amang1802
/

Llama3.2-1B-summary-length-exp6

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Llama3.2-1B-summary-length-exp6 / README.md

amang1802's picture

Update README.md

7ee374f verified about 2 months ago

|

history blame contribute delete

308 Bytes

metadata

library_name: transformers
tags: []

Model Card for Model ID

Summary Length PPO experiment #5
No KL divergence in loss

Model Details

Dataset size: 1024
Epochs: 1
Batch Size: 4 * 4 (w/ 4 GPUs) * 8 (w/ Gradient Accumulation)

Optimizer args: Torch AdamW default, except

LR = 0.00001