Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: ayshi/basic_distil
+base_model: distilbert-base-multilingual-cased
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,12 +13,12 @@ probably proofread and complete it, then remove this comment. -->
 
 # ayshi/basic_distil
 
-This model is a fine-tuned version of [ayshi/basic_distil](https://huggingface.co/ayshi/basic_distil) on an unknown dataset.
+This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0069
-- Validation Loss: 1.3626
-- Train Accuracy: 0.7556
-- Epoch: 9
+- Train Loss: 1.4022
+- Validation Loss: 1.1513
+- Train Accuracy: 0.6667
+- Epoch: 0
 
 ## Model description
 
@@ -44,16 +44,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.0198     | 1.1937          | 0.7911         | 0     |
-| 0.0220     | 1.3049          | 0.7511         | 1     |
-| 0.0186     | 1.5090          | 0.7822         | 2     |
-| 0.0181     | 1.3297          | 0.7867         | 3     |
-| 0.0095     | 1.4989          | 0.68           | 4     |
-| 0.0101     | 1.4034          | 0.7689         | 5     |
-| 0.0076     | 1.3720          | 0.7689         | 6     |
-| 0.0077     | 1.3592          | 0.76           | 7     |
-| 0.0065     | 1.3647          | 0.7556         | 8     |
-| 0.0069     | 1.3626          | 0.7556         | 9     |
+| 1.4022     | 1.1513          | 0.6667         | 0     |
 
 
 ### Framework versions
@@ -61,4 +52,4 @@ The following hyperparameters were used during training:
 - Transformers 4.34.0
 - TensorFlow 2.13.0
 - Datasets 2.14.5
-- Tokenizers 0.14.0
+- Tokenizers 0.14.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "ayshi/basic_distil",
+  "_name_or_path": "distilbert-base-multilingual-cased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"

special_tokens_map.json

@@ -1,11 +1,4 @@
 {
-  "additional_special_tokens": [
-    "[PAD]",
-    "[UNK]",
-    "[CLS]",
-    "[SEP]",
-    "[MASK]"
-  ],
   "cls_token": "[CLS]",
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a21e7a86ad0ab691d73fa3af4989cb2f43c79cfeb5dc30851ca4888634a8587e
-size 541452232
+oid sha256:8dc816525040da74b29612a32b721a7383fcc1ba2b328b441ed58bd7f0e2f282
+size 541448896

tokenizer_config.json

@@ -41,26 +41,16 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "[PAD]",
-    "[UNK]",
-    "[CLS]",
-    "[SEP]",
-    "[MASK]"
-  ],
+  "additional_special_tokens": [],
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "mask_token": "[MASK]",
-  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "DistilBertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }