Model save

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # peft-starcoder-lora-a100
 
 This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8163
 
 ## Model description
 
@@ -42,6 +44,23 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 30
 - training_steps: 2000
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0488        | 0.05  | 100  | 0.9203          |
+| 0.766         | 0.1   | 200  | 0.8664          |
+| 0.8261        | 0.15  | 300  | 0.8255          |
+| 0.7837        | 0.2   | 400  | 0.8087          |
+| 0.7211        | 0.25  | 500  | 0.7944          |
+| 0.6909        | 0.3   | 600  | 0.8020          |
+| 0.7019        | 0.35  | 700  | 0.7912          |
+| 0.6232        | 0.4   | 800  | 0.7917          |
+| 0.6041        | 0.45  | 900  | 0.7836          |
+| 0.7069        | 0.5   | 1000 | 0.7867          |
+| 0.5512        | 0.55  | 1100 | 0.8163          |
+
+
 ### Framework versions
 
 - PEFT 0.14.0

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6080df656ac6bc2f2048b935f72e92056955338012deebaf62cd895b1f3be74c
+oid sha256:2fadc89d27c0c726cd7037b7bfe047fad62c860d1585887ea22d6e6edb2d0fcc
 size 22241240