amiguel
/

Finetune_on_Qwen1.5-0.5B

Text Generation

Generated from Trainer

text-generation-inference

4-bit precision

Model card Files Files and versions Community

amiguel commited on 5 days ago

Commit

db19b25

·

verified ·

1 Parent(s): 7e33272

End of training

Files changed (2) hide show

README.md +2 -2
model.safetensors +2 -2

README.md CHANGED Viewed

@@ -33,7 +33,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 2
 ### Training results

 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 1e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - total_train_batch_size: 16
 - optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
+- num_epochs: 5
 ### Training results

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dc169127908ae6983a35980fe7e85cbbad2f9eb41348401058d0b5d456382eb
-size 782204672

 version https://git-lfs.github.com/spec/v1
+oid sha256:36ea2f9b71f994435c0a2cb57178c116c6030a6487b65ba5e386a4c526f9be0a
+size 782204669