luis_model

README.md

@@ -19,6 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 # Luis_Park
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1467
 
 ## Model description
 
@@ -41,8 +43,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 1
 - eval_batch_size: 1
 - seed: 42
-- gradient_accumulation_steps: 25
-- total_train_batch_size: 25
+- gradient_accumulation_steps: 15
+- total_train_batch_size: 15
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - num_epochs: 2
@@ -50,6 +52,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.8955 | 4    | 1.1497          |
+| 1.1263        | 1.7910 | 8    | 1.1467          |
 
 
 ### Framework versions

adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "v_proj",
     "k_proj",
-    "o_proj"
+    "o_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3964b66415083461d71aef914bf6f54bd7a75979b4270fac628ccc5ef5175e15
+oid sha256:f6c2172d04e3bd263af8b57092464288d05e3332fd3bb2ccc4aa4c9698140bc7
 size 218138576

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5fde48e5136c307e594c570c6e625840ee1180faf484e1329b2b74b05e716e
+oid sha256:5ff2b9be92f95c47ef86e28e6c9c7ef50aa5bce1ed608c77768a9bdb0eb3c66c
 size 5112