Model save

README.md

@@ -0,0 +1,59 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen2-VL-7B-Instruct
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: qwen2-7b-instruct-template-matching-overfit-v1
+  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. -->
+
+# qwen2-7b-instruct-template-matching-overfit-v1
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.13.0
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "/home/ubuntu/snappr/Qwen_Qwen2-VL-7B-Instruct",
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_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:d8ecdcbe1c29ef31362ff3fda0a208f39db6a3d9390172def42884958110ad6d
+oid sha256:ec534e4442b891e5cfba32d30b23f00f54de83ad4b0328e27465dafb0dffb35f
 size 10107280

runs/Nov13_22-37-09_ip-172-30-1-15/events.out.tfevents.1731537430.ip-172-30-1-15

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f90c90acd535a7a8c75725f98b601d4448803033d85c7a286126cfaa1a0a7188
-size 4699
+oid sha256:7a482060f393d5fcb587deb5ecb4195d730d97f4015876edd9b4b845549bf649
+size 6793

runs/Nov13_22-38-14_ip-172-30-1-15/events.out.tfevents.1731537495.ip-172-30-1-15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8278e0001bf8f870e2b27a982a1a81bb91deb26134f4861132cc92181a742f98
+size 6793

runs/Nov13_23-06-40_ip-172-30-1-15/events.out.tfevents.1731539201.ip-172-30-1-15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b3a3d4c84bac0ac9194d6e62faca3067aa94952678fce05af45b0b225d6528
+size 6773

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f92d208e4850f92603b2d1e0887750aea522d91e5a8bc1995bbd73c48448c34
+oid sha256:947c0980aa95052e981d074c9a21c6cd8733e21cd940920b90f0a06a12275a12
 size 5688