Upload configs.yaml with huggingface_hub

configs.yaml

@@ -0,0 +1,47 @@
+assistant_tag: assistant
+bf16: true
+content_tag: value
+cutoff_len: 16384
+dataloader_num_workers: 4
+dataloader_persistent_workers: true
+dataloader_pin_memory: true
+dataset: /leonardo_work/EUHPC_E03_068/eguha/datasets_cache/mlfoundations-dev/hero_run_2_fix_conversations
+dataset_dir: ONLINE
+ddp_timeout: 180000000
+deepspeed: dcft/train/zero3.json
+do_train: true
+enable_liger_kernel: false
+finetuning_type: full
+flash_attn: sdpa
+formatting: sharegpt
+global_batch_size: 512
+gradient_accumulation_steps: 1
+hub_model_id: mlfoundations-dev/DCFT-hero_run_2_fix_conversations-etash
+include_hp: dcft/train/hp_settings/reasoning_32b_5epoch.yaml
+learning_rate: 8.0e-05
+logging_steps: 1
+lr_scheduler_type: cosine
+messages: conversations
+model_name_or_path: /leonardo_work/EUHPC_E03_068/eguha/models_cache/models--Qwen--Qwen2.5-32B-Instruct/snapshots/5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd/
+neat_packing: true
+num_train_epochs: 5.0
+output_dir: /leonardo_work/EUHPC_E03_068/eguha/checkoints/hero_run_2_fix_conversations
+overwrite_cache: true
+packing: true
+per_device_train_batch_size: 1
+plot_loss: true
+preprocessing_num_workers: 16
+push_to_db: false
+push_to_hub: false
+report_to: wandb
+role_tag: from
+run_name: DCFT-hero_run_2_fix_conversations-etash
+save_steps: 500
+save_strategy: steps
+stage: sft
+template: qwen25
+tokenized_path: /leonardo_work/EUHPC_E03_068/DCFT_shared/datasets/mlfoundations-dev/hero_run_2_fix_conversations_tokenized
+torch_compile: true
+use_unsloth_gc: false
+user_tag: user
+warmup_ratio: 0.1