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: 1.1043
-- Eval/rewards/chosen: -0.1559
-- Eval/logps/chosen: -209.1386
-- Eval/rewards/rejected: -0.1992
-- Eval/logps/rejected: -223.5693
-- Eval/rewards/margins: 0.0434
-- Eval/kl: 0.0
+- Loss: 1.9373
+- Eval/rewards/chosen: 1.7801
+- Eval/logps/chosen: -189.7792
+- Eval/rewards/rejected: 1.3841
+- Eval/logps/rejected: -207.7363
+- Eval/rewards/margins: 0.3960
+- Eval/kl: 13.1057
 
 ## 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 |        |
-|:-------------:|:------:|:----:|:---------------:|:------:|
-| 0.7709        | 0.9412 | 12   | 1.1519          | 0.0384 |
-| 0.7453        | 1.9608 | 25   | 1.1408          | 0.0025 |
-| 0.7183        | 2.9804 | 38   | 1.1208          | 0.0    |
-| 0.6972        | 4.0    | 51   | 1.1199          | 0.0    |
-| 0.7078        | 4.9412 | 63   | 1.1090          | 0.0016 |
-| 0.5307        | 5.6471 | 72   | 1.1043          | 0.0    |
+| Training Loss | Epoch  | Step | Validation Loss |         |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.8263        | 0.9412 | 12   | 0.7743          | 0.0     |
+| 0.827         | 1.9608 | 25   | 0.7659          | 0.0     |
+| 0.4971        | 2.9804 | 38   | 1.9715          | 9.9657  |
+| 0.2863        | 4.0    | 51   | 1.9235          | 11.1631 |
+| 0.2741        | 4.9412 | 63   | 1.9366          | 13.0766 |
+| 0.428         | 5.6471 | 72   | 1.9373          | 13.1057 |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c46272a49d3f8cee679071f6197cb36adac8f289024b42863005fe92c34d509
+oid sha256:35c7d33d32a283cbdb481d2da12a823358c4a1563dd3875722c78b034cf5aa62
 size 27297544

metrics.jsonl

@@ -118,3 +118,9 @@
 {"epoch": 4.0, "precision": 0.4230769222633136, "recall": 0.9166666628472222, "fold": 0}
 {"epoch": 4.9411764705882355, "precision": 0.41999999915999997, "recall": 0.8749999963541666, "fold": 0}
 {"epoch": 5.647058823529412, "precision": 0.47916666566840277, "recall": 0.9583333293402777, "fold": 0}
+{"epoch": 0.9411764705882353, "precision": 0.5238095225623582, "recall": 0.9166666628472222, "fold": 0}
+{"epoch": 1.9607843137254903, "precision": 0.6571428552653061, "recall": 0.9583333293402777, "fold": 0}
+{"epoch": 2.980392156862745, "precision": 0.47058823437139563, "recall": 0.9999999958333333, "fold": 0}
+{"epoch": 4.0, "precision": 0.7407407379972565, "recall": 0.8333333298611111, "fold": 0}
+{"epoch": 4.9411764705882355, "precision": 0.6896551700356718, "recall": 0.8333333298611111, "fold": 0}
+{"epoch": 5.647058823529412, "precision": 0.7037037010973937, "recall": 0.7916666633680556, "fold": 0}

metrics_epoch_0.9411764705882353_fold_0_lr_0.0001_seed_9012_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 0.9411764705882353, "precision": 0.5238095225623582, "recall": 0.9166666628472222, "fold": 0}

metrics_epoch_1.9607843137254903_fold_0_lr_0.0001_seed_9012_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 1.9607843137254903, "precision": 0.6571428552653061, "recall": 0.9583333293402777, "fold": 0}

metrics_epoch_2.980392156862745_fold_0_lr_0.0001_seed_9012_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 2.980392156862745, "precision": 0.47058823437139563, "recall": 0.9999999958333333, "fold": 0}

metrics_epoch_4.0_fold_0_lr_0.0001_seed_9012_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 4.0, "precision": 0.7407407379972565, "recall": 0.8333333298611111, "fold": 0}

metrics_epoch_4.9411764705882355_fold_0_lr_0.0001_seed_9012_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 4.9411764705882355, "precision": 0.6896551700356718, "recall": 0.8333333298611111, "fold": 0}

metrics_epoch_5.647058823529412_fold_0_lr_0.0001_seed_9012_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 5.647058823529412, "precision": 0.7037037010973937, "recall": 0.7916666633680556, "fold": 0}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17d1cc7550239903db5c7966246500b720f8059322783a7c1e5f8da08cd93d5c
+oid sha256:02fd3c6ce3518dfa2edf93ab61e2c61d6105c19d097f9404884b700243c420da
 size 5688