Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: distilbert-base-multilingual-cased
+base_model: ayshi/basic_distil
 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 [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
+This model is a fine-tuned version of [ayshi/basic_distil](https://huggingface.co/ayshi/basic_distil) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.2951
-- Validation Loss: 0.8023
-- Train Accuracy: 0.7733
-- Epoch: 9
+- Train Loss: 0.3282
+- Validation Loss: 0.7966
+- Train Accuracy: 0.7644
+- Epoch: 0
 
 ## Model description
 
@@ -37,23 +37,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 320, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 640, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.4022     | 1.1513          | 0.6667         | 0     |
-| 1.1292     | 1.0600          | 0.6667         | 1     |
-| 0.9590     | 0.9466          | 0.7022         | 2     |
-| 0.7990     | 0.9353          | 0.7111         | 3     |
-| 0.6333     | 0.8576          | 0.76           | 4     |
-| 0.5108     | 0.8356          | 0.7422         | 5     |
-| 0.4181     | 0.8314          | 0.7556         | 6     |
-| 0.3560     | 0.8161          | 0.7689         | 7     |
-| 0.3210     | 0.8005          | 0.7733         | 8     |
-| 0.2951     | 0.8023          | 0.7733         | 9     |
+| 0.3282     | 0.7966          | 0.7644         | 0     |
 
 
 ### Framework versions

config.json

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

special_tokens_map.json

@@ -1,4 +1,11 @@
 {
+  "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 sha256:703cdba3a802ecb42d614bd6d4f91d85a46fe0e2eac250525f46140adb46d4c5
+oid sha256:797202d7989753c7fd666d49fe24ab425968405c6b6a250408c82754975ee3c3
 size 541448896

tokenizer_config.json

@@ -41,16 +41,26 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
+  "additional_special_tokens": [
+    "[PAD]",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[MASK]"
+  ],
   "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]"
 }