| WARNING:__main__:Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, 16-bits training: False | |
| INFO:__main__:Training/evaluation parameters TrainingArguments( | |
| _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, | |
| batch_eval_metrics=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, | |
| dataloader_prefetch_factor=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, | |
| dispatch_batches=None, | |
| do_eval=True, | |
| do_predict=False, | |
| do_train=True, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_do_concat_batches=True, | |
| eval_on_start=False, | |
| eval_steps=None, | |
| eval_strategy=IntervalStrategy.EPOCH, | |
| eval_use_gather_object=False, | |
| evaluation_strategy=epoch, | |
| 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=1, | |
| gradient_checkpointing=False, | |
| gradient_checkpointing_kwargs=None, | |
| greater_is_better=False, | |
| group_by_length=False, | |
| half_precision_backend=auto, | |
| hub_always_push=False, | |
| hub_model_id=None, | |
| hub_private_repo=False, | |
| hub_strategy=HubStrategy.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=True, | |
| local_rank=0, | |
| log_level=passive, | |
| log_level_replica=warning, | |
| log_on_each_node=True, | |
| logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_yem_aragpt2-base/runs/Sep07_09-00-55_lmgpu-node-07, | |
| logging_first_step=False, | |
| logging_nan_inf_filter=True, | |
| logging_steps=500, | |
| logging_strategy=IntervalStrategy.EPOCH, | |
| lr_scheduler_kwargs={}, | |
| lr_scheduler_type=SchedulerType.LINEAR, | |
| max_grad_norm=1.0, | |
| max_steps=-1, | |
| metric_for_best_model=loss, | |
| mp_parameters=, | |
| neftune_noise_alpha=None, | |
| no_cuda=False, | |
| num_train_epochs=20.0, | |
| optim=OptimizerNames.ADAMW_TORCH, | |
| optim_args=None, | |
| optim_target_modules=None, | |
| output_dir=/home/iais_marenpielka/Bouthaina/res_nw_yem_aragpt2-base, | |
| overwrite_output_dir=False, | |
| past_index=-1, | |
| per_device_eval_batch_size=8, | |
| per_device_train_batch_size=8, | |
| prediction_loss_only=False, | |
| push_to_hub=True, | |
| 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=[], | |
| restore_callback_states_from_checkpoint=False, | |
| resume_from_checkpoint=None, | |
| run_name=/home/iais_marenpielka/Bouthaina/res_nw_yem_aragpt2-base, | |
| save_on_each_node=False, | |
| save_only_model=False, | |
| save_safetensors=True, | |
| save_steps=500, | |
| save_strategy=IntervalStrategy.EPOCH, | |
| save_total_limit=None, | |
| seed=42, | |
| skip_memory_metrics=True, | |
| split_batches=None, | |
| tf32=None, | |
| torch_compile=False, | |
| torch_compile_backend=None, | |
| torch_compile_mode=None, | |
| torch_empty_cache_steps=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=500, | |
| weight_decay=0.0, | |
| ) | |
| INFO:datasets.builder:Using custom data configuration default-7d1e1bd6ffb527f0 | |
| INFO:datasets.info:Loading Dataset Infos from /home/iais_marenpielka/Bouthaina/miniconda3/lib/python3.12/site-packages/datasets/packaged_modules/text | |
| INFO:datasets.builder:Overwrite dataset info from restored data version if exists. | |
| INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-7d1e1bd6ffb527f0/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101 | |
| INFO:datasets.builder:Found cached dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-7d1e1bd6ffb527f0/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101) | |
| INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-7d1e1bd6ffb527f0/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101 | |
| WARNING:__main__:Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, 16-bits training: False | |
| INFO:__main__:Training/evaluation parameters TrainingArguments( | |
| _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, | |
| batch_eval_metrics=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, | |
| dataloader_prefetch_factor=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, | |
| dispatch_batches=None, | |
| do_eval=True, | |
| do_predict=False, | |
| do_train=True, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_do_concat_batches=True, | |
| eval_on_start=False, | |
| eval_steps=None, | |
| eval_strategy=IntervalStrategy.EPOCH, | |
| eval_use_gather_object=False, | |
| evaluation_strategy=epoch, | |
| 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=1, | |
| gradient_checkpointing=False, | |
| gradient_checkpointing_kwargs=None, | |
| greater_is_better=False, | |
| group_by_length=False, | |
| half_precision_backend=auto, | |
| hub_always_push=False, | |
| hub_model_id=None, | |
| hub_private_repo=False, | |
| hub_strategy=HubStrategy.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=True, | |
| local_rank=0, | |
| log_level=passive, | |
| log_level_replica=warning, | |
| log_on_each_node=True, | |
| logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_yem_aragpt2-base/runs/Sep07_21-03-25_lmgpu-node-07, | |
| logging_first_step=False, | |
| logging_nan_inf_filter=True, | |
| logging_steps=500, | |
| logging_strategy=IntervalStrategy.EPOCH, | |
| lr_scheduler_kwargs={}, | |
| lr_scheduler_type=SchedulerType.LINEAR, | |
| max_grad_norm=1.0, | |
| max_steps=-1, | |
| metric_for_best_model=loss, | |
| mp_parameters=, | |
| neftune_noise_alpha=None, | |
| no_cuda=False, | |
| num_train_epochs=20.0, | |
| optim=OptimizerNames.ADAMW_TORCH, | |
| optim_args=None, | |
| optim_target_modules=None, | |
| output_dir=/home/iais_marenpielka/Bouthaina/res_nw_yem_aragpt2-base, | |
| overwrite_output_dir=False, | |
| past_index=-1, | |
| per_device_eval_batch_size=8, | |
| per_device_train_batch_size=8, | |
| prediction_loss_only=False, | |
| push_to_hub=True, | |
| 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=[], | |
| restore_callback_states_from_checkpoint=False, | |
| resume_from_checkpoint=None, | |
| run_name=/home/iais_marenpielka/Bouthaina/res_nw_yem_aragpt2-base, | |
| save_on_each_node=False, | |
| save_only_model=False, | |
| save_safetensors=True, | |
| save_steps=500, | |
| save_strategy=IntervalStrategy.EPOCH, | |
| save_total_limit=None, | |
| seed=42, | |
| skip_memory_metrics=True, | |
| split_batches=None, | |
| tf32=None, | |
| torch_compile=False, | |
| torch_compile_backend=None, | |
| torch_compile_mode=None, | |
| torch_empty_cache_steps=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=500, | |
| weight_decay=0.0, | |
| ) | |
| INFO:datasets.builder:Using custom data configuration default-7d1e1bd6ffb527f0 | |
| INFO:datasets.info:Loading Dataset Infos from /home/iais_marenpielka/Bouthaina/miniconda3/lib/python3.12/site-packages/datasets/packaged_modules/text | |
| INFO:datasets.builder:Overwrite dataset info from restored data version if exists. | |
| INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-7d1e1bd6ffb527f0/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101 | |
| INFO:datasets.builder:Found cached dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-7d1e1bd6ffb527f0/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101) | |
| INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-7d1e1bd6ffb527f0/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101 | |
| INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-7d1e1bd6ffb527f0/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-a27d6b05e7aac9fa.arrow | |
| INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-7d1e1bd6ffb527f0/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-3d57f3aaa6815ded.arrow | |
| WARNING:__main__:The tokenizer picked seems to have a very large `model_max_length` (1000000000000000019884624838656). Using block_size=1024 instead. You can change that default value by passing --block_size xxx. | |
| INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-7d1e1bd6ffb527f0/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-ec1d8f12ea0419b8.arrow | |
| INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-7d1e1bd6ffb527f0/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-a45fe2c42de400e2.arrow | |
| 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. | |
| INFO:root:Epoch 1.0: Train Loss = None, Eval Loss = None | |
| INFO:absl:Using default tokenizer. | |
| INFO:root:Epoch 2.0: Train Loss = 5.8224, Eval Loss = 0.1128806546330452 | |
| INFO:absl:Using default tokenizer. | |
| INFO:root:Epoch 3.0: Train Loss = 0.1108, Eval Loss = 0.06912114471197128 | |
| INFO:absl:Using default tokenizer. | |
| INFO:root:Epoch 4.0: Train Loss = 0.0775, Eval Loss = 0.06276746839284897 | |
| INFO:absl:Using default tokenizer. | |
| INFO:root:Epoch 5.0: Train Loss = 0.0678, Eval Loss = 0.059174273163080215 | |
| INFO:absl:Using default tokenizer. | |
| INFO:root:Epoch 6.0: Train Loss = 0.0603, Eval Loss = 0.05656920000910759 | |
| INFO:absl:Using default tokenizer. | |
| INFO:root:Epoch 7.0: Train Loss = 0.0547, Eval Loss = 0.05464606359601021 | |
| INFO:absl:Using default tokenizer. | |
| INFO:root:Epoch 8.0: Train Loss = 0.0498, Eval Loss = 0.054019927978515625 | |
| INFO:absl:Using default tokenizer. | |
| INFO:root:Epoch 9.0: Train Loss = 0.0456, Eval Loss = 0.053611643612384796 | |
| INFO:absl:Using default tokenizer. | |
| INFO:root:Epoch 10.0: Train Loss = 0.0419, Eval Loss = 0.05337703973054886 | |
| INFO:absl:Using default tokenizer. | |
| INFO:root:Epoch 11.0: Train Loss = 0.0385, Eval Loss = 0.05344715714454651 | |
| INFO:absl:Using default tokenizer. | |
| INFO:root:Epoch 12.0: Train Loss = 0.0354, Eval Loss = 0.05403715744614601 | |
| INFO:absl:Using default tokenizer. | |
| INFO:root:Epoch 13.0: Train Loss = 0.0331, Eval Loss = 0.05399588495492935 | |
| INFO:absl:Using default tokenizer. | |
| INFO:root:Epoch 14.0: Train Loss = 0.0308, Eval Loss = 0.05515788868069649 | |
| INFO:absl:Using default tokenizer. | |
| INFO:__main__:*** Evaluate *** | |
| INFO:absl:Using default tokenizer. | |