baotnguyen/ncis

README.md

@@ -14,13 +14,13 @@ 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/phdatdt/huggingface/runs/d3ojqo4j)
+[<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/phdatdt/Fine%20tuning%20mistral%207B/runs/bcp8q4u5)
 # ncis
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.4991
-- Accuracy: 0.6325
+- Loss: 1.5884
+- Accuracy: 0.8205
 
 ## Model description
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 19   | 2.5426          | 0.5983   |
-| No log        | 2.0   | 38   | 8.6762          | 0.4444   |
-| No log        | 3.0   | 57   | 0.2207          | 0.9658   |
-| No log        | 4.0   | 76   | 2.1915          | 0.7607   |
-| No log        | 5.0   | 95   | 4.1816          | 0.6496   |
-| No log        | 6.0   | 114  | 4.4624          | 0.6325   |
-| No log        | 7.0   | 133  | 4.4956          | 0.6325   |
-| No log        | 8.0   | 152  | 4.4989          | 0.6325   |
-| No log        | 9.0   | 171  | 4.4991          | 0.6325   |
-| No log        | 10.0  | 190  | 4.4991          | 0.6325   |
+| No log        | 1.0   | 19   | 4.9428          | 0.4786   |
+| No log        | 2.0   | 38   | 4.6067          | 0.6325   |
+| No log        | 3.0   | 57   | 1.0003          | 0.8632   |
+| No log        | 4.0   | 76   | 1.4983          | 0.8376   |
+| No log        | 5.0   | 95   | 1.5749          | 0.8291   |
+| No log        | 6.0   | 114  | 1.5852          | 0.8205   |
+| No log        | 7.0   | 133  | 1.5872          | 0.8205   |
+| No log        | 8.0   | 152  | 1.5881          | 0.8205   |
+| No log        | 9.0   | 171  | 1.5883          | 0.8205   |
+| No log        | 10.0  | 190  | 1.5884          | 0.8205   |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b39fe68229505557e46825cf7f0c7c948b27bb8a86f8e893b6b545b5720d62a8
+oid sha256:50c94f9beb1061b5a465ffb22755c42d961992fe8be2c12a1d4abc7ff3875963
 size 54593240

runs/Jul17_17-34-10_514e4dc42f97/events.out.tfevents.1721237651.514e4dc42f97.33.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32efa9ece8d26d90024fb46ae4f20c403d16cc43ab4b902d68fac046062e60d
+size 8865

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eaf82094e2fa119e9c6788b314112b77db22dec69262dce10d9fc537b0dad04
+oid sha256:16f01a08c55ecfc060eda800bf9f7dbc66243f103854aa02528a0df2e0578541
 size 5112