End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2424
+- Loss: 0.2105
 
 ## Model description
 
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
 - total_eval_batch_size: 16
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -56,6 +56,11 @@ The following hyperparameters were used during training:
 | 0.3256        | 0.4001 | 1258 | 0.2849          |
 | 0.2909        | 0.6002 | 1887 | 0.2562          |
 | 0.2536        | 0.8003 | 2516 | 0.2424          |
+| 0.2435        | 1.0003 | 3145 | 0.2343          |
+| 0.2396        | 1.2004 | 3774 | 0.2342          |
+| 0.2342        | 1.4004 | 4403 | 0.2229          |
+| 0.2175        | 1.6005 | 5032 | 0.2162          |
+| 0.2144        | 1.8006 | 5661 | 0.2105          |
 
 
 ### Framework versions

adapter_config.json

@@ -23,8 +23,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_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 sha256:8f69867821b1b0e74654974465611a29e9041ec85fe72d4c9ab469b8931e214a
+oid sha256:a6312d95a01cc4db50a00ade14fc2dce072339b2e4fc91d0d6523afe8b1aa8dc
 size 6304096

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a77e41ba7390d63e904702f19dc81f4c9e1287298b794e3a46f5296f3156a33
+oid sha256:913f56bc3317ac3c0dc3fd469f0574f3f7c35ce87b809b8220e3bb53492c9caa
 size 5496