Upload configs.yaml with huggingface_hub

configs.yaml

@@ -0,0 +1,42 @@
+assistant_tag: gpt
+bf16: 'True'
+content_tag: value
+cutoff_len: '16384'
+dataloader_num_workers: '8'
+dataloader_persistent_workers: 'True'
+dataloader_pin_memory: 'True'
+dataset: mlfoundations-dev/wikipedia_seed_science
+dataset_dir: ONLINE
+ddp_timeout: '180000000'
+deepspeed: /opt/ml/code/zero3.json
+do_train: 'True'
+enable_liger_kernel: 'True'
+finetuning_type: full
+formatting: sharegpt
+global_batch_size: '96'
+gradient_accumulation_steps: '3'
+hub_model_id: mlfoundations-dev/ds_no_offload_liger_packing_dataloader
+learning_rate: 1e-05
+logging_steps: '1'
+lr_scheduler_type: cosine
+max_samples: '1000000'
+messages: conversations
+model_name_or_path: Qwen/Qwen2.5-7B-Instruct
+neat_packing: 'True'
+num_train_epochs: '3.0'
+output_dir: /opt/ml/model
+overwrite_cache: 'True'
+packing: 'True'
+per_device_train_batch_size: '1'
+plot_loss: 'True'
+preprocessing_num_workers: '16'
+push_to_db: 'True'
+push_to_hub: 'True'
+report_to: wandb
+role_tag: from
+run_name: ds_no_offload_liger_packing_dataloader
+save_strategy: epoch
+stage: sft
+template: qwen25
+user_tag: human
+warmup_ratio: '0.1'