Training in progress epoch 0

README.md

@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.5440
-- Validation Loss: 0.7428
-- Train Accuracy: 0.7761
-- Epoch: 4
+- Train Loss: 1.4044
+- Validation Loss: 1.1742
+- Train Accuracy: 0.6766
+- Epoch: 0
 
 ## Model description
 
@@ -37,18 +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': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 145, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 145, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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 |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.6175     | 0.7485          | 0.7463         | 0     |
-| 0.5581     | 0.7428          | 0.7761         | 1     |
-| 0.5490     | 0.7428          | 0.7761         | 2     |
-| 0.5456     | 0.7428          | 0.7761         | 3     |
-| 0.5440     | 0.7428          | 0.7761         | 4     |
+| 1.4044     | 1.1742          | 0.6766         | 0     |
 
 
 ### Framework versions

config.json

@@ -28,6 +28,7 @@
   "n_heads": 12,
   "n_layers": 6,
   "pad_token_id": 0,
+  "problem_type": "multi_label_classification",
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade97dbf9203a395c76eee0489c99dab8290251ddba8395d9d302cf449137b91
+oid sha256:34aeddd89fd41cae5a6496c8360b3e92ff2eca14d1beb37118a85fcc87837824
 size 267961024