Upload configs.yaml with huggingface_hub

configs.yaml

@@ -1,37 +1,39 @@
 assistant_tag: gpt
-bf16: true
+bf16: 'True'
 content_tag: value
-cutoff_len: 16384
-dataloader_num_workers: 4
-dataloader_persistent_workers: true
-dataloader_pin_memory: true
+cutoff_len: '16384'
+dataloader_num_workers: '4'
+dataloader_persistent_workers: 'True'
+dataloader_pin_memory: 'True'
 dataset: mlfoundations-dev/e1_science_longest_qwq_together
 dataset_dir: ONLINE
-ddp_timeout: 180000000
-deepspeed: dcft/train/zero3.json
-do_train: true
-enable_liger_kernel: true
+ddp_timeout: '180000000'
+deepspeed: /opt/ml/code/zero3.json
+do_train: 'True'
+enable_liger_kernel: 'True'
 finetuning_type: full
-global_batch_size: 128
-gradient_accumulation_steps: 4
+formatting: sharegpt
+global_batch_size: '128'
+gradient_accumulation_steps: '4'
 hub_model_id: mlfoundations-dev/e1_science_longest_qwq_together
-learning_rate: 4.0e-05
-logging_steps: 1
+learning_rate: 4e-05
+logging_steps: '1'
 lr_scheduler_type: cosine
 messages: conversations
 model_name_or_path: Qwen/Qwen2.5-7B-Instruct
-num_train_epochs: 5.0
-output_dir: /scratch/08002/gsmyrnis/checkpoints/e1_science_longest_qwq_together
-overwrite_cache: true
-per_device_train_batch_size: 1
-plot_loss: true
-preprocessing_num_workers: 16
-push_to_db: true
-push_to_hub: true
+num_train_epochs: '5.0'
+output_dir: /opt/ml/model
+overwrite_cache: '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: e1_science_longest_qwq_together
 save_strategy: epoch
 stage: sft
 template: qwen25
 user_tag: human
-warmup_ratio: 0.1
+warmup_ratio: '0.1'