Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: ayshi/basic_roberta
+base_model: xlm-roberta-base
 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 [ayshi/basic_roberta](https://huggingface.co/ayshi/basic_roberta) on an unknown dataset.
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0661
-- Validation Loss: 0.8073
-- Train Accuracy: 0.8
-- Epoch: 10
+- Train Loss: 1.3581
+- Validation Loss: 1.1546
+- Train Accuracy: 0.6667
+- Epoch: 0
 
 ## Model description
 
@@ -37,24 +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': 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}
+- 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}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.5693     | 0.8997          | 0.7689         | 0     |
-| 0.4191     | 0.8351          | 0.7778         | 1     |
-| 0.3566     | 0.8170          | 0.7733         | 2     |
-| 0.2794     | 0.8220          | 0.8089         | 3     |
-| 0.2342     | 0.8998          | 0.7867         | 4     |
-| 0.1893     | 0.8396          | 0.8089         | 5     |
-| 0.1335     | 0.9013          | 0.7689         | 6     |
-| 0.1115     | 0.8215          | 0.8089         | 7     |
-| 0.0790     | 0.7676          | 0.8222         | 8     |
-| 0.0848     | 0.7698          | 0.8222         | 9     |
-| 0.0661     | 0.8073          | 0.8            | 10    |
+| 1.3581     | 1.1546          | 0.6667         | 0     |
 
 
 ### Framework versions

config.json

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

special_tokens_map.json

@@ -1,11 +1,4 @@
 {
-  "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:df90eeb472c747dca6fbc1544c1bce75ad6bd220b4468095742ab300d55217e9
+oid sha256:2b9dc23e8424daf17dc7653c7892a28c93ce9039bee5b0927e2868fc9bab3dbc
 size 1112482624

tokenizer_config.json

@@ -41,25 +41,15 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<s>",
-    "<pad>",
-    "</s>",
-    "<unk>",
-    "<mask>"
-  ],
+  "additional_special_tokens": [],
   "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>"
 }