576  | 0.8082          | 0.0       | 0.0    | 0.0 | 0.8061   |
+| 0.8505        | 5.0   | 720  | 0.8124          | 0.0       | 0.0    | 0.0 | 0.8061   |
 
 
 ### Framework versions
 
-- Transformers 4.34.0
-- Pytorch 2.0.1+cu118
+- Transformers 4.33.0
+- Pytorch 2.0.0
 - Datasets 2.14.5
-- Tokenizers 0.14.1
+- Tokenizers 0.13.3

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "google/muril-base-cased",
+  "_name_or_path": "bert-base-multilingual-cased",
   "architectures": [
     "BertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "embedding_size": 768,
+  "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -37,10 +37,15 @@
   "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": "4.34.0",
+  "transformers_version": "4.33.0",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 197285
+  "vocab_size": 119547
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3ce5a87329bb5881425d4d7cd02dfad47fb181a09438a89ccd29c6d9dee03f
-size 947954857
+oid sha256:3a5bc9bac19e69cf61755a4fb27ced379e68df30549c7c0a65d05bf394676039
+size 709143721

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cb5ee143f24f08e5fe598915cbcddb36d298e8532097433837bfa51087e77f1
-size 6408480
+oid sha256:a4a4fa4b10a2a40361529954532f10257fda53cb22177554a862bcc661b7e4d8
+size 2919615

tokenizer_config.json

@@ -1,58 +1,12 @@
 {
-  "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
-    },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "104": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "105": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [],
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": false,
-  "lowercase": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "strip_accents": false,
+  "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59111861ed364cfb71e03f5ee0106e30f137b578d01f5e213c5d25309ee53c11
-size 4091
+oid sha256:637b712e8a0acc8970a3b35f23b02a148360df800a7fc3b24973022aa209a19b
+size 4027