Training in progress, epoch 8

egy_training_log.txt

@@ -570,3 +570,291 @@ INFO:root:Epoch 7.0: Train Loss = 0.0164, Eval Loss = 0.05724157765507698
 INFO:absl:Using default tokenizer.
 INFO:__main__:*** Evaluate ***
 INFO:absl:Using default tokenizer.
+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_gulf_aragpt2-large/runs/Sep08_18-44-04_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_gulf_aragpt2-large,
+overwrite_output_dir=False,
+past_index=-1,
+per_device_eval_batch_size=4,
+per_device_train_batch_size=4,
+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_gulf_aragpt2-large,
+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:__main__:Checkpoint detected, resuming training at /home/iais_marenpielka/Bouthaina/res_nw_gulf_aragpt2-large/checkpoint-11704. To avoid this behavior, change the `--output_dir` or add `--overwrite_output_dir` to train from scratch.
+INFO:datasets.builder:Using custom data configuration default-481a1a6a0ca4575e
+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-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
+INFO:datasets.builder:Found cached dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101)
+INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
+INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-798e68ee1238406a.arrow
+INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-08141c170f1669b9.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:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-2ba0b834485aeaf5.arrow
+INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-7a0a05502f2d2ac6.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_gulf_aragpt2-large/runs/Sep08_18-48-04_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_gulf_aragpt2-large,
+overwrite_output_dir=False,
+past_index=-1,
+per_device_eval_batch_size=4,
+per_device_train_batch_size=4,
+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_gulf_aragpt2-large,
+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:__main__:Checkpoint detected, resuming training at /home/iais_marenpielka/Bouthaina/res_nw_gulf_aragpt2-large/checkpoint-11704. To avoid this behavior, change the `--output_dir` or add `--overwrite_output_dir` to train from scratch.
+INFO:datasets.builder:Using custom data configuration default-481a1a6a0ca4575e
+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-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
+INFO:datasets.builder:Found cached dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101)
+INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
+INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-798e68ee1238406a.arrow
+INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-08141c170f1669b9.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:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-2ba0b834485aeaf5.arrow
+INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-7a0a05502f2d2ac6.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 8.0: Train Loss = 0.0148, Eval Loss = 0.05825383961200714
+INFO:absl:Using default tokenizer.

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45e0cf31bee1b8b8387fb0f29745e522f94fc53235332e2b661c0c8c7023676e
+oid sha256:72428eb693eb4400f6f9ebc2b541739b8e512b7964d04dea4072bfce7197fd14
 size 3166550552

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 1024
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 64002,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c626dac860f540845e1264968171d09c78ff900fa0e28bb6553c1e6488baadbb
+oid sha256:e35118fac8928c2503b72682aeecba0516bf0a7b8ce487ee06590491631f00dc
 size 5240