Upload TFGPT2ForSequenceClassification

README.md

@@ -14,8 +14,8 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [raygx/distilGPT-Nepali](https://huggingface.co/raygx/distilGPT-Nepali) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.6596
-- Validation Loss: 0.6809
+- Train Loss: 0.6068
+- Validation Loss: 0.6592
 - Epoch: 1
 
 ## Model description
@@ -35,15 +35,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.03}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.04}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.8788     | 0.7572          | 0     |
-| 0.6596     | 0.6809          | 1     |
+| 0.8415     | 0.7254          | 0     |
+| 0.6068     | 0.6592          | 1     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cf295902ff41cd0fe53ad81486af836bd3c509e68586f9c7f3adbc99977219b
+oid sha256:092cd73404d46b159572737e4cdfb64a5a5a1a42875bff2ae080b26f46535280
 size 480590728