fionazhang/mistral-experiment-6

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0203
+- Loss: 2.1400
 
 ## Model description
 
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 1
+- num_epochs: 2
 
 ### Training results
 

adapter_config.json

@@ -20,10 +20,10 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "k_proj",
     "gate_proj",
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "k_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a35597ba87f48f26d72744e18209d52551a85b7132f4df95dabe30094e461c4
+oid sha256:4084bac1af648b499f5aff5cfaa0442b653b5773c9715720e487156157d98843
 size 23111352

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:277e5baab97c340ab6fd277f05670c021e8a94d43fa7c5ea8c2537114bc3eaa3
+oid sha256:d34b253ed769e6b3ffd1a0af7920ff9dc1af6bb97a2425819231127b0e983954
 size 4664