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: 1.1781
-- Eval/rewards/chosen: -0.0396
-- Eval/logps/chosen: -200.9254
-- Eval/rewards/rejected: -0.0766
-- Eval/logps/rejected: -241.0806
-- Eval/rewards/margins: 0.0370
-- Eval/kl: 0.0308
+- Loss: 0.7208
+- Eval/rewards/chosen: 5.9950
+- Eval/logps/chosen: -150.6513
+- Eval/rewards/rejected: 5.3806
+- Eval/logps/rejected: -180.0595
+- Eval/rewards/margins: 0.6145
+- Eval/kl: 52.5969
 
 ## Model description
 
@@ -43,10 +43,10 @@ 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: 5678
+- seed: 9012
 - gradient_accumulation_steps: 8
 - total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -56,10 +56,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |        |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.7403        | 0.96  | 12   | 1.2009          | 0.1233 |
-| 0.961         | 2.0   | 25   | 1.1781          | 0.0308 |
+| Training Loss | Epoch  | Step | Validation Loss |         |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.4454        | 0.9412 | 12   | 0.6884          | 36.2845 |
+| 0.3037        | 1.9608 | 25   | 0.7410          | 37.1582 |
+| 0.129         | 2.9804 | 38   | 0.7208          | 52.5969 |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd6946db558e74bfb454bad307b0bdc33704e39f257b512a5d6be81e58304d46
+oid sha256:7bc45d7319b9241c7d7a54616050d81ee34483405c3742434e459d9e266f94fc
 size 27297544

metrics.jsonl

@@ -22,3 +22,6 @@
 {"epoch": 2.0, "precision": 0.6444444430123457, "recall": 0.9666666634444444, "fold": 0}
 {"epoch": 0.96, "precision": 0.34939758994048487, "recall": 0.9666666634444444, "fold": 0}
 {"epoch": 2.0, "precision": 0.3717948713182117, "recall": 0.9666666634444444, "fold": 0}
+{"epoch": 0.9411764705882353, "precision": 0.4999999916666668, "recall": 0.0749999998125, "fold": 0}
+{"epoch": 1.9607843137254903, "precision": 0.6326530599333611, "recall": 0.7749999980625, "fold": 0}
+{"epoch": 2.980392156862745, "precision": 0.7419354814776274, "recall": 0.5749999985625, "fold": 0}

metrics_epoch_0.9411764705882353_fold_0_lr_0.001_seed_9012_weight_2.0.json

@@ -0,0 +1 @@
+{"epoch": 0.9411764705882353, "precision": 0.4999999916666668, "recall": 0.0749999998125, "fold": 0}

metrics_epoch_1.9607843137254903_fold_0_lr_0.001_seed_9012_weight_2.0.json

@@ -0,0 +1 @@
+{"epoch": 1.9607843137254903, "precision": 0.6326530599333611, "recall": 0.7749999980625, "fold": 0}

metrics_epoch_2.980392156862745_fold_0_lr_0.001_seed_9012_weight_2.0.json

@@ -0,0 +1 @@
+{"epoch": 2.980392156862745, "precision": 0.7419354814776274, "recall": 0.5749999985625, "fold": 0}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5783f3b3aa05b56860198428463dd5f7822af851e3ab42375ceb413fc156243e
+oid sha256:155482eea6cfc9856e03cc92d1779c2047923e077d880b4dbb6e4d3a605f29f7
 size 5688