Training in progress epoch 0

README.md

@@ -1,6 +1,4 @@
 ---
-license: apache-2.0
-base_model: borough-oblast/distilbert-base-multilingual-cased-finetuned-en-de-2
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,10 +11,10 @@ probably proofread and complete it, then remove this comment. -->
 
 # borough-oblast/distilbert-base-multilingual-cased-finetuned-en-de-v4
 
-This model is a fine-tuned version of [borough-oblast/distilbert-base-multilingual-cased-finetuned-en-de-2](https://huggingface.co/borough-oblast/distilbert-base-multilingual-cased-finetuned-en-de-2) 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: 2.5904
-- Validation Loss: 2.7529
+- Train Loss: 1.9530
+- Validation Loss: 2.7814
 - Epoch: 0
 
 ## Model description
@@ -36,14 +34,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -876, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 123673, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.5904     | 2.7529          | 0     |
+| 1.9530     | 2.7814          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "borough-oblast/distilbert-base-multilingual-cased-finetuned-en-de-2",
+  "_name_or_path": "borough-oblast/distilbert-base-multilingual-cased-finetuned-en-de-v4",
   "activation": "gelu",
   "architectures": [
     "DistilBertForMaskedLM"

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5695f546b359cced1e4eaa0f53944185597af60ef1fe204f12b1708d0ee444be
+oid sha256:ae3d07fec51e1b1442d0457fe9598a72e4d84cfdba001c5a2d44c828073b9854
 size 910749348