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 [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0261
-- Validation Loss: 0.7460
-- Train Accuracy: 0.8543
-- Epoch: 15
+- Train Loss: 0.4663
+- Validation Loss: 0.3563
+- Train Accuracy: 0.8653
+- Epoch: 0
 
 ## Model description
 
@@ -37,34 +37,19 @@ 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': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 736290, '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', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 24543, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, '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 |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.4875     | 0.3953          | 0.8520         | 0     |
-| 0.3445     | 0.3865          | 0.8604         | 1     |
-| 0.2584     | 0.4243          | 0.8552         | 2     |
-| 0.1934     | 0.4391          | 0.8604         | 3     |
-| 0.1492     | 0.5194          | 0.8564         | 4     |
-| 0.1174     | 0.5558          | 0.8532         | 5     |
-| 0.0956     | 0.6335          | 0.8486         | 6     |
-| 0.0789     | 0.5730          | 0.8493         | 7     |
-| 0.0670     | 0.6334          | 0.8558         | 8     |
-| 0.0576     | 0.6707          | 0.8589         | 9     |
-| 0.0493     | 0.6674          | 0.8548         | 10    |
-| 0.0432     | 0.6876          | 0.8562         | 11    |
-| 0.0384     | 0.7246          | 0.8520         | 12    |
-| 0.0332     | 0.6818          | 0.8543         | 13    |
-| 0.0297     | 0.8101          | 0.8528         | 14    |
-| 0.0261     | 0.7460          | 0.8543         | 15    |
+| 0.4663     | 0.3563          | 0.8653         | 0     |
 
 
 ### Framework versions
 
 - Transformers 4.35.2
-- TensorFlow 2.11.0
+- TensorFlow 2.9.1
 - Datasets 2.15.0
 - Tokenizers 0.15.0

logs/train/events.out.tfevents.1701804059.104-171-203-254.134182.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0595f013eb692ca4a220a872306a7d1b5bd7fa83cb128857912a70d3a1dd0b3a
+size 2646291

logs/validation/events.out.tfevents.1701806579.104-171-203-254.134182.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e44cced372b3baa07b05f1a94c30dc93a765c46263029c7d8e1d0979c463386
+size 195

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
+size 798011

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18053f98c878b5427ec4765407838b590c6e1b193d0755a9388c4604d24dd643
+oid sha256:c9d2dc92d353eeae0dbc9828de94b018af1fad4b2d043c967a667e00bd323fda
 size 469433904