Model save

README.md

@@ -1,27 +1,19 @@
 ---
 library_name: peft
 tags:
-- liuhaotian/llava-v1.5-13b_2.0
 - generated_from_trainer
 base_model: liuhaotian/llava-v1.5-13b
 model-index:
-- name: liuhaotian/llava-v1.5-13b_2.0
+- name: llava_13b_country_synthetic
   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_2.0
+# llava_13b_country_synthetic
 
-This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b_2.0](https://huggingface.co/liuhaotian/llava-v1.5-13b_2.0) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 0.2012
-- eval_runtime: 95.921
-- eval_samples_per_second: 9.039
-- eval_steps_per_second: 0.573
-- epoch: 1.0
-- step: 55
+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.
 
 ## Model description
 
@@ -45,13 +37,13 @@ The following hyperparameters were used during training:
 - eval_batch_size: 4
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 4
-- total_train_batch_size: 16
-- total_eval_batch_size: 16
+- num_devices: 16
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 100.0
+- num_epochs: 500.0
 
 ### Framework versions
 

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eab3819f14293e58edb2bc32b2f95a4f93ac7ec01b07b359ae1641f60899016
+oid sha256:fca7a4bb02803e47991156b8325a0284a33be47b7d3a4708324bfd3517abe0a2
 size 1001466944

num_examples=200/llava-v1.5-13b_1.0/adapter_config.json

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

num_examples=200/llava-v1.5-13b_1.0/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:947df129e84dc1324bc53c86a935664a781f42c90e286f668b00ff184a5ae470
+oid sha256:fca7a4bb02803e47991156b8325a0284a33be47b7d3a4708324bfd3517abe0a2
 size 1001466944

num_examples=200/llava-v1.5-13b_1.0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fc910803574f32371809a6f98cc71adab02449a4db261c926bd2eaaef3435a9
-size 6840
+oid sha256:56eb5594d9c23ae8570c5df68c8b639485f606f0213d28463c09b8103e702bf9
+size 6776

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fc910803574f32371809a6f98cc71adab02449a4db261c926bd2eaaef3435a9
-size 6840
+oid sha256:56eb5594d9c23ae8570c5df68c8b639485f606f0213d28463c09b8103e702bf9
+size 6776