diff --git "a/training_artifacts/logs/pipeline_cleaned.txt" "b/training_artifacts/logs/pipeline_cleaned.txt"
--- "a/training_artifacts/logs/pipeline_cleaned.txt"
+++ "b/training_artifacts/logs/pipeline_cleaned.txt"
@@ -7839,11 +7839,15 @@ Setting OMP_NUM_THREADS environment variable for each process to be 1 in default
   warnings.warn(
 /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
   warnings.warn(
-/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
-  import pkg_resources
-/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
-  import pkg_resources
-[INFO|2025-10-22 17:23:38] llamafactory.hparams.parser:143 >> Set `ddp_find_unused_parameters` to False in DDP training since LoRA is enabled.
+
+*****************************************
+Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
+*****************************************
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
+  warnings.warn(
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
+  warnings.warn(
+et `ddp_find_unused_parameters` to False in DDP training since LoRA is enabled.
 [INFO|2025-10-22 17:23:38] llamafactory.hparams.parser:423 >> Process rank: 0, world size: 4, device: cuda:0, distributed training: True, compute dtype: torch.float16
 [INFO|2025-10-22 17:23:38] llamafactory.hparams.parser:423 >> Process rank: 1, world size: 4, device: cuda:1, distributed training: True, compute dtype: torch.float16
 [INFO|tokenization_utils_base.py:2095] 2025-10-22 17:23:38,584 >> loading file vocab.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/vocab.json
@@ -7920,19 +7924,16 @@ Setting OMP_NUM_THREADS environment variable for each process to be 1 in default
 [INFO|tokenization_utils_base.py:2095] 2025-10-22 17:23:39,011 >> loading file chat_template.jinja from cache at None
 [INFO|tokenization_utils_base.py:2364] 2025-10-22 17:23:39,177 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
 [INFO|2025-10-22 17:23:39] llamafactory.data.loader:143 >> Loading dataset TAUR-dev/D-SFT_C-sft_exp_AT_pvv2__fixed-sft-data...
-Converting format of dataset: 100%|| 54000/54000 [00:00<?, ? examples/s]Converting format of dataset: 56506 examples [00:00, 24952.40 examples/s]         Converting format of dataset: 59043 examples [00:00, 25195.44 examples/s]Converting format of dataset: 61801 examples [00:00, 26279.56 examples/s]Converting format of dataset: 65717 examples [00:00, 25622.99 examples/s]Converting format of dataset: 68428 examples [00:00, 25496.50 examples/s]Converting format of dataset: 71000 examples [00:00, 25308.97 examples/s]Converting format of dataset: 74435 examples [00:00, 18413.77 examples/s]Converting format of dataset: 77000 examples [00:01, 19909.90 examples/s]Converting format of dataset: 79911 examples [00:01, 22105.66 examples/s]Converting format of dataset: 82438 examples [00:01, 22901.93 examples/s]Converting format of dataset: 85000 examples [00:01, 23422.51 examples/s]Converting format of dataset: 87846 examples [00:01, 24801.96 examples/s]Converting format of dataset: 90442 examples [00:01, 25019.10 examples/s]Converting format of dataset: 94424 examples [00:01, 25584.61 examples/s]Converting format of dataset: 98414 examples [00:01, 25890.02 examples/s]Converting format of dataset: 102444 examples [00:02, 26079.45 examples/s]Converting format of dataset: 106373 examples [00:02, 26078.84 examples/s]Converting format of dataset: 108000 examples [00:03, 17701.41 examples/s]
-/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py:4876: UserWarning: barrier(): using the device under current context. You can specify `device_id` in `init_process_group` to mute this warning.
-  warnings.warn(  # warn only once
-[rank0]:[W1022 17:23:42.608673411 ProcessGroupNCCL.cpp:5068] Guessing device ID based on global rank. This can cause a hang if rank to GPU mapping is heterogeneous. You can specify device_id in init_process_group()
-gl064:2409682:2409682 [0] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ibs
-gl064:2409682:2409682 [0] NCCL INFO Bootstrap: Using ibs3:10.0.5.0<0>
-gl064:2409682:2409682 [0] NCCL INFO cudaDriverVersion 13000
-gl064:2409682:2409682 [0] NCCL INFO NCCL version 2.27.5+cuda12.9
-gl064:2409682:2409682 [0] NCCL INFO Comm config Blocking set to 1
-gl064:2409683:2409683 [1] NCCL INFO cudaDriverVersion 13000
-gl064:2409683:2409683 [1] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ibs
-gl064:2409683:2409683 [1] NCCL INFO Bootstrap: Using ibs3:10.0.5.0<0>
-gl064:2409683:2409683 [1] NCCL INFO NCCL version 2.27.5+cuda12.9
+Converting format of dataset: 100%|| 54000/54000 [00:00<?, ? examples/s]Converting format of dataset: 56506 examples [00:00, 24952.40 examples/s]         Converting format of dataset: 59043 examples [00:00, 25195.44 examples/s]Converting format of dataset: 61801 examples [00:00, 26279.56 examples/s]Converting format of dataset: 65717 examples [00:00, 25622.99 examples/s]Converting format of dataset: 68428 examples [00:00, 25496.50 examples/s]Converting format of dataset: 71000 examples [00:00, 25308.97 examples/s]Converting format of dataset: 74435 examples [00:00, 18413.77 examples/s]/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
+  import pkg_resources
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
+  import pkg_resources
+[INFO|2025-10-22 17:23:41] llamafactory.hparams.parser:143 >> Set `ddp_find_unused_parameters` to False in DDP training since LoRA is enabled.
+[INFO|2025-10-22 17:23:41] llamafactory.hparams.parser:423 >> Process rank: 3, world size: 4, device: cuda:1, distributed training: True, compute dtype: torch.float16
+[INFO|2025-10-22 17:23:41] llamafactory.hparams.parser:423 >> Process rank: 2, world size: 4, device: cuda:0, distributed training: True, compute dtype: torch.float16
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 17:23:42,037 >> loading file vocab.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/vocab.json
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 17:23:42,038 >> loading file merges.txt from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/merges.txt
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 17:23:42,038 >> loading file tokenizer.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26909683 [1] NCCL INFO NCCL version 2.27.5+cuda12.9
 gl064:2409683:2409683 [1] NCCL INFO Comm config Blocking set to 1
 gl064:2409682:2409720 [0] NCCL INFO NET/Plugin: Could not find: libnccl-net.so. 
 gl064:2409683:2409721 [1] NCCL INFO NET/Plugin: Could not find: libnccl-net.so. 
@@ -7994,7 +7995,25 @@ gl064:2409683:2409735 [1] NCCL INFO Channel 01/0 : 1[1] -> 2[0] [send] via NET/I
 gl064:2409683:2409738 [1] NCCL INFO [Proxy Progress] Device 1 CPU core 15
 gl064:2409683:2409735 [1] NCCL INFO Connected all rings, use ring PXN 0 GDR 0
 gl064:2409682:2409736 [0] NCCL INFO Connected all rings, use ring PXN 0 GDR 0
-Running tokenizer on dataset: 100%|| 54000/54000 [00:00<?, ? examples/s]Running tokenizer on dataset: 55000 examples [00:02, 381.21 examples/s]           Running tokenizer on dataset: 56000 examples [00:05, 383.21 examples/s]Running tokenizer on dataset: 57000 examples [00:07, 379.29 examples/s]Running tokenizer on dataset: 58000 examples [00:10, 384.32 examples/s]Running tokenizer on dataset: 59000 examples [00:13, 377.98 examples/s]Running tokenizer on dataset: 60000 examples [00:15, 383.78 examples/s]Running tokenizer on dataset: 61000 examples [00:18, 381.79 examples/s]Running tokenizer on dataset: 62000 examples [00:21, 377.11 examples/s]Running tokenizer on dataset: 63000 examples [00:23, 377.18 examples/s]NCCL INFO Bootstrap timings total 2.765264 (create 0.000027, send 0.000355, recv 0.001108, ring 0.001354, delay 0.000000)
+Running tokenizer on dataset: 100%|| 54000/54000 [00:00<?, ? examples/s]Running tokenizer on dataset: 55000 examples [00:02, 381.21 examples/s]           Running tokenizer on dataset: 56000 examples [00:05, 383.21 examples/s]Running tokenizer on dataset: 57000 examples [00:07, 379.29 examples/s]Running tokenizer on dataset: 58000 examples [00:10, 384.32 examples/s]Running tokenizer on dataset: 59000 examples [00:13, 377.98 examples/s]Running tokenizer on dataset: 60000 examples [00:15, 383.78 examples/s]Running tokenizer on dataset: 61000 examples [00:18, 381.79 examples/s]Running tokenizer on dataset: 62000 examples [00:21, 377.11 examples/s]Running tokenizer on dataset: 63000 examples [00:23, 377.18 examples/s]amples/s]Converting format of dataset: 107795 examples [00:02, 26163.31 examples/s]Converting format of dataset: 108000 examples [00:02, 19835.90 examples/s]
+[rank2]:[W1022 17:23:45.497008806 ProcessGroupNCCL.cpp:5068] Guessing device ID based on global rank. This can cause a hang if rank to GPU mapping is heterogeneous. You can specify device_id in init_process_group()
+gl065:3813031:3813031 [0] NCCL INFO cudaDriverVersion 13000
+gl065:3813031:3813031 [0] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ibs
+gl065:3813031:3813031 [0] NCCL INFO Bootstrap: Using ibs3:10.0.5.1<0>
+gl065:3813031:3813031 [0] NCCL INFO NCCL version 2.27.5+cuda12.9
+gl065:3813031:3813031 [0] NCCL INFO Comm config Blocking set to 1
+gl065:3813031:3813151 [0] NCCL INFO NET/Plugin: Could not find: libnccl-net.so. 
+gl065:3813031:3813151 [0] NCCL INFO NCCL_IB_DISABLE set by environment to 0.
+gl065:3813031:3813151 [0] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ibs
+gl065:3813031:3813151 [0] NCCL INFO NCCL_IB_HCA set to mlx5
+gl065:3813031:3813151 [0] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [RO]; OOB ibs3:10.0.5.1<0>
+gl065:3813031:3813151 [0] NCCL INFO Initialized NET plugin IB
+gl065:3813031:3813151 [0] NCCL INFO Assigned NET plugin IB to comm
+gl065:3813031:3813151 [0] NCCL INFO Using network IB
+gl065:3813031:3813151 [0] NCCL INFO ncclCommInitRankConfig comm 0x1376a6e0 rank 2 nranks 4 cudaDev 0 nvmlDev 0 busId 47000 commId 0xdc96a09c11393e3 - Init START
+gl065:3813032:3813142 [1] NCCL INFO RAS client listening socket at ::1<28028>
+gl065:3813031:3813151 [0] NCCL INFO RAS client listening socket at ::1<28028>
+gl065:3813032:3813142 [1] NCCL INFO Bootstrap timings total 2.765264 (create 0.000027, send 0.000355, recv 0.001108, ring 0.001354, delay 0.000000)
 gl065:3813031:3813151 [0] NCCL INFO Bootstrap timings total 0.014762 (create 0.000029, send 0.000443, recv 0.001086, ring 0.001169, delay 0.000000)
 gl065:3813032:3813142 [1] NCCL INFO Setting affinity for GPU 1 to 0-31
 gl065:3813031:3813151 [0] NCCL INFO Setting affinity for GPU 0 to 0-31
@@ -8030,7 +8049,7 @@ gl065:3813032:3813161 [1] NCCL INFO Channel 01/0 : 3[1] -> 0[0] [send] via NET/I
 gl065:3813032:3813163 [1] NCCL INFO [Proxy Progress] Device 1 CPU core 28
 gl065:3813031:3813160 [0] NCCL INFO Connected all rings, use ring PXN 0 GDR 0
 gl065:3813032:3813161 [1] NCCL INFO Connected all rings, use ring PXN 0 GDR 0
-Running tokenizer on dataset: 100%|| 54000/54000 [00:00<?, ? examples/s]Running tokenizer on dataset: 55000 examples [00:02, 383.46 examples/s]           Running tokenizer on dataset: 56000 examples [00:05, 384.43 examples/s]Running tokenizer on dataset: 57000 examples [00:07, 380.44 examples/s]Running tokenizer on dataset: 58000 examples [00:10, 386.60 examples/s]Running tokenizer on dataset: 59000 examples [00:13, 379.68 examples/s]Running tokenizer on dataset: 60000 examples [00:15, 383.63 examples/s]Running tokenizer on dataset: 61000 examples [00:18, 381.30 examples/s]Running tokenizer on dataset: 62000 examples [00:21, 378.17 examples/s]Running tokenizer on dataset: 63000 examples [00:23, 378.29 examples/s]Running tokenizer on dataset: 64000 examples [00:26, 377.59 examples/s]Running tokenizer on dataset: 65000 examples [00:28, 379.11 examples/s]Running tokenizer on dataset: 66000 examples [00:31, 378.79 examples/s]Running tokenizer on dataset: 67000 examples [00:34, 380.48 examples/s]Running tokenizer on dataset: 68000 examples [00:36, 382.52 examples/s]Running tokenizer on dataset: 69000 examples [00:39, 380.15 examples/s]Running tokenizer on dataset: 70000 examples [00:42, 384.24 examples/s]Running tokenizer on dataset: 71000 examples [00:44, 381.38 examples/s]Running tokenizer on dataset: 72000 examples [00:47, 380.47 examples/s]Running tokenizer on dataset: 73000 examples [00:50, 377.72 examples/s]Running tokenizer on dataset: 74000 examples [00:52, 379.71 examples/s]Running tokenizer on dataset: 75000 examples [00:55, 378.57 examples/s]Running tokenizer on dataset: 76000 examples [00:57, 377.41 examples/s]Running tokenizer on dataset: 77000 examples [01:00, 380.88 examples/s]Running tokenizer on dataset: 78000 examples [01:03, 371.78 examples/s]Running tokenizer on dataset: 79000 examples [01:05, 376.52 examples/s]Running tokenizer on dataset: 80000 examples [01:08, 377.27 examples/s]Running tokenizer on dataset: 81000 examples [01:11, 376.67 examples/s]Running tokenizer on dataset: 82000 examples [01:13, 379.51 examples/s]Running tokenizer on dataset: 83000 examples [01:16, 379.42 examples/s]Running tokenizer on dataset: 84000 examples [01:19, 382.57 examples/s]Running tokenizer on dataset: 85000 examples [01:21, 380.28 examples/s]Running tokenizer on dataset: 86000 examples [01:24, 380.09 examples/s]Running tokenizer on dataset: 87000 examples [01:26, 379.76 examples/s]Running tokenizer on dataset: 88000 examples [01:29, 384.36 examples/s]Running tokenizer on dataset: 89000 examples [01:32, 382.64 examples/s]Running tokenizer on dataset: 90000 examples [01:34, 384.34 examples/s]Running tokenizer on dataset: 91000 examples [01:37, 384.94 examples/s]Running tokenizer on dataset: 92000 examples [01:39, 385.98 examples/s]Running tokenizer on dataset: 93000 examples [01:42, 381.24 examples/s]Running tokenizer on dataset: 94000 examples [01:45, 382.69 examples/s]Running tokenizer on dataset: 95000 examples [01:47, 382.80 examples/s]Running tokenizer on dataset: 96000 examples [01:50, 377.51 examples/s]Running tokenizer on dataset: 97000 examples [01:53, 375.05 examples/s]Running tokenizer on dataset: 98000 examples [01:55, 375.18 examples/s]Running tokenizer on dataset: 99000 examples [01:58, 377.27 examples/s]Running tokenizer on dataset: 100000 examples [02:01, 380.03 examples/s]Running tokenizer on dataset: 101000 examples [02:03, 381.19 examples/s]Running tokenizer on dataset: 102000 examples [02:06, 379.07 examples/s]Running tokenizer on dataset: 103000 examples [02:09, 377.06 examples/s]Running tokenizer on dataset: 104000 examples [02:11, 380.79 examples/s]Running tokenizer on dataset: 105000 examples [02:14, 380.50 examples/s]Running tokenizer on dataset: 106000 examples [02:16, 378.94 examples/s]Running tokenizer on dataset: 107000 examples [02:19, 376.66 examples/s]Running tokenizer on dataset: 108000 examples [02:22, 348.45 examples/s]Running tokenizer on dataset: 108000 examples [02:23, 377.00 examples/s]
+Running tokenizer on dataset: 100%|| 54000/54000 [00:00<?, ? examples/s]Running tokenizer on dataset: 55000 examples [00:02, 383.46 examples/s]           Running tokenizer on dataset: 56000 examples [00:05, 384.43 examples/s]Running tokenizer on dataset: 57000 examples [00:07, 380.44 examples/s]Running tokenizer on dataset: 58000 examples [00:10, 386.60 examples/s]Running tokenizer on dataset: 59000 examples [00:13, 379.68 examples/s]Running tokenizer on dataset: 60000 examples [00:15, 383.63 examples/s]Running tokenizer on dataset: 61000 examples [00:18, 381.30 examples/s]Running tokenizer on dataset: 62000 examples [00:21, 378.17 examples/s]Running tokenizer on dataset: 63000 examples [00:23, 378.29 examples/s]Running tokenizer on dataset: 64000 examples [00:26, 378.12 examples/s]Running tokenizer on dataset: 65000 examples [00:28, 378.05 examples/s]Running tokenizer on dataset: 66000 examples [00:31, 377.80 examples/s]Running tokenizer on dataset: 67000 examples [00:34, 379.32 examples/s]Running tokenizer on dataset: 68000 examples [00:36, 381.73 examples/s]Running tokenizer on dataset: 69000 examples [00:39, 379.36 examples/s]Running tokenizer on dataset: 70000 examples [00:41, 383.70 examples/s]Running tokenizer on dataset: 71000 examples [00:44, 380.99 examples/s]Running tokenizer on dataset: 72000 examples [00:47, 380.47 examples/s]Running tokenizer on dataset: 73000 examples [00:49, 377.80 examples/s]Running tokenizer on dataset: 74000 examples [00:52, 380.66 examples/s]Running tokenizer on dataset: 75000 examples [00:55, 379.44 examples/s]Running tokenizer on dataset: 76000 examples [00:57, 378.39 examples/s]Running tokenizer on dataset: 77000 examples [01:00, 381.56 examples/s]Running tokenizer on dataset: 78000 examples [01:03, 372.00 examples/s]Running tokenizer on dataset: 79000 examples [01:05, 376.38 examples/s]Running tokenizer on dataset: 80000 examples [01:08, 377.21 examples/s]Running tokenizer on dataset: 81000 examples [01:11, 376.02 examples/s]Running tokenizer on dataset: 82000 examples [01:13, 379.32 examples/s]Running tokenizer on dataset: 83000 examples [01:16, 379.13 examples/s]Running tokenizer on dataset: 84000 examples [01:18, 381.91 examples/s]Running tokenizer on dataset: 85000 examples [01:21, 379.37 examples/s]Running tokenizer on dataset: 86000 examples [01:24, 379.49 examples/s]Running tokenizer on dataset: 87000 examples [01:26, 378.04 examples/s]Running tokenizer on dataset: 88000 examples [01:29, 382.82 examples/s]Running tokenizer on dataset: 89000 examples [01:32, 368.61 examples/s]Running tokenizer on dataset: 90000 examples [01:35, 374.11 examples/s]Running tokenizer on dataset: 91000 examples [01:37, 377.71 examples/s]Running tokenizer on dataset: 92000 examples [01:40, 380.98 examples/s]Running tokenizer on dataset: 93000 examples [01:42, 377.89 examples/s]Running tokenizer on dataset: 94000 examples [01:45, 380.36 examples/s]Running tokenizer on dataset: 95000 examples [01:48, 380.56 examples/s]Running tokenizer on dataset: 96000 examples [01:50, 378.09 examples/s]Running tokenizer on dataset: 97000 examples [01:53, 374.76 examples/s]Running tokenizer on dataset: 98000 examples [01:56, 374.19 examples/s]Running tokenizer on dataset: 99000 examples [01:58, 375.94 examples/s]Running tokenizer on dataset: 100000 examples [02:01, 378.60 examples/s]Running tokenizer on dataset: 101000 examples [02:04, 379.68 examples/s]Running tokenizer on dataset: 102000 examples [02:06, 378.20 examples/s]Running tokenizer on dataset: 103000 examples [02:09, 376.01 examples/s]Running tokenizer on dataset: 104000 examples [02:11, 379.80 examples/s]Running tokenizer on dataset: 105000 examples [02:14, 379.64 examples/s]Running tokenizer on dataset: 106000 examples [02:17, 378.08 examples/s]Running tokenizer on dataset: 107000 examples [02:19, 375.63 examples/s]Running tokenizer on dataset: 108000 examples [02:22, 374.19 examples/s]Running tokenizer on dataset: 108000 examples [02:23, 376.01 examples/s]
 training example:
 input_ids:
 [33975, 25, 21806, 279, 2701, 3491, 13, 81917, 697, 32711, 3019, 553, 3019, 13, 3197, 498, 525, 8060, 11, 2968, 697, 4226, 304, 419, 3561, 25, 366, 9217, 2235, 21732, 4226, 12533, 9217, 94367, 2, 22079, 198, 16429, 279, 5109, 304, 279, 1140, 508, 21, 22, 11, 220, 22, 16, 11, 220, 18, 16, 1125, 1855, 458, 23606, 429, 16819, 220, 16, 21, 24, 13, 1446, 646, 990, 6770, 34784, 7525, 17973, 11, 85922, 11777, 608, 8, 323, 1817, 1372, 646, 1172, 387, 1483, 3055, 13, 4615, 6291, 1265, 2924, 264, 4013, 315, 7354, 330, 8304, 1599, 2974, 1380, 1817, 3019, 374, 264, 35972, 5666, 323, 279, 1590, 3019, 13653, 11508, 311, 279, 2169, 1372, 476, 432, 1265, 387, 264, 3175, 23606, 429, 3059, 304, 279, 2169, 382, 35127, 697, 4226, 304, 279, 2701, 3561, 510, 27, 9217, 397, 7021, 413, 4226, 340, 522, 9217, 1339, 9064, 11993, 21732, 4226, 9940, 374, 279, 1140, 315, 7354, 311, 5545, 279, 2169, 1372, 476, 432, 1265, 387, 264, 3175, 23606, 429, 3059, 304, 279, 2169, 13, 4710, 2461, 3110, 510, 2679, 279, 1140, 315, 5109, 572, 508, 16, 11, 220, 17, 11, 220, 18, 60, 323, 279, 2169, 572, 220, 16, 11, 498, 1410, 3270, 510, 27, 9217, 397, 8304, 220, 16, 25, 220, 16, 488, 220, 17, 284, 220, 18, 198, 8304, 220, 17, 25, 220, 18, 608, 220, 18, 284, 220, 16, 198, 522, 9217, 1339, 269, 4710, 27, 9217, 397, 7, 16, 488, 220, 17, 8, 608, 220, 18, 198, 522, 9217, 1339, 10061, 594, 1744, 3019, 553, 3019, 13, 151643, 198, 71703, 25, 13708, 766, 397, 27, 13611, 397, 5338, 11, 358, 3278, 1430, 311, 3535, 279, 3491, 2664, 553, 4378, 700, 264, 3119, 323, 728, 2167, 5538, 1119, 7716, 911, 1246, 358, 1265, 11625, 419, 624, 8304, 220, 16, 25, 64547, 279, 5795, 481, 1205, 1184, 311, 1855, 458, 23606, 1667, 279, 5109, 508, 21, 22, 11, 220, 22, 16, 11, 220, 18, 16, 60, 429, 16819, 220, 16, 21, 24, 624, 8304, 220, 17, 25, 21144, 3204, 7525, 481, 78646, 11, 75240, 11, 46444, 11, 323, 12804, 624, 8304, 220, 18, 25, 9735, 2155, 27459, 315, 1493, 7525, 448, 279, 2661, 5109, 624, 8304, 220, 19, 25, 3393, 5257, 37906, 3080, 582, 1477, 825, 429, 16819, 220, 16, 21, 24, 624, 8304, 220, 20, 25, 9646, 582, 614, 1730, 279, 4396, 23606, 11, 3042, 432, 304, 279, 5189, 3561, 624, 6025, 2087, 1526, 678, 1493, 7354, 11, 1588, 594, 279, 1590, 23606, 429, 16819, 220, 16, 21, 24, 1447, 27, 9217, 397, 7, 21, 22, 353, 220, 17, 8, 488, 220, 22, 16, 481, 220, 18, 16, 198, 522, 9217, 397, 522, 13611, 397, 27, 34913, 397, 10061, 601, 10146, 419, 4226, 1447, 5338, 11, 220, 21, 22, 488, 220, 22, 16, 284, 220, 16, 18, 23, 11, 1221, 220, 16, 18, 23, 481, 220, 18, 16, 284, 220, 16, 15, 22, 13, 1096, 1558, 537, 6144, 220, 16, 21, 24, 11, 773, 279, 4226, 374, 15114, 382, 27, 423, 8477, 397, 40468, 198, 522, 423, 8477, 397, 522, 34913, 397, 10061, 752, 10146, 847, 4226, 624, 27, 13611, 397, 58465, 12153, 15846, 1447, 10253, 279, 5109, 504, 279, 2661, 738, 508, 21, 22, 11, 220, 22, 16, 11, 220, 18, 16, 60, 311, 1352, 458, 23606, 6144, 287, 220, 16, 21, 24, 1667, 6770, 34784, 7525, 17973, 11, 85922, 11777, 608, 3593, 8304, 220, 16, 25, 71059, 220, 21, 22, 323, 220, 18, 16, 624, 8304, 220, 17, 25, 2691, 220, 22, 16, 311, 279, 1102, 504, 14822, 220, 16, 624, 8304, 220, 18, 25, 576, 1590, 1102, 686, 387, 220, 16, 21, 24, 382, 27, 9217, 397, 7, 21, 22, 353, 220, 18, 16, 8, 488, 220, 22, 16, 284, 220, 16, 21, 24, 198, 522, 9217, 397, 522, 13611, 397, 27, 34913, 397, 10061, 601, 10146, 419, 4226, 1447, 5338, 11, 220, 21, 22, 353, 220, 18, 16, 284, 220, 17, 11, 15, 22, 22, 11, 1221, 220, 17, 11, 15, 22, 22, 481, 220, 22, 16, 284, 220, 17, 11, 15, 15, 21, 13, 1096, 374, 537, 6144, 311, 220, 16, 21, 24, 11, 773, 279, 4226, 374, 15114, 382, 27, 423, 8477, 397, 40468, 198, 522, 423, 8477, 397, 522, 34913, 397, 1462, 311, 3395, 847, 2033, 825, 803, 882, 624, 27, 13611, 397, 5338, 11, 358, 3278, 1430, 311, 3535, 279, 3491, 2664, 553, 4378, 700, 264, 3119, 323, 728, 2167, 5538, 1119, 7716, 911, 1246, 358, 1265, 11625, 419, 624, 785, 5795, 374, 311, 1855, 458, 23606, 1667, 279, 5109, 220, 21, 22, 11, 220, 22, 16, 11, 323, 220, 18, 16, 429, 16819, 220, 16, 21, 24, 624, 40, 686, 1191, 553, 4460, 2155, 27459, 315, 1493, 2326, 5109, 323, 862, 3204, 7525, 17973, 11, 85922, 11777, 608, 568, 715, 12209, 358, 686, 15442, 1817, 10601, 323, 1779, 421, 807, 6144, 220, 16, 21, 24, 13, 1416, 537, 11, 358, 686, 3271, 389, 311, 279, 1790, 10601, 3080, 358, 1477, 825, 429, 4278, 624, 6025, 9271, 279, 4396, 10601, 11, 358, 686, 3042, 847, 6291, 304, 279, 4055, 9217, 397, 7021, 413, 4226, 340, 522, 9217, 9877, 3561, 624, 8420, 594, 847, 11682, 3119, 1447, 16, 13, 4230, 678, 3204, 27459, 315, 220, 21, 22, 11, 220, 22, 16, 11, 323, 220, 18, 16, 1667, 5256, 11, 75240, 11, 46444, 11, 323, 12804, 624, 17, 13, 54115, 1817, 10601, 311, 1490, 421, 432, 16819, 220, 16, 21, 24, 624, 18, 13, 1416, 902, 10601, 16819, 220, 16, 21, 24, 11, 13153, 279, 1882, 448, 501, 27459, 3080, 358, 1477, 825, 429, 4278, 624, 19, 13, 9646, 358, 614, 1730, 279, 4396, 10601, 11, 3158, 432, 438, 264, 3175, 23606, 304, 279, 4055, 9217, 397, 7021, 413, 4226, 340, 522, 9217, 9877, 3561, 382, 7039, 1077, 752, 3161, 15039, 369, 279, 4396, 10601, 4894, 522, 13611, 397, 27, 34913, 397, 10061, 601, 10146, 419, 4226, 1447, 16, 13, 14822, 220, 16, 25, 220, 21, 22, 353, 220, 18, 16, 284, 220, 17, 15, 22, 22, 198, 17, 13, 14822, 220, 17, 25, 220, 17, 15, 22, 22, 481, 220, 22, 16, 284, 220, 17, 15, 15, 21, 271, 54815, 11, 279, 1590, 1102, 374, 220, 17, 15, 15, 21, 11, 892, 1558, 537, 6144, 220, 16, 21, 24, 13, 576, 4226, 374, 15114, 382, 27, 423, 8477, 397, 40468, 198, 522, 423, 8477, 397, 522, 34913, 397, 3983, 3783, 11, 1077, 752, 1744, 911, 432, 1549, 624, 27, 13611, 397, 58465, 12153, 15846, 1447, 3838, 374, 279, 1102, 979, 498, 912, 1378, 5109, 504, 279, 1140, 508, 21, 22, 11, 220, 22, 16, 11, 220, 18, 16, 60, 3786, 1939, 8304, 220, 16, 25, 2691, 220, 21, 22, 323, 220, 18, 16, 624, 8304, 220, 17, 25, 11778, 279, 2629, 504, 14822, 220, 16, 323, 912, 220, 22, 16, 382, 19357, 84670, 25, 320, 21, 22, 488, 220, 18, 16, 8, 488, 220, 22, 16, 271, 27, 9217, 397, 7, 21, 22, 488, 220, 18, 16, 8, 488, 220, 22, 16, 198, 522, 9217, 397, 522, 13611, 397, 27, 34913, 397, 10061, 601, 10146, 419, 4226, 25, 5512, 11, 220, 21, 22, 488, 220, 18, 16, 284, 220, 24, 23, 11, 1221, 220, 24, 23, 488, 220, 22, 16, 284, 220, 16, 21, 24, 13, 576, 4226, 374, 4396, 382, 27, 423, 8477, 397, 33092, 198, 522, 423, 8477, 397, 522, 34913, 397, 522, 26865, 10370, 39, 763, 11, 279, 4396, 4226, 374, 1447, 27, 9217, 397, 7, 21, 22, 488, 220, 18, 16, 8, 488, 220, 22, 16, 198, 522, 9217, 29, 151643, 198]
@@ -8282,8 +8301,8 @@ Hence, the correct answer is:
 (67 + 31) + 71
 </answer><|endoftext|>
 
-[INFO|configuration_utils.py:765] 2025-10-22 17:26:09,864 >> loading configuration file config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/config.json
-[INFO|configuration_utils.py:839] 2025-10-22 17:26:09,865 >> Model config Qwen2Config {
+[INFO|configuration_utils.py:765] 2025-10-22 17:26:09,835 >> loading configuration file config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/config.json
+[INFO|configuration_utils.py:839] 2025-10-22 17:26:09,836 >> Model config Qwen2Config {
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -8340,44 +8359,45 @@ Hence, the correct answer is:
 }
 
 [INFO|2025-10-22 17:26:09] llamafactory.model.model_utils.kv_cache:143 >> KV cache is disabled during training.
-[WARNING|logging.py:328] 2025-10-22 17:26:10,583 >> `torch_dtype` is deprecated! Use `dtype` instead!
 `torch_dtype` is deprecated! Use `dtype` instead!
-[INFO|modeling_utils.py:1172] 2025-10-22 17:26:10,584 >> loading weights file model.safetensors from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/model.safetensors
-[INFO|modeling_utils.py:2341] 2025-10-22 17:26:10,585 >> Instantiating Qwen2ForCausalLM model under default dtype torch.float16.
-[INFO|configuration_utils.py:986] 2025-10-22 17:26:10,587 >> Generate config GenerationConfig {
+[WARNING|logging.py:328] 2025-10-22 17:26:10,486 >> `torch_dtype` is deprecated! Use `dtype` instead!
+[INFO|modeling_utils.py:1172] 2025-10-22 17:26:10,487 >> loading weights file model.safetensors from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/model.safetensors
+[INFO|modeling_utils.py:2341] 2025-10-22 17:26:10,488 >> Instantiating Qwen2ForCausalLM model under default dtype torch.float16.
+[INFO|configuration_utils.py:986] 2025-10-22 17:26:10,490 >> Generate config GenerationConfig {
   "bos_token_id": 151643,
   "eos_token_id": 151643,
   "use_cache": false
 }
 
-[INFO|configuration_utils.py:941] 2025-10-22 17:26:11,032 >> loading configuration file generation_config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/generation_config.json
-[INFO|configuration_utils.py:986] 2025-10-22 17:26:11,033 >> Generate config GenerationConfig {
+[INFO|configuration_utils.py:941] 2025-10-22 17:26:10,913 >> loading configuration file generation_config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/generation_config.json
+[INFO|configuration_utils.py:986] 2025-10-22 17:26:10,913 >> Generate config GenerationConfig {
   "bos_token_id": 151643,
   "eos_token_id": 151643,
   "max_new_tokens": 2048
 }
 
-[INFO|dynamic_module_utils.py:423] 2025-10-22 17:26:11,064 >> Could not locate the custom_generate/generate.py inside Qwen/Qwen2.5-0.5B.
-[INFO|2025-10-22 17:26:11] llamafactory.model.model_utils.checkpointing:143 >> Gradient checkpointing enabled.
-[INFO|2025-10-22 17:26:11] llamafactory.model.model_utils.attention:143 >> Using torch SDPA for faster training and inference.
-[INFO|2025-10-22 17:26:11] llamafactory.model.adapter:143 >> Upcasting trainable params to float32.
-[INFO|2025-10-22 17:26:11] llamafactory.model.adapter:143 >> Fine-tuning method: LoRA
-[INFO|2025-10-22 17:26:11] llamafactory.model.model_utils.misc:143 >> Found linear modules: o_proj,down_proj,gate_proj,up_proj,v_proj,k_proj,q_proj
+[INFO|dynamic_module_utils.py:423] 2025-10-22 17:26:10,963 >> Could not locate the custom_generate/generate.py inside Qwen/Qwen2.5-0.5B.
+[INFO|2025-10-22 17:26:10] llamafactory.model.model_utils.checkpointing:143 >> Gradient checkpointing enabled.
+[INFO|2025-10-22 17:26:10] llamafactory.model.model_utils.attention:143 >> Using torch SDPA for faster training and inference.
+[INFO|2025-10-22 17:26:10] llamafactory.model.adapter:143 >> Upcasting trainable params to float32.
+[INFO|2025-10-22 17:26:10] llamafactory.model.adapter:143 >> Fine-tuning method: LoRA
+[INFO|2025-10-22 17:26:10] llamafactory.model.model_utils.misc:143 >> Found linear modules: v_proj,k_proj,q_proj,up_proj,gate_proj,down_proj,o_proj
 [INFO|2025-10-22 17:26:11] llamafactory.model.loader:143 >> trainable params: 4,399,104 || all params: 498,431,872 || trainable%: 0.8826
-[WARNING|trainer.py:906] 2025-10-22 17:26:11,180 >> The model is already on multiple devices. Skipping the move to device specified in `args`.
+[WARNING|trainer.py:906] 2025-10-22 17:26:11,078 >> The model is already on multiple devices. Skipping the move to device specified in `args`.
+[INFO|trainer.py:699] 2025-10-22 17:26:11,080 >> max_steps is given, it will override any value given in num_train_epochs
+[INFO|trainer.py:749] 2025-10-22 17:26:11,080 >> Using auto half precision backend
+[WARNING|trainer.py:982] 2025-10-22 17:26:11,081 >> The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.
 The model is already on multiple devices. Skipping the move to device specified in `args`.
-[INFO|trainer.py:699] 2025-10-22 17:26:11,183 >> max_steps is given, it will override any value given in num_train_epochs
-[INFO|trainer.py:749] 2025-10-22 17:26:11,183 >> Using auto half precision backend
-[WARNING|2025-10-22 17:26:11] llamafactory.train.callbacks:154 >> Previous trainer log in this folder will be deleted.
 The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.
-[WARNING|trainer.py:982] 2025-10-22 17:26:11,187 >> The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.
-[INFO|trainer.py:2519] 2025-10-22 17:26:11,475 >> ***** Running training *****
-[INFO|trainer.py:2520] 2025-10-22 17:26:11,475 >>   Num examples = 48,600
-[INFO|trainer.py:2521] 2025-10-22 17:26:11,475 >>   Num Epochs = 1
-[INFO|trainer.py:2522] 2025-10-22 17:26:11,475 >>   Instantaneous batch size per device = 1
-[INFO|trainer.py:2525] 2025-10-22 17:26:11,475 >>   Total train batch size (w. parallel, distributed & accumulation) = 4
-[INFO|trainer.py:2526] 2025-10-22 17:26:11,475 >>   Gradient Accumulation steps = 1
-[INFO|trainer.py:2527] 2025-10-22 17:26:11,475 >>   Total optimization steps = 100
+[INFO|trainer.py:2519] 2025-10-22 17:26:11,476 >> ***** Running training *****
+[INFO|trainer.py:2520] 2025-10-22 17:26:11,476 >>   Num examples = 48,600
+[INFO|trainer.py:2521] 2025-10-22 17:26:11,476 >>   Num Epochs = 1
+[INFO|trainer.py:2522] 2025-10-22 17:26:11,476 >>   Instantaneous batch size per device = 1
+[INFO|trainer.py:2525] 2025-10-22 17:26:11,476 >>   Total train batch size (w. parallel, distributed & accumulation) = 4
+[INFO|trainer.py:2526] 2025-10-22 17:26:11,476 >>   Gradient Accumulation steps = 1
+[INFO|trainer.py:2527] 2025-10-22 17:26:11,476 >>   Total optimization steps = 100
+[INFO|trainer.py:2528] 2025-10-22 17:26:11,478 >>   Number of trainable parameters = 4,399,104
+ptimization steps = 100
 [INFO|trainer.py:2528] 2025-10-22 17:26:11,477 >>   Number of trainable parameters = 4,399,104
 [INFO|integration_utils.py:867] 2025-10-22 17:26:11,499 >> Automatic Weights & Biases logging enabled, to disable set os.environ["WANDB_DISABLED"] = "true"
 wandb: Currently logged in as: zsprague (ut_nlp_deduce) to https://api.wandb.ai. Use `wandb login --relogin` to force relogin
@@ -8391,7 +8411,14 @@ wandb:  View run at https://wandb.ai/ut_nlp_deduce/llamafactory/runs/36bddmt4
  10%|         | 10/100 [00:03<00:22,  3.98it/s] 11%|         | 11/100 [00:03<00:21,  4.09it/s] 12%|        | 12/100 [00:04<00:34,  2.53it/s] 13%|        | 13/100 [00:04<00:28,  3.09it/s] 14%|        | 14/100 [00:04<00:23,  3.65it/s] 15%|        | 15/100 [00:04<00:20,  4.10it/s] 16%|        | 16/100 [00:04<00:19,  4.40it/s] 17%|        | 17/100 [00:04<00:20,  4.11it/s] 18%|        | 18/100 [00:05<00:23,  3.55it/s] 19%|        | 19/100 [00:05<00:22,  3.55it/s] 20%|        | 20/100 [00:05<00:20,  3.83it/s]                                                {'loss': 0.7526, 'grad_norm': 0.39774543046951294, 'learning_rate': 4.05e-05, 'epoch': 0.0}
  20%|        | 20/100 [00:05<00:20,  3.83it/s] 21%|        | 21/100 [00:06<00:20,  3.81it/s] 22%|       | 22/100 [00:06<00:19,  4.03it/s] 23%|       | 23/100 [00:06<00:19,  3.93it/s] 24%|       | 24/100 [00:06<00:18,  4.10it/s] 25%|       | 25/100 [00:07<00:19,  3.80it/s] 26%|       | 26/100 [00:07<00:18,  3.98it/s] 27%|       | 27/100 [00:07<00:18,  3.93it/s] 28%|       | 28/100 [00:07<00:20,  3.55it/s] 29%|       | 29/100 [00:08<00:19,  3.64it/s] 30%|       | 30/100 [00:08<00:18,  3.74it/s]                                                {'loss': 0.7383, 'grad_norm': 0.4655744731426239, 'learning_rate': 3.55e-05, 'epoch': 0.0}
  30%|       | 30/100 [00:08<00:18,  3.74it/s] 31%|       | 31/100 [00:08<00:18,  3.74it/s] 32%|      | 32/100 [00:08<00:17,  3.96it/s] 33%|      | 33/100 [00:09<00:15,  4.34it/s] 34%|      | 34/100 [00:09<00:13,  4.74it/s] 35%|      | 35/100 [00:09<00:14,  4.46it/s] 36%|      | 36/100 [00:09<00:13,  4.91it/s] 37%|      | 37/100 [00:09<00:13,  4.60it/s] 38%|      | 38/100 [00:10<00:13,  4.56it/s] 39%|      | 39/100 [00:10<00:12,  4.85it/s] 40%|      | 40/100 [00:10<00:13,  4.48it/s]                                                {'loss': 0.7139, 'grad_norm': 0.3746405839920044, 'learning_rate': 3.05e-05, 'epoch': 0.0}
- 40%|      | 40/100 [00:10<00:13,  4.48it/s] 41%|      | 41/100 [00:10<00:14,  4.01it/s] 42%|     | 42/100 [00:11<00:14,  3.99it/s] 43%|     | 43/100 [00:11<00:12,  4.48it/s] 44%|     | 44/100 [00:11<00:11,  4.77it/s] 45%|     | 45/100 [00:11<00:10,  5.20it/s] 46%|     | 46/100 [00:11<00:11,  4.85it/s] 47%|     | 47/100 [00:12<00:11,  4.76it/s] 48%|     | 48/100 [00:12<00:10,  5.01it/s] 49%|     | 49/100 [00:12<00:11,  4.40it/s] 50%|     | 50/100 [00:12<00:11,  4.37it/s]                                                {'loss': 0.6497, 'grad_norm': 0.5908131003379822, 'learning_rate': 2.5500000000000003e-05, 'epoch': 0.0}
+ 40%|      | 40/100 [00:10<00:13,  4.48it/s] 41%|      | 41/100 [00:10<00:14,  4.01it/s] 42%|     | 42/100 [00:11<00:14,  3.99it/s] 43%|     | 43/100 [00:11<00:12,  4.48it/s] 44%|     | 44/100 [00:11<00:11,  4.77it/s][INFO|trainer.py:2810] 2025-10-22 17:26:37,491 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+gl065:3813031:3813031 [0] NCCL INFO comm 0x1376a6e0 rank 2 nranks 4 cudaDev 0 busId 47000 - Destroy COMPLETE
+gl065:3813032:3813032 [1] NCCL INFO comm 0x12d355a0 rank 3 nranks 4 cudaDev 1 busId 59000 - Destroy COMPLETE
+                                                {'loss': 0.6497, 'grad_norm': 0.5908131003379822, 'learning_rate': 2.5500000000000003e-05, 'epoch': 0.0}
  50%|     | 50/100 [00:12<00:11,  4.37it/s][INFO|trainer.py:4309] 2025-10-22 17:26:25,397 >> Saving model checkpoint to /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/checkpoint-50
 [INFO|configuration_utils.py:765] 2025-10-22 17:26:25,617 >> loading configuration file config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/config.json
 [INFO|configuration_utils.py:839] 2025-10-22 17:26:25,619 >> Model config Qwen2Config {
@@ -8598,15 +8625,16 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
 gl064:2409683:2409683 [1] NCCL INFO comm 0x12e235c0 rank 1 nranks 4 cudaDev 1 busId 59000 - Destroy COMPLETE
 gl064:2409682:2409682 [0] NCCL INFO comm 0x13300130 rank 0 nranks 4 cudaDev 0 busId 47000 - Destroy COMPLETE
-[1;34mwandb[0m: 
-[1;34mwandb[0m:  View run [33minteractive_test[0m at: [34m[0m
-[1;34mwandb[0m: Find logs at: [1;35mwandb/run-20251022_172611-36bddmt4/logs[0m
-
-========================================
-Training completed successfully
-End Time: Wed Oct 22 05:26:40 PM EDT 2025
-========================================
-/libtorch_python.so)
+[W1022 17:26:40.190845830 TCPStore.cpp:115] [c10d] recvVector failed on SocketImpl(fd=29, addr=[gl065.hpc.nyu.edu]:52464, remote=[gl064.hpc.nyu.edu]:29500): Failed to recv, got 0 bytes. Connection was likely closed. Did the remote server shutdown or crash?
+Exception raised from recvBytes at /pytorch/torch/csrc/distributed/c10d/Utils.hpp:697 (most recent call first):
+frame #0: c10::Error::Error(c10::SourceLocation, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >) + 0x80 (0x7f1568d55b80 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libc10.so)
+frame #1: <unknown function> + 0x5ffd531 (0x7f15ab15d531 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #2: <unknown function> + 0x5ffdacd (0x7f15ab15dacd in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #3: <unknown function> + 0x5ffe19b (0x7f15ab15e19b in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #4: <unknown function> + 0x5fff0d7 (0x7f15ab15f0d7 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #5: c10d::TCPStore::compareSet(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::vector<unsigned char, std::allocator<unsigned char> > const&, std::vector<unsigned char, std::allocator<unsigned char> > const&) + 0x261 (0x7f15ab159c31 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #6: <unknown function> + 0xd9d16d (0x7f15ba8a416d in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_python.so)
+frame #7: <unknown function> + 0x3c072e (0x7f15b9ec772e in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_python.so)
 frame #8: python() [0x543944]
 <omitting python frames>
 frame #10: python() [0x56cd70]
@@ -8830,3 +8858,1940 @@ Preparing Training Artifacts
 ========================================
 Copying configuration files...
 Copying and cleaning training logs...
+Training artifacts prepared in: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged/training_artifacts
+Contents:
+Log files:
+
+========================================
+STAGE 3: Uploading to HuggingFace Hub
+Repository: TAUR-dev/testing_llamafactory_helper_quick_test__interactive
+Start Time: Wed Oct 22 05:26:55 PM EDT 2025
+========================================
+Uploading contents of: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged
+Directory structure:
+
+Executing: huggingface-cli upload TAUR-dev/testing_llamafactory_helper_quick_test__interactive /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged .
+Start hashing 17 files.
+Finished hashing 17 files.
+[33m  Warning: 'huggingface-cli upload' is deprecated. Use 'hf upload' instead.[0m
+Processing Files (0 / 0)      : |          |  0.00B /  0.00B            
+New Data Upload               : |          |  0.00B /  0.00B            [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  10%|         |  101MB /  988MB            [A[A[A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  10%|         |  101MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  11%|         |  112MB / 1.00GB,   ???B/s  
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  22%|       |  218MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  23%|       |  229MB / 1.00GB,  588MB/s  
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  28%|       |  272MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  28%|       |  284MB / 1.00GB,  429MB/s  
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  28%|       |  273MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  28%|       |  284MB / 1.00GB,  287MB/s  
+New Data Upload               :   1%|          |  605kB / 67.0MB, 1.01MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  34%|      |  339MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  35%|      |  350MB / 1.00GB,  298MB/s  
+New Data Upload               :  50%|     | 66.6MB /  134MB, 83.2MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  40%|      |  392MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  40%|      |  404MB / 1.00GB,  292MB/s  
+New Data Upload               :  60%|    |  120MB /  201MB,  120MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  45%|     |  440MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  45%|     |  451MB / 1.00GB,  283MB/s  
+New Data Upload               :  62%|   |  168MB /  268MB,  140MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  50%|     |  498MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  51%|     |  509MB / 1.00GB,  284MB/s  
+New Data Upload               :  67%|   |  226MB /  335MB,  161MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  59%|    |  583MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  60%|    |  595MB / 1.00GB,  302MB/s  
+New Data Upload               :  93%||  311MB /  335MB,  194MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  61%|   |  607MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  62%|   |  619MB / 1.00GB,  282MB/s  
+New Data Upload               :  83%| |  335MB /  403MB,  186MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  69%|   |  678MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  69%|   |  689MB / 1.00GB,  289MB/s  
+New Data Upload               :  86%| |  406MB /  470MB,  203MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  75%|  |  741MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  75%|  |  752MB / 1.00GB,  291MB/s  
+New Data Upload               :  87%| |  469MB /  537MB,  213MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  81%|  |  799MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  81%|  |  810MB / 1.00GB,  291MB/s  
+New Data Upload               :  87%| |  526MB /  604MB,  219MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  86%| |  854MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  87%| |  865MB / 1.00GB,  290MB/s  
+New Data Upload               :  87%| |  581MB /  671MB,  224MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  93%||  917MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  93%||  928MB / 1.00GB,  292MB/s  
+New Data Upload               :  90%| |  645MB /  716MB,  230MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors:  99%||  976MB /  988MB            [A[A[AProcessing Files (1 / 2)      :  99%||  987MB / 1.00GB,  292MB/s  
+New Data Upload               :  98%||  703MB /  716MB,  234MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors: 100%||  987MB /  988MB            [A[A[AProcessing Files (1 / 2)      : 100%||  999MB / 1.00GB,  277MB/s  
+New Data Upload               : 100%||  715MB /  716MB,  223MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors: 100%||  987MB /  988MB            [A[A[AProcessing Files (1 / 2)      : 100%||  999MB / 1.00GB,  261MB/s  
+New Data Upload               : 100%||  715MB /  716MB,  210MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors: 100%||  987MB /  988MB            [A[A[A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors: 100%||  988MB /  988MB            [A[A[AProcessing Files (1 / 2)      : 100%||  999MB / 1.00GB,  233MB/s  
+New Data Upload               : 100%||  715MB /  716MB,  188MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors: 100%||  988MB /  988MB            [A[A[A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors: 100%||  988MB /  988MB            [A[A[A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors: 100%||  988MB /  988MB            [A[A[A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors: 100%||  988MB /  988MB            [A[A[AProcessing Files (2 / 2)      : 100%|| 1.00GB / 1.00GB,  193MB/s  
+New Data Upload               : 100%||  716MB /  716MB,  156MB/s  [A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors: 100%||  988MB /  988MB            [A[A[A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors: 100%||  988MB /  988MB            [A[A[A
+
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            [A[A
+
+
+  .../merged/model.safetensors: 100%||  988MB /  988MB            [A[A[AProcessing Files (2 / 2)      : 100%|| 1.00GB / 1.00GB,  177MB/s  
+New Data Upload               : 100%||  716MB /  716MB,  143MB/s  
+  ...ive/merged/tokenizer.json: 100%|| 11.4MB / 11.4MB            
+  .../merged/model.safetensors: 100%||  988MB /  988MB            
+Removing 13 file(s) from commit that have not changed.
+https://huggingface.co/TAUR-dev/testing_llamafactory_helper_quick_test__interactive/tree/main/.
+
+========================================
+Upload completed successfully
+Model and training artifacts uploaded to: TAUR-dev/testing_llamafactory_helper_quick_test__interactive
+End Time: Wed Oct 22 05:27:04 PM EDT 2025
+========================================
+
+========================================
+STAGE 4: Cleanup
+========================================
+Keeping checkpoints in: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints
+Keeping merged model in: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged
+
+========================================
+PIPELINE COMPLETED SUCCESSFULLY
+End Time: Wed Oct 22 05:27:04 PM EDT 2025
+========================================
+
+========================================
+Cleaning up LlamaFactory processes
+========================================
+Cleaned up processes on gl064.hpc.nyu.edu
+Cleaning up processes on worker node: gl065
+Process cleanup complete
+========================================
+Job Name: lf_torch_test__interactive
+Hostname: gl064.hpc.nyu.edu
+Number of nodes: 2
+GPUs per node: 2
+Start Time: Wed Oct 22 08:24:54 PM EDT 2025
+Log file: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/logs/pipeline.log
+========================================
+Sourcing secrets from: /scratch/zrs2020/LlamaFactoryHelper/secrets.env
+
+========================================
+Configuration Paths
+========================================
+Train Config: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/configs/train_config.yaml
+Merge Config: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/configs/merge_config.yaml
+Dataset Info: 
+Output Dir: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints
+Export Dir: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged
+HF Repo ID: TAUR-dev/testing_llamafactory_helper_quick_test__interactive
+
+
+========================================
+Multi-Node Coordination
+========================================
+This is the master node - coordinating worker nodes...
+Master node: gl064
+Master port: 29500
+World size: 2
+
+Launching on worker node 1: gl065
+All worker nodes launched successfully
+Master node (this node) will now join training as rank 0
+
+
+========================================
+STAGE 0: Pre-tokenize Dataset (one-time)
+========================================
+Tokenized dataset not found at: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/tokenized/my_custom_sft12
+Pre-tokenizing on a single node to avoid multi-node mmap conflicts...
+========================================
+Job Name: lf_torch_test__interactive
+Hostname: gl064.hpc.nyu.edu
+Number of nodes: 2
+GPUs per node: 2
+Start Time: Wed Oct 22 08:24:59 PM EDT 2025
+Log file: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/logs/pipeline.log
+========================================
+Sourcing secrets from: /scratch/zrs2020/LlamaFactoryHelper/secrets.env
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
+  warnings.warn(
+st__interactive/logs/pipeline.log
+========================================
+Sourcing secrets from: /scratch/zrs2020/LlamaFactoryHelper/secrets.env
+
+========================================
+Configuration Paths
+========================================
+Train Config: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/configs/train_config.yaml
+Merge Config: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/configs/merge_config.yaml
+Dataset Info: 
+Output Dir: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints
+Export Dir: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged
+HF Repo ID: TAUR-dev/testing_llamafactory_helper_quick_test__interactive
+
+
+========================================
+Multi-Node Coordination
+========================================
+This is the master node - coordinating worker nodes...
+Master node: gl064
+Master port: 29500
+World size: 2
+
+Launching on worker node 1: gl065
+All worker nodes launched successfully
+Master node (this node) will now join training as rank 0
+
+
+========================================
+STAGE 0: Pre-tokenize Dataset (one-time)
+========================================
+Tokenized dataset not found at: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/tokenized/my_custom_sft12
+Pre-tokenizing on a single node to avoid multi-node mmap conflicts...
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
+  warnings.warn(
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
+  warnings.warn(
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
+  warnings.warn(
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
+  import pkg_resources
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/accelerate/state.py:271: UserWarning: OMP_NUM_THREADS/MKL_NUM_THREADS unset, we set it at 128 to improve oob performance.
+  warnings.warn(
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
+  import pkg_resources
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/accelerate/state.py:271: UserWarning: OMP_NUM_THREADS/MKL_NUM_THREADS unset, we set it at 128 to improve oob performance.
+  warnings.warn(
+Traceback (most recent call last):
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/llamafactory-cli", line 7, in <module>
+    sys.exit(main())
+             ^^^^^^
+  File "/scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory/src/llamafactory/cli.py", line 24, in main
+    launcher.launch()
+  File "/scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory/src/llamafactory/launcher.py", line 152, in launch
+    run_exp()
+  File "/scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory/src/llamafactory/train/tuner.py", line 110, in run_exp
+    _training_function(config={"args": args, "callbacks": callbacks})
+  File "/scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory/src/llamafactory/train/tuner.py", line 55, in _training_function
+    model_args, data_args, training_args, finetuning_args, generating_args = get_train_args(args)
+                                                                             ^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory/src/llamafactory/hparams/parser.py", line 219, in get_train_args
+    model_args, data_args, training_args, finetuning_args, generating_args = _parse_train_args(args)
+                                                                             ^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory/src/llamafactory/hparams/parser.py", line 197, in _parse_train_args
+    return _parse_args(parser, args, allow_extra_keys=allow_extra_keys)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory/src/llamafactory/hparams/parser.py", line 79, in _parse_args
+    return parser.parse_dict(args, allow_extra_keys=allow_extra_keys)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/hf_argparser.py", line 380, in parse_dict
+    obj = dtype(**inputs)
+          ^^^^^^^^^^^^^^^
+  File "<string>", line 147, in __init__
+  File "/scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory/src/llamafactory/hparams/training_args.py", line 90, in __post_init__
+    Seq2SeqTrainingArguments.__post_init__(self)
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/training_args.py", line 1811, in __post_init__
+    self.device
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/training_args.py", line 2355, in device
+    return self._setup_devices
+           ^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/functools.py", line 998, in __get__
+    val = self.func(instance)
+          ^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/training_args.py", line 2282, in _setup_devices
+    self.distributed_state = PartialState(**accelerator_state_kwargs)
+                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/accelerate/state.py", line 277, in __init__
+    torch.distributed.init_process_group(backend=self.backend, **kwargs)
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/distributed/c10d_logger.py", line 81, in wrapper
+    return func(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/distributed/c10d_logger.py", line 95, in wrapper
+    func_return = func(*args, **kwargs)
+                  ^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py", line 1762, in init_process_group
+    store, rank, world_size = next(rendezvous_iterator)
+                              ^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/distributed/rendezvous.py", line 278, in _env_rendezvous_handler
+    store = _create_c10d_store(
+            ^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/distributed/rendezvous.py", line 198, in _create_c10d_store
+    return TCPStore(
+           ^^^^^^^^^
+torch.distributed.DistNetworkError: The server socket has failed to listen on any local network address. port: 29500, useIpv6: false, code: -98, name: EADDRINUSE, message: address already in use
+ERROR: Pre-tokenization failed (exit 1).
+
+========================================
+Cleaning up LlamaFactory processes
+========================================
+Cleaned up processes on gl064.hpc.nyu.edu
+Cleaning up processes on worker node: gl065
+Terminated
+ERROR: Pre-tokenization failed (exit 143).
+
+========================================
+Cleaning up LlamaFactory processes
+========================================
+Terminated
+Process cleanup complete
+Cleaned up processes on gl064.hpc.nyu.edu
+Cleaning up processes on worker node: gl065
+Process cleanup complete
+Terminated
+Terminated
+Terminated
+n failed (exit 143).
+
+========================================
+Cleaning up LlamaFactory processes
+========================================
+Terminated
+ERROR: Pre-tokenization failed (exit 143).
+
+========================================
+Cleaning up LlamaFactory processes
+========================================
+Terminated
+Cleaned up processes on gl065.hpc.nyu.edu
+Cleaned up processes on gl065.hpc.nyu.edu
+Process cleanup complete
+Process cleanup complete
+========================================
+Job Name: lf_torch_test__interactive
+Hostname: gl064.hpc.nyu.edu
+Number of nodes: 2
+GPUs per node: 2
+Start Time: Wed Oct 22 08:25:32 PM EDT 2025
+Log file: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/logs/pipeline.log
+========================================
+Sourcing secrets from: /scratch/zrs2020/LlamaFactoryHelper/secrets.env
+
+========================================
+Configuration Paths
+========================================
+Train Config: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/configs/train_config.yaml
+Merge Config: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/configs/merge_config.yaml
+Dataset Info: 
+Output Dir: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints
+Export Dir: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged
+HF Repo ID: TAUR-dev/testing_llamafactory_helper_quick_test__interactive
+
+
+========================================
+Multi-Node Coordination
+========================================
+This is the master node - coordinating worker nodes...
+Master node: gl064
+Master port: 29500
+World size: 2
+
+Launching on worker node 1: gl065
+All worker nodes launched successfully
+Master node (this node) will now join training as rank 0
+
+
+========================================
+STAGE 0: Pre-tokenize Dataset (one-time)
+========================================
+Tokenized dataset not found at: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/tokenized/my_custom_sft12
+Pre-tokenizing on a single node to avoid multi-node mmap conflicts...
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
+  warnings.warn(
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
+  warnings.warn(
+st__interactive/logs/pipeline.log
+========================================
+Sourcing secrets from: /scratch/zrs2020/LlamaFactoryHelper/secrets.env
+
+========================================
+Configuration Paths
+========================================
+Train Config: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/configs/train_config.yaml
+Merge Config: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/configs/merge_config.yaml
+Dataset Info: 
+Output Dir: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints
+Export Dir: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged
+HF Repo ID: TAUR-dev/testing_llamafactory_helper_quick_test__interactive
+
+
+========================================
+STAGE 0: Pre-tokenize Dataset (one-time)
+========================================
+Tokenized dataset not found at: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/tokenized/my_custom_sft12
+Pre-tokenizing on a single node to avoid multi-node mmap conflicts...
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
+  warnings.warn(
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
+  import pkg_resources
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/accelerate/state.py:271: UserWarning: OMP_NUM_THREADS/MKL_NUM_THREADS unset, we set it at 128 to improve oob performance.
+  warnings.warn(
+[W1022 20:32:56.009084699 TCPStore.cpp:138] [c10d] recvValueWithTimeout failed on SocketImpl(fd=33, addr=[gl065.hpc.nyu.edu]:38048, remote=[gl064.hpc.nyu.edu]:29500): Failed to recv, got 0 bytes. Connection was likely closed. Did the remote server shutdown or crash?
+Exception raised from recvBytes at /pytorch/torch/csrc/distributed/c10d/Utils.hpp:697 (most recent call first):
+frame #0: c10::Error::Error(c10::SourceLocation, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >) + 0x80 (0x7f09d69ceb80 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libc10.so)
+frame #1: <unknown function> + 0x5ffd531 (0x7f0a18dd6531 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #2: <unknown function> + 0x5ffeb8d (0x7f0a18dd7b8d in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #3: <unknown function> + 0x5fff249 (0x7f0a18dd8249 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #4: c10d::TCPStore::doWait(c10::ArrayRef<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::chrono::duration<long, std::ratio<1l, 1000l> >) + 0x1c6 (0x7f0a18dd34f6 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #5: c10d::TCPStore::wait(std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > const&, std::chrono::duration<long, std::ratio<1l, 1000l> > const&) + 0x206 (0x7f0a18dd37c6 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #6: c10d::PrefixStore::wait(std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > const&, std::chrono::duration<long, std::ratio<1l, 1000l> > const&) + 0x2f (0x7f0a18d80f5f in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #7: c10d::PrefixStore::wait(std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > const&, std::chrono::duration<long, std::ratio<1l, 1000l> > const&) + 0x2f (0x7f0a18d80f5f in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #8: c10d::PrefixStore::wait(std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > const&, std::chrono::duration<long, std::ratio<1l, 1000l> > const&) + 0x2f (0x7f0a18d80f5f in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #9: gloo::rendezvous::PrefixStore::wait(std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > const&, std::chrono::duration<long, std::ratio<1l, 1000l> > const&) + 0x109 (0x7f0a1b2ec0f9 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #10: gloo::transport::tcp::Context::createAndConnectAllPairs(std::shared_ptr<gloo::IStore>) + 0xa18 (0x7f0a1b3095f8 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #11: gloo::rendezvous::Context::connectFullMesh(std::shared_ptr<gloo::rendezvous::Store>, std::shared_ptr<gloo::transport::Device>&) + 0x5c (0x7f0a1b2e8ebc in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #12: c10d::ProcessGroupGloo::ProcessGroupGloo(c10::intrusive_ptr<c10d::Store, c10::detail::intrusive_target_default_null_type<c10d::Store> > const&, int, int, c10::intrusive_ptr<c10d::ProcessGroupGloo::Options, c10::detail::intrusive_target_default_null_type<c10d::ProcessGroupGloo::Options> >) + 0x430 (0x7f0a18dab440 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so)
+frame #13: <unknown function> + 0xd7190a (0x7f0a284f190a in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_python.so)
+frame #14: <unknown function> + 0xda5bb5 (0x7f0a28525bb5 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_python.so)
+frame #15: <unknown function> + 0x3c072e (0x7f0a27b4072e in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_python.so)
+frame #16: /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12() [0x543944]
+frame #17: _PyObject_MakeTpCall + 0x2fc (0x51778c in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #18: /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12() [0x56ccad]
+frame #19: _PyObject_Call + 0x122 (0x555d42 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #20: /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12() [0x552d05]
+frame #21: /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12() [0x517aab]
+frame #22: <unknown function> + 0x3be9eb (0x7f0a27b3e9eb in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/lib/libtorch_python.so)
+frame #23: _PyObject_MakeTpCall + 0x2fc (0x51778c in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #24: _PyEval_EvalFrameDefault + 0x6d2 (0x521952 in /scrat2 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #25: _PyObject_FastCallDictTstate + 0x285 (0x519fc5 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #26: /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12() [0x552ad4]
+frame #27: /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12() [0x517aab]
+frame #28: _PyObject_Call + 0xb5 (0x555cd5 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #29: _PyEval_EvalFrameDefault + 0x53fe (0x52667e in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #30: PyObject_Vectorcall + 0x51 (0x539261 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #31: /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12() [0x628004]
+frame #32: _PyObject_GenericGetAttrWithDict + 0x181 (0x5425f1 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #33: PyObject_GetAttr + 0x3c (0x5199dc in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #34: _PyEval_EvalFrameDefault + 0x11bb (0x52243b in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #35: PyObject_CallOneArg + 0x66 (0x550c56 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #36: _PyObject_GenericGetAttrWithDict + 0x2dd (0x54274d in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #37: PyObject_GetAttr + 0x3c (0x5199dc in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #38: _PyEval_EvalFrameDefault + 0x11bb (0x52243b in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #39: _PyObject_FastCallDictTstate + 0x285 (0x519fc5 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #40: /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12() [0x552ad4]
+frame #41: /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12() [0x517aab]
+fERROR: Pre-tokenization failed (exit 143).
+rame #42: _PyObject_Call + 0xb5 (0x555cd5 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #43: _PyEval_EvalFrameDefault + 0x53fe (0x52667e in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #44: PyEval_EvalCode + 0xae (0x5de5ce in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #45: /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12() [0x61b7b7]
+frame #46: /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12() [0x616307]
+frame #47: /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12() [0x6131c2]
+frame #48: _PyRun_SimpleFileObject + 0x1b0 (0x612d80 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #49: _PyRun_AnyFileObject + 0x43 (0x612883 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #50: Py_RunMain + 0x3a7 (0x60f6c7 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #51: Py_BytesMain + 0x39 (0x5c6bb9 in /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12)
+frame #52: <unknown function> + 0x295d0 (0x7f0a366295d0 in /lib64/libc.so.6)
+frame #53: __libc_start_main + 0x80 (0x7f0a36629680 in /lib64/libc.so.6)
+frame #54: /scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/python3.12() [0x5c69e9]
+
+
+========================================
+Cleaning up LlamaFactory processes
+Traceback (most recent call last):
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/bin/llamafactory-cli", line 7, in <module>
+========================================
+Cleaned up processes on gl064.hpc.nyu.edu
+    sys.exit(main())
+             ^^^^^^
+  File "/scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory/src/llamafactory/cli.py", line 24, in main
+Cleaning up processes on worker node: gl065
+    launcher.launch()
+  File "/scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory/src/llamafactory/lmaFactoryHelper/LLaMA-Factory/src/llamafactory/train/tuner.py", line 55, in _training_function
+    model_args, data_args, training_args, finetuning_args, generating_args = get_train_args(args)
+                                                                             ^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory/src/llamafactory/hparams/parser.py", line 219, in get_train_args
+    model_args, data_args, training_args, finetuning_args, generating_args = _parse_train_args(args)
+                                                                             ^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory/src/llamafactory/hparams/parser.py", line 197, in _parse_train_args
+    return _parse_args(parser, args, allow_extra_keys=allow_extra_keys)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory/src/llamafactory/hparams/parser.py", line 79, in _parse_args
+    return parser.parse_dict(args, allow_extra_keys=allow_extra_keys)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/hf_argparser.py", line 380, in parse_dict
+    obj = dtype(**inputs)
+          ^^^^^^^^^^^^^^^
+  File "<string>", line 147, in __init__
+  File "/scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory/src/llamafactory/hparams/training_args.py", line 90, in __post_init__
+    Seq2SeqTrainingArguments.__post_init__(self)
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/training_args.py", line 1811, in __post_init__
+    self.device
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/training_args.py", line 2355, in device
+    return self._setup_devices
+           ^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/functools.py", line 998, in __get__
+    val = self.func(instance)
+          ^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/training_args.py", line 2282, in _setup_devices
+    self.distributed_state = PartialState(**accelerator_state_kwargs)
+                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/accelerate/state.py", line 277, in __init__
+    torch.distributed.init_process_group(backend=self.backend, **kwargs)
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/distributed/c10d_logger.py", line 81, in wrapper
+    return func(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/distributed/c10d_logger.py", line 95, in wrapper
+    func_return = func(*args, **kwargs)
+                  ^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py", line 1769, in init_process_group
+    default_pg, _ = _new_process_group_helper(
+                    ^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py", line 1996, in _new_process_group_helper
+    backend_class = ProcessGroupGloo(
+                    ^^^^^^^^^^^^^^^^^
+torch.distributed.DistNetworkError: Failed to recv, got 0 bytes. Connection was likely closed. Did the remote server shutdown or crash?
+ERROR: Pre-tokenization failed (exit 1).
+
+========================================
+Cleaning up LlamaFactory processes
+========================================
+Cleaned up processes on gl065.hpc.nyu.edu
+Process cleanup complete
+========================================
+Job Name: lf_torch_test__interactive
+Hostname: gl064.hpc.nyu.edu
+Number of nodes: 2
+GPUs per node: 2
+Start Time: Wed Oct 22 08:34:53 PM EDT 2025
+Log file: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/logs/pipeline.log
+========================================
+Sourcing secrets from: /scratch/zrs2020/LlamaFactoryHelper/secrets.env
+
+========================================
+Configuration Paths
+========================================
+Train Config: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/configs/train_config.yaml
+Merge Config: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/configs/merge_config.yaml
+Dataset Info: 
+Output Dir: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints
+Export Dir: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged
+HF Repo ID: TAUR-dev/testing_llamafactory_helper_quick_test__interactive
+
+
+========================================
+Multi-Node Coordination
+========================================
+This is the master node - coordinating worker nodes...
+Master node: gl064
+Master port: 29500
+World size: 2
+
+Launching on worker node 1: gl065
+All worker nodes launched successfully
+Master node (this node) will now join training as rank 0
+
+
+Tokenized dataset will be created at: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/tokenized/my_custom_sft12
+First run will tokenize and cache; subsequent runs will reuse
+
+========================================
+STAGE 1: Training Model
+Start Time: Wed Oct 22 08:34:56 PM EDT 2025
+========================================
+Multi-node training detected
+Nodes: 2, GPUs per node: 2
+Master address: gl064
+Master port: 29500
+Node rank: 0
+World size: 2
+CUDA_VISIBLE_DEVICES: 0,1
+LLaMA-Factory path: /scratch/zrs2020/LlamaFactoryHelper/LLaMA-Factory
+Training config: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/configs/train_config.yaml
+
+Starting distributed training with torch.distributed.run...
+
+*****************************************
+Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
+*****************************************
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
+  warnings.warn(
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
+  warnings.warn(
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
+  import pkg_resources
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
+  import pkg_resources
+[INFO|2025-10-22 20:35:15] llamafactory.hparams.parser:423 >> Process rank: 1, world size: 4, device: cuda:1, distributed training: True, compute dtype: torch.float16
+[INFO|2025-10-22 20:35:15] llamafactory.hparams.parser:143 >> Set `ddp_find_unused_parameters` to False in DDP training since LoRA is enabled.
+[INFO|2025-10-22 20:35:15] llamafactory.hparams.parser:423 >> Process rank: 0, world size: 4, device: cuda:0, distributed training: True, compute dtype: torch.float16
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:35:15,237 >> loading file vocab.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/vocab.json
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:35:15,237 >> loading file merges.txt from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/merges.txt
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:35:15,237 >> loading file tokenizer.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/tokenizer.json
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:35:15,237 >> loading file added_tokens.json from cache at None
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:35:15,238 >> loading file special_tokens_map.json from cache at None
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:35:15,238 >> loading file tokenizer_config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:35:15,238 >> loading file chat_template.jinja from cache at None
+[INFO|tokenization_utils_base.py:2364] 2025-10-22 20:35:15,408 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+[INFO|configuration_utils.py:765] 2025-10-22 20:35:15,689 >> loading configuration file config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/config.json
+[INFO|configuration_utils.py:839] 2025-10-22 20:35:15,691 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:35:15,755 >> loading file vocab.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/vocab.json
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:35:15,755 >> loading file merges.txt from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/merges.txt
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:35:15,755 >> loading file tokenizer.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/tokenizer.json
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:35:15,755 >> loading file added_tokens.json from cache at None
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:35:15,755 >> loading file special_tokens_map.json from cache at None
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:35:15,755 >> loading file tokenizer_config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:35:15,755 >> loading file chat_template.jinja from cache at None
+[INFO|tokenization_utils_base.py:2364] 2025-10-22 20:35:15,922 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+[INFO|2025-10-22 20:35:15] llamafactory.data.loader:143 >> Loading dataset TAUR-dev/D-SFT_C-BASELINE_r1_distillation-sft-data...
+Converting format of dataset (num_proc=16):   0%|          | 0/3998 [00:00<?, ? examples/s]Converting format of dataset (num_proc=16):   6%|         | 250/3998 [00:00<00:02, 1282.23 examples/s]Converting format of dataset (num_proc=16): 100%|| 3998/3998 [00:00<00:00, 11930.03 examples/s]
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py:4876: UserWarning: barrier(): using the device under current context. You can specify `device_id` in `init_process_group` to mute this warning.
+  warnings.warn(  # warn only once
+[rank0]:[W1022 20:35:16.478700264 ProcessGroupNCCL.cpp:5068] Guessing device ID based on global rank. This can cause a hang if rank to GPU mapping is heterogeneous. You can specify device_id in init_process_group()
+gl064:2626306:2626306 [0] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ibs
+gl064:2626306:2626306 [0] NCCL INFO Bootstrap: Using ibs3:10.0.5.0<0>
+gl064:2626306:2626306 [0] NCCL INFO cudaDriverVersion 13000
+gl064:2626306:2626306 [0] NCCL INFO NCCL version 2.27.5+cuda12.9
+gl064:2626306:2626306 [0] NCCL INFO Comm config Blocking set to 1
+gl064:2626307:2626307 [1] NCCL INFO cudaDriverVersion 13000
+gl064:2626307:2626307 [1] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ibs
+gl064:2626307:2626307 [1] NCCL INFO Bootstrap: Using ibs3:10.0.5.0<0>
+gl064:2626307:2626307 [1] NCCL INFO NCCL version 2.27.5+cuda12.9
+gl064:2626307:2626307 [1] NCCL INFO Comm config Blocking set to 1
+gl064:2626306:2626406 [0] NCCL INFO NET/Plugin: Could not find: libnccl-net.so. 
+gl064:2626306:2626406 [0] NCCL INFO NCCL_IB_DISABLE set by environment to 0.
+gl064:2626306:2626406 [0] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ibs
+gl064:2626306:2626406 [0] NCCL INFO NCCL_IB_HCA set to mlx5
+gl064:2626307:2626407 [1] NCCL INFO NET/Plugin: Could not find: libnccl-net.so. 
+gl064:2626307:2626407 [1] NCCL INFO NCCL_IB_DISABLE set by environment to 0.
+gl064:2626307:2626407 [1] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ibs
+gl064:2626307:2626407 [1] NCCL INFO NCCL_IB_HCA set to mlx5
+gl064:2626306:2626406 [0] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [RO]; OOB ibs3:10.0.5.0<0>
+gl064:2626306:2626406 [0] NCCL INFO Initialized NET plugin IB
+gl064:2626306:2626406 [0] NCCL INFO Assigned NET plugin IB to comm
+gl064:2626306:2626406 [0] NCCL INFO Using network IB
+gl064:2626307:2626407 [1] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [RO]; OOB ibs3:10.0.5.0<0>
+gl064:2626307:2626407 [1] NCCL INFO Initialized NET plugin IB
+gl064:2626306:2626406 [0] NCCL INFO ncclCommInitRankConfig comm 0x13d4e850 rank 0 nranks 4 cudaDev 0 nvmlDev 0 busId 47000 commId 0x5fc912795e7fee89 - Init START
+gl064:2626307:2626407 [1] NCCL INFO Assigned NET plugin IB to comm
+gl064:2626307:2626407 [1] NCCL INFO Using network IB
+gl064:2626307:2626407 [1] NCCL INFO ncclCommInitRankConfig comm 0x15ba7840 rank 1 nranks 4 cudaDev 1 nvmlDev 1 busId 59000 commId 0x5fc912795e7fee89 - Init START
+gl064:2626306:2626406 [0] NCCL INFO RAS client listening socket at ::1<28028>
+gl064:2626307:2626407 [1] NCCL INFO RAS client listening socket at ::1<28028>
+gl064:2626306:2626406 [0] NCCL INFO Bootstrap timings total 1.008501 (create 0.000023, send 0.000230, recv 0.000728, ring 0.438069, delay 0.000000)
+gl064:2626307:2626407 [1] NCCL INFO Bootstrap timings total 1.007716 (create 0.000021, send 0.000076, recv 1.006053, ring 0.000830, delay 0.000000)
+gl064:2626306:2626406 [0] NCCL INFO Setting affinity for GPU 0 to 0-15
+gl064:2626307:2626407 [1] NCCL INFO Setting affinity for GPU 1 to 0-15
+gl064:2626307:2626407 [1] NCCL INFO comm 0x15ba7840 rank 1 nRanks 4 nNodes 2 localRanks 2 localRank 1 MNNVL 0
+gl064:2626306:2626406 [0] NCCL INFO comm 0x13d4e850 rank 0 nRanks 4 nNodes 2 localRanks 2 localRank 0 MNNVL 0
+gl064:2626306:2626406 [0] NCCL INFO Channel 00/02 : 0 1 2 3
+gl064:2626307:2626407 [1] NCCL INFO Trees [0] -1/-1/-1->1->0 [1] -1/-1/-1->1->0
+gl064:2626306:2626406 [0] NCCL INFO Channel 01/02 : 0 1 2 3
+gl064:2626307:2626407 [1] NCCL INFO P2P Chunksize set to 131072
+gl064:2626306:2626406 [0] NCCL INFO Trees [0] 1/2/-1->0->-1 [1] 1/-1/-1->0->2
+gl064:2626306:2626406 [0] NCCL INFO P2P Chunksize set to 131072
+gl064:2626306:2626406 [0] NCCL INFO PROFILER/Plugin: Could not find: libnccl-profiler.so. 
+gl064:2626307:2626407 [1] NCCL INFO PROFILER/Plugin: Could not find: libnccl-profiler.so. 
+gl064:2626306:2626406 [0] NCCL INFO Check P2P Type isAllDirectP2p 0 directMode 0
+gl064:2626306:2626412 [0] NCCL INFO [Proxy Service] Device 0 CPU core 6
+gl064:2626307:2626413 [1] NCCL INFO [Proxy Service] Device 1 CPU core 2
+gl064:2626307:2626414 [1] NCCL INFO [Proxy Service UDS] Device 1 CPU core 10
+gl064:2626306:2626415 [0] NCCL INFO [Proxy Service UDS] Device 0 CPU core 10
+gl064:2626307:2626407 [1] NCCL INFO threadThresholds 8/8/64 | 32/8/64 | 512 | 512
+gl064:2626307:2626407 [1] NCCL INFO 2 coll channels, 2 collnet channels, 0 nvls channels, 2 p2p channels, 2 p2p channels per peer
+gl064:2626306:2626406 [0] NCCL INFO threadThresholds 8/8/64 | 32/8/64 | 512 | 512
+gl064:2626306:2626406 [0] NCCL INFO 2 coll channels, 2 collnet channels, 0 nvls channels, 2 p2p channels, 2 p2p channels per peer
+gl064:2626306:2626406 [0] NCCL INFO CC Off, workFifoBytes 1048576
+gl064:2626307:2626407 [1] NCCL INFO TUNER/Plugin: Could not find: libnccl-tuner.so. Using internal tuner plugin.
+gl064:2626307:2626407 [1] NCCL INFO ncclCommInitRankConfig comm 0x15ba7840 rank 1 nranks 4 cudaDev 1 nvmlDev 1 busId 59000 commId 0x5fc912795e7fee89 - Init COMPLETE
+gl064:2626307:2626407 [1] NCCL INFO Init timings - ncclCommInitRankConfig: rank 1 nranks 4 total 1.12 (kernels 0.08, alloc 0.01, bootstrap 1.01, allgathers 0.00, topo 0.01, graphs 0.00, connections 0.00, rest 0.00)
+gl064:2626306:2626406 [0] NCCL INFO TUNER/Plugin: Could not find: libnccl-tuner.so. Using internal tuner plugin.
+gl064:2626306:2626406 [0] NCCL INFO ncclCommInitRankConfig comm 0x13d4e850 rank 0 nranks 4 cudaDev 0 nvmlDev 0 busId 47000 commId 0x5fc912795e7fee89 - Init COMPLETE
+gl064:2626306:2626406 [0] NCCL INFO Init timings - ncclCommInitRankConfig: rank 0 nranks 4 total 1.12 (kernels 0.08, alloc 0.01, bootstrap 1.01, allgathers 0.00, topo 0.01, graphs 0.00, connections 0.00, rest 0.00)
+gl064:2626306:2626417 [0] NCCL INFO Channel 00/0 : 3[1] -> 0[0] [receive] via NET/IB/0
+gl064:2626306:2626417 [0] NCCL INFO Channel 01/0 : 3[1] -> 0[0] [receive] via NET/IB/0
+gl064:2626306:2626418 [0] NCCL INFO [Proxy Progress] Device 0 CPU core 14
+gl064:2626306:2626417 [0] NCCL INFO Channel 00 : 0[0] -> 1[1] via SHM/direct/direct
+gl064:2626306:2626417 [0] NCCL INFO Channel 01 : 0[0] -> 1[1] via SHM/direct/direct
+gl064:2626307:2626419 [1] NCCL INFO [Proxy Progress] Device 1 CPU core 3
+gl064:2626307:2626416 [1] NCCL INFO Channel 00/0 : 1[1] -> 2[0] [send] via NET/IB/0
+gl064:2626307:2626416 [1] NCCL INFO Channel 01/0 : 1[1] -> 2[0] [send] via NET/IB/0
+gl064:2626307:2626416 [1] NCCL INFO Connected all rings, use ring PXN 0 GDR 0
+gl064:2626306:2626417 [0] NCCL INFO Connected all rings, use ring PXN 0 GDR 0
+Running tokenizer on dataset (num_proc=16):   0%|          | 0/3998 [00:00<?, ? examples/s]Running tokenizer on dataset (num_proc=16):   6%|         | 250/3998 [00:01<00:23, 157.21 examples/s]Running tokenizer on dataset (num_proc=16):  13%|        | 500/3998 [00:01<00:10, 349.48 examples/s]Running tokenizer on dataset (num_proc=16):  38%|      | 1500/3998 [00:01<00:01, 1332.30 examples/s]Running tokenizer on dataset (num_proc=16):  50%|     | 2000/3998 [00:01<00:01, 1720.97 examples/s]Running tokenizer on dataset (num_proc=16):  63%|   | 2500/3998 [00:02<00:00, 1942.73 examples/s]Running tokenizer on dataset (num_proc=16):  75%|  | 3000/3998 [00:02<00:00, 2399.16 examples/s]Running tokenizer on dataset (num_proc=16):  88%| | 3500/3998 [00:02<00:00, 2677.06 examples/s]Running tokenizer on dataset (num_proc=16): 100%|| 3998/3998 [00:02<00:00, 2308.38 examples/s]Running tokenizer on dataset (num_proc=16): 100%|| 3998/3998 [00:02<00:00, 1420.00 examples/s]
+training example:
+input_ids:
+[33975, 25, 21806, 279, 2701, 3491, 13, 81917, 697, 32711, 3019, 553, 3019, 13, 3197, 498, 525, 8060, 11, 2968, 697, 4226, 304, 419, 3561, 25, 366, 9217, 2235, 21732, 4226, 12533, 9217, 94367, 2, 22079, 198, 16429, 279, 5109, 304, 279, 1140, 508, 24, 24, 11, 220, 20, 22, 11, 220, 21, 22, 1125, 1855, 458, 23606, 429, 16819, 220, 16, 15, 24, 13, 1446, 646, 990, 6770, 34784, 7525, 17973, 11, 85922, 11777, 608, 8, 323, 1817, 1372, 646, 1172, 387, 1483, 3055, 13, 4615, 6291, 1265, 2924, 264, 4013, 315, 7354, 330, 8304, 1599, 2974, 1380, 1817, 3019, 374, 264, 35972, 5666, 323, 279, 1590, 3019, 13653, 11508, 311, 279, 2169, 1372, 476, 432, 1265, 387, 264, 3175, 23606, 429, 3059, 304, 279, 2169, 382, 35127, 697, 4226, 304, 279, 2701, 3561, 510, 27, 9217, 397, 7021, 413, 4226, 340, 522, 9217, 1339, 9064, 11993, 21732, 4226, 9940, 374, 279, 1140, 315, 7354, 311, 5545, 279, 2169, 1372, 476, 432, 1265, 387, 264, 3175, 23606, 429, 3059, 304, 279, 2169, 13, 4710, 2461, 3110, 510, 2679, 279, 1140, 315, 5109, 572, 508, 16, 11, 220, 17, 11, 220, 18, 60, 323, 279, 2169, 572, 220, 16, 11, 498, 1410, 3270, 510, 27, 9217, 397, 8304, 220, 16, 25, 220, 16, 488, 220, 17, 284, 220, 18, 198, 8304, 220, 17, 25, 220, 18, 608, 220, 18, 284, 220, 16, 198, 522, 9217, 1339, 269, 4710, 27, 9217, 397, 7, 16, 488, 220, 17, 8, 608, 220, 18, 198, 522, 9217, 1339, 10061, 594, 1744, 3019, 553, 3019, 13, 151643, 198, 71703, 25, 13708, 766, 397, 40, 614, 279, 5109, 508, 24, 24, 11, 220, 20, 22, 11, 220, 21, 22, 60, 323, 1184, 311, 1281, 220, 16, 15, 24, 1667, 6770, 34784, 7525, 25, 5256, 11, 75240, 11, 46444, 11, 323, 12804, 13, 8886, 1372, 646, 1172, 387, 1483, 3055, 382, 5338, 11, 358, 1265, 2908, 1128, 7525, 2578, 975, 13, 8704, 220, 16, 15, 24, 374, 264, 2699, 8131, 1091, 279, 5109, 11, 46444, 2578, 387, 6398, 11, 714, 220, 24, 24, 323, 220, 21, 22, 525, 2176, 3460, 11, 323, 220, 20, 22, 374, 9155, 13, 6771, 752, 1490, 279, 11799, 476, 36398, 382, 2679, 358, 912, 220, 24, 24, 323, 220, 20, 22, 11, 429, 594, 220, 24, 24, 488, 220, 20, 22, 284, 220, 16, 20, 21, 11, 892, 374, 11243, 1091, 220, 16, 15, 24, 13, 5005, 358, 614, 220, 21, 22, 2115, 13, 1416, 358, 32256, 220, 21, 22, 504, 220, 16, 20, 21, 11, 429, 594, 220, 16, 20, 21, 481, 220, 21, 22, 284, 220, 23, 24, 11, 892, 374, 2686, 1091, 220, 16, 15, 24, 13, 220, 23, 24, 374, 2238, 2613, 13, 1416, 358, 653, 220, 16, 20, 21, 481, 220, 21, 22, 284, 220, 23, 24, 11, 537, 220, 16, 15, 24, 382, 21390, 358, 646, 30270, 13, 220, 24, 24, 3039, 2494, 13, 220, 24, 24, 353, 220, 16, 284, 220, 24, 24, 11, 2238, 2613, 13, 220, 24, 24, 353, 220, 17, 284, 220, 16, 24, 23, 11, 2238, 2409, 13, 1988, 358, 614, 311, 990, 279, 5109, 2661, 382, 31476, 12804, 13, 220, 24, 24, 17779, 553, 2494, 13, 220, 24, 24, 608, 220, 16, 284, 220, 24, 24, 11, 537, 10950, 13, 220, 24, 24, 608, 220, 15, 13, 24, 476, 2494, 11, 714, 358, 614, 311, 990, 279, 5109, 382, 14037, 4522, 25, 7196, 358, 646, 653, 220, 21, 22, 488, 220, 20, 22, 284, 220, 16, 17, 19, 11, 1221, 220, 16, 17, 19, 481, 220, 16, 20, 11, 714, 358, 1513, 944, 614, 220, 16, 20, 11, 358, 614, 220, 24, 24, 13, 220, 16, 17, 19, 481, 220, 24, 24, 284, 220, 17, 20, 11, 537, 220, 16, 15, 24, 382, 2623, 3238, 13, 6771, 594, 1140, 279, 5109, 25, 220, 24, 24, 11, 220, 20, 22, 11, 220, 21, 22, 13, 13483, 220, 16, 15, 24, 382, 31476, 358, 1184, 311, 990, 75240, 476, 12804, 311, 633, 9155, 5109, 382, 21390, 320, 24, 24, 353, 2494, 8, 488, 2494, 382, 24, 24, 353, 220, 16, 284, 220, 24, 24, 11, 1221, 358, 1184, 488, 16, 15, 11, 714, 358, 614, 220, 20, 22, 323, 220, 21, 22, 11, 2176, 8131, 1091, 220, 16, 15, 382, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 11, 1221, 220, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 13, 8670, 0, 2938, 1410, 975, 382, 4416, 11, 1156, 11, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 11, 1221, 220, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 382, 3983, 304, 3793, 315, 7354, 11, 358, 1184, 311, 990, 279, 5109, 1172, 3055, 11, 323, 304, 419, 1142, 11, 358, 1483, 220, 21, 22, 323, 220, 20, 22, 311, 1281, 220, 16, 15, 11, 1221, 3694, 311, 220, 24, 24, 382, 4416, 11, 14822, 220, 16, 25, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 271, 8304, 220, 17, 25, 220, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 271, 3983, 220, 16, 15, 374, 537, 825, 315, 279, 4024, 5109, 26, 432, 594, 14257, 13, 1988, 304, 279, 2266, 11, 432, 1265, 387, 6915, 11, 438, 817, 279, 3110, 382, 641, 279, 3110, 448, 508, 16, 11, 17, 11, 18, 60, 311, 1281, 220, 16, 11, 807, 1521, 320, 16, 10, 17, 5620, 18, 476, 7354, 1075, 220, 16, 10, 17, 28, 18, 1221, 220, 18, 14, 18, 28, 16, 382, 67691, 1588, 11, 358, 646, 614, 7354, 382, 3983, 1077, 752, 7683, 25, 1667, 220, 21, 22, 11, 220, 20, 22, 11, 323, 220, 24, 24, 382, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 11, 1221, 220, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 13, 7414, 382, 40, 1410, 3270, 432, 438, 458, 23606, 25, 220, 24, 24, 488, 320, 21, 22, 481, 220, 20, 22, 8, 284, 220, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 382, 4792, 4977, 4396, 382, 3983, 374, 1052, 2441, 1616, 30, 10696, 448, 46444, 476, 12804, 382, 2461, 3110, 11, 220, 24, 24, 353, 220, 21, 22, 374, 6765, 11, 1075, 220, 21, 21, 18, 18, 11, 17779, 553, 220, 20, 22, 476, 2494, 13, 220, 21, 21, 18, 18, 608, 220, 20, 22, 13, 6771, 752, 11047, 25, 220, 20, 22, 353, 220, 16, 16, 21, 284, 220, 20, 22, 9, 16, 15, 15, 28, 20, 22, 15, 15, 11, 220, 20, 22, 9, 16, 21, 28, 24, 16, 17, 11, 2790, 220, 20, 22, 15, 15, 10, 24, 16, 17, 28, 21, 21, 16, 17, 11, 220, 21, 21, 18, 18, 12, 21, 21, 16, 17, 28, 17, 16, 11, 773, 220, 16, 16, 21, 488, 220, 17, 16, 14, 20, 22, 11, 537, 7546, 11, 323, 537, 220, 16, 15, 24, 382, 2623, 1661, 382, 20, 22, 353, 220, 21, 22, 284, 937, 220, 20, 15, 9, 21, 22, 28, 18, 18, 20, 15, 11, 220, 22, 9, 21, 22, 28, 19, 21, 24, 11, 2790, 220, 18, 18, 20, 15, 10, 19, 21, 24, 28, 18, 23, 16, 24, 11, 1221, 17779, 553, 220, 24, 24, 30, 220, 18, 23, 16, 24, 608, 220, 24, 24, 13, 220, 24, 24, 9, 18, 23, 28, 18, 22, 21, 17, 11, 220, 18, 23, 16, 24, 12, 18, 22, 21, 17, 28, 20, 22, 11, 773, 220, 18, 23, 488, 220, 20, 22, 14, 24, 24, 11, 537, 220, 16, 15, 24, 382, 2623, 3238, 382, 24, 24, 353, 220, 20, 22, 284, 220, 20, 21, 19, 18, 11, 17779, 553, 220, 21, 22, 30, 220, 21, 22, 9, 23, 19, 28, 21, 22, 9, 23, 15, 28, 20, 18, 21, 15, 11, 220, 21, 22, 9, 19, 28, 17, 21, 23, 11, 2790, 220, 20, 18, 21, 15, 10, 17, 21, 23, 28, 20, 21, 17, 23, 11, 220, 20, 21, 19, 18, 12, 20, 21, 17, 23, 28, 16, 20, 11, 773, 220, 23, 19, 488, 220, 16, 20, 14, 21, 22, 11, 537, 7546, 382, 2623, 220, 16, 15, 24, 382, 4416, 11, 5256, 323, 75240, 2803, 2664, 382, 14037, 10601, 25, 220, 24, 24, 488, 220, 21, 22, 284, 220, 16, 21, 21, 11, 1221, 27283, 220, 20, 22, 284, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 30, 220, 16, 21, 21, 481, 220, 20, 22, 382, 16, 21, 21, 481, 220, 20, 15, 284, 220, 16, 16, 21, 11, 27283, 220, 22, 803, 374, 220, 16, 15, 24, 30, 220, 16, 16, 21, 481, 220, 22, 284, 220, 16, 15, 24, 11, 9834, 0, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 382, 16, 21, 21, 481, 220, 20, 22, 25, 220, 16, 21, 21, 481, 220, 20, 15, 284, 220, 16, 16, 21, 11, 220, 16, 16, 21, 481, 220, 22, 284, 220, 16, 15, 24, 11, 9834, 382, 3036, 220, 24, 24, 488, 220, 21, 22, 284, 220, 16, 21, 21, 11, 1221, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 382, 4416, 11, 14822, 220, 16, 25, 220, 24, 24, 488, 220, 21, 22, 284, 220, 16, 21, 21, 271, 8304, 220, 17, 25, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 271, 4792, 1083, 4278, 382, 641, 419, 1142, 11, 358, 1483, 678, 2326, 5109, 5961, 382, 67691, 11, 304, 279, 1156, 1714, 11, 358, 1483, 75240, 1156, 382, 20629, 525, 2697, 382, 3983, 304, 279, 1156, 1714, 11, 358, 1030, 220, 21, 22, 481, 220, 20, 22, 1156, 11, 1221, 912, 311, 220, 24, 24, 382, 8420, 11, 220, 24, 24, 488, 220, 21, 22, 1156, 11, 1221, 32256, 220, 20, 22, 382, 7039, 11, 892, 825, 311, 3042, 30, 358, 1744, 2987, 374, 6915, 382, 3983, 1077, 752, 1490, 279, 2169, 25, 220, 16, 15, 24, 382, 641, 279, 2086, 1714, 11, 432, 594, 30339, 25, 320, 24, 24, 488, 220, 21, 22, 8, 481, 220, 20, 22, 284, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 382, 641, 279, 1156, 25, 220, 24, 24, 488, 320, 21, 22, 481, 220, 20, 22, 8, 284, 220, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 382, 20629, 525, 4396, 382, 31476, 358, 1265, 3270, 432, 438, 264, 3175, 23606, 382, 785, 3491, 2727, 25, 330, 64, 4013, 315, 7354, 1, 476, 330, 64, 3175, 23606, 11436, 40, 646, 653, 2987, 382, 641, 279, 4226, 3561, 11, 358, 646, 5157, 382, 3983, 1077, 752, 1490, 421, 1052, 594, 12804, 476, 2494, 11, 714, 537, 5871, 382, 14037, 1616, 25, 220, 16, 15, 24, 374, 3265, 311, 220, 16, 15, 15, 11, 714, 220, 24, 24, 374, 4558, 220, 16, 15, 15, 382, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 11, 323, 220, 16, 15, 504, 220, 21, 22, 12, 20, 22, 382, 2195, 5961, 382, 40, 1744, 432, 594, 6915, 382, 7039, 11, 369, 279, 4226, 11, 358, 1184, 311, 2182, 432, 304, 279, 3561, 382, 13394, 11, 304, 279, 7354, 11, 358, 1184, 311, 13837, 279, 7525, 382, 641, 279, 1156, 3019, 14319, 29208, 25, 14822, 220, 16, 25, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 11, 14822, 220, 17, 25, 220, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 382, 3983, 304, 14822, 220, 17, 11, 358, 2776, 7842, 220, 24, 24, 323, 220, 16, 15, 11, 714, 220, 16, 15, 374, 537, 264, 1372, 11, 432, 594, 279, 1102, 13, 1988, 304, 279, 2266, 11, 432, 1265, 387, 21555, 11, 438, 817, 279, 3110, 382, 67691, 11, 304, 279, 2086, 25, 14822, 220, 16, 25, 220, 24, 24, 488, 220, 21, 22, 284, 220, 16, 21, 21, 11, 14822, 220, 17, 25, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 382, 8420, 11, 220, 16, 21, 21, 374, 28439, 382, 40, 1410, 3270, 279, 23606, 5961, 382, 12549, 279, 3491, 2727, 330, 3182, 458, 23606, 497, 714, 432, 6147, 7354, 476, 3175, 23606, 382, 40, 1744, 358, 3278, 728, 448, 279, 3175, 23606, 369, 38975, 382, 4416, 11, 320, 24, 24, 488, 220, 21, 22, 8, 481, 220, 20, 22, 284, 220, 16, 15, 24, 271, 2195, 220, 24, 24, 488, 320, 21, 22, 481, 220, 20, 22, 8, 284, 220, 16, 15, 24, 271, 49244, 1616, 382, 31476, 2041, 73975, 11, 714, 1973, 12850, 382, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 382, 7039, 11, 5256, 323, 75240, 614, 1852, 53056, 11, 2115, 311, 1290, 382, 4416, 11, 220, 24, 24, 488, 220, 21, 22, 284, 220, 16, 21, 21, 11, 1221, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 11, 892, 374, 4396, 382, 67691, 11, 421, 358, 653, 220, 21, 22, 481, 220, 20, 22, 488, 220, 24, 24, 11, 429, 594, 220, 16, 15, 488, 220, 24, 24, 284, 220, 16, 15, 24, 11, 1083, 4396, 382, 4416, 11, 304, 2176, 5048, 11, 2041, 73975, 11, 432, 4278, 1576, 315, 2115, 311, 1290, 16460, 382, 21, 22, 481, 220, 20, 22, 488, 220, 24, 24, 25, 1156, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 11, 1221, 220, 16, 15, 488, 220, 24, 24, 284, 220, 16, 15, 24, 382, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 25, 220, 24, 24, 488, 220, 21, 22, 284, 220, 16, 21, 21, 11, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 382, 20629, 6915, 382, 4416, 11, 358, 646, 3270, 432, 438, 220, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 24, 382, 2195, 220, 21, 22, 481, 220, 20, 22, 488, 220, 24, 24, 284, 220, 16, 15, 24, 382, 40, 1744, 220, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 374, 803, 5810, 382, 12549, 220, 24, 24, 374, 1156, 304, 279, 1140, 11, 714, 537, 5871, 382, 641, 279, 1140, 11, 432, 594, 508, 24, 24, 11, 220, 20, 22, 11, 220, 21, 22, 1125, 714, 1973, 3171, 944, 4925, 369, 279, 23606, 382, 641, 279, 7354, 11, 358, 2578, 1184, 311, 990, 1105, 304, 1973, 11, 714, 537, 5189, 382, 40, 1744, 369, 279, 23606, 11, 432, 594, 6915, 382, 7039, 11, 311, 3042, 382, 40, 1744, 358, 3278, 3270, 279, 3175, 23606, 382, 3983, 304, 279, 4226, 3561, 11, 432, 1265, 387, 43810, 304, 366, 9217, 29, 9492, 382, 13394, 11, 369, 279, 23606, 11, 358, 1184, 311, 1473, 432, 16819, 220, 16, 15, 24, 382, 31476, 358, 646, 3270, 25, 220, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 24, 271, 3983, 304, 279, 2266, 11, 2474, 432, 594, 279, 6291, 11, 432, 1265, 387, 2797, 382, 14037, 3166, 25, 304, 279, 3491, 11, 432, 2727, 330, 3182, 458, 23606, 429, 16819, 220, 16, 15, 24, 497, 773, 358, 1265, 614, 458, 7493, 6144, 311, 220, 16, 15, 24, 382, 4416, 11, 320, 24, 24, 488, 220, 21, 22, 8, 481, 220, 20, 22, 476, 2494, 382, 3983, 438, 358, 1053, 11, 2041, 73975, 432, 4278, 382, 1249, 387, 23560, 11, 358, 646, 990, 73975, 382, 3983, 537, 5871, 382, 40, 1744, 432, 594, 6915, 382, 31476, 358, 1265, 3270, 279, 7354, 311, 387, 12966, 448, 279, 3110, 382, 641, 279, 3110, 11, 807, 1030, 1378, 2606, 382, 40, 1744, 358, 3278, 653, 2176, 369, 31273, 11, 714, 279, 3491, 2727, 330, 46430, 697, 4226, 1, 304, 279, 3561, 11, 773, 825, 374, 3322, 382, 40, 3278, 728, 448, 279, 23606, 382, 4416, 11, 366, 9217, 29, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 24, 522, 9217, 1339, 3983, 304, 279, 23606, 11, 358, 1184, 311, 990, 279, 5109, 11, 323, 432, 1265, 15442, 311, 220, 16, 15, 24, 382, 24, 24, 488, 220, 21, 22, 374, 220, 16, 21, 21, 11, 27283, 220, 20, 22, 374, 220, 16, 15, 24, 11, 9834, 382, 1249, 3270, 432, 438, 458, 7493, 25, 220, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 271, 3983, 358, 1184, 311, 1473, 432, 16819, 220, 16, 15, 24, 382, 641, 279, 4226, 11, 358, 646, 3270, 279, 23606, 382, 67691, 11, 304, 279, 3019, 14319, 29208, 382, 40, 1744, 2987, 374, 6915, 382, 3983, 1077, 752, 1490, 279, 3491, 25, 330, 21732, 6291, 1265, 2924, 264, 4013, 315, 7354, 1112, 476, 432, 1265, 387, 264, 3175, 23606, 1837, 40, 646, 5157, 382, 40, 1744, 279, 3175, 23606, 374, 63594, 382, 4416, 11, 358, 3278, 653, 429, 382, 3983, 304, 279, 1140, 11, 220, 20, 22, 374, 2086, 11, 714, 304, 279, 23606, 11, 358, 614, 220, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 11, 892, 5711, 678, 382, 14037, 10601, 25, 1128, 421, 358, 990, 12804, 1939, 2461, 3110, 11, 220, 16, 15, 24, 284, 220, 16, 15, 15, 488, 220, 24, 11, 714, 537, 10950, 382, 21, 22, 353, 220, 17, 284, 220, 16, 18, 19, 11, 2238, 2409, 11, 27283, 220, 17, 20, 11, 902, 382, 20, 22, 353, 220, 17, 284, 220, 16, 16, 19, 11, 3265, 311, 220, 16, 15, 24, 11, 220, 16, 16, 19, 481, 220, 20, 11, 714, 902, 220, 20, 382, 16, 16, 19, 481, 220, 20, 11, 714, 358, 614, 220, 24, 24, 323, 220, 21, 22, 382, 16, 16, 19, 481, 220, 20, 11, 714, 220, 20, 537, 2500, 382, 7, 20, 22, 353, 220, 17, 8, 481, 2494, 11, 714, 358, 1513, 944, 614, 220, 17, 11, 358, 614, 311, 990, 279, 5109, 3055, 11, 773, 358, 646, 944, 30270, 553, 220, 17, 7241, 358, 42430, 432, 382, 2461, 3110, 11, 358, 1410, 653, 12804, 311, 633, 64895, 382, 10048, 2900, 358, 653, 220, 24, 24, 608, 220, 20, 22, 476, 2494, 382, 24, 24, 608, 220, 20, 22, 284, 220, 18, 18, 14, 16, 24, 11, 13187, 220, 16, 13, 22, 18, 21, 11, 537, 7546, 382, 12209, 30270, 553, 220, 21, 22, 30, 220, 16, 13, 22, 18, 21, 353, 220, 21, 22, 21103, 230, 220, 16, 16, 21, 13, 2494, 11, 537, 220, 16, 15, 24, 382, 2623, 1661, 382, 21, 22, 608, 220, 20, 22, 21103, 230, 220, 16, 13, 16, 22, 20, 11, 3039, 220, 24, 24, 21103, 230, 220, 16, 16, 21, 13, 18, 17, 20, 11, 537, 220, 16, 15, 24, 382, 2753, 382, 4416, 11, 5256, 323, 75240, 525, 279, 1616, 311, 728, 382, 54815, 11, 220, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 24, 374, 4396, 382, 1249, 3270, 432, 448, 279, 5109, 304, 1973, 25, 714, 537, 5871, 382, 40, 1744, 358, 2776, 1661, 624, 522, 26865, 397, 1249, 11625, 279, 3491, 315, 6825, 458, 23606, 6144, 311, 220, 16, 15, 24, 1667, 279, 5109, 508, 24, 24, 11, 220, 20, 22, 11, 220, 21, 22, 60, 448, 6770, 34784, 7525, 17973, 11, 85922, 11777, 608, 701, 1817, 1483, 3055, 11, 358, 6509, 3204, 27459, 13, 8704, 220, 16, 15, 24, 374, 3265, 311, 279, 2629, 315, 220, 24, 24, 323, 220, 21, 22, 320, 8206, 374, 220, 16, 21, 21, 701, 32256, 287, 220, 20, 22, 504, 419, 2629, 3059, 304, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 13, 1096, 5486, 5711, 5256, 323, 75240, 11, 892, 525, 5420, 7525, 382, 785, 23606, 646, 387, 5326, 438, 510, 59, 9640, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 24, 198, 59, 2533, 1986, 374, 2697, 1576, 510, 12, 78646, 323, 75240, 525, 10660, 2115, 311, 1290, 25, 1156, 11, 17767, 24, 24, 488, 220, 21, 22, 284, 220, 16, 21, 21, 59, 701, 1221, 17767, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 59, 4292, 12, 2009, 5109, 504, 279, 1140, 525, 1483, 6896, 3055, 382, 92014, 11, 279, 23606, 646, 387, 13302, 448, 73975, 369, 31273, 11, 714, 807, 525, 537, 5871, 4152, 311, 2115, 4686, 6701, 16460, 369, 7525, 315, 279, 1852, 53056, 510, 59, 9640, 7, 24, 24, 488, 220, 21, 22, 8, 481, 220, 20, 22, 284, 220, 16, 15, 24, 198, 59, 2533, 20629, 7586, 7540, 279, 2169, 1372, 220, 16, 15, 24, 382, 27, 9217, 397, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 24, 198, 522, 9217, 29, 151643, 198]
+inputs:
+Human: Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.
+
+# Problem
+Using the numbers in the list [99, 57, 67], create an equation that equals 109. You can use basic arithmetic operations (+, -, *, /) and each number can only be used once. Your solution should include a series of steps "Step X:" where each step is a mathematical operation and the final step ultimately leads to the target number or it should be a single equation that results in the target.
+
+Give your answer in the following format:
+<answer>
+(your answer)
+</answer>
+
+Where "(your answer)" is the list of steps to reach the target number or it should be a single equation that results in the target. 
+
+For example:
+If the list of numbers was [1, 2, 3] and the target was 1, you could write:
+<answer>
+Step 1: 1 + 2 = 3
+Step 2: 3 / 3 = 1
+</answer>
+
+or 
+
+<answer>
+(1 + 2) / 3
+</answer>
+
+Let's think step by step.<|endoftext|>
+Assistant:<think>
+I have the numbers [99, 57, 67] and need to make 109 using basic arithmetic operations: addition, subtraction, multiplication, and division. Each number can only be used once.
+
+First, I should consider what operations might work. Since 109 is a bit larger than the numbers, multiplication might be involved, but 99 and 67 are both large, and 57 is smaller. Let me see the differences or sums.
+
+If I add 99 and 57, that's 99 + 57 = 156, which is bigger than 109. Then I have 67 left. If I subtract 67 from 156, that's 156 - 67 = 89, which is less than 109. 89 is too small. If I do 156 - 67 = 89, not 109.
+
+Maybe I can multiply. 99 times something. 99 * 1 = 99, too small. 99 * 2 = 198, too big. But I have to use the numbers given.
+
+Perhaps division. 99 divided by something. 99 / 1 = 99, not helpful. 99 / 0.9 or something, but I have to use the numbers.
+
+Another idea: maybe I can do 67 + 57 = 124, then 124 - 15, but I don't have 15, I have 99. 124 - 99 = 25, not 109.
+
+Not working. Let's list the numbers: 99, 57, 67. Target 109.
+
+Perhaps I need to use subtraction or division to get smaller numbers.
+
+Maybe (99 * something) + something.
+
+99 * 1 = 99, then I need +10, but I have 57 and 67, both larger than 10.
+
+67 - 57 = 10, then 99 + 10 = 109. Oh! That could work.
+
+So, first, 67 - 57 = 10, then 99 + 10 = 109.
+
+But in terms of steps, I need to use the numbers only once, and in this case, I used 67 and 57 to make 10, then added to 99.
+
+So, Step 1: 67 - 57 = 10
+
+Step 2: 99 + 10 = 109
+
+But 10 is not one of the original numbers; it's derived. But in the context, it should be fine, as per the example.
+
+In the example with [1,2,3] to make 1, they did (1+2)/3 or steps like 1+2=3 then 3/3=1.
+
+Similarly here, I can have steps.
+
+But let me confirm: using 67, 57, and 99.
+
+67 - 57 = 10, then 99 + 10 = 109. Yes.
+
+I could write it as an equation: 99 + (67 - 57) = 99 + 10 = 109.
+
+That seems correct.
+
+But is there another way? Maybe with multiplication or division.
+
+For example, 99 * 67 is huge, like 6633, divided by 57 or something. 6633 / 57. Let me calculate: 57 * 116 = 57*100=5700, 57*16=912, total 5700+912=6612, 6633-6612=21, so 116 + 21/57, not integer, and not 109.
+
+Not good.
+
+57 * 67 = ? 50*67=3350, 7*67=469, total 3350+469=3819, then divided by 99? 3819 / 99. 99*38=3762, 3819-3762=57, so 38 + 57/99, not 109.
+
+Not working.
+
+99 * 57 = 5643, divided by 67? 67*84=67*80=5360, 67*4=268, total 5360+268=5628, 5643-5628=15, so 84 + 15/67, not integer.
+
+Not 109.
+
+So, addition and subtraction seem better.
+
+Another combination: 99 + 67 = 166, then minus 57 = 166 - 57 = 109? 166 - 57.
+
+166 - 50 = 116, minus 7 more is 109? 116 - 7 = 109, yes! 166 - 57 = 109.
+
+166 - 57: 166 - 50 = 116, 116 - 7 = 109, yes.
+
+And 99 + 67 = 166, then 166 - 57 = 109.
+
+So, Step 1: 99 + 67 = 166
+
+Step 2: 166 - 57 = 109
+
+That also works.
+
+In this case, I used all three numbers directly.
+
+Similarly, in the first method, I used subtraction first.
+
+Both are valid.
+
+But in the first method, I had 67 - 57 first, then add to 99.
+
+Here, 99 + 67 first, then subtract 57.
+
+Now, which one to present? I think either is fine.
+
+But let me see the target: 109.
+
+In the second method, it's straightforward: (99 + 67) - 57 = 166 - 57 = 109.
+
+In the first: 99 + (67 - 57) = 99 + 10 = 109.
+
+Both are correct.
+
+Perhaps I should write it as a single equation.
+
+The problem says: "a series of steps" or "a single equation".
+
+I can do either.
+
+In the answer format, I can choose.
+
+But let me see if there's division or something, but not necessary.
+
+Another way: 109 is close to 100, but 99 is almost 100.
+
+99 + 10 = 109, and 10 from 67-57.
+
+Or directly.
+
+I think it's fine.
+
+Now, for the answer, I need to put it in the format.
+
+Also, in the steps, I need to specify the operations.
+
+In the first step-by-step: Step 1: 67 - 57 = 10, Step 2: 99 + 10 = 109.
+
+But in Step 2, I'm adding 99 and 10, but 10 is not a number, it's the result. But in the context, it should be acceptable, as per the example.
+
+Similarly, in the second: Step 1: 99 + 67 = 166, Step 2: 166 - 57 = 109.
+
+Here, 166 is intermediate.
+
+I could write the equation directly.
+
+Since the problem says "create an equation", but it allows steps or single equation.
+
+I think I'll go with the single equation for simplicity.
+
+So, (99 + 67) - 57 = 109
+
+Or 99 + (67 - 57) = 109
+
+Either way.
+
+Perhaps without parentheses, but order matters.
+
+99 + 67 - 57.
+
+Now, addition and subtraction have same precedence, left to right.
+
+So, 99 + 67 = 166, then 166 - 57 = 109, which is correct.
+
+Similarly, if I do 67 - 57 + 99, that's 10 + 99 = 109, also correct.
+
+So, in both cases, without parentheses, it works because of left to right evaluation.
+
+67 - 57 + 99: first 67 - 57 = 10, then 10 + 99 = 109.
+
+99 + 67 - 57: 99 + 67 = 166, 166 - 57 = 109.
+
+Both fine.
+
+So, I can write it as 99 + 67 - 57 = 109.
+
+Or 67 - 57 + 99 = 109.
+
+I think 99 + 67 - 57 is more natural.
+
+Since 99 is first in the list, but not necessary.
+
+In the list, it's [99, 57, 67], but order doesn't matter for the equation.
+
+In the steps, I might need to use them in order, but not specified.
+
+I think for the equation, it's fine.
+
+Now, to present.
+
+I think I'll write the single equation.
+
+But in the answer format, it should be enclosed in <answer> tags.
+
+Also, for the equation, I need to show it equals 109.
+
+Perhaps I can write: 99 + 67 - 57 = 109
+
+But in the context, since it's the solution, it should be clear.
+
+Another thing: in the problem, it says "create an equation that equals 109", so I should have an expression equal to 109.
+
+So, (99 + 67) - 57 or something.
+
+But as I said, without parentheses it works.
+
+To be precise, I can use parentheses.
+
+But not necessary.
+
+I think it's fine.
+
+Perhaps I should write the steps to be consistent with the example.
+
+In the example, they had two options.
+
+I think I'll do both for clarity, but the problem says "give your answer" in the format, so one is enough.
+
+I'll go with the equation.
+
+So, <answer>99 + 67 - 57 = 109</answer>
+
+But in the equation, I need to use the numbers, and it should evaluate to 109.
+
+99 + 67 is 166, minus 57 is 109, yes.
+
+To write it as an expression: 99 + 67 - 57
+
+But I need to show it equals 109.
+
+In the answer, I can write the equation.
+
+Similarly, in the step-by-step.
+
+I think either is fine.
+
+But let me see the problem: "your solution should include a series of steps... or it should be a single equation"
+
+I can choose.
+
+I think the single equation is concise.
+
+So, I'll do that.
+
+But in the list, 57 is second, but in the equation, I have 99 + 67 - 57, which uses all.
+
+Another combination: what if I use division?
+
+For example, 109 = 100 + 9, but not helpful.
+
+67 * 2 = 134, too big, minus 25, no.
+
+57 * 2 = 114, close to 109, 114 - 5, but no 5.
+
+114 - 5, but I have 99 and 67.
+
+114 - 5, but 5 not available.
+
+(57 * 2) - something, but I don't have 2, I have to use the numbers once, so I can't multiply by 2 unless I derive it.
+
+For example, I could do division to get fractions.
+
+Suppose I do 99 / 57 or something.
+
+99 / 57 = 33/19, approximately 1.736, not integer.
+
+Then multiply by 67? 1.736 * 67  116. something, not 109.
+
+Not good.
+
+67 / 57  1.175, times 99  116.325, not 109.
+
+No.
+
+So, addition and subtraction are the way to go.
+
+Therefore, 99 + 67 - 57 = 109 is correct.
+
+To write it with the numbers in order: but not necessary.
+
+I think I'm good.
+</think>
+To solve the problem of creating an equation equal to 109 using the numbers [99, 57, 67] with basic arithmetic operations (+, -, *, /), each used once, I considered possible combinations. Since 109 is close to the sum of 99 and 67 (which is 166), subtracting 57 from this sum results in 166 - 57 = 109. This approach uses addition and subtraction, which are allowed operations.
+
+The equation can be written as:
+\[
+99 + 67 - 57 = 109
+\]
+
+This is valid because:
+- Addition and subtraction are performed left to right: first, \(99 + 67 = 166\), then \(166 - 57 = 109\).
+- All numbers from the list are used exactly once.
+
+Alternatively, the equation can be expressed with parentheses for clarity, but they are not necessary due to left-to-right evaluation for operations of the same precedence:
+\[
+(99 + 67) - 57 = 109
+\]
+
+Both forms yield the target number 109.
+
+<answer>
+99 + 67 - 57 = 109
+</answer><|endoftext|>
+
+label_ids:
+[-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 13708, 766, 397, 40, 614, 279, 5109, 508, 24, 24, 11, 220, 20, 22, 11, 220, 21, 22, 60, 323, 1184, 311, 1281, 220, 16, 15, 24, 1667, 6770, 34784, 7525, 25, 5256, 11, 75240, 11, 46444, 11, 323, 12804, 13, 8886, 1372, 646, 1172, 387, 1483, 3055, 382, 5338, 11, 358, 1265, 2908, 1128, 7525, 2578, 975, 13, 8704, 220, 16, 15, 24, 374, 264, 2699, 8131, 1091, 279, 5109, 11, 46444, 2578, 387, 6398, 11, 714, 220, 24, 24, 323, 220, 21, 22, 525, 2176, 3460, 11, 323, 220, 20, 22, 374, 9155, 13, 6771, 752, 1490, 279, 11799, 476, 36398, 382, 2679, 358, 912, 220, 24, 24, 323, 220, 20, 22, 11, 429, 594, 220, 24, 24, 488, 220, 20, 22, 284, 220, 16, 20, 21, 11, 892, 374, 11243, 1091, 220, 16, 15, 24, 13, 5005, 358, 614, 220, 21, 22, 2115, 13, 1416, 358, 32256, 220, 21, 22, 504, 220, 16, 20, 21, 11, 429, 594, 220, 16, 20, 21, 481, 220, 21, 22, 284, 220, 23, 24, 11, 892, 374, 2686, 1091, 220, 16, 15, 24, 13, 220, 23, 24, 374, 2238, 2613, 13, 1416, 358, 653, 220, 16, 20, 21, 481, 220, 21, 22, 284, 220, 23, 24, 11, 537, 220, 16, 15, 24, 382, 21390, 358, 646, 30270, 13, 220, 24, 24, 3039, 2494, 13, 220, 24, 24, 353, 220, 16, 284, 220, 24, 24, 11, 2238, 2613, 13, 220, 24, 24, 353, 220, 17, 284, 220, 16, 24, 23, 11, 2238, 2409, 13, 1988, 358, 614, 311, 990, 279, 5109, 2661, 382, 31476, 12804, 13, 220, 24, 24, 17779, 553, 2494, 13, 220, 24, 24, 608, 220, 16, 284, 220, 24, 24, 11, 537, 10950, 13, 220, 24, 24, 608, 220, 15, 13, 24, 476, 2494, 11, 714, 358, 614, 311, 990, 279, 5109, 382, 14037, 4522, 25, 7196, 358, 646, 653, 220, 21, 22, 488, 220, 20, 22, 284, 220, 16, 17, 19, 11, 1221, 220, 16, 17, 19, 481, 220, 16, 20, 11, 714, 358, 1513, 944, 614, 220, 16, 20, 11, 358, 614, 220, 24, 24, 13, 220, 16, 17, 19, 481, 220, 24, 24, 284, 220, 17, 20, 11, 537, 220, 16, 15, 24, 382, 2623, 3238, 13, 6771, 594, 1140, 279, 5109, 25, 220, 24, 24, 11, 220, 20, 22, 11, 220, 21, 22, 13, 13483, 220, 16, 15, 24, 382, 31476, 358, 1184, 311, 990, 75240, 476, 12804, 311, 633, 9155, 5109, 382, 21390, 320, 24, 24, 353, 2494, 8, 488, 2494, 382, 24, 24, 353, 220, 16, 284, 220, 24, 24, 11, 1221, 358, 1184, 488, 16, 15, 11, 714, 358, 614, 220, 20, 22, 323, 220, 21, 22, 11, 2176, 8131, 1091, 220, 16, 15, 382, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 11, 1221, 220, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 13, 8670, 0, 2938, 1410, 975, 382, 4416, 11, 1156, 11, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 11, 1221, 220, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 382, 3983, 304, 3793, 315, 7354, 11, 358, 1184, 311, 990, 279, 5109, 1172, 3055, 11, 323, 304, 419, 1142, 11, 358, 1483, 220, 21, 22, 323, 220, 20, 22, 311, 1281, 220, 16, 15, 11, 1221, 3694, 311, 220, 24, 24, 382, 4416, 11, 14822, 220, 16, 25, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 271, 8304, 220, 17, 25, 220, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 271, 3983, 220, 16, 15, 374, 537, 825, 315, 279, 4024, 5109, 26, 432, 594, 14257, 13, 1988, 304, 279, 2266, 11, 432, 1265, 387, 6915, 11, 438, 817, 279, 3110, 382, 641, 279, 3110, 448, 508, 16, 11, 17, 11, 18, 60, 311, 1281, 220, 16, 11, 807, 1521, 320, 16, 10, 17, 5620, 18, 476, 7354, 1075, 220, 16, 10, 17, 28, 18, 1221, 220, 18, 14, 18, 28, 16, 382, 67691, 1588, 11, 358, 646, 614, 7354, 382, 3983, 1077, 752, 7683, 25, 1667, 220, 21, 22, 11, 220, 20, 22, 11, 323, 220, 24, 24, 382, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 11, 1221, 220, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 13, 7414, 382, 40, 1410, 3270, 432, 438, 458, 23606, 25, 220, 24, 24, 488, 320, 21, 22, 481, 220, 20, 22, 8, 284, 220, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 382, 4792, 4977, 4396, 382, 3983, 374, 1052, 2441, 1616, 30, 10696, 448, 46444, 476, 12804, 382, 2461, 3110, 11, 220, 24, 24, 353, 220, 21, 22, 374, 6765, 11, 1075, 220, 21, 21, 18, 18, 11, 17779, 553, 220, 20, 22, 476, 2494, 13, 220, 21, 21, 18, 18, 608, 220, 20, 22, 13, 6771, 752, 11047, 25, 220, 20, 22, 353, 220, 16, 16, 21, 284, 220, 20, 22, 9, 16, 15, 15, 28, 20, 22, 15, 15, 11, 220, 20, 22, 9, 16, 21, 28, 24, 16, 17, 11, 2790, 220, 20, 22, 15, 15, 10, 24, 16, 17, 28, 21, 21, 16, 17, 11, 220, 21, 21, 18, 18, 12, 21, 21, 16, 17, 28, 17, 16, 11, 773, 220, 16, 16, 21, 488, 220, 17, 16, 14, 20, 22, 11, 537, 7546, 11, 323, 537, 220, 16, 15, 24, 382, 2623, 1661, 382, 20, 22, 353, 220, 21, 22, 284, 937, 220, 20, 15, 9, 21, 22, 28, 18, 18, 20, 15, 11, 220, 22, 9, 21, 22, 28, 19, 21, 24, 11, 2790, 220, 18, 18, 20, 15, 10, 19, 21, 24, 28, 18, 23, 16, 24, 11, 1221, 17779, 553, 220, 24, 24, 30, 220, 18, 23, 16, 24, 608, 220, 24, 24, 13, 220, 24, 24, 9, 18, 23, 28, 18, 22, 21, 17, 11, 220, 18, 23, 16, 24, 12, 18, 22, 21, 17, 28, 20, 22, 11, 773, 220, 18, 23, 488, 220, 20, 22, 14, 24, 24, 11, 537, 220, 16, 15, 24, 382, 2623, 3238, 382, 24, 24, 353, 220, 20, 22, 284, 220, 20, 21, 19, 18, 11, 17779, 553, 220, 21, 22, 30, 220, 21, 22, 9, 23, 19, 28, 21, 22, 9, 23, 15, 28, 20, 18, 21, 15, 11, 220, 21, 22, 9, 19, 28, 17, 21, 23, 11, 2790, 220, 20, 18, 21, 15, 10, 17, 21, 23, 28, 20, 21, 17, 23, 11, 220, 20, 21, 19, 18, 12, 20, 21, 17, 23, 28, 16, 20, 11, 773, 220, 23, 19, 488, 220, 16, 20, 14, 21, 22, 11, 537, 7546, 382, 2623, 220, 16, 15, 24, 382, 4416, 11, 5256, 323, 75240, 2803, 2664, 382, 14037, 10601, 25, 220, 24, 24, 488, 220, 21, 22, 284, 220, 16, 21, 21, 11, 1221, 27283, 220, 20, 22, 284, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 30, 220, 16, 21, 21, 481, 220, 20, 22, 382, 16, 21, 21, 481, 220, 20, 15, 284, 220, 16, 16, 21, 11, 27283, 220, 22, 803, 374, 220, 16, 15, 24, 30, 220, 16, 16, 21, 481, 220, 22, 284, 220, 16, 15, 24, 11, 9834, 0, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 382, 16, 21, 21, 481, 220, 20, 22, 25, 220, 16, 21, 21, 481, 220, 20, 15, 284, 220, 16, 16, 21, 11, 220, 16, 16, 21, 481, 220, 22, 284, 220, 16, 15, 24, 11, 9834, 382, 3036, 220, 24, 24, 488, 220, 21, 22, 284, 220, 16, 21, 21, 11, 1221, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 382, 4416, 11, 14822, 220, 16, 25, 220, 24, 24, 488, 220, 21, 22, 284, 220, 16, 21, 21, 271, 8304, 220, 17, 25, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 271, 4792, 1083, 4278, 382, 641, 419, 1142, 11, 358, 1483, 678, 2326, 5109, 5961, 382, 67691, 11, 304, 279, 1156, 1714, 11, 358, 1483, 75240, 1156, 382, 20629, 525, 2697, 382, 3983, 304, 279, 1156, 1714, 11, 358, 1030, 220, 21, 22, 481, 220, 20, 22, 1156, 11, 1221, 912, 311, 220, 24, 24, 382, 8420, 11, 220, 24, 24, 488, 220, 21, 22, 1156, 11, 1221, 32256, 220, 20, 22, 382, 7039, 11, 892, 825, 311, 3042, 30, 358, 1744, 2987, 374, 6915, 382, 3983, 1077, 752, 1490, 279, 2169, 25, 220, 16, 15, 24, 382, 641, 279, 2086, 1714, 11, 432, 594, 30339, 25, 320, 24, 24, 488, 220, 21, 22, 8, 481, 220, 20, 22, 284, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 382, 641, 279, 1156, 25, 220, 24, 24, 488, 320, 21, 22, 481, 220, 20, 22, 8, 284, 220, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 382, 20629, 525, 4396, 382, 31476, 358, 1265, 3270, 432, 438, 264, 3175, 23606, 382, 785, 3491, 2727, 25, 330, 64, 4013, 315, 7354, 1, 476, 330, 64, 3175, 23606, 11436, 40, 646, 653, 2987, 382, 641, 279, 4226, 3561, 11, 358, 646, 5157, 382, 3983, 1077, 752, 1490, 421, 1052, 594, 12804, 476, 2494, 11, 714, 537, 5871, 382, 14037, 1616, 25, 220, 16, 15, 24, 374, 3265, 311, 220, 16, 15, 15, 11, 714, 220, 24, 24, 374, 4558, 220, 16, 15, 15, 382, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 11, 323, 220, 16, 15, 504, 220, 21, 22, 12, 20, 22, 382, 2195, 5961, 382, 40, 1744, 432, 594, 6915, 382, 7039, 11, 369, 279, 4226, 11, 358, 1184, 311, 2182, 432, 304, 279, 3561, 382, 13394, 11, 304, 279, 7354, 11, 358, 1184, 311, 13837, 279, 7525, 382, 641, 279, 1156, 3019, 14319, 29208, 25, 14822, 220, 16, 25, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 11, 14822, 220, 17, 25, 220, 24, 24, 488, 220, 16, 15, 284, 220, 16, 15, 24, 382, 3983, 304, 14822, 220, 17, 11, 358, 2776, 7842, 220, 24, 24, 323, 220, 16, 15, 11, 714, 220, 16, 15, 374, 537, 264, 1372, 11, 432, 594, 279, 1102, 13, 1988, 304, 279, 2266, 11, 432, 1265, 387, 21555, 11, 438, 817, 279, 3110, 382, 67691, 11, 304, 279, 2086, 25, 14822, 220, 16, 25, 220, 24, 24, 488, 220, 21, 22, 284, 220, 16, 21, 21, 11, 14822, 220, 17, 25, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 382, 8420, 11, 220, 16, 21, 21, 374, 28439, 382, 40, 1410, 3270, 279, 23606, 5961, 382, 12549, 279, 3491, 2727, 330, 3182, 458, 23606, 497, 714, 432, 6147, 7354, 476, 3175, 23606, 382, 40, 1744, 358, 3278, 728, 448, 279, 3175, 23606, 369, 38975, 382, 4416, 11, 320, 24, 24, 488, 220, 21, 22, 8, 481, 220, 20, 22, 284, 220, 16, 15, 24, 271, 2195, 220, 24, 24, 488, 320, 21, 22, 481, 220, 20, 22, 8, 284, 220, 16, 15, 24, 271, 49244, 1616, 382, 31476, 2041, 73975, 11, 714, 1973, 12850, 382, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 382, 7039, 11, 5256, 323, 75240, 614, 1852, 53056, 11, 2115, 311, 1290, 382, 4416, 11, 220, 24, 24, 488, 220, 21, 22, 284, 220, 16, 21, 21, 11, 1221, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 11, 892, 374, 4396, 382, 67691, 11, 421, 358, 653, 220, 21, 22, 481, 220, 20, 22, 488, 220, 24, 24, 11, 429, 594, 220, 16, 15, 488, 220, 24, 24, 284, 220, 16, 15, 24, 11, 1083, 4396, 382, 4416, 11, 304, 2176, 5048, 11, 2041, 73975, 11, 432, 4278, 1576, 315, 2115, 311, 1290, 16460, 382, 21, 22, 481, 220, 20, 22, 488, 220, 24, 24, 25, 1156, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 11, 1221, 220, 16, 15, 488, 220, 24, 24, 284, 220, 16, 15, 24, 382, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 25, 220, 24, 24, 488, 220, 21, 22, 284, 220, 16, 21, 21, 11, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 382, 20629, 6915, 382, 4416, 11, 358, 646, 3270, 432, 438, 220, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 24, 382, 2195, 220, 21, 22, 481, 220, 20, 22, 488, 220, 24, 24, 284, 220, 16, 15, 24, 382, 40, 1744, 220, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 374, 803, 5810, 382, 12549, 220, 24, 24, 374, 1156, 304, 279, 1140, 11, 714, 537, 5871, 382, 641, 279, 1140, 11, 432, 594, 508, 24, 24, 11, 220, 20, 22, 11, 220, 21, 22, 1125, 714, 1973, 3171, 944, 4925, 369, 279, 23606, 382, 641, 279, 7354, 11, 358, 2578, 1184, 311, 990, 1105, 304, 1973, 11, 714, 537, 5189, 382, 40, 1744, 369, 279, 23606, 11, 432, 594, 6915, 382, 7039, 11, 311, 3042, 382, 40, 1744, 358, 3278, 3270, 279, 3175, 23606, 382, 3983, 304, 279, 4226, 3561, 11, 432, 1265, 387, 43810, 304, 366, 9217, 29, 9492, 382, 13394, 11, 369, 279, 23606, 11, 358, 1184, 311, 1473, 432, 16819, 220, 16, 15, 24, 382, 31476, 358, 646, 3270, 25, 220, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 24, 271, 3983, 304, 279, 2266, 11, 2474, 432, 594, 279, 6291, 11, 432, 1265, 387, 2797, 382, 14037, 3166, 25, 304, 279, 3491, 11, 432, 2727, 330, 3182, 458, 23606, 429, 16819, 220, 16, 15, 24, 497, 773, 358, 1265, 614, 458, 7493, 6144, 311, 220, 16, 15, 24, 382, 4416, 11, 320, 24, 24, 488, 220, 21, 22, 8, 481, 220, 20, 22, 476, 2494, 382, 3983, 438, 358, 1053, 11, 2041, 73975, 432, 4278, 382, 1249, 387, 23560, 11, 358, 646, 990, 73975, 382, 3983, 537, 5871, 382, 40, 1744, 432, 594, 6915, 382, 31476, 358, 1265, 3270, 279, 7354, 311, 387, 12966, 448, 279, 3110, 382, 641, 279, 3110, 11, 807, 1030, 1378, 2606, 382, 40, 1744, 358, 3278, 653, 2176, 369, 31273, 11, 714, 279, 3491, 2727, 330, 46430, 697, 4226, 1, 304, 279, 3561, 11, 773, 825, 374, 3322, 382, 40, 3278, 728, 448, 279, 23606, 382, 4416, 11, 366, 9217, 29, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 24, 522, 9217, 1339, 3983, 304, 279, 23606, 11, 358, 1184, 311, 990, 279, 5109, 11, 323, 432, 1265, 15442, 311, 220, 16, 15, 24, 382, 24, 24, 488, 220, 21, 22, 374, 220, 16, 21, 21, 11, 27283, 220, 20, 22, 374, 220, 16, 15, 24, 11, 9834, 382, 1249, 3270, 432, 438, 458, 7493, 25, 220, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 271, 3983, 358, 1184, 311, 1473, 432, 16819, 220, 16, 15, 24, 382, 641, 279, 4226, 11, 358, 646, 3270, 279, 23606, 382, 67691, 11, 304, 279, 3019, 14319, 29208, 382, 40, 1744, 2987, 374, 6915, 382, 3983, 1077, 752, 1490, 279, 3491, 25, 330, 21732, 6291, 1265, 2924, 264, 4013, 315, 7354, 1112, 476, 432, 1265, 387, 264, 3175, 23606, 1837, 40, 646, 5157, 382, 40, 1744, 279, 3175, 23606, 374, 63594, 382, 4416, 11, 358, 3278, 653, 429, 382, 3983, 304, 279, 1140, 11, 220, 20, 22, 374, 2086, 11, 714, 304, 279, 23606, 11, 358, 614, 220, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 11, 892, 5711, 678, 382, 14037, 10601, 25, 1128, 421, 358, 990, 12804, 1939, 2461, 3110, 11, 220, 16, 15, 24, 284, 220, 16, 15, 15, 488, 220, 24, 11, 714, 537, 10950, 382, 21, 22, 353, 220, 17, 284, 220, 16, 18, 19, 11, 2238, 2409, 11, 27283, 220, 17, 20, 11, 902, 382, 20, 22, 353, 220, 17, 284, 220, 16, 16, 19, 11, 3265, 311, 220, 16, 15, 24, 11, 220, 16, 16, 19, 481, 220, 20, 11, 714, 902, 220, 20, 382, 16, 16, 19, 481, 220, 20, 11, 714, 358, 614, 220, 24, 24, 323, 220, 21, 22, 382, 16, 16, 19, 481, 220, 20, 11, 714, 220, 20, 537, 2500, 382, 7, 20, 22, 353, 220, 17, 8, 481, 2494, 11, 714, 358, 1513, 944, 614, 220, 17, 11, 358, 614, 311, 990, 279, 5109, 3055, 11, 773, 358, 646, 944, 30270, 553, 220, 17, 7241, 358, 42430, 432, 382, 2461, 3110, 11, 358, 1410, 653, 12804, 311, 633, 64895, 382, 10048, 2900, 358, 653, 220, 24, 24, 608, 220, 20, 22, 476, 2494, 382, 24, 24, 608, 220, 20, 22, 284, 220, 18, 18, 14, 16, 24, 11, 13187, 220, 16, 13, 22, 18, 21, 11, 537, 7546, 382, 12209, 30270, 553, 220, 21, 22, 30, 220, 16, 13, 22, 18, 21, 353, 220, 21, 22, 21103, 230, 220, 16, 16, 21, 13, 2494, 11, 537, 220, 16, 15, 24, 382, 2623, 1661, 382, 21, 22, 608, 220, 20, 22, 21103, 230, 220, 16, 13, 16, 22, 20, 11, 3039, 220, 24, 24, 21103, 230, 220, 16, 16, 21, 13, 18, 17, 20, 11, 537, 220, 16, 15, 24, 382, 2753, 382, 4416, 11, 5256, 323, 75240, 525, 279, 1616, 311, 728, 382, 54815, 11, 220, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 24, 374, 4396, 382, 1249, 3270, 432, 448, 279, 5109, 304, 1973, 25, 714, 537, 5871, 382, 40, 1744, 358, 2776, 1661, 624, 522, 26865, 397, 1249, 11625, 279, 3491, 315, 6825, 458, 23606, 6144, 311, 220, 16, 15, 24, 1667, 279, 5109, 508, 24, 24, 11, 220, 20, 22, 11, 220, 21, 22, 60, 448, 6770, 34784, 7525, 17973, 11, 85922, 11777, 608, 701, 1817, 1483, 3055, 11, 358, 6509, 3204, 27459, 13, 8704, 220, 16, 15, 24, 374, 3265, 311, 279, 2629, 315, 220, 24, 24, 323, 220, 21, 22, 320, 8206, 374, 220, 16, 21, 21, 701, 32256, 287, 220, 20, 22, 504, 419, 2629, 3059, 304, 220, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 13, 1096, 5486, 5711, 5256, 323, 75240, 11, 892, 525, 5420, 7525, 382, 785, 23606, 646, 387, 5326, 438, 510, 59, 9640, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 24, 198, 59, 2533, 1986, 374, 2697, 1576, 510, 12, 78646, 323, 75240, 525, 10660, 2115, 311, 1290, 25, 1156, 11, 17767, 24, 24, 488, 220, 21, 22, 284, 220, 16, 21, 21, 59, 701, 1221, 17767, 16, 21, 21, 481, 220, 20, 22, 284, 220, 16, 15, 24, 59, 4292, 12, 2009, 5109, 504, 279, 1140, 525, 1483, 6896, 3055, 382, 92014, 11, 279, 23606, 646, 387, 13302, 448, 73975, 369, 31273, 11, 714, 807, 525, 537, 5871, 4152, 311, 2115, 4686, 6701, 16460, 369, 7525, 315, 279, 1852, 53056, 510, 59, 9640, 7, 24, 24, 488, 220, 21, 22, 8, 481, 220, 20, 22, 284, 220, 16, 15, 24, 198, 59, 2533, 20629, 7586, 7540, 279, 2169, 1372, 220, 16, 15, 24, 382, 27, 9217, 397, 24, 24, 488, 220, 21, 22, 481, 220, 20, 22, 284, 220, 16, 15, 24, 198, 522, 9217, 29, 151643, 198]
+labels:
+<think>
+I have the numbers [99, 57, 67] and need to make 109 using basic arithmetic operations: addition, subtraction, multiplication, and division. Each number can only be used once.
+
+First, I should consider what operations might work. Since 109 is a bit larger than the numbers, multiplication might be involved, but 99 and 67 are both large, and 57 is smaller. Let me see the differences or sums.
+
+If I add 99 and 57, that's 99 + 57 = 156, which is bigger than 109. Then I have 67 left. If I subtract 67 from 156, that's 156 - 67 = 89, which is less than 109. 89 is too small. If I do 156 - 67 = 89, not 109.
+
+Maybe I can multiply. 99 times something. 99 * 1 = 99, too small. 99 * 2 = 198, too big. But I have to use the numbers given.
+
+Perhaps division. 99 divided by something. 99 / 1 = 99, not helpful. 99 / 0.9 or something, but I have to use the numbers.
+
+Another idea: maybe I can do 67 + 57 = 124, then 124 - 15, but I don't have 15, I have 99. 124 - 99 = 25, not 109.
+
+Not working. Let's list the numbers: 99, 57, 67. Target 109.
+
+Perhaps I need to use subtraction or division to get smaller numbers.
+
+Maybe (99 * something) + something.
+
+99 * 1 = 99, then I need +10, but I have 57 and 67, both larger than 10.
+
+67 - 57 = 10, then 99 + 10 = 109. Oh! That could work.
+
+So, first, 67 - 57 = 10, then 99 + 10 = 109.
+
+But in terms of steps, I need to use the numbers only once, and in this case, I used 67 and 57 to make 10, then added to 99.
+
+So, Step 1: 67 - 57 = 10
+
+Step 2: 99 + 10 = 109
+
+But 10 is not one of the original numbers; it's derived. But in the context, it should be fine, as per the example.
+
+In the example with [1,2,3] to make 1, they did (1+2)/3 or steps like 1+2=3 then 3/3=1.
+
+Similarly here, I can have steps.
+
+But let me confirm: using 67, 57, and 99.
+
+67 - 57 = 10, then 99 + 10 = 109. Yes.
+
+I could write it as an equation: 99 + (67 - 57) = 99 + 10 = 109.
+
+That seems correct.
+
+But is there another way? Maybe with multiplication or division.
+
+For example, 99 * 67 is huge, like 6633, divided by 57 or something. 6633 / 57. Let me calculate: 57 * 116 = 57*100=5700, 57*16=912, total 5700+912=6612, 6633-6612=21, so 116 + 21/57, not integer, and not 109.
+
+Not good.
+
+57 * 67 = ? 50*67=3350, 7*67=469, total 3350+469=3819, then divided by 99? 3819 / 99. 99*38=3762, 3819-3762=57, so 38 + 57/99, not 109.
+
+Not working.
+
+99 * 57 = 5643, divided by 67? 67*84=67*80=5360, 67*4=268, total 5360+268=5628, 5643-5628=15, so 84 + 15/67, not integer.
+
+Not 109.
+
+So, addition and subtraction seem better.
+
+Another combination: 99 + 67 = 166, then minus 57 = 166 - 57 = 109? 166 - 57.
+
+166 - 50 = 116, minus 7 more is 109? 116 - 7 = 109, yes! 166 - 57 = 109.
+
+166 - 57: 166 - 50 = 116, 116 - 7 = 109, yes.
+
+And 99 + 67 = 166, then 166 - 57 = 109.
+
+So, Step 1: 99 + 67 = 166
+
+Step 2: 166 - 57 = 109
+
+That also works.
+
+In this case, I used all three numbers directly.
+
+Similarly, in the first method, I used subtraction first.
+
+Both are valid.
+
+But in the first method, I had 67 - 57 first, then add to 99.
+
+Here, 99 + 67 first, then subtract 57.
+
+Now, which one to present? I think either is fine.
+
+But let me see the target: 109.
+
+In the second method, it's straightforward: (99 + 67) - 57 = 166 - 57 = 109.
+
+In the first: 99 + (67 - 57) = 99 + 10 = 109.
+
+Both are correct.
+
+Perhaps I should write it as a single equation.
+
+The problem says: "a series of steps" or "a single equation".
+
+I can do either.
+
+In the answer format, I can choose.
+
+But let me see if there's division or something, but not necessary.
+
+Another way: 109 is close to 100, but 99 is almost 100.
+
+99 + 10 = 109, and 10 from 67-57.
+
+Or directly.
+
+I think it's fine.
+
+Now, for the answer, I need to put it in the format.
+
+Also, in the steps, I need to specify the operations.
+
+In the first step-by-step: Step 1: 67 - 57 = 10, Step 2: 99 + 10 = 109.
+
+But in Step 2, I'm adding 99 and 10, but 10 is not a number, it's the result. But in the context, it should be acceptable, as per the example.
+
+Similarly, in the second: Step 1: 99 + 67 = 166, Step 2: 166 - 57 = 109.
+
+Here, 166 is intermediate.
+
+I could write the equation directly.
+
+Since the problem says "create an equation", but it allows steps or single equation.
+
+I think I'll go with the single equation for simplicity.
+
+So, (99 + 67) - 57 = 109
+
+Or 99 + (67 - 57) = 109
+
+Either way.
+
+Perhaps without parentheses, but order matters.
+
+99 + 67 - 57.
+
+Now, addition and subtraction have same precedence, left to right.
+
+So, 99 + 67 = 166, then 166 - 57 = 109, which is correct.
+
+Similarly, if I do 67 - 57 + 99, that's 10 + 99 = 109, also correct.
+
+So, in both cases, without parentheses, it works because of left to right evaluation.
+
+67 - 57 + 99: first 67 - 57 = 10, then 10 + 99 = 109.
+
+99 + 67 - 57: 99 + 67 = 166, 166 - 57 = 109.
+
+Both fine.
+
+So, I can write it as 99 + 67 - 57 = 109.
+
+Or 67 - 57 + 99 = 109.
+
+I think 99 + 67 - 57 is more natural.
+
+Since 99 is first in the list, but not necessary.
+
+In the list, it's [99, 57, 67], but order doesn't matter for the equation.
+
+In the steps, I might need to use them in order, but not specified.
+
+I think for the equation, it's fine.
+
+Now, to present.
+
+I think I'll write the single equation.
+
+But in the answer format, it should be enclosed in <answer> tags.
+
+Also, for the equation, I need to show it equals 109.
+
+Perhaps I can write: 99 + 67 - 57 = 109
+
+But in the context, since it's the solution, it should be clear.
+
+Another thing: in the problem, it says "create an equation that equals 109", so I should have an expression equal to 109.
+
+So, (99 + 67) - 57 or something.
+
+But as I said, without parentheses it works.
+
+To be precise, I can use parentheses.
+
+But not necessary.
+
+I think it's fine.
+
+Perhaps I should write the steps to be consistent with the example.
+
+In the example, they had two options.
+
+I think I'll do both for clarity, but the problem says "give your answer" in the format, so one is enough.
+
+I'll go with the equation.
+
+So, <answer>99 + 67 - 57 = 109</answer>
+
+But in the equation, I need to use the numbers, and it should evaluate to 109.
+
+99 + 67 is 166, minus 57 is 109, yes.
+
+To write it as an expression: 99 + 67 - 57
+
+But I need to show it equals 109.
+
+In the answer, I can write the equation.
+
+Similarly, in the step-by-step.
+
+I think either is fine.
+
+But let me see the problem: "your solution should include a series of steps... or it should be a single equation"
+
+I can choose.
+
+I think the single equation is concise.
+
+So, I'll do that.
+
+But in the list, 57 is second, but in the equation, I have 99 + 67 - 57, which uses all.
+
+Another combination: what if I use division?
+
+For example, 109 = 100 + 9, but not helpful.
+
+67 * 2 = 134, too big, minus 25, no.
+
+57 * 2 = 114, close to 109, 114 - 5, but no 5.
+
+114 - 5, but I have 99 and 67.
+
+114 - 5, but 5 not available.
+
+(57 * 2) - something, but I don't have 2, I have to use the numbers once, so I can't multiply by 2 unless I derive it.
+
+For example, I could do division to get fractions.
+
+Suppose I do 99 / 57 or something.
+
+99 / 57 = 33/19, approximately 1.736, not integer.
+
+Then multiply by 67? 1.736 * 67  116. something, not 109.
+
+Not good.
+
+67 / 57  1.175, times 99  116.325, not 109.
+
+No.
+
+So, addition and subtraction are the way to go.
+
+Therefore, 99 + 67 - 57 = 109 is correct.
+
+To write it with the numbers in order: but not necessary.
+
+I think I'm good.
+</think>
+To solve the problem of creating an equation equal to 109 using the numbers [99, 57, 67] with basic arithmetic operations (+, -, *, /), each used once, I considered possible combinations. Since 109 is close to the sum of 99 and 67 (which is 166), subtracting 57 from this sum results in 166 - 57 = 109. This approach uses addition and subtraction, which are allowed operations.
+
+The equation can be written as:
+\[
+99 + 67 - 57 = 109
+\]
+
+This is valid because:
+- Addition and subtraction are performed left to right: first, \(99 + 67 = 166\), then \(166 - 57 = 109\).
+- All numbers from the list are used exactly once.
+
+Alternatively, the equation can be expressed with parentheses for clarity, but they are not necessary due to left-to-right evaluation for operations of the same precedence:
+\[
+(99 + 67) - 57 = 109
+\]
+
+Both forms yield the target number 109.
+
+<answer>
+99 + 67 - 57 = 109
+</answer><|endoftext|>
+
+Saving the dataset (0/1 shards):   0%|          | 0/3598 [00:00<?, ? examples/s]Saving the dataset (0/1 shards):  28%|       | 1000/3598 [00:00<00:01, 1303.45 examples/s]Saving the dataset (0/1 shards):  56%|    | 2000/3598 [00:00<00:00, 2466.38 examples/s]Saving the dataset (1/1 shards): 100%|| 3598/3598 [00:01<00:00, 2466.38 examples/s]Saving the dataset (1/1 shards): 100%|| 3598/3598 [00:01<00:00, 2204.39 examples/s]
+Saving the dataset (0/1 shards):   0%|          | 0/400 [00:00<?, ? examples/s]Saving the dataset (1/1 shards): 100%|| 400/400 [00:00<00:00, 9897.65 examples/s]Saving the dataset (1/1 shards): 100%|| 400/400 [00:00<00:00, 9812.67 examples/s]
+[INFO|2025-10-22 20:35:22] llamafactory.data.loader:143 >> Tokenized dataset is saved at /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/tokenized/my_custom_sft12.
+[INFO|2025-10-22 20:35:22] llamafactory.data.loader:143 >> Please launch the training with `tokenized_path: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/tokenized/my_custom_sft12`.
+[INFO|configuration_utils.py:765] 2025-10-22 20:35:22,705 >> loading configuration file config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/config.json
+[INFO|configuration_utils.py:839] 2025-10-22 20:35:22,705 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+
+[INFO|2025-10-22 20:35:22] llamafactory.model.model_utils.kv_cache:143 >> KV cache is disabled during training.
+[WARNING|logging.py:328] 2025-10-22 20:35:23,064 >> `torch_dtype` is deprecated! Use `dtype` instead!
+[INFO|modeling_utils.py:1172] 2025-10-22 20:35:23,065 >> loading weights file model.safetensors from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/model.safetensors
+[INFO|modeling_utils.py:2341] 2025-10-22 20:35:23,066 >> Instantiating Qwen2ForCausalLM model under default dtype torch.float16.
+[INFO|configuration_utils.py:986] 2025-10-22 20:35:23,067 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "use_cache": false
+}
+
+`torch_dtype` is deprecated! Use `dtype` instead!
+[INFO|configuration_utils.py:941] 2025-10-22 20:35:23,333 >> loading configuration file generation_config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/generation_config.json
+[INFO|configuration_utils.py:986] 2025-10-22 20:35:23,333 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048
+}
+
+[INFO|dynamic_module_utils.py:423] 2025-10-22 20:35:23,367 >> Could not locate the custom_generate/generate.py inside Qwen/Qwen2.5-0.5B.
+[INFO|2025-10-22 20:35:23] llamafactory.model.model_utils.checkpointing:143 >> Gradient checkpointing enabled.
+[INFO|2025-10-22 20:35:23] llamafactory.model.model_utils.attention:143 >> Using torch SDPA for faster training and inference.
+[INFO|2025-10-22 20:35:23] llamafactory.model.adapter:143 >> Upcasting trainable params to float32.
+[INFO|2025-10-22 20:35:23] llamafactory.model.adapter:143 >> Fine-tuning method: LoRA
+[INFO|2025-10-22 20:35:23] llamafactory.model.model_utils.misc:143 >> Found linear modules: gate_proj,up_proj,v_proj,q_proj,o_proj,down_proj,k_proj
+[INFO|2025-10-22 20:35:23] llamafactory.model.loader:143 >> trainable params: 4,399,104 || all params: 498,431,872 || trainable%: 0.8826
+[WARNING|trainer.py:906] 2025-10-22 20:35:23,620 >> The model is already on multiple devices. Skipping the move to device specified in `args`.
+[INFO|trainer.py:699] 2025-10-22 20:35:23,623 >> max_steps is given, it will override any value given in num_train_epochs
+[INFO|trainer.py:749] 2025-10-22 20:35:23,623 >> Using auto half precision backend
+[WARNING|2025-10-22 20:35:23] llamafactory.train.callbacks:154 >> Previous trainer log in this folder will be deleted.
+[WARNING|trainer.py:982] 2025-10-22 20:35:23,627 >> The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.
+The model is already on multiple devices. Skipping the move to device specified in `args`.
+The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.
+[INFO|trainer.py:2519] 2025-10-22 20:35:26,876 >> ***** Running training *****
+[INFO|trainer.py:2520] 2025-10-22 20:35:26,876 >>   Num examples = 3,598
+[INFO|trainer.py:2521] 2025-10-22 20:35:26,876 >>   Num Epochs = 1
+[INFO|trainer.py:2522] 2025-10-22 20:35:26,876 >>   Instantaneous batch size per device = 1
+[INFO|trainer.py:2525] 2025-10-22 20:35:26,876 >>   Total train batch size (w. parallel, distributed & accumulation) = 4
+[INFO|trainer.py:2526] 2025-10-22 20:35:26,876 >>   Gradient Accumulation steps = 1
+[INFO|trainer.py:2527] 2025-10-22 20:35:26,876 >>   Total optimization steps = 100
+[INFO|trainer.py:2528] 2025-10-22 20:35:26,878 >>   Number of trainable parameters = 4,399,104
+[INFO|integration_utils.py:867] 2025-10-22 20:35:26,899 >> Automatic Weights & Biases logging enabled, to disable set os.environ["WANDB_DISABLED"] = "true"
+wandb: Currently logged in as: zsprague (ut_nlp_deduce) to https://api.wandb.ai. Use `wandb login --relogin` to force relogin
+wandb: Tracking run with wandb version 0.22.2
+wandb: Run data is saved locally in /scratch/zrs2020/LlamaFactoryHelper/wandb/run-20251022_203527-54101z6o
+wandb: Run `wandb offline` to turn off syncing.
+wandb: Syncing run interactive_test
+wandb:  View project at https://wandb.ai/ut_nlp_deduce/llamafactory
+wandb:  View run at https://wandb.ai/ut_nlp_deduce/llamafactory/runs/54101z6o
+  0%|          | 0/100 [00:00<?, ?it/s]  1%|          | 1/100 [00:00<01:22,  1.21it/s]  2%|         | 2/100 [00:01<00:50,  1.94it/s]  3%|         | 3/100 [00:01<00:38,  2.50it/s]  4%|         | 4/100 [00:01<00:33,  2.88it/s]  5%|         | 5/100 [00:02<00:41,  2.31it/s]  6%|         | 6/100 [00:02<00:34,  2.72it/s]  7%|         | 7/100 [00:02<00:31,  2.97it/s]  8%|         | 8/100 [00:03<00:29,  3.13it/s]  9%|         | 9/100 [00:03<00:27,  3.30it/s] 10%|         | 10/100 [00:03<00:34,  2.62it/s]                                                {'loss': 1.286, 'grad_norm': 0.36362695693969727, 'learning_rate': 4.55e-05, 'epoch': 0.01}
+ 10%|         | 10/100 [00:03<00:34,  2.62it/s] 11%|         | 11/100 [00:04<00:38,  2.30it/s] 12%|        | 12/100 [00:04<00:36,  2.41it/s] 13%|        | 13/100 [00:05<00:37,  2.34it/s] 14%|        | 14/100 [00:05<00:34,  2.50it/s] 15%|        | 15/100 [00:05<00:33,  2.55it/s] 16%|        | 16/100 [00:06<00:29,  2.86it/s] 17%|        | 17/100 [00:06<00:28,  2.89it/s] 18%|        | 18/100 [00:06<00:28,  2.85it/s] 19%|        | 19/100 [00:07<00:28,  2.81it/s] 20%|        | 20/100 [00:07<00:27,  2.95it/s]                                                {'loss': 1.1751, 'grad_norm': 0.389845609664917, 'learning_rate': 4.05e-05, 'epoch': 0.02}
+ 20%|        | 20/100 [00:07<00:27,  2.95it/s] 21%|        | 21/100 [00:08<00:32,  2.43it/s] 22%|       | 22/100 [00:08<00:30,  2.56it/s] 23%|       | 23/100 [00:08<00:29,  2.61it/s] 24%|       | 24/100 [00:09<00:26,  2.84it/s] 25%|       | 25/100 [00:09<00:32,  2.31it/s] 26%|       | 26/100 [00:10<00:28,  2.59it/s] 27%|       | 27/100 [00:10<00:25,  2.85it/s] 28%|       | 28/100 [00:10<00:24,  2.92it/s] 29%|       | 29/100 [00:10<00:23,  3.01it/s] 30%|       | 30/100 [00:11<00:22,  3.11it/s]                                                {'loss': 1.1373, 'grad_norm': 0.4257446825504303, 'learning_rate': 3.55e-05, 'epoch': 0.03}
+ 30%|       | 30/100 [00:11<00:22,  3.11it/s] 31%|       | 31/100 [00:11<00:23,  2.92it/s] 32%|      | 32/100 [00:11<00:22,  3.05it/s] 33%|      | 33/100 [00:12<00:20,  3.19it/s] 34%|      | 34/100 [00:12<00:24,  2.67it/s] 35%|      | 35/100 [00:13<00:23,  2.75it/s] 36%|      | 36/100 [00:13<00:22,  2.88it/s] 37%|      | 37/100 [00:13<00:19,  3.26it/s] 38%|      | 38/100 [00:13<00:18,  3.37it/s] 39%|      | 39/100 [00:14<00:16,  3.62it/s] 40%|      | 40/100 [00:14<00:19,  3.13it/s]                                                {'loss': 1.0636, 'grad_norm': 0.42937755584716797, 'learning_rate': 3.05e-05, 'epoch': 0.04}
+ 40%|      | 40/100 [00:14<00:19,  3.13it/s] 41%|      | 41/100 [00:14<00:18,  3.24it/s] 42%|     | 42/100 [00:15<00:17,  3.37it/s] 43%|     | 43/100 [00:15<00:18,  3.14it/s] 44%|     | 44/100 [00:15<00:16,  3.30it/s] 45%|     | 45/100 [00:15<00:16,  3.33it/s] 46%|     | 46/100 [00:16<00:17,  3.15it/s] 47%|     | 47/100 [00:16<00:15,  3.40it/s] 48%|     | 48/100 [00:16<00:15,  3.38it/s] 49%|     | 49/100 [00:17<00:15,  3.24it/s] 50%|     | 50/100 [00:17<00:15,  3.23it/s]                                                {'loss': 1.0329, 'grad_norm': 0.4311900734901428, 'learning_rate': 2.5500000000000003e-05, 'epoch': 0.06}
+ 50%|     | 50/100 [00:17<00:15,  3.23it/s][INFO|trainer.py:4309] 2025-10-22 20:35:45,420 >> Saving model checkpoint to /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/checkpoint-50
+[INFO|configuration_utils.py:765] 2025-10-22 20:35:45,553 >> loading configuration file config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/config.json
+[INFO|configuration_utils.py:839] 2025-10-22 20:35:45,554 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+
+[INFO|tokenization_utils_base.py:2421] 2025-10-22 20:35:45,732 >> chat template saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/checkpoint-50/chat_template.jinja
+[INFO|tokenization_utils_base.py:2590] 2025-10-22 20:35:45,737 >> tokenizer config file saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/checkpoint-50/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2599] 2025-10-22 20:35:45,757 >> Special tokens file saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/checkpoint-50/special_tokens_map.json
+ 51%|     | 51/100 [00:18<00:27,  1.76it/s] 52%|    | 52/100 [00:19<00:23,  2.02it/s] 53%|    | 53/100 [00:19<00:22,  2.10it/s] 54%|    | 54/100 [00:19<00:20,  2.24it/s] 55%|    | 55/100 [00:20<00:18,  2.39it/s] 56%|    | 56/100 [00:20<00:16,  2.59it/s] 57%|    | 57/100 [00:20<00:15,  2.77it/s] 58%|    | 58/100 [00:21<00:14,  2.82it/s] 59%|    | 59/100 [00:21<00:14,  2.89it/s] 60%|    | 60/100 [00:21<00:13,  3.01it/s]                                                {'loss': 0.9982, 'grad_norm': 0.4509340524673462, 'learning_rate': 2.05e-05, 'epoch': 0.07}
+ 60%|    | 60/100 [00:21<00:13,  3.01it/s] 61%|    | 61/100 [00:22<00:12,  3.06it/s] 62%|   | 62/100 [00:22<00:12,  3.14it/s] 63%|   | 63/100 [00:22<00:11,  3.29it/s] 64%|   | 64/100 [00:22<00:10,  3.45it/s] 65%|   | 65/100 [00:23<00:10,  3.34it/s] 66%|   | 66/100 [00:23<00:10,  3.14it/s] 67%|   | 67/100 [00:23<00:09,  3.33it/s] 68%|   | 68/100 [00:24<00:09,  3.37it/s] 69%|   | 69/100 [00:24<00:09,  3.22it/s] 70%|   | 70/100 [00:24<00:09,  3.06it/s]                                                {'loss': 0.9991, 'grad_norm': 0.4352080523967743, 'learning_rate': 1.55e-05, 'epoch': 0.08}
+ 70%|   | 70/100 [00:24<00:09,  3.06it/s] 71%|   | 71/100 [00:25<00:09,  3.20it/s] 72%|  | 72/100 [00:25<00:08,  3.46it/s] 73%|  | 73/100 [00:25<00:07,  3.72it/s] 74%|  | 74/100 [00:26<00:09,  2.77it/s] 75%|  | 75/100 [00:26<00:08,  3.00it/s] 76%|  | 76/100 [00:26<00:07,  3.32it/s] 77%|  | 77/100 [00:26<00:07,  3.20it/s] 78%|  | 78/100 [00:27<00:06,  3.53it/s] 79%|  | 79/100 [00:27<00:05,  3.54it/s] 80%|  | 80/100 [00:27<00:05,  3.72it/s]                                                {'loss': 0.9537, 'grad_norm': 0.4677208364009857, 'learning_rate': 1.05e-05, 'epoch': 0.09}
+ 80%|  | 80/100 [00:27<00:05,  3.72it/s] 81%|  | 81/100 [00:27<00:05,  3.74it/s] 82%| | 82/100 [00:28<00:04,  3.71it/s] 83%| | 83/100 [00:28<00:05,  3.27it/s] 84%| | 84/100 [00:28<00:04,  3.29it/s] 85%| | 85/100 [00:29<00:04,  3.35it/s] 86%| | 86/100 [00:29<00:04,  3.41it/s] 87%| | 87/100 [00:29<00:03,  3.43it/s] 88%| | 88/100 [00:30<00:03,  3.54it/s] 89%| | 89/100 [00:30<00:03,  3.63it/s] 90%| | 90/100 [00:30<00:02,  3.47it/s]                                                {'loss': 0.9677, 'grad_norm': 0.46978959441185, 'learning_rate': 5.500000000000001e-06, 'epoch': 0.1}
+ 90%| | 90/100 [00:30<00:02,  3.47it/s] 91%| | 91/100 [00:30<00:02,  3.36it/s] 92%|| 92/100 [00:31<00:03,  2.64it/s] 93%|| 93/100 [00:31<00:02,  2.71it/s] 94%|| 94/100 [00:32<00:02,  2.74it/s] 95%|| 95/100 [00:32<00:01,  2.93it/s] 96%|| 96/100 [00:32<00:01,  3.09it/s] 97%|| 97/100 [00:33<00:00,  3.24it/s] 98%|| 98/100 [00:33<00:00,  3.13it/s] 99%|| 99/100 [00:33<00:00,  3.00it/s]100%|| 100/100 [00:34<00:00,  2.92it/s]                                                 {'loss': 0.9472, 'grad_norm': 0.4593953490257263, 'learning_rate': 5.000000000000001e-07, 'epoch': 0.11}
+100%|| 100/100 [00:34<00:00,  2.92it/s][INFO|trainer.py:4309] 2025-10-22 20:36:02,040 >> Saving model checkpoint to /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/checkpoint-100
+[INFO|configuration_utils.py:765] 2025-10-22 20:36:02,193 >> loading configuration file config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/config.json
+[INFO|configuration_utils.py:839] 2025-10-22 20:36:02,194 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+
+[INFO|tokenization_utils_base.py:2421] 2025-10-22 20:36:02,350 >> chat template saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/checkpoint-100/chat_template.jinja
+[INFO|tokenization_utils_base.py:2590] 2025-10-22 20:36:02,355 >> tokenizer config file saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/checkpoint-100/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2599] 2025-10-22 20:36:02,360 >> Special tokens file saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/checkpoint-100/special_tokens_map.json
+[INFO|trainer.py:2810] 2025-10-22 20:36:02,873 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+                                                 {'train_runtime': 35.9957, 'train_samples_per_second': 11.112, 'train_steps_per_second': 2.778, 'train_loss': 1.0560624694824219, 'epoch': 0.11}
+100%|| 100/100 [00:35<00:00,  2.92it/s]100%|| 100/100 [00:35<00:00,  2.86it/s]
+[INFO|trainer.py:4309] 2025-10-22 20:36:02,884 >> Saving model checkpoint to /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints
+[INFO|configuration_utils.py:765] 2025-10-22 20:36:02,976 >> loading configuration file config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/config.json
+[INFO|configuration_utils.py:839] 2025-10-22 20:36:02,977 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+
+[INFO|tokenization_utils_base.py:2421] 2025-10-22 20:36:03,093 >> chat template saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/chat_template.jinja
+[INFO|tokenization_utils_base.py:2590] 2025-10-22 20:36:03,098 >> tokenizer config file saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2599] 2025-10-22 20:36:03,103 >> Special tokens file saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/special_tokens_map.json
+***** train metrics *****
+  epoch                    =     0.1111
+  total_flos               =  2407106GF
+  train_loss               =     1.0561
+  train_runtime            = 0:00:35.99
+  train_samples_per_second =     11.112
+  train_steps_per_second   =      2.778
+[INFO|modelcard.py:456] 2025-10-22 20:36:03,259 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+gl064:2626307:2626307 [1] NCCL INFO comm 0x15ba7840 rank 1 nranks 4 cudaDev 1 busId 59000 - Destroy COMPLETE
+gl064:2626306:2626306 [0] NCCL INFO comm 0x13d4e850 rank 0 nranks 4 cudaDev 0 busId 47000 - Destroy COMPLETE
+[1;34mwandb[0m: 
+[1;34mwandb[0m:  View run [33minteractive_test[0m at: [34m[0m
+[1;34mwandb[0m: Find logs at: [1;35mwandb/run-20251022_203527-54101z6o/logs[0m
+
+========================================
+Training completed successfully
+End Time: Wed Oct 22 08:36:05 PM EDT 2025
+========================================
+
+========================================
+STAGE 2: Merging/Exporting Model
+Start Time: Wed Oct 22 08:36:05 PM EDT 2025
+========================================
+Looking for checkpoints in: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints
+Analyzing checkpoints to find the one from current training run...
+  - checkpoint-100: trainer_state.json modified at Wed Oct 22 08:36:02 PM EDT 2025
+  - checkpoint-50: trainer_state.json modified at Wed Oct 22 08:35:46 PM EDT 2025
+
+Selected checkpoint: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/checkpoint-100
+This checkpoint has the most recently updated trainer_state.json
+Checkpoint details:
+  Path: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/checkpoint-100
+  Last modified: 2025-10-22 16:54:17.414188691 -0400
+  Training step: 100
+Updating merge config to point to checkpoint...
+Successfully updated merge config
+Updated merge config to use: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/checkpoint-100
+
+Merge config contents:
+  model_name_or_path: Qwen/Qwen2.5-0.5B
+  finetuning_type: lora
+  trust_remote_code: true
+  adapter_name_or_path: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/checkpoint-100
+  template: default
+  export_dir: /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged
+
+Executing command: llamafactory-cli export /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/configs/merge_config.yaml
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
+  warnings.warn(
+/scratch/zrs2020/miniconda/miniconda3/envs/llamafactory/lib/python3.12/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
+  import pkg_resources
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:36:15,905 >> loading file vocab.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/vocab.json
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:36:15,905 >> loading file merges.txt from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/merges.txt
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:36:15,905 >> loading file tokenizer.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/tokenizer.json
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:36:15,905 >> loading file added_tokens.json from cache at None
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:36:15,905 >> loading file special_tokens_map.json from cache at None
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:36:15,905 >> loading file tokenizer_config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:36:15,905 >> loading file chat_template.jinja from cache at None
+[INFO|tokenization_utils_base.py:2364] 2025-10-22 20:36:16,078 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+[INFO|configuration_utils.py:765] 2025-10-22 20:36:16,354 >> loading configuration file config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/config.json
+[INFO|configuration_utils.py:839] 2025-10-22 20:36:16,356 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:36:16,445 >> loading file vocab.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/vocab.json
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:36:16,446 >> loading file merges.txt from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/merges.txt
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:36:16,446 >> loading file tokenizer.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/tokenizer.json
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:36:16,446 >> loading file added_tokens.json from cache at None
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:36:16,446 >> loading file special_tokens_map.json from cache at None
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:36:16,446 >> loading file tokenizer_config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2095] 2025-10-22 20:36:16,446 >> loading file chat_template.jinja from cache at None
+[INFO|tokenization_utils_base.py:2364] 2025-10-22 20:36:16,612 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+[INFO|configuration_utils.py:765] 2025-10-22 20:36:16,666 >> loading configuration file config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/config.json
+[INFO|configuration_utils.py:839] 2025-10-22 20:36:16,666 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+
+[WARNING|logging.py:328] 2025-10-22 20:36:16,667 >> `torch_dtype` is deprecated! Use `dtype` instead!
+[INFO|2025-10-22 20:36:16] llamafactory.model.model_utils.kv_cache:143 >> KV cache is enabled for faster generation.
+[WARNING|logging.py:328] 2025-10-22 20:36:17,018 >> `torch_dtype` is deprecated! Use `dtype` instead!
+[INFO|modeling_utils.py:1172] 2025-10-22 20:36:17,019 >> loading weights file model.safetensors from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/model.safetensors
+[INFO|modeling_utils.py:2341] 2025-10-22 20:36:17,020 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
+[INFO|configuration_utils.py:986] 2025-10-22 20:36:17,020 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151643
+}
+
+[INFO|configuration_utils.py:941] 2025-10-22 20:36:17,100 >> loading configuration file generation_config.json from cache at /scratch/zrs2020/.cache/hf_cache/home/hub/models--Qwen--Qwen2.5-0.5B/snapshots/060db6499f32faf8b98477b0a26969ef7d8b9987/generation_config.json
+[INFO|configuration_utils.py:986] 2025-10-22 20:36:17,101 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048
+}
+
+[INFO|dynamic_module_utils.py:423] 2025-10-22 20:36:17,125 >> Could not locate the custom_generate/generate.py inside Qwen/Qwen2.5-0.5B.
+[INFO|2025-10-22 20:36:17] llamafactory.model.model_utils.attention:143 >> Using torch SDPA for faster training and inference.
+[INFO|2025-10-22 20:36:18] llamafactory.model.adapter:143 >> Merged 1 adapter(s).
+[INFO|2025-10-22 20:36:18] llamafactory.model.adapter:143 >> Loaded adapter(s): /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/checkpoints/checkpoint-100
+[INFO|2025-10-22 20:36:18] llamafactory.model.loader:143 >> all params: 494,032,768
+[INFO|2025-10-22 20:36:18] llamafactory.train.tuner:143 >> Convert model dtype to: torch.bfloat16.
+[INFO|configuration_utils.py:491] 2025-10-22 20:36:18,042 >> Configuration saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged/config.json
+[INFO|configuration_utils.py:757] 2025-10-22 20:36:18,047 >> Configuration saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged/generation_config.json
+[INFO|modeling_utils.py:4181] 2025-10-22 20:36:19,774 >> Model weights saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged/model.safetensors
+[INFO|tokenization_utils_base.py:2421] 2025-10-22 20:36:19,779 >> chat template saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged/chat_template.jinja
+[INFO|tokenization_utils_base.py:2590] 2025-10-22 20:36:19,784 >> tokenizer config file saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2599] 2025-10-22 20:36:19,789 >> Special tokens file saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged/special_tokens_map.json
+[INFO|2025-10-22 20:36:19] llamafactory.train.tuner:143 >> Ollama modelfile saved in /scratch/zrs2020/LlamaFactoryHelper/experiments/lf_torch_test__interactive/merged/Modelfile
+
+========================================
+Merge/Export completed successfully
+End Time: Wed Oct 22 08:36:20 PM EDT 2025
+========================================
+
+========================================
+Preparing Training Artifacts
+========================================
+Copying configuration files...
+Copying and cleaning training logs...