Training in progress, epoch 1

egy_training_log.txt

@@ -70,7 +70,7 @@ local_rank=0,
 log_level=passive,
 log_level_replica=warning,
 log_on_each_node=True,
-logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy/runs/Aug25_19-01-10_lmgpu-node-09,
+logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy/runs/Aug26_08-29-09_lmgpu-node-02,
 logging_first_step=False,
 logging_nan_inf_filter=True,
 logging_steps=500,
@@ -134,11 +134,153 @@ INFO:datasets.builder:Overwrite dataset info from restored data version if exist
 INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
 INFO:datasets.builder:Found cached dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101)
 INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
-INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-2e8b6b1ec83a74b2.arrow
-INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-81e3380949037f68.arrow
+INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-4cda59a599643701.arrow
+INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-d82ef9a45800c64f.arrow
+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.
+INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-e14de7cbddab934f.arrow
+INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-bac4c1d937397873.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.
+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_egy/runs/Aug26_08-30-54_lmgpu-node-02,
+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=3.0,
+optim=OptimizerNames.ADAMW_TORCH,
+optim_args=None,
+optim_target_modules=None,
+output_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy,
+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_egy,
+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-93ed01be52df6f6e
+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-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
+INFO:datasets.builder:Found cached dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101)
+INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
+INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-4cda59a599643701.arrow
+INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-d82ef9a45800c64f.arrow
 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.
-INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-931a5c298c87592b.arrow
-INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-5f36ba68f7702ab7.arrow
+INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-e14de7cbddab934f.arrow
+INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-bac4c1d937397873.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.
 WARNING:__main__:Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, 16-bits training: False
 INFO:__main__:Training/evaluation parameters TrainingArguments(
@@ -212,7 +354,279 @@ local_rank=0,
 log_level=passive,
 log_level_replica=warning,
 log_on_each_node=True,
-logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy/runs/Aug25_19-02-04_lmgpu-node-09,
+logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy/runs/Aug26_08-34-56_lmgpu-node-02,
+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=3.0,
+optim=OptimizerNames.ADAMW_TORCH,
+optim_args=None,
+optim_target_modules=None,
+output_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy,
+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_egy,
+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-93ed01be52df6f6e
+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-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
+INFO:datasets.builder:Found cached dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101)
+INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/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_egy/runs/Aug26_08-36-31_lmgpu-node-02,
+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=3.0,
+optim=OptimizerNames.ADAMW_TORCH,
+optim_args=None,
+optim_target_modules=None,
+output_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy,
+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_egy,
+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-93ed01be52df6f6e
+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-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
+INFO:datasets.builder:Found cached dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101)
+INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/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_egy/runs/Aug26_08-37-48_lmgpu-node-02,
 logging_first_step=False,
 logging_nan_inf_filter=True,
 logging_steps=500,
@@ -276,11 +690,11 @@ INFO:datasets.builder:Overwrite dataset info from restored data version if exist
 INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
 INFO:datasets.builder:Found cached dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101)
 INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
-INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-2e8b6b1ec83a74b2.arrow
-INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-81e3380949037f68.arrow
+INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-15c48f6e90050931.arrow
+INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-6922352c25c70c34.arrow
 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.
-INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-2e8b6b1ec83a74b2.arrow
-INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-81e3380949037f68.arrow
+INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-4bc8134882fda7ba.arrow
+INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-42e32fa86dce08b8.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.
 WARNING:__main__:Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, 16-bits training: False
 INFO:__main__:Training/evaluation parameters TrainingArguments(
@@ -354,7 +768,143 @@ local_rank=0,
 log_level=passive,
 log_level_replica=warning,
 log_on_each_node=True,
-logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy/runs/Aug25_19-04-25_lmgpu-node-09,
+logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy/runs/Aug26_08-45-12_lmgpu-node-02,
+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=3.0,
+optim=OptimizerNames.ADAMW_TORCH,
+optim_args=None,
+optim_target_modules=None,
+output_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy,
+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_egy,
+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-93ed01be52df6f6e
+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-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
+INFO:datasets.builder:Found cached dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101)
+INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/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_egy/runs/Aug26_08-49-29_lmgpu-node-02,
 logging_first_step=False,
 logging_nan_inf_filter=True,
 logging_steps=500,
@@ -490,7 +1040,7 @@ local_rank=0,
 log_level=passive,
 log_level_replica=warning,
 log_on_each_node=True,
-logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy/runs/Aug25_19-05-20_lmgpu-node-09,
+logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy/runs/Aug26_08-54-02_lmgpu-node-02,
 logging_first_step=False,
 logging_nan_inf_filter=True,
 logging_steps=500,
@@ -626,7 +1176,7 @@ local_rank=0,
 log_level=passive,
 log_level_replica=warning,
 log_on_each_node=True,
-logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy/runs/Aug25_19-06-09_lmgpu-node-09,
+logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy/runs/Aug26_08-55-36_lmgpu-node-02,
 logging_first_step=False,
 logging_nan_inf_filter=True,
 logging_steps=500,
@@ -690,11 +1240,11 @@ INFO:datasets.builder:Overwrite dataset info from restored data version if exist
 INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
 INFO:datasets.builder:Found cached dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101)
 INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
-INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-ffc142ffcddbe7b3.arrow
-INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-1a35f1b6580983eb.arrow
+INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-1618ed1dbdc1fac3.arrow
+INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-4dd41ff5ffd8ebb9.arrow
 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.
-INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-a683048173790563.arrow
-INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-1a35f1b6580983eb.arrow
+INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-968ccd46e919b580.arrow
+INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-fc6af2bb14f3f4a5.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.
 WARNING:__main__:Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, 16-bits training: False
 INFO:__main__:Training/evaluation parameters TrainingArguments(
@@ -768,7 +1318,7 @@ local_rank=0,
 log_level=passive,
 log_level_replica=warning,
 log_on_each_node=True,
-logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy/runs/Aug25_21-19-07_lmgpu-node-06,
+logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_egy/runs/Aug26_09-01-10_lmgpu-node-02,
 logging_first_step=False,
 logging_nan_inf_filter=True,
 logging_steps=500,
@@ -832,17 +1382,11 @@ INFO:datasets.builder:Overwrite dataset info from restored data version if exist
 INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
 INFO:datasets.builder:Found cached dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101)
 INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
-INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-4cda59a599643701.arrow
-INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-d82ef9a45800c64f.arrow
+INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-8ff24a6e5f07e751.arrow
+INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-24c3792376099a13.arrow
 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.
-INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-038f8e8385bf6638.arrow
-INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-51f1e2b6546273ed.arrow
+INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-7eeb52512f3f992e.arrow
+INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-93ed01be52df6f6e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-c6b81df4fac91850.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 = 4.0723, Eval Loss = 2.958087921142578
-INFO:absl:Using default tokenizer.
-INFO:root:Epoch 3.0: Train Loss = 2.8055, Eval Loss = 2.606330394744873
-INFO:absl:Using default tokenizer.
-INFO:__main__:*** Evaluate ***
-INFO:absl:Using default tokenizer.

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e0e5f1169bcbd77625282e5c08ab19b475c7735aaf2f2cc78a0878271a1a2a2
+oid sha256:3bc793473cba110a469709dabdfd86c02a23876b3cec7ad4127b45d7df83c22f
 size 539221632

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 128
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 64000,
+    "pad_type_id": 0,
+    "pad_token": "<EOS>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dd387c20f29a9602c739eddd06e5cc1283cac4ac8c19e05cd6e5a99446c6a7e
+oid sha256:5f45e298f33c57c9b0a30141fc68a3f3abb5e9893518b28a61febed9782ea88e
 size 5240