diff --git "a/wandb/run-20240416_205309-xdytsc71/files/output.log" "b/wandb/run-20240416_205309-xdytsc71/files/output.log" new file mode 100644--- /dev/null +++ "b/wandb/run-20240416_205309-xdytsc71/files/output.log" @@ -0,0 +1,36074 @@ +04/16/2024 20:53:15 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, 16-bits training: False +04/16/2024 20:53:15 - INFO - __main__ - Training/evaluation parameters DistillationTrainingArguments( +_n_gpu=1, +accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'gradient_accumulation_kwargs': None}, +adafactor=False, +adam_beta1=0.9, +adam_beta2=0.999, +adam_epsilon=1e-08, +auto_find_batch_size=False, +bf16=False, +bf16_full_eval=False, +data_seed=None, +dataloader_drop_last=False, +dataloader_num_workers=4, +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=7200, +debug=[], +deepspeed=None, +disable_tqdm=False, +dispatch_batches=None, +do_eval=True, +do_predict=False, +do_train=True, +dtype=bfloat16, +eval_accumulation_steps=None, +eval_delay=0, +eval_steps=None, +evaluation_strategy=IntervalStrategy.EPOCH, +fp16=False, +fp16_backend=auto, +fp16_full_eval=False, +fp16_opt_level=O1, +freeze_lm_head=False, +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, +generation_config=None, +generation_max_length=None, +generation_num_beams=None, +gradient_accumulation_steps=1, +gradient_checkpointing=True, +gradient_checkpointing_kwargs=None, +greater_is_better=None, +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=, +ignore_data_skip=False, +include_inputs_for_metrics=False, +include_num_input_tokens_seen=False, +include_tokens_per_second=False, +jit_mode_eval=False, +kl_weight=1.0, +label_names=None, +label_smoothing_factor=0.0, +learning_rate=0.0003, +length_column_name=length, +load_best_model_at_end=False, +local_rank=0, +log_level=passive, +log_level_replica=warning, +log_on_each_node=True, +logging_dir=./runs/Apr16_20-53-02_ip-26-0-164-187, +logging_first_step=False, +logging_nan_inf_filter=True, +logging_steps=25, +logging_strategy=IntervalStrategy.STEPS, +lr_scheduler_kwargs={}, +lr_scheduler_type=SchedulerType.LINEAR, +max_grad_norm=1.0, +max_steps=50000, +metric_for_best_model=None, +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=./, +output_router_logits=True, +overwrite_output_dir=True, +past_index=-1, +per_device_eval_batch_size=8, +per_device_train_batch_size=8, +predict_with_generate=False, +prediction_loss_only=False, +push_to_hub=False, +push_to_hub_model_id=None, +push_to_hub_organization=None, +push_to_hub_token=, +ray_scope=last, +remove_unused_columns=True, +report_to=['wandb'], +resume_from_checkpoint=None, +run_name=./, +save_on_each_node=False, +save_only_model=False, +save_safetensors=True, +save_steps=500, +save_strategy=IntervalStrategy.EPOCH, +save_total_limit=1, +seed=42, +skip_memory_metrics=True, +sortish_sampler=False, +split_batches=None, +temperature=2.0, +tf32=None, +torch_compile=False, +torch_compile_backend=None, +torch_compile_mode=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, +) +Combining datasets...: 0%| | 0/8 [00:00