End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: bert-base-uncased
+base_model: google-bert/bert-base-multilingual-cased
 tags:
 - generated_from_trainer
 metrics:
@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-f1-durga-muhammad
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0313
+- Loss: 0.0281
 - Accuracy: 0.995
 - Precision: 0.995
 - Recall: 0.995
@@ -56,13 +56,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1    |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:-----:|
-| 0.3962        | 1.2   | 60   | 0.0549          | 0.995    | 0.995     | 0.995  | 0.995 |
-| 0.0345        | 2.4   | 120  | 0.0314          | 0.995    | 0.995     | 0.995  | 0.995 |
+| 0.4433        | 1.2   | 60   | 0.2100          | 0.945    | 0.945     | 0.945  | 0.945 |
+| 0.0858        | 2.4   | 120  | 0.0321          | 0.995    | 0.995     | 0.995  | 0.995 |
 
 
 ### Framework versions
 
-- Transformers 4.45.2
+- Transformers 4.44.2
 - Pytorch 2.5.0+cu121
 - Datasets 3.0.2
-- Tokenizers 0.20.1
+- Tokenizers 0.19.1

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "google-bert/bert-base-multilingual-cased",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -17,11 +17,16 @@
   "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",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.45.2",
+  "transformers_version": "4.44.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20382e9b8b6cc41d647b8e8ea58f8e6bc9db532718d69ec5989098c66ed5f0af
-size 437958648
+oid sha256:daf381230470913999b9ddfca697ab1e0b1fc50db21850d3823e13d9774ad328
+size 711443456

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07aebc5b3d196d036f02f131a1e7cd14e28652993094a0c1e6adce5a9da77c09
-size 5240
+oid sha256:f754167c4e13a0f6c12429afaaa74def00ddf249463e3d7446cd3d413998da12
+size 5176