BUT-FIT
/

CSTinyLLama-1.2B-RAGsum

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

mfajcik commited on Dec 6, 2024

Commit

026855a

·

verified ·

1 Parent(s): 6dea900

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ Training configuration
 gradient_checkpointing: true
 learning_rate: 1e-5
 max_grad_norm: 5.0
-num_epochs: 4 # 2740 steps in total
 optimizer: adamw_torch
 lr_scheduler: cosine
 batch_size: 128

 gradient_checkpointing: true
 learning_rate: 1e-5
 max_grad_norm: 5.0
+num_epochs: 6 # 4110 steps in total
 optimizer: adamw_torch
 lr_scheduler: cosine
 batch_size: 128