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: 0.0570
+- Loss: 0.0519
 
 ## 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 |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.3224        | 1.0   | 638  | 0.3134          |
-| 0.0971        | 2.0   | 1276 | 0.0951          |
-| 0.0563        | 3.0   | 1914 | 0.0615          |
-| 0.0528        | 4.0   | 2552 | 0.0570          |
+| 0.3632        | 1.0   | 638  | 0.3282          |
+| 0.1027        | 2.0   | 1276 | 0.1067          |
+| 0.0539        | 3.0   | 1914 | 0.0570          |
+| 0.0512        | 4.0   | 2552 | 0.0519          |
 
 
 ### 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 sha256:1cc57afcbd59e350b6f2d229f67a10da596fb7ba70457d3cd8d1e899ad3c9464
-size 67201357
+oid sha256:80330548b6d71b614e251a842e9119ae3aa63b4004f594fa7bcf1ba709a4852c
+size 268527949

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2101b54f4451c893b0a17b8300a66958bc22d3e86f6c935dd6c1bbcf61f292f
+oid sha256:47f2a88dea389299b5771ea92f747125293336feba60b7810640c57bb50e1b9d
 size 3963