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: 0.7208
-- 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
+- Loss: 0.5680
+- Eval/rewards/chosen: 3.9758
+- Eval/logps/chosen: -170.8436
+- Eval/rewards/rejected: 2.3382
+- Eval/logps/rejected: -210.4830
+- Eval/rewards/margins: 1.6376
+- Eval/kl: 26.3467
 
 ## Model description
 
@@ -43,7 +43,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.001
+- learning_rate: 0.0001
 - train_batch_size: 1
 - eval_batch_size: 2
 - seed: 9012
@@ -58,9 +58,9 @@ The following hyperparameters were used during training:
 
 | 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 |
+| 0.5428        | 0.9412 | 12   | 0.6298          | 16.0880 |
+| 0.3477        | 1.9608 | 25   | 0.5670          | 22.6355 |
+| 0.1303        | 2.9804 | 38   | 0.5680          | 26.3467 |
 
 
 ### 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 sha256:7bc45d7319b9241c7d7a54616050d81ee34483405c3742434e459d9e266f94fc
+oid sha256:88b4c3ca0d2bad82a3e96e4f1fb0f3de056911d7536aaa285f992b76a2120fbf
 size 27297544

metrics.jsonl

@@ -25,3 +25,6 @@
 {"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}
+{"epoch": 0.9411764705882353, "precision": 0.49333333267555557, "recall": 0.9249999976875, "fold": 0}
+{"epoch": 1.9607843137254903, "precision": 0.6249999990234376, "recall": 0.9999999975, "fold": 0}
+{"epoch": 2.980392156862745, "precision": 0.8205128184089414, "recall": 0.799999998, "fold": 0}

metrics_epoch_0.9411764705882353_fold_0_lr_0.0001_seed_9012_weight_2.0.json

@@ -0,0 +1 @@
+{"epoch": 0.9411764705882353, "precision": 0.49333333267555557, "recall": 0.9249999976875, "fold": 0}

metrics_epoch_1.9607843137254903_fold_0_lr_0.0001_seed_9012_weight_2.0.json

@@ -0,0 +1 @@
+{"epoch": 1.9607843137254903, "precision": 0.6249999990234376, "recall": 0.9999999975, "fold": 0}

metrics_epoch_2.980392156862745_fold_0_lr_0.0001_seed_9012_weight_2.0.json

@@ -0,0 +1 @@
+{"epoch": 2.980392156862745, "precision": 0.8205128184089414, "recall": 0.799999998, "fold": 0}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:155482eea6cfc9856e03cc92d1779c2047923e077d880b4dbb6e4d3a605f29f7
+oid sha256:e5a2481931f20bccdc398d9b890e8de6bb840e721f95972412d38e5edcac1b7b
 size 5688