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: 1.9373
-- Eval/rewards/chosen: 1.7801
-- Eval/logps/chosen: -189.7792
-- Eval/rewards/rejected: 1.3841
-- Eval/logps/rejected: -207.7363
-- Eval/rewards/margins: 0.3960
-- Eval/kl: 13.1057
+- Loss: 1.6916
+- Eval/rewards/chosen: -0.4209
+- Eval/logps/chosen: -211.7889
+- Eval/rewards/rejected: -0.4483
+- Eval/logps/rejected: -226.0602
+- Eval/rewards/margins: 0.0274
+- 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: 9012
@@ -56,14 +56,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |         |
-|:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.8263        | 0.9412 | 12   | 0.7743          | 0.0     |
-| 0.827         | 1.9608 | 25   | 0.7659          | 0.0     |
-| 0.4971        | 2.9804 | 38   | 1.9715          | 9.9657  |
-| 0.2863        | 4.0    | 51   | 1.9235          | 11.1631 |
-| 0.2741        | 4.9412 | 63   | 1.9366          | 13.0766 |
-| 0.428         | 5.6471 | 72   | 1.9373          | 13.1057 |
+| Training Loss | Epoch  | Step | Validation Loss |        |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 1.074         | 0.9412 | 12   | 1.9606          | 0.0013 |
+| 1.0223        | 1.9608 | 25   | 1.8546          | 0.0    |
+| 0.9832        | 2.9804 | 38   | 1.7737          | 0.0    |
+| 0.9095        | 4.0    | 51   | 1.6998          | 0.0    |
+| 0.9155        | 4.9412 | 63   | 1.6833          | 0.0    |
+| 0.5901        | 5.6471 | 72   | 1.6916          | 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 sha256:35c7d33d32a283cbdb481d2da12a823358c4a1563dd3875722c78b034cf5aa62
+oid sha256:0d4f4801933fb10ed34a020af01f57536309084c7d678224b7c23af10b7bcf2a
 size 27297544

metrics.jsonl

@@ -1,126 +1,5 @@
-{"epoch": 0.96, "precision": 0.6428571405612244, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 2.0, "precision": 0.749999996875, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 2.96, "precision": 0.8888888839506173, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 3.84, "precision": 0.8421052587257617, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 0.96, "precision": 0.4324324312636961, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 2.0, "precision": 0.4857142843265306, "recall": 0.9444444391975308, "fold": 0}
-{"epoch": 2.96, "precision": 0.586206894530321, "recall": 0.9444444391975308, "fold": 0}
-{"epoch": 3.84, "precision": 0.45454545316804407, "recall": 0.8333333287037037, "fold": 0}
-{"epoch": 0.96, "precision": 0.45945945821767714, "recall": 0.9444444391975308, "fold": 0}
-{"epoch": 2.0, "precision": 0.7368421013850416, "recall": 0.7777777734567901, "fold": 0}
-{"epoch": 2.96, "precision": 0.7083333303819445, "recall": 0.9444444391975308, "fold": 0}
-{"epoch": 3.84, "precision": 0.6799999972799999, "recall": 0.9444444391975308, "fold": 0}
-{"epoch": 0.96, "precision": 0.37499999921875, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 2.0, "precision": 0.3529411757785467, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 2.96, "precision": 0.3333333326797386, "recall": 0.9444444391975308, "fold": 0}
-{"epoch": 3.84, "precision": 0.33333333271604937, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 0.9411764705882353, "precision": 0.47058823437139563, "recall": 0.9999999958333333, "fold": 0}
-{"epoch": 1.9607843137254903, "precision": 0.6666666646464646, "recall": 0.9166666628472222, "fold": 0}
-{"epoch": 2.980392156862745, "precision": 0.6451612882414152, "recall": 0.8333333298611111, "fold": 0}
-{"epoch": 3.764705882352941, "precision": 0.6451612882414152, "recall": 0.8333333298611111, "fold": 0}
-{"epoch": 0.9411764705882353, "precision": 0.4313725481737793, "recall": 0.9166666628472222, "fold": 0}
-{"epoch": 1.9607843137254903, "precision": 0.4999999989130435, "recall": 0.9583333293402777, "fold": 0}
-{"epoch": 2.980392156862745, "precision": 0.4693877541441066, "recall": 0.9583333293402777, "fold": 0}
-{"epoch": 3.764705882352941, "precision": 0.4423076914571006, "recall": 0.9583333293402777, "fold": 0}
-{"epoch": 0.96, "precision": 0.5624999982421874, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 2.0, "precision": 0.749999996875, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 2.96, "precision": 0.9999999933333334, "recall": 0.8333333287037037, "fold": 0}
-{"epoch": 4.0, "precision": 0.9999999923076924, "recall": 0.7222222182098765, "fold": 0}
-{"epoch": 4.96, "precision": 0.9999999928571429, "recall": 0.7777777734567901, "fold": 0}
-{"epoch": 5.76, "precision": 0.8888888839506173, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 0.96, "precision": 0.4324324312636961, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 2.0, "precision": 0.5142857128163265, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 2.96, "precision": 0.51515151359045, "recall": 0.9444444391975308, "fold": 0}
-{"epoch": 4.0, "precision": 0.4444444432098765, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 4.96, "precision": 0.5624999982421874, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 5.76, "precision": 0.5624999982421874, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 0.96, "precision": 0.7368421013850416, "recall": 0.7777777734567901, "fold": 0}
-{"epoch": 2.0, "precision": 0.9166666590277779, "recall": 0.6111111077160494, "fold": 0}
-{"epoch": 2.96, "precision": 0.9090909008264464, "recall": 0.5555555524691358, "fold": 0}
-{"epoch": 4.0, "precision": 0.5999999976, "recall": 0.8333333287037037, "fold": 0}
-{"epoch": 4.96, "precision": 0.8571428530612245, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 5.76, "precision": 0.6521739102079395, "recall": 0.8333333287037037, "fold": 0}
-{"epoch": 0.96, "precision": 0.4736842092797784, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 2.0, "precision": 0.4615384603550296, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 2.96, "precision": 0.4999999984375, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 4.0, "precision": 0.5454545438016529, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 4.96, "precision": 0.49999999852941174, "recall": 0.9444444391975308, "fold": 0}
-{"epoch": 5.76, "precision": 0.47058823391003457, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 0.96, "precision": 0.7999999946666667, "recall": 0.666666662962963, "fold": 0}
-{"epoch": 2.0, "precision": 0.9999999500000026, "recall": 0.11111111049382716, "fold": 0}
-{"epoch": 2.96, "precision": 0.0, "recall": 0.0, "fold": 0}
-{"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}
-{"epoch": 0.96, "precision": 0.4210526304709141, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 2.0, "precision": 0.8461538396449705, "recall": 0.6111111077160494, "fold": 0}
-{"epoch": 2.96, "precision": 0.5714285693877551, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 4.0, "precision": 0.6363636334710744, "recall": 0.7777777734567901, "fold": 0}
-{"epoch": 4.96, "precision": 0.6666666638888888, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 5.76, "precision": 0.5517241360285374, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 0.96, "precision": 0.28846153790680473, "recall": 0.8333333287037037, "fold": 0}
-{"epoch": 2.0, "precision": 0.38297872258940696, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 2.96, "precision": 0.33333333259259257, "recall": 0.8333333287037037, "fold": 0}
-{"epoch": 4.0, "precision": 0.3673469380258226, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 4.96, "precision": 0.3617021268899955, "recall": 0.9444444391975308, "fold": 0}
-{"epoch": 5.76, "precision": 0.33999999931999997, "recall": 0.9444444391975308, "fold": 0}
-{"epoch": 0.96, "precision": 0.4999999984375, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 2.0, "precision": 0.5333333315555555, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 2.96, "precision": 0.6799999972799999, "recall": 0.9444444391975308, "fold": 0}
-{"epoch": 4.0, "precision": 0.6999999965, "recall": 0.7777777734567901, "fold": 0}
-{"epoch": 4.96, "precision": 0.5999999976, "recall": 0.8333333287037037, "fold": 0}
-{"epoch": 5.76, "precision": 0.6799999972799999, "recall": 0.9444444391975308, "fold": 0}
-{"epoch": 0.96, "precision": 0.34042553119058394, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 2.0, "precision": 0.37499999921875, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 2.96, "precision": 0.35999999928, "recall": 0.9999999944444444, "fold": 0}
-{"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}
-{"epoch": 0.96, "precision": 0.357142856292517, "recall": 0.8333333287037037, "fold": 0}
-{"epoch": 2.0, "precision": 0.35416666592881946, "recall": 0.9444444391975308, "fold": 0}
-{"epoch": 2.96, "precision": 0.3913043469754253, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 4.0, "precision": 0.3809523800453515, "recall": 0.8888888839506173, "fold": 0}
-{"epoch": 4.96, "precision": 0.39534883628988643, "recall": 0.9444444391975308, "fold": 0}
-{"epoch": 5.76, "precision": 0.37499999921875, "recall": 0.9999999944444444, "fold": 0}
-{"epoch": 0.9411764705882353, "precision": 0.47826086852551986, "recall": 0.9166666628472222, "fold": 0}
-{"epoch": 1.9607843137254903, "precision": 0.6486486468955441, "recall": 0.9999999958333333, "fold": 0}
-{"epoch": 2.980392156862745, "precision": 0.7916666633680556, "recall": 0.7916666633680556, "fold": 0}
-{"epoch": 4.0, "precision": 0.758620687039239, "recall": 0.9166666628472222, "fold": 0}
-{"epoch": 4.9411764705882355, "precision": 0.758620687039239, "recall": 0.9166666628472222, "fold": 0}
-{"epoch": 5.647058823529412, "precision": 0.6785714261479592, "recall": 0.7916666633680556, "fold": 0}
-{"epoch": 0.9411764705882353, "precision": 0.4035087712219144, "recall": 0.9583333293402777, "fold": 0}
-{"epoch": 1.9607843137254903, "precision": 0.49999999886363633, "recall": 0.9166666628472222, "fold": 0}
-{"epoch": 2.980392156862745, "precision": 0.45098039127258743, "recall": 0.9583333293402777, "fold": 0}
-{"epoch": 4.0, "precision": 0.46808510538705295, "recall": 0.9166666628472222, "fold": 0}
-{"epoch": 4.9411764705882355, "precision": 0.4259259251371742, "recall": 0.9583333293402777, "fold": 0}
-{"epoch": 5.647058823529412, "precision": 0.4693877541441066, "recall": 0.9583333293402777, "fold": 0}
-{"epoch": 0.9411764705882353, "precision": 0.5111111099753086, "recall": 0.9583333293402777, "fold": 0}
-{"epoch": 1.9607843137254903, "precision": 0.5483870950052029, "recall": 0.7083333303819445, "fold": 0}
-{"epoch": 2.980392156862745, "precision": 0.6785714261479592, "recall": 0.7916666633680556, "fold": 0}
-{"epoch": 4.0, "precision": 0.7096774170655566, "recall": 0.9166666628472222, "fold": 0}
-{"epoch": 4.9411764705882355, "precision": 0.7916666633680556, "recall": 0.7916666633680556, "fold": 0}
-{"epoch": 5.647058823529412, "precision": 0.7999999968, "recall": 0.8333333298611111, "fold": 0}
-{"epoch": 0.9411764705882353, "precision": 0.4444444436213992, "recall": 0.9999999958333333, "fold": 0}
-{"epoch": 1.9607843137254903, "precision": 0.47916666566840277, "recall": 0.9583333293402777, "fold": 0}
-{"epoch": 2.980392156862745, "precision": 0.45652173813799624, "recall": 0.8749999963541666, "fold": 0}
-{"epoch": 4.0, "precision": 0.4230769222633136, "recall": 0.9166666628472222, "fold": 0}
-{"epoch": 4.9411764705882355, "precision": 0.41999999915999997, "recall": 0.8749999963541666, "fold": 0}
-{"epoch": 5.647058823529412, "precision": 0.47916666566840277, "recall": 0.9583333293402777, "fold": 0}
-{"epoch": 0.9411764705882353, "precision": 0.5238095225623582, "recall": 0.9166666628472222, "fold": 0}
-{"epoch": 1.9607843137254903, "precision": 0.6571428552653061, "recall": 0.9583333293402777, "fold": 0}
-{"epoch": 2.980392156862745, "precision": 0.47058823437139563, "recall": 0.9999999958333333, "fold": 0}
-{"epoch": 4.0, "precision": 0.7407407379972565, "recall": 0.8333333298611111, "fold": 0}
-{"epoch": 4.9411764705882355, "precision": 0.6896551700356718, "recall": 0.8333333298611111, "fold": 0}
-{"epoch": 5.647058823529412, "precision": 0.7037037010973937, "recall": 0.7916666633680556, "fold": 0}
+{"epoch": 1.9607843137254903, "precision": 0.4897959173677634, "recall": 0.9999999958333333, "fold": 0}
+{"epoch": 2.980392156862745, "precision": 0.48888888780246914, "recall": 0.9166666628472222, "fold": 0}
+{"epoch": 4.0, "precision": 0.45999999908, "recall": 0.9583333293402777, "fold": 0}
+{"epoch": 4.9411764705882355, "precision": 0.47058823437139563, "recall": 0.9999999958333333, "fold": 0}
+{"epoch": 5.647058823529412, "precision": 0.4038461530695266, "recall": 0.8749999963541666, "fold": 0}

metrics_epoch_1.9607843137254903_fold_0_lr_1e-05_seed_9012_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 1.9607843137254903, "precision": 0.4897959173677634, "recall": 0.9999999958333333, "fold": 0}

metrics_epoch_2.980392156862745_fold_0_lr_1e-05_seed_9012_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 2.980392156862745, "precision": 0.48888888780246914, "recall": 0.9166666628472222, "fold": 0}

metrics_epoch_4.0_fold_0_lr_1e-05_seed_9012_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 4.0, "precision": 0.45999999908, "recall": 0.9583333293402777, "fold": 0}

metrics_epoch_4.9411764705882355_fold_0_lr_1e-05_seed_9012_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 4.9411764705882355, "precision": 0.47058823437139563, "recall": 0.9999999958333333, "fold": 0}

metrics_epoch_5.647058823529412_fold_0_lr_1e-05_seed_9012_weight_10.0.json

@@ -0,0 +1 @@
+{"epoch": 5.647058823529412, "precision": 0.4038461530695266, "recall": 0.8749999963541666, "fold": 0}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02fd3c6ce3518dfa2edf93ab61e2c61d6105c19d097f9404884b700243c420da
+oid sha256:12c8fd0a4b73198cfb183f8b9c6d47cfa697f16811760ffce0155941f1d89d93
 size 5688