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: 0.5201
+- Loss: 0.4935
 
 ## 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 |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.5384        | 1.0   | 46   | 0.5398          |
-| 0.5364        | 2.0   | 92   | 0.5310          |
-| 0.5254        | 3.0   | 138  | 0.5246          |
-| 0.4929        | 4.0   | 184  | 0.5201          |
+| 0.5752        | 1.0   | 46   | 0.5406          |
+| 0.5341        | 2.0   | 92   | 0.5026          |
+| 0.5516        | 3.0   | 138  | 0.4957          |
+| 0.4672        | 4.0   | 184  | 0.4935          |
 
 
 ### 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 sha256:7ca95afdc866a78090f3e92fe50a01e411e286508a2164481b2aeeaadee6583f
-size 67201357
+oid sha256:085c5d4244e14280d2a2988c43ccf2d75f7ae5f153700377d4e1f6c67fc0d5f9
+size 268527949

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04dad6dc76428bc2bb5da2f0eb8f16edf18a4b9f242aef43bdb1b487a99c4c35
+oid sha256:afc388763747f76d8c018e8ee1a8d7b489e9013005d80a199a7ad7059fefce84
 size 3963