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: 0.6321
-- Eval/rewards/chosen: 3.4733
-- Eval/logps/chosen: -163.4038
-- Eval/rewards/rejected: 3.5641
-- Eval/logps/rejected: -175.3719
-- Eval/rewards/margins: -0.0908
-- Eval/kl: 32.9546
+- Loss: 0.6200
+- Eval/rewards/chosen: 0.1376
+- Eval/logps/chosen: -196.7612
+- Eval/rewards/rejected: 0.1472
+- Eval/logps/rejected: -209.5413
+- Eval/rewards/margins: -0.0096
+- Eval/kl: 1.2612
 
 ## Model description
 
@@ -43,7 +43,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 1e-05
 - train_batch_size: 1
 - eval_batch_size: 2
 - seed: 42
@@ -56,12 +56,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |         |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.4545        | 0.96  | 12   | 0.6038          | 15.7553 |
-| 0.1426        | 2.0   | 25   | 0.6101          | 26.9743 |
-| 0.2499        | 2.96  | 37   | 0.6388          | 32.6091 |
-| 0.1412        | 3.84  | 48   | 0.6321          | 32.9546 |
+| Training Loss | Epoch | Step | Validation Loss |        |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.4989        | 0.96  | 12   | 0.6223          | 0.2616 |
+| 0.6212        | 2.0   | 25   | 0.6215          | 0.8164 |
+| 0.4973        | 2.96  | 37   | 0.6192          | 1.2270 |
+| 0.7188        | 3.84  | 48   | 0.6200          | 1.2612 |
 
 
 ### Framework versions

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
     "o_proj",
-    "v_proj"
+    "v_proj",
+    "q_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 sha256:5beb462336ad17624de25d9e1e28cb7d8d39975afdaca7cab37b8855bad8ce2c
+oid sha256:86b8954f2edd9c34d1abd858abb49c7a3b2f272fbff94c230797e73bdad2e2af
 size 27297544

metrics.jsonl

@@ -2,3 +2,7 @@
 {"epoch": 2.0, "precision": 0.9999999947368421, "recall": 0.6333333312222222, "fold": 0}
 {"epoch": 2.96, "precision": 0.9999999947368421, "recall": 0.6333333312222222, "fold": 0}
 {"epoch": 3.84, "precision": 0.8260869529300567, "recall": 0.6333333312222222, "fold": 0}
+{"epoch": 0.96, "precision": 0.586956520463138, "recall": 0.899999997, "fold": 0}
+{"epoch": 2.0, "precision": 0.537037036042524, "recall": 0.9666666634444444, "fold": 0}
+{"epoch": 2.96, "precision": 0.5769230758136095, "recall": 0.9999999966666666, "fold": 0}
+{"epoch": 3.84, "precision": 0.5714285702623907, "recall": 0.9333333302222222, "fold": 0}

metrics_epoch_0.96_fold_0_lr_1e-05.json

@@ -0,0 +1 @@
+{"epoch": 0.96, "precision": 0.586956520463138, "recall": 0.899999997, "fold": 0}

metrics_epoch_2.0_fold_0_lr_1e-05.json

@@ -0,0 +1 @@
+{"epoch": 2.0, "precision": 0.537037036042524, "recall": 0.9666666634444444, "fold": 0}

metrics_epoch_2.96_fold_0_lr_1e-05.json

@@ -0,0 +1 @@
+{"epoch": 2.96, "precision": 0.5769230758136095, "recall": 0.9999999966666666, "fold": 0}

metrics_epoch_3.84_fold_0_lr_1e-05.json

@@ -0,0 +1 @@
+{"epoch": 3.84, "precision": 0.5714285702623907, "recall": 0.9333333302222222, "fold": 0}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcfd25f6fdb034ced2e3d2e0eda8743a26a9973765b4078049eee67e4e5099ca
+oid sha256:b92d954154fe72cd0367e750ecc63430dff6be850343798677c5f4463d2710b2
 size 5688