End of training

README.md

@@ -18,15 +18,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1762
-- Rewards/chosen: 0.3518
-- Rewards/rejected: -1.3902
+- Loss: 0.2506
+- Rewards/chosen: 0.2764
+- Rewards/rejected: -1.0388
 - Rewards/accuracies: 1.0
-- Rewards/margins: 1.7421
-- Logps/rejected: -198.1086
-- Logps/chosen: -155.2773
-- Logits/rejected: -1.0539
-- Logits/chosen: -0.8615
+- Rewards/margins: 1.3152
+- Logps/rejected: -194.5943
+- Logps/chosen: -156.0318
+- Logits/rejected: -1.0532
+- Logits/chosen: -0.8577
 
 ## Model description
 
@@ -45,7 +45,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-06
+- learning_rate: 5e-07
 - train_batch_size: 1
 - eval_batch_size: 1
 - seed: 42
@@ -53,13 +53,14 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
-| 0.184         | 0.79  | 200  | 0.1762          | 0.3518         | -1.3902          | 1.0                | 1.7421          | -198.1086      | -155.2773    | -1.0539         | -0.8615       |
+| 0.3358        | 0.79  | 200  | 0.3244          | 0.2277         | -0.7696          | 1.0                | 0.9973          | -191.9022      | -156.5185    | -1.0547         | -0.8590       |
+| 0.2428        | 1.59  | 400  | 0.2506          | 0.2764         | -1.0388          | 1.0                | 1.3152          | -194.5943      | -156.0318    | -1.0532         | -0.8577       |
 
 
 ### Framework versions