Model-text-generation

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.6650
+- Loss: 3.6440
 
 ## Model description
 
@@ -45,15 +45,18 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 2
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.6573        | 1.0   | 984  | 3.6703          |
-| 3.6659        | 2.0   | 1968 | 3.6650          |
+| 3.6532        | 1.0   | 984  | 3.6656          |
+| 3.6525        | 2.0   | 1968 | 3.6521          |
+| 3.6304        | 3.0   | 2953 | 3.6462          |
+| 3.6281        | 4.0   | 3937 | 3.6445          |
+| 3.6389        | 5.0   | 4920 | 3.6440          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74cda05cc88960d1602906b18bfda0952b59110fd15aeefd752e342d7b4852b9
+oid sha256:04cd16fff0c4fdad2a74f791c965c7be01b1d7df620a3b653fbd8f2ac2fd5796
 size 25173000

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55b17cf570a213fa193c9a52d5aba88eda9ea26d949983b16dce11342e2f413a
+oid sha256:f84c3d2b2ba808076cff8036502c3bcb871aea1652c94a6c8ca776fe0978d1c4
 size 4283