End of training

README.md

@@ -105,7 +105,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [openlm-research/open_llama_3b](https://huggingface.co/openlm-research/open_llama_3b) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0476
+- Loss: 1.0479
 
 ## Model description
 
@@ -143,7 +143,7 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 1.2924        | 0.1019 | 1    | 1.4097          |
-| 0.9544        | 2.6369 | 25   | 1.0476          |
+| 0.954         | 2.6369 | 25   | 1.0479          |
 
 
 ### Framework versions

adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "gate_proj",
     "v_proj",
     "down_proj",
     "o_proj",
     "q_proj",
-    "k_proj"
+    "k_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f58f5179602d2f95e7276c99b743fef489000c00e1655b9e9eee754c323afd
+oid sha256:282ec3653226e6c810c19bcb85382ed98528740029944eaa1b81bd5db3928b9f
 size 203538938

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2992ed27423bd6f37bd60b4c426bf1dca01691a329a2e81eb4f1e1ed877bc2c
+oid sha256:f00f9538b271e8d8961813afd5ab30b65fd44804ac0d2fd5fc611c77eb726d97
 size 203456160

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9feb44dd06351a4ebb3399d9273df0fe7c81cda65ffedc861c36f176fba73ef5
+oid sha256:11310abb03160086896271409f285f645e098cc1d2c620a9c8e344ab93359699
 size 6776