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: 2048
+sequence_len: 3072
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -103,7 +103,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [unsloth/gemma-2b-it](https://huggingface.co/unsloth/gemma-2b-it) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1827
+- Loss: 1.1491
 
 ## Model description
 
@@ -135,7 +135,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.3076        | 0.0046 | 10   | 1.1827          |
+| 1.3424        | 0.0046 | 10   | 1.1491          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "up_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
     "q_proj",
     "gate_proj",
-    "down_proj",
-    "o_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:ee3649262999aa3c61bd48c21fc879dc2a5ce0760d6dcc09dd68b540d5458fcb
+oid sha256:fe68c5ecae888631cb76716cb2ac236080f417b646cefd2561e378e70cd6ba85
 size 78537274

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:614dd8f0204a963ebebf6e1ac06ace2de16a3ace590bb3ee3134ef7220b429cb
+oid sha256:8a57f75a35cea0ebeff06fc046a1c7f3075a87554f0291766141805c3e43f38c
 size 78480072

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b991a4e1c6dfa4ed81243d209bdc061e7a670ccd591d81686f35c699ad10a756
+oid sha256:abe0ebb60c3333ae384da44c98de6aa8aaa0ee15e6f147db2e4a44f6405504b1
 size 6776