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: 0.3554
+- Loss: 0.3565
 
 ## 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 |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.3887        | 1.0   | 71   | 0.3729          |
-| 0.3541        | 2.0   | 142  | 0.3604          |
-| 0.3343        | 3.0   | 213  | 0.3549          |
-| 0.3261        | 4.0   | 284  | 0.3554          |
+| 0.3784        | 1.0   | 71   | 0.3750          |
+| 0.3439        | 2.0   | 142  | 0.3620          |
+| 0.3265        | 3.0   | 213  | 0.3574          |
+| 0.3194        | 4.0   | 284  | 0.3565          |
 
 
 ### 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 sha256:11b872400cb675529afe6887b96629f13e71147020631a39178cfaeaf6ff8ded
-size 67201357
+oid sha256:8145b2eeff2310df90ca583109bff0afe16e9b5600227176dbf77eb128ddd9f8
+size 268527949

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a471c1c6d6d16f1d45d33413609f98ac1a97a77261d1dc80df5594e0bfb5345
+oid sha256:a2afbc52b85944e511106582d64f2c5878d2905fa037dd369232845094fd7b0b
 size 3963