Training in progress, epoch 3

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "riotu-lab/ArabianGPT-01B",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": null,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 64000,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 768,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 768,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "vocab_size": 64005
+}

egy_training_log.txt

@@ -0,0 +1,159 @@
+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/runs/Aug31_18-23-30_lmgpu-node-09,
+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,
+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,
+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-553f61aee4dda760
+INFO:datasets.info:Loading Dataset Infos from /home/iais_marenpielka/Bouthaina/miniconda3/lib/python3.12/site-packages/datasets/packaged_modules/text
+INFO:datasets.builder:Generating dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-553f61aee4dda760/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101)
+INFO:datasets.builder:Downloading and preparing dataset text/default to /home/iais_marenpielka/.cache/huggingface/datasets/text/default-553f61aee4dda760/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101...
+INFO:datasets.download.download_manager:Downloading took 0.0 min
+INFO:datasets.download.download_manager:Checksum Computation took 0.0 min
+INFO:datasets.builder:Generating train split
+INFO:datasets.builder:Generating validation split
+INFO:datasets.utils.info_utils:Unable to verify splits sizes.
+INFO:datasets.builder:Dataset text downloaded and prepared to /home/iais_marenpielka/.cache/huggingface/datasets/text/default-553f61aee4dda760/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101. Subsequent calls will reuse this data.
+INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-553f61aee4dda760/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-0c0ca65a5faa1c69.arrow
+INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-553f61aee4dda760/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-ff33919083e7cfc3.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-553f61aee4dda760/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-b67d61859d143d55.arrow
+INFO:datasets.arrow_dataset:Caching processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-553f61aee4dda760/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-b5882b385151b146.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 = 7.8314, Eval Loss = 2.359743595123291
+INFO:absl:Using default tokenizer.
+WARNING:huggingface_hub.utils._http:'(MaxRetryError("HTTPSConnectionPool(host='hf-hub-lfs-us-east-1.s3-accelerate.amazonaws.com', port=443): Max retries exceeded with url: /repos/4e/c5/4ec5c12bd4b31fb218515ee480d86e26419d948a9a596a06a6ad09ce77d37e3a/deff7f99580238a45f3ba2bc7047e31a358560b58dc3266d8058c6e623cbfa0f?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=AKIA2JU7TKAQLC2QXPN7%2F20240831%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240831T182623Z&X-Amz-Expires=86400&X-Amz-Signature=e2b8cc4c6a6039dd14e9fd45f97285bd8f4c36e3b9f82774a0533eb3ab485699&X-Amz-SignedHeaders=host&partNumber=30&uploadId=1pifW86uMHklMcYfwNTOkTEVjye.aOXHsYNw1UiFajy5ulD2SMmE7lXK11IQuIa2xOtCET.QPTYOMxy0LOMBKD1rWT_Aq4IFRTZ.IqMHIpcpxuwSEUr.74Jrxu7CFsaq&x-id=UploadPart (Caused by SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:2406)')))"), '(Request ID: 45c28252-333d-4bd7-bdae-103a87df191a)')' thrown while requesting PUT https://hf-hub-lfs-us-east-1.s3-accelerate.amazonaws.com/repos/4e/c5/4ec5c12bd4b31fb218515ee480d86e26419d948a9a596a06a6ad09ce77d37e3a/deff7f99580238a45f3ba2bc7047e31a358560b58dc3266d8058c6e623cbfa0f?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=AKIA2JU7TKAQLC2QXPN7%2F20240831%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240831T182623Z&X-Amz-Expires=86400&X-Amz-Signature=e2b8cc4c6a6039dd14e9fd45f97285bd8f4c36e3b9f82774a0533eb3ab485699&X-Amz-SignedHeaders=host&partNumber=30&uploadId=1pifW86uMHklMcYfwNTOkTEVjye.aOXHsYNw1UiFajy5ulD2SMmE7lXK11IQuIa2xOtCET.QPTYOMxy0LOMBKD1rWT_Aq4IFRTZ.IqMHIpcpxuwSEUr.74Jrxu7CFsaq&x-id=UploadPart
+WARNING:huggingface_hub.utils._http:Retrying in 1s [Retry 1/5].
+INFO:root:Epoch 3.0: Train Loss = 0.9995, Eval Loss = 0.5537932515144348
+INFO:absl:Using default tokenizer.
+INFO:root:Epoch 4.0: Train Loss = 0.4848, Eval Loss = 0.5034472942352295
+INFO:absl:Using default tokenizer.
+INFO:root:Epoch 5.0: Train Loss = 0.3823, Eval Loss = 0.4827471375465393
+INFO:absl:Using default tokenizer.
+INFO:root:Epoch 6.0: Train Loss = 0.293, Eval Loss = 0.4732062816619873

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:154e656891141c4b6e56691de7b6e5e274a9e122d269e3d25cef7a95cf6d92a6
+size 539221632

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "[s]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[sep]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": {
+    "content": "<EOS>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<EOS>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<EOS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64001": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64002": {
+      "content": "[s]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64003": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64004": {
+      "content": "[sep]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[s]",
+    "</s>",
+    "[sep]"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<EOS>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<EOS>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a80b641e121dfe14109ce291c3105dd7ce50626e7c8145f15a49c5d87658a2ca
+size 5240