End of training

README.md

@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1495
-- Accuracy: 0.342
-- F1: 0.3287
+- Loss: 1.9589
+- Accuracy: 0.372
+- F1: 0.3552
 
 ## Model description
 
@@ -54,14 +54,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 4.1982        | 1.0   | 250  | 4.4680          | 0.2805   | 0.2586 |
-| 2.5719        | 2.0   | 500  | 2.4286          | 0.3145   | 0.3057 |
-| 1.8911        | 3.0   | 750  | 2.1495          | 0.342    | 0.3287 |
+| 2.887         | 1.0   | 250  | 2.9863          | 0.2865   | 0.2788 |
+| 2.4198        | 2.0   | 500  | 2.1868          | 0.345    | 0.3360 |
+| 1.7684        | 3.0   | 750  | 1.9589          | 0.372    | 0.3552 |
 
 
 ### Framework versions
 
-- PEFT 0.8.0
+- PEFT 0.8.2.dev0
 - Transformers 4.38.0.dev0
 - Pytorch 2.1.0+cu121
 - Datasets 2.16.0

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2be8b921c57c23a9e0ae62f901320fe9ef30945910115f8974c28c3fd3fca6f0
+oid sha256:91ba0e782eba4a2e080e97e3b35d662b2add3363949ecc2a1e8e9ddf3b5fcd78
 size 6323232

runs/Jan31_10-47-41_38264010b883/events.out.tfevents.1706698073.38264010b883.173.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b4612169b3cf868ff81557fcf859ed403b0c88089f05353af886f3a02e3d4f3
-size 83713
+oid sha256:b8efc46484928235f1f9169df1c5bdac2ae5bae29eac5c4bbaa6e8175cb58b75
+size 124055

runs/Jan31_10-47-41_38264010b883/events.out.tfevents.1706699477.38264010b883.173.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:252484aa8b658de41739007543fc228d94eb32c88265c5b6bd243948cfa21f50
+size 457