Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:943098d8c73dfce4549b6f6d316bcbde820346c79c1a7fec0b3481003e157c04
+oid sha256:1cfc35f90ef6d5aac8099351ed95e482789a3930ab9364744ee737be0e9fe7bd
 size 988097824

training_artifacts/README.md

@@ -12,5 +12,5 @@ This directory contains the training configuration and logs for this model.
 ## Job Information
 
 - Job Name: lf_torch_test__interactive
-- Timestamp: 2025-10-22 20:54:32 UTC
+- Timestamp: 2025-10-22 21:18:35 UTC
 - Execution Mode: Local

training_artifacts/hydra_config.yaml

@@ -167,13 +167,13 @@ lora:
   dropout: 0.05
   target: all
 dataset:
-  name: my_custom_sft
+  name: my_custom_sft9
   dir: null
   info_json: null
   template: default
   cutoff_len: 8096
   val_size: 0.1
-  hf_hub_url: TAUR-dev/D-SFT_C-sft_exp_AT_pvv2__fixed-sft-data
+  hf_hub_url: TAUR-dev/D-SFT_C-BASELINE_r1_distillation-sft-data
   formatting: sharegpt
   ranking: false
   subset: null

training_artifacts/train_config.yaml

@@ -13,7 +13,7 @@ gradient_accumulation_steps: 1
 gradient_checkpointing: true
 model_name_or_path: Qwen/Qwen2.5-0.5B
 finetuning_type: lora
-dataset: my_custom_sft
+dataset: my_custom_sft9
 dataset_dir: /scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory/data
 template: default
 cutoff_len: 8096
@@ -23,3 +23,6 @@ lora_alpha: 16
 lora_dropout: 0.05
 lora_target: all
 output_dir: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints
+preprocessing_num_workers: 1
+disable_tqdm: false
+overwrite_cache: true