Kartheekb7/peft_phi3.5

README.md

@@ -44,9 +44,13 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- training_steps: 500
+- training_steps: 300
 - mixed_precision_training: Native AMP
 
+### Training results
+
+
+
 ### Framework versions
 
 - PEFT 0.13.1.dev0

adapter_config.json

@@ -16,7 +16,7 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae561b6112b7f2e31a38aa937242d03eeb9d8bfd780d3700caa936eed7adcb26
-size 151012416
+oid sha256:64032f232b90b7240ec45b80517eeb93e002e32f1701edf70268adb90bb88259
+size 37766064

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 4096,
+    "max_length": 200,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85c89bda7fdf50c8461889c9e9cc7d9de55b0c94e5050954e064d397012aef6f
+oid sha256:18e1022b455637d528b58d0b5059aec337aad91414be689a636e1718e4f1bebe
 size 5432