End of training

README.md

@@ -18,12 +18,12 @@ 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: 0.8136
-- Eval/rewards/chosen: -15.7423
-- Eval/logps/chosen: -350.2482
-- Eval/rewards/rejected: -21.6619
-- Eval/logps/rejected: -446.4881
-- Eval/rewards/margins: 5.9196
+- Loss: 1.0917
+- Eval/rewards/chosen: -0.8414
+- Eval/logps/chosen: -201.2396
+- Eval/rewards/rejected: -0.9419
+- Eval/logps/rejected: -239.2882
+- Eval/rewards/margins: 0.1005
 - Eval/kl: 0.0
 
 ## 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: 1234
@@ -56,14 +56,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |     |
-|:-------------:|:-----:|:----:|:---------------:|:---:|
-| 0.4474        | 0.96  | 12   | 0.8052          | 0.0 |
-| 0.625         | 2.0   | 25   | 0.8136          | 0.0 |
-| 0.375         | 2.96  | 37   | 0.8136          | 0.0 |
-| 0.625         | 4.0   | 50   | 0.8136          | 0.0 |
-| 0.375         | 4.96  | 62   | 0.8136          | 0.0 |
-| 0.625         | 5.76  | 72   | 0.8136          | 0.0 |
+| Training Loss | Epoch | Step | Validation Loss |        |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 3.2209        | 0.96  | 12   | 1.3225          | 0.0157 |
+| 1.9694        | 2.0   | 25   | 1.2416          | 0.0    |
+| 2.2976        | 2.96  | 37   | 1.1633          | 0.0    |
+| 1.5033        | 4.0   | 50   | 1.1103          | 0.0    |
+| 1.7639        | 4.96  | 62   | 1.0895          | 0.0    |
+| 1.3062        | 5.76  | 72   | 1.0917          | 0.0    |
 
 
 ### Framework versions

adapter_config.json

@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
     "k_proj",
+    "v_proj",
+    "q_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6762a0a26fc0e7ab6290206c8f7f28688d71b8bbe0bebfd84cf7b3dde3572737
+oid sha256:03a7e2f5c9ec7835f5cba668e0f49b88fc9d3834182d78f7d43ca22c3627d6ca
 size 27297544

metrics.jsonl

@@ -52,3 +52,9 @@
 {"epoch": 4.0, "precision": 0.0, "recall": 0.0, "fold": 0}
 {"epoch": 4.96, "precision": 0.0, "recall": 0.0, "fold": 0}
 {"epoch": 5.76, "precision": 0.0, "recall": 0.0, "fold": 0}
+{"epoch": 0.96, "precision": 0.4285714275510204, "recall": 0.9999999944444444, "fold": 0}
+{"epoch": 2.0, "precision": 0.45945945821767714, "recall": 0.9444444391975308, "fold": 0}
+{"epoch": 2.96, "precision": 0.5294117631487889, "recall": 0.9999999944444444, "fold": 0}
+{"epoch": 4.0, "precision": 0.5624999982421874, "recall": 0.9999999944444444, "fold": 0}
+{"epoch": 4.96, "precision": 0.6153846130177515, "recall": 0.8888888839506173, "fold": 0}
+{"epoch": 5.76, "precision": 0.5999999976, "recall": 0.8333333287037037, "fold": 0}

metrics_epoch_0.96_fold_0_lr_1e-05_seed_1234_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 0.96, "precision": 0.4285714275510204, "recall": 0.9999999944444444, "fold": 0}

metrics_epoch_2.0_fold_0_lr_1e-05_seed_1234_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 2.0, "precision": 0.45945945821767714, "recall": 0.9444444391975308, "fold": 0}

metrics_epoch_2.96_fold_0_lr_1e-05_seed_1234_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 2.96, "precision": 0.5294117631487889, "recall": 0.9999999944444444, "fold": 0}

metrics_epoch_4.0_fold_0_lr_1e-05_seed_1234_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 4.0, "precision": 0.5624999982421874, "recall": 0.9999999944444444, "fold": 0}

metrics_epoch_4.96_fold_0_lr_1e-05_seed_1234_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 4.96, "precision": 0.6153846130177515, "recall": 0.8888888839506173, "fold": 0}

metrics_epoch_5.76_fold_0_lr_1e-05_seed_1234_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 5.76, "precision": 0.5999999976, "recall": 0.8333333287037037, "fold": 0}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b340257b7c876c7bc2e3b43481f52c813b86aef192525a86f64b55c23483da
+oid sha256:30ced44d801d4a06b88c5bdfaa381f53508cf093350b9fd4b96ff2f2bfa704d4
 size 5688