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 [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2545
+- Loss: 0.1670
 
 ## Model description
 
@@ -44,33 +44,14 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 30
-- training_steps: 2000
+- training_steps: 150
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.1617        | 0.05  | 100  | 0.1605          |
-| 0.1147        | 0.1   | 200  | 0.1518          |
-| 0.087         | 0.15  | 300  | 0.1739          |
-| 0.0738        | 0.2   | 400  | 0.2029          |
-| 0.0707        | 0.25  | 500  | 0.2067          |
-| 0.0655        | 0.3   | 600  | 0.2156          |
-| 0.0632        | 0.35  | 700  | 0.2138          |
-| 0.0613        | 0.4   | 800  | 0.2285          |
-| 0.058         | 0.45  | 900  | 0.2292          |
-| 0.0582        | 0.5   | 1000 | 0.2417          |
-| 0.0545        | 0.55  | 1100 | 0.2513          |
-| 0.0531        | 0.6   | 1200 | 0.2393          |
-| 0.0527        | 0.65  | 1300 | 0.2526          |
-| 0.0518        | 0.7   | 1400 | 0.2541          |
-| 0.0511        | 0.75  | 1500 | 0.2407          |
-| 0.0501        | 0.8   | 1600 | 0.2527          |
-| 0.0498        | 0.85  | 1700 | 0.2511          |
-| 0.0499        | 0.9   | 1800 | 0.2549          |
-| 0.05          | 0.95  | 1900 | 0.2557          |
-| 0.0492        | 1.0   | 2000 | 0.2545          |
+| 0.1662        | 0.67  | 100  | 0.1670          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de6ce0a7fc08a4d8bfb903207840df689b68e60954d2521f06c5c4e13784b1db
+oid sha256:d6385fd2bbda25ab5eedde86c08d4b0098a5abd609a90bbf443d31fe634d5d22
 size 88891680

final_checkpoint/adapter_config.json

@@ -20,8 +20,8 @@
   "revision": null,
   "target_modules": [
     "c_fc",
-    "c_attn",
     "c_proj",
+    "c_attn",
     "q_attn"
   ],
   "task_type": "CAUSAL_LM"

final_checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cd04770c38477828c7612bee4ff6d4038cd4b74b2deda77faa63f6d355c9f95
+oid sha256:d6385fd2bbda25ab5eedde86c08d4b0098a5abd609a90bbf443d31fe634d5d22
 size 88891680

runs/Jan30_10-32-47_hgx049.scc.idea/events.out.tfevents.1706581988.hgx049.scc.idea.1712895.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:159d188379da99dc4f5b4258ab7c26fdb2f8bc56a59c94b43f91a1465d865dd7
-size 6052
+oid sha256:c4af7a561b5ad03bc9cd2a7ca2ff82b963da194cdf0c57ecf0a4d82a6ea89d8a
+size 6785