Model save

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [LDCC/LDCC-SOLAR-10.7B](https://huggingface.co/LDCC/LDCC-SOLAR-10.7B) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7299
+- Loss: 0.6884
 
 ## Model description
 
@@ -35,10 +35,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
-- train_batch_size: 4
-- eval_batch_size: 16
+- learning_rate: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - num_epochs: 3
@@ -46,6 +48,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.7581        | 1.0   | 21   | 0.7133          |
+| 0.612         | 2.0   | 42   | 0.6810          |
+| 0.4944        | 3.0   | 63   | 0.6884          |
 
 
 ### Framework versions