Training in progress epoch 0

README.md

@@ -1,5 +1,4 @@
 ---
-license: apache-2.0
 tags:
 - generated_from_keras_callback
 model-index:
@@ -12,10 +11,12 @@ probably proofread and complete it, then remove this comment. -->
 
 # veb/twitch-bert-base-cased-finetuned
 
-This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.4267
-- Validation Loss: 2.8382
+- Train Loss: 0.2938
+- Train Sparse Categorical Accuracy: 0.8775
+- Validation Loss: 0.1106
+- Validation Sparse Categorical Accuracy: 0.9602
 - Epoch: 0
 
 ## Model description
@@ -35,14 +36,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- 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
+- 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
 
 ### Training results
 
-| Train Loss | Validation Loss | Epoch |
-|:----------:|:---------------:|:-----:|
-| 3.4267     | 2.8382          | 0     |
+| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
+|:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
+| 0.2938     | 0.8775                            | 0.1106          | 0.9602                                 | 0     |
 
 
 ### Framework versions

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "veb/twitch-bert-base-cased-finetuned",
   "architectures": [
-    "BertForMaskedLM"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:282bc9df943f6d25931ab3a34b93824ddc65d7ab6a592d0920fed998ff2a6451
-size 524305832
+oid sha256:4b4c0f472476696eadba465432aef5fc7bd13d93ba10714d2551cacc3ca2d17a
+size 433535320

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "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]"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -3,7 +3,7 @@
   "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "bert-base-cased",
+  "name_or_path": "veb/twitch-bert-base-cased-finetuned",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "special_tokens_map_file": null,