End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [obrmmk/tinycodellama-jp-1.3b-1k](https://huggingface.co/obrmmk/tinycodellama-jp-1.3b-1k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9164
+- Loss: 1.3754
 
 ## Model description
 
@@ -43,15 +43,11 @@ 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_steps: 50
-- training_steps: 200
+- training_steps: 50
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.7064        | 0.16  | 100  | 1.0144          |
-| 0.6659        | 0.33  | 200  | 0.9164          |
 
 
 ### Framework versions

adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "q_proj",
     "k_proj",
-    "o_proj",
-    "v_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ff97b54ab432c2159542a95f3c9553611cbe9e4e6ff7302bfbaf64bd7da0b0
+oid sha256:ffed5f8ea0860d188317af6c76611724acdd5e3d277fffefaead7c24524f57f4
 size 4920