Model save

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: Qwen/Qwen2.5-7B-Instruct
+base_model: Qwen/Qwen2.5-14B-Instruct
 tags:
 - generated_from_trainer
 library_name: peft
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # robust_llm_r2d2_tom-debug_Qwen2.5-7B-Instruct_lora
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on an unknown dataset.
 
 ## Model description
 
@@ -38,10 +38,10 @@ The following hyperparameters were used during training:
 - eval_batch_size: 2
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 4
+- num_devices: 8
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 16
-- total_eval_batch_size: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - num_epochs: 1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "base_model_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -16,10 +16,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "v_proj",
+    "k_proj",
     "q_proj",
-    "k_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:916deea7e1fc999df6e785e88afe3227a7b77250daeef65cde68ccf8ff619ab9
-size 80770656
+oid sha256:054fd3370c720b1fcc8a362a30b4d9226c219b1d816fc9d8a008a38bdb8d621d
+size 201379120

runs/Feb02_01-49-13_r2d2-devbox-526kp/events.out.tfevents.1738460975.r2d2-devbox-526kp.1829.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0416d226fb80c8b548ec11c2d48b834931f6a7815381007c10fb378535857320
-size 4622
+oid sha256:af79440ab54b24adffc0649e162e3cf0d74cf071a7b0d10c2692b33bd1489f47
+size 4776

runs/Feb02_02-31-29_r2d2-devbox-526kp/events.out.tfevents.1738463538.r2d2-devbox-526kp.5134.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c9d280afedbad93bd14ee7cbef5a98d8bbc166dcea4c53376673701568bec27
+size 4623

step_0/README.md

@@ -1,5 +1,5 @@
 ---
-base_model: Qwen/Qwen2.5-7B-Instruct
+base_model: Qwen/Qwen2.5-14B-Instruct
 library_name: peft
 ---
 
@@ -203,4 +203,11 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 ### Framework versions
 
 
+- PEFT 0.6.1
+## Training procedure
+
+
+### Framework versions
+
+
 - PEFT 0.6.1

step_0/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "base_model_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -16,10 +16,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "v_proj",
+    "k_proj",
     "q_proj",
-    "k_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

step_0/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:916deea7e1fc999df6e785e88afe3227a7b77250daeef65cde68ccf8ff619ab9
-size 80770656
+oid sha256:054fd3370c720b1fcc8a362a30b4d9226c219b1d816fc9d8a008a38bdb8d621d
+size 201379120

step_0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b46f0df35125f293adfdbfb156efdb1968b7dc0752cae97daa96b012f0b3464
+oid sha256:fd29f6ce8baa4403da6138b1ab6401e9f3f3e2e8b1f571f87bed547b2cef427f
 size 5816

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b46f0df35125f293adfdbfb156efdb1968b7dc0752cae97daa96b012f0b3464
+oid sha256:fd29f6ce8baa4403da6138b1ab6401e9f3f3e2e8b1f571f87bed547b2cef427f
 size 5816