Upload TFGPT2ForSequenceClassification

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [raygx/GNePT](https://huggingface.co/raygx/GNePT) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.5905
-- Validation Loss: 0.6977
-- Epoch: 3
+- Train Loss: 0.4830
+- Validation Loss: 0.6690
+- Epoch: 0
 
 ## Model description
 
@@ -35,17 +35,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 6.99e-06, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.001}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-06, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.03}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.9549     | 0.7891          | 0     |
-| 0.7454     | 0.6990          | 1     |
-| 0.6544     | 0.6724          | 2     |
-| 0.5905     | 0.6977          | 3     |
+| 0.4830     | 0.6690          | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c8e4595ef305a9765546d2c7e5bff639cafcdf7aa020f5d5a77d3497d966f03
+oid sha256:52c8ba370824f38303e7ee7a00d384a266a6c884bc1c0a40d7bf8d50e72f0b39
 size 497166832