End of training

README.md

@@ -103,7 +103,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [unsloth/SmolLM-135M](https://huggingface.co/unsloth/SmolLM-135M) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4438
+- Loss: 2.4179
 
 ## Model description
 
@@ -141,8 +141,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 4.9719        | 0.0091 | 1    | 4.9420          |
-| 3.1668        | 0.2275 | 25   | 3.0763          |
-| 2.6059        | 0.4551 | 50   | 2.4438          |
+| 3.144         | 0.2275 | 25   | 3.0552          |
+| 2.5736        | 0.4551 | 50   | 2.4179          |
 
 
 ### Framework versions

adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "v_proj",
-    "o_proj",
-    "down_proj",
     "q_proj",
+    "o_proj",
+    "v_proj",
     "k_proj",
-    "gate_proj"
+    "gate_proj",
+    "down_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:fcaf08b24a9679e42efa194a2c1670e239f3ce1351bd27e7f386af5e73fc67c2
+oid sha256:dc044a70695607cc17aec63eb6538e44648968728e3d55fa8a1c2b025cfaec27
 size 39226778

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf2ded8e59d9dc6a945e9d305f14e24f190d04cd7b65f6cbcfb045b227ef09c6
+oid sha256:c9c9f5fcea190ce3edfa354c1b1207dfa263fe771f75c07167f7bb081d2502a3
 size 39131224

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5c0bebfbdf04b7958b1fae63dbe06a88e4db1f5fe8c714531900fb37bc3fc22
+oid sha256:5f1847c084eed9b0fa107ac868a39a27dca587d90916c6d92b3c3a3faeadaf97
 size 6776