epochs=4.0

README.md

@@ -1,27 +1,28 @@
 ---
 library_name: peft
 tags:
+- liuhaotian/llava-v1.5-13b_19.0
 - liuhaotian/llava-v1.5-13b_4.0
 - generated_from_trainer
 base_model: liuhaotian/llava-v1.5-13b
 model-index:
-- name: liuhaotian/llava-v1.5-13b_4.0
+- name: liuhaotian/llava-v1.5-13b_19.0
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# liuhaotian/llava-v1.5-13b_4.0
+# liuhaotian/llava-v1.5-13b_19.0
 
-This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b_4.0](https://huggingface.co/liuhaotian/llava-v1.5-13b_4.0) on an unknown dataset.
+This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b_19.0](https://huggingface.co/liuhaotian/llava-v1.5-13b_19.0) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.0141
-- eval_runtime: 97.3873
-- eval_samples_per_second: 8.903
-- eval_steps_per_second: 0.565
-- epoch: 3.0
-- step: 165
+- eval_loss: 0.0092
+- eval_runtime: 47.3085
+- eval_samples_per_second: 8.984
+- eval_steps_per_second: 0.571
+- epoch: 18.0
+- step: 486
 
 ## Model description
 

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:887b9fe51f95d1de9794c06cb807dd37710554d90005d8b36e781366b433e236
+oid sha256:b989c11d5ef5515fbc79936902002b48adef8e4ac0ba544836b5c34f7e981f74
 size 1001466944