minimini99/phi3-lora-test

README.md

@@ -14,10 +14,12 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/jongmin4422/Phi3-mini-ft-python-code/runs/m45sqgct)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/jongmin4422/Phi3-mini-ft-python-code/runs/zwsclld3)
 # 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: 1.2828
 
 ## Model description
 
@@ -45,10 +47,14 @@ 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: 100
 
 ### Training results
 
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 1.8947        | 36.3636 | 100  | 1.3447          |
+| 1.2021        | 72.7273 | 200  | 1.2828          |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e11053eab17375c76ad4ffd1cbd9c698b26b7d72ff6ea1b0781ff9feb9f6dd
+oid sha256:b56250c1d445672e33739f90290fe3313d10728e8e71bd17e19af78b4e4d9dde
 size 17842848

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c16ec886ade37376dcd6f12d9f6b72a2632a574dcc6d3a9283c2f6b1dd06e78c
+oid sha256:63201426a51d343157d04f71be0c65aa11fe8df67638436bed9ff0f6ec6ddf2e
 size 5368