markrodrigo
/

Llama-3.1-8B-Instruct-Spatial-SQL-1.0-gguf

Text Generation

Model card Files Files and versions Community

markrodrigo commited on Oct 6, 2024

Commit

1bb7464

·

verified ·

1 Parent(s): 2f3a504

Update Hypers

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -179,7 +179,7 @@ Custom synthetic
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 2e-06
 - train_batch_size: 1
 - eval_batch_size: 1
 - distributed_type: multi-GPU
@@ -195,8 +195,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.5438        |   1    |  10  |  	0.5247        |
-| 0.4889        |   2    |  20  |   0.4494        |
 | 0.4072        |   3    |  30  |   0.4051        |

 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 2e-04
 - train_batch_size: 1
 - eval_batch_size: 1
 - distributed_type: multi-GPU
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
+| 0.5438        |   3    |  10  |  	0.5247        |
+| 0.4889        |   3    |  20  |   0.4494        |
 | 0.4072        |   3    |  30  |   0.4051        |