moushi21
/

agent-bench-alfworld-merged3

Text Generation

text-generation-inference

Model card Files Files and versions

moushi21 commited on 9 days ago

Commit

dfe00a2

·

verified ·

1 Parent(s): ef6a347

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -33,7 +33,7 @@ This model is specialized for **ALFWorld trajectory tasks**, trained to handle m
 - **Format**: Merged Full Weights (bfloat16)
 - **Method**: LoRA fine-tuning (Merged via Unsloth `merge_and_unload`)
 - **Max sequence length**: 4096
-- **Epochs**: 1
 - **Learning rate**: 5e-07
 - **LoRA Parameters during training**: r=64, alpha=128
 - **Platform**: Trained with Unsloth

 - **Format**: Merged Full Weights (bfloat16)
 - **Method**: LoRA fine-tuning (Merged via Unsloth `merge_and_unload`)
 - **Max sequence length**: 4096
+- **Steps**: 600
 - **Learning rate**: 5e-07
 - **LoRA Parameters during training**: r=64, alpha=128
 - **Platform**: Trained with Unsloth