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 [bigscience/bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.9550
+- Loss: 4.3832
 
 ## Model description
 
@@ -35,27 +35,34 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 0.0002
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.5928        | 1.0   | 829  | 5.0717          |
-| 5.0339        | 2.0   | 1658 | 4.9774          |
-| 4.9752        | 3.0   | 2487 | 4.9550          |
+| 5.0298        | 1.0   | 829  | 4.7124          |
+| 4.681         | 2.0   | 1658 | 4.5977          |
+| 4.6154        | 3.0   | 2487 | 4.5345          |
+| 4.5244        | 4.0   | 3316 | 4.4902          |
+| 4.4751        | 5.0   | 4145 | 4.4582          |
+| 4.4559        | 6.0   | 4974 | 4.4347          |
+| 4.4124        | 7.0   | 5803 | 4.4158          |
+| 4.3982        | 8.0   | 6632 | 4.4015          |
+| 4.3716        | 9.0   | 7461 | 4.3889          |
+| 4.341         | 10.0  | 8290 | 4.3832          |
 
 
 ### Framework versions
 
 - PEFT 0.9.0
-- Transformers 4.38.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- Transformers 4.36.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6e2c94ea47c55c44b0f19ea76090fd8a611672237e6005c91846463b3a0570d
+oid sha256:fdd7563eda7b4c56689a8d510a1ac76ae40e3820c88463a88d650e4197b61651
 size 9444296