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: 0.4207
+- Loss: 0.3829
 
 ## 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 |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.4046        | 1.0   | 92   | 0.4372          |
-| 0.4353        | 2.0   | 184  | 0.4241          |
-| 0.4031        | 3.0   | 276  | 0.4195          |
-| 0.3939        | 4.0   | 368  | 0.4207          |
+| 0.4283        | 1.0   | 92   | 0.3975          |
+| 0.3979        | 2.0   | 184  | 0.3871          |
+| 0.3607        | 3.0   | 276  | 0.3833          |
+| 0.3438        | 4.0   | 368  | 0.3829          |
 
 
 ### 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:c7e76f28fa949b2277adaeb50f04afcbc2cffe3a7bc57a9647960bd8ec4aa62d
-size 67201357
+oid sha256:d6e278a9d3d1a81f2fb30a991972f6babb50fa8c0578d2de8dbcd9218a9625f5
+size 268527949

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b1455d093870eaacf16564d183a23a7efbb71836a701a26680e585321e54b4d
+oid sha256:08b71f8d317f9558b726e1d8dc8875b532bc90476548193d888cd6e96a1998ff
 size 3963