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: 0.6495
-- Eval/rewards/chosen: -0.0147
-- Eval/logps/chosen: -197.5959
-- Eval/rewards/rejected: -0.0005
-- Eval/logps/rejected: -254.4111
-- Eval/rewards/margins: -0.0142
-- Eval/kl: 0.0906
+- Loss: 0.7059
+- Eval/rewards/chosen: -117.4201
+- Eval/logps/chosen: -1371.6493
+- Eval/rewards/rejected: -168.1753
+- Eval/logps/rejected: -1936.1584
+- Eval/rewards/margins: 50.7552
+- Eval/kl: 0.0
 
 ## Model description
 
@@ -43,7 +43,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 0.001
 - train_batch_size: 1
 - eval_batch_size: 2
 - seed: 1234
@@ -56,10 +56,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |        |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.8104        | 0.96  | 12   | 0.6455          | 0.1366 |
-| 0.6833        | 2.0   | 25   | 0.6495          | 0.0906 |
+| Training Loss | Epoch | Step | Validation Loss |     |
+|:-------------:|:-----:|:----:|:---------------:|:---:|
+| 0.375         | 0.96  | 12   | 0.7059          | 0.0 |
+| 0.625         | 2.0   | 25   | 0.7059          | 0.0 |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b45cc67d6d667c4d8a1ab0f3032f7cedab6dc4f309fe56b539f7300495bed3f
+oid sha256:e9eba38acc006583ffa23a72c1d8cbe44b953594fc99b6508ca1019d9ea3f791
 size 27297544

metrics.jsonl

@@ -4,3 +4,5 @@
 {"epoch": 2.0, "precision": 0.8529411739619377, "recall": 0.9666666634444444, "fold": 0}
 {"epoch": 0.96, "precision": 0.43548387026534857, "recall": 0.899999997, "fold": 0}
 {"epoch": 2.0, "precision": 0.4754098352862134, "recall": 0.9666666634444444, "fold": 0}
+{"epoch": 0.96, "precision": 0.0, "recall": 0.0, "fold": 0}
+{"epoch": 2.0, "precision": 0.0, "recall": 0.0, "fold": 0}

metrics_epoch_0.96_fold_0_lr_0.001_seed_1234_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 0.96, "precision": 0.0, "recall": 0.0, "fold": 0}

metrics_epoch_2.0_fold_0_lr_0.001_seed_1234_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 2.0, "precision": 0.0, "recall": 0.0, "fold": 0}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97cd3fa005c4ebb2d26706ac9858584ceae99f4a07a031c4da87805249f0f73a
+oid sha256:83a282cecb6c39a1af7182b08a056f87ee2bec2312e20a9676d8f3239628cacd
 size 5688