End of training

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3347
+- Loss: 0.3320
 
 ## Model description
 
@@ -39,16 +39,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.03
 - num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.3601        | 1.0   | 71   | 0.3547          |
-| 0.3492        | 2.0   | 142  | 0.3417          |
-| 0.3385        | 3.0   | 213  | 0.3357          |
-| 0.3223        | 4.0   | 284  | 0.3347          |
+| 0.3716        | 1.0   | 71   | 0.3512          |
+| 0.3324        | 2.0   | 142  | 0.3387          |
+| 0.2808        | 3.0   | 213  | 0.3339          |
+| 0.2974        | 4.0   | 284  | 0.3320          |
 
 
 ### Framework versions

adapter_config.json

@@ -11,7 +11,7 @@
   "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 64,
   "revision": null,
   "target_modules": [
     "q_proj",

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8232162f84b8997a29f74c95c4d6f28b889b1ae042e591978a1ab66c849d56e2
-size 67201357
+oid sha256:40cd531ca853203a3494fd3f9cacad4121e1d778ed8ef8bce6371d0ec537498f
+size 268527949

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5db0c5a3ab3eb0af8a0b84a7d7e09c60cafbda6462dab28bc9cadaf0c7289a63
+oid sha256:770385d85429bea66b87c42602effd33ff943d6a8bccd49241c20af5b1e31044
 size 3963