End of training

README.md

@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6530
-- Eval/rewards/chosen: 0.4001
-- Eval/logps/chosen: -203.5786
-- Eval/rewards/rejected: 0.3489
-- Eval/logps/rejected: -218.0877
-- Eval/rewards/margins: 0.0512
-- Eval/kl: 3.6727
+- Loss: 1.1779
+- Eval/rewards/chosen: 3.0961
+- Eval/logps/chosen: -176.6188
+- Eval/rewards/rejected: 2.8259
+- Eval/logps/rejected: -193.3174
+- Eval/rewards/margins: 0.2702
+- Eval/kl: 24.7168
 
 ## Model description
 
@@ -43,7 +43,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 0.0001
 - train_batch_size: 1
 - eval_batch_size: 2
 - seed: 9012
@@ -56,14 +56,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |        |
-|:-------------:|:------:|:----:|:---------------:|:------:|
-| 0.578         | 0.9412 | 12   | 0.6626          | 0.2550 |
-| 0.5683        | 1.9608 | 25   | 0.6610          | 1.2536 |
-| 0.551         | 2.9804 | 38   | 0.6581          | 2.3757 |
-| 0.537         | 4.0    | 51   | 0.6512          | 3.2689 |
-| 0.5566        | 4.9412 | 63   | 0.6495          | 3.6167 |
-| 0.4981        | 5.6471 | 72   | 0.6530          | 3.6727 |
+| Training Loss | Epoch  | Step | Validation Loss |         |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.7171        | 0.9412 | 12   | 0.8669          | 0.0     |
+| 0.4176        | 1.9608 | 25   | 1.0862          | 11.9864 |
+| 0.2679        | 2.9804 | 38   | 1.1516          | 17.8582 |
+| 0.1715        | 4.0    | 51   | 1.1719          | 23.9545 |
+| 0.1537        | 4.9412 | 63   | 1.1700          | 24.7377 |
+| 0.325         | 5.6471 | 72   | 1.1779          | 24.7168 |
 
 
 ### Framework versions

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "k_proj",
+    "v_proj",
     "q_proj",
-    "v_proj"
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6122b1e52823d1a014bf05be82520cde32cce59f762e4289a3d31104dae30c1
+oid sha256:ff2b2eb9b288eed8180429ef37b6b4e3958ad4986b9c283604743f4e6dac53a5
 size 27297544

metrics.jsonl

@@ -106,3 +106,9 @@
 {"epoch": 4.0, "precision": 0.46808510538705295, "recall": 0.9166666628472222, "fold": 0}
 {"epoch": 4.9411764705882355, "precision": 0.4259259251371742, "recall": 0.9583333293402777, "fold": 0}
 {"epoch": 5.647058823529412, "precision": 0.4693877541441066, "recall": 0.9583333293402777, "fold": 0}
+{"epoch": 0.9411764705882353, "precision": 0.5111111099753086, "recall": 0.9583333293402777, "fold": 0}
+{"epoch": 1.9607843137254903, "precision": 0.5483870950052029, "recall": 0.7083333303819445, "fold": 0}
+{"epoch": 2.980392156862745, "precision": 0.6785714261479592, "recall": 0.7916666633680556, "fold": 0}
+{"epoch": 4.0, "precision": 0.7096774170655566, "recall": 0.9166666628472222, "fold": 0}
+{"epoch": 4.9411764705882355, "precision": 0.7916666633680556, "recall": 0.7916666633680556, "fold": 0}
+{"epoch": 5.647058823529412, "precision": 0.7999999968, "recall": 0.8333333298611111, "fold": 0}

metrics_epoch_0.9411764705882353_fold_0_lr_0.0001_seed_9012_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 0.9411764705882353, "precision": 0.5111111099753086, "recall": 0.9583333293402777, "fold": 0}

metrics_epoch_1.9607843137254903_fold_0_lr_0.0001_seed_9012_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 1.9607843137254903, "precision": 0.5483870950052029, "recall": 0.7083333303819445, "fold": 0}

metrics_epoch_2.980392156862745_fold_0_lr_0.0001_seed_9012_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 2.980392156862745, "precision": 0.6785714261479592, "recall": 0.7916666633680556, "fold": 0}

metrics_epoch_4.0_fold_0_lr_0.0001_seed_9012_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 4.0, "precision": 0.7096774170655566, "recall": 0.9166666628472222, "fold": 0}

metrics_epoch_4.9411764705882355_fold_0_lr_0.0001_seed_9012_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 4.9411764705882355, "precision": 0.7916666633680556, "recall": 0.7916666633680556, "fold": 0}

metrics_epoch_5.647058823529412_fold_0_lr_0.0001_seed_9012_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 5.647058823529412, "precision": 0.7999999968, "recall": 0.8333333298611111, "fold": 0}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e08ca3a4446f7d782f7302ca228dbf55179039a84f7fdd64939a4c1174a84307
+oid sha256:28ec7bf8868727e6af608d55a688985efd09071eba2cf3d41ff0393020ae3fbe
 size 5688