Training in progress, step 500
Browse files- egy_training_log.txt +144 -0
- model.safetensors +1 -1
- training_args.bin +1 -1
egy_training_log.txt
CHANGED
|
@@ -290,3 +290,147 @@ WARNING:accelerate.utils.other:Detected kernel version 5.4.0, which is below the
|
|
| 290 |
INFO:__main__:*** Evaluate ***
|
| 291 |
INFO:absl:Using default tokenizer.
|
| 292 |
WARNING:root:No losses were recorded, so the loss graph was not generated.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 290 |
INFO:__main__:*** Evaluate ***
|
| 291 |
INFO:absl:Using default tokenizer.
|
| 292 |
WARNING:root:No losses were recorded, so the loss graph was not generated.
|
| 293 |
+
WARNING:__main__:Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, 16-bits training: False
|
| 294 |
+
INFO:__main__:Training/evaluation parameters TrainingArguments(
|
| 295 |
+
_n_gpu=1,
|
| 296 |
+
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},
|
| 297 |
+
adafactor=False,
|
| 298 |
+
adam_beta1=0.9,
|
| 299 |
+
adam_beta2=0.999,
|
| 300 |
+
adam_epsilon=1e-08,
|
| 301 |
+
auto_find_batch_size=False,
|
| 302 |
+
batch_eval_metrics=False,
|
| 303 |
+
bf16=False,
|
| 304 |
+
bf16_full_eval=False,
|
| 305 |
+
data_seed=None,
|
| 306 |
+
dataloader_drop_last=False,
|
| 307 |
+
dataloader_num_workers=0,
|
| 308 |
+
dataloader_persistent_workers=False,
|
| 309 |
+
dataloader_pin_memory=True,
|
| 310 |
+
dataloader_prefetch_factor=None,
|
| 311 |
+
ddp_backend=None,
|
| 312 |
+
ddp_broadcast_buffers=None,
|
| 313 |
+
ddp_bucket_cap_mb=None,
|
| 314 |
+
ddp_find_unused_parameters=None,
|
| 315 |
+
ddp_timeout=1800,
|
| 316 |
+
debug=[],
|
| 317 |
+
deepspeed=None,
|
| 318 |
+
disable_tqdm=False,
|
| 319 |
+
dispatch_batches=None,
|
| 320 |
+
do_eval=True,
|
| 321 |
+
do_predict=False,
|
| 322 |
+
do_train=True,
|
| 323 |
+
eval_accumulation_steps=None,
|
| 324 |
+
eval_delay=0,
|
| 325 |
+
eval_do_concat_batches=True,
|
| 326 |
+
eval_on_start=False,
|
| 327 |
+
eval_steps=500,
|
| 328 |
+
eval_strategy=IntervalStrategy.STEPS,
|
| 329 |
+
eval_use_gather_object=False,
|
| 330 |
+
evaluation_strategy=steps,
|
| 331 |
+
fp16=False,
|
| 332 |
+
fp16_backend=auto,
|
| 333 |
+
fp16_full_eval=False,
|
| 334 |
+
fp16_opt_level=O1,
|
| 335 |
+
fsdp=[],
|
| 336 |
+
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
|
| 337 |
+
fsdp_min_num_params=0,
|
| 338 |
+
fsdp_transformer_layer_cls_to_wrap=None,
|
| 339 |
+
full_determinism=False,
|
| 340 |
+
gradient_accumulation_steps=1,
|
| 341 |
+
gradient_checkpointing=False,
|
| 342 |
+
gradient_checkpointing_kwargs=None,
|
| 343 |
+
greater_is_better=False,
|
| 344 |
+
group_by_length=False,
|
| 345 |
+
half_precision_backend=auto,
|
| 346 |
+
hub_always_push=False,
|
| 347 |
+
hub_model_id=None,
|
| 348 |
+
hub_private_repo=False,
|
| 349 |
+
hub_strategy=HubStrategy.EVERY_SAVE,
|
| 350 |
+
hub_token=<HUB_TOKEN>,
|
| 351 |
+
ignore_data_skip=False,
|
| 352 |
+
include_inputs_for_metrics=False,
|
| 353 |
+
include_num_input_tokens_seen=False,
|
| 354 |
+
include_tokens_per_second=False,
|
| 355 |
+
jit_mode_eval=False,
|
| 356 |
+
label_names=None,
|
| 357 |
+
label_smoothing_factor=0.0,
|
| 358 |
+
learning_rate=5e-05,
|
| 359 |
+
length_column_name=length,
|
| 360 |
+
load_best_model_at_end=True,
|
| 361 |
+
local_rank=0,
|
| 362 |
+
log_level=passive,
|
| 363 |
+
log_level_replica=warning,
|
| 364 |
+
log_on_each_node=True,
|
| 365 |
+
logging_dir=/home/iais_marenpielka/Bouthaina/results/runs/Aug25_12-13-00_lmgpu-node-09,
|
| 366 |
+
logging_first_step=False,
|
| 367 |
+
logging_nan_inf_filter=True,
|
| 368 |
+
logging_steps=500,
|
| 369 |
+
logging_strategy=IntervalStrategy.STEPS,
|
| 370 |
+
lr_scheduler_kwargs={},
|
| 371 |
+
lr_scheduler_type=SchedulerType.LINEAR,
|
| 372 |
+
max_grad_norm=1.0,
|
| 373 |
+
max_steps=-1,
|
| 374 |
+
metric_for_best_model=loss,
|
| 375 |
+
mp_parameters=,
|
| 376 |
+
neftune_noise_alpha=None,
|
| 377 |
+
no_cuda=False,
|
| 378 |
+
num_train_epochs=5.0,
|
| 379 |
+
optim=OptimizerNames.ADAMW_TORCH,
|
| 380 |
+
optim_args=None,
|
| 381 |
+
optim_target_modules=None,
|
| 382 |
+
output_dir=/home/iais_marenpielka/Bouthaina/results,
|
| 383 |
+
overwrite_output_dir=False,
|
| 384 |
+
past_index=-1,
|
| 385 |
+
per_device_eval_batch_size=8,
|
| 386 |
+
per_device_train_batch_size=8,
|
| 387 |
+
prediction_loss_only=False,
|
| 388 |
+
push_to_hub=True,
|
| 389 |
+
push_to_hub_model_id=None,
|
| 390 |
+
push_to_hub_organization=None,
|
| 391 |
+
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
|
| 392 |
+
ray_scope=last,
|
| 393 |
+
remove_unused_columns=True,
|
| 394 |
+
report_to=[],
|
| 395 |
+
restore_callback_states_from_checkpoint=False,
|
| 396 |
+
resume_from_checkpoint=None,
|
| 397 |
+
run_name=/home/iais_marenpielka/Bouthaina/results,
|
| 398 |
+
save_on_each_node=False,
|
| 399 |
+
save_only_model=False,
|
| 400 |
+
save_safetensors=True,
|
| 401 |
+
save_steps=500,
|
| 402 |
+
save_strategy=IntervalStrategy.STEPS,
|
| 403 |
+
save_total_limit=None,
|
| 404 |
+
seed=42,
|
| 405 |
+
skip_memory_metrics=True,
|
| 406 |
+
split_batches=None,
|
| 407 |
+
tf32=None,
|
| 408 |
+
torch_compile=False,
|
| 409 |
+
torch_compile_backend=None,
|
| 410 |
+
torch_compile_mode=None,
|
| 411 |
+
torch_empty_cache_steps=None,
|
| 412 |
+
torchdynamo=None,
|
| 413 |
+
tpu_metrics_debug=False,
|
| 414 |
+
tpu_num_cores=None,
|
| 415 |
+
use_cpu=False,
|
| 416 |
+
use_ipex=False,
|
| 417 |
+
use_legacy_prediction_loop=False,
|
| 418 |
+
use_mps_device=False,
|
| 419 |
+
warmup_ratio=0.0,
|
| 420 |
+
warmup_steps=500,
|
| 421 |
+
weight_decay=0.0,
|
| 422 |
+
)
|
| 423 |
+
INFO:__main__:Checkpoint detected, resuming training at /home/iais_marenpielka/Bouthaina/results/checkpoint-319. To avoid this behavior, change the `--output_dir` or add `--overwrite_output_dir` to train from scratch.
|
| 424 |
+
INFO:datasets.builder:Using custom data configuration default-0637777c38512acf
|
| 425 |
+
INFO:datasets.info:Loading Dataset Infos from /home/iais_marenpielka/Bouthaina/miniconda3/lib/python3.12/site-packages/datasets/packaged_modules/text
|
| 426 |
+
INFO:datasets.builder:Overwrite dataset info from restored data version if exists.
|
| 427 |
+
INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-0637777c38512acf/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
|
| 428 |
+
INFO:datasets.builder:Found cached dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-0637777c38512acf/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101)
|
| 429 |
+
INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-0637777c38512acf/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
|
| 430 |
+
INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-0637777c38512acf/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-37ea47da1c3ae86a.arrow
|
| 431 |
+
INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-0637777c38512acf/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-d1d890b04a73f183.arrow
|
| 432 |
+
WARNING:__main__:The tokenizer picked seems to have a very large `model_max_length` (1000000000000000019884624838656). Using block_size=768 instead. You can change that default value by passing --block_size xxx.
|
| 433 |
+
INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-0637777c38512acf/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-607ae57e4b4160b3.arrow
|
| 434 |
+
INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-0637777c38512acf/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-4ddbb6e08bb37d3f.arrow
|
| 435 |
+
WARNING:accelerate.utils.other: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.
|
| 436 |
+
INFO:absl:Using default tokenizer.
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 539218560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb08dc5a82c4a5b849cec59a04b33b1e0ae635d1ed1c8afa9c12abf53999c3c0
|
| 3 |
size 539218560
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2031df67d3f7c6b87317a09678a7218f25c1c8016608a67706479562146840ba
|
| 3 |
size 5240
|