|
[2023-12-23 01:04:26,606] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect) |
|
/root/miniconda3/envs/textgen/lib/python3.10/site-packages/trl/trainer/ppo_config.py:141: UserWarning: The `optimize_cuda_cache` arguement will be deprecated soon, please use `optimize_device_cache` instead. |
|
warnings.warn( |
|
12/23/2023 01:04:33 - WARNING - llmtuner.model.parser - `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training. |
|
/root/miniconda3/envs/textgen/lib/python3.10/site-packages/transformers/training_args.py:1751: FutureWarning: `--push_to_hub_token` is deprecated and will be removed in version 5 of π€ Transformers. Use `--hub_token` instead. |
|
warnings.warn( |
|
12/23/2023 01:04:33 - INFO - llmtuner.model.parser - Process rank: 0, device: cuda:0, n_gpu: 1 |
|
distributed training: True, compute dtype: None |
|
12/23/2023 01:04:33 - INFO - llmtuner.model.parser - Training/evaluation parameters Seq2SeqTrainingArguments( |
|
_n_gpu=1, |
|
adafactor=False, |
|
adam_beta1=0.9, |
|
adam_beta2=0.999, |
|
adam_epsilon=1e-08, |
|
auto_find_batch_size=False, |
|
bf16=False, |
|
bf16_full_eval=False, |
|
data_seed=None, |
|
dataloader_drop_last=False, |
|
dataloader_num_workers=0, |
|
dataloader_persistent_workers=False, |
|
dataloader_pin_memory=True, |
|
ddp_backend=None, |
|
ddp_broadcast_buffers=None, |
|
ddp_bucket_cap_mb=None, |
|
ddp_find_unused_parameters=False, |
|
ddp_timeout=1800, |
|
debug=[], |
|
deepspeed=None, |
|
disable_tqdm=False, |
|
dispatch_batches=None, |
|
do_eval=False, |
|
do_predict=True, |
|
do_train=False, |
|
eval_accumulation_steps=None, |
|
eval_delay=0, |
|
eval_steps=None, |
|
evaluation_strategy=no, |
|
fp16=False, |
|
fp16_backend=auto, |
|
fp16_full_eval=False, |
|
fp16_opt_level=O1, |
|
fsdp=[], |
|
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, |
|
fsdp_min_num_params=0, |
|
fsdp_transformer_layer_cls_to_wrap=None, |
|
full_determinism=False, |
|
generation_config=None, |
|
generation_max_length=None, |
|
generation_num_beams=None, |
|
gradient_accumulation_steps=1, |
|
gradient_checkpointing=False, |
|
gradient_checkpointing_kwargs=None, |
|
greater_is_better=None, |
|
group_by_length=False, |
|
half_precision_backend=auto, |
|
hub_always_push=False, |
|
hub_model_id=None, |
|
hub_private_repo=False, |
|
hub_strategy=every_save, |
|
hub_token=<HUB_TOKEN>, |
|
ignore_data_skip=False, |
|
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=5e-05, |
|
length_column_name=length, |
|
load_best_model_at_end=False, |
|
local_rank=0, |
|
log_level=passive, |
|
log_level_replica=warning, |
|
log_on_each_node=True, |
|
logging_dir=./models/dpo/phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1-lora-2nd/Predict_20/runs/Dec23_01-04-33_autodl-container-e8c311843c-66abc214, |
|
logging_first_step=False, |
|
logging_nan_inf_filter=True, |
|
logging_steps=500, |
|
logging_strategy=steps, |
|
lr_scheduler_kwargs={}, |
|
lr_scheduler_type=linear, |
|
max_grad_norm=1.0, |
|
max_steps=-1, |
|
metric_for_best_model=None, |
|
mp_parameters=, |
|
neftune_noise_alpha=None, |
|
no_cuda=False, |
|
num_train_epochs=3.0, |
|
optim=adamw_torch, |
|
optim_args=None, |
|
output_dir=./models/dpo/phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1-lora-2nd/Predict_20, |
|
overwrite_output_dir=False, |
|
past_index=-1, |
|
per_device_eval_batch_size=1, |
|
per_device_train_batch_size=8, |
|
predict_with_generate=True, |
|
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=['tensorboard', 'wandb'], |
|
resume_from_checkpoint=None, |
|
run_name=./models/dpo/phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1-lora-2nd/Predict_20, |
|
save_on_each_node=False, |
|
save_only_model=False, |
|
save_safetensors=True, |
|
save_steps=500, |
|
save_strategy=steps, |
|
save_total_limit=None, |
|
seed=42, |
|
skip_memory_metrics=True, |
|
sortish_sampler=False, |
|
split_batches=False, |
|
tf32=None, |
|
torch_compile=False, |
|
torch_compile_backend=None, |
|
torch_compile_mode=None, |
|
torchdynamo=None, |
|
tpu_metrics_debug=False, |
|
tpu_num_cores=None, |
|
use_cpu=False, |
|
use_ipex=False, |
|
use_legacy_prediction_loop=False, |
|
use_mps_device=False, |
|
warmup_ratio=0.0, |
|
warmup_steps=0, |
|
weight_decay=0.0, |
|
) |
|
12/23/2023 01:04:33 - INFO - llmtuner.data.loader - Loading dataset alpaca_gpt4_data_en.json... |
|
[WARNING|logging.py:314] 2023-12-23 01:04:34,195 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. |
|
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|βββββ | 1/2 [00:00<00:00, 4.78it/s]
Loading checkpoint shards: 100%|ββββββββββ| 2/2 [00:00<00:00, 6.05it/s]
Loading checkpoint shards: 100%|ββββββββββ| 2/2 [00:00<00:00, 5.81it/s] |
|
12/23/2023 01:04:34 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA |
|
12/23/2023 01:04:37 - INFO - llmtuner.model.adapter - Merged 1 adapter(s). |
|
12/23/2023 01:04:37 - INFO - llmtuner.model.adapter - Loaded adapter(s): ./models/dpo/phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1-lora-2nd |
|
12/23/2023 01:04:37 - INFO - llmtuner.model.loader - trainable params: 0 || all params: 2779683840 || trainable%: 0.0000 |
|
12/23/2023 01:04:37 - INFO - llmtuner.model.loader - This IS expected that the trainable params is 0 if you are using model for inference only. |
|
12/23/2023 01:04:37 - INFO - llmtuner.data.template - Add pad token: <|endoftext|> |
|
Running tokenizer on dataset: 0%| | 0/20 [00:00<?, ? examples/s]
Running tokenizer on dataset: 100%|ββββββββββ| 20/20 [00:00<00:00, 319.59 examples/s] |
|
Detected kernel version 5.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
|
input_ids: |
|
[32, 8537, 1022, 257, 11040, 2836, 290, 281, 11666, 4430, 8796, 13, 383, 8796, 3607, 7613, 11, 6496, 11, 290, 23507, 7429, 284, 262, 2836, 338, 2683, 13, 198, 20490, 25, 13786, 1115, 9040, 329, 10589, 5448, 13, 198, 48902, 25] |
|
inputs: |
|
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. |
|
Human: Give three tips for staying healthy. |
|
Assistant: |
|
0%| | 0/20 [00:00<?, ?it/s]
10%|β | 2/20 [00:01<00:15, 1.16it/s]
15%|ββ | 3/20 [00:06<00:45, 2.70s/it]
20%|ββ | 4/20 [00:16<01:25, 5.31s/it]
25%|βββ | 5/20 [00:25<01:36, 6.46s/it]
30%|βββ | 6/20 [00:26<01:04, 4.61s/it]
35%|ββββ | 7/20 [00:29<00:55, 4.29s/it]
40%|ββββ | 8/20 [00:38<01:08, 5.74s/it]
45%|βββββ | 9/20 [00:43<00:59, 5.38s/it]
50%|βββββ | 10/20 [00:44<00:42, 4.23s/it]
55%|ββββββ | 11/20 [00:48<00:37, 4.13s/it]
60%|ββββββ | 12/20 [00:50<00:26, 3.34s/it]
65%|βββββββ | 13/20 [00:52<00:20, 2.97s/it]
70%|βββββββ | 14/20 [01:08<00:41, 6.89s/it]
75%|ββββββββ | 15/20 [01:09<00:25, 5.02s/it]
80%|ββββββββ | 16/20 [01:21<00:28, 7.22s/it]
85%|βββββββββ | 17/20 [01:26<00:19, 6.50s/it]
90%|βββββββββ | 18/20 [01:32<00:13, 6.54s/it]
95%|ββββββββββ| 19/20 [01:39<00:06, 6.54s/it]
100%|ββββββββββ| 20/20 [01:40<00:00, 5.02s/it]Building prefix dict from the default dictionary ... |
|
Loading model from cache /tmp/jieba.cache |
|
Loading model cost 0.703 seconds. |
|
Prefix dict has been built successfully. |
|
100%|ββββββββββ| 20/20 [01:42<00:00, 5.11s/it] |
|
***** predict metrics ***** |
|
predict_bleu-4 = 44.3112 |
|
predict_rouge-1 = 51.57 |
|
predict_rouge-2 = 30.4331 |
|
predict_rouge-l = 36.0243 |
|
predict_runtime = 0:01:49.52 |
|
predict_samples_per_second = 0.183 |
|
predict_steps_per_second = 0.183 |
|
12/23/2023 01:06:28 - INFO - llmtuner.train.sft.trainer - Saving prediction results to ./models/dpo/phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1-lora-2nd/Predict_20/generated_predictions.jsonl |
|
|