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: 0.9779
-- Eval/rewards/chosen: -0.1420
-- Eval/logps/chosen: -204.9554
-- Eval/rewards/rejected: -0.2358
-- Eval/logps/rejected: -217.5698
-- Eval/rewards/margins: 0.0939
-- Eval/kl: 0.0017
+- Loss: 1.9747
+- Eval/rewards/chosen: 3.2495
+- Eval/logps/chosen: -171.0409
+- Eval/rewards/rejected: 3.4477
+- Eval/logps/rejected: -180.7343
+- Eval/rewards/margins: -0.1982
+- Eval/kl: 30.9634
 
 ## 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: 5678
@@ -56,14 +56,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |        |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.7513        | 0.96  | 12   | 1.0249          | 0.0985 |
-| 0.9525        | 2.0   | 25   | 1.0135          | 0.0195 |
-| 0.7253        | 2.96  | 37   | 0.9964          | 0.0117 |
-| 0.8924        | 4.0   | 50   | 0.9858          | 0.0097 |
-| 0.7014        | 4.96  | 62   | 0.9809          | 0.0136 |
-| 0.6514        | 5.76  | 72   | 0.9779          | 0.0017 |
+| Training Loss | Epoch | Step | Validation Loss |         |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.7853        | 0.96  | 12   | 0.8873          | 0.0     |
+| 0.7587        | 2.0   | 25   | 1.5629          | 7.2240  |
+| 0.4339        | 2.96  | 37   | 1.8790          | 24.4316 |
+| 0.434         | 4.0   | 50   | 1.9581          | 28.7113 |
+| 0.3651        | 4.96  | 62   | 1.9744          | 30.8687 |
+| 0.3787        | 5.76  | 72   | 1.9747          | 30.9634 |
 
 
 ### Framework versions

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
+    "v_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 sha256:4fc67192acce172526cb049fef2d05ddf1304efe649c5d02ec47eaca5686b251
+oid sha256:e1b55893ad2942d29af08f831060bae969ffda1d32e439b5d08adb190bdfbc49
 size 27297544

metrics.jsonl

@@ -82,3 +82,9 @@
 {"epoch": 4.0, "precision": 0.3333333326797386, "recall": 0.9444444391975308, "fold": 0}
 {"epoch": 4.96, "precision": 0.3478260862003781, "recall": 0.8888888839506173, "fold": 0}
 {"epoch": 5.76, "precision": 0.3673469380258226, "recall": 0.9999999944444444, "fold": 0}
+{"epoch": 0.96, "precision": 0.4411764692906574, "recall": 0.8333333287037037, "fold": 0}
+{"epoch": 2.0, "precision": 0.5925925903978052, "recall": 0.8888888839506173, "fold": 0}
+{"epoch": 2.96, "precision": 0.7272727239669421, "recall": 0.8888888839506173, "fold": 0}
+{"epoch": 4.0, "precision": 0.5714285693877551, "recall": 0.8888888839506173, "fold": 0}
+{"epoch": 4.96, "precision": 0.5652173888468809, "recall": 0.7222222182098765, "fold": 0}
+{"epoch": 5.76, "precision": 0.6666666634920635, "recall": 0.7777777734567901, "fold": 0}

metrics_epoch_0.96_fold_0_lr_0.0001_seed_5678_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 0.96, "precision": 0.4411764692906574, "recall": 0.8333333287037037, "fold": 0}

metrics_epoch_2.0_fold_0_lr_0.0001_seed_5678_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 2.0, "precision": 0.5925925903978052, "recall": 0.8888888839506173, "fold": 0}

metrics_epoch_2.96_fold_0_lr_0.0001_seed_5678_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 2.96, "precision": 0.7272727239669421, "recall": 0.8888888839506173, "fold": 0}

metrics_epoch_4.0_fold_0_lr_0.0001_seed_5678_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 4.0, "precision": 0.5714285693877551, "recall": 0.8888888839506173, "fold": 0}

metrics_epoch_4.96_fold_0_lr_0.0001_seed_5678_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 4.96, "precision": 0.5652173888468809, "recall": 0.7222222182098765, "fold": 0}

metrics_epoch_5.76_fold_0_lr_0.0001_seed_5678_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 5.76, "precision": 0.6666666634920635, "recall": 0.7777777734567901, "fold": 0}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a3e5c02b9e2d6b945fd3552f9850aa91e7f136b0a542c17a843e83e6c54c20d
+oid sha256:31792599ae436cf4842d989d28a1bef8d71a9a9ffdff2ea6759a84ba464b566d
 size 5688