enzoampil / tito-joker Goto Github PK

!python3 /Users/andrew/Downloads/tito-joker-master/experiments/transformers/examples/legacy/run_language_modeling.py \
--overwrite_output_dir \
--output_dir='./models/finetuned' \
--model_type=gpt2\
--model_name_or_path=gpt2\
--tokenizer_name="./models/pretrained" \
--do_train\
--train_data_file="./data/riddle_jokes.txt" \
--per_gpu_train_batch_size=4 \
--block_size=50 


09/07/2022 15:55:11 - WARNING - __main__ - Process rank: -1, device: cpu, n_gpu: 0, distributed training: False, 16-bits training: False
09/07/2022 15:55:11 - INFO - __main__ - Training/evaluation parameters TrainingArguments(
_n_gpu=0,
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
bf16=False,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_pin_memory=True,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=None,
debug=[],
deepspeed=None,
disable_tqdm=False,
do_eval=False,
do_predict=False,
do_train=True,
eval_accumulation_steps=None,
eval_delay=0,
eval_steps=None,
evaluation_strategy=IntervalStrategy.NO,
fp16=False,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
gradient_accumulation_steps=1,
gradient_checkpointing=False,
greater_is_better=None,
group_by_length=False,
half_precision_backend=auto,
hub_model_id=None,
hub_strategy=HubStrategy.EVERY_SAVE,
hub_token=<HUB_TOKEN>,
ignore_data_skip=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=-1,
log_level=-1,
log_level_replica=-1,
log_on_each_node=True,
logging_dir=./models/finetuned/runs/Sep07_15-55-11_voyager-528.local,
logging_first_step=False,
logging_nan_inf_filter=True,
logging_steps=500,
logging_strategy=IntervalStrategy.STEPS,
lr_scheduler_type=SchedulerType.LINEAR,
max_grad_norm=1.0,
max_steps=-1,
metric_for_best_model=None,
mp_parameters=,
no_cuda=False,
num_train_epochs=3.0,
optim=OptimizerNames.ADAMW_HF,
output_dir=./models/finetuned,
overwrite_output_dir=True,
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>,
remove_unused_columns=True,
report_to=[],
resume_from_checkpoint=None,
run_name=./models/finetuned,
save_on_each_node=False,
save_steps=500,
save_strategy=IntervalStrategy.STEPS,
save_total_limit=None,
seed=42,
sharded_ddp=[],
skip_memory_metrics=True,
tf32=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_legacy_prediction_loop=False,
warmup_ratio=0.0,
warmup_steps=0,
weight_decay=0.0,
xpu_backend=None,
)
[INFO|configuration_utils.py:654] 2022-09-07 15:55:12,110 >> loading configuration file https://huggingface.co/gpt2/resolve/main/config.json from cache at /Users/andrew/.cache/huggingface/transformers/fc674cd6907b4c9e933cb42d67662436b89fa9540a1f40d7c919d0109289ad01.7d2e0efa5ca20cef4fb199382111e9d3ad96fd77b849e1d4bed13a66e1336f51
[INFO|configuration_utils.py:690] 2022-09-07 15:55:12,114 >> Model config GPT2Config {
  "_name_or_path": "gpt2",
  "activation_function": "gelu_new",
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "attn_pdrop": 0.1,
  "bos_token_id": 50256,
  "embd_pdrop": 0.1,
  "eos_token_id": 50256,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "gpt2",
  "n_ctx": 1024,
  "n_embd": 768,
  "n_head": 12,
  "n_inner": null,
  "n_layer": 12,
  "n_positions": 1024,
  "reorder_and_upcast_attn": false,
  "resid_pdrop": 0.1,
  "scale_attn_by_inverse_layer_idx": false,
  "scale_attn_weights": true,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "task_specific_params": {
    "text-generation": {
      "do_sample": true,
      "max_length": 50
    }
  },
  "transformers_version": "4.18.0",
  "use_cache": true,
  "vocab_size": 50257
}

Traceback (most recent call last):
  File "/Users/andrew/Downloads/tito-joker-master/experiments/transformers/examples/legacy/run_language_modeling.py", line 375, in <module>
    main()
  File "/Users/andrew/Downloads/tito-joker-master/experiments/transformers/examples/legacy/run_language_modeling.py", line 262, in main
    tokenizer = AutoTokenizer.from_pretrained(model_args.tokenizer_name, cache_dir=model_args.cache_dir)
  File "/Users/andrew/Library/Python/3.6/lib/python/site-packages/transformers/models/auto/tokenization_auto.py", line 471, in from_pretrained
    tokenizer_config = get_tokenizer_config(pretrained_model_name_or_path, **kwargs)
  File "/Users/andrew/Library/Python/3.6/lib/python/site-packages/transformers/models/auto/tokenization_auto.py", line 341, in get_tokenizer_config
    local_files_only=local_files_only,
  File "/Users/andrew/Library/Python/3.6/lib/python/site-packages/transformers/utils/hub.py", line 685, in get_file_from_repo
    use_auth_token=use_auth_token,
  File "/Users/andrew/Library/Python/3.6/lib/python/site-packages/transformers/utils/hub.py", line 290, in cached_path
    local_files_only=local_files_only,
  File "/Users/andrew/Library/Python/3.6/lib/python/site-packages/transformers/utils/hub.py", line 546, in get_from_cache
    "Connection error, and we cannot find the requested files in the cached path."
ValueError: Connection error, and we cannot find the requested files in the cached path. Please try again or make sure your Internet connection is on.

Input: Why did the chicken cross the road?
Output: Why did the chicken cross the road ? To go to wor

embedding_vector = [0.1, 0.2, 0.3]
sentiment_score = [0.8]
model_inpute = embedding_vector + sentiment_score = [0.1, 0.2, 0.3, 0.8]

raw_input = "Why did the chicken cross the road?"
processed_input = "<sad> Why did the chicken cross the road?"

raw_input = "My dog died today and I am very sad"
output = "My dog died today and <sad> I am very sad </sad>"