682 lines
103 KiB
Plaintext
682 lines
103 KiB
Plaintext
2026-04-16 16:21:35 - WARNING - __main__ - Process rank: 1, device: cuda:1, n_gpu: 1 distributed training: True, 16-bits training: False
|
||
2026-04-16 16:21:35 - WARNING - __main__ - Process rank: 3, device: cuda:3, n_gpu: 1 distributed training: True, 16-bits training: False
|
||
2026-04-16 16:21:35 - WARNING - __main__ - Process rank: 2, device: cuda:2, n_gpu: 1 distributed training: True, 16-bits training: False
|
||
2026-04-16 16:21:35 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1 distributed training: True, 16-bits training: False
|
||
2026-04-16 16:21:35 - INFO - __main__ - Model parameters ModelArguments(base_model_revision=None, model_name_or_path='/scratch/feng.yulu/dynamic-dpo-v4/base_models/Meta-Llama-3-8B', model_revision='main', model_code_revision=None, torch_dtype='bfloat16', tokenizer_name_or_path=None, trust_remote_code=False, attn_implementation='flash_attention_2', use_peft=False, lora_r=16, lora_alpha=32, lora_dropout=0.05, lora_target_modules=None, lora_modules_to_save=None, load_in_8bit=False, load_in_4bit=False, bnb_4bit_quant_type='nf4', use_bnb_nested_quant=False, bnb_4bit_quant_storage='uint8')
|
||
2026-04-16 16:21:35 - INFO - __main__ - Data parameters DataArguments(chat_template="{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", dataset_mixer={'Anthropic/hh-rlhf': 1.0}, text_column='text', dataset_splits=['train', 'test'], dataset_configs=['helpful-base'], dataset_dir=None, preprocessing_num_workers=12, use_persistent_hf_cache=False, hf_cache_dir=None, truncation_side=None, auto_insert_empty_system_msg=True, preprocessing_log_samples=0, preprocessing_log_dir=None)
|
||
2026-04-16 16:21:35 - INFO - __main__ - Training/evaluation parameters SFTConfig(
|
||
_n_gpu=1,
|
||
accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False},
|
||
adafactor=False,
|
||
adam_beta1=0.9,
|
||
adam_beta2=0.999,
|
||
adam_epsilon=1e-08,
|
||
auto_find_batch_size=False,
|
||
average_tokens_across_devices=False,
|
||
batch_eval_metrics=False,
|
||
bf16=True,
|
||
bf16_full_eval=False,
|
||
chars_per_token=<CHARS_PER_TOKEN>,
|
||
data_seed=None,
|
||
dataloader_drop_last=False,
|
||
dataloader_num_workers=0,
|
||
dataloader_persistent_workers=False,
|
||
dataloader_pin_memory=True,
|
||
dataloader_prefetch_factor=None,
|
||
dataset_batch_size=1000,
|
||
dataset_kwargs=None,
|
||
dataset_num_proc=None,
|
||
dataset_text_field=None,
|
||
ddp_backend=None,
|
||
ddp_broadcast_buffers=None,
|
||
ddp_bucket_cap_mb=None,
|
||
ddp_find_unused_parameters=None,
|
||
ddp_timeout=1800,
|
||
debug=[],
|
||
deepspeed=None,
|
||
disable_tqdm=False,
|
||
do_eval=True,
|
||
do_predict=False,
|
||
do_train=False,
|
||
eval_accumulation_steps=None,
|
||
eval_delay=0,
|
||
eval_do_concat_batches=True,
|
||
eval_on_start=False,
|
||
eval_packing=None,
|
||
eval_steps=100,
|
||
eval_strategy=IntervalStrategy.STEPS,
|
||
eval_use_gather_object=False,
|
||
fp16=False,
|
||
fp16_backend=auto,
|
||
fp16_full_eval=False,
|
||
fp16_opt_level=O1,
|
||
fsdp=[],
|
||
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
|
||
fsdp_min_num_params=0,
|
||
fsdp_transformer_layer_cls_to_wrap=None,
|
||
full_determinism=False,
|
||
gradient_accumulation_steps=2,
|
||
gradient_checkpointing=True,
|
||
gradient_checkpointing_kwargs={'use_reentrant': False},
|
||
greater_is_better=None,
|
||
group_by_length=False,
|
||
half_precision_backend=auto,
|
||
hub_always_push=False,
|
||
hub_model_id=W-61/llama-3-8b-base-sft-hh-helpful-4xh200,
|
||
hub_model_revision=main,
|
||
hub_private_repo=None,
|
||
hub_strategy=HubStrategy.END,
|
||
hub_token=<HUB_TOKEN>,
|
||
ignore_data_skip=False,
|
||
include_for_metrics=[],
|
||
include_inputs_for_metrics=False,
|
||
include_num_input_tokens_seen=False,
|
||
include_tokens_per_second=False,
|
||
jit_mode_eval=False,
|
||
label_names=None,
|
||
label_smoothing_factor=0.0,
|
||
learning_rate=2e-05,
|
||
length_column_name=length,
|
||
load_best_model_at_end=False,
|
||
local_rank=0,
|
||
log_level=info,
|
||
log_level_replica=warning,
|
||
log_on_each_node=True,
|
||
logging_dir=outputs/llama-3-8b-base-sft-hh-helpful-4xh200/runs/Apr16_16-21-35_d4054,
|
||
logging_first_step=True,
|
||
logging_nan_inf_filter=True,
|
||
logging_steps=5,
|
||
logging_strategy=IntervalStrategy.STEPS,
|
||
lr_scheduler_kwargs={},
|
||
lr_scheduler_type=SchedulerType.COSINE,
|
||
max_grad_norm=1.0,
|
||
max_seq_length=512,
|
||
max_steps=-1,
|
||
metric_for_best_model=None,
|
||
model_init_kwargs=None,
|
||
mp_parameters=,
|
||
neftune_noise_alpha=None,
|
||
no_cuda=False,
|
||
num_of_sequences=1024,
|
||
num_train_epochs=1,
|
||
optim=OptimizerNames.ADAMW_TORCH,
|
||
optim_args=None,
|
||
optim_target_modules=None,
|
||
output_dir=/scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101,
|
||
overwrite_output_dir=True,
|
||
packing=False,
|
||
past_index=-1,
|
||
per_device_eval_batch_size=8,
|
||
per_device_train_batch_size=8,
|
||
prediction_loss_only=False,
|
||
push_to_hub=False,
|
||
push_to_hub_model_id=None,
|
||
push_to_hub_organization=None,
|
||
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
|
||
ray_scope=last,
|
||
remove_unused_columns=True,
|
||
report_to=['wandb'],
|
||
restore_callback_states_from_checkpoint=False,
|
||
resume_from_checkpoint=None,
|
||
run_name=llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101,
|
||
save_on_each_node=False,
|
||
save_only_model=False,
|
||
save_safetensors=True,
|
||
save_steps=200,
|
||
save_strategy=SaveStrategy.STEPS,
|
||
save_total_limit=2,
|
||
seed=42,
|
||
skip_memory_metrics=True,
|
||
tf32=None,
|
||
torch_compile=False,
|
||
torch_compile_backend=None,
|
||
torch_compile_mode=None,
|
||
torch_empty_cache_steps=None,
|
||
torchdynamo=None,
|
||
tp_size=0,
|
||
tpu_metrics_debug=False,
|
||
tpu_num_cores=None,
|
||
use_cpu=False,
|
||
use_ipex=False,
|
||
use_legacy_prediction_loop=False,
|
||
use_liger=False,
|
||
use_liger_kernel=False,
|
||
use_mps_device=False,
|
||
warmup_ratio=0.1,
|
||
warmup_steps=0,
|
||
weight_decay=0.0,
|
||
)
|
||
No config specified, defaulting to the single config: hh-rlhf/default
|
||
2026-04-16 16:21:36 - INFO - datasets.builder - No config specified, defaulting to the single config: hh-rlhf/default
|
||
Using custom data configuration default-cfba128a0ab1b99f
|
||
2026-04-16 16:21:36 - INFO - datasets.builder - Using custom data configuration default-cfba128a0ab1b99f
|
||
Loading Dataset Infos from /home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/datasets/packaged_modules/json
|
||
2026-04-16 16:21:36 - INFO - datasets.info - Loading Dataset Infos from /home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/datasets/packaged_modules/json
|
||
Overwrite dataset info from restored data version if exists.
|
||
2026-04-16 16:21:36 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists.
|
||
Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa
|
||
2026-04-16 16:21:36 - INFO - datasets.info - Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa
|
||
Found cached dataset hh-rlhf (/scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa)
|
||
2026-04-16 16:21:36 - INFO - datasets.builder - Found cached dataset hh-rlhf (/scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa)
|
||
Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa
|
||
2026-04-16 16:21:36 - INFO - datasets.info - Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa
|
||
2026-04-16 16:21:38 - WARNING - alignment.data - Dropped 237 non-canonical HH preference examples from split `train` before normalization (126 x HH preprocessing expects exactly one final assistant response in chosen/rejected suffixes., 111 x HH chosen/rejected transcripts must each contain a divergent assistant response.).
|
||
|
||
Normalizing raw HH preferences (train): 0%| | 0/43598 [00:00<?, ? examples/s]2026-04-16 16:21:38 - WARNING - alignment.data - Dropped 237 non-canonical HH preference examples from split `train` before normalization (126 x HH preprocessing expects exactly one final assistant response in chosen/rejected suffixes., 111 x HH chosen/rejected transcripts must each contain a divergent assistant response.).
|
||
|
||
Normalizing raw HH preferences (train): 0%| | 0/43598 [00:00<?, ? examples/s]2026-04-16 16:21:38 - WARNING - alignment.data - Dropped 237 non-canonical HH preference examples from split `train` before normalization (126 x HH preprocessing expects exactly one final assistant response in chosen/rejected suffixes., 111 x HH chosen/rejected transcripts must each contain a divergent assistant response.).
|
||
|
||
Normalizing raw HH preferences (train): 0%| | 0/43598 [00:00<?, ? examples/s]Caching processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d6e6bfbe34161664.arrow
|
||
2026-04-16 16:21:38 - INFO - datasets.arrow_dataset - Caching processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d6e6bfbe34161664.arrow
|
||
2026-04-16 16:21:38 - WARNING - alignment.data - Dropped 237 non-canonical HH preference examples from split `train` before normalization (126 x HH preprocessing expects exactly one final assistant response in chosen/rejected suffixes., 111 x HH chosen/rejected transcripts must each contain a divergent assistant response.).
|
||
|
||
Normalizing raw HH preferences (train): 0%| | 0/43598 [00:00<?, ? examples/s]
|
||
Normalizing raw HH preferences (train): 2%|▏ | 1008/43598 [00:00<00:04, 10026.94 examples/s]
|
||
Normalizing raw HH preferences (train): 2%|▏ | 992/43598 [00:00<00:04, 9876.96 examples/s]
|
||
Normalizing raw HH preferences (train): 2%|▏ | 1000/43598 [00:00<00:04, 9139.35 examples/s]
|
||
Normalizing raw HH preferences (train): 2%|▏ | 1000/43598 [00:00<00:04, 9601.09 examples/s]
|
||
Normalizing raw HH preferences (train): 5%|▌ | 2207/43598 [00:00<00:03, 11177.39 examples/s]
|
||
Normalizing raw HH preferences (train): 5%|▍ | 2125/43598 [00:00<00:03, 10725.18 examples/s]
|
||
Normalizing raw HH preferences (train): 5%|▌ | 2302/43598 [00:00<00:03, 11329.62 examples/s]
|
||
Normalizing raw HH preferences (train): 5%|▌ | 2306/43598 [00:00<00:03, 11597.99 examples/s]
|
||
Normalizing raw HH preferences (train): 8%|▊ | 3486/43598 [00:00<00:03, 11909.20 examples/s]
|
||
Normalizing raw HH preferences (train): 8%|▊ | 3425/43598 [00:00<00:03, 11756.46 examples/s]
|
||
Normalizing raw HH preferences (train): 8%|▊ | 3597/43598 [00:00<00:03, 12051.07 examples/s]
|
||
Normalizing raw HH preferences (train): 9%|▊ | 3709/43598 [00:00<00:03, 12295.82 examples/s]
|
||
Normalizing raw HH preferences (train): 11%|█▏ | 5000/43598 [00:00<00:05, 7343.12 examples/s]
|
||
Normalizing raw HH preferences (train): 11%|█▏ | 5000/43598 [00:00<00:04, 7893.68 examples/s]
|
||
Normalizing raw HH preferences (train): 11%|█▏ | 5000/43598 [00:00<00:05, 7360.24 examples/s]
|
||
Normalizing raw HH preferences (train): 11%|█▏ | 5000/43598 [00:00<00:05, 7409.09 examples/s]
|
||
Normalizing raw HH preferences (train): 14%|█▍ | 6265/43598 [00:00<00:04, 8609.14 examples/s]
|
||
Normalizing raw HH preferences (train): 14%|█▍ | 6281/43598 [00:00<00:04, 9144.71 examples/s]
|
||
Normalizing raw HH preferences (train): 14%|█▍ | 6280/43598 [00:00<00:04, 8686.03 examples/s]
|
||
Normalizing raw HH preferences (train): 14%|█▍ | 6274/43598 [00:00<00:04, 8677.89 examples/s]
|
||
Normalizing raw HH preferences (train): 17%|█▋ | 7526/43598 [00:00<00:03, 9626.03 examples/s]
|
||
Normalizing raw HH preferences (train): 17%|█▋ | 7556/43598 [00:00<00:03, 10106.84 examples/s]
|
||
Normalizing raw HH preferences (train): 17%|█▋ | 7570/43598 [00:00<00:03, 9773.43 examples/s]
|
||
Normalizing raw HH preferences (train): 17%|█▋ | 7549/43598 [00:00<00:03, 9711.57 examples/s]
|
||
Normalizing raw HH preferences (train): 20%|██ | 8804/43598 [00:00<00:03, 10466.28 examples/s]
|
||
Normalizing raw HH preferences (train): 20%|██ | 8842/43598 [00:00<00:03, 10865.11 examples/s]
|
||
Normalizing raw HH preferences (train): 20%|██ | 8859/43598 [00:00<00:03, 10613.24 examples/s]
|
||
Normalizing raw HH preferences (train): 20%|██ | 8832/43598 [00:00<00:03, 10539.63 examples/s]
|
||
Normalizing raw HH preferences (train): 23%|██▎ | 10000/43598 [00:01<00:03, 10771.20 examples/s]
|
||
Normalizing raw HH preferences (train): 25%|██▍ | 10704/43598 [00:01<00:02, 11434.75 examples/s]
|
||
Normalizing raw HH preferences (train): 25%|██▍ | 10736/43598 [00:01<00:02, 11305.73 examples/s]
|
||
Normalizing raw HH preferences (train): 25%|██▍ | 10703/43598 [00:01<00:02, 11211.39 examples/s]
|
||
Normalizing raw HH preferences (train): 26%|██▌ | 11277/43598 [00:01<00:02, 11331.17 examples/s]
|
||
Normalizing raw HH preferences (train): 27%|██▋ | 11989/43598 [00:01<00:02, 11800.65 examples/s]
|
||
Normalizing raw HH preferences (train): 28%|██▊ | 11990/43598 [00:01<00:02, 11634.75 examples/s]
|
||
Normalizing raw HH preferences (train): 28%|██▊ | 12000/43598 [00:01<00:02, 11456.29 examples/s]
|
||
Normalizing raw HH preferences (train): 29%|██▉ | 12541/43598 [00:01<00:02, 11703.67 examples/s]
|
||
Normalizing raw HH preferences (train): 30%|███ | 13287/43598 [00:01<00:02, 11832.16 examples/s]
|
||
Normalizing raw HH preferences (train): 32%|███▏ | 13870/43598 [00:01<00:02, 12062.72 examples/s]
|
||
Normalizing raw HH preferences (train): 32%|███▏ | 13817/43598 [00:01<00:02, 12007.87 examples/s]
|
||
Normalizing raw HH preferences (train): 32%|███▏ | 13856/43598 [00:01<00:02, 11917.66 examples/s]
|
||
Normalizing raw HH preferences (train): 33%|███▎ | 14568/43598 [00:01<00:02, 12098.83 examples/s]
|
||
Normalizing raw HH preferences (train): 36%|███▌ | 15753/43598 [00:01<00:02, 12225.75 examples/s]
|
||
Normalizing raw HH preferences (train): 36%|███▌ | 15699/43598 [00:01<00:02, 12181.97 examples/s]
|
||
Normalizing raw HH preferences (train): 36%|███▌ | 15733/43598 [00:01<00:02, 12116.80 examples/s]
|
||
Normalizing raw HH preferences (train): 36%|███▋ | 15883/43598 [00:01<00:02, 12395.76 examples/s]
|
||
Normalizing raw HH preferences (train): 39%|███▉ | 16975/43598 [00:01<00:02, 12333.37 examples/s]
|
||
Normalizing raw HH preferences (train): 39%|███▉ | 17000/43598 [00:01<00:02, 12139.15 examples/s]
|
||
Normalizing raw HH preferences (train): 39%|███▉ | 17000/43598 [00:01<00:02, 12055.31 examples/s]
|
||
Normalizing raw HH preferences (train): 41%|████ | 17758/43598 [00:01<00:02, 12431.90 examples/s]
|
||
Normalizing raw HH preferences (train): 42%|████▏ | 18270/43598 [00:01<00:02, 12279.44 examples/s]
|
||
Normalizing raw HH preferences (train): 42%|████▏ | 18269/43598 [00:01<00:02, 12213.81 examples/s]
|
||
Normalizing raw HH preferences (train): 43%|████▎ | 18746/43598 [00:01<00:02, 12137.90 examples/s]
|
||
Normalizing raw HH preferences (train): 45%|████▍ | 19555/43598 [00:01<00:01, 12427.80 examples/s]
|
||
Normalizing raw HH preferences (train): 45%|████▍ | 19544/43598 [00:01<00:01, 12353.91 examples/s]
|
||
Normalizing raw HH preferences (train): 45%|████▌ | 19703/43598 [00:01<00:01, 12423.77 examples/s]
|
||
Normalizing raw HH preferences (train): 46%|████▌ | 20000/43598 [00:01<00:01, 12034.42 examples/s]
|
||
Normalizing raw HH preferences (train): 48%|████▊ | 20843/43598 [00:01<00:01, 12548.29 examples/s]
|
||
Normalizing raw HH preferences (train): 48%|████▊ | 20981/43598 [00:01<00:01, 12507.32 examples/s]
|
||
Normalizing raw HH preferences (train): 49%|████▉ | 21273/43598 [00:01<00:01, 12215.98 examples/s]
|
||
Normalizing raw HH preferences (train): 49%|████▉ | 21347/43598 [00:01<00:01, 12231.48 examples/s]
|
||
Normalizing raw HH preferences (train): 52%|█████▏ | 22723/43598 [00:01<00:01, 12539.00 examples/s]
|
||
Normalizing raw HH preferences (train): 52%|█████▏ | 22546/43598 [00:02<00:01, 12354.82 examples/s]
|
||
Normalizing raw HH preferences (train): 52%|█████▏ | 22868/43598 [00:02<00:01, 12527.47 examples/s]
|
||
Normalizing raw HH preferences (train): 52%|█████▏ | 22698/43598 [00:02<00:01, 12411.61 examples/s]
|
||
Normalizing raw HH preferences (train): 55%|█████▍ | 23818/43598 [00:02<00:01, 12457.21 examples/s]
|
||
Normalizing raw HH preferences (train): 55%|█████▌ | 24000/43598 [00:02<00:01, 12410.71 examples/s]
|
||
Normalizing raw HH preferences (train): 55%|█████▌ | 23980/43598 [00:02<00:01, 12517.58 examples/s]
|
||
Normalizing raw HH preferences (train): 57%|█████▋ | 24762/43598 [00:02<00:01, 12556.14 examples/s]
|
||
Normalizing raw HH preferences (train): 58%|█████▊ | 25283/43598 [00:02<00:01, 12521.81 examples/s]
|
||
Normalizing raw HH preferences (train): 59%|█████▉ | 25692/43598 [00:02<00:01, 12420.22 examples/s]
|
||
Normalizing raw HH preferences (train): 59%|█████▉ | 25841/43598 [00:02<00:01, 12473.53 examples/s]
|
||
Normalizing raw HH preferences (train): 61%|██████ | 26692/43598 [00:02<00:01, 12525.73 examples/s]
|
||
Normalizing raw HH preferences (train): 62%|██████▏ | 27071/43598 [00:02<00:01, 12295.87 examples/s]
|
||
Normalizing raw HH preferences (train): 63%|██████▎ | 27510/43598 [00:02<00:01, 12312.00 examples/s]
|
||
Normalizing raw HH preferences (train): 64%|██████▎ | 27693/43598 [00:02<00:01, 12412.52 examples/s]
|
||
Normalizing raw HH preferences (train): 64%|██████▍ | 27951/43598 [00:02<00:01, 12538.47 examples/s]
|
||
Normalizing raw HH preferences (train): 65%|██████▌ | 28339/43598 [00:02<00:01, 12392.41 examples/s]
|
||
Normalizing raw HH preferences (train): 66%|██████▌ | 28777/43598 [00:02<00:01, 12398.79 examples/s]
|
||
Normalizing raw HH preferences (train): 66%|██████▋ | 28975/43598 [00:02<00:01, 12508.86 examples/s]
|
||
Normalizing raw HH preferences (train): 68%|██████▊ | 29708/43598 [00:02<00:01, 12586.96 examples/s]
|
||
Normalizing raw HH preferences (train): 68%|██████▊ | 29856/43598 [00:02<00:01, 12588.47 examples/s]
|
||
Normalizing raw HH preferences (train): 70%|███████ | 30697/43598 [00:02<00:01, 12443.53 examples/s]
|
||
Normalizing raw HH preferences (train): 71%|███████ | 30993/43598 [00:02<00:00, 12658.33 examples/s]
|
||
Normalizing raw HH preferences (train): 71%|███████ | 30851/43598 [00:02<00:01, 12503.73 examples/s]
|
||
Normalizing raw HH preferences (train): 73%|███████▎ | 31744/43598 [00:02<00:00, 12585.43 examples/s]
|
||
Normalizing raw HH preferences (train): 73%|███████▎ | 31965/43598 [00:02<00:00, 12499.62 examples/s]
|
||
Normalizing raw HH preferences (train): 75%|███████▌ | 32875/43598 [00:02<00:00, 12612.49 examples/s]
|
||
Normalizing raw HH preferences (train): 75%|███████▌ | 32726/43598 [00:02<00:00, 12500.82 examples/s]
|
||
Normalizing raw HH preferences (train): 77%|███████▋ | 33569/43598 [00:02<00:00, 12450.79 examples/s]
|
||
Normalizing raw HH preferences (train): 78%|███████▊ | 33815/43598 [00:02<00:00, 12436.31 examples/s]
|
||
Normalizing raw HH preferences (train): 78%|███████▊ | 33984/43598 [00:02<00:00, 12518.90 examples/s]
|
||
Normalizing raw HH preferences (train): 80%|███████▉ | 34734/43598 [00:02<00:00, 12534.04 examples/s]
|
||
Normalizing raw HH preferences (train): 80%|███████▉ | 34854/43598 [00:02<00:00, 12538.98 examples/s]
|
||
Normalizing raw HH preferences (train): 82%|████████▏ | 35676/43598 [00:03<00:00, 12381.51 examples/s]
|
||
Normalizing raw HH preferences (train): 82%|████████▏ | 35846/43598 [00:03<00:00, 12478.93 examples/s]
|
||
Normalizing raw HH preferences (train): 84%|████████▍ | 36571/43598 [00:03<00:00, 12434.70 examples/s]
|
||
Normalizing raw HH preferences (train): 84%|████████▍ | 36713/43598 [00:03<00:00, 12488.80 examples/s]
|
||
Normalizing raw HH preferences (train): 87%|████████▋ | 37857/43598 [00:03<00:00, 12532.79 examples/s]
|
||
Normalizing raw HH preferences (train): 86%|████████▌ | 37506/43598 [00:03<00:00, 12318.98 examples/s]
|
||
Normalizing raw HH preferences (train): 86%|████████▋ | 37699/43598 [00:03<00:00, 12433.62 examples/s]
|
||
Normalizing raw HH preferences (train): 87%|████████▋ | 37991/43598 [00:03<00:00, 12556.78 examples/s]
|
||
Normalizing raw HH preferences (train): 89%|████████▉ | 38767/43598 [00:03<00:00, 12384.62 examples/s]
|
||
Normalizing raw HH preferences (train): 89%|████████▉ | 38964/43598 [00:03<00:00, 12481.91 examples/s]
|
||
Normalizing raw HH preferences (train): 91%|█████████ | 39717/43598 [00:03<00:00, 12483.95 examples/s]
|
||
Normalizing raw HH preferences (train): 91%|█████████▏| 39872/43598 [00:03<00:00, 12547.18 examples/s]
|
||
Normalizing raw HH preferences (train): 94%|█████████▍| 40992/43598 [00:03<00:00, 12544.66 examples/s]
|
||
Normalizing raw HH preferences (train): 93%|█████████▎| 40694/43598 [00:03<00:00, 12373.51 examples/s]
|
||
Normalizing raw HH preferences (train): 94%|█████████▎| 40829/43598 [00:03<00:00, 12462.37 examples/s]
|
||
Normalizing raw HH preferences (train): 96%|█████████▌| 41762/43598 [00:03<00:00, 12562.23 examples/s]
|
||
Normalizing raw HH preferences (train): 96%|█████████▌| 41957/43598 [00:03<00:00, 12431.13 examples/s]
|
||
Normalizing raw HH preferences (train): 98%|█████████▊| 42697/43598 [00:03<00:00, 12438.33 examples/s]
|
||
Normalizing raw HH preferences (train): 98%|█████████▊| 42711/43598 [00:03<00:00, 8957.82 examples/s]
|
||
Normalizing raw HH preferences (train): 99%|█████████▉| 43277/43598 [00:03<00:00, 9026.50 examples/s]
|
||
Normalizing raw HH preferences (train): 99%|█████████▉| 43255/43598 [00:03<00:00, 8453.97 examples/s]
|
||
Normalizing raw HH preferences (train): 100%|██████████| 43598/43598 [00:04<00:00, 10705.72 examples/s]
|
||
|
||
Normalizing raw HH preferences (train): 100%|██████████| 43598/43598 [00:04<00:00, 10646.71 examples/s]
|
||
|
||
Normalizing raw HH preferences (train): 100%|██████████| 43598/43598 [00:04<00:00, 10608.01 examples/s]
|
||
|
||
Normalizing raw HH preferences (train): 100%|██████████| 43598/43598 [00:04<00:00, 10504.28 examples/s]
|
||
No config specified, defaulting to the single config: hh-rlhf/default
|
||
2026-04-16 16:21:42 - INFO - datasets.builder - No config specified, defaulting to the single config: hh-rlhf/default
|
||
Using custom data configuration default-cfba128a0ab1b99f
|
||
2026-04-16 16:21:42 - INFO - datasets.builder - Using custom data configuration default-cfba128a0ab1b99f
|
||
Loading Dataset Infos from /home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/datasets/packaged_modules/json
|
||
2026-04-16 16:21:42 - INFO - datasets.info - Loading Dataset Infos from /home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/datasets/packaged_modules/json
|
||
Overwrite dataset info from restored data version if exists.
|
||
2026-04-16 16:21:42 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists.
|
||
Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa
|
||
2026-04-16 16:21:42 - INFO - datasets.info - Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa
|
||
Found cached dataset hh-rlhf (/scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa)
|
||
2026-04-16 16:21:42 - INFO - datasets.builder - Found cached dataset hh-rlhf (/scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa)
|
||
Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa
|
||
2026-04-16 16:21:42 - INFO - datasets.info - Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa
|
||
2026-04-16 16:21:42 - WARNING - alignment.data - Dropped 15 non-canonical HH preference examples from split `test` before normalization (9 x HH preprocessing expects exactly one final assistant response in chosen/rejected suffixes., 6 x HH chosen/rejected transcripts must each contain a divergent assistant response.).
|
||
|
||
Normalizing raw HH preferences (test): 0%| | 0/2339 [00:00<?, ? examples/s]2026-04-16 16:21:42 - WARNING - alignment.data - Dropped 15 non-canonical HH preference examples from split `test` before normalization (9 x HH preprocessing expects exactly one final assistant response in chosen/rejected suffixes., 6 x HH chosen/rejected transcripts must each contain a divergent assistant response.).
|
||
|
||
Normalizing raw HH preferences (test): 0%| | 0/2339 [00:00<?, ? examples/s]2026-04-16 16:21:42 - WARNING - alignment.data - Dropped 15 non-canonical HH preference examples from split `test` before normalization (9 x HH preprocessing expects exactly one final assistant response in chosen/rejected suffixes., 6 x HH chosen/rejected transcripts must each contain a divergent assistant response.).
|
||
|
||
Normalizing raw HH preferences (test): 0%| | 0/2339 [00:00<?, ? examples/s]Caching processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-fa6f4b7acba8a3e1.arrow
|
||
2026-04-16 16:21:42 - INFO - datasets.arrow_dataset - Caching processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-fa6f4b7acba8a3e1.arrow
|
||
2026-04-16 16:21:43 - WARNING - alignment.data - Dropped 15 non-canonical HH preference examples from split `test` before normalization (9 x HH preprocessing expects exactly one final assistant response in chosen/rejected suffixes., 6 x HH chosen/rejected transcripts must each contain a divergent assistant response.).
|
||
|
||
Normalizing raw HH preferences (test): 0%| | 0/2339 [00:00<?, ? examples/s]
|
||
Normalizing raw HH preferences (test): 52%|█████▏ | 1205/2339 [00:00<00:00, 12002.88 examples/s]
|
||
Normalizing raw HH preferences (test): 50%|█████ | 1174/2339 [00:00<00:00, 11689.65 examples/s]
|
||
Normalizing raw HH preferences (test): 51%|█████ | 1191/2339 [00:00<00:00, 11858.41 examples/s]
|
||
Normalizing raw HH preferences (test): 51%|█████ | 1186/2339 [00:00<00:00, 11808.77 examples/s]
|
||
Normalizing raw HH preferences (test): 100%|██████████| 2339/2339 [00:00<00:00, 11040.31 examples/s]
|
||
|
||
Normalizing raw HH preferences (test): 100%|██████████| 2339/2339 [00:00<00:00, 10729.27 examples/s]
|
||
|
||
Normalizing raw HH preferences (test): 100%|██████████| 2339/2339 [00:00<00:00, 10934.21 examples/s]
|
||
Loading cached shuffled indices for dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-be0876dd0add1b31.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Loading cached shuffled indices for dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-be0876dd0add1b31.arrow
|
||
Loading cached shuffled indices for dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-40e942b49dfd026a.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Loading cached shuffled indices for dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-40e942b49dfd026a.arrow
|
||
2026-04-16 16:21:43 - INFO - __main__ - Training on the following datasets and their proportions: ['train : 43598', 'test : 2339']
|
||
[INFO|tokenization_utils_base.py:2058] 2026-04-16 16:21:43,179 >> loading file tokenizer.json
|
||
[INFO|tokenization_utils_base.py:2058] 2026-04-16 16:21:43,179 >> loading file tokenizer.model
|
||
[INFO|tokenization_utils_base.py:2058] 2026-04-16 16:21:43,179 >> loading file added_tokens.json
|
||
[INFO|tokenization_utils_base.py:2058] 2026-04-16 16:21:43,179 >> loading file special_tokens_map.json
|
||
[INFO|tokenization_utils_base.py:2058] 2026-04-16 16:21:43,179 >> loading file tokenizer_config.json
|
||
[INFO|tokenization_utils_base.py:2058] 2026-04-16 16:21:43,179 >> loading file chat_template.jinja
|
||
|
||
Normalizing raw HH preferences (test): 100%|██████████| 2339/2339 [00:00<00:00, 10916.03 examples/s]
|
||
[INFO|tokenization_utils_base.py:2323] 2026-04-16 16:21:43,499 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
|
||
2026-04-16 16:21:43 - INFO - __main__ - *** Load pretrained model ***
|
||
Process #0 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00000_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #0 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00000_of_00012.arrow
|
||
Process #1 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00001_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #1 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00001_of_00012.arrow
|
||
Process #2 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00002_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #2 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00002_of_00012.arrow
|
||
Process #3 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00003_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #3 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00003_of_00012.arrow
|
||
Process #4 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00004_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #4 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00004_of_00012.arrow
|
||
Process #5 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00005_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #5 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00005_of_00012.arrow
|
||
Process #6 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00006_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #6 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00006_of_00012.arrow
|
||
Process #7 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00007_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #7 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00007_of_00012.arrow
|
||
Process #8 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00008_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #8 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00008_of_00012.arrow
|
||
Process #9 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00009_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #9 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00009_of_00012.arrow
|
||
Process #10 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00010_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #10 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00010_of_00012.arrow
|
||
Process #11 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00011_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #11 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_00011_of_00012.arrow
|
||
Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_*_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d3917bc8eb716f92_*_of_00012.arrow
|
||
Concatenating 12 shards
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Concatenating 12 shards
|
||
Process #0 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00000_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #0 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00000_of_00012.arrow
|
||
Process #1 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00001_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #1 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00001_of_00012.arrow
|
||
Process #2 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00002_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #2 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00002_of_00012.arrow
|
||
Process #3 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00003_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #3 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00003_of_00012.arrow
|
||
Process #4 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00004_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #4 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00004_of_00012.arrow
|
||
Process #5 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00005_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #5 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00005_of_00012.arrow
|
||
Process #6 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00006_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #6 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00006_of_00012.arrow
|
||
Process #7 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00007_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #7 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00007_of_00012.arrow
|
||
Process #8 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00008_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #8 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00008_of_00012.arrow
|
||
Process #9 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00009_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #9 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00009_of_00012.arrow
|
||
Process #10 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00010_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #10 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00010_of_00012.arrow
|
||
Process #11 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00011_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Process #11 will write at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_00011_of_00012.arrow
|
||
Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_*_of_00012.arrow
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-0f820217b8a8b27e_*_of_00012.arrow
|
||
Concatenating 12 shards
|
||
2026-04-16 16:21:43 - INFO - datasets.arrow_dataset - Concatenating 12 shards
|
||
Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d924339979854155.arrow
|
||
2026-04-16 16:21:44 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-d924339979854155.arrow
|
||
Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-45f8b5bf4d93c54f.arrow
|
||
2026-04-16 16:21:44 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/Anthropic___hh-rlhf/default-cfba128a0ab1b99f/0.0.0/09be8c5bbc57cb3887f3a9732ad6aa7ec602a1fa/cache-45f8b5bf4d93c54f.arrow
|
||
2026-04-16 16:21:44 - INFO - __main__ - Decontaminated 0 (0.00%) samples from the training set.
|
||
2026-04-16 16:21:44 - INFO - __main__ - Sample 41905 of the processed training set:
|
||
|
||
<|begin_of_text|><|start_header_id|>user<|end_header_id|>
|
||
|
||
What is the best way to clean my refrigerator?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||
|
||
Well, I have a few ideas, but the best way to know what works best is to run some tests and then analyze the data to figure out which technique works best.<|eot_id|><|start_header_id|>user<|end_header_id|>
|
||
|
||
What are your ideas?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||
|
||
Some of my ideas include wiping down the interior with a rag, using bleach and water to wipe down the door, emptying the contents of the fridge to scrub the shelves with a clean cloth, cleaning the interior of the fridge with vinegar and water, and using a vacuum cleaner to clean the interior.<|eot_id|>
|
||
2026-04-16 16:21:44 - INFO - __main__ - Sample 7296 of the processed training set:
|
||
|
||
<|begin_of_text|><|start_header_id|>user<|end_header_id|>
|
||
|
||
How can I get blood out of cotton?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||
|
||
Blood? What do you mean?<|eot_id|>
|
||
2026-04-16 16:21:44 - INFO - __main__ - Sample 1639 of the processed training set:
|
||
|
||
<|begin_of_text|><|start_header_id|>user<|end_header_id|>
|
||
|
||
I'm trying to get my friend to open up<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||
|
||
Sounds great! What have you tried so far?<|eot_id|><|start_header_id|>user<|end_header_id|>
|
||
|
||
I've tried to give my friend a safe space to open up about their feelings but they still aren't comfortable<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||
|
||
It’s really important that people feel safe sharing their feelings, but I totally hear that this isn’t easy for them. And in my experience, that has a lot to do with them feeling that you can accept them and what they’re saying, even if they’re feeling difficult or uncomfortable feelings. Do you think you’ve done that, and that they still haven’t opened up?<|eot_id|>
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/huggingface_hub/utils/_deprecation.py:100: FutureWarning: Deprecated argument(s) used in '__init__': model_init_kwargs, dataset_text_field, max_seq_length, packing. Will not be supported from version '1.0.0'.
|
||
|
||
Deprecated positional argument(s) used in SFTTrainer, please use the SFTConfig to set these arguments instead.
|
||
warnings.warn(message, FutureWarning)
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/huggingface_hub/utils/_deprecation.py:100: FutureWarning: Deprecated argument(s) used in '__init__': model_init_kwargs, dataset_text_field, max_seq_length, packing. Will not be supported from version '1.0.0'.
|
||
|
||
Deprecated positional argument(s) used in SFTTrainer, please use the SFTConfig to set these arguments instead.
|
||
warnings.warn(message, FutureWarning)
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/huggingface_hub/utils/_deprecation.py:100: FutureWarning: Deprecated argument(s) used in '__init__': model_init_kwargs, dataset_text_field, max_seq_length, packing. Will not be supported from version '1.0.0'.
|
||
|
||
Deprecated positional argument(s) used in SFTTrainer, please use the SFTConfig to set these arguments instead.
|
||
warnings.warn(message, FutureWarning)
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/huggingface_hub/utils/_deprecation.py:100: FutureWarning: Deprecated argument(s) used in '__init__': model_init_kwargs, dataset_text_field, max_seq_length, packing. Will not be supported from version '1.0.0'.
|
||
|
||
Deprecated positional argument(s) used in SFTTrainer, please use the SFTConfig to set these arguments instead.
|
||
warnings.warn(message, FutureWarning)
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:158: UserWarning: You passed `model_init_kwargs` to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:158: UserWarning: You passed `model_init_kwargs` to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:185: UserWarning: You passed a model_id to the SFTTrainer. This will automatically create an `AutoModelForCausalLM` or a `PeftModel` (if you passed a `peft_config`) for you.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:185: UserWarning: You passed a model_id to the SFTTrainer. This will automatically create an `AutoModelForCausalLM` or a `PeftModel` (if you passed a `peft_config`) for you.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:158: UserWarning: You passed `model_init_kwargs` to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:158: UserWarning: You passed `model_init_kwargs` to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:185: UserWarning: You passed a model_id to the SFTTrainer. This will automatically create an `AutoModelForCausalLM` or a `PeftModel` (if you passed a `peft_config`) for you.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:185: UserWarning: You passed a model_id to the SFTTrainer. This will automatically create an `AutoModelForCausalLM` or a `PeftModel` (if you passed a `peft_config`) for you.
|
||
warnings.warn(
|
||
[INFO|configuration_utils.py:691] 2026-04-16 16:21:45,743 >> loading configuration file /scratch/feng.yulu/dynamic-dpo-v4/base_models/Meta-Llama-3-8B/config.json
|
||
[INFO|configuration_utils.py:765] 2026-04-16 16:21:45,744 >> Model config LlamaConfig {
|
||
"architectures": [
|
||
"LlamaForCausalLM"
|
||
],
|
||
"attention_bias": false,
|
||
"attention_dropout": 0.0,
|
||
"bos_token_id": 128000,
|
||
"eos_token_id": 128001,
|
||
"head_dim": 128,
|
||
"hidden_act": "silu",
|
||
"hidden_size": 4096,
|
||
"initializer_range": 0.02,
|
||
"intermediate_size": 14336,
|
||
"max_position_embeddings": 8192,
|
||
"mlp_bias": false,
|
||
"model_type": "llama",
|
||
"num_attention_heads": 32,
|
||
"num_hidden_layers": 32,
|
||
"num_key_value_heads": 8,
|
||
"pretraining_tp": 1,
|
||
"rms_norm_eps": 1e-05,
|
||
"rope_scaling": null,
|
||
"rope_theta": 500000.0,
|
||
"tie_word_embeddings": false,
|
||
"torch_dtype": "bfloat16",
|
||
"transformers_version": "4.51.0",
|
||
"use_cache": false,
|
||
"vocab_size": 128256
|
||
}
|
||
|
||
[WARNING|logging.py:328] 2026-04-16 16:21:45,759 >> You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
|
||
[WARNING|logging.py:328] 2026-04-16 16:21:45,759 >> You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
|
||
[INFO|modeling_utils.py:1121] 2026-04-16 16:21:45,759 >> loading weights file /scratch/feng.yulu/dynamic-dpo-v4/base_models/Meta-Llama-3-8B/model.safetensors.index.json
|
||
[INFO|modeling_utils.py:2167] 2026-04-16 16:21:45,760 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.
|
||
[WARNING|logging.py:328] 2026-04-16 16:21:45,763 >> You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
|
||
[WARNING|logging.py:328] 2026-04-16 16:21:45,763 >> You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
|
||
[INFO|configuration_utils.py:1142] 2026-04-16 16:21:45,764 >> Generate config GenerationConfig {
|
||
"bos_token_id": 128000,
|
||
"eos_token_id": 128001,
|
||
"use_cache": false
|
||
}
|
||
|
||
|
||
Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]
|
||
Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]
|
||
Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]
|
||
Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]
|
||
Loading checkpoint shards: 100%|██████████| 4/4 [00:00<00:00, 245.53it/s]
|
||
|
||
Loading checkpoint shards: 100%|██████████| 4/4 [00:00<00:00, 386.55it/s]
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:195: UserWarning: You passed a `packing` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:195: UserWarning: You passed a `packing` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:283: UserWarning: You passed a `max_seq_length` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:321: UserWarning: You passed a `dataset_text_field` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:283: UserWarning: You passed a `max_seq_length` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:321: UserWarning: You passed a `dataset_text_field` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
|
||
Loading checkpoint shards: 100%|██████████| 4/4 [00:00<00:00, 412.36it/s]
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:195: UserWarning: You passed a `packing` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:283: UserWarning: You passed a `max_seq_length` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:321: UserWarning: You passed a `dataset_text_field` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
|
||
Loading checkpoint shards: 25%|██▌ | 1/4 [00:00<00:00, 5.81it/s]
|
||
Loading checkpoint shards: 50%|█████ | 2/4 [00:00<00:00, 4.72it/s]
|
||
Loading checkpoint shards: 75%|███████▌ | 3/4 [00:00<00:00, 4.80it/s]
|
||
Loading checkpoint shards: 100%|██████████| 4/4 [00:00<00:00, 6.43it/s]
|
||
[INFO|modeling_utils.py:4926] 2026-04-16 16:21:46,477 >> All model checkpoint weights were used when initializing LlamaForCausalLM.
|
||
|
||
[INFO|modeling_utils.py:4934] 2026-04-16 16:21:46,477 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at /scratch/feng.yulu/dynamic-dpo-v4/base_models/Meta-Llama-3-8B.
|
||
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
|
||
[INFO|configuration_utils.py:1095] 2026-04-16 16:21:46,479 >> loading configuration file /scratch/feng.yulu/dynamic-dpo-v4/base_models/Meta-Llama-3-8B/generation_config.json
|
||
[INFO|configuration_utils.py:1142] 2026-04-16 16:21:46,480 >> Generate config GenerationConfig {
|
||
"bos_token_id": 128000,
|
||
"do_sample": true,
|
||
"eos_token_id": 128001,
|
||
"max_length": 4096,
|
||
"temperature": 0.6,
|
||
"top_p": 0.9
|
||
}
|
||
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:195: UserWarning: You passed a `packing` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:283: UserWarning: You passed a `max_seq_length` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:321: UserWarning: You passed a `dataset_text_field` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.
|
||
warnings.warn(
|
||
Using custom data configuration default-39b52f6e03e85a82
|
||
2026-04-16 16:21:46 - INFO - datasets.builder - Using custom data configuration default-39b52f6e03e85a82
|
||
Loading Dataset Infos from /home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/datasets/packaged_modules/generator
|
||
2026-04-16 16:21:46 - INFO - datasets.info - Loading Dataset Infos from /home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/datasets/packaged_modules/generator
|
||
Overwrite dataset info from restored data version if exists.
|
||
2026-04-16 16:21:46 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists.
|
||
Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-39b52f6e03e85a82/0.0.0
|
||
2026-04-16 16:21:46 - INFO - datasets.info - Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-39b52f6e03e85a82/0.0.0
|
||
Found cached dataset generator (/scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-39b52f6e03e85a82/0.0.0)
|
||
2026-04-16 16:21:46 - INFO - datasets.builder - Found cached dataset generator (/scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-39b52f6e03e85a82/0.0.0)
|
||
Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-39b52f6e03e85a82/0.0.0
|
||
2026-04-16 16:21:46 - INFO - datasets.info - Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-39b52f6e03e85a82/0.0.0
|
||
Using custom data configuration default-1519231937de8df3
|
||
2026-04-16 16:21:46 - INFO - datasets.builder - Using custom data configuration default-1519231937de8df3
|
||
Loading Dataset Infos from /home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/datasets/packaged_modules/generator
|
||
2026-04-16 16:21:46 - INFO - datasets.info - Loading Dataset Infos from /home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/datasets/packaged_modules/generator
|
||
Overwrite dataset info from restored data version if exists.
|
||
2026-04-16 16:21:46 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists.
|
||
Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-1519231937de8df3/0.0.0
|
||
2026-04-16 16:21:46 - INFO - datasets.info - Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-1519231937de8df3/0.0.0
|
||
Found cached dataset generator (/scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-1519231937de8df3/0.0.0)
|
||
2026-04-16 16:21:46 - INFO - datasets.builder - Found cached dataset generator (/scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-1519231937de8df3/0.0.0)
|
||
Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-1519231937de8df3/0.0.0
|
||
2026-04-16 16:21:46 - INFO - datasets.info - Loading Dataset info from /scratch/feng.yulu/dynamic-dpo-v4/hf/datasets/generator/default-1519231937de8df3/0.0.0
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:412: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `SFTTrainer.__init__`. Use `processing_class` instead.
|
||
super().__init__(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:412: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `SFTTrainer.__init__`. Use `processing_class` instead.
|
||
super().__init__(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:412: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `SFTTrainer.__init__`. Use `processing_class` instead.
|
||
super().__init__(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/trl/trainer/sft_trainer.py:412: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `SFTTrainer.__init__`. Use `processing_class` instead.
|
||
super().__init__(
|
||
[INFO|trainer.py:748] 2026-04-16 16:21:49,099 >> Using auto half precision backend
|
||
2026-04-16 16:21:49 - INFO - __main__ - *** Train ***
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/accelerate/accelerator.py:1557: UserWarning: Upcasted low precision parameters in LlamaForCausalLM because mixed precision turned on in FSDP. Affects: model.embed_tokens.weight, model.norm.weight, lm_head.weight.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/accelerate/accelerator.py:1557: UserWarning: Upcasted low precision parameters in LlamaDecoderLayer because mixed precision turned on in FSDP. Affects: self_attn.q_proj.weight, self_attn.k_proj.weight, self_attn.v_proj.weight, self_attn.o_proj.weight, mlp.gate_proj.weight, mlp.up_proj.weight, mlp.down_proj.weight, input_layernorm.weight, post_attention_layernorm.weight.
|
||
warnings.warn(
|
||
/home/feng.yulu/.conda/envs/dpo_venv/lib/python3.11/site-packages/accelerate/accelerator.py:1563: UserWarning: FSDP upcast of low precision parameters may affect the precision of model checkpoints.
|
||
warnings.warn(
|
||
[INFO|trainer.py:2414] 2026-04-16 16:22:27,009 >> ***** Running training *****
|
||
[INFO|trainer.py:2415] 2026-04-16 16:22:27,009 >> Num examples = 16,516
|
||
[INFO|trainer.py:2416] 2026-04-16 16:22:27,009 >> Num Epochs = 1
|
||
[INFO|trainer.py:2417] 2026-04-16 16:22:27,009 >> Instantaneous batch size per device = 8
|
||
[INFO|trainer.py:2420] 2026-04-16 16:22:27,009 >> Total train batch size (w. parallel, distributed & accumulation) = 64
|
||
[INFO|trainer.py:2421] 2026-04-16 16:22:27,009 >> Gradient Accumulation steps = 2
|
||
[INFO|trainer.py:2422] 2026-04-16 16:22:27,009 >> Total optimization steps = 258
|
||
[INFO|trainer.py:2423] 2026-04-16 16:22:27,010 >> Number of trainable parameters = 2,007,565,312
|
||
[INFO|integration_utils.py:831] 2026-04-16 16:22:27,011 >> Automatic Weights & Biases logging enabled, to disable set os.environ["WANDB_DISABLED"] = "true"
|
||
wandb: Currently logged in as: can-not-fand (can-not-fand-northeastern-university). Use `wandb login --relogin` to force relogin
|
||
wandb: wandb version 0.26.0 is available! To upgrade, please run:
|
||
wandb: $ pip install wandb --upgrade
|
||
wandb: Tracking run with wandb version 0.17.5
|
||
wandb: Run data is saved locally in /scratch/feng.yulu/dynamic-dpo-v4/wandb/wandb/run-20260416_162228-ivik22vv
|
||
wandb: Run `wandb offline` to turn off syncing.
|
||
wandb: Syncing run llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101
|
||
wandb: ⭐️ View project at https://wandb.ai/can-not-fand-northeastern-university/huggingface
|
||
wandb: 🚀 View run at https://wandb.ai/can-not-fand-northeastern-university/huggingface/runs/ivik22vv
|
||
|
||
0%| | 0/258 [00:00<?, ?it/s]
|
||
0%| | 1/258 [00:02<11:29, 2.68s/it]
|
||
|
||
{'loss': 3.1242, 'grad_norm': 6.09610478125056e+18, 'learning_rate': 0.0, 'epoch': 0.0}
|
||
|
||
0%| | 1/258 [00:02<11:29, 2.68s/it]
|
||
1%| | 2/258 [00:03<07:51, 1.84s/it]
|
||
1%| | 3/258 [00:05<06:44, 1.58s/it]
|
||
2%|▏ | 4/258 [00:06<06:14, 1.47s/it]
|
||
2%|▏ | 5/258 [00:07<05:55, 1.41s/it]
|
||
|
||
{'loss': 3.1772, 'grad_norm': 2697.71337890625, 'learning_rate': 3.0769230769230774e-06, 'epoch': 0.02}
|
||
|
||
2%|▏ | 5/258 [00:07<05:55, 1.41s/it]
|
||
2%|▏ | 6/258 [00:09<05:43, 1.36s/it]
|
||
3%|▎ | 7/258 [00:10<05:34, 1.33s/it]
|
||
3%|▎ | 8/258 [00:11<05:28, 1.31s/it]
|
||
3%|▎ | 9/258 [00:12<05:23, 1.30s/it]
|
||
4%|▍ | 10/258 [00:14<05:20, 1.29s/it]
|
||
|
||
{'loss': 2.8881, 'grad_norm': 25.10409927368164, 'learning_rate': 6.923076923076923e-06, 'epoch': 0.04}
|
||
|
||
4%|▍ | 10/258 [00:14<05:20, 1.29s/it]
|
||
4%|▍ | 11/258 [00:15<05:16, 1.28s/it]
|
||
5%|▍ | 12/258 [00:16<05:14, 1.28s/it]
|
||
5%|▌ | 13/258 [00:17<05:12, 1.27s/it]
|
||
5%|▌ | 14/258 [00:19<05:09, 1.27s/it]
|
||
6%|▌ | 15/258 [00:20<05:08, 1.27s/it]
|
||
|
||
{'loss': 2.4609, 'grad_norm': 12.363713264465332, 'learning_rate': 1.076923076923077e-05, 'epoch': 0.06}
|
||
|
||
6%|▌ | 15/258 [00:20<05:08, 1.27s/it]
|
||
6%|▌ | 16/258 [00:21<05:06, 1.27s/it]
|
||
7%|▋ | 17/258 [00:23<05:04, 1.26s/it]
|
||
7%|▋ | 18/258 [00:24<05:03, 1.27s/it]
|
||
7%|▋ | 19/258 [00:25<05:13, 1.31s/it]
|
||
8%|▊ | 20/258 [00:26<05:08, 1.30s/it]
|
||
|
||
{'loss': 2.2508, 'grad_norm': 22.165477752685547, 'learning_rate': 1.4615384615384615e-05, 'epoch': 0.08}
|
||
|
||
8%|▊ | 20/258 [00:27<05:08, 1.30s/it]
|
||
8%|▊ | 21/258 [00:28<05:05, 1.29s/it]
|
||
9%|▊ | 22/258 [00:29<05:02, 1.28s/it]
|
||
9%|▉ | 23/258 [00:30<04:59, 1.27s/it]
|
||
9%|▉ | 24/258 [00:32<04:57, 1.27s/it]
|
||
10%|▉ | 25/258 [00:33<04:55, 1.27s/it]
|
||
|
||
{'loss': 2.0898, 'grad_norm': 14.86285400390625, 'learning_rate': 1.8461538461538465e-05, 'epoch': 0.1}
|
||
|
||
10%|▉ | 25/258 [00:33<04:55, 1.27s/it]
|
||
10%|█ | 26/258 [00:34<04:53, 1.27s/it]
|
||
10%|█ | 27/258 [00:35<04:51, 1.26s/it]
|
||
11%|█ | 28/258 [00:37<04:51, 1.27s/it]
|
||
11%|█ | 29/258 [00:38<04:49, 1.26s/it]
|
||
12%|█▏ | 30/258 [00:39<04:47, 1.26s/it]
|
||
|
||
{'loss': 1.9877, 'grad_norm': 7.5494914054870605, 'learning_rate': 1.9991749570421146e-05, 'epoch': 0.12}
|
||
|
||
12%|█▏ | 30/258 [00:39<04:47, 1.26s/it]
|
||
12%|█▏ | 31/258 [00:40<04:46, 1.26s/it]
|
||
12%|█▏ | 32/258 [00:42<04:45, 1.26s/it]
|
||
13%|█▎ | 33/258 [00:43<04:44, 1.27s/it]
|
||
13%|█▎ | 34/258 [00:44<04:42, 1.26s/it]
|
||
14%|█▎ | 35/258 [00:45<04:41, 1.26s/it]
|
||
|
||
{'loss': 1.8119, 'grad_norm': 4.193073272705078, 'learning_rate': 1.9941379571543597e-05, 'epoch': 0.14}
|
||
|
||
14%|█▎ | 35/258 [00:45<04:41, 1.26s/it]
|
||
14%|█▍ | 36/258 [00:47<04:51, 1.31s/it]
|
||
14%|█▍ | 37/258 [00:48<04:46, 1.30s/it]
|
||
15%|█▍ | 38/258 [00:49<04:42, 1.28s/it]
|
||
15%|█▌ | 39/258 [00:51<04:48, 1.32s/it]
|
||
16%|█▌ | 40/258 [00:52<04:43, 1.30s/it]
|
||
|
||
{'loss': 1.7714, 'grad_norm': 5.1745171546936035, 'learning_rate': 1.984545368367337e-05, 'epoch': 0.15}
|
||
|
||
16%|█▌ | 40/258 [00:52<04:43, 1.30s/it]
|
||
16%|█▌ | 41/258 [00:53<04:39, 1.29s/it]
|
||
16%|█▋ | 42/258 [00:55<04:36, 1.28s/it]
|
||
17%|█▋ | 43/258 [00:56<04:33, 1.27s/it]
|
||
17%|█▋ | 44/258 [00:57<04:31, 1.27s/it]
|
||
17%|█▋ | 45/258 [00:58<04:30, 1.27s/it]
|
||
|
||
{'loss': 1.7391, 'grad_norm': 6.300442695617676, 'learning_rate': 1.9704411482532116e-05, 'epoch': 0.17}
|
||
|
||
17%|█▋ | 45/258 [00:58<04:30, 1.27s/it]
|
||
18%|█▊ | 46/258 [01:00<04:28, 1.27s/it]
|
||
18%|█▊ | 47/258 [01:01<04:26, 1.26s/it]
|
||
19%|█▊ | 48/258 [01:02<04:25, 1.26s/it]
|
||
19%|█▉ | 49/258 [01:03<04:23, 1.26s/it]
|
||
19%|█▉ | 50/258 [01:05<04:22, 1.26s/it]
|
||
|
||
{'loss': 1.7088, 'grad_norm': 5.5538201332092285, 'learning_rate': 1.9518899287155558e-05, 'epoch': 0.19}
|
||
|
||
19%|█▉ | 50/258 [01:05<04:22, 1.26s/it]
|
||
20%|█▉ | 51/258 [01:06<04:40, 1.36s/it]
|
||
20%|██ | 52/258 [01:07<04:33, 1.33s/it]
|
||
21%|██ | 53/258 [01:09<04:27, 1.31s/it]
|
||
21%|██ | 54/258 [01:10<04:23, 1.29s/it]
|
||
21%|██▏ | 55/258 [01:11<04:20, 1.28s/it]
|
||
|
||
{'loss': 1.6553, 'grad_norm': 4.729171276092529, 'learning_rate': 1.9289767198167918e-05, 'epoch': 0.21}
|
||
|
||
21%|██▏ | 55/258 [01:11<04:20, 1.28s/it]
|
||
22%|██▏ | 56/258 [01:12<04:17, 1.28s/it]
|
||
22%|██▏ | 57/258 [01:14<04:15, 1.27s/it]
|
||
22%|██▏ | 58/258 [01:15<04:13, 1.27s/it]
|
||
23%|██▎ | 59/258 [01:16<04:11, 1.26s/it]
|
||
23%|██▎ | 60/258 [01:18<04:10, 1.26s/it]
|
||
|
||
{'loss': 1.6234, 'grad_norm': 2.736438512802124, 'learning_rate': 1.9018065202237083e-05, 'epoch': 0.23}
|
||
|
||
23%|██▎ | 60/258 [01:18<04:10, 1.26s/it]
|
||
24%|██▎ | 61/258 [01:19<04:08, 1.26s/it]
|
||
24%|██▍ | 62/258 [01:20<04:07, 1.26s/it]
|
||
24%|██▍ | 63/258 [01:21<04:05, 1.26s/it]
|
||
25%|██▍ | 64/258 [01:23<04:22, 1.35s/it]
|
||
25%|██▌ | 65/258 [01:24<04:15, 1.32s/it]
|
||
|
||
{'loss': 1.6005, 'grad_norm': 2.781848192214966, 'learning_rate': 1.8705038360561724e-05, 'epoch': 0.25}
|
||
|
||
25%|██▌ | 65/258 [01:24<04:15, 1.32s/it]
|
||
26%|██▌ | 66/258 [01:25<04:10, 1.31s/it]
|
||
26%|██▌ | 67/258 [01:27<04:06, 1.29s/it]
|
||
26%|██▋ | 68/258 [01:28<04:04, 1.28s/it]
|
||
27%|██▋ | 69/258 [01:29<04:01, 1.28s/it]
|
||
27%|██▋ | 70/258 [01:31<04:06, 1.31s/it]
|
||
|
||
{'loss': 1.6161, 'grad_norm': 30.041719436645508, 'learning_rate': 1.8352121103438804e-05, 'epoch': 0.27}
|
||
|
||
27%|██▋ | 70/258 [01:31<04:06, 1.31s/it]
|
||
28%|██▊ | 71/258 [01:32<04:02, 1.30s/it]
|
||
28%|██▊ | 72/258 [01:33<03:59, 1.29s/it]
|
||
28%|██▊ | 73/258 [01:34<03:56, 1.28s/it]
|
||
29%|██▊ | 74/258 [01:36<03:54, 1.27s/it]
|
||
29%|██▉ | 75/258 [01:37<04:00, 1.32s/it]
|
||
|
||
{'loss': 1.5743, 'grad_norm': 2.318030595779419, 'learning_rate': 1.796093065705644e-05, 'epoch': 0.29}
|
||
|
||
29%|██▉ | 75/258 [01:37<04:00, 1.32s/it]
|
||
29%|██▉ | 76/258 [01:38<04:03, 1.34s/it]
|
||
30%|██▉ | 77/258 [01:40<03:57, 1.31s/it]
|
||
30%|███ | 78/258 [01:41<03:53, 1.30s/it]
|
||
31%|███ | 79/258 [01:42<03:49, 1.28s/it]
|
||
31%|███ | 80/258 [01:43<03:47, 1.28s/it]
|
||
|
||
{'loss': 1.537, 'grad_norm': 2.369173526763916, 'learning_rate': 1.7533259632633443e-05, 'epoch': 0.31}
|
||
|
||
31%|███ | 80/258 [01:43<03:47, 1.28s/it]
|
||
31%|███▏ | 81/258 [01:45<03:45, 1.27s/it]
|
||
32%|███▏ | 82/258 [01:46<03:43, 1.27s/it]
|
||
32%|███▏ | 83/258 [01:47<03:41, 1.27s/it]
|
||
33%|███▎ | 84/258 [01:48<03:40, 1.27s/it]
|
||
33%|███▎ | 85/258 [01:50<03:38, 1.27s/it]
|
||
|
||
{'loss': 1.5716, 'grad_norm': 8.767570495605469, 'learning_rate': 1.7071067811865477e-05, 'epoch': 0.33}
|
||
|
||
33%|███▎ | 85/258 [01:50<03:38, 1.27s/it]
|
||
33%|███▎ | 86/258 [01:51<03:45, 1.31s/it]
|
||
34%|███▎ | 87/258 [01:53<03:49, 1.34s/it]
|
||
34%|███▍ | 88/258 [01:54<03:44, 1.32s/it]
|
||
34%|███▍ | 89/258 [01:55<03:39, 1.30s/it]
|
||
35%|███▍ | 90/258 [01:56<03:36, 1.29s/it]
|
||
|
||
{'loss': 1.5327, 'grad_norm': 2.4866902828216553, 'learning_rate': 1.6576473166320644e-05, 'epoch': 0.35}
|
||
|
||
35%|███▍ | 90/258 [01:56<03:36, 1.29s/it]
|
||
35%|███▌ | 91/258 [01:58<03:33, 1.28s/it]
|
||
36%|███▌ | 92/258 [01:59<03:31, 1.28s/it]
|
||
36%|███▌ | 93/258 [02:00<03:30, 1.27s/it]
|
||
36%|███▋ | 94/258 [02:02<03:35, 1.31s/it]
|
||
37%|███▋ | 95/258 [02:03<03:31, 1.29s/it]
|
||
|
||
{'loss': 1.5223, 'grad_norm': 2.8688602447509766, 'learning_rate': 1.6051742151937655e-05, 'epoch': 0.37}
|
||
|
||
37%|███▋ | 95/258 [02:03<03:31, 1.29s/it]
|
||
37%|███▋ | 96/258 [02:04<03:36, 1.33s/it]
|
||
38%|███▊ | 97/258 [02:06<03:37, 1.35s/it]
|
||
38%|███▊ | 98/258 [02:07<03:31, 1.32s/it]
|
||
38%|███▊ | 99/258 [02:08<03:27, 1.30s/it]
|
||
39%|███▉ | 100/258 [02:09<03:24, 1.29s/it]
|
||
|
||
{'loss': 1.5069, 'grad_norm': 9.360047340393066, 'learning_rate': 1.549927932310155e-05, 'epoch': 0.39}
|
||
|
||
39%|███▉ | 100/258 [02:09<03:24, 1.29s/it][INFO|trainer.py:4307] 2026-04-16 16:24:43,454 >>
|
||
***** Running Evaluation *****
|
||
[INFO|trainer.py:4309] 2026-04-16 16:24:43,454 >> Num examples = 895
|
||
[INFO|trainer.py:4312] 2026-04-16 16:24:43,454 >> Batch size = 8
|
||
|
||
|
||
0%| | 0/28 [00:00<?, ?it/s][A
|
||
|
||
7%|▋ | 2/28 [00:00<00:02, 11.79it/s][A
|
||
|
||
14%|█▍ | 4/28 [00:00<00:03, 7.44it/s][A
|
||
|
||
18%|█▊ | 5/28 [00:00<00:03, 6.93it/s][A
|
||
|
||
21%|██▏ | 6/28 [00:00<00:03, 6.50it/s][A
|
||
|
||
25%|██▌ | 7/28 [00:01<00:03, 6.28it/s][A
|
||
|
||
29%|██▊ | 8/28 [00:01<00:03, 6.14it/s][A
|
||
|
||
32%|███▏ | 9/28 [00:01<00:03, 6.11it/s][A
|
||
|
||
36%|███▌ | 10/28 [00:01<00:02, 6.07it/s][A
|
||
|
||
39%|███▉ | 11/28 [00:01<00:02, 5.98it/s][A
|
||
|
||
43%|████▎ | 12/28 [00:01<00:02, 5.89it/s][A
|
||
|
||
46%|████▋ | 13/28 [00:02<00:02, 5.89it/s][A
|
||
|
||
50%|█████ | 14/28 [00:02<00:02, 5.89it/s][A
|
||
|
||
54%|█████▎ | 15/28 [00:02<00:02, 5.89it/s][A
|
||
|
||
57%|█████▋ | 16/28 [00:02<00:02, 5.87it/s][A
|
||
|
||
61%|██████ | 17/28 [00:02<00:01, 5.87it/s][A
|
||
|
||
64%|██████▍ | 18/28 [00:02<00:01, 5.82it/s][A
|
||
|
||
68%|██████▊ | 19/28 [00:03<00:01, 5.80it/s][A
|
||
|
||
71%|███████▏ | 20/28 [00:03<00:01, 5.82it/s][A
|
||
|
||
75%|███████▌ | 21/28 [00:03<00:01, 5.83it/s][A
|
||
|
||
79%|███████▊ | 22/28 [00:03<00:01, 5.86it/s][A
|
||
|
||
82%|████████▏ | 23/28 [00:03<00:00, 5.84it/s][A
|
||
|
||
86%|████████▌ | 24/28 [00:03<00:00, 5.83it/s][A
|
||
|
||
89%|████████▉ | 25/28 [00:04<00:00, 5.84it/s][A
|
||
|
||
93%|█████████▎| 26/28 [00:04<00:00, 5.87it/s][A
|
||
|
||
96%|█████████▋| 27/28 [00:04<00:00, 5.86it/s][A
|
||
|
||
100%|██████████| 28/28 [00:04<00:00, 5.89it/s][A
|
||
|
||
|
||
|
||
[A{'eval_loss': 1.489111065864563, 'eval_runtime': 4.7946, 'eval_samples_per_second': 186.667, 'eval_steps_per_second': 5.84, 'epoch': 0.39}
|
||
|
||
39%|███▉ | 100/258 [02:14<03:24, 1.29s/it]
|
||
|
||
100%|██████████| 28/28 [00:04<00:00, 5.89it/s][A
|
||
|
||
[A
|
||
39%|███▉ | 101/258 [02:15<07:07, 2.72s/it]
|
||
40%|███▉ | 102/258 [02:17<05:56, 2.28s/it]
|
||
40%|███▉ | 103/258 [02:18<05:06, 1.97s/it]
|
||
40%|████ | 104/258 [02:19<04:31, 1.76s/it]
|
||
41%|████ | 105/258 [02:21<04:14, 1.66s/it]
|
||
|
||
{'loss': 1.4631, 'grad_norm': 2.7148385047912598, 'learning_rate': 1.4921616313890073e-05, 'epoch': 0.41}
|
||
|
||
41%|████ | 105/258 [02:21<04:14, 1.66s/it]
|
||
41%|████ | 106/258 [02:22<04:00, 1.58s/it]
|
||
41%|████▏ | 107/258 [02:23<03:44, 1.49s/it]
|
||
42%|████▏ | 108/258 [02:25<03:32, 1.42s/it]
|
||
42%|████▏ | 109/258 [02:26<03:23, 1.37s/it]
|
||
43%|████▎ | 110/258 [02:27<03:17, 1.34s/it]
|
||
|
||
{'loss': 1.4502, 'grad_norm': 2.1432764530181885, 'learning_rate': 1.4321400236983459e-05, 'epoch': 0.43}
|
||
|
||
43%|████▎ | 110/258 [02:27<03:17, 1.34s/it]
|
||
43%|████▎ | 111/258 [02:28<03:12, 1.31s/it]
|
||
43%|████▎ | 112/258 [02:30<03:09, 1.30s/it]
|
||
44%|████▍ | 113/258 [02:31<03:05, 1.28s/it]
|
||
44%|████▍ | 114/258 [02:32<03:03, 1.27s/it]
|
||
45%|████▍ | 115/258 [02:34<03:08, 1.31s/it]
|
||
|
||
{'loss': 1.411, 'grad_norm': 2.373682975769043, 'learning_rate': 1.3701381553399147e-05, 'epoch': 0.44}
|
||
|
||
45%|████▍ | 115/258 [02:34<03:08, 1.31s/it]
|
||
45%|████▍ | 116/258 [02:35<03:09, 1.34s/it]
|
||
45%|████▌ | 117/258 [02:36<03:10, 1.35s/it]
|
||
46%|████▌ | 118/258 [02:38<03:05, 1.32s/it]
|
||
46%|████▌ | 119/258 [02:39<03:01, 1.30s/it]
|
||
47%|████▋ | 120/258 [02:40<02:58, 1.29s/it]
|
||
|
||
{'loss': 1.4031, 'grad_norm': 2.2317380905151367, 'learning_rate': 1.3064401468637793e-05, 'epoch': 0.46}
|
||
|
||
47%|████▋ | 120/258 [02:40<02:58, 1.29s/it]
|
||
47%|████▋ | 121/258 [02:41<02:55, 1.28s/it]
|
||
47%|████▋ | 122/258 [02:43<02:53, 1.27s/it]
|
||
48%|████▊ | 123/258 [02:44<02:51, 1.27s/it]
|
||
48%|████▊ | 124/258 [02:45<02:55, 1.31s/it]
|
||
48%|████▊ | 125/258 [02:47<02:56, 1.33s/it]
|
||
|
||
{'loss': 1.3929, 'grad_norm': 1.9476709365844727, 'learning_rate': 1.2413378912997058e-05, 'epoch': 0.48}
|
||
|
||
48%|████▊ | 125/258 [02:47<02:56, 1.33s/it]
|
||
49%|████▉ | 126/258 [02:48<02:52, 1.31s/it]
|
||
49%|████▉ | 127/258 [02:49<02:49, 1.29s/it]
|
||
50%|████▉ | 128/258 [02:50<02:46, 1.28s/it]
|
||
50%|█████ | 129/258 [02:52<02:44, 1.27s/it]
|
||
50%|█████ | 130/258 [02:53<02:42, 1.27s/it]
|
||
|
||
{'loss': 1.3855, 'grad_norm': 1.9585973024368286, 'learning_rate': 1.175129716571531e-05, 'epoch': 0.5}
|
||
|
||
50%|█████ | 130/258 [02:53<02:42, 1.27s/it]
|
||
51%|█████ | 131/258 [02:54<02:40, 1.27s/it]
|
||
51%|█████ | 132/258 [02:55<02:39, 1.26s/it]
|
||
52%|█████▏ | 133/258 [02:57<02:43, 1.31s/it]
|
||
52%|█████▏ | 134/258 [02:58<02:46, 1.34s/it]
|
||
52%|█████▏ | 135/258 [03:00<02:41, 1.32s/it]
|
||
|
||
{'loss': 1.3818, 'grad_norm': 2.38059401512146, 'learning_rate': 1.1081190184239418e-05, 'epoch': 0.52}
|
||
|
||
52%|█████▏ | 135/258 [03:00<02:41, 1.32s/it]
|
||
53%|█████▎ | 136/258 [03:01<02:38, 1.30s/it]
|
||
53%|█████▎ | 137/258 [03:02<02:41, 1.33s/it]
|
||
53%|█████▎ | 138/258 [03:03<02:37, 1.31s/it]
|
||
54%|█████▍ | 139/258 [03:05<02:34, 1.30s/it]
|
||
54%|█████▍ | 140/258 [03:06<02:31, 1.29s/it]
|
||
|
||
{'loss': 1.334, 'grad_norm': 2.2399237155914307, 'learning_rate': 1.0406128701262128e-05, 'epoch': 0.54}
|
||
|
||
54%|█████▍ | 140/258 [03:06<02:31, 1.29s/it]
|
||
55%|█████▍ | 141/258 [03:07<02:29, 1.28s/it]
|
||
55%|█████▌ | 142/258 [03:09<02:33, 1.32s/it]
|
||
55%|█████▌ | 143/258 [03:10<02:35, 1.35s/it]
|
||
56%|█████▌ | 144/258 [03:11<02:30, 1.32s/it]
|
||
56%|█████▌ | 145/258 [03:13<02:27, 1.30s/it]
|
||
|
||
{'loss': 1.3365, 'grad_norm': 2.42098069190979, 'learning_rate': 9.729206153238658e-06, 'epoch': 0.56}
|
||
|
||
56%|█████▌ | 145/258 [03:13<02:27, 1.30s/it]
|
||
57%|█████▋ | 146/258 [03:14<02:24, 1.29s/it]
|
||
57%|█████▋ | 147/258 [03:15<02:21, 1.28s/it]
|
||
57%|█████▋ | 148/258 [03:16<02:19, 1.27s/it]
|
||
58%|█████▊ | 149/258 [03:18<02:17, 1.26s/it]
|
||
58%|█████▊ | 150/258 [03:19<02:16, 1.26s/it]
|
||
|
||
{'loss': 1.3288, 'grad_norm': 2.278903007507324, 'learning_rate': 9.053524504864391e-06, 'epoch': 0.58}
|
||
|
||
58%|█████▊ | 150/258 [03:19<02:16, 1.26s/it]
|
||
59%|█████▊ | 151/258 [03:20<02:20, 1.31s/it]
|
||
59%|█████▉ | 152/258 [03:22<02:21, 1.34s/it]
|
||
59%|█████▉ | 153/258 [03:23<02:17, 1.31s/it]
|
||
60%|█████▉ | 154/258 [03:24<02:18, 1.33s/it]
|
||
60%|██████ | 155/258 [03:26<02:14, 1.31s/it]
|
||
|
||
{'loss': 1.309, 'grad_norm': 1.902079701423645, 'learning_rate': 8.382180034472353e-06, 'epoch': 0.6}
|
||
|
||
60%|██████ | 155/258 [03:26<02:14, 1.31s/it]
|
||
60%|██████ | 156/258 [03:27<02:12, 1.29s/it]
|
||
61%|██████ | 157/258 [03:28<02:09, 1.28s/it]
|
||
61%|██████ | 158/258 [03:29<02:07, 1.28s/it]
|
||
62%|██████▏ | 159/258 [03:31<02:05, 1.27s/it]
|
||
62%|██████▏ | 160/258 [03:32<02:08, 1.31s/it]
|
||
|
||
{'loss': 1.3069, 'grad_norm': 1.8283921480178833, 'learning_rate': 7.718249145488143e-06, 'epoch': 0.62}
|
||
|
||
62%|██████▏ | 160/258 [03:32<02:08, 1.31s/it]
|
||
62%|██████▏ | 161/258 [03:33<02:09, 1.33s/it]
|
||
63%|██████▎ | 162/258 [03:35<02:05, 1.31s/it]
|
||
63%|██████▎ | 163/258 [03:36<02:02, 1.29s/it]
|
||
64%|██████▎ | 164/258 [03:37<02:00, 1.28s/it]
|
||
64%|██████▍ | 165/258 [03:38<01:58, 1.27s/it]
|
||
|
||
{'loss': 1.2787, 'grad_norm': 1.9884213209152222, 'learning_rate': 7.064774268960654e-06, 'epoch': 0.64}
|
||
|
||
64%|██████▍ | 165/258 [03:38<01:58, 1.27s/it]
|
||
64%|██████▍ | 166/258 [03:40<01:56, 1.27s/it]
|
||
65%|██████▍ | 167/258 [03:41<01:54, 1.26s/it]
|
||
65%|██████▌ | 168/258 [03:42<01:53, 1.26s/it]
|
||
66%|██████▌ | 169/258 [03:44<01:59, 1.34s/it]
|
||
66%|██████▌ | 170/258 [03:45<01:59, 1.36s/it]
|
||
|
||
{'loss': 1.2678, 'grad_norm': 2.0930237770080566, 'learning_rate': 6.4247499217695995e-06, 'epoch': 0.66}
|
||
|
||
66%|██████▌ | 170/258 [03:45<01:59, 1.36s/it]
|
||
66%|██████▋ | 171/258 [03:46<01:55, 1.33s/it]
|
||
67%|██████▋ | 172/258 [03:48<01:52, 1.31s/it]
|
||
67%|██████▋ | 173/258 [03:49<01:49, 1.29s/it]
|
||
67%|██████▋ | 174/258 [03:50<01:47, 1.28s/it]
|
||
68%|██████▊ | 175/258 [03:51<01:45, 1.27s/it]
|
||
|
||
{'loss': 1.2107, 'grad_norm': 2.522498369216919, 'learning_rate': 5.801108984397355e-06, 'epoch': 0.68}
|
||
|
||
68%|██████▊ | 175/258 [03:51<01:45, 1.27s/it]
|
||
68%|██████▊ | 176/258 [03:53<01:43, 1.26s/it]
|
||
69%|██████▊ | 177/258 [03:54<01:42, 1.26s/it]
|
||
69%|██████▉ | 178/258 [03:55<01:44, 1.31s/it]
|
||
69%|██████▉ | 179/258 [03:57<01:45, 1.33s/it]
|
||
70%|██████▉ | 180/258 [03:58<01:42, 1.31s/it]
|
||
|
||
{'loss': 1.2417, 'grad_norm': 2.825383424758911, 'learning_rate': 5.196709261146606e-06, 'epoch': 0.7}
|
||
|
||
70%|██████▉ | 180/258 [03:58<01:42, 1.31s/it]
|
||
70%|███████ | 181/258 [03:59<01:39, 1.29s/it]
|
||
71%|███████ | 182/258 [04:01<01:40, 1.32s/it]
|
||
71%|███████ | 183/258 [04:02<01:37, 1.30s/it]
|
||
71%|███████▏ | 184/258 [04:03<01:35, 1.29s/it]
|
||
72%|███████▏ | 185/258 [04:04<01:33, 1.28s/it]
|
||
|
||
{'loss': 1.2198, 'grad_norm': 2.353144645690918, 'learning_rate': 4.614320384390959e-06, 'epoch': 0.72}
|
||
|
||
72%|███████▏ | 185/258 [04:04<01:33, 1.28s/it]
|
||
72%|███████▏ | 186/258 [04:06<01:31, 1.27s/it]
|
||
72%|███████▏ | 187/258 [04:07<01:32, 1.31s/it]
|
||
73%|███████▎ | 188/258 [04:08<01:33, 1.33s/it]
|
||
73%|███████▎ | 189/258 [04:10<01:30, 1.31s/it]
|
||
74%|███████▎ | 190/258 [04:11<01:27, 1.29s/it]
|
||
|
||
{'loss': 1.2026, 'grad_norm': 2.3441641330718994, 'learning_rate': 4.056611122869106e-06, 'epoch': 0.74}
|
||
|
||
74%|███████▎ | 190/258 [04:11<01:27, 1.29s/it]
|
||
74%|███████▍ | 191/258 [04:12<01:25, 1.28s/it]
|
||
74%|███████▍ | 192/258 [04:13<01:24, 1.27s/it]
|
||
75%|███████▍ | 193/258 [04:15<01:22, 1.27s/it]
|
||
75%|███████▌ | 194/258 [04:16<01:23, 1.31s/it]
|
||
76%|███████▌ | 195/258 [04:17<01:21, 1.29s/it]
|
||
|
||
{'loss': 1.1828, 'grad_norm': 2.090709924697876, 'learning_rate': 3.5261371521817247e-06, 'epoch': 0.75}
|
||
|
||
76%|███████▌ | 195/258 [04:17<01:21, 1.29s/it]
|
||
76%|███████▌ | 196/258 [04:19<01:22, 1.33s/it]
|
||
76%|███████▋ | 197/258 [04:20<01:22, 1.35s/it]
|
||
77%|███████▋ | 198/258 [04:21<01:19, 1.32s/it]
|
||
77%|███████▋ | 199/258 [04:23<01:16, 1.30s/it]
|
||
78%|███████▊ | 200/258 [04:24<01:14, 1.29s/it]
|
||
|
||
{'loss': 1.2171, 'grad_norm': 1.8887003660202026, 'learning_rate': 3.0253293435321797e-06, 'epoch': 0.77}
|
||
|
||
78%|███████▊ | 200/258 [04:24<01:14, 1.29s/it][INFO|trainer.py:4307] 2026-04-16 16:26:57,969 >>
|
||
***** Running Evaluation *****
|
||
[INFO|trainer.py:4309] 2026-04-16 16:26:57,969 >> Num examples = 895
|
||
[INFO|trainer.py:4312] 2026-04-16 16:26:57,969 >> Batch size = 8
|
||
|
||
|
||
0%| | 0/28 [00:00<?, ?it/s][A
|
||
|
||
7%|▋ | 2/28 [00:00<00:02, 11.85it/s][A
|
||
|
||
14%|█▍ | 4/28 [00:00<00:03, 7.45it/s][A
|
||
|
||
18%|█▊ | 5/28 [00:00<00:03, 6.90it/s][A
|
||
|
||
21%|██▏ | 6/28 [00:00<00:03, 6.51it/s][A
|
||
|
||
25%|██▌ | 7/28 [00:01<00:03, 6.32it/s][A
|
||
|
||
29%|██▊ | 8/28 [00:01<00:03, 6.18it/s][A
|
||
|
||
32%|███▏ | 9/28 [00:01<00:03, 6.06it/s][A
|
||
|
||
36%|███▌ | 10/28 [00:01<00:02, 6.02it/s][A
|
||
|
||
39%|███▉ | 11/28 [00:01<00:02, 6.01it/s][A
|
||
|
||
43%|████▎ | 12/28 [00:01<00:02, 5.96it/s][A
|
||
|
||
46%|████▋ | 13/28 [00:02<00:02, 5.92it/s][A
|
||
|
||
50%|█████ | 14/28 [00:02<00:02, 5.95it/s][A
|
||
|
||
54%|█████▎ | 15/28 [00:02<00:02, 5.92it/s][A
|
||
|
||
57%|█████▋ | 16/28 [00:02<00:02, 5.90it/s][A
|
||
|
||
61%|██████ | 17/28 [00:02<00:01, 5.89it/s][A
|
||
|
||
64%|██████▍ | 18/28 [00:02<00:01, 5.91it/s][A
|
||
|
||
68%|██████▊ | 19/28 [00:03<00:01, 5.91it/s][A
|
||
|
||
71%|███████▏ | 20/28 [00:03<00:01, 5.90it/s][A
|
||
|
||
75%|███████▌ | 21/28 [00:03<00:01, 5.89it/s][A
|
||
|
||
79%|███████▊ | 22/28 [00:03<00:01, 5.88it/s][A
|
||
|
||
82%|████████▏ | 23/28 [00:03<00:00, 5.90it/s][A
|
||
|
||
86%|████████▌ | 24/28 [00:03<00:00, 5.88it/s][A
|
||
|
||
89%|████████▉ | 25/28 [00:04<00:00, 5.91it/s][A
|
||
|
||
93%|█████████▎| 26/28 [00:04<00:00, 5.88it/s][A
|
||
|
||
96%|█████████▋| 27/28 [00:04<00:00, 5.88it/s][A
|
||
|
||
100%|██████████| 28/28 [00:04<00:00, 5.92it/s][A
|
||
|
||
|
||
|
||
[A{'eval_loss': 1.193406581878662, 'eval_runtime': 4.7625, 'eval_samples_per_second': 187.926, 'eval_steps_per_second': 5.879, 'epoch': 0.77}
|
||
|
||
78%|███████▊ | 200/258 [04:29<01:14, 1.29s/it]
|
||
|
||
100%|██████████| 28/28 [00:04<00:00, 5.92it/s][A
|
||
|
||
[A[INFO|trainer.py:3984] 2026-04-16 16:27:21,898 >> Saving model checkpoint to /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-200
|
||
[INFO|configuration_utils.py:419] 2026-04-16 16:27:21,904 >> Configuration saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-200/config.json
|
||
[INFO|configuration_utils.py:911] 2026-04-16 16:27:21,910 >> Configuration saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-200/generation_config.json
|
||
[INFO|modeling_utils.py:3580] 2026-04-16 16:28:10,583 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 6 checkpoint shards. You can find where each parameters has been saved in the index located at /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-200/model.safetensors.index.json.
|
||
[INFO|tokenization_utils_base.py:2510] 2026-04-16 16:28:10,589 >> tokenizer config file saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-200/tokenizer_config.json
|
||
[INFO|tokenization_utils_base.py:2519] 2026-04-16 16:28:10,592 >> Special tokens file saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-200/special_tokens_map.json
|
||
|
||
78%|███████▊ | 201/258 [09:14<1:23:30, 87.91s/it]
|
||
78%|███████▊ | 202/258 [09:15<57:47, 61.91s/it]
|
||
79%|███████▊ | 203/258 [09:16<40:04, 43.71s/it]
|
||
79%|███████▉ | 204/258 [09:18<27:52, 30.97s/it]
|
||
79%|███████▉ | 205/258 [09:19<19:32, 22.11s/it]
|
||
|
||
{'loss': 1.1818, 'grad_norm': 2.0174171924591064, 'learning_rate': 2.5564826243772965e-06, 'epoch': 0.79}
|
||
|
||
79%|███████▉ | 205/258 [09:19<19:32, 22.11s/it]
|
||
80%|███████▉ | 206/258 [09:21<13:47, 15.91s/it]
|
||
80%|████████ | 207/258 [09:22<09:49, 11.56s/it]
|
||
81%|████████ | 208/258 [09:23<07:03, 8.47s/it]
|
||
81%|████████ | 209/258 [09:24<05:08, 6.30s/it]
|
||
81%|████████▏ | 210/258 [09:26<03:49, 4.79s/it]
|
||
|
||
{'loss': 1.1851, 'grad_norm': 2.1461687088012695, 'learning_rate': 2.1217454620337842e-06, 'epoch': 0.81}
|
||
|
||
81%|████████▏ | 210/258 [09:26<03:49, 4.79s/it]
|
||
82%|████████▏ | 211/258 [09:27<02:55, 3.73s/it]
|
||
82%|████████▏ | 212/258 [09:28<02:17, 2.99s/it]
|
||
83%|████████▎ | 213/258 [09:30<01:51, 2.47s/it]
|
||
83%|████████▎ | 214/258 [09:31<01:34, 2.16s/it]
|
||
83%|████████▎ | 215/258 [09:32<01:22, 1.92s/it]
|
||
|
||
{'loss': 1.1799, 'grad_norm': 1.9792951345443726, 'learning_rate': 1.7231100184310955e-06, 'epoch': 0.83}
|
||
|
||
83%|████████▎ | 215/258 [09:32<01:22, 1.92s/it]
|
||
84%|████████▎ | 216/258 [09:34<01:12, 1.72s/it]
|
||
84%|████████▍ | 217/258 [09:35<01:04, 1.58s/it]
|
||
84%|████████▍ | 218/258 [09:36<00:59, 1.48s/it]
|
||
85%|████████▍ | 219/258 [09:37<00:55, 1.42s/it]
|
||
85%|████████▌ | 220/258 [09:39<00:52, 1.37s/it]
|
||
|
||
{'loss': 1.1748, 'grad_norm': 2.1498570442199707, 'learning_rate': 1.3624030211261684e-06, 'epoch': 0.85}
|
||
|
||
85%|████████▌ | 220/258 [09:39<00:52, 1.37s/it]
|
||
86%|████████▌ | 221/258 [09:40<00:49, 1.34s/it]
|
||
86%|████████▌ | 222/258 [09:41<00:49, 1.37s/it]
|
||
86%|████████▋ | 223/258 [09:43<00:48, 1.38s/it]
|
||
87%|████████▋ | 224/258 [09:44<00:46, 1.38s/it]
|
||
87%|████████▋ | 225/258 [09:45<00:44, 1.34s/it]
|
||
|
||
{'loss': 1.1529, 'grad_norm': 2.3734147548675537, 'learning_rate': 1.0412773924131202e-06, 'epoch': 0.87}
|
||
|
||
87%|████████▋ | 225/258 [09:45<00:44, 1.34s/it]
|
||
88%|████████▊ | 226/258 [09:47<00:42, 1.32s/it]
|
||
88%|████████▊ | 227/258 [09:48<00:40, 1.30s/it]
|
||
88%|████████▊ | 228/258 [09:49<00:38, 1.29s/it]
|
||
89%|████████▉ | 229/258 [09:50<00:37, 1.28s/it]
|
||
89%|████████▉ | 230/258 [09:52<00:35, 1.27s/it]
|
||
|
||
{'loss': 1.1486, 'grad_norm': 21.268768310546875, 'learning_rate': 7.612046748871327e-07, 'epoch': 0.89}
|
||
|
||
89%|████████▉ | 230/258 [09:52<00:35, 1.27s/it]
|
||
90%|████████▉ | 231/258 [09:53<00:34, 1.27s/it]
|
||
90%|████████▉ | 232/258 [09:54<00:34, 1.31s/it]
|
||
90%|█████████ | 233/258 [09:56<00:33, 1.33s/it]
|
||
91%|█████████ | 234/258 [09:57<00:31, 1.31s/it]
|
||
91%|█████████ | 235/258 [09:58<00:30, 1.34s/it]
|
||
|
||
{'loss': 1.1451, 'grad_norm': 2.0091605186462402, 'learning_rate': 5.234682881719766e-07, 'epoch': 0.91}
|
||
|
||
91%|█████████ | 235/258 [09:58<00:30, 1.34s/it]
|
||
91%|█████████▏| 236/258 [10:00<00:29, 1.32s/it]
|
||
92%|█████████▏| 237/258 [10:01<00:27, 1.30s/it]
|
||
92%|█████████▏| 238/258 [10:02<00:25, 1.29s/it]
|
||
93%|█████████▎| 239/258 [10:03<00:24, 1.28s/it]
|
||
93%|█████████▎| 240/258 [10:05<00:22, 1.27s/it]
|
||
|
||
{'loss': 1.1681, 'grad_norm': 1.8940573930740356, 'learning_rate': 3.2915764771193294e-07, 'epoch': 0.93}
|
||
|
||
93%|█████████▎| 240/258 [10:05<00:22, 1.27s/it]
|
||
93%|█████████▎| 241/258 [10:06<00:22, 1.31s/it]
|
||
94%|█████████▍| 242/258 [10:07<00:21, 1.33s/it]
|
||
94%|█████████▍| 243/258 [10:09<00:19, 1.31s/it]
|
||
95%|█████████▍| 244/258 [10:10<00:18, 1.30s/it]
|
||
95%|█████████▍| 245/258 [10:11<00:16, 1.29s/it]
|
||
|
||
{'loss': 1.1391, 'grad_norm': 2.0212926864624023, 'learning_rate': 1.791631725784404e-07, 'epoch': 0.95}
|
||
|
||
95%|█████████▍| 245/258 [10:11<00:16, 1.29s/it]
|
||
95%|█████████▌| 246/258 [10:13<00:15, 1.28s/it]
|
||
96%|█████████▌| 247/258 [10:14<00:14, 1.32s/it]
|
||
96%|█████████▌| 248/258 [10:15<00:13, 1.30s/it]
|
||
97%|█████████▋| 249/258 [10:16<00:11, 1.29s/it]
|
||
97%|█████████▋| 250/258 [10:18<00:10, 1.32s/it]
|
||
|
||
{'loss': 1.1662, 'grad_norm': 2.1692233085632324, 'learning_rate': 7.4172205167945e-08, 'epoch': 0.97}
|
||
|
||
97%|█████████▋| 250/258 [10:18<00:10, 1.32s/it]
|
||
97%|█████████▋| 251/258 [10:19<00:09, 1.34s/it]
|
||
98%|█████████▊| 252/258 [10:20<00:07, 1.32s/it]
|
||
98%|█████████▊| 253/258 [10:22<00:06, 1.30s/it]
|
||
98%|█████████▊| 254/258 [10:23<00:05, 1.29s/it]
|
||
99%|█████████▉| 255/258 [10:24<00:03, 1.28s/it]
|
||
|
||
{'loss': 1.163, 'grad_norm': 1.9714499711990356, 'learning_rate': 1.4665861488761813e-08, 'epoch': 0.99}
|
||
|
||
99%|█████████▉| 255/258 [10:24<00:03, 1.28s/it]
|
||
99%|█████████▉| 256/258 [10:26<00:02, 1.27s/it]
|
||
100%|█████████▉| 257/258 [10:27<00:01, 1.27s/it]
|
||
100%|██████████| 258/258 [10:28<00:00, 1.31s/it][INFO|trainer.py:3984] 2026-04-16 16:33:17,710 >> Saving model checkpoint to /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-258
|
||
[INFO|configuration_utils.py:419] 2026-04-16 16:33:17,717 >> Configuration saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-258/config.json
|
||
[INFO|configuration_utils.py:911] 2026-04-16 16:33:17,725 >> Configuration saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-258/generation_config.json
|
||
[INFO|modeling_utils.py:3580] 2026-04-16 16:34:00,825 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 6 checkpoint shards. You can find where each parameters has been saved in the index located at /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-258/model.safetensors.index.json.
|
||
[INFO|tokenization_utils_base.py:2510] 2026-04-16 16:34:00,890 >> tokenizer config file saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-258/tokenizer_config.json
|
||
[INFO|tokenization_utils_base.py:2519] 2026-04-16 16:34:00,904 >> Special tokens file saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/checkpoint-258/special_tokens_map.json
|
||
[INFO|trainer.py:2681] 2026-04-16 16:37:12,033 >>
|
||
|
||
Training completed. Do not forget to share your model on huggingface.co/models =)
|
||
|
||
|
||
|
||
|
||
{'train_runtime': 885.0234, 'train_samples_per_second': 18.662, 'train_steps_per_second': 0.292, 'train_loss': 1.5008004404777704, 'epoch': 1.0}
|
||
|
||
100%|██████████| 258/258 [14:38<00:00, 1.31s/it]
|
||
100%|██████████| 258/258 [14:38<00:00, 3.41s/it]
|
||
***** train metrics *****
|
||
epoch = 0.9981
|
||
total_flos = 88635435GF
|
||
train_loss = 1.5008
|
||
train_runtime = 0:14:45.02
|
||
train_samples = 43598
|
||
train_samples_per_second = 18.662
|
||
train_steps_per_second = 0.292
|
||
2026-04-16 16:37:12 - INFO - __main__ - *** Save model ***
|
||
[INFO|configuration_utils.py:419] 2026-04-16 16:37:29,519 >> Configuration saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/config.json
|
||
[INFO|configuration_utils.py:911] 2026-04-16 16:37:29,523 >> Configuration saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/generation_config.json
|
||
[INFO|modeling_utils.py:3580] 2026-04-16 16:38:16,222 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 7 checkpoint shards. You can find where each parameters has been saved in the index located at /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/model.safetensors.index.json.
|
||
[INFO|tokenization_utils_base.py:2510] 2026-04-16 16:38:16,229 >> tokenizer config file saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/tokenizer_config.json
|
||
[INFO|tokenization_utils_base.py:2519] 2026-04-16 16:38:16,232 >> Special tokens file saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/special_tokens_map.json
|
||
2026-04-16 16:38:16 - INFO - __main__ - Saved HF-compatible model artifacts to /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101
|
||
2026-04-16 16:38:16 - INFO - __main__ - Saved validated HF-compatible model artifacts to /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101
|
||
[INFO|modelcard.py:450] 2026-04-16 16:38:16,543 >> Dropping the following result as it does not have all the necessary fields:
|
||
{'dataset': {'name': 'Anthropic/hh-rlhf', 'type': 'Anthropic/hh-rlhf', 'config': 'default', 'split': 'train', 'args': 'default'}}
|
||
[INFO|configuration_utils.py:419] 2026-04-16 16:38:16,550 >> Configuration saved in /scratch/feng.yulu/dynamic-dpo-v4/outputs/llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101/config.json
|
||
2026-04-16 16:38:16 - INFO - __main__ - *** Evaluate ***
|
||
[INFO|trainer.py:4307] 2026-04-16 16:38:16,552 >>
|
||
***** Running Evaluation *****
|
||
[INFO|trainer.py:4309] 2026-04-16 16:38:16,552 >> Num examples = 895
|
||
[INFO|trainer.py:4312] 2026-04-16 16:38:16,552 >> Batch size = 8
|
||
|
||
0%| | 0/28 [00:00<?, ?it/s]
|
||
7%|▋ | 2/28 [00:00<00:02, 12.23it/s]
|
||
14%|█▍ | 4/28 [00:00<00:03, 7.54it/s]
|
||
18%|█▊ | 5/28 [00:00<00:03, 7.03it/s]
|
||
21%|██▏ | 6/28 [00:00<00:03, 6.59it/s]
|
||
25%|██▌ | 7/28 [00:01<00:03, 6.39it/s]
|
||
29%|██▊ | 8/28 [00:01<00:03, 6.23it/s]
|
||
32%|███▏ | 9/28 [00:01<00:03, 6.12it/s]
|
||
36%|███▌ | 10/28 [00:01<00:02, 6.10it/s]
|
||
39%|███▉ | 11/28 [00:01<00:02, 6.08it/s]
|
||
43%|████▎ | 12/28 [00:01<00:02, 5.99it/s]
|
||
46%|████▋ | 13/28 [00:02<00:02, 5.96it/s]
|
||
50%|█████ | 14/28 [00:02<00:02, 5.94it/s]
|
||
54%|█████▎ | 15/28 [00:02<00:02, 5.94it/s]
|
||
57%|█████▋ | 16/28 [00:02<00:02, 5.90it/s]
|
||
61%|██████ | 17/28 [00:02<00:01, 5.90it/s]
|
||
64%|██████▍ | 18/28 [00:02<00:01, 5.90it/s]
|
||
68%|██████▊ | 19/28 [00:03<00:01, 5.87it/s]
|
||
71%|███████▏ | 20/28 [00:03<00:01, 5.89it/s]
|
||
75%|███████▌ | 21/28 [00:03<00:01, 5.91it/s]
|
||
79%|███████▊ | 22/28 [00:03<00:01, 5.91it/s]
|
||
82%|████████▏ | 23/28 [00:03<00:00, 5.91it/s]
|
||
86%|████████▌ | 24/28 [00:03<00:00, 5.91it/s]
|
||
89%|████████▉ | 25/28 [00:04<00:00, 5.89it/s]
|
||
93%|█████████▎| 26/28 [00:04<00:00, 5.89it/s]
|
||
96%|█████████▋| 27/28 [00:04<00:00, 5.90it/s]
|
||
100%|██████████| 28/28 [00:04<00:00, 5.90it/s]
|
||
100%|██████████| 28/28 [00:04<00:00, 6.12it/s]
|
||
***** eval metrics *****
|
||
epoch = 0.9981
|
||
eval_loss = 1.1544
|
||
eval_runtime = 0:00:04.73
|
||
eval_samples = 2339
|
||
eval_samples_per_second = 188.882
|
||
eval_steps_per_second = 5.909
|
||
2026-04-16 16:38:21 - INFO - __main__ - *** Training complete ***
|
||
wandb: - 0.014 MB of 0.014 MB uploaded
|
||
wandb: \ 0.014 MB of 0.014 MB uploaded
|
||
wandb: | 0.014 MB of 0.014 MB uploaded
|
||
wandb: / 0.014 MB of 0.014 MB uploaded
|
||
wandb: - 0.043 MB of 0.069 MB uploaded
|
||
wandb: \ 0.070 MB of 0.070 MB uploaded
|
||
wandb:
|
||
wandb: Run history:
|
||
wandb: eval/loss █▂▁
|
||
wandb: eval/runtime █▄▁
|
||
wandb: eval/samples_per_second ▁▅█
|
||
wandb: eval/steps_per_second ▁▅█
|
||
wandb: train/epoch ▁▁▁▂▂▂▂▂▂▃▃▃▃▃▄▄▄▄▄▄▅▅▅▅▅▆▆▆▆▆▆▇▇▇▇▇████
|
||
wandb: train/global_step ▁▁▁▂▂▂▂▂▂▃▃▃▃▃▄▄▄▄▄▄▅▅▅▅▅▆▆▆▆▆▆▇▇▇▇▇████
|
||
wandb: train/grad_norm █▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
|
||
wandb: train/learning_rate ▁▂▃▅▇██████▇▇▇▇▇▆▆▆▆▅▅▅▄▄▄▃▃▃▃▂▂▂▂▁▁▁▁▁▁
|
||
wandb: train/loss ██▇▆▄▄▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁
|
||
wandb:
|
||
wandb: Run summary:
|
||
wandb: eval/loss 1.15445
|
||
wandb: eval/runtime 4.7384
|
||
wandb: eval/samples_per_second 188.882
|
||
wandb: eval/steps_per_second 5.909
|
||
wandb: total_flos 9.517157411769549e+16
|
||
wandb: train/epoch 0.99807
|
||
wandb: train/global_step 258
|
||
wandb: train/grad_norm 1.97145
|
||
wandb: train/learning_rate 0.0
|
||
wandb: train/loss 1.163
|
||
wandb: train_loss 1.5008
|
||
wandb: train_runtime 885.0234
|
||
wandb: train_samples_per_second 18.662
|
||
wandb: train_steps_per_second 0.292
|
||
wandb:
|
||
wandb: 🚀 View run llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101 at: https://wandb.ai/can-not-fand-northeastern-university/huggingface/runs/ivik22vv
|
||
wandb: ⭐️ View project at: https://wandb.ai/can-not-fand-northeastern-university/huggingface
|
||
wandb: Synced 6 W&B file(s), 0 media file(s), 2 artifact file(s) and 0 other file(s)
|
||
wandb: Find logs at: /scratch/feng.yulu/dynamic-dpo-v4/wandb/wandb/run-20260416_162228-ivik22vv/logs
|
||
wandb: WARNING The new W&B backend becomes opt-out in version 0.18.0; try it out with `wandb.require("core")`! See https://wandb.me/wandb-core for more information.
|