Confusing Error Message (i think). #290
Comments
|
Idk what happened to the formatting... |
|
Can you check all your prompts have non-empty output? I recall this |
|
@NanoCode012 One of them I think is empty. Is there a way to just drop columns with empty things? |
|
@ashercn97 , unfortunately not with axolotl, I think you can simply load into pandas and drop it. |
|
@NanoCode012 Okay. I will try to do that now. Thanks so much! |
|
MY thing is fixed! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I am getting thsi error:
2023-07-18 01:04:39,361] [WARNING] [axolotl.validate_config:16] [PID:640] batch_size is not recommended. Please use gradient_accumulation_steps instead.
To calculate the equivalent gradient_accumulation_steps, divide batch_size / micro_batch_size / number of gpus.
[2023-07-18 01:04:39,362] [INFO] [axolotl.scripts.train:219] [PID:640] loading tokenizer... openlm-research/open_llama_3b
You are using the legacy behaviour of the <class 'transformers.models.llama.tokenization_llama.LlamaTokenizer'>. This means that tokens that come after special tokens will not be properly handled. We recommend you to read the related pull request available at huggingface/transformers#24565
[2023-07-18 01:04:39,438] [DEBUG] [axolotl.load_tokenizer:55] [PID:640] EOS: 2 /
[2023-07-18 01:04:39,438] [DEBUG] [axolotl.load_tokenizer:56] [PID:640] BOS: 1 /
[2023-07-18 01:04:39,438] [DEBUG] [axolotl.load_tokenizer:57] [PID:640] PAD: None / None
[2023-07-18 01:04:39,438] [DEBUG] [axolotl.load_tokenizer:58] [PID:640] UNK: 0 /
[2023-07-18 01:04:39,438] [INFO] [axolotl.load_tokenized_prepared_datasets:82] [PID:640] Unable to find prepared dataset in last_run_prepared/ba96bd8ae0099721227d1c8a23d6d7a4
[2023-07-18 01:04:39,438] [INFO] [axolotl.load_tokenized_prepared_datasets:83] [PID:640] Loading raw datasets...
[2023-07-18 01:04:39,438] [INFO] [axolotl.load_tokenized_prepared_datasets:88] [PID:640] No seed provided, using default seed of 42
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 320.57it/s]
[2023-07-18 01:04:39,971] [INFO] [axolotl.load_tokenized_prepared_datasets:264] [PID:640] tokenizing, merging, and shuffling master dataset
Traceback (most recent call last):
File "/home/studio-lab-user/axolotl/scripts/finetune.py", line 356, in
fire.Fire(train)
File "/home/studio-lab-user/.conda/envs/python39/lib/python3.9/site-packages/fire/core.py", line 141, in Fire
component_trace = _Fire(component, args, parsed_flag_args, context, name)
File "/home/studio-lab-user/.conda/envs/python39/lib/python3.9/site-packages/fire/core.py", line 475, in _Fire
component, remaining_args = _CallAndUpdateTrace(
File "/home/studio-lab-user/.conda/envs/python39/lib/python3.9/site-packages/fire/core.py", line 691, in _CallAndUpdateTrace
component = fn(*varargs, **kwargs)
File "/home/studio-lab-user/axolotl/scripts/finetune.py", line 226, in train
train_dataset, eval_dataset = load_prepare_datasets(
File "/home/studio-lab-user/axolotl/src/axolotl/utils/data.py", line 393, in load_prepare_datasets
dataset = load_tokenized_prepared_datasets(
File "/home/studio-lab-user/axolotl/src/axolotl/utils/data.py", line 268, in load_tokenized_prepared_datasets
samples = samples + list(d)
File "/home/studio-lab-user/axolotl/src/axolotl/datasets.py", line 42, in iter
yield self.prompt_tokenizer.tokenize_prompt(example)
File "/home/studio-lab-user/axolotl/src/axolotl/prompt_tokenizers.py", line 116, in tokenize_prompt
tokenized_res_prompt = self._tokenize(
File "/home/studio-lab-user/axolotl/src/axolotl/prompt_tokenizers.py", line 64, in _tokenize
result = self.tokenizer(
File "/home/studio-lab-user/.conda/envs/python39/lib/python3.9/site-packages/transformers/tokenization_utils_base.py", line 2571, in call
raise ValueError("You need to specify either
textortext_target.")ValueError: You need to specify either
textortext_target.Traceback (most recent call last):
File "/home/studio-lab-user/.conda/envs/python39/bin/accelerate", line 8, in
sys.exit(main())
File "/home/studio-lab-user/.conda/envs/python39/lib/python3.9/site-packages/accelerate/commands/accelerate_cli.py", line 45, in main
args.func(args)
File "/home/studio-lab-user/.conda/envs/python39/lib/python3.9/site-packages/accelerate/commands/launch.py", line 979, in launch_command
simple_launcher(args)
File "/home/studio-lab-user/.conda/envs/python39/lib/python3.9/site-packages/accelerate/commands/launch.py", line 628, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['/home/studio-lab-user/.conda/envs/python39/bin/python3.9', 'scripts/finetune.py', 'config/OpenOrcaTest.yml']' returned non-zero exit status 1.
My config settings are:
`
base_model: openlm-research/open_llama_3b
base_model_config: openlm-research/open_llama_3b
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
load_in_8bit: true
load_in_4bit: false
strict: false
push_dataset_to_hub:
datasets:
type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.02
adapter: lora
lora_model_dir:
sequence_len: 256
max_packed_sequence_len:
lora_r: 8
lora_alpha: 16
lora_dropout: 0.0
lora_target_modules:
lora_fan_in_fan_out:
wandb_project:
wandb_watch:
wandb_run_id:
wandb_log_model:
output_dir: ./openorca-out
batch_size: 16
micro_batch_size: 4
num_epochs: 3
optimizer: adamw_bnb_8bit
torchdistx_path:
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: false
fp16: true
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention: true
flash_attention:
gptq_groupsize:
gptq_model_v1:
warmup_steps: 10
eval_steps: 50
save_steps:
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: "
""eos_token: "
unk_token: ""
'
The text was updated successfully, but these errors were encountered: