End of training

README.md

@@ -102,7 +102,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [jingyeom/seal3.1.6n_7b](https://huggingface.co/jingyeom/seal3.1.6n_7b) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0028
+- Loss: 0.0026
 
 ## Model description
 
@@ -140,7 +140,7 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 5.0286        | 0.0894 | 1    | 4.4021          |
-| 0.1096        | 2.2570 | 25   | 0.0028          |
+| 0.1083        | 2.2570 | 25   | 0.0026          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "up_proj",
-    "gate_proj",
-    "down_proj",
     "k_proj",
+    "down_proj",
+    "gate_proj",
     "o_proj",
-    "v_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4afc47dbc501b822e25c0cdc000280de74095b83eeb25555ac12858797c3b73
+oid sha256:e9fdb9670a96fe67b4bc6e3eeda9d9b6493db3e78f9073fe17654ed7426c4041
 size 319977674

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6be8897042dd870908e2b95e92353fbf5ecafc46d10f1068c1bf13a0323783cd
+oid sha256:28d188f7fdb1614fff7516bcb2a64d97efd1597a52d86de66c194cfd5eaa2403
 size 319876032

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36764b90adc2cda234cb27fbe5577f8dd90ec791c0bc4559b1a90ac18fa5b20d
+oid sha256:b42f1ce68c7b4db4cb68bcee97e43a6c1d797d25c673c723efcb20fa6d8d4fb5
 size 6776