End of training

README.md

@@ -78,7 +78,7 @@ resume_from_checkpoint: null
 s2_attention: null
 sample_packing: false
 saves_per_epoch: 1
-sequence_len: 1024
+sequence_len: 2048
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -103,7 +103,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.1230
+- Loss: 3.0159
 
 ## Model description
 
@@ -135,7 +135,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 3.0102        | 0.0001 | 10   | 3.1230          |
+| 2.8271        | 0.0001 | 10   | 3.0159          |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58bcbd18514541ed340d8523ff610c7b7f212bed04c7c9a650d7d5dba956ccfe
+oid sha256:3171ffe45a2e29c53c9a07b40d42aed106c4e0993beb852fdf1cce321aad761d
 size 35313738

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f1db7887debfd2a32b2e57a127d6281b99952db790ecad675f64520d9d580e2
+oid sha256:e1e86263d6fe5ce97a419dcce48175915dabd6fc412ba243dae088f80ec18ac3
 size 35237104

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30b9e2d7aefc0f289b61119392da92e0ae12ee60a04680b0afe44550998d7cf4
+oid sha256:8449a25b4683306f9896742b3f4db40ff66c2ad119d6f70b37c39d8a7db972ad
 size 6776