End of training

README.md

@@ -13,9 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llava_13b_exact_location_name_synthetic
 
-This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b](https://huggingface.co/liuhaotian/llava-v1.5-13b) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0391
+This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b_1.0](https://huggingface.co/liuhaotian/llava-v1.5-13b_1.0) on an unknown dataset.
 
 ## Model description
 
@@ -47,14 +45,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.03
 - num_epochs: 2.0
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.2814        | 1.0   | 28   | 0.2219          |
-| 0.0352        | 2.0   | 56   | 0.0391          |
-
-
 ### Framework versions
 
 - PEFT 0.10.0

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1d531a6681773c67fa85d0b32dcebe3868f3b9c3256ee6f9ead3094f389cbb
+oid sha256:4d16696fb0254a9bb207ac6e00eb960ad5cdae962a401235a04085da127ec68e
 size 1001466944

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2991e82ab7ba907139f4bba931d14f8c3eec79df0068ef25c0b71ee52d6e0b
+oid sha256:ca823d71f9f1dfe99c4c12b322baa8687b341261d17a6a38a37d4ca0be5ed1d7
 size 6840