sujithatz/finbot-modelV2

README.md

@@ -17,6 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 # phi-3-mini-LoRA
 
 This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2990
 
 ## Model description
 
@@ -44,10 +46,13 @@ 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_ratio: 0.1
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.619         | 4.6667 | 70   | 0.2990          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
     "k_proj",
+    "gate_proj",
     "down_proj",
-    "o_proj",
-    "q_proj",
-    "v_proj",
-    "up_proj"
+    "q_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:cd76fdbbed63a80436041d4c3661a32e099f0d39223e7c8d8671f6bb38274dd1
+oid sha256:9683bef0e3f11bbdb5fef4040748cefcdfce22840d306c6861c340871b8d49d2
 size 35668592

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f254e5f41843921593ec646e1bef99c5fb44ba052c05ea1c1df45e790b2efde
+oid sha256:0ce710ba59e50ddc28a07ae112ed2d16849ac7630a3c9206dbc26cb350177409
 size 5432