thorirhrafn
/

llama_DPO_model_e1

@@ -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: 0.0071
-- Rewards/chosen: 0.5889
-- Rewards/rejected: -5.0531
 - Rewards/accuracies: 1.0
-- Rewards/margins: 5.6419
-- Logps/rejected: -235.3402
-- Logps/chosen: -154.7451
-- Logits/rejected: -1.0643
-- Logits/chosen: -0.8789
 ## Model description
@@ -45,7 +45,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 5e-06
 - train_batch_size: 1
 - eval_batch_size: 1
 - seed: 42
@@ -59,16 +59,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
-| 0.3699        | 0.1   | 25   | 0.1650          | 0.3739         | -1.4468          | 1.0                | 1.8207          | -199.2772      | -156.8949    | -1.0531         | -0.8630       |
-| 0.0503        | 0.2   | 50   | 0.0317          | 0.5533         | -3.2234          | 1.0                | 3.7768          | -217.0439      | -155.1004    | -1.0589         | -0.8704       |
-| 0.0179        | 0.3   | 75   | 0.0145          | 0.5776         | -4.1388          | 1.0                | 4.7164          | -226.1972      | -154.8575    | -1.0622         | -0.8764       |
-| 0.0119        | 0.4   | 100  | 0.0103          | 0.5835         | -4.5814          | 1.0                | 5.1648          | -230.6233      | -154.7993    | -1.0647         | -0.8764       |
-| 0.0092        | 0.5   | 125  | 0.0084          | 0.5818         | -4.8305          | 1.0                | 5.4123          | -233.1143      | -154.8155    | -1.0657         | -0.8775       |
-| 0.0076        | 0.6   | 150  | 0.0077          | 0.5824         | -4.9413          | 1.0                | 5.5236          | -234.2221      | -154.8100    | -1.0651         | -0.8784       |
-| 0.008         | 0.7   | 175  | 0.0074          | 0.5873         | -5.0013          | 1.0                | 5.5886          | -234.8223      | -154.7610    | -1.0653         | -0.8776       |
-| 0.0097        | 0.79  | 200  | 0.0071          | 0.5891         | -5.0424          | 1.0                | 5.6315          | -235.2336      | -154.7425    | -1.0646         | -0.8784       |
-| 0.0077        | 0.89  | 225  | 0.0072          | 0.5884         | -5.0430          | 1.0                | 5.6313          | -235.2391      | -154.7501    | -1.0645         | -0.8790       |
-| 0.0068        | 0.99  | 250  | 0.0071          | 0.5889         | -5.0531          | 1.0                | 5.6419          | -235.3402      | -154.7451    | -1.0643         | -0.8789       |
 ### Framework versions

 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: 0.1779
+- Rewards/chosen: 0.3527
+- Rewards/rejected: -1.3764
 - Rewards/accuracies: 1.0
+- Rewards/margins: 1.7292
+- Logps/rejected: -198.5740
+- Logps/chosen: -157.1067
+- Logits/rejected: -1.0528
+- Logits/chosen: -0.8587
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 1e-06
 - train_batch_size: 1
 - eval_batch_size: 1
 - seed: 42
 | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.6603        | 0.1   | 25   | 0.6253          | 0.0416         | -0.1007          | 0.9633             | 0.1423          | -185.8169      | -160.2181    | -1.0525         | -0.8550       |
+| 0.5342        | 0.2   | 50   | 0.5074          | 0.1130         | -0.3090          | 1.0                | 0.4220          | -187.8993      | -159.5039    | -1.0525         | -0.8569       |
+| 0.4382        | 0.3   | 75   | 0.4022          | 0.1798         | -0.5442          | 1.0                | 0.7241          | -190.2517      | -158.8354    | -1.0530         | -0.8563       |
+| 0.3592        | 0.4   | 100  | 0.3212          | 0.2338         | -0.7752          | 1.0                | 1.0090          | -192.5613      | -158.2961    | -1.0531         | -0.8579       |
+| 0.3035        | 0.5   | 125  | 0.2590          | 0.2824         | -0.9912          | 1.0                | 1.2736          | -194.7217      | -157.8096    | -1.0528         | -0.8583       |
+| 0.2374        | 0.6   | 150  | 0.2125          | 0.3190         | -1.1966          | 1.0                | 1.5157          | -196.7760      | -157.4438    | -1.0528         | -0.8575       |
+| 0.2094        | 0.7   | 175  | 0.1868          | 0.3455         | -1.3260          | 1.0                | 1.6714          | -198.0693      | -157.1793    | -1.0528         | -0.8598       |
+| 0.1886        | 0.79  | 200  | 0.1796          | 0.3491         | -1.3639          | 1.0                | 1.7130          | -198.4486      | -157.1428    | -1.0532         | -0.8617       |
+| 0.1805        | 0.89  | 225  | 0.1785          | 0.3523         | -1.3731          | 1.0                | 1.7254          | -198.5406      | -157.1107    | -1.0530         | -0.8593       |
+| 0.1821        | 0.99  | 250  | 0.1779          | 0.3527         | -1.3764          | 1.0                | 1.7292          | -198.5740      | -157.1067    | -1.0528         | -0.8587       |
 ### Framework versions