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: 0.6904
-- Eval/rewards/chosen: 0.2879
-- Eval/logps/chosen: -207.7220
-- Eval/rewards/rejected: 0.2057
-- Eval/logps/rejected: -231.8078
-- Eval/rewards/margins: 0.0822
-- Eval/kl: 2.3918
+- Loss: 0.5882
+- Eval/rewards/chosen: -241.2744
+- Eval/logps/chosen: -2623.3453
+- Eval/rewards/rejected: -268.1879
+- Eval/logps/rejected: -2915.7442
+- Eval/rewards/margins: 26.9135
+- 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: 9012
@@ -56,11 +56,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |        |
-|:-------------:|:------:|:----:|:---------------:|:------:|
-| 0.5741        | 0.9412 | 12   | 0.7027          | 0.2679 |
-| 0.5688        | 1.9608 | 25   | 0.6958          | 1.1968 |
-| 0.5388        | 2.9804 | 38   | 0.6904          | 2.3918 |
+| Training Loss | Epoch  | Step | Validation Loss |     |
+|:-------------:|:------:|:----:|:---------------:|:---:|
+| 0.875         | 0.9412 | 12   | 0.5882          | 0.0 |
+| 0.875         | 1.9608 | 25   | 0.5882          | 0.0 |
+| 0.875         | 2.9804 | 38   | 0.5882          | 0.0 |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44d1a4060b2636a2207c060cb070244eb68733afbaea4f524a9f9f887c183659
+oid sha256:b2839b132c4abc0e58aac28c72e2046ef49c371afa54e0ab61553e2f4deb5d2e
 size 27297544

metrics.jsonl

@@ -31,3 +31,6 @@
 {"epoch": 0.9411764705882353, "precision": 0.385416666265191, "recall": 0.9249999976875, "fold": 0}
 {"epoch": 1.9607843137254903, "precision": 0.4269662916550941, "recall": 0.949999997625, "fold": 0}
 {"epoch": 2.980392156862745, "precision": 0.43373493923646395, "recall": 0.89999999775, "fold": 0}
+{"epoch": 0.9411764705882353, "precision": 0.0, "recall": 0.0, "fold": 0}
+{"epoch": 1.9607843137254903, "precision": 0.0, "recall": 0.0, "fold": 0}
+{"epoch": 2.980392156862745, "precision": 0.0, "recall": 0.0, "fold": 0}

metrics_epoch_0.9411764705882353_fold_0_lr_0.001_seed_9012_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 0.9411764705882353, "precision": 0.0, "recall": 0.0, "fold": 0}

metrics_epoch_1.9607843137254903_fold_0_lr_0.001_seed_9012_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 1.9607843137254903, "precision": 0.0, "recall": 0.0, "fold": 0}

metrics_epoch_2.980392156862745_fold_0_lr_0.001_seed_9012_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 2.980392156862745, "precision": 0.0, "recall": 0.0, "fold": 0}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34b070ada030b749bd5a5f03820c6a2d654b58004254a367a4667200dd36c02f
+oid sha256:e383eaf321bb11703b6334e8ba447aa8a47c6a80fc0f1193f8d31661e23eee53
 size 5688