End of training

README.md

@@ -42,7 +42,7 @@ early_stopping_patience: null
 eval_max_new_tokens: 128
 eval_table_size: null
 evals_per_epoch: 1
-flash_attention: false
+flash_attention: true
 fp16: null
 fsdp: null
 fsdp_config: null
@@ -102,7 +102,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [unsloth/Qwen2-7B](https://huggingface.co/unsloth/Qwen2-7B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
+- Loss: 0.8507
 
 ## Model description
 
@@ -136,11 +136,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.0           | 0.0044 | 1    | nan             |
-| 0.0           | 0.1106 | 25   | nan             |
-| 0.0           | 0.2211 | 50   | nan             |
-| 0.0           | 0.3317 | 75   | nan             |
-| 0.0           | 0.4422 | 100  | nan             |
+| 1.8272        | 0.0044 | 1    | 1.9260          |
+| 0.8706        | 0.1106 | 25   | 0.9072          |
+| 0.9693        | 0.2211 | 50   | 0.8707          |
+| 0.7109        | 0.3317 | 75   | 0.8530          |
+| 0.6786        | 0.4422 | 100  | 0.8507          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "k_proj",
     "o_proj",
+    "v_proj",
+    "down_proj",
     "gate_proj",
-    "k_proj",
-    "q_proj",
     "up_proj",
-    "down_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9606a4718cbf605fac2f9f3a7bd9f241c176317d4e2e367804b2d84c1210b79b
+oid sha256:d44aa5af6009b5829f29130b49aa01c47d83e67dbe1c0ca8bbe4382d9a61c689
 size 323103018

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22f5f7fd591b8777ebb93ab7cdbca3a92cf15051b9528de45a8917b17a81d33d
+oid sha256:6bf3a39e95c63fd317b4511b04b2b99d1f0c8e2c21346f3119f4e957cbbfc4d3
 size 323014168

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f8735a73365b512b9f48f10b65433a4cbab77cedd6badac3f38ce1ab2b45ce
+oid sha256:a9b5a647679363a8a6842c95e00e29abca1fa0c4d3c9b3a2d819be7d3f45d4cd
 size 6776