Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: xlm-roberta-base
+base_model: ayshi/basic_roberta
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,12 +13,12 @@ probably proofread and complete it, then remove this comment. -->
 
 # ayshi/basic_roberta
 
-This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
+This model is a fine-tuned version of [ayshi/basic_roberta](https://huggingface.co/ayshi/basic_roberta) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.5068
-- Validation Loss: 0.8336
-- Train Accuracy: 0.7644
-- Epoch: 9
+- Train Loss: 0.5675
+- Validation Loss: 0.8138
+- Train Accuracy: 0.7556
+- 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': 960, '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 |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.3394     | 1.1667          | 0.6667         | 0     |
-| 1.1446     | 1.1147          | 0.6667         | 1     |
-| 1.0726     | 1.0547          | 0.6667         | 2     |
-| 0.9986     | 1.0134          | 0.6844         | 3     |
-| 0.8905     | 0.9697          | 0.7378         | 4     |
-| 0.7645     | 0.9131          | 0.7556         | 5     |
-| 0.6761     | 0.8459          | 0.76           | 6     |
-| 0.5992     | 0.7954          | 0.7778         | 7     |
-| 0.5088     | 0.8055          | 0.7733         | 8     |
-| 0.5068     | 0.8336          | 0.7644         | 9     |
+| 0.5675     | 0.8138          | 0.7556         | 0     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "ayshi/basic_roberta",
   "architectures": [
     "XLMRobertaForSequenceClassification"
   ],

special_tokens_map.json

@@ -1,4 +1,11 @@
 {
+  "additional_special_tokens": [
+    "<s>",
+    "<pad>",
+    "</s>",
+    "<unk>",
+    "<mask>"
+  ],
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8a7258c0a6ebb8ee47331d7d2c492bcdbe5df37dec05e7800932b5cd775f68
+oid sha256:065b9a8885bdf0abc715afd0a6094bdaf9545e8e566addae7e99a08a706e7e73
 size 1112482624

tokenizer_config.json

@@ -41,15 +41,25 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
+  "additional_special_tokens": [
+    "<s>",
+    "<pad>",
+    "</s>",
+    "<unk>",
+    "<mask>"
+  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
+  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
+  "stride": 0,
   "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }