End of training

README.md

@@ -20,7 +20,7 @@ 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 generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3356
+- Loss: 0.5056
 
 ## Model description
 
@@ -45,17 +45,13 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 5
+- num_epochs: 0.1
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 0.3543        | 1.0   | 2211  | 0.3467          |
-| 0.3446        | 2.0   | 4422  | 0.3378          |
-| 0.3585        | 3.0   | 6633  | 0.3359          |
-| 0.3683        | 4.0   | 8844  | 0.3356          |
-| 0.3682        | 5.0   | 11055 | 0.3356          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.4888        | 0.1001 | 221  | 0.5056          |
 
 
 ### Framework versions

adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
+    "q_proj",
     "o_proj",
-    "q_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:ff1c66d971abbb77586a8265956696ec7a10f2f442cea8401d1c65ec2cf89551
+oid sha256:690b91bb78ee86cac1bbbe477280220b0553b55fd4e31dccccbd1b8cc150bcce
 size 109086672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9283cd3c63170cd3edd91f0038e0ccc62b7584647025b2e1620235581a77bab8
+oid sha256:bf72002a1828cd3c54a688adf05274b16c4d723a4e69e9cc138d999c5580f6bc
 size 5240