Training in progress epoch 0

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: distilbert-base-uncased
+base_model: bert-base-multilingual-cased
 tags:
 - generated_from_keras_callback
 model-index:
@@ -14,15 +14,15 @@ probably proofread and complete it, then remove this comment. -->
 
 # mahabharahta/my_awesome_wnut_model
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) 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:
-- Train Loss: 0.1102
-- Validation Loss: 0.2670
-- Train Precision: 0.5755
-- Train Recall: 0.4151
-- Train F1: 0.4823
-- Train Accuracy: 0.9460
-- Epoch: 2
+- Train Loss: 0.2774
+- Validation Loss: 0.3035
+- Train Precision: 0.5376
+- Train Recall: 0.2907
+- Train F1: 0.3773
+- Train Accuracy: 0.9383
+- Epoch: 0
 
 ## Model description
 
@@ -48,14 +48,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
 |:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
-| 0.1101     | 0.2670          | 0.5755          | 0.4151       | 0.4823   | 0.9460         | 0     |
-| 0.1097     | 0.2670          | 0.5755          | 0.4151       | 0.4823   | 0.9460         | 1     |
-| 0.1102     | 0.2670          | 0.5755          | 0.4151       | 0.4823   | 0.9460         | 2     |
+| 0.2774     | 0.3035          | 0.5376          | 0.2907       | 0.3773   | 0.9383         | 0     |
 
 
 ### Framework versions
 
 - Transformers 4.44.2
 - TensorFlow 2.17.0
-- Datasets 3.0.0
+- Datasets 3.0.1
 - Tokenizers 0.19.1

config.json

@@ -1,13 +1,14 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "bert-base-multilingual-cased",
   "architectures": [
-    "DistilBertForTokenClassification"
+    "BertForTokenClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "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-corporation",
@@ -24,6 +25,7 @@
     "12": "I-product"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "B-corporation": 1,
     "B-creative-work": 3,
@@ -39,15 +41,20 @@
     "I-product": 12,
     "O": 0
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "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",
   "transformers_version": "4.44.2",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:def1ffe30d31165cc7d079d4701ed0c60dc4140dca3188797608bfa0e8b3fbc9
-size 265618704
+oid sha256:7821a2d61b697b574b0701fa83f57858545bc7972a3ad8e9e5431f4cb7e87b69
+size 709377020

tokenizer_config.json

@@ -43,13 +43,13 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "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",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }