File size: 9,306 Bytes
df772d3 f70ff28 df772d3 f70ff28 df772d3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 |
2024-04-09 22:07:00,438 INFO MainThread:415 [wandb_setup.py:_flush():76] Current SDK version is 0.16.5
2024-04-09 22:07:00,438 INFO MainThread:415 [wandb_setup.py:_flush():76] Configure stats pid to 415
2024-04-09 22:07:00,439 INFO MainThread:415 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
2024-04-09 22:07:00,439 INFO MainThread:415 [wandb_setup.py:_flush():76] Loading settings from /kaggle/working/wandb/settings
2024-04-09 22:07:00,439 INFO MainThread:415 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
2024-04-09 22:07:00,439 INFO MainThread:415 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
2024-04-09 22:07:00,439 INFO MainThread:415 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
2024-04-09 22:07:00,439 INFO MainThread:415 [wandb_setup.py:_flush():76] Applying login settings: {}
2024-04-09 22:07:00,439 INFO MainThread:415 [wandb_init.py:_log_setup():527] Logging user logs to /kaggle/working/wandb/run-20240409_220700-9aom042n/logs/debug.log
2024-04-09 22:07:00,439 INFO MainThread:415 [wandb_init.py:_log_setup():528] Logging internal logs to /kaggle/working/wandb/run-20240409_220700-9aom042n/logs/debug-internal.log
2024-04-09 22:07:00,439 INFO MainThread:415 [wandb_init.py:_jupyter_setup():473] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7d36045756c0>
2024-04-09 22:07:00,439 INFO MainThread:415 [wandb_init.py:init():567] calling init triggers
2024-04-09 22:07:00,439 INFO MainThread:415 [wandb_init.py:init():574] wandb.init called with sweep_config: {}
config: {}
2024-04-09 22:07:00,439 INFO MainThread:415 [wandb_init.py:init():617] starting backend
2024-04-09 22:07:00,439 INFO MainThread:415 [wandb_init.py:init():621] setting up manager
2024-04-09 22:07:00,441 INFO MainThread:415 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
2024-04-09 22:07:00,442 INFO MainThread:415 [wandb_init.py:init():629] backend started and connected
2024-04-09 22:07:00,454 INFO MainThread:415 [wandb_run.py:_label_probe_notebook():1299] probe notebook
2024-04-09 22:07:00,766 INFO MainThread:415 [wandb_init.py:init():721] updated telemetry
2024-04-09 22:07:00,769 INFO MainThread:415 [wandb_init.py:init():754] communicating run to backend with 90.0 second timeout
2024-04-09 22:07:03,999 INFO MainThread:415 [wandb_run.py:_on_init():2344] communicating current version
2024-04-09 22:07:04,090 INFO MainThread:415 [wandb_run.py:_on_init():2353] got version response upgrade_message: "wandb version 0.16.6 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
2024-04-09 22:07:04,090 INFO MainThread:415 [wandb_init.py:init():805] starting run threads in backend
2024-04-09 22:07:20,151 INFO MainThread:415 [wandb_run.py:_console_start():2323] atexit reg
2024-04-09 22:07:20,151 INFO MainThread:415 [wandb_run.py:_redirect():2178] redirect: wrap_raw
2024-04-09 22:07:20,153 INFO MainThread:415 [wandb_run.py:_redirect():2243] Wrapping output streams.
2024-04-09 22:07:20,153 INFO MainThread:415 [wandb_run.py:_redirect():2268] Redirects installed.
2024-04-09 22:07:20,154 INFO MainThread:415 [wandb_init.py:init():848] run started, returning control to user process
2024-04-09 22:07:20,160 INFO MainThread:415 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 32000, 'max_position_embeddings': 2048, 'hidden_size': 2048, 'intermediate_size': 5632, 'num_hidden_layers': 22, 'num_attention_heads': 32, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'pretraining_tp': 1, 'use_cache': False, 'rope_theta': 10000.0, 'rope_scaling': None, 'attention_bias': False, 'attention_dropout': 0.0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['LlamaForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': None, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T', 'transformers_version': '4.39.3', 'model_type': 'llama', 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': False, 'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 1e-06, 'weight_decay': 0.001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.1, 'num_train_epochs': 5, 'max_steps': 200, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/Apr09_22-04-47_6e44b39f6877', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 100, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 100, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 8, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_32bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': True, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
|