End of training

README.md

@@ -123,8 +123,11 @@ The following hyperparameters were used during training:
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 8
+- total_train_batch_size: 16
+- total_eval_batch_size: 4
 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 10
@@ -135,9 +138,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 0.0           | 0.0000 | 1    | nan             |
-| 0.0           | 0.0000 | 3    | nan             |
-| 0.0           | 0.0001 | 6    | nan             |
-| 0.0           | 0.0001 | 9    | nan             |
+| 0.0           | 0.0001 | 3    | nan             |
+| 0.0           | 0.0002 | 6    | nan             |
+| 0.0           | 0.0003 | 9    | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48e5aa0d64488c4c7c9cd4ca5e8fcf03ebe42abe6c98483a22d69c6f3f6c7768
+oid sha256:18d34c08fbf953fd05b18ad005e6a21bba2e99b7f05948ac70b2f17425c518d4
 size 17717130