Training in progress epoch 0

README.md

@@ -1,4 +1,5 @@
 ---
+license: apache-2.0
 tags:
 - generated_from_keras_callback
 model-index:
@@ -11,12 +12,10 @@ probably proofread and complete it, then remove this comment. -->
 
 # veb/twitch-bert-base-cased-finetuned
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.2929
-- Train Sparse Categorical Accuracy: 0.8768
-- Validation Loss: 0.1927
-- Validation Sparse Categorical Accuracy: 0.9483
+- Train Loss: 3.4267
+- Validation Loss: 2.8382
 - Epoch: 0
 
 ## Model description
@@ -36,19 +35,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
-- training_precision: float32
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -610, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: mixed_float16
 
 ### Training results
 
-| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
-|:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
-| 0.2929     | 0.8768                            | 0.1927          | 0.9483                                 | 0     |
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 3.4267     | 2.8382          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.19.2
-- TensorFlow 2.7.0
-- Datasets 2.2.2
+- Transformers 4.20.1
+- TensorFlow 2.6.4
+- Datasets 2.3.2
 - Tokenizers 0.12.1

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "veb/twitch-bert-base-cased-finetuned",
+  "_name_or_path": "bert-base-cased",
   "architectures": [
-    "BertForSequenceClassification"
+    "BertForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
@@ -18,7 +18,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.19.2",
+  "transformers_version": "4.20.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 28996

special_tokens_map.json

@@ -1 +1,7 @@
-{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2f508293dc744f769dc04c1f63cda14895450cf69850a06dc85ff12f489c232
-size 433518320
+oid sha256:99ba8bf9725f9187d817d90d271da844d908e8fecff67ed97a88a79ada208766
+size 524305832

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -1 +1,14 @@
-{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "veb/twitch-bert-base-cased-finetuned", "tokenizer_class": "BertTokenizer"}
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-cased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}