sujithatz/finbot-transofrmer-based-phi3.5_adapter

README.md

@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 90
+- training_steps: 40
 
 ### Training results
 

adapter_config.json

@@ -23,10 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "down_proj",
     "gate_up_proj",
-    "o_proj",
-    "qkv_proj"
+    "qkv_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07f56375e6cce0d9c0438b48860300a5fb4928e1613e15ea2ffd123ca4e0f2fb
+oid sha256:b80404a3a2d36415f7078686ffa4c6b502772e8282234b557cf72ea50b2078b5
 size 100697728

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 300,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0e2d4fdfa338331d313dd64d51a403616f18a6a2dd45381ee57bc1641693d1c
+oid sha256:b0a2be6a1a67e267ee48988636890206a6b852bcb9df9d4ce59bc67b3f8b0854
 size 5432