| 2025-05-12 22:49:28 - WARNING - __main__ - Process rank: 1, device: cuda:1, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:28 - WARNING - __main__ - Process rank: 4, device: cuda:4, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:28 - WARNING - __main__ - Process rank: 5, device: cuda:5, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:28 - WARNING - __main__ - Process rank: 6, device: cuda:6, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:28 - WARNING - __main__ - Process rank: 2, device: cuda:2, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:28 - WARNING - __main__ - Process rank: 7, device: cuda:7, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:28 - WARNING - __main__ - Process rank: 3, device: cuda:3, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:33 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:33 - INFO - __main__ - Model parameters ModelArguments(base_model_revision=None, model_name_or_path='/gscratch/weirdlab/mateogc/projects/vlm-navigation/data/paligemma2-3b-pt-224-sft-lora-magicsoup_no_cfiphone_no_insta_sub5', model_revision='main', model_code_revision=None, torch_dtype='bfloat16', tokenizer_name_or_path=None, processor_name_or_path=None, trust_remote_code=False, attn_implementation='eager', use_peft=True, lora_r=16, lora_alpha=16, lora_dropout=0.05, lora_target_modules=['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj'], lora_modules_to_save=None, load_in_8bit=False, load_in_4bit=False, bnb_4bit_quant_type='nf4', use_bnb_nested_quant=False, bnb_4bit_quant_storage='uint8') | |
| 2025-05-12 22:49:33 - INFO - __main__ - Data parameters DataArguments(chat_template=None, dataset_mixer={'mateoguaman/vlmn_0.1_cotrain_magicsoup_standalone_sub5': 1.0, 'mateoguaman/iphone_gates_every1_100pct_sub5': 1.0}, eval_dataset_mixer={'mateoguaman/vlmn_0.1_cotrain_magicsoup_standalone_sub5': 1.0, 'mateoguaman/iphone_gates_every1_100pct_sub5': 1.0}, text_column='text', dataset_splits=['train', 'test'], train_splits=['train'], validation_splits=['validation'], processing_params={}, dataset_configs=None, preprocessing_num_workers=12, truncation_side=None, auto_insert_empty_system_msg=True, auto_set_chat_template=False, cache_dataset_only=False, just_combine_data=False, output_dataset_name=None, output_dataset_description=None, hf_entity=None) | |
| 2025-05-12 22:49:33 - INFO - __main__ - Training/evaluation parameters SFTConfig( | |
| _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, | |
| average_tokens_across_devices=False, | |
| batch_eval_metrics=False, | |
| bf16=True, | |
| bf16_full_eval=False, | |
| chars_per_token=<CHARS_PER_TOKEN>, | |
| data_seed=None, | |
| dataloader_drop_last=False, | |
| dataloader_num_workers=0, | |
| dataloader_persistent_workers=False, | |
| dataloader_pin_memory=True, | |
| dataloader_prefetch_factor=None, | |
| dataset_batch_size=None, | |
| dataset_kwargs=None, | |
| dataset_num_proc=None, | |
| dataset_text_field=text, | |
| 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=False, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_do_concat_batches=True, | |
| eval_on_start=False, | |
| eval_packing=None, | |
| eval_steps=0.25, | |
| eval_strategy=IntervalStrategy.STEPS, | |
| eval_use_gather_object=False, | |
| evaluation_strategy=None, | |
| 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=paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5, | |
| hub_model_revision=main, | |
| hub_private_repo=None, | |
| hub_strategy=HubStrategy.EVERY_SAVE, | |
| hub_token=<HUB_TOKEN>, | |
| ignore_data_skip=False, | |
| include_for_metrics=[], | |
| 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=0.0001, | |
| length_column_name=length, | |
| load_best_model_at_end=True, | |
| local_rank=0, | |
| log_level=info, | |
| log_level_replica=warning, | |
| log_on_each_node=True, | |
| logging_dir=data/paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5/runs/May12_22-49-27_g3093, | |
| logging_first_step=True, | |
| logging_nan_inf_filter=True, | |
| logging_steps=20, | |
| logging_strategy=IntervalStrategy.STEPS, | |
| lr_scheduler_kwargs={}, | |
| lr_scheduler_type=SchedulerType.COSINE, | |
| max_grad_norm=1.0, | |
| max_seq_length=2048, | |
| max_steps=-1, | |
| metric_for_best_model=loss, | |
| model_init_kwargs=None, | |
| mp_parameters=, | |
| neftune_noise_alpha=None, | |
| no_cuda=False, | |
| num_of_sequences=None, | |
| num_train_epochs=1, | |
| optim=OptimizerNames.ADAMW_TORCH, | |
| optim_args=None, | |
| optim_target_modules=None, | |
| output_dir=data/paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5, | |
| overwrite_output_dir=True, | |
| packing=True, | |
| past_index=-1, | |
| per_device_eval_batch_size=8, | |
| per_device_train_batch_size=8, | |
| prediction_loss_only=False, | |
| push_to_hub=False, | |
| 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=['wandb'], | |
| restore_callback_states_from_checkpoint=False, | |
| resume_from_checkpoint=None, | |
| run_name=data/paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5, | |
| save_on_each_node=False, | |
| save_only_model=False, | |
| save_safetensors=True, | |
| save_steps=0.25, | |
| save_strategy=SaveStrategy.STEPS, | |
| 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_liger=False, | |
| use_liger_kernel=False, | |
| use_mps_device=False, | |
| warmup_ratio=0.1, | |
| warmup_steps=0, | |
| weight_decay=1e-05, | |
| ) | |
| 2025-05-12 22:49:47 - WARNING - __main__ - Process rank: 2, device: cuda:2, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:47 - WARNING - __main__ - Process rank: 4, device: cuda:4, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:47 - WARNING - __main__ - Process rank: 5, device: cuda:5, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:47 - WARNING - __main__ - Process rank: 7, device: cuda:7, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:47 - WARNING - __main__ - Process rank: 6, device: cuda:6, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:47 - WARNING - __main__ - Process rank: 3, device: cuda:3, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:47 - WARNING - __main__ - Process rank: 1, device: cuda:1, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:48 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:49:48 - INFO - __main__ - Model parameters ModelArguments(base_model_revision=None, model_name_or_path='/gscratch/weirdlab/mateogc/projects/vlm-navigation/data/paligemma2-3b-pt-224-sft-lora-magicsoup_no_cfiphone_no_insta_sub5', model_revision='main', model_code_revision=None, torch_dtype='bfloat16', tokenizer_name_or_path=None, processor_name_or_path=None, trust_remote_code=False, attn_implementation='eager', use_peft=True, lora_r=16, lora_alpha=16, lora_dropout=0.05, lora_target_modules=['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj'], lora_modules_to_save=None, load_in_8bit=False, load_in_4bit=False, bnb_4bit_quant_type='nf4', use_bnb_nested_quant=False, bnb_4bit_quant_storage='uint8') | |
| 2025-05-12 22:49:48 - INFO - __main__ - Data parameters DataArguments(chat_template=None, dataset_mixer={'mateoguaman/vlmn_0.1_cotrain_magicsoup_standalone_sub5': 1.0, 'mateoguaman/iphone_gates_every1_100pct_sub5': 1.0}, eval_dataset_mixer={'mateoguaman/vlmn_0.1_cotrain_magicsoup_standalone_sub5': 1.0, 'mateoguaman/iphone_gates_every1_100pct_sub5': 1.0}, text_column='text', dataset_splits=['train', 'test'], train_splits=['train'], validation_splits=['validation'], processing_params={}, dataset_configs=None, preprocessing_num_workers=12, truncation_side=None, auto_insert_empty_system_msg=True, auto_set_chat_template=False, cache_dataset_only=False, just_combine_data=False, output_dataset_name=None, output_dataset_description=None, hf_entity=None) | |
| 2025-05-12 22:49:48 - INFO - __main__ - Training/evaluation parameters SFTConfig( | |
| _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, | |
| average_tokens_across_devices=False, | |
| batch_eval_metrics=False, | |
| bf16=True, | |
| bf16_full_eval=False, | |
| chars_per_token=<CHARS_PER_TOKEN>, | |
| data_seed=None, | |
| dataloader_drop_last=False, | |
| dataloader_num_workers=0, | |
| dataloader_persistent_workers=False, | |
| dataloader_pin_memory=True, | |
| dataloader_prefetch_factor=None, | |
| dataset_batch_size=None, | |
| dataset_kwargs=None, | |
| dataset_num_proc=None, | |
| dataset_text_field=text, | |
| 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=False, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_do_concat_batches=True, | |
| eval_on_start=False, | |
| eval_packing=None, | |
| eval_steps=0.25, | |
| eval_strategy=IntervalStrategy.STEPS, | |
| eval_use_gather_object=False, | |
| evaluation_strategy=None, | |
| 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=paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5, | |
| hub_model_revision=main, | |
| hub_private_repo=None, | |
| hub_strategy=HubStrategy.EVERY_SAVE, | |
| hub_token=<HUB_TOKEN>, | |
| ignore_data_skip=False, | |
| include_for_metrics=[], | |
| 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=0.0001, | |
| length_column_name=length, | |
| load_best_model_at_end=True, | |
| local_rank=0, | |
| log_level=info, | |
| log_level_replica=warning, | |
| log_on_each_node=True, | |
| logging_dir=data/paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5/runs/May12_22-49-46_g3093, | |
| logging_first_step=True, | |
| logging_nan_inf_filter=True, | |
| logging_steps=20, | |
| logging_strategy=IntervalStrategy.STEPS, | |
| lr_scheduler_kwargs={}, | |
| lr_scheduler_type=SchedulerType.COSINE, | |
| max_grad_norm=1.0, | |
| max_seq_length=2048, | |
| max_steps=-1, | |
| metric_for_best_model=loss, | |
| model_init_kwargs=None, | |
| mp_parameters=, | |
| neftune_noise_alpha=None, | |
| no_cuda=False, | |
| num_of_sequences=None, | |
| num_train_epochs=1, | |
| optim=OptimizerNames.ADAMW_TORCH, | |
| optim_args=None, | |
| optim_target_modules=None, | |
| output_dir=data/paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5, | |
| overwrite_output_dir=True, | |
| packing=True, | |
| past_index=-1, | |
| per_device_eval_batch_size=8, | |
| per_device_train_batch_size=8, | |
| prediction_loss_only=False, | |
| push_to_hub=False, | |
| 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=['wandb'], | |
| restore_callback_states_from_checkpoint=False, | |
| resume_from_checkpoint=None, | |
| run_name=data/paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5, | |
| save_on_each_node=False, | |
| save_only_model=False, | |
| save_safetensors=True, | |
| save_steps=0.25, | |
| save_strategy=SaveStrategy.STEPS, | |
| 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_liger=False, | |
| use_liger_kernel=False, | |
| use_mps_device=False, | |
| warmup_ratio=0.1, | |
| warmup_steps=0, | |
| weight_decay=1e-05, | |
| ) | |
| 2025-05-12 22:58:27 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 8 distributed training: True, 16-bits training: False | |
| 2025-05-12 22:58:27 - INFO - __main__ - Model parameters ModelArguments(base_model_revision=None, model_name_or_path='/gscratch/weirdlab/mateogc/projects/vlm-navigation/data/paligemma2-3b-pt-224-sft-lora-magicsoup_no_cfiphone_no_insta_sub5', model_revision='main', model_code_revision=None, torch_dtype='bfloat16', tokenizer_name_or_path=None, processor_name_or_path=None, trust_remote_code=False, attn_implementation='eager', use_peft=True, lora_r=16, lora_alpha=16, lora_dropout=0.05, lora_target_modules=['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj'], lora_modules_to_save=None, load_in_8bit=False, load_in_4bit=False, bnb_4bit_quant_type='nf4', use_bnb_nested_quant=False, bnb_4bit_quant_storage='uint8') | |
| 2025-05-12 22:58:27 - INFO - __main__ - Data parameters DataArguments(chat_template=None, dataset_mixer={'mateoguaman/vlmn_0.1_cotrain_magicsoup_standalone_sub5': 1.0, 'mateoguaman/iphone_gates_every1_100pct_sub5': 1.0}, eval_dataset_mixer={'mateoguaman/vlmn_0.1_cotrain_magicsoup_standalone_sub5': 1.0, 'mateoguaman/iphone_gates_every1_100pct_sub5': 1.0}, text_column='text', dataset_splits=['train', 'test'], train_splits=['train'], validation_splits=['validation'], processing_params={}, dataset_configs=None, preprocessing_num_workers=12, truncation_side=None, auto_insert_empty_system_msg=True, auto_set_chat_template=False, cache_dataset_only=True, just_combine_data=False, output_dataset_name='mateoguaman/vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5', output_dataset_description='VLN Navigation dataset with 100% of gates iphone data, 10% of magicsoup no insta subsampled to 5 points.', hf_entity=None) | |
| 2025-05-12 22:58:27 - INFO - __main__ - Training/evaluation parameters SFTConfig( | |
| _n_gpu=8, | |
| 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, | |
| average_tokens_across_devices=False, | |
| batch_eval_metrics=False, | |
| bf16=True, | |
| bf16_full_eval=False, | |
| chars_per_token=<CHARS_PER_TOKEN>, | |
| data_seed=None, | |
| dataloader_drop_last=False, | |
| dataloader_num_workers=0, | |
| dataloader_persistent_workers=False, | |
| dataloader_pin_memory=True, | |
| dataloader_prefetch_factor=None, | |
| dataset_batch_size=None, | |
| dataset_kwargs=None, | |
| dataset_num_proc=None, | |
| dataset_text_field=text, | |
| 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=False, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_do_concat_batches=True, | |
| eval_on_start=False, | |
| eval_packing=None, | |
| eval_steps=0.25, | |
| eval_strategy=IntervalStrategy.STEPS, | |
| eval_use_gather_object=False, | |
| evaluation_strategy=None, | |
| 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=paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5, | |
| hub_model_revision=main, | |
| hub_private_repo=None, | |
| hub_strategy=HubStrategy.EVERY_SAVE, | |
| hub_token=<HUB_TOKEN>, | |
| ignore_data_skip=False, | |
| include_for_metrics=[], | |
| 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=0.0001, | |
| length_column_name=length, | |
| load_best_model_at_end=True, | |
| local_rank=0, | |
| log_level=info, | |
| log_level_replica=warning, | |
| log_on_each_node=True, | |
| logging_dir=data/paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5/runs/May12_22-58-26_g3093, | |
| logging_first_step=True, | |
| logging_nan_inf_filter=True, | |
| logging_steps=20, | |
| logging_strategy=IntervalStrategy.STEPS, | |
| lr_scheduler_kwargs={}, | |
| lr_scheduler_type=SchedulerType.COSINE, | |
| max_grad_norm=1.0, | |
| max_seq_length=2048, | |
| max_steps=-1, | |
| metric_for_best_model=loss, | |
| model_init_kwargs=None, | |
| mp_parameters=, | |
| neftune_noise_alpha=None, | |
| no_cuda=False, | |
| num_of_sequences=None, | |
| num_train_epochs=1, | |
| optim=OptimizerNames.ADAMW_TORCH, | |
| optim_args=None, | |
| optim_target_modules=None, | |
| output_dir=data/paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5, | |
| overwrite_output_dir=True, | |
| packing=True, | |
| past_index=-1, | |
| per_device_eval_batch_size=8, | |
| per_device_train_batch_size=8, | |
| prediction_loss_only=False, | |
| push_to_hub=False, | |
| 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=['wandb'], | |
| restore_callback_states_from_checkpoint=False, | |
| resume_from_checkpoint=None, | |
| run_name=data/paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5, | |
| save_on_each_node=False, | |
| save_only_model=False, | |
| save_safetensors=True, | |
| save_steps=0.25, | |
| save_strategy=SaveStrategy.STEPS, | |
| 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_liger=False, | |
| use_liger_kernel=False, | |
| use_mps_device=False, | |
| warmup_ratio=0.1, | |
| warmup_steps=0, | |
| weight_decay=1e-05, | |
| ) | |
| 2025-05-12 22:58:33 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists. | |
| 2025-05-12 22:58:33 - INFO - datasets.info - Loading Dataset info from /gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___vlmn_0.1_cotrain_magicsoup_standalone_sub5/default/0.0.0/3741cbdbb80e0dfa24ee255851ae3b93bfaf0448 | |
| 2025-05-12 22:58:34 - INFO - datasets.builder - Found cached dataset vlmn_0.1_cotrain_magicsoup_standalone_sub5 (/gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___vlmn_0.1_cotrain_magicsoup_standalone_sub5/default/0.0.0/3741cbdbb80e0dfa24ee255851ae3b93bfaf0448) | |
| 2025-05-12 22:58:34 - INFO - datasets.info - Loading Dataset info from /gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___vlmn_0.1_cotrain_magicsoup_standalone_sub5/default/0.0.0/3741cbdbb80e0dfa24ee255851ae3b93bfaf0448 | |
| 2025-05-12 22:58:38 - INFO - datasets.arrow_dataset - Caching indices mapping at /gscratch/robotics/mateogc/tmp/hf_datasets-rcx67u3z/cache-833ff5863f04cd23.arrow | |
| 2025-05-12 22:58:38 - INFO - datasets.arrow_dataset - Caching indices mapping at /gscratch/robotics/mateogc/tmp/hf_datasets-rcx67u3z/cache-436cddd51a04475d.arrow | |
| 2025-05-12 23:45:39 - INFO - datasets.builder - No config specified, defaulting to the single config: dataset-mix-cached/default | |
| 2025-05-12 23:45:39 - INFO - datasets.info - Loading Dataset Infos from /gscratch/weirdlab/mateogc/miniconda3/envs/vlmn/lib/python3.11/site-packages/datasets/packaged_modules/parquet | |
| 2025-05-12 23:45:39 - INFO - datasets.builder - Generating dataset dataset-mix-cached (/gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___dataset-mix-cached/default/0.0.0/2ea82b7ea446357f81cd9f966ee04b12cc4a32a4) | |
| 2025-05-12 23:45:39 - INFO - datasets.builder - Downloading and preparing dataset dataset-mix-cached/default to /gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___dataset-mix-cached/default/0.0.0/2ea82b7ea446357f81cd9f966ee04b12cc4a32a4... | |
| 2025-05-12 23:48:35 - INFO - datasets.download.download_manager - Downloading took 2.0 min | |
| 2025-05-12 23:48:35 - INFO - datasets.download.download_manager - Checksum Computation took 0.0 min | |
| 2025-05-12 23:48:37 - INFO - datasets.builder - Generating train split | |
| 2025-05-12 23:48:50 - INFO - datasets.utils.info_utils - Unable to verify splits sizes. | |
| 2025-05-12 23:48:50 - INFO - datasets.builder - Dataset dataset-mix-cached downloaded and prepared to /gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___dataset-mix-cached/default/0.0.0/2ea82b7ea446357f81cd9f966ee04b12cc4a32a4. Subsequent calls will reuse this data. | |
| 2025-05-12 23:48:55 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists. | |
| 2025-05-12 23:48:55 - INFO - datasets.info - Loading Dataset info from /gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___vlmn_0.1_cotrain_magicsoup_standalone_sub5/default/0.0.0/3741cbdbb80e0dfa24ee255851ae3b93bfaf0448 | |
| 2025-05-12 23:48:55 - INFO - datasets.builder - Found cached dataset vlmn_0.1_cotrain_magicsoup_standalone_sub5 (/gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___vlmn_0.1_cotrain_magicsoup_standalone_sub5/default/0.0.0/3741cbdbb80e0dfa24ee255851ae3b93bfaf0448) | |
| 2025-05-12 23:48:55 - INFO - datasets.info - Loading Dataset info from /gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___vlmn_0.1_cotrain_magicsoup_standalone_sub5/default/0.0.0/3741cbdbb80e0dfa24ee255851ae3b93bfaf0448 | |
| 2025-05-12 23:48:55 - INFO - datasets.arrow_dataset - Caching indices mapping at /gscratch/robotics/mateogc/tmp/hf_datasets-rcx67u3z/cache-ef4bd045e795c20a.arrow | |
| 2025-05-12 23:48:56 - INFO - datasets.arrow_dataset - Caching indices mapping at /gscratch/robotics/mateogc/tmp/hf_datasets-rcx67u3z/cache-18785f463805c080.arrow | |
| 2025-05-12 23:51:36 - INFO - datasets.builder - No config specified, defaulting to the single config: dataset-mix-cached/default | |
| 2025-05-12 23:51:36 - INFO - datasets.info - Loading Dataset Infos from /gscratch/weirdlab/mateogc/miniconda3/envs/vlmn/lib/python3.11/site-packages/datasets/packaged_modules/parquet | |
| 2025-05-12 23:51:36 - INFO - datasets.builder - Generating dataset dataset-mix-cached (/gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___dataset-mix-cached/default/0.0.0/af2f1399f076247c62b24d8a50f6597586f6a768) | |
| 2025-05-12 23:51:36 - INFO - datasets.builder - Downloading and preparing dataset dataset-mix-cached/default to /gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___dataset-mix-cached/default/0.0.0/af2f1399f076247c62b24d8a50f6597586f6a768... | |
| 2025-05-12 23:52:20 - INFO - datasets.download.download_manager - Downloading took 0.0 min | |
| 2025-05-12 23:52:20 - INFO - datasets.download.download_manager - Checksum Computation took 0.0 min | |
| 2025-05-12 23:52:20 - INFO - datasets.builder - Generating train split | |
| 2025-05-12 23:52:22 - INFO - datasets.utils.info_utils - Unable to verify splits sizes. | |
| 2025-05-12 23:52:22 - INFO - datasets.builder - Dataset dataset-mix-cached downloaded and prepared to /gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___dataset-mix-cached/default/0.0.0/af2f1399f076247c62b24d8a50f6597586f6a768. Subsequent calls will reuse this data. | |
| 2025-05-12 23:52:22 - INFO - __main__ - Consolidating dataset into standalone dataset at: mateoguaman/vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5 | |
| 2025-05-12 23:52:28 - INFO - datasets.dataset_dict - Pushing split train to the Hub. | |
| 2025-05-12 23:58:31 - INFO - datasets.dataset_dict - Pushing split validation to the Hub. | |
| 2025-05-13 00:00:11 - INFO - datasets.builder - No config specified, defaulting to the single config: vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5/default | |
| 2025-05-13 00:00:11 - INFO - datasets.info - Loading Dataset Infos from /gscratch/weirdlab/mateogc/miniconda3/envs/vlmn/lib/python3.11/site-packages/datasets/packaged_modules/parquet | |
| 2025-05-13 00:00:11 - INFO - datasets.builder - Generating dataset vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5 (/gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5/default/0.0.0/bd19619fabdce622fb4839978815e43642d3d72e) | |
| 2025-05-13 00:00:11 - INFO - datasets.builder - Downloading and preparing dataset vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5/default to /gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5/default/0.0.0/bd19619fabdce622fb4839978815e43642d3d72e... | |
| 2025-05-13 00:03:24 - INFO - datasets.download.download_manager - Downloading took 3.0 min | |
| 2025-05-13 00:03:24 - INFO - datasets.download.download_manager - Checksum Computation took 0.0 min | |
| 2025-05-13 00:03:26 - INFO - datasets.builder - Generating train split | |
| 2025-05-13 00:03:39 - INFO - datasets.builder - Generating validation split | |
| 2025-05-13 00:03:42 - INFO - datasets.utils.info_utils - Unable to verify splits sizes. | |
| 2025-05-13 00:03:42 - INFO - datasets.builder - Dataset vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5 downloaded and prepared to /gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5/default/0.0.0/bd19619fabdce622fb4839978815e43642d3d72e. Subsequent calls will reuse this data. | |
| 2025-05-13 00:03:43 - INFO - __main__ - *** Dataset cached! Exiting now. *** | |
| 2025-05-13 00:07:04 - WARNING - __main__ - Process rank: 2, device: cuda:2, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-13 00:07:04 - WARNING - __main__ - Process rank: 1, device: cuda:1, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-13 00:07:04 - WARNING - __main__ - Process rank: 3, device: cuda:3, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-13 00:07:04 - WARNING - __main__ - Process rank: 4, device: cuda:4, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-13 00:07:04 - WARNING - __main__ - Process rank: 6, device: cuda:6, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-13 00:07:04 - WARNING - __main__ - Process rank: 7, device: cuda:7, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-13 00:07:04 - WARNING - __main__ - Process rank: 5, device: cuda:5, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-13 00:07:06 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1 distributed training: True, 16-bits training: False | |
| 2025-05-13 00:07:06 - INFO - __main__ - Model parameters ModelArguments(base_model_revision=None, model_name_or_path='/gscratch/weirdlab/mateogc/projects/vlm-navigation/data/paligemma2-3b-pt-224-sft-lora-magicsoup_no_cfiphone_no_insta_sub5', model_revision='main', model_code_revision=None, torch_dtype='bfloat16', tokenizer_name_or_path=None, processor_name_or_path=None, trust_remote_code=False, attn_implementation='eager', use_peft=True, lora_r=16, lora_alpha=16, lora_dropout=0.05, lora_target_modules=['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj'], lora_modules_to_save=None, load_in_8bit=False, load_in_4bit=False, bnb_4bit_quant_type='nf4', use_bnb_nested_quant=False, bnb_4bit_quant_storage='uint8') | |
| 2025-05-13 00:07:06 - INFO - __main__ - Data parameters DataArguments(chat_template=None, dataset_mixer={'mateoguaman/vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5': 1.0}, eval_dataset_mixer={'mateoguaman/vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5': 1.0}, text_column='text', dataset_splits=['train', 'test'], train_splits=['train'], validation_splits=['validation'], processing_params={}, dataset_configs=None, preprocessing_num_workers=12, truncation_side=None, auto_insert_empty_system_msg=True, auto_set_chat_template=False, cache_dataset_only=False, just_combine_data=False, output_dataset_name=None, output_dataset_description=None, hf_entity=None) | |
| 2025-05-13 00:07:06 - INFO - __main__ - Training/evaluation parameters SFTConfig( | |
| _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, | |
| average_tokens_across_devices=False, | |
| batch_eval_metrics=False, | |
| bf16=True, | |
| bf16_full_eval=False, | |
| chars_per_token=<CHARS_PER_TOKEN>, | |
| data_seed=None, | |
| dataloader_drop_last=False, | |
| dataloader_num_workers=0, | |
| dataloader_persistent_workers=False, | |
| dataloader_pin_memory=True, | |
| dataloader_prefetch_factor=None, | |
| dataset_batch_size=None, | |
| dataset_kwargs=None, | |
| dataset_num_proc=None, | |
| dataset_text_field=text, | |
| 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=False, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_do_concat_batches=True, | |
| eval_on_start=False, | |
| eval_packing=None, | |
| eval_steps=0.25, | |
| eval_strategy=IntervalStrategy.STEPS, | |
| eval_use_gather_object=False, | |
| evaluation_strategy=None, | |
| 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=paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5, | |
| hub_model_revision=main, | |
| hub_private_repo=None, | |
| hub_strategy=HubStrategy.EVERY_SAVE, | |
| hub_token=<HUB_TOKEN>, | |
| ignore_data_skip=False, | |
| include_for_metrics=[], | |
| 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=0.0001, | |
| length_column_name=length, | |
| load_best_model_at_end=True, | |
| local_rank=0, | |
| log_level=info, | |
| log_level_replica=warning, | |
| log_on_each_node=True, | |
| logging_dir=data/paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5/runs/May13_00-07-04_g3118, | |
| logging_first_step=True, | |
| logging_nan_inf_filter=True, | |
| logging_steps=20, | |
| logging_strategy=IntervalStrategy.STEPS, | |
| lr_scheduler_kwargs={}, | |
| lr_scheduler_type=SchedulerType.COSINE, | |
| max_grad_norm=1.0, | |
| max_seq_length=2048, | |
| max_steps=-1, | |
| metric_for_best_model=loss, | |
| model_init_kwargs=None, | |
| mp_parameters=, | |
| neftune_noise_alpha=None, | |
| no_cuda=False, | |
| num_of_sequences=None, | |
| num_train_epochs=1, | |
| optim=OptimizerNames.ADAMW_TORCH, | |
| optim_args=None, | |
| optim_target_modules=None, | |
| output_dir=data/paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5, | |
| overwrite_output_dir=True, | |
| packing=True, | |
| past_index=-1, | |
| per_device_eval_batch_size=8, | |
| per_device_train_batch_size=8, | |
| prediction_loss_only=False, | |
| push_to_hub=False, | |
| 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=['wandb'], | |
| restore_callback_states_from_checkpoint=False, | |
| resume_from_checkpoint=None, | |
| run_name=data/paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5, | |
| save_on_each_node=False, | |
| save_only_model=False, | |
| save_safetensors=True, | |
| save_steps=0.25, | |
| save_strategy=SaveStrategy.STEPS, | |
| 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_liger=False, | |
| use_liger_kernel=False, | |
| use_mps_device=False, | |
| warmup_ratio=0.1, | |
| warmup_steps=0, | |
| weight_decay=1e-05, | |
| ) | |
| 2025-05-13 00:07:10 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists. | |
| 2025-05-13 00:07:10 - INFO - datasets.info - Loading Dataset info from /gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5/default/0.0.0/bd19619fabdce622fb4839978815e43642d3d72e | |
| 2025-05-13 00:07:10 - INFO - datasets.builder - Found cached dataset vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5 (/gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5/default/0.0.0/bd19619fabdce622fb4839978815e43642d3d72e) | |
| 2025-05-13 00:07:10 - INFO - datasets.info - Loading Dataset info from /gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5/default/0.0.0/bd19619fabdce622fb4839978815e43642d3d72e | |
| 2025-05-13 00:07:10 - INFO - datasets.arrow_dataset - Caching indices mapping at /gscratch/robotics/mateogc/tmp/hf_datasets-4se5rdmo/cache-0d6f9d3071a76d2b.arrow | |
| 2025-05-13 00:07:10 - INFO - datasets.arrow_dataset - Caching indices mapping at /gscratch/robotics/mateogc/tmp/hf_datasets-4se5rdmo/cache-3513e5aed38b6b61.arrow | |
| 2025-05-13 00:07:11 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists. | |
| 2025-05-13 00:07:11 - INFO - datasets.info - Loading Dataset info from /gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5/default/0.0.0/bd19619fabdce622fb4839978815e43642d3d72e | |
| 2025-05-13 00:07:11 - INFO - datasets.builder - Found cached dataset vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5 (/gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5/default/0.0.0/bd19619fabdce622fb4839978815e43642d3d72e) | |
| 2025-05-13 00:07:11 - INFO - datasets.info - Loading Dataset info from /gscratch/weirdlab/mateogc/huggingface/datasets/mateoguaman___vlmn_iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5/default/0.0.0/bd19619fabdce622fb4839978815e43642d3d72e | |
| 2025-05-13 00:07:12 - INFO - datasets.arrow_dataset - Caching indices mapping at /gscratch/robotics/mateogc/tmp/hf_datasets-4se5rdmo/cache-679c7fa4d30b333a.arrow | |
| 2025-05-13 00:07:12 - INFO - datasets.arrow_dataset - Caching indices mapping at /gscratch/robotics/mateogc/tmp/hf_datasets-4se5rdmo/cache-48bbf81c93a87cba.arrow | |
| 2025-05-13 00:07:12 - INFO - __main__ - *** Load pretrained model *** | |
| 2025-05-13 00:07:23 - INFO - peft.tuners.tuners_utils - Already found a `peft_config` attribute in the model. This will lead to having multiple adapters in the model. Make sure to know what you are doing! | |
| 2025-05-13 00:07:23 - INFO - peft.tuners.tuners_utils - Already found a `peft_config` attribute in the model. This will lead to having multiple adapters in the model. Make sure to know what you are doing! | |
| 2025-05-13 00:07:23 - INFO - peft.tuners.tuners_utils - Already found a `peft_config` attribute in the model. This will lead to having multiple adapters in the model. Make sure to know what you are doing! | |
| 2025-05-13 00:07:23 - INFO - peft.tuners.tuners_utils - Already found a `peft_config` attribute in the model. This will lead to having multiple adapters in the model. Make sure to know what you are doing! | |
| 2025-05-13 00:07:23 - INFO - peft.tuners.tuners_utils - Already found a `peft_config` attribute in the model. This will lead to having multiple adapters in the model. Make sure to know what you are doing! | |
| 2025-05-13 00:07:23 - INFO - peft.tuners.tuners_utils - Already found a `peft_config` attribute in the model. This will lead to having multiple adapters in the model. Make sure to know what you are doing! | |
| 2025-05-13 00:07:23 - INFO - peft.tuners.tuners_utils - Already found a `peft_config` attribute in the model. This will lead to having multiple adapters in the model. Make sure to know what you are doing! | |
| 2025-05-13 00:07:23 - INFO - peft.tuners.tuners_utils - Already found a `peft_config` attribute in the model. This will lead to having multiple adapters in the model. Make sure to know what you are doing! | |
| 2025-05-13 00:07:24 - INFO - __main__ - Model has these adapters: dict_keys(['default']) | |
| 2025-05-13 00:07:24 - INFO - __main__ - Sample 7296 of the processed training set: | |
| Navigate to x=<loc0468>, y=<loc0507> | |
| <loc0525><loc0668><loc0520><loc0584><loc0505><loc0546><loc0485><loc0524><loc0468><loc0507> | |
| 2025-05-13 00:07:25 - INFO - __main__ - Sample 1639 of the processed training set: | |
| Navigate to x=<loc0512>, y=<loc0506> | |
| <loc0522><loc0704><loc0519><loc0614><loc0518><loc0570><loc0516><loc0537><loc0512><loc0506> | |
| 2025-05-13 00:07:25 - INFO - __main__ - Sample 18024 of the processed training set: | |
| Navigate to x=<loc0608>, y=<loc0529> | |
| <loc0552><loc0696><loc0569><loc0614><loc0591><loc0578><loc0614><loc0554><loc0608><loc0529> | |
| 2025-05-13 00:07:25 - INFO - __main__ - Loaded model is already a PeftModel. Continuing LoRA training without creating a new PEFT config. | |
| 2025-05-13 00:07:25 - WARNING - accelerate.utils.other - Detected kernel version 4.18.0, 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. | |
| 2025-05-13 00:07:51 - INFO - __main__ - *** Train *** | |
| 2025-05-13 00:27:26 - INFO - __main__ - *** Save model *** | |
| 2025-05-13 00:27:27 - INFO - __main__ - Model saved to data/paligemma2-3b-pt-224-sft-lora-iphone_gates_cotrain_0.1_magicsoup_no_insta_sub5 | |
| 2025-05-13 00:27:27 - INFO - __main__ - *** Evaluate *** | |
| 2025-05-13 00:28:33 - INFO - __main__ - *** Training complete *** | |