avikmall/imessages2

README.md

@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 5
-- training_steps: 500
+- training_steps: 750
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -55,7 +55,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.11.1
-- Transformers 4.41.2
+- Transformers 4.42.3
 - Pytorch 2.3.0+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
-    "gate_proj",
-    "up_proj",
-    "k_proj",
-    "v_proj",
     "o_proj",
+    "k_proj",
+    "up_proj",
     "down_proj",
+    "gate_proj",
+    "v_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98100288c15f0853559d6aad24deda4004e70eae7a1e6bfbb4a665b3bdb6465a
+oid sha256:58ae3d107358585ad41ad812404e25562ee5992c38979d2fc1759c6c36f279b2
 size 167832240

runs/Jul04_15-45-20_6278aa578ff7/events.out.tfevents.1720107939.6278aa578ff7.609.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58dc12abd00a23535671cc7c6af8dcb8519133fbc99235403c9f416e861e94b8
+size 163670

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f15210dddf599e71cdab2c8f6cf907b01270ee863e4a3fa186103c41c53f5e
+oid sha256:114a101df75e33b870a428acf00bdf874a408dd58d386358ae6a0664aff27d83
 size 5368