Training in progress epoch 0

README.md

@@ -13,9 +13,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [vinai/phobert-base](https://huggingface.co/vinai/phobert-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 4.2959
-- Validation Loss: 4.2424
-- Epoch: 2
+- Train Loss: 5.5981
+- Validation Loss: 4.6262
+- Epoch: 0
 
 ## Model description
 
@@ -34,21 +34,19 @@ 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': -356, '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': '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': -687, '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: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 5.2260     | 4.5287          | 0     |
-| 4.3544     | 4.3212          | 1     |
-| 4.2959     | 4.2424          | 2     |
+| 5.5981     | 4.6262          | 0     |
 
 
 ### Framework versions
 
 - Transformers 4.18.0
-- TensorFlow 2.8.0
+- TensorFlow 2.10.1
 - Datasets 2.7.0
 - Tokenizers 0.11.0

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77988eccb4b335fd49a2110bae779157c452c65ec72ffdad45ef334e256366ed
+oid sha256:ce96b892de4f324bb1e811a3951f4518bc0f7f76f2c239bb5fe2e2306eddd75d
 size 737945212