Training in progress epoch 0

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_keras_callback
 model-index:
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # Ketki0203/punctuation-predict
 
-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:
 - Train Loss: nan
 - Validation Loss: nan
-- Epoch: 2
+- Epoch: 0
 
 ## Model description
 
@@ -44,8 +44,6 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | nan        | nan             | 0     |
-| nan        | nan             | 1     |
-| nan        | nan             | 2     |
 
 
 ### Framework versions

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,
@@ -29,9 +29,14 @@
   "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",
   "transformers_version": "4.40.0",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 197285
+  "vocab_size": 119547
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6cbb86a33cf2bf93ab93c020c670e7681fa0ad595242d59cf3fd3b23a8e250e
-size 948148184
+oid sha256:c8620fa2e9231b6e420eb26cc8fde32261a2b842949c5da43140c906ba50252d
+size 709349336

tokenizer_config.json

@@ -16,24 +16,24 @@
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "104": {
-      "content": "[CLS]",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "105": {
-      "content": "[SEP]",
+    "103": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -43,15 +43,12 @@
   },
   "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]"