End of training

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # peft-lora-zencoder15B-personal-copilot
 
 This model is a fine-tuned version of [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3124
 
 ## Model description
 
@@ -44,6 +46,22 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 30
 - training_steps: 1000
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.7534        | 0.1   | 100  | 0.4016          |
+| 0.6715        | 0.2   | 200  | 0.3700          |
+| 0.5283        | 0.3   | 300  | 0.3647          |
+| 0.574         | 0.4   | 400  | 0.3388          |
+| 0.5841        | 0.5   | 500  | 0.3193          |
+| 0.5268        | 0.6   | 600  | 0.3202          |
+| 0.5043        | 0.7   | 700  | 0.3124          |
+| 0.4981        | 0.8   | 800  | 0.3138          |
+| 0.4995        | 0.9   | 900  | 0.3126          |
+| 0.4779        | 1.0   | 1000 | 0.3124          |
+
+
 ### Framework versions
 
 - PEFT 0.7.2.dev0

final_checkpoint/adapter_config.json

@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "c_fc",
-    "c_attn",
+    "q_attn",
     "c_proj",
-    "q_attn"
+    "c_attn"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

final_checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa7bbda47bbce958ade6b3b23cbfcaa26d1e5fe7dcbab547da1000f7511a02b
+oid sha256:fee0979e8d55db1b3e939258da2d0e1f2cf418303d675d10fd4e3ef3dc5443f3
 size 55255584