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/Meta-Llama-3.1-8B](https://huggingface.co/unsloth/Meta-Llama-3.1-8B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
+- Loss: 0.8628
 
 ## Model description
 
@@ -136,11 +136,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.0           | 0.0004 | 1    | nan             |
-| 0.0           | 0.0103 | 25   | nan             |
-| 0.0           | 0.0206 | 50   | nan             |
-| 0.0           | 0.0309 | 75   | nan             |
-| 0.0           | 0.0412 | 100  | nan             |
+| 1.4349        | 0.0004 | 1    | 1.4960          |
+| 1.0719        | 0.0103 | 25   | 0.9809          |
+| 0.8261        | 0.0206 | 50   | 0.8903          |
+| 0.8859        | 0.0309 | 75   | 0.8677          |
+| 0.8202        | 0.0412 | 100  | 0.8628          |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16184e613928f3396f83c0c7ff31330d342233fdbecb20944b82a69ed0829da3
+oid sha256:92ed922a0f732a1e202018c98c4068cda3ed9dc18911402fa2073540e3ddb3b6
 size 335706186

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6283686037b29c419488a0dfab5a8ac24663cbe9678b492717761a6b3996ff6
+oid sha256:12565efd5f64bc493473760b2fa639964bcbbe89ace12120fc59dbaa190cc379
 size 335604696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3888676450e93ddaf7e7bf415d416189cffc6565f5de5935ce9cb7a326a69c8d
+oid sha256:bd170f249f9caf7a2a3855411a8014d5fd024df787e2726693ab5077b1224fb5
 size 6776