diff --git "a/training.log" "b/training.log" new file mode 100644--- /dev/null +++ "b/training.log" @@ -0,0 +1,2304 @@ +Setting ds_accelerator to cuda (auto detect) +[2023-06-12 07:26:44,544] [WARNING] [runner.py:196:fetch_hostfile] Unable to find hostfile, will proceed with training with local resources only. +Detected CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7: setting --include=localhost:0,1,2,3,4,5,6,7 +[2023-06-12 07:26:44,602] [INFO] [runner.py:555:main] cmd = /home/zhaiyuanzhao/anaconda3/envs/RLHF/bin/python -u -m deepspeed.launcher.launch --world_info=eyJsb2NhbGhvc3QiOiBbMCwgMSwgMiwgMywgNCwgNSwgNiwgN119 --master_addr=127.0.0.1 --master_port=29500 --enable_each_rank_log=None main.py --data_path /home/zhaiyuanzhao/llm/dataset/rm-static/data /home/zhaiyuanzhao/llm/dataset/full-hh-rlhf/data /home/zhaiyuanzhao/llm/dataset/synthetic-instruct-gptj-pairwise/data /home/zhaiyuanzhao/llm/dataset/rlhf-reward-datasets/data --data_split 2,4,4 --model_name_or_path /home/zhaiyuanzhao/llm/opt-350m --num_padding_at_beginning 1 --per_device_train_batch_size 4 --per_device_eval_batch_size 4 --max_seq_len 512 --learning_rate 5e-5 --weight_decay 0.1 --num_train_epochs 1 --disable_dropout --gradient_accumulation_steps 1 --lr_scheduler_type cosine --num_warmup_steps 0 --seed 1234 --zero_stage 0 --deepspeed --output_dir ./output +Setting ds_accelerator to cuda (auto detect) +[2023-06-12 07:26:46,974] [INFO] [launch.py:145:main] WORLD INFO DICT: {'localhost': [0, 1, 2, 3, 4, 5, 6, 7]} +[2023-06-12 07:26:46,974] [INFO] [launch.py:151:main] nnodes=1, num_local_procs=8, node_rank=0 +[2023-06-12 07:26:46,974] [INFO] [launch.py:162:main] global_rank_mapping=defaultdict(, {'localhost': [0, 1, 2, 3, 4, 5, 6, 7]}) +[2023-06-12 07:26:46,974] [INFO] [launch.py:163:main] dist_world_size=8 +[2023-06-12 07:26:46,974] [INFO] [launch.py:165:main] Setting CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 +Setting ds_accelerator to cuda (auto detect) +Setting ds_accelerator to cuda (auto detect) +Setting ds_accelerator to cuda (auto detect) +Setting ds_accelerator to cuda (auto detect) +Setting ds_accelerator to cuda (auto detect) +Setting ds_accelerator to cuda (auto detect) +Setting ds_accelerator to cuda (auto detect) +Setting ds_accelerator to cuda (auto detect) +[2023-06-12 07:26:51,092] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2023-06-12 07:26:51,093] [INFO] [comm.py:594:init_distributed] cdb=None +[2023-06-12 07:26:51,093] [INFO] [comm.py:625:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[2023-06-12 07:26:51,137] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2023-06-12 07:26:51,138] [INFO] [comm.py:594:init_distributed] cdb=None +[2023-06-12 07:26:51,228] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2023-06-12 07:26:51,229] [INFO] [comm.py:594:init_distributed] cdb=None +[2023-06-12 07:26:51,237] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2023-06-12 07:26:51,237] [INFO] [comm.py:594:init_distributed] cdb=None +[2023-06-12 07:26:51,268] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2023-06-12 07:26:51,268] [INFO] [comm.py:594:init_distributed] cdb=None +[2023-06-12 07:26:51,291] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2023-06-12 07:26:51,291] [INFO] [comm.py:594:init_distributed] cdb=None +[2023-06-12 07:26:51,301] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2023-06-12 07:26:51,301] [INFO] [comm.py:594:init_distributed] cdb=None +[2023-06-12 07:26:51,302] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2023-06-12 07:26:51,302] [INFO] [comm.py:594:init_distributed] cdb=None +model loaded +model loaded +model loaded +model loaded +model loaded +model loaded +model loaded +model loaded +Found cached dataset parquet (/home/zhaiyuanzhao/.cache/huggingface/datasets/parquet/default-d09980a08a1dbd7c/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec) + 0%| | 0/2 [00:00 +[2023-06-12 07:32:34,410] [INFO] [logging.py:96:log_dist] [Rank 0] step=0, skipped=0, lr=[5e-05, 5e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +Using /home/zhaiyuanzhao/.cache/torch_extensions/py39_cu117 as PyTorch extensions root... +[2023-06-12 07:32:34,410] [INFO] [config.py:960:print] DeepSpeedEngine configuration: +Using /home/zhaiyuanzhao/.cache/torch_extensions/py39_cu117 as PyTorch extensions root... +Using /home/zhaiyuanzhao/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...Using /home/zhaiyuanzhao/.cache/torch_extensions/py39_cu117 as PyTorch extensions root... + +Using /home/zhaiyuanzhao/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...[2023-06-12 07:32:34,411] [INFO] [config.py:964:print] activation_checkpointing_config { + "partition_activations": false, + "contiguous_memory_optimization": false, + "cpu_checkpointing": false, + "number_checkpoints": null, + "synchronize_checkpoint_boundary": false, + "profile": false +} + +[2023-06-12 07:32:34,411] [INFO] [config.py:964:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} +Using /home/zhaiyuanzhao/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...[2023-06-12 07:32:34,411] [INFO] [config.py:964:print] amp_enabled .................. False + +Using /home/zhaiyuanzhao/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...[2023-06-12 07:32:34,411] [INFO] [config.py:964:print] amp_params ................... False + +[2023-06-12 07:32:34,411] [INFO] [config.py:964:print] autotuning_config ............ { + "enabled": false, + "start_step": null, + "end_step": null, + "metric_path": null, + "arg_mappings": null, + "metric": "throughput", + "model_info": null, + "results_dir": "autotuning_results", + "exps_dir": "autotuning_exps", + "overwrite": true, + "fast": true, + "start_profile_step": 3, + "end_profile_step": 5, + "tuner_type": "gridsearch", + "tuner_early_stopping": 5, + "tuner_num_trials": 50, + "model_info_path": null, + "mp_size": 1, + "max_train_batch_size": null, + "min_train_batch_size": 1, + "max_train_micro_batch_size_per_gpu": 1.024000e+03, + "min_train_micro_batch_size_per_gpu": 1, + "num_tuning_micro_batch_sizes": 3 +} +[2023-06-12 07:32:34,411] [INFO] [config.py:964:print] bfloat16_enabled ............. False +[2023-06-12 07:32:34,411] [INFO] [config.py:964:print] checkpoint_parallel_write_pipeline False +[2023-06-12 07:32:34,411] [INFO] [config.py:964:print] checkpoint_tag_validation_enabled True +[2023-06-12 07:32:34,411] [INFO] [config.py:964:print] checkpoint_tag_validation_fail False +[2023-06-12 07:32:34,411] [INFO] [config.py:964:print] comms_config ................. +[2023-06-12 07:32:34,411] [INFO] [config.py:964:print] communication_data_type ...... None +[2023-06-12 07:32:34,411] [INFO] [config.py:964:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} +[2023-06-12 07:32:34,411] [INFO] [config.py:964:print] curriculum_enabled_legacy .... False +[2023-06-12 07:32:34,411] [INFO] [config.py:964:print] curriculum_params_legacy ..... False +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] data_efficiency_config ....... {'enabled': False, 'seed': 1234, 'data_sampling': {'enabled': False, 'num_epochs': 1000, 'num_workers': 0, 'curriculum_learning': {'enabled': False}}, 'data_routing': {'enabled': False, 'random_ltd': {'enabled': False, 'layer_token_lr_schedule': {'enabled': False}}}} +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] data_efficiency_enabled ...... False +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] dataloader_drop_last ......... False +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] disable_allgather ............ False +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] dump_state ................... False +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] dynamic_loss_scale_args ...... {'init_scale': 65536, 'scale_window': 100, 'delayed_shift': 2, 'consecutive_hysteresis': False, 'min_scale': 1} +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] eigenvalue_enabled ........... False +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] eigenvalue_gas_boundary_resolution 1 +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] eigenvalue_layer_name ........ bert.encoder.layer +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] eigenvalue_layer_num ......... 0 +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] eigenvalue_max_iter .......... 100 +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] eigenvalue_stability ......... 1e-06 +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] eigenvalue_tol ............... 0.01 +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] eigenvalue_verbose ........... False +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] elasticity_enabled ........... False +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] flops_profiler_config ........ { + "enabled": false, + "recompute_fwd_factor": 0.0, + "profile_step": 1, + "module_depth": -1, + "top_modules": 1, + "detailed": true, + "output_file": null +} +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] fp16_auto_cast ............... False +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] fp16_enabled ................. True +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] fp16_master_weights_and_gradients False +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] global_rank .................. 0 +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] grad_accum_dtype ............. None +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] gradient_accumulation_steps .. 1 +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] gradient_clipping ............ 1.0 +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] gradient_predivide_factor .... 1.0 +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] hybrid_engine ................ enabled=False max_out_tokens=512 inference_tp_size=1 release_inference_cache=False pin_parameters=True tp_gather_partition_size=8 +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] initial_dynamic_scale ........ 65536 +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] load_universal_checkpoint .... False +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] loss_scale ................... 0 +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] memory_breakdown ............. False +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] mics_hierarchial_params_gather False +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] mics_shard_size .............. -1 +[2023-06-12 07:32:34,412] [INFO] [config.py:964:print] monitor_config ............... tensorboard=TensorBoardConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') wandb=WandbConfig(enabled=False, group=None, team=None, project='deepspeed') csv_monitor=CSVConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') enabled=False +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] nebula_config ................ { + "enabled": false, + "persistent_storage_path": null, + "persistent_time_interval": 100, + "num_of_version_in_retention": 2, + "enable_nebula_load": true, + "load_path": null +} +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] optimizer_legacy_fusion ...... False +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] optimizer_name ............... None +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] optimizer_params ............. None +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] pld_enabled .................. False +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] pld_params ................... False +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] prescale_gradients ........... False +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] scheduler_name ............... None +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] scheduler_params ............. None +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] sparse_attention ............. None +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] sparse_gradients_enabled ..... False +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] steps_per_print .............. 10 +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] train_batch_size ............. 32 +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] train_micro_batch_size_per_gpu 4 +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] use_node_local_storage ....... False +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] wall_clock_breakdown ......... False +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] world_size ................... 8 +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] zero_allow_untested_optimizer False +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] zero_config .................. stage=0 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500,000,000 allgather_partitions=True allgather_bucket_size=500,000,000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=DeepSpeedZeroOffloadParamConfig(device='none', nvme_path=None, buffer_count=5, buffer_size=100,000,000, max_in_cpu=1,000,000,000, pin_memory=False) offload_optimizer=DeepSpeedZeroOffloadOptimizerConfig(device='none', nvme_path=None, buffer_count=4, pin_memory=False, pipeline=False, pipeline_read=False, pipeline_write=False, fast_init=False) sub_group_size=1,000,000,000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=30000000 param_persistence_threshold=10000 model_persistence_threshold=sys.maxsize max_live_parameters=30000000 max_reuse_distance=1,000,000,000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False mics_shard_size=-1 mics_hierarchical_params_gather=False memory_efficient_linear=False +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] zero_enabled ................. False +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] zero_force_ds_cpu_optimizer .. True +[2023-06-12 07:32:34,413] [INFO] [config.py:964:print] zero_optimization_stage ...... 0 +[2023-06-12 07:32:34,413] [INFO] [config.py:950:print_user_config] json = { + "train_batch_size": 32, + "train_micro_batch_size_per_gpu": 4, + "steps_per_print": 10, + "zero_optimization": { + "stage": 0, + "offload_param": { + "device": "none" + }, + "offload_optimizer": { + "device": "none" + }, + "stage3_param_persistence_threshold": 1.000000e+04, + "stage3_max_live_parameters": 3.000000e+07, + "stage3_prefetch_bucket_size": 3.000000e+07, + "memory_efficient_linear": false + }, + "fp16": { + "enabled": true, + "loss_scale_window": 100 + }, + "gradient_clipping": 1.0, + "prescale_gradients": false, + "wall_clock_breakdown": false, + "hybrid_engine": { + "enabled": false, + "max_out_tokens": 512, + "inference_tp_size": 1, + "release_inference_cache": false, + "pin_parameters": true, + "tp_gather_partition_size": 8 + } +} +Using /home/zhaiyuanzhao/.cache/torch_extensions/py39_cu117 as PyTorch extensions root... +Emitting ninja build file /home/zhaiyuanzhao/.cache/torch_extensions/py39_cu117/utils/build.ninja... +Building extension module utils... +Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +ninja: no work to do. +Loading extension module utils... +Time to load utils op: 1.7743585109710693 seconds +Loading extension module utils... +Loading extension module utils... +Loading extension module utils... +Loading extension module utils... +Loading extension module utils... +Loading extension module utils... +Loading extension module utils... +Time to load utils op: 1.8262453079223633 seconds +Time to load utils op: 1.8265697956085205 seconds +Time to load utils op: 1.8265929222106934 seconds +Time to load utils op: 1.8270368576049805 secondsTime to load utils op: 1.8266544342041016 seconds + +Time to load utils op: 1.82395339012146 secondsTime to load utils op: 1.8270204067230225 seconds + +***** Running training ***** +***** Evaluating reward, Epoch 0/1 ***** +chosen_last_scores (higher is better) : 2.576474905014038, acc (higher is better) : 0.4899999797344208 +Beginning of Epoch 1/1, Total Micro Batches 3680 +[2023-06-12 07:32:42,955] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 0 +[2023-06-12 07:32:42,955] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 0 +[2023-06-12 07:32:42,955] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 0 +[2023-06-12 07:32:42,955] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 0 +[2023-06-12 07:32:42,956] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 65536 to 32768.0 +[2023-06-12 07:32:42,956] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 65536 to 32768.0 +[2023-06-12 07:32:42,956] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 65536 to 32768.0 +[2023-06-12 07:32:42,956] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 65536 to 32768.0 +[2023-06-12 07:32:42,955] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 0 +[2023-06-12 07:32:42,956] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 65536, reducing to 32768.0 +[2023-06-12 07:32:42,955] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 0 +[2023-06-12 07:32:42,956] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 0 +[2023-06-12 07:32:42,956] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 65536 to 32768.0 +[2023-06-12 07:32:42,956] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 65536 to 32768.0 +[2023-06-12 07:32:42,955] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 0 +[2023-06-12 07:32:42,957] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 65536 to 32768.0 +[2023-06-12 07:32:42,957] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 65536 to 32768.0 +[2023-06-12 07:32:43,187] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1 +[2023-06-12 07:32:43,187] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:32:43,187] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1 +[2023-06-12 07:32:43,187] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1 +[2023-06-12 07:32:43,187] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:32:43,187] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:32:43,187] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1 +[2023-06-12 07:32:43,187] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1 +[2023-06-12 07:32:43,187] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 32768.0, reducing to 16384.0 +[2023-06-12 07:32:43,187] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1 +[2023-06-12 07:32:43,187] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:32:43,187] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:32:43,187] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:32:43,187] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1 +[2023-06-12 07:32:43,187] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1 +[2023-06-12 07:32:43,187] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:32:43,188] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:32:43,403] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2 +[2023-06-12 07:32:43,404] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2 +[2023-06-12 07:32:43,404] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:32:43,404] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2 +[2023-06-12 07:32:43,404] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:32:43,404] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2 +[2023-06-12 07:32:43,404] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:32:43,404] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:32:43,404] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2 +[2023-06-12 07:32:43,404] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 16384.0, reducing to 8192.0 +[2023-06-12 07:32:43,404] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:32:43,404] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2 +[2023-06-12 07:32:43,404] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2 +[2023-06-12 07:32:43,404] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:32:43,404] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:32:43,404] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2 +[2023-06-12 07:32:43,404] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:32:43,620] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 8192.0, reducing to 4096.0 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:32:43,620] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:32:43,835] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 4 +[2023-06-12 07:32:43,835] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 4 +[2023-06-12 07:32:43,835] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 4 +[2023-06-12 07:32:43,836] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:32:43,836] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:32:43,835] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 4 +[2023-06-12 07:32:43,836] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:32:43,836] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 4096.0, reducing to 2048.0 +[2023-06-12 07:32:43,835] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 4 +[2023-06-12 07:32:43,836] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:32:43,835] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 4 +[2023-06-12 07:32:43,836] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:32:43,835] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 4 +[2023-06-12 07:32:43,836] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:32:43,835] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 4 +[2023-06-12 07:32:43,836] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:32:43,836] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:32:44,052] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 5 +[2023-06-12 07:32:44,052] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 5 +[2023-06-12 07:32:44,052] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 2048.0 to 1024.0 +[2023-06-12 07:32:44,052] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 5 +[2023-06-12 07:32:44,053] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 2048.0 to 1024.0 +[2023-06-12 07:32:44,053] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 5 +[2023-06-12 07:32:44,053] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 2048.0 to 1024.0 +[2023-06-12 07:32:44,053] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 5 +[2023-06-12 07:32:44,053] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 2048.0, reducing to 1024.0 +[2023-06-12 07:32:44,053] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 5 +[2023-06-12 07:32:44,053] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 2048.0 to 1024.0 +[2023-06-12 07:32:44,053] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 2048.0 to 1024.0 +[2023-06-12 07:32:44,053] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 5 +[2023-06-12 07:32:44,053] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 2048.0 to 1024.0 +[2023-06-12 07:32:44,053] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 2048.0 to 1024.0 +[2023-06-12 07:32:44,053] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 5 +[2023-06-12 07:32:44,053] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 2048.0 to 1024.0 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 6 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 6 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 6 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 6 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 6 +[2023-06-12 07:32:44,269] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 1024.0, reducing to 512.0 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 6 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 6 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 6 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:32:44,269] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:32:45,018] [INFO] [logging.py:96:log_dist] [Rank 0] step=10, skipped=7, lr=[4.999991801084829e-05, 4.999991801084829e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:32:45,027] [INFO] [timer.py:215:stop] epoch=0/micro_step=10/global_step=10, RunningAvgSamplesPerSec=139.45916111120349, CurrSamplesPerSec=128.15631859921302, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:32:47,514] [INFO] [logging.py:96:log_dist] [Rank 0] step=20, skipped=7, lr=[4.999846044088921e-05, 4.999846044088921e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:32:47,524] [INFO] [timer.py:215:stop] epoch=0/micro_step=20/global_step=20, RunningAvgSamplesPerSec=133.08776115147245, CurrSamplesPerSec=128.86802949171062, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:32:50,006] [INFO] [logging.py:96:log_dist] [Rank 0] step=30, skipped=7, lr=[4.9995181012051625e-05, 4.9995181012051625e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:32:50,015] [INFO] [timer.py:215:stop] epoch=0/micro_step=30/global_step=30, RunningAvgSamplesPerSec=131.49171226334505, CurrSamplesPerSec=128.62005460359686, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:32:52,496] [INFO] [logging.py:96:log_dist] [Rank 0] step=40, skipped=7, lr=[4.9990079963336504e-05, 4.9990079963336504e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:32:52,505] [INFO] [timer.py:215:stop] epoch=0/micro_step=40/global_step=40, RunningAvgSamplesPerSec=130.75525989930847, CurrSamplesPerSec=128.66518206786145, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:32:54,989] [INFO] [logging.py:96:log_dist] [Rank 0] step=50, skipped=7, lr=[4.998315766650239e-05, 4.998315766650239e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:32:54,998] [INFO] [timer.py:215:stop] epoch=0/micro_step=50/global_step=50, RunningAvgSamplesPerSec=130.30280993651792, CurrSamplesPerSec=128.76022582826883, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:32:57,476] [INFO] [logging.py:96:log_dist] [Rank 0] step=60, skipped=7, lr=[4.997441462603825e-05, 4.997441462603825e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:32:57,485] [INFO] [timer.py:215:stop] epoch=0/micro_step=60/global_step=60, RunningAvgSamplesPerSec=130.0584389411792, CurrSamplesPerSec=128.32271098027707, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:32:59,969] [INFO] [logging.py:96:log_dist] [Rank 0] step=70, skipped=7, lr=[4.996385147912677e-05, 4.996385147912677e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:32:59,978] [INFO] [timer.py:215:stop] epoch=0/micro_step=70/global_step=70, RunningAvgSamplesPerSec=129.84299111248677, CurrSamplesPerSec=128.00317390682372, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:02,463] [INFO] [logging.py:96:log_dist] [Rank 0] step=80, skipped=7, lr=[4.995146899559788e-05, 4.995146899559788e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:02,472] [INFO] [timer.py:215:stop] epoch=0/micro_step=80/global_step=80, RunningAvgSamplesPerSec=129.66959360325677, CurrSamplesPerSec=128.52410993009673, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:04,960] [INFO] [logging.py:96:log_dist] [Rank 0] step=90, skipped=7, lr=[4.993726807787265e-05, 4.993726807787265e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:04,969] [INFO] [timer.py:215:stop] epoch=0/micro_step=90/global_step=90, RunningAvgSamplesPerSec=129.5227164533939, CurrSamplesPerSec=127.3706632553805, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:07,458] [INFO] [logging.py:96:log_dist] [Rank 0] step=100, skipped=7, lr=[4.9921249760897536e-05, 4.9921249760897536e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:07,467] [INFO] [timer.py:215:stop] epoch=0/micro_step=100/global_step=100, RunningAvgSamplesPerSec=129.40289835578912, CurrSamplesPerSec=128.923113571832, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:09,442] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:09,443] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:09,442] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:09,443] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:09,443] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:09,442] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:09,443] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:09,443] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:09,442] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:09,443] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:09,443] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:09,443] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:09,443] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:09,442] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:09,443] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:09,443] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:09,954] [INFO] [logging.py:96:log_dist] [Rank 0] step=110, skipped=7, lr=[4.990341521206896e-05, 4.990341521206896e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:09,963] [INFO] [timer.py:215:stop] epoch=0/micro_step=110/global_step=110, RunningAvgSamplesPerSec=129.3134761036645, CurrSamplesPerSec=129.07052455141417, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:12,450] [INFO] [logging.py:96:log_dist] [Rank 0] step=120, skipped=7, lr=[4.9883765731148184e-05, 4.9883765731148184e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:12,459] [INFO] [timer.py:215:stop] epoch=0/micro_step=120/global_step=120, RunningAvgSamplesPerSec=129.23928190718652, CurrSamplesPerSec=128.01355123919254, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:14,952] [INFO] [logging.py:96:log_dist] [Rank 0] step=130, skipped=7, lr=[4.986230275016667e-05, 4.986230275016667e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:14,961] [INFO] [timer.py:215:stop] epoch=0/micro_step=130/global_step=130, RunningAvgSamplesPerSec=129.153005016377, CurrSamplesPerSec=126.98083618419061, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:17,456] [INFO] [logging.py:96:log_dist] [Rank 0] step=140, skipped=7, lr=[4.983902783332164e-05, 4.983902783332164e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:17,465] [INFO] [timer.py:215:stop] epoch=0/micro_step=140/global_step=140, RunningAvgSamplesPerSec=129.06913315521484, CurrSamplesPerSec=127.52023760095999, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:19,962] [INFO] [logging.py:96:log_dist] [Rank 0] step=150, skipped=7, lr=[4.98139426768621e-05, 4.98139426768621e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:19,971] [INFO] [timer.py:215:stop] epoch=0/micro_step=150/global_step=150, RunningAvgSamplesPerSec=128.99316406920303, CurrSamplesPerSec=128.62523155712765, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:20,939] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 153 +[2023-06-12 07:33:20,939] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 153 +[2023-06-12 07:33:20,939] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 153 +[2023-06-12 07:33:20,940] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:33:20,940] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:33:20,939] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 153 +[2023-06-12 07:33:20,940] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:33:20,940] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 1024.0, reducing to 512.0 +[2023-06-12 07:33:20,939] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 153 +[2023-06-12 07:33:20,940] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:33:20,939] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 153 +[2023-06-12 07:33:20,940] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:33:20,939] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 153 +[2023-06-12 07:33:20,940] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:33:20,939] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 153 +[2023-06-12 07:33:20,940] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:33:20,940] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 1024.0 to 512.0 +[2023-06-12 07:33:22,431] [INFO] [logging.py:96:log_dist] [Rank 0] step=160, skipped=8, lr=[4.978981978944271e-05, 4.978981978944271e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:22,440] [INFO] [timer.py:215:stop] epoch=0/micro_step=160/global_step=160, RunningAvgSamplesPerSec=129.0466569387555, CurrSamplesPerSec=128.65728864217388, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:24,935] [INFO] [logging.py:96:log_dist] [Rank 0] step=170, skipped=8, lr=[4.9761300323275173e-05, 4.9761300323275173e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:24,944] [INFO] [timer.py:215:stop] epoch=0/micro_step=170/global_step=170, RunningAvgSamplesPerSec=128.98792191920867, CurrSamplesPerSec=127.31713906279643, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:27,437] [INFO] [logging.py:96:log_dist] [Rank 0] step=180, skipped=8, lr=[4.973097628218415e-05, 4.973097628218415e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:27,446] [INFO] [timer.py:215:stop] epoch=0/micro_step=180/global_step=180, RunningAvgSamplesPerSec=128.93962083991278, CurrSamplesPerSec=127.7033259372871, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:29,941] [INFO] [logging.py:96:log_dist] [Rank 0] step=190, skipped=8, lr=[4.9698849876150674e-05, 4.9698849876150674e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:29,950] [INFO] [timer.py:215:stop] epoch=0/micro_step=190/global_step=190, RunningAvgSamplesPerSec=128.89003113944034, CurrSamplesPerSec=127.6620275607028, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:32,445] [INFO] [logging.py:96:log_dist] [Rank 0] step=200, skipped=8, lr=[4.966492344651005e-05, 4.966492344651005e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:32,454] [INFO] [timer.py:215:stop] epoch=0/micro_step=200/global_step=200, RunningAvgSamplesPerSec=128.84730591363484, CurrSamplesPerSec=128.1066561802343, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:34,948] [INFO] [logging.py:96:log_dist] [Rank 0] step=210, skipped=8, lr=[4.962919946578123e-05, 4.962919946578123e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:34,957] [INFO] [timer.py:215:stop] epoch=0/micro_step=210/global_step=210, RunningAvgSamplesPerSec=128.8093961189123, CurrSamplesPerSec=128.07291749166728, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:37,446] [INFO] [logging.py:96:log_dist] [Rank 0] step=220, skipped=8, lr=[4.95916805374866e-05, 4.95916805374866e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:37,455] [INFO] [timer.py:215:stop] epoch=0/micro_step=220/global_step=220, RunningAvgSamplesPerSec=128.78839050454786, CurrSamplesPerSec=128.18385746156903, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:39,943] [INFO] [logging.py:96:log_dist] [Rank 0] step=230, skipped=8, lr=[4.955236939596225e-05, 4.955236939596225e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:39,952] [INFO] [timer.py:215:stop] epoch=0/micro_step=230/global_step=230, RunningAvgSamplesPerSec=128.77077558798177, CurrSamplesPerSec=128.37364613342208, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:42,440] [INFO] [logging.py:96:log_dist] [Rank 0] step=240, skipped=8, lr=[4.95112689061587e-05, 4.95112689061587e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:42,449] [INFO] [timer.py:215:stop] epoch=0/micro_step=240/global_step=240, RunningAvgSamplesPerSec=128.75464099241177, CurrSamplesPerSec=128.27463584659156, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:44,938] [INFO] [logging.py:96:log_dist] [Rank 0] step=250, skipped=8, lr=[4.946838206343211e-05, 4.946838206343211e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:44,947] [INFO] [timer.py:215:stop] epoch=0/micro_step=250/global_step=250, RunningAvgSamplesPerSec=128.73673254242163, CurrSamplesPerSec=128.1510569633548, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:46,175] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:46,176] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:46,176] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:46,176] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:46,176] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:46,176] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:46,176] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:46,175] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:46,176] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:46,176] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:46,176] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:46,176] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:46,176] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:46,176] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:33:46,176] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:46,176] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 512.0 to 1024.0 +[2023-06-12 07:33:47,439] [INFO] [logging.py:96:log_dist] [Rank 0] step=260, skipped=8, lr=[4.9423711993325955e-05, 4.9423711993325955e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:47,448] [INFO] [timer.py:215:stop] epoch=0/micro_step=260/global_step=260, RunningAvgSamplesPerSec=128.7151608599872, CurrSamplesPerSec=127.82080785032275, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:49,938] [INFO] [logging.py:96:log_dist] [Rank 0] step=270, skipped=8, lr=[4.9377261951343265e-05, 4.9377261951343265e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:49,947] [INFO] [timer.py:215:stop] epoch=0/micro_step=270/global_step=270, RunningAvgSamplesPerSec=128.6987933502108, CurrSamplesPerSec=128.839453838947, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:52,437] [INFO] [logging.py:96:log_dist] [Rank 0] step=280, skipped=8, lr=[4.9329035322709386e-05, 4.9329035322709386e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:52,447] [INFO] [timer.py:215:stop] epoch=0/micro_step=280/global_step=280, RunningAvgSamplesPerSec=128.6829715578517, CurrSamplesPerSec=127.99377471684403, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:54,944] [INFO] [logging.py:96:log_dist] [Rank 0] step=290, skipped=8, lr=[4.927903562212521e-05, 4.927903562212521e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:54,953] [INFO] [timer.py:215:stop] epoch=0/micro_step=290/global_step=290, RunningAvgSamplesPerSec=128.65557921272662, CurrSamplesPerSec=127.4600510152723, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:57,450] [INFO] [logging.py:96:log_dist] [Rank 0] step=300, skipped=8, lr=[4.922726649351108e-05, 4.922726649351108e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:57,459] [INFO] [timer.py:215:stop] epoch=0/micro_step=300/global_step=300, RunningAvgSamplesPerSec=128.6298066168354, CurrSamplesPerSec=127.62633814040086, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:33:59,954] [INFO] [logging.py:96:log_dist] [Rank 0] step=310, skipped=8, lr=[4.917373170974119e-05, 4.917373170974119e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:33:59,963] [INFO] [timer.py:215:stop] epoch=0/micro_step=310/global_step=310, RunningAvgSamplesPerSec=128.6110159438476, CurrSamplesPerSec=128.21336777378585, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:02,459] [INFO] [logging.py:96:log_dist] [Rank 0] step=320, skipped=8, lr=[4.9118435172368673e-05, 4.9118435172368673e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:02,468] [INFO] [timer.py:215:stop] epoch=0/micro_step=320/global_step=320, RunningAvgSamplesPerSec=128.59017355702366, CurrSamplesPerSec=128.34504382949385, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:04,965] [INFO] [logging.py:96:log_dist] [Rank 0] step=330, skipped=8, lr=[4.906138091134118e-05, 4.906138091134118e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:04,974] [INFO] [timer.py:215:stop] epoch=0/micro_step=330/global_step=330, RunningAvgSamplesPerSec=128.57031005727694, CurrSamplesPerSec=127.65025027366995, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:07,472] [INFO] [logging.py:96:log_dist] [Rank 0] step=340, skipped=8, lr=[4.900257308470728e-05, 4.900257308470728e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:07,481] [INFO] [timer.py:215:stop] epoch=0/micro_step=340/global_step=340, RunningAvgSamplesPerSec=128.54944919086356, CurrSamplesPerSec=127.49334642928046, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:09,973] [INFO] [logging.py:96:log_dist] [Rank 0] step=350, skipped=8, lr=[4.894201597831334e-05, 4.894201597831334e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:09,983] [INFO] [timer.py:215:stop] epoch=0/micro_step=350/global_step=350, RunningAvgSamplesPerSec=128.53784489123402, CurrSamplesPerSec=128.61376886309714, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:11,210] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:11,211] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:11,212] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 1024.0 to 2048.0 +[2023-06-12 07:34:11,211] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:11,212] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 1024.0 to 2048.0 +[2023-06-12 07:34:11,211] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:11,212] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 1024.0 to 2048.0 +[2023-06-12 07:34:11,212] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:11,212] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 1024.0 to 2048.0 +[2023-06-12 07:34:11,212] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 1024.0 to 2048.0 +[2023-06-12 07:34:11,212] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:11,212] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:11,212] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 1024.0 to 2048.0 +[2023-06-12 07:34:11,212] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 1024.0 to 2048.0 +[2023-06-12 07:34:11,212] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:11,212] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 1024.0 to 2048.0 +[2023-06-12 07:34:12,474] [INFO] [logging.py:96:log_dist] [Rank 0] step=360, skipped=8, lr=[4.88797140054912e-05, 4.88797140054912e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:12,483] [INFO] [timer.py:215:stop] epoch=0/micro_step=360/global_step=360, RunningAvgSamplesPerSec=128.5282209420601, CurrSamplesPerSec=128.1801849294529, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:14,976] [INFO] [logging.py:96:log_dist] [Rank 0] step=370, skipped=8, lr=[4.88156717067366e-05, 4.88156717067366e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:14,986] [INFO] [timer.py:215:stop] epoch=0/micro_step=370/global_step=370, RunningAvgSamplesPerSec=128.5168424032244, CurrSamplesPerSec=127.65110010823231, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:17,481] [INFO] [logging.py:96:log_dist] [Rank 0] step=380, skipped=8, lr=[4.874989374937817e-05, 4.874989374937817e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:17,490] [INFO] [timer.py:215:stop] epoch=0/micro_step=380/global_step=380, RunningAvgSamplesPerSec=128.502842177046, CurrSamplesPerSec=128.73219184126023, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:19,986] [INFO] [logging.py:96:log_dist] [Rank 0] step=390, skipped=8, lr=[4.8682384927237355e-05, 4.8682384927237355e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:19,995] [INFO] [timer.py:215:stop] epoch=0/micro_step=390/global_step=390, RunningAvgSamplesPerSec=128.4893315147837, CurrSamplesPerSec=128.33682149195275, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:22,493] [INFO] [logging.py:96:log_dist] [Rank 0] step=400, skipped=8, lr=[4.861315016027902e-05, 4.861315016027902e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:22,503] [INFO] [timer.py:215:stop] epoch=0/micro_step=400/global_step=400, RunningAvgSamplesPerSec=128.4729178346795, CurrSamplesPerSec=127.45932476372808, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:25,001] [INFO] [logging.py:96:log_dist] [Rank 0] step=410, skipped=8, lr=[4.854219449425288e-05, 4.854219449425288e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:25,010] [INFO] [timer.py:215:stop] epoch=0/micro_step=410/global_step=410, RunningAvgSamplesPerSec=128.45682658711848, CurrSamplesPerSec=128.3436938211917, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:27,509] [INFO] [logging.py:96:log_dist] [Rank 0] step=420, skipped=8, lr=[4.84695231003258e-05, 4.84695231003258e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:27,518] [INFO] [timer.py:215:stop] epoch=0/micro_step=420/global_step=420, RunningAvgSamplesPerSec=128.44162868085314, CurrSamplesPerSec=128.25183728501304, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:30,011] [INFO] [logging.py:96:log_dist] [Rank 0] step=430, skipped=8, lr=[4.83951412747049e-05, 4.83951412747049e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:30,020] [INFO] [timer.py:215:stop] epoch=0/micro_step=430/global_step=430, RunningAvgSamplesPerSec=128.43448259167772, CurrSamplesPerSec=128.02905933010155, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:32,518] [INFO] [logging.py:96:log_dist] [Rank 0] step=440, skipped=8, lr=[4.831905443825159e-05, 4.831905443825159e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:32,527] [INFO] [timer.py:215:stop] epoch=0/micro_step=440/global_step=440, RunningAvgSamplesPerSec=128.4210509777968, CurrSamplesPerSec=127.48486958272741, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:35,022] [INFO] [logging.py:96:log_dist] [Rank 0] step=450, skipped=8, lr=[4.824126813608649e-05, 4.824126813608649e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:35,032] [INFO] [timer.py:215:stop] epoch=0/micro_step=450/global_step=450, RunningAvgSamplesPerSec=128.41147064387533, CurrSamplesPerSec=128.35289898660506, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:36,265] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:36,266] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:36,266] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:36,266] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:34:36,266] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:34:36,265] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:36,266] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:34:36,265] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:36,266] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:34:36,265] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:36,266] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:34:36,266] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:36,266] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:34:36,266] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:34:36,266] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:34:36,266] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:34:37,529] [INFO] [logging.py:96:log_dist] [Rank 0] step=460, skipped=8, lr=[4.8161788037185327e-05, 4.8161788037185327e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:37,538] [INFO] [timer.py:215:stop] epoch=0/micro_step=460/global_step=460, RunningAvgSamplesPerSec=128.39982672043462, CurrSamplesPerSec=128.5660911970681, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:40,035] [INFO] [logging.py:96:log_dist] [Rank 0] step=470, skipped=8, lr=[4.808061993396574e-05, 4.808061993396574e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:40,044] [INFO] [timer.py:215:stop] epoch=0/micro_step=470/global_step=470, RunningAvgSamplesPerSec=128.3898396634247, CurrSamplesPerSec=128.38248719214272, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:42,538] [INFO] [logging.py:96:log_dist] [Rank 0] step=480, skipped=8, lr=[4.7997769741865226e-05, 4.7997769741865226e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:42,548] [INFO] [timer.py:215:stop] epoch=0/micro_step=480/global_step=480, RunningAvgSamplesPerSec=128.38231635005965, CurrSamplesPerSec=128.10751210274736, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:45,043] [INFO] [logging.py:96:log_dist] [Rank 0] step=490, skipped=8, lr=[4.791324349890993e-05, 4.791324349890993e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:45,052] [INFO] [timer.py:215:stop] epoch=0/micro_step=490/global_step=490, RunningAvgSamplesPerSec=128.3740816659432, CurrSamplesPerSec=128.71256296924253, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:47,545] [INFO] [logging.py:96:log_dist] [Rank 0] step=500, skipped=8, lr=[4.782704736527466e-05, 4.782704736527466e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:47,554] [INFO] [timer.py:215:stop] epoch=0/micro_step=500/global_step=500, RunningAvgSamplesPerSec=128.3689129590794, CurrSamplesPerSec=128.39808480616077, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:50,053] [INFO] [logging.py:96:log_dist] [Rank 0] step=510, skipped=8, lr=[4.7739187622833914e-05, 4.7739187622833914e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:50,062] [INFO] [timer.py:215:stop] epoch=0/micro_step=510/global_step=510, RunningAvgSamplesPerSec=128.358240762381, CurrSamplesPerSec=127.65571369330914, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:52,559] [INFO] [logging.py:96:log_dist] [Rank 0] step=520, skipped=8, lr=[4.76496706747041e-05, 4.76496706747041e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:52,568] [INFO] [timer.py:215:stop] epoch=0/micro_step=520/global_step=520, RunningAvgSamplesPerSec=128.34929447986508, CurrSamplesPerSec=126.91059658067451, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:54,540] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 527 +[2023-06-12 07:34:54,540] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 527 +[2023-06-12 07:34:54,541] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:34:54,540] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 527 +[2023-06-12 07:34:54,541] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:34:54,540] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 527 +[2023-06-12 07:34:54,540] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 527 +[2023-06-12 07:34:54,541] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:34:54,540] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 527 +[2023-06-12 07:34:54,541] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:34:54,541] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:34:54,540] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 527 +[2023-06-12 07:34:54,541] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:34:54,541] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 4096.0, reducing to 2048.0 +[2023-06-12 07:34:54,540] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 527 +[2023-06-12 07:34:54,541] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:34:54,541] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 4096.0 to 2048.0 +[2023-06-12 07:34:55,032] [INFO] [logging.py:96:log_dist] [Rank 0] step=530, skipped=9, lr=[4.756769390003164e-05, 4.756769390003164e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:55,041] [INFO] [timer.py:215:stop] epoch=0/micro_step=530/global_step=530, RunningAvgSamplesPerSec=128.3737817075941, CurrSamplesPerSec=128.51980255377825, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:34:57,536] [INFO] [logging.py:96:log_dist] [Rank 0] step=540, skipped=9, lr=[4.7475046333851735e-05, 4.7475046333851735e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:34:57,546] [INFO] [timer.py:215:stop] epoch=0/micro_step=540/global_step=540, RunningAvgSamplesPerSec=128.3665334982638, CurrSamplesPerSec=127.20672912431347, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:00,037] [INFO] [logging.py:96:log_dist] [Rank 0] step=550, skipped=9, lr=[4.738076081229433e-05, 4.738076081229433e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:00,047] [INFO] [timer.py:215:stop] epoch=0/micro_step=550/global_step=550, RunningAvgSamplesPerSec=128.36303470660093, CurrSamplesPerSec=128.1854489575086, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:02,546] [INFO] [logging.py:96:log_dist] [Rank 0] step=560, skipped=9, lr=[4.728484420677918e-05, 4.728484420677918e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:02,555] [INFO] [timer.py:215:stop] epoch=0/micro_step=560/global_step=560, RunningAvgSamplesPerSec=128.352690453546, CurrSamplesPerSec=127.53926208042084, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:05,052] [INFO] [logging.py:96:log_dist] [Rank 0] step=570, skipped=9, lr=[4.718730350759753e-05, 4.718730350759753e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:05,061] [INFO] [timer.py:215:stop] epoch=0/micro_step=570/global_step=570, RunningAvgSamplesPerSec=128.34481997852183, CurrSamplesPerSec=128.06986232876974, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:07,561] [INFO] [logging.py:96:log_dist] [Rank 0] step=580, skipped=9, lr=[4.7088145823402683e-05, 4.7088145823402683e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:07,570] [INFO] [timer.py:215:stop] epoch=0/micro_step=580/global_step=580, RunningAvgSamplesPerSec=128.33496935018465, CurrSamplesPerSec=126.01858106046309, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:10,069] [INFO] [logging.py:96:log_dist] [Rank 0] step=590, skipped=9, lr=[4.698737838069198e-05, 4.698737838069198e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:10,080] [INFO] [timer.py:215:stop] epoch=0/micro_step=590/global_step=590, RunningAvgSamplesPerSec=128.3248254812987, CurrSamplesPerSec=127.2321727853909, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:12,574] [INFO] [logging.py:96:log_dist] [Rank 0] step=600, skipped=9, lr=[4.6885008523280066e-05, 4.6885008523280066e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:12,583] [INFO] [timer.py:215:stop] epoch=0/micro_step=600/global_step=600, RunningAvgSamplesPerSec=128.3202640650528, CurrSamplesPerSec=127.35748947209608, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:15,080] [INFO] [logging.py:96:log_dist] [Rank 0] step=610, skipped=9, lr=[4.678104371176373e-05, 4.678104371176373e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:15,089] [INFO] [timer.py:215:stop] epoch=0/micro_step=610/global_step=610, RunningAvgSamplesPerSec=128.31383356351878, CurrSamplesPerSec=128.36185994912108, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:17,587] [INFO] [logging.py:96:log_dist] [Rank 0] step=620, skipped=9, lr=[4.667549152297817e-05, 4.667549152297817e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:17,597] [INFO] [timer.py:215:stop] epoch=0/micro_step=620/global_step=620, RunningAvgSamplesPerSec=128.30616372284862, CurrSamplesPerSec=128.1126478780208, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:19,828] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:19,829] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:19,830] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:19,830] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:19,830] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:35:19,830] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:35:19,830] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:19,830] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:35:19,830] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:35:19,829] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:19,830] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:35:19,829] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:19,830] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:19,830] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:35:19,830] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:35:19,830] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 2048.0 to 4096.0 +[2023-06-12 07:35:20,092] [INFO] [logging.py:96:log_dist] [Rank 0] step=630, skipped=9, lr=[4.65683596494448e-05, 4.65683596494448e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:20,101] [INFO] [timer.py:215:stop] epoch=0/micro_step=630/global_step=630, RunningAvgSamplesPerSec=128.30143717198132, CurrSamplesPerSec=127.93533541891858, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:22,594] [INFO] [logging.py:96:log_dist] [Rank 0] step=640, skipped=9, lr=[4.645965589881063e-05, 4.645965589881063e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:22,603] [INFO] [timer.py:215:stop] epoch=0/micro_step=640/global_step=640, RunningAvgSamplesPerSec=128.2985768333149, CurrSamplesPerSec=127.84126155610461, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:25,098] [INFO] [logging.py:96:log_dist] [Rank 0] step=650, skipped=9, lr=[4.634938819327925e-05, 4.634938819327925e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:25,108] [INFO] [timer.py:215:stop] epoch=0/micro_step=650/global_step=650, RunningAvgSamplesPerSec=128.29372997520036, CurrSamplesPerSec=127.30627057071584, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:27,607] [INFO] [logging.py:96:log_dist] [Rank 0] step=660, skipped=9, lr=[4.6237564569033496e-05, 4.6237564569033496e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:27,617] [INFO] [timer.py:215:stop] epoch=0/micro_step=660/global_step=660, RunningAvgSamplesPerSec=128.2856388262904, CurrSamplesPerSec=127.33670702574291, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:30,110] [INFO] [logging.py:96:log_dist] [Rank 0] step=670, skipped=9, lr=[4.612419317564973e-05, 4.612419317564973e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:30,119] [INFO] [timer.py:215:stop] epoch=0/micro_step=670/global_step=670, RunningAvgSamplesPerSec=128.2829462134768, CurrSamplesPerSec=128.31167013534042, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:32,618] [INFO] [logging.py:96:log_dist] [Rank 0] step=680, skipped=9, lr=[4.6009282275503976e-05, 4.6009282275503976e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:32,628] [INFO] [timer.py:215:stop] epoch=0/micro_step=680/global_step=680, RunningAvgSamplesPerSec=128.27544356632112, CurrSamplesPerSec=128.14114668313889, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:35,125] [INFO] [logging.py:96:log_dist] [Rank 0] step=690, skipped=9, lr=[4.589284024316967e-05, 4.589284024316967e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:35,134] [INFO] [timer.py:215:stop] epoch=0/micro_step=690/global_step=690, RunningAvgSamplesPerSec=128.26987496543404, CurrSamplesPerSec=127.9328965252982, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:37,631] [INFO] [logging.py:96:log_dist] [Rank 0] step=700, skipped=9, lr=[4.5774875564807464e-05, 4.5774875564807464e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:37,641] [INFO] [timer.py:215:stop] epoch=0/micro_step=700/global_step=700, RunningAvgSamplesPerSec=128.26432308919502, CurrSamplesPerSec=127.89961492244609, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:40,142] [INFO] [logging.py:96:log_dist] [Rank 0] step=710, skipped=9, lr=[4.5655396837546625e-05, 4.5655396837546625e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:40,152] [INFO] [timer.py:215:stop] epoch=0/micro_step=710/global_step=710, RunningAvgSamplesPerSec=128.25584438199786, CurrSamplesPerSec=127.44613263471945, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:42,648] [INFO] [logging.py:96:log_dist] [Rank 0] step=720, skipped=9, lr=[4.5534412768858605e-05, 4.5534412768858605e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:42,657] [INFO] [timer.py:215:stop] epoch=0/micro_step=720/global_step=720, RunningAvgSamplesPerSec=128.25162341829233, CurrSamplesPerSec=128.2617646946397, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:44,893] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:44,894] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:44,894] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:35:44,894] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:44,894] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:35:44,894] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:44,895] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:35:44,894] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:44,895] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:35:44,895] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:44,895] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:35:44,895] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:35:44,895] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:44,895] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:35:44,895] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:35:44,895] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:35:45,157] [INFO] [logging.py:96:log_dist] [Rank 0] step=730, skipped=9, lr=[4.541193217592236e-05, 4.541193217592236e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:45,166] [INFO] [timer.py:215:stop] epoch=0/micro_step=730/global_step=730, RunningAvgSamplesPerSec=128.24468611851677, CurrSamplesPerSec=127.89181514736585, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:47,664] [INFO] [logging.py:96:log_dist] [Rank 0] step=740, skipped=9, lr=[4.528796398498182e-05, 4.528796398498182e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:47,673] [INFO] [timer.py:215:stop] epoch=0/micro_step=740/global_step=740, RunningAvgSamplesPerSec=128.23981378876826, CurrSamplesPerSec=128.59516174310616, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:50,168] [INFO] [logging.py:96:log_dist] [Rank 0] step=750, skipped=9, lr=[4.516251723069534e-05, 4.516251723069534e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:50,178] [INFO] [timer.py:215:stop] epoch=0/micro_step=750/global_step=750, RunningAvgSamplesPerSec=128.23634332075477, CurrSamplesPerSec=127.36002732849707, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:52,677] [INFO] [logging.py:96:log_dist] [Rank 0] step=760, skipped=9, lr=[4.5035601055477245e-05, 4.5035601055477245e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:52,687] [INFO] [timer.py:215:stop] epoch=0/micro_step=760/global_step=760, RunningAvgSamplesPerSec=128.230046450437, CurrSamplesPerSec=127.5808448690663, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:55,183] [INFO] [logging.py:96:log_dist] [Rank 0] step=770, skipped=9, lr=[4.4907224708831575e-05, 4.4907224708831575e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:55,193] [INFO] [timer.py:215:stop] epoch=0/micro_step=770/global_step=770, RunningAvgSamplesPerSec=128.22597894609675, CurrSamplesPerSec=127.77760874180431, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:35:57,694] [INFO] [logging.py:96:log_dist] [Rank 0] step=780, skipped=9, lr=[4.477739754667796e-05, 4.477739754667796e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:35:57,703] [INFO] [timer.py:215:stop] epoch=0/micro_step=780/global_step=780, RunningAvgSamplesPerSec=128.21925090506426, CurrSamplesPerSec=128.1185178397222, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:00,198] [INFO] [logging.py:96:log_dist] [Rank 0] step=790, skipped=9, lr=[4.4646129030669795e-05, 4.4646129030669795e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:00,208] [INFO] [timer.py:215:stop] epoch=0/micro_step=790/global_step=790, RunningAvgSamplesPerSec=128.21628880718973, CurrSamplesPerSec=128.48252504695407, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:02,709] [INFO] [logging.py:96:log_dist] [Rank 0] step=800, skipped=9, lr=[4.451342872750468e-05, 4.451342872750468e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:02,718] [INFO] [timer.py:215:stop] epoch=0/micro_step=800/global_step=800, RunningAvgSamplesPerSec=128.20979376777623, CurrSamplesPerSec=128.1073898274024, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:05,217] [INFO] [logging.py:96:log_dist] [Rank 0] step=810, skipped=9, lr=[4.43793063082272e-05, 4.43793063082272e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:05,227] [INFO] [timer.py:215:stop] epoch=0/micro_step=810/global_step=810, RunningAvgSamplesPerSec=128.20442298428011, CurrSamplesPerSec=127.25400697623925, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:07,727] [INFO] [logging.py:96:log_dist] [Rank 0] step=820, skipped=9, lr=[4.42437715475241e-05, 4.42437715475241e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:07,736] [INFO] [timer.py:215:stop] epoch=0/micro_step=820/global_step=820, RunningAvgSamplesPerSec=128.19871914803585, CurrSamplesPerSec=127.99011306842942, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:09,975] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:09,975] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:09,975] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:09,976] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:36:09,976] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:09,976] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:36:09,976] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:36:09,975] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:09,976] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:36:09,976] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:09,976] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:09,976] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:36:09,976] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:36:09,976] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:09,976] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:36:09,976] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:36:10,238] [INFO] [logging.py:96:log_dist] [Rank 0] step=830, skipped=9, lr=[4.410683432301198e-05, 4.410683432301198e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:10,247] [INFO] [timer.py:215:stop] epoch=0/micro_step=830/global_step=830, RunningAvgSamplesPerSec=128.19199218936544, CurrSamplesPerSec=127.7917212946962, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:12,748] [INFO] [logging.py:96:log_dist] [Rank 0] step=840, skipped=9, lr=[4.3968504614517336e-05, 4.3968504614517336e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:12,757] [INFO] [timer.py:215:stop] epoch=0/micro_step=840/global_step=840, RunningAvgSamplesPerSec=128.18673223397778, CurrSamplesPerSec=128.4114747573707, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:15,259] [INFO] [logging.py:96:log_dist] [Rank 0] step=850, skipped=9, lr=[4.38287925033493e-05, 4.38287925033493e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:15,268] [INFO] [timer.py:215:stop] epoch=0/micro_step=850/global_step=850, RunningAvgSamplesPerSec=128.18034314426606, CurrSamplesPerSec=127.34202281986425, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:17,770] [INFO] [logging.py:96:log_dist] [Rank 0] step=860, skipped=9, lr=[4.3687708171564925e-05, 4.3687708171564925e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:17,780] [INFO] [timer.py:215:stop] epoch=0/micro_step=860/global_step=860, RunningAvgSamplesPerSec=128.17389331807945, CurrSamplesPerSec=127.53271798847986, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:20,282] [INFO] [logging.py:96:log_dist] [Rank 0] step=870, skipped=9, lr=[4.354526190122709e-05, 4.354526190122709e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:20,292] [INFO] [timer.py:215:stop] epoch=0/micro_step=870/global_step=870, RunningAvgSamplesPerSec=128.1674302975097, CurrSamplesPerSec=127.39411691564719, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:22,793] [INFO] [logging.py:96:log_dist] [Rank 0] step=880, skipped=9, lr=[4.340146407365521e-05, 4.340146407365521e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:22,802] [INFO] [timer.py:215:stop] epoch=0/micro_step=880/global_step=880, RunningAvgSamplesPerSec=128.16183615758715, CurrSamplesPerSec=127.50182440320974, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:25,301] [INFO] [logging.py:96:log_dist] [Rank 0] step=890, skipped=9, lr=[4.3256325168668596e-05, 4.3256325168668596e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:25,310] [INFO] [timer.py:215:stop] epoch=0/micro_step=890/global_step=890, RunningAvgSamplesPerSec=128.15784808777184, CurrSamplesPerSec=128.4201981543231, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:27,811] [INFO] [logging.py:96:log_dist] [Rank 0] step=900, skipped=9, lr=[4.310985576382276e-05, 4.310985576382276e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:27,820] [INFO] [timer.py:215:stop] epoch=0/micro_step=900/global_step=900, RunningAvgSamplesPerSec=128.1531796068461, CurrSamplesPerSec=127.60862223709631, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:30,321] [INFO] [logging.py:96:log_dist] [Rank 0] step=910, skipped=9, lr=[4.296206653363848e-05, 4.296206653363848e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:30,330] [INFO] [timer.py:215:stop] epoch=0/micro_step=910/global_step=910, RunningAvgSamplesPerSec=128.14845002355648, CurrSamplesPerSec=128.18789748996934, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:32,834] [INFO] [logging.py:96:log_dist] [Rank 0] step=920, skipped=9, lr=[4.2812968248823894e-05, 4.2812968248823894e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:32,843] [INFO] [timer.py:215:stop] epoch=0/micro_step=920/global_step=920, RunningAvgSamplesPerSec=128.14203984896605, CurrSamplesPerSec=127.86233084533274, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:35,080] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:35,081] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:35,081] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:35,082] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:36:35,082] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:36:35,081] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:35,082] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:36:35,081] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:35,082] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:36:35,081] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:35,081] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:35,082] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:36:35,082] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:36:35,082] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:36:35,082] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:36:35,082] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:36:35,345] [INFO] [logging.py:96:log_dist] [Rank 0] step=930, skipped=9, lr=[4.2662571775489523e-05, 4.2662571775489523e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:35,354] [INFO] [timer.py:215:stop] epoch=0/micro_step=930/global_step=930, RunningAvgSamplesPerSec=128.1367082004806, CurrSamplesPerSec=127.28381489953304, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:37,855] [INFO] [logging.py:96:log_dist] [Rank 0] step=940, skipped=9, lr=[4.251088807435636e-05, 4.251088807435636e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:37,864] [INFO] [timer.py:215:stop] epoch=0/micro_step=940/global_step=940, RunningAvgSamplesPerSec=128.13219029713017, CurrSamplesPerSec=127.73346631593773, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:39,586] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 946 +[2023-06-12 07:36:39,586] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 946 +[2023-06-12 07:36:39,586] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 946 +[2023-06-12 07:36:39,587] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:36:39,586] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 946 +[2023-06-12 07:36:39,587] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:36:39,587] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:36:39,587] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 32768.0, reducing to 16384.0 +[2023-06-12 07:36:39,586] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 946 +[2023-06-12 07:36:39,587] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:36:39,586] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 946 +[2023-06-12 07:36:39,588] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:36:39,587] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 946 +[2023-06-12 07:36:39,588] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:36:39,587] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 946 +[2023-06-12 07:36:39,588] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:36:39,588] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:36:40,332] [INFO] [logging.py:96:log_dist] [Rank 0] step=950, skipped=10, lr=[4.2373281298214366e-05, 4.2373281298214366e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:40,341] [INFO] [timer.py:215:stop] epoch=0/micro_step=950/global_step=950, RunningAvgSamplesPerSec=128.14558216615114, CurrSamplesPerSec=128.01001054846284, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:42,843] [INFO] [logging.py:96:log_dist] [Rank 0] step=960, skipped=10, lr=[4.221918239638724e-05, 4.221918239638724e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:42,852] [INFO] [timer.py:215:stop] epoch=0/micro_step=960/global_step=960, RunningAvgSamplesPerSec=128.14033730529505, CurrSamplesPerSec=127.39351233142996, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:45,354] [INFO] [logging.py:96:log_dist] [Rank 0] step=970, skipped=10, lr=[4.206382858046636e-05, 4.206382858046636e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:45,363] [INFO] [timer.py:215:stop] epoch=0/micro_step=970/global_step=970, RunningAvgSamplesPerSec=128.13558678828747, CurrSamplesPerSec=127.98693980926552, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:47,867] [INFO] [logging.py:96:log_dist] [Rank 0] step=980, skipped=10, lr=[4.190723117245809e-05, 4.190723117245809e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:47,877] [INFO] [timer.py:215:stop] epoch=0/micro_step=980/global_step=980, RunningAvgSamplesPerSec=128.12917327451635, CurrSamplesPerSec=128.0449376459634, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:50,380] [INFO] [logging.py:96:log_dist] [Rank 0] step=990, skipped=10, lr=[4.174940158500041e-05, 4.174940158500041e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:50,389] [INFO] [timer.py:215:stop] epoch=0/micro_step=990/global_step=990, RunningAvgSamplesPerSec=128.1238394426681, CurrSamplesPerSec=128.03260107468313, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:52,891] [INFO] [logging.py:96:log_dist] [Rank 0] step=1000, skipped=10, lr=[4.1590351320531064e-05, 4.1590351320531064e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:52,900] [INFO] [timer.py:215:stop] epoch=0/micro_step=1000/global_step=1000, RunningAvgSamplesPerSec=128.11886230495972, CurrSamplesPerSec=127.76313444770209, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:54,873] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1007 +[2023-06-12 07:36:54,873] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1007 +[2023-06-12 07:36:54,874] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:36:54,873] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1007 +[2023-06-12 07:36:54,874] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:36:54,873] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1007 +[2023-06-12 07:36:54,873] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1007 +[2023-06-12 07:36:54,874] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:36:54,874] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 16384.0, reducing to 8192.0 +[2023-06-12 07:36:54,874] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:36:54,873] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1007 +[2023-06-12 07:36:54,874] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:36:54,873] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1007 +[2023-06-12 07:36:54,874] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:36:54,874] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1007 +[2023-06-12 07:36:54,874] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:36:54,874] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:36:55,369] [INFO] [logging.py:96:log_dist] [Rank 0] step=1010, skipped=11, lr=[4.144617198213059e-05, 4.144617198213059e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:55,378] [INFO] [timer.py:215:stop] epoch=0/micro_step=1010/global_step=1010, RunningAvgSamplesPerSec=128.13123745018407, CurrSamplesPerSec=126.9736285442911, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:36:57,878] [INFO] [logging.py:96:log_dist] [Rank 0] step=1020, skipped=11, lr=[4.128483443849015e-05, 4.128483443849015e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:36:57,887] [INFO] [timer.py:215:stop] epoch=0/micro_step=1020/global_step=1020, RunningAvgSamplesPerSec=128.1274498289982, CurrSamplesPerSec=128.18140908344253, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:00,388] [INFO] [logging.py:96:log_dist] [Rank 0] step=1030, skipped=11, lr=[4.1122310074954256e-05, 4.1122310074954256e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:00,397] [INFO] [timer.py:215:stop] epoch=0/micro_step=1030/global_step=1030, RunningAvgSamplesPerSec=128.12353718825966, CurrSamplesPerSec=127.2963697822021, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:02,895] [INFO] [logging.py:96:log_dist] [Rank 0] step=1040, skipped=11, lr=[4.095861073611052e-05, 4.095861073611052e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:02,904] [INFO] [timer.py:215:stop] epoch=0/micro_step=1040/global_step=1040, RunningAvgSamplesPerSec=128.12089818801556, CurrSamplesPerSec=128.31154746995784, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:05,402] [INFO] [logging.py:96:log_dist] [Rank 0] step=1050, skipped=11, lr=[4.079374835217739e-05, 4.079374835217739e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:05,412] [INFO] [timer.py:215:stop] epoch=0/micro_step=1050/global_step=1050, RunningAvgSamplesPerSec=128.11831630758965, CurrSamplesPerSec=127.54629166801291, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:07,910] [INFO] [logging.py:96:log_dist] [Rank 0] step=1060, skipped=11, lr=[4.062773493813468e-05, 4.062773493813468e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:07,919] [INFO] [timer.py:215:stop] epoch=0/micro_step=1060/global_step=1060, RunningAvgSamplesPerSec=128.1156902874788, CurrSamplesPerSec=127.75936437164879, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:10,421] [INFO] [logging.py:96:log_dist] [Rank 0] step=1070, skipped=11, lr=[4.046058259284796e-05, 4.046058259284796e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:10,430] [INFO] [timer.py:215:stop] epoch=0/micro_step=1070/global_step=1070, RunningAvgSamplesPerSec=128.11119192130886, CurrSamplesPerSec=127.44952117785026, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:12,929] [INFO] [logging.py:96:log_dist] [Rank 0] step=1080, skipped=11, lr=[4.0292303498186814e-05, 4.0292303498186814e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:12,938] [INFO] [timer.py:215:stop] epoch=0/micro_step=1080/global_step=1080, RunningAvgSamplesPerSec=128.1086252955196, CurrSamplesPerSec=127.83334714360684, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:15,432] [INFO] [logging.py:96:log_dist] [Rank 0] step=1090, skipped=11, lr=[4.012290991813698e-05, 4.012290991813698e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:15,442] [INFO] [timer.py:215:stop] epoch=0/micro_step=1090/global_step=1090, RunningAvgSamplesPerSec=128.10793591000052, CurrSamplesPerSec=128.9187794099143, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:17,942] [INFO] [logging.py:96:log_dist] [Rank 0] step=1100, skipped=11, lr=[3.995241419790661e-05, 3.995241419790661e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:17,951] [INFO] [timer.py:215:stop] epoch=0/micro_step=1100/global_step=1100, RunningAvgSamplesPerSec=128.10443613580182, CurrSamplesPerSec=128.32050265928714, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:20,186] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:37:20,186] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:37:20,187] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:37:20,186] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:37:20,187] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:37:20,186] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:37:20,187] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:37:20,187] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:37:20,187] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:37:20,187] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:37:20,187] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:37:20,187] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:37:20,188] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:37:20,187] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:37:20,188] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:37:20,188] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:37:20,450] [INFO] [logging.py:96:log_dist] [Rank 0] step=1110, skipped=11, lr=[3.978082876302658e-05, 3.978082876302658e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:20,459] [INFO] [timer.py:215:stop] epoch=0/micro_step=1110/global_step=1110, RunningAvgSamplesPerSec=128.10202837132144, CurrSamplesPerSec=127.6826734095523, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:22,961] [INFO] [logging.py:96:log_dist] [Rank 0] step=1120, skipped=11, lr=[3.9608166118444864e-05, 3.9608166118444864e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:22,970] [INFO] [timer.py:215:stop] epoch=0/micro_step=1120/global_step=1120, RunningAvgSamplesPerSec=128.0980853364955, CurrSamplesPerSec=126.97422914969722, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:25,467] [INFO] [logging.py:96:log_dist] [Rank 0] step=1130, skipped=11, lr=[3.94344388476153e-05, 3.94344388476153e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:25,476] [INFO] [timer.py:215:stop] epoch=0/micro_step=1130/global_step=1130, RunningAvgSamplesPerSec=128.09640421019526, CurrSamplesPerSec=127.90278385283402, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:27,975] [INFO] [logging.py:96:log_dist] [Rank 0] step=1140, skipped=11, lr=[3.925965961158039e-05, 3.925965961158039e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:27,984] [INFO] [timer.py:215:stop] epoch=0/micro_step=1140/global_step=1140, RunningAvgSamplesPerSec=128.09360773309078, CurrSamplesPerSec=127.65522803707029, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:30,486] [INFO] [logging.py:96:log_dist] [Rank 0] step=1150, skipped=11, lr=[3.908384114804867e-05, 3.908384114804867e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:30,495] [INFO] [timer.py:215:stop] epoch=0/micro_step=1150/global_step=1150, RunningAvgSamplesPerSec=128.08979377174293, CurrSamplesPerSec=127.96900164945701, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:32,993] [INFO] [logging.py:96:log_dist] [Rank 0] step=1160, skipped=11, lr=[3.890699627046639e-05, 3.890699627046639e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:33,002] [INFO] [timer.py:215:stop] epoch=0/micro_step=1160/global_step=1160, RunningAvgSamplesPerSec=128.08783954523238, CurrSamplesPerSec=127.55077646495336, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:35,502] [INFO] [logging.py:96:log_dist] [Rank 0] step=1170, skipped=11, lr=[3.872913786708364e-05, 3.872913786708364e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:35,511] [INFO] [timer.py:215:stop] epoch=0/micro_step=1170/global_step=1170, RunningAvgSamplesPerSec=128.08525628738477, CurrSamplesPerSec=127.49370974789596, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:36,230] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1172 +[2023-06-12 07:37:36,230] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1172 +[2023-06-12 07:37:36,231] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:37:36,230] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1172 +[2023-06-12 07:37:36,231] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:37:36,231] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 16384.0, reducing to 8192.0 +[2023-06-12 07:37:36,231] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:37:36,230] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1172 +[2023-06-12 07:37:36,230] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1172 +[2023-06-12 07:37:36,231] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:37:36,230] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1172 +[2023-06-12 07:37:36,230] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1172 +[2023-06-12 07:37:36,231] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:37:36,231] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:37:36,230] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1172 +[2023-06-12 07:37:36,231] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:37:36,231] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:37:37,979] [INFO] [logging.py:96:log_dist] [Rank 0] step=1180, skipped=12, lr=[3.856820945115655e-05, 3.856820945115655e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:37,988] [INFO] [timer.py:215:stop] epoch=0/micro_step=1180/global_step=1180, RunningAvgSamplesPerSec=128.0961629767614, CurrSamplesPerSec=128.1045775588898, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:40,489] [INFO] [logging.py:96:log_dist] [Rank 0] step=1190, skipped=12, lr=[3.83884611196668e-05, 3.83884611196668e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:40,499] [INFO] [timer.py:215:stop] epoch=0/micro_step=1190/global_step=1190, RunningAvgSamplesPerSec=128.09278505785804, CurrSamplesPerSec=128.2882453021353, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:43,006] [INFO] [logging.py:96:log_dist] [Rank 0] step=1200, skipped=12, lr=[3.8207737052618545e-05, 3.8207737052618545e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:43,015] [INFO] [timer.py:215:stop] epoch=0/micro_step=1200/global_step=1200, RunningAvgSamplesPerSec=128.08689649145865, CurrSamplesPerSec=127.12708756402873, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:45,515] [INFO] [logging.py:96:log_dist] [Rank 0] step=1210, skipped=12, lr=[3.80260504209727e-05, 3.80260504209727e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:45,525] [INFO] [timer.py:215:stop] epoch=0/micro_step=1210/global_step=1210, RunningAvgSamplesPerSec=128.0837623724224, CurrSamplesPerSec=127.99108948752156, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:48,026] [INFO] [logging.py:96:log_dist] [Rank 0] step=1220, skipped=12, lr=[3.784341446584082e-05, 3.784341446584082e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:48,035] [INFO] [timer.py:215:stop] epoch=0/micro_step=1220/global_step=1220, RunningAvgSamplesPerSec=128.080630595365, CurrSamplesPerSec=127.5270227513504, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:50,539] [INFO] [logging.py:96:log_dist] [Rank 0] step=1230, skipped=12, lr=[3.765984249752004e-05, 3.765984249752004e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:50,548] [INFO] [timer.py:215:stop] epoch=0/micro_step=1230/global_step=1230, RunningAvgSamplesPerSec=128.07615990540486, CurrSamplesPerSec=128.02185431663767, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:53,051] [INFO] [logging.py:96:log_dist] [Rank 0] step=1240, skipped=12, lr=[3.747534789452304e-05, 3.747534789452304e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:53,060] [INFO] [timer.py:215:stop] epoch=0/micro_step=1240/global_step=1240, RunningAvgSamplesPerSec=128.072433295388, CurrSamplesPerSec=127.87183256528272, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:55,561] [INFO] [logging.py:96:log_dist] [Rank 0] step=1250, skipped=12, lr=[3.728994410260308e-05, 3.728994410260308e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:55,570] [INFO] [timer.py:215:stop] epoch=0/micro_step=1250/global_step=1250, RunningAvgSamplesPerSec=128.06959324640667, CurrSamplesPerSec=127.9232638044996, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:37:58,072] [INFO] [logging.py:96:log_dist] [Rank 0] step=1260, skipped=12, lr=[3.7103644633774014e-05, 3.7103644633774014e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:37:58,081] [INFO] [timer.py:215:stop] epoch=0/micro_step=1260/global_step=1260, RunningAvgSamplesPerSec=128.06627112015954, CurrSamplesPerSec=126.90459680019515, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:00,583] [INFO] [logging.py:96:log_dist] [Rank 0] step=1270, skipped=12, lr=[3.691646306532564e-05, 3.691646306532564e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:00,592] [INFO] [timer.py:215:stop] epoch=0/micro_step=1270/global_step=1270, RunningAvgSamplesPerSec=128.0632752381575, CurrSamplesPerSec=128.22573920686327, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:01,575] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:01,575] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:01,576] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:01,576] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:01,576] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:01,575] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:01,576] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:01,575] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:01,575] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:01,576] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:01,576] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:01,576] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:01,576] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:01,576] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:01,576] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:01,576] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:03,095] [INFO] [logging.py:96:log_dist] [Rank 0] step=1280, skipped=12, lr=[3.672841303883413e-05, 3.672841303883413e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:03,104] [INFO] [timer.py:215:stop] epoch=0/micro_step=1280/global_step=1280, RunningAvgSamplesPerSec=128.05958409059627, CurrSamplesPerSec=127.58339163498098, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:05,610] [INFO] [logging.py:96:log_dist] [Rank 0] step=1290, skipped=12, lr=[3.6539508259167863e-05, 3.6539508259167863e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:05,619] [INFO] [timer.py:215:stop] epoch=0/micro_step=1290/global_step=1290, RunningAvgSamplesPerSec=128.05502779010172, CurrSamplesPerSec=127.81776470352958, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:08,116] [INFO] [logging.py:96:log_dist] [Rank 0] step=1300, skipped=12, lr=[3.634976249348867e-05, 3.634976249348867e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:08,125] [INFO] [timer.py:215:stop] epoch=0/micro_step=1300/global_step=1300, RunningAvgSamplesPerSec=128.0539067673024, CurrSamplesPerSec=127.46622448756703, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:10,627] [INFO] [logging.py:96:log_dist] [Rank 0] step=1310, skipped=12, lr=[3.615918957024845e-05, 3.615918957024845e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:10,636] [INFO] [timer.py:215:stop] epoch=0/micro_step=1310/global_step=1310, RunningAvgSamplesPerSec=128.05069035183686, CurrSamplesPerSec=127.95728964674343, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:13,135] [INFO] [logging.py:96:log_dist] [Rank 0] step=1320, skipped=12, lr=[3.5967803378181386e-05, 3.5967803378181386e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:13,144] [INFO] [timer.py:215:stop] epoch=0/micro_step=1320/global_step=1320, RunningAvgSamplesPerSec=128.0491720961679, CurrSamplesPerSec=128.09406321399192, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:15,646] [INFO] [logging.py:96:log_dist] [Rank 0] step=1330, skipped=12, lr=[3.577561786529177e-05, 3.577561786529177e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:15,656] [INFO] [timer.py:215:stop] epoch=0/micro_step=1330/global_step=1330, RunningAvgSamplesPerSec=128.04584756774636, CurrSamplesPerSec=127.55586769774963, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1330 +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1330 +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1330 +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1330 +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:38:15,872] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 16384.0, reducing to 8192.0 +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1330 +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1330 +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1330 +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1330 +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:38:15,872] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:38:18,124] [INFO] [logging.py:96:log_dist] [Rank 0] step=1340, skipped=13, lr=[3.560197905937272e-05, 3.560197905937272e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:18,133] [INFO] [timer.py:215:stop] epoch=0/micro_step=1340/global_step=1340, RunningAvgSamplesPerSec=128.055812100271, CurrSamplesPerSec=126.93124015869037, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:20,635] [INFO] [logging.py:96:log_dist] [Rank 0] step=1350, skipped=13, lr=[3.5408313471484715e-05, 3.5408313471484715e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:20,645] [INFO] [timer.py:215:stop] epoch=0/micro_step=1350/global_step=1350, RunningAvgSamplesPerSec=128.0528605171604, CurrSamplesPerSec=127.37646541882057, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:23,147] [INFO] [logging.py:96:log_dist] [Rank 0] step=1360, skipped=13, lr=[3.521388933775134e-05, 3.521388933775134e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:23,156] [INFO] [timer.py:215:stop] epoch=0/micro_step=1360/global_step=1360, RunningAvgSamplesPerSec=128.0496495522943, CurrSamplesPerSec=127.58242142645302, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:25,659] [INFO] [logging.py:96:log_dist] [Rank 0] step=1370, skipped=13, lr=[3.5018720827578524e-05, 3.5018720827578524e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:25,668] [INFO] [timer.py:215:stop] epoch=0/micro_step=1370/global_step=1370, RunningAvgSamplesPerSec=128.04659186369958, CurrSamplesPerSec=127.69020473399802, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:28,166] [INFO] [logging.py:96:log_dist] [Rank 0] step=1380, skipped=13, lr=[3.4822822164621546e-05, 3.4822822164621546e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:28,176] [INFO] [timer.py:215:stop] epoch=0/micro_step=1380/global_step=1380, RunningAvgSamplesPerSec=128.0449536024872, CurrSamplesPerSec=127.81411311864288, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:30,681] [INFO] [logging.py:96:log_dist] [Rank 0] step=1390, skipped=13, lr=[3.462620762574832e-05, 3.462620762574832e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:30,690] [INFO] [timer.py:215:stop] epoch=0/micro_step=1390/global_step=1390, RunningAvgSamplesPerSec=128.040906447566, CurrSamplesPerSec=127.93948175149085, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:33,193] [INFO] [logging.py:96:log_dist] [Rank 0] step=1400, skipped=13, lr=[3.442889153999901e-05, 3.442889153999901e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:33,203] [INFO] [timer.py:215:stop] epoch=0/micro_step=1400/global_step=1400, RunningAvgSamplesPerSec=128.03758458924017, CurrSamplesPerSec=127.8893779127437, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:35,702] [INFO] [logging.py:96:log_dist] [Rank 0] step=1410, skipped=13, lr=[3.423088828754168e-05, 3.423088828754168e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:35,712] [INFO] [timer.py:215:stop] epoch=0/micro_step=1410/global_step=1410, RunningAvgSamplesPerSec=128.03561672556455, CurrSamplesPerSec=128.03284534015322, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:38,211] [INFO] [logging.py:96:log_dist] [Rank 0] step=1420, skipped=13, lr=[3.4032212298624314e-05, 3.4032212298624314e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:38,220] [INFO] [timer.py:215:stop] epoch=0/micro_step=1420/global_step=1420, RunningAvgSamplesPerSec=128.03393007614144, CurrSamplesPerSec=128.22047186925914, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:40,720] [INFO] [logging.py:96:log_dist] [Rank 0] step=1430, skipped=13, lr=[3.383287805252317e-05, 3.383287805252317e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:40,730] [INFO] [timer.py:215:stop] epoch=0/micro_step=1430/global_step=1430, RunningAvgSamplesPerSec=128.03171151492984, CurrSamplesPerSec=127.30433858860711, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:41,210] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:41,211] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:41,211] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:41,211] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:41,211] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:41,211] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:41,211] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:41,211] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:41,211] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:41,211] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:41,211] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:41,212] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:41,211] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:38:41,212] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:41,212] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:41,212] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:38:43,233] [INFO] [logging.py:96:log_dist] [Rank 0] step=1440, skipped=13, lr=[3.36329000764875e-05, 3.36329000764875e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:43,242] [INFO] [timer.py:215:stop] epoch=0/micro_step=1440/global_step=1440, RunningAvgSamplesPerSec=128.02857872718292, CurrSamplesPerSec=126.91299665171712, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:45,743] [INFO] [logging.py:96:log_dist] [Rank 0] step=1450, skipped=13, lr=[3.343229294468086e-05, 3.343229294468086e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:45,752] [INFO] [timer.py:215:stop] epoch=0/micro_step=1450/global_step=1450, RunningAvgSamplesPerSec=128.02635980080208, CurrSamplesPerSec=127.73091355510404, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:48,251] [INFO] [logging.py:96:log_dist] [Rank 0] step=1460, skipped=13, lr=[3.323107127711897e-05, 3.323107127711897e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:48,260] [INFO] [timer.py:215:stop] epoch=0/micro_step=1460/global_step=1460, RunningAvgSamplesPerSec=128.02481849074564, CurrSamplesPerSec=127.96900164945701, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:50,761] [INFO] [logging.py:96:log_dist] [Rank 0] step=1470, skipped=13, lr=[3.302924973860416e-05, 3.302924973860416e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:50,770] [INFO] [timer.py:215:stop] epoch=0/micro_step=1470/global_step=1470, RunningAvgSamplesPerSec=128.02267882749456, CurrSamplesPerSec=128.42548191468393, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:53,274] [INFO] [logging.py:96:log_dist] [Rank 0] step=1480, skipped=13, lr=[3.282684303765669e-05, 3.282684303765669e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:53,283] [INFO] [timer.py:215:stop] epoch=0/micro_step=1480/global_step=1480, RunningAvgSamplesPerSec=128.01956050282269, CurrSamplesPerSec=127.57272015268684, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:55,782] [INFO] [logging.py:96:log_dist] [Rank 0] step=1490, skipped=13, lr=[3.2623865925442816e-05, 3.2623865925442816e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:55,791] [INFO] [timer.py:215:stop] epoch=0/micro_step=1490/global_step=1490, RunningAvgSamplesPerSec=128.01798402487617, CurrSamplesPerSec=127.41540193680005, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:38:58,290] [INFO] [logging.py:96:log_dist] [Rank 0] step=1500, skipped=13, lr=[3.242033319469963e-05, 3.242033319469963e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:38:58,299] [INFO] [timer.py:215:stop] epoch=0/micro_step=1500/global_step=1500, RunningAvgSamplesPerSec=128.01676885547505, CurrSamplesPerSec=128.48719892781926, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:00,797] [INFO] [logging.py:96:log_dist] [Rank 0] step=1510, skipped=13, lr=[3.221625967865712e-05, 3.221625967865712e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:00,806] [INFO] [timer.py:215:stop] epoch=0/micro_step=1510/global_step=1510, RunningAvgSamplesPerSec=128.01553598030188, CurrSamplesPerSec=128.3371896337901, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:03,302] [INFO] [logging.py:96:log_dist] [Rank 0] step=1520, skipped=13, lr=[3.201166024995706e-05, 3.201166024995706e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:03,311] [INFO] [timer.py:215:stop] epoch=0/micro_step=1520/global_step=1520, RunningAvgSamplesPerSec=128.0153895447443, CurrSamplesPerSec=128.11338159381776, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:05,808] [INFO] [logging.py:96:log_dist] [Rank 0] step=1530, skipped=13, lr=[3.180654981956912e-05, 3.180654981956912e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:05,817] [INFO] [timer.py:215:stop] epoch=0/micro_step=1530/global_step=1530, RunningAvgSamplesPerSec=128.01462318533956, CurrSamplesPerSec=128.11533821036394, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:06,297] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:06,297] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:06,297] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:06,298] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:39:06,298] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:39:06,297] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:06,298] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:39:06,297] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:06,298] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:39:06,298] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:06,298] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:39:06,298] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:06,298] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:39:06,298] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:06,298] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:39:06,298] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:39:07,294] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1535 +[2023-06-12 07:39:07,294] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1535 +[2023-06-12 07:39:07,295] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1535 +[2023-06-12 07:39:07,295] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:39:07,295] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:39:07,295] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1535 +[2023-06-12 07:39:07,296] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:39:07,295] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1535 +[2023-06-12 07:39:07,296] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:39:07,295] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1535 +[2023-06-12 07:39:07,295] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1535 +[2023-06-12 07:39:07,296] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:39:07,296] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:39:07,295] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1535 +[2023-06-12 07:39:07,296] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:39:07,296] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 32768.0, reducing to 16384.0 +[2023-06-12 07:39:07,296] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:39:08,290] [INFO] [logging.py:96:log_dist] [Rank 0] step=1540, skipped=14, lr=[3.1621525879721206e-05, 3.1621525879721206e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:08,299] [INFO] [timer.py:215:stop] epoch=0/micro_step=1540/global_step=1540, RunningAvgSamplesPerSec=128.02190124005665, CurrSamplesPerSec=127.72131122581038, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:10,801] [INFO] [logging.py:96:log_dist] [Rank 0] step=1550, skipped=14, lr=[3.1415485758349346e-05, 3.1415485758349346e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:10,810] [INFO] [timer.py:215:stop] epoch=0/micro_step=1550/global_step=1550, RunningAvgSamplesPerSec=128.01959591555064, CurrSamplesPerSec=129.09758854088014, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:13,036] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1558 +[2023-06-12 07:39:13,036] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1558 +[2023-06-12 07:39:13,036] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1558 +[2023-06-12 07:39:13,038] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:39:13,038] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:39:13,036] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1558 +[2023-06-12 07:39:13,038] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:39:13,038] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 16384.0, reducing to 8192.0 +[2023-06-12 07:39:13,037] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1558 +[2023-06-12 07:39:13,038] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:39:13,037] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1558 +[2023-06-12 07:39:13,038] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:39:13,037] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1558 +[2023-06-12 07:39:13,038] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:39:13,037] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1558 +[2023-06-12 07:39:13,038] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:39:13,038] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:39:13,281] [INFO] [logging.py:96:log_dist] [Rank 0] step=1560, skipped=15, lr=[3.122964946248119e-05, 3.122964946248119e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:13,290] [INFO] [timer.py:215:stop] epoch=0/micro_step=1560/global_step=1560, RunningAvgSamplesPerSec=128.02739920968037, CurrSamplesPerSec=127.17466772663143, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:15,789] [INFO] [logging.py:96:log_dist] [Rank 0] step=1570, skipped=15, lr=[3.102273385690231e-05, 3.102273385690231e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:15,798] [INFO] [timer.py:215:stop] epoch=0/micro_step=1570/global_step=1570, RunningAvgSamplesPerSec=128.02605166485563, CurrSamplesPerSec=127.60947151746792, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:18,299] [INFO] [logging.py:96:log_dist] [Rank 0] step=1580, skipped=15, lr=[3.08153793214471e-05, 3.08153793214471e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:18,309] [INFO] [timer.py:215:stop] epoch=0/micro_step=1580/global_step=1580, RunningAvgSamplesPerSec=128.0239027046948, CurrSamplesPerSec=127.93606710513774, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:20,808] [INFO] [logging.py:96:log_dist] [Rank 0] step=1590, skipped=15, lr=[3.0607600967874206e-05, 3.0607600967874206e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:20,818] [INFO] [timer.py:215:stop] epoch=0/micro_step=1590/global_step=1590, RunningAvgSamplesPerSec=128.02218666514744, CurrSamplesPerSec=127.55550402478545, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:23,319] [INFO] [logging.py:96:log_dist] [Rank 0] step=1600, skipped=15, lr=[3.039941393882969e-05, 3.039941393882969e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:23,328] [INFO] [timer.py:215:stop] epoch=0/micro_step=1600/global_step=1600, RunningAvgSamplesPerSec=128.02011053823924, CurrSamplesPerSec=127.61626616742525, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:25,830] [INFO] [logging.py:96:log_dist] [Rank 0] step=1610, skipped=15, lr=[3.0190833406743398e-05, 3.0190833406743398e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:25,839] [INFO] [timer.py:215:stop] epoch=0/micro_step=1610/global_step=1610, RunningAvgSamplesPerSec=128.0178990883948, CurrSamplesPerSec=127.2088992765594, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:28,340] [INFO] [logging.py:96:log_dist] [Rank 0] step=1620, skipped=15, lr=[2.9981874572723222e-05, 2.9981874572723222e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:28,349] [INFO] [timer.py:215:stop] epoch=0/micro_step=1620/global_step=1620, RunningAvgSamplesPerSec=128.0158363194406, CurrSamplesPerSec=127.82080785032275, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:30,847] [INFO] [logging.py:96:log_dist] [Rank 0] step=1630, skipped=15, lr=[2.9772552665447263e-05, 2.9772552665447263e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:30,856] [INFO] [timer.py:215:stop] epoch=0/micro_step=1630/global_step=1630, RunningAvgSamplesPerSec=128.01484766155724, CurrSamplesPerSec=128.17541095229774, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:33,357] [INFO] [logging.py:96:log_dist] [Rank 0] step=1640, skipped=15, lr=[2.9562882940053975e-05, 2.9562882940053975e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:33,366] [INFO] [timer.py:215:stop] epoch=0/micro_step=1640/global_step=1640, RunningAvgSamplesPerSec=128.01300963543733, CurrSamplesPerSec=127.5270227513504, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:35,866] [INFO] [logging.py:96:log_dist] [Rank 0] step=1650, skipped=15, lr=[2.9352880677030386e-05, 2.9352880677030386e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:35,876] [INFO] [timer.py:215:stop] epoch=0/micro_step=1650/global_step=1650, RunningAvgSamplesPerSec=128.01130887282926, CurrSamplesPerSec=127.86671607906874, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:38,365] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:38,366] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:38,366] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:39:38,366] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:38,366] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:39:38,366] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:38,366] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:38,367] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:39:38,367] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:39:38,366] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:38,367] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:39:38,366] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:38,367] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:39:38,366] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:39:38,367] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:39:38,367] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:39:38,378] [INFO] [logging.py:96:log_dist] [Rank 0] step=1660, skipped=15, lr=[2.9142561181098505e-05, 2.9142561181098505e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:38,387] [INFO] [timer.py:215:stop] epoch=0/micro_step=1660/global_step=1660, RunningAvgSamplesPerSec=128.0090507031761, CurrSamplesPerSec=127.28478057181441, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:40,895] [INFO] [logging.py:96:log_dist] [Rank 0] step=1670, skipped=15, lr=[2.89319397800999e-05, 2.89319397800999e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:40,904] [INFO] [timer.py:215:stop] epoch=0/micro_step=1670/global_step=1670, RunningAvgSamplesPerSec=128.0049951247616, CurrSamplesPerSec=127.60947151746792, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:43,407] [INFO] [logging.py:96:log_dist] [Rank 0] step=1680, skipped=15, lr=[2.872103182387862e-05, 2.872103182387862e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:43,416] [INFO] [timer.py:215:stop] epoch=0/micro_step=1680/global_step=1680, RunningAvgSamplesPerSec=128.00260288589115, CurrSamplesPerSec=128.11790636028067, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:45,920] [INFO] [logging.py:96:log_dist] [Rank 0] step=1690, skipped=15, lr=[2.8509852683162536e-05, 2.8509852683162536e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:45,929] [INFO] [timer.py:215:stop] epoch=0/micro_step=1690/global_step=1690, RunningAvgSamplesPerSec=128.0000851166193, CurrSamplesPerSec=127.57635795745101, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:48,431] [INFO] [logging.py:96:log_dist] [Rank 0] step=1700, skipped=15, lr=[2.8298417748443116e-05, 2.8298417748443116e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:48,441] [INFO] [timer.py:215:stop] epoch=0/micro_step=1700/global_step=1700, RunningAvgSamplesPerSec=127.99784957131214, CurrSamplesPerSec=127.41552289474134, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:50,943] [INFO] [logging.py:96:log_dist] [Rank 0] step=1710, skipped=15, lr=[2.8086742428853836e-05, 2.8086742428853836e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:50,952] [INFO] [timer.py:215:stop] epoch=0/micro_step=1710/global_step=1710, RunningAvgSamplesPerSec=127.99564664044512, CurrSamplesPerSec=127.53053677373256, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:53,455] [INFO] [logging.py:96:log_dist] [Rank 0] step=1720, skipped=15, lr=[2.7874842151047114e-05, 2.7874842151047114e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:53,464] [INFO] [timer.py:215:stop] epoch=0/micro_step=1720/global_step=1720, RunningAvgSamplesPerSec=127.99340847152818, CurrSamplesPerSec=126.9660614029694, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:55,970] [INFO] [logging.py:96:log_dist] [Rank 0] step=1730, skipped=15, lr=[2.766273235807006e-05, 2.766273235807006e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:55,979] [INFO] [timer.py:215:stop] epoch=0/micro_step=1730/global_step=1730, RunningAvgSamplesPerSec=127.99030342095347, CurrSamplesPerSec=127.37235549844696, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:39:58,482] [INFO] [logging.py:96:log_dist] [Rank 0] step=1740, skipped=15, lr=[2.7450428508239024e-05, 2.7450428508239024e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:39:58,491] [INFO] [timer.py:215:stop] epoch=0/micro_step=1740/global_step=1740, RunningAvgSamplesPerSec=127.9881257251868, CurrSamplesPerSec=128.11668341890817, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:00,994] [INFO] [logging.py:96:log_dist] [Rank 0] step=1750, skipped=15, lr=[2.723794607401297e-05, 2.723794607401297e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:01,003] [INFO] [timer.py:215:stop] epoch=0/micro_step=1750/global_step=1750, RunningAvgSamplesPerSec=127.9859074587052, CurrSamplesPerSec=127.83188612845312, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:03,493] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:03,493] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:03,493] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:03,494] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:03,494] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:03,493] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:03,494] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:03,493] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:03,494] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:03,494] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:03,494] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:03,494] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:03,494] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:03,494] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:03,494] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:03,494] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:03,505] [INFO] [logging.py:96:log_dist] [Rank 0] step=1760, skipped=15, lr=[2.7025300540865923e-05, 2.7025300540865923e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:03,514] [INFO] [timer.py:215:stop] epoch=0/micro_step=1760/global_step=1760, RunningAvgSamplesPerSec=127.98394740646945, CurrSamplesPerSec=127.18286233562934, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:03,738] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1760 +[2023-06-12 07:40:03,738] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:03,738] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1760 +[2023-06-12 07:40:03,738] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1760 +[2023-06-12 07:40:03,739] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:03,739] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:03,739] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1760 +[2023-06-12 07:40:03,739] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:03,739] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1760 +[2023-06-12 07:40:03,739] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1760 +[2023-06-12 07:40:03,739] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:03,739] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1760 +[2023-06-12 07:40:03,739] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:03,739] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1760 +[2023-06-12 07:40:03,739] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 32768.0, reducing to 16384.0 +[2023-06-12 07:40:03,739] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:03,739] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:05,990] [INFO] [logging.py:96:log_dist] [Rank 0] step=1770, skipped=16, lr=[2.6833792919797152e-05, 2.6833792919797152e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:05,999] [INFO] [timer.py:215:stop] epoch=0/micro_step=1770/global_step=1770, RunningAvgSamplesPerSec=127.98976375922193, CurrSamplesPerSec=127.46101936353881, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:08,497] [INFO] [logging.py:96:log_dist] [Rank 0] step=1780, skipped=16, lr=[2.6620880202842324e-05, 2.6620880202842324e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:08,506] [INFO] [timer.py:215:stop] epoch=0/micro_step=1780/global_step=1780, RunningAvgSamplesPerSec=127.9889938155736, CurrSamplesPerSec=127.24061605901971, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:11,012] [INFO] [logging.py:96:log_dist] [Rank 0] step=1790, skipped=16, lr=[2.6407849358013358e-05, 2.6407849358013358e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:11,021] [INFO] [timer.py:215:stop] epoch=0/micro_step=1790/global_step=1790, RunningAvgSamplesPerSec=127.98586912236219, CurrSamplesPerSec=127.06715113692091, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:13,523] [INFO] [logging.py:96:log_dist] [Rank 0] step=1800, skipped=16, lr=[2.6194715910751803e-05, 2.6194715910751803e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:13,532] [INFO] [timer.py:215:stop] epoch=0/micro_step=1800/global_step=1800, RunningAvgSamplesPerSec=127.98419696887774, CurrSamplesPerSec=128.00781297686626, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:16,034] [INFO] [logging.py:96:log_dist] [Rank 0] step=1810, skipped=16, lr=[2.598149539397672e-05, 2.598149539397672e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:16,044] [INFO] [timer.py:215:stop] epoch=0/micro_step=1810/global_step=1810, RunningAvgSamplesPerSec=127.98218899027498, CurrSamplesPerSec=127.46259296085364, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:18,544] [INFO] [logging.py:96:log_dist] [Rank 0] step=1820, skipped=16, lr=[2.576820334695273e-05, 2.576820334695273e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:18,554] [INFO] [timer.py:215:stop] epoch=0/micro_step=1820/global_step=1820, RunningAvgSamplesPerSec=127.98065290013902, CurrSamplesPerSec=127.3195545352786, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:21,058] [INFO] [logging.py:96:log_dist] [Rank 0] step=1830, skipped=16, lr=[2.5554855314157468e-05, 2.5554855314157468e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:21,068] [INFO] [timer.py:215:stop] epoch=0/micro_step=1830/global_step=1830, RunningAvgSamplesPerSec=127.97801155570318, CurrSamplesPerSec=126.86369341983878, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:23,570] [INFO] [logging.py:96:log_dist] [Rank 0] step=1840, skipped=16, lr=[2.5341466844148775e-05, 2.5341466844148775e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:23,579] [INFO] [timer.py:215:stop] epoch=0/micro_step=1840/global_step=1840, RunningAvgSamplesPerSec=127.97610936228, CurrSamplesPerSec=127.60292021877873, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:26,079] [INFO] [logging.py:96:log_dist] [Rank 0] step=1850, skipped=16, lr=[2.5128053488431502e-05, 2.5128053488431502e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:26,088] [INFO] [timer.py:215:stop] epoch=0/micro_step=1850/global_step=1850, RunningAvgSamplesPerSec=127.9749128631184, CurrSamplesPerSec=128.07988380814604, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:28,591] [INFO] [logging.py:96:log_dist] [Rank 0] step=1860, skipped=16, lr=[2.4914630800324114e-05, 2.4914630800324114e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:28,600] [INFO] [timer.py:215:stop] epoch=0/micro_step=1860/global_step=1860, RunningAvgSamplesPerSec=127.97290021634043, CurrSamplesPerSec=126.6620815135535, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:29,083] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:29,084] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:29,084] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:29,084] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:29,084] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:29,084] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:29,084] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:29,084] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:29,085] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:29,085] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:29,085] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:29,085] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:29,085] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:29,085] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:29,085] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:29,085] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:29,580] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1863 +[2023-06-12 07:40:29,580] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1863 +[2023-06-12 07:40:29,580] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1863 +[2023-06-12 07:40:29,581] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:29,580] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1863 +[2023-06-12 07:40:29,581] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:29,581] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:29,580] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1863 +[2023-06-12 07:40:29,581] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:29,580] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1863 +[2023-06-12 07:40:29,581] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:29,581] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 32768.0, reducing to 16384.0 +[2023-06-12 07:40:29,580] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1863 +[2023-06-12 07:40:29,581] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:29,580] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1863 +[2023-06-12 07:40:29,581] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:29,581] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:31,078] [INFO] [logging.py:96:log_dist] [Rank 0] step=1870, skipped=17, lr=[2.472255525721801e-05, 2.472255525721801e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:31,087] [INFO] [timer.py:215:stop] epoch=0/micro_step=1870/global_step=1870, RunningAvgSamplesPerSec=127.97781932937943, CurrSamplesPerSec=127.72374205876419, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:33,586] [INFO] [logging.py:96:log_dist] [Rank 0] step=1880, skipped=17, lr=[2.4509157688484295e-05, 2.4509157688484295e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:33,596] [INFO] [timer.py:215:stop] epoch=0/micro_step=1880/global_step=1880, RunningAvgSamplesPerSec=127.97675106399706, CurrSamplesPerSec=127.58933448421077, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:36,100] [INFO] [logging.py:96:log_dist] [Rank 0] step=1890, skipped=17, lr=[2.4295795891770427e-05, 2.4295795891770427e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:36,109] [INFO] [timer.py:215:stop] epoch=0/micro_step=1890/global_step=1890, RunningAvgSamplesPerSec=127.9742864775827, CurrSamplesPerSec=127.54701891095695, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:38,614] [INFO] [logging.py:96:log_dist] [Rank 0] step=1900, skipped=17, lr=[2.408248541663735e-05, 2.408248541663735e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:38,623] [INFO] [timer.py:215:stop] epoch=0/micro_step=1900/global_step=1900, RunningAvgSamplesPerSec=127.97192220641512, CurrSamplesPerSec=127.32897575376956, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:41,123] [INFO] [logging.py:96:log_dist] [Rank 0] step=1910, skipped=17, lr=[2.386924180890572e-05, 2.386924180890572e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:41,132] [INFO] [timer.py:215:stop] epoch=0/micro_step=1910/global_step=1910, RunningAvgSamplesPerSec=127.97079360206841, CurrSamplesPerSec=127.90717186185182, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:43,633] [INFO] [logging.py:96:log_dist] [Rank 0] step=1920, skipped=17, lr=[2.3656080609522975e-05, 2.3656080609522975e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:43,642] [INFO] [timer.py:215:stop] epoch=0/micro_step=1920/global_step=1920, RunningAvgSamplesPerSec=127.9695497479756, CurrSamplesPerSec=128.14273711867773, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:46,144] [INFO] [logging.py:96:log_dist] [Rank 0] step=1930, skipped=17, lr=[2.3443017353430764e-05, 2.3443017353430764e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:46,153] [INFO] [timer.py:215:stop] epoch=0/micro_step=1930/global_step=1930, RunningAvgSamplesPerSec=127.96782046795583, CurrSamplesPerSec=127.90558726830895, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:48,654] [INFO] [logging.py:96:log_dist] [Rank 0] step=1940, skipped=17, lr=[2.3230067568432687e-05, 2.3230067568432687e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:48,663] [INFO] [timer.py:215:stop] epoch=0/micro_step=1940/global_step=1940, RunningAvgSamplesPerSec=127.96649297722442, CurrSamplesPerSec=127.75535130936699, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:51,161] [INFO] [logging.py:96:log_dist] [Rank 0] step=1950, skipped=17, lr=[2.301724677406277e-05, 2.301724677406277e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:51,170] [INFO] [timer.py:215:stop] epoch=0/micro_step=1950/global_step=1950, RunningAvgSamplesPerSec=127.96594524180867, CurrSamplesPerSec=127.3443184136246, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:53,675] [INFO] [logging.py:96:log_dist] [Rank 0] step=1960, skipped=17, lr=[2.280457048045429e-05, 2.280457048045429e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:53,684] [INFO] [timer.py:215:stop] epoch=0/micro_step=1960/global_step=1960, RunningAvgSamplesPerSec=127.96365830567592, CurrSamplesPerSec=127.54144359364696, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:54,922] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:54,923] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:54,923] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:54,923] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:54,923] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:54,923] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:54,923] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:54,923] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:54,923] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:54,923] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:54,923] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:54,923] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:54,923] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:54,923] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:54,923] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:40:54,924] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:40:55,168] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1965 +[2023-06-12 07:40:55,169] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:55,169] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1965 +[2023-06-12 07:40:55,169] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:55,169] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1965 +[2023-06-12 07:40:55,169] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1965 +[2023-06-12 07:40:55,169] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:55,169] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1965 +[2023-06-12 07:40:55,169] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:55,169] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1965 +[2023-06-12 07:40:55,169] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:55,169] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:55,169] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1965 +[2023-06-12 07:40:55,169] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:55,169] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 1965 +[2023-06-12 07:40:55,169] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:40:55,169] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 32768.0, reducing to 16384.0 +[2023-06-12 07:40:56,163] [INFO] [logging.py:96:log_dist] [Rank 0] step=1970, skipped=18, lr=[2.261329817501475e-05, 2.261329817501475e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:56,173] [INFO] [timer.py:215:stop] epoch=0/micro_step=1970/global_step=1970, RunningAvgSamplesPerSec=127.96797590807468, CurrSamplesPerSec=127.84077448703759, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:40:58,675] [INFO] [logging.py:96:log_dist] [Rank 0] step=1980, skipped=18, lr=[2.240093912464302e-05, 2.240093912464302e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:40:58,684] [INFO] [timer.py:215:stop] epoch=0/micro_step=1980/global_step=1980, RunningAvgSamplesPerSec=127.96626928620911, CurrSamplesPerSec=127.60680238865115, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:01,187] [INFO] [logging.py:96:log_dist] [Rank 0] step=1990, skipped=18, lr=[2.218876949082127e-05, 2.218876949082127e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:01,197] [INFO] [timer.py:215:stop] epoch=0/micro_step=1990/global_step=1990, RunningAvgSamplesPerSec=127.96435508196535, CurrSamplesPerSec=127.37380602829374, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:03,699] [INFO] [logging.py:96:log_dist] [Rank 0] step=2000, skipped=18, lr=[2.197680473622697e-05, 2.197680473622697e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:03,708] [INFO] [timer.py:215:stop] epoch=0/micro_step=2000/global_step=2000, RunningAvgSamplesPerSec=127.96279629489702, CurrSamplesPerSec=126.87340708412147, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:06,211] [INFO] [logging.py:96:log_dist] [Rank 0] step=2010, skipped=18, lr=[2.1765060308606246e-05, 2.1765060308606246e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:06,221] [INFO] [timer.py:215:stop] epoch=0/micro_step=2010/global_step=2010, RunningAvgSamplesPerSec=127.96080050720353, CurrSamplesPerSec=127.31279144328215, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:08,721] [INFO] [logging.py:96:log_dist] [Rank 0] step=2020, skipped=18, lr=[2.1553551639648015e-05, 2.1553551639648015e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:08,730] [INFO] [timer.py:215:stop] epoch=0/micro_step=2020/global_step=2020, RunningAvgSamplesPerSec=127.9598035855475, CurrSamplesPerSec=127.40935433253246, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:11,234] [INFO] [logging.py:96:log_dist] [Rank 0] step=2030, skipped=18, lr=[2.1342294143859416e-05, 2.1342294143859416e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:11,243] [INFO] [timer.py:215:stop] epoch=0/micro_step=2030/global_step=2030, RunningAvgSamplesPerSec=127.95767612643242, CurrSamplesPerSec=127.7106166599426, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:13,745] [INFO] [logging.py:96:log_dist] [Rank 0] step=2040, skipped=18, lr=[2.1131303217442347e-05, 2.1131303217442347e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:13,755] [INFO] [timer.py:215:stop] epoch=0/micro_step=2040/global_step=2040, RunningAvgSamplesPerSec=127.95616404302373, CurrSamplesPerSec=127.32184931903191, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:16,258] [INFO] [logging.py:96:log_dist] [Rank 0] step=2050, skipped=18, lr=[2.092059423717145e-05, 2.092059423717145e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:16,267] [INFO] [timer.py:215:stop] epoch=0/micro_step=2050/global_step=2050, RunningAvgSamplesPerSec=127.9542541140684, CurrSamplesPerSec=127.61663018694983, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:18,770] [INFO] [logging.py:96:log_dist] [Rank 0] step=2060, skipped=18, lr=[2.0710182559273457e-05, 2.0710182559273457e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:18,779] [INFO] [timer.py:215:stop] epoch=0/micro_step=2060/global_step=2060, RunningAvgSamplesPerSec=127.95262418743026, CurrSamplesPerSec=127.2794695555859, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:20,517] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:20,518] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:20,518] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:20,518] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:20,518] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:20,518] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:20,518] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:20,518] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:20,518] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:20,518] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:20,518] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:20,518] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:20,518] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:20,519] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:20,518] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:20,519] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2067 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2067 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2067 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2067 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2067 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2067 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2067 +[2023-06-12 07:41:20,764] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 32768.0, reducing to 16384.0 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2067 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:20,764] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:21,257] [INFO] [logging.py:96:log_dist] [Rank 0] step=2070, skipped=19, lr=[2.052107891717339e-05, 2.052107891717339e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:21,266] [INFO] [timer.py:215:stop] epoch=0/micro_step=2070/global_step=2070, RunningAvgSamplesPerSec=127.95708082669086, CurrSamplesPerSec=127.8349299477108, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:23,766] [INFO] [logging.py:96:log_dist] [Rank 0] step=2080, skipped=19, lr=[2.0311274341687408e-05, 2.0311274341687408e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:23,776] [INFO] [timer.py:215:stop] epoch=0/micro_step=2080/global_step=2080, RunningAvgSamplesPerSec=127.95606859567125, CurrSamplesPerSec=126.9831187740841, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:26,275] [INFO] [logging.py:96:log_dist] [Rank 0] step=2090, skipped=19, lr=[2.0101811475103458e-05, 2.0101811475103458e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:26,284] [INFO] [timer.py:215:stop] epoch=0/micro_step=2090/global_step=2090, RunningAvgSamplesPerSec=127.95531244114856, CurrSamplesPerSec=127.5664151158591, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:28,788] [INFO] [logging.py:96:log_dist] [Rank 0] step=2100, skipped=19, lr=[1.9892705582832933e-05, 1.9892705582832933e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:28,797] [INFO] [timer.py:215:stop] epoch=0/micro_step=2100/global_step=2100, RunningAvgSamplesPerSec=127.95344641526509, CurrSamplesPerSec=127.59709740685074, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:31,301] [INFO] [logging.py:96:log_dist] [Rank 0] step=2110, skipped=19, lr=[1.9683971904271375e-05, 1.9683971904271375e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:31,310] [INFO] [timer.py:215:stop] epoch=0/micro_step=2110/global_step=2110, RunningAvgSamplesPerSec=127.95152130347918, CurrSamplesPerSec=127.17623426141402, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:33,816] [INFO] [logging.py:96:log_dist] [Rank 0] step=2120, skipped=19, lr=[1.947562565168781e-05, 1.947562565168781e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:33,825] [INFO] [timer.py:215:stop] epoch=0/micro_step=2120/global_step=2120, RunningAvgSamplesPerSec=127.9490116425704, CurrSamplesPerSec=127.3644990358775, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:36,328] [INFO] [logging.py:96:log_dist] [Rank 0] step=2130, skipped=19, lr=[1.9267682009116103e-05, 1.9267682009116103e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:36,337] [INFO] [timer.py:215:stop] epoch=0/micro_step=2130/global_step=2130, RunningAvgSamplesPerSec=127.9474658835021, CurrSamplesPerSec=127.60777296802907, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:38,839] [INFO] [logging.py:96:log_dist] [Rank 0] step=2140, skipped=19, lr=[1.906015613124839e-05, 1.906015613124839e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:38,848] [INFO] [timer.py:215:stop] epoch=0/micro_step=2140/global_step=2140, RunningAvgSamplesPerSec=127.94610718955609, CurrSamplesPerSec=127.55974700507035, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:41,350] [INFO] [logging.py:96:log_dist] [Rank 0] step=2150, skipped=19, lr=[1.8853063142330564e-05, 1.8853063142330564e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:41,359] [INFO] [timer.py:215:stop] epoch=0/micro_step=2150/global_step=2150, RunningAvgSamplesPerSec=127.94478553377729, CurrSamplesPerSec=128.05654352154778, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:43,864] [INFO] [logging.py:96:log_dist] [Rank 0] step=2160, skipped=19, lr=[1.8646418135060102e-05, 1.8646418135060102e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:43,873] [INFO] [timer.py:215:stop] epoch=0/micro_step=2160/global_step=2160, RunningAvgSamplesPerSec=127.94280242462052, CurrSamplesPerSec=127.37054238259638, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:46,112] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:46,113] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:46,113] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:46,113] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:46,113] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:46,113] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:46,113] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:46,113] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:46,113] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:46,113] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:46,113] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:46,113] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:46,113] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:46,113] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:41:46,114] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:46,114] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:41:46,375] [INFO] [logging.py:96:log_dist] [Rank 0] step=2170, skipped=19, lr=[1.844023616948608e-05, 1.844023616948608e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:46,384] [INFO] [timer.py:215:stop] epoch=0/micro_step=2170/global_step=2170, RunningAvgSamplesPerSec=127.94144284801101, CurrSamplesPerSec=127.95838755592673, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:46,610] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2170 +[2023-06-12 07:41:46,610] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2170 +[2023-06-12 07:41:46,610] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2170 +[2023-06-12 07:41:46,611] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:46,611] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:46,610] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2170 +[2023-06-12 07:41:46,611] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:46,610] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2170 +[2023-06-12 07:41:46,610] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2170 +[2023-06-12 07:41:46,611] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:46,611] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:46,611] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2170 +[2023-06-12 07:41:46,611] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:46,611] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2170 +[2023-06-12 07:41:46,611] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:46,611] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:41:46,611] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 32768.0, reducing to 16384.0 +[2023-06-12 07:41:48,862] [INFO] [logging.py:96:log_dist] [Rank 0] step=2180, skipped=20, lr=[1.825508072107439e-05, 1.825508072107439e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:48,871] [INFO] [timer.py:215:stop] epoch=0/micro_step=2180/global_step=2180, RunningAvgSamplesPerSec=127.94576083373323, CurrSamplesPerSec=128.050190571141, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:51,375] [INFO] [logging.py:96:log_dist] [Rank 0] step=2190, skipped=20, lr=[1.8049819903415228e-05, 1.8049819903415228e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:51,385] [INFO] [timer.py:215:stop] epoch=0/micro_step=2190/global_step=2190, RunningAvgSamplesPerSec=127.94387372821984, CurrSamplesPerSec=128.15790941139176, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:53,883] [INFO] [logging.py:96:log_dist] [Rank 0] step=2200, skipped=20, lr=[1.7845065606841472e-05, 1.7845065606841472e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:53,893] [INFO] [timer.py:215:stop] epoch=0/micro_step=2200/global_step=2200, RunningAvgSamplesPerSec=127.9432796111559, CurrSamplesPerSec=127.48438522554252, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:56,395] [INFO] [logging.py:96:log_dist] [Rank 0] step=2210, skipped=20, lr=[1.76408327536094e-05, 1.76408327536094e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:56,405] [INFO] [timer.py:215:stop] epoch=0/micro_step=2210/global_step=2210, RunningAvgSamplesPerSec=127.94174684998022, CurrSamplesPerSec=127.31411985107543, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:41:58,906] [INFO] [logging.py:96:log_dist] [Rank 0] step=2220, skipped=20, lr=[1.743713622797311e-05, 1.743713622797311e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:41:58,915] [INFO] [timer.py:215:stop] epoch=0/micro_step=2220/global_step=2220, RunningAvgSamplesPerSec=127.94062801695311, CurrSamplesPerSec=127.3644990358775, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:01,418] [INFO] [logging.py:96:log_dist] [Rank 0] step=2230, skipped=20, lr=[1.723399087509974e-05, 1.723399087509974e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:01,427] [INFO] [timer.py:215:stop] epoch=0/micro_step=2230/global_step=2230, RunningAvgSamplesPerSec=127.93906558444975, CurrSamplesPerSec=127.38347707162998, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:03,932] [INFO] [logging.py:96:log_dist] [Rank 0] step=2240, skipped=20, lr=[1.7031411499987605e-05, 1.7031411499987605e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:03,941] [INFO] [timer.py:215:stop] epoch=0/micro_step=2240/global_step=2240, RunningAvgSamplesPerSec=127.9370898887745, CurrSamplesPerSec=127.03552076264248, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:06,440] [INFO] [logging.py:96:log_dist] [Rank 0] step=2250, skipped=20, lr=[1.6829412866387228e-05, 1.6829412866387228e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:06,450] [INFO] [timer.py:215:stop] epoch=0/micro_step=2250/global_step=2250, RunningAvgSamplesPerSec=127.93651448591038, CurrSamplesPerSec=128.44514623778161, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:08,950] [INFO] [logging.py:96:log_dist] [Rank 0] step=2260, skipped=20, lr=[1.6628009695725346e-05, 1.6628009695725346e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:08,959] [INFO] [timer.py:215:stop] epoch=0/micro_step=2260/global_step=2260, RunningAvgSamplesPerSec=127.93573474530254, CurrSamplesPerSec=127.5608381027689, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:10,680] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2266 +[2023-06-12 07:42:10,680] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2266 +[2023-06-12 07:42:10,680] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2266 +[2023-06-12 07:42:10,682] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:42:10,682] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:42:10,680] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2266 +[2023-06-12 07:42:10,682] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:42:10,682] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 16384.0, reducing to 8192.0 +[2023-06-12 07:42:10,681] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2266 +[2023-06-12 07:42:10,682] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:42:10,681] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2266 +[2023-06-12 07:42:10,682] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:42:10,681] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2266 +[2023-06-12 07:42:10,681] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2266 +[2023-06-12 07:42:10,682] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:42:10,682] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:42:10,682] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:42:11,426] [INFO] [logging.py:96:log_dist] [Rank 0] step=2270, skipped=21, lr=[1.6447268095247876e-05, 1.6447268095247876e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:11,436] [INFO] [timer.py:215:stop] epoch=0/micro_step=2270/global_step=2270, RunningAvgSamplesPerSec=127.94218766985102, CurrSamplesPerSec=127.98193614335135, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:13,939] [INFO] [logging.py:96:log_dist] [Rank 0] step=2280, skipped=21, lr=[1.6247036705412644e-05, 1.6247036705412644e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:13,948] [INFO] [timer.py:215:stop] epoch=0/micro_step=2280/global_step=2280, RunningAvgSamplesPerSec=127.94069686865086, CurrSamplesPerSec=127.60279890477639, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:16,447] [INFO] [logging.py:96:log_dist] [Rank 0] step=2290, skipped=21, lr=[1.604744322141682e-05, 1.604744322141682e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:16,456] [INFO] [timer.py:215:stop] epoch=0/micro_step=2290/global_step=2290, RunningAvgSamplesPerSec=127.93998311179779, CurrSamplesPerSec=127.75875631570331, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:17,680] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2294 +[2023-06-12 07:42:17,680] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2294 +[2023-06-12 07:42:17,681] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:42:17,680] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2294 +[2023-06-12 07:42:17,681] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:42:17,681] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 8192.0, reducing to 4096.0 +[2023-06-12 07:42:17,680] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2294 +[2023-06-12 07:42:17,681] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:42:17,680] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2294 +[2023-06-12 07:42:17,681] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:42:17,680] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2294 +[2023-06-12 07:42:17,681] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:42:17,680] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2294 +[2023-06-12 07:42:17,681] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:42:17,680] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2294 +[2023-06-12 07:42:17,681] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:42:17,681] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 8192.0 to 4096.0 +[2023-06-12 07:42:18,927] [INFO] [logging.py:96:log_dist] [Rank 0] step=2300, skipped=22, lr=[1.5868366518677517e-05, 1.5868366518677517e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:18,937] [INFO] [timer.py:215:stop] epoch=0/micro_step=2300/global_step=2300, RunningAvgSamplesPerSec=127.94571677458067, CurrSamplesPerSec=128.19842724554016, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:21,437] [INFO] [logging.py:96:log_dist] [Rank 0] step=2310, skipped=22, lr=[1.567002509112022e-05, 1.567002509112022e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:21,446] [INFO] [timer.py:215:stop] epoch=0/micro_step=2310/global_step=2310, RunningAvgSamplesPerSec=127.94487483763727, CurrSamplesPerSec=127.97498047733511, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:23,951] [INFO] [logging.py:96:log_dist] [Rank 0] step=2320, skipped=22, lr=[1.5472363621341286e-05, 1.5472363621341286e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:23,960] [INFO] [timer.py:215:stop] epoch=0/micro_step=2320/global_step=2320, RunningAvgSamplesPerSec=127.94287116711554, CurrSamplesPerSec=127.68522424252802, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:26,465] [INFO] [logging.py:96:log_dist] [Rank 0] step=2330, skipped=22, lr=[1.5275396514679986e-05, 1.5275396514679986e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:26,474] [INFO] [timer.py:215:stop] epoch=0/micro_step=2330/global_step=2330, RunningAvgSamplesPerSec=127.94092809650165, CurrSamplesPerSec=127.10409321503418, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:28,976] [INFO] [logging.py:96:log_dist] [Rank 0] step=2340, skipped=22, lr=[1.5079138125871195e-05, 1.5079138125871195e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:28,986] [INFO] [timer.py:215:stop] epoch=0/micro_step=2340/global_step=2340, RunningAvgSamplesPerSec=127.93967047412413, CurrSamplesPerSec=127.43076543303648, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:31,490] [INFO] [logging.py:96:log_dist] [Rank 0] step=2350, skipped=22, lr=[1.4883602757999259e-05, 1.4883602757999259e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:31,499] [INFO] [timer.py:215:stop] epoch=0/micro_step=2350/global_step=2350, RunningAvgSamplesPerSec=127.9379248716125, CurrSamplesPerSec=126.83528049858015, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:34,001] [INFO] [logging.py:96:log_dist] [Rank 0] step=2360, skipped=22, lr=[1.468880466145559e-05, 1.468880466145559e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:34,011] [INFO] [timer.py:215:stop] epoch=0/micro_step=2360/global_step=2360, RunningAvgSamplesPerSec=127.93658681016575, CurrSamplesPerSec=127.8181298734939, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:36,509] [INFO] [logging.py:96:log_dist] [Rank 0] step=2370, skipped=22, lr=[1.4494758032900119e-05, 1.4494758032900119e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:36,518] [INFO] [timer.py:215:stop] epoch=0/micro_step=2370/global_step=2370, RunningAvgSamplesPerSec=127.93609815872871, CurrSamplesPerSec=128.24791576887466, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:39,019] [INFO] [logging.py:96:log_dist] [Rank 0] step=2380, skipped=22, lr=[1.4301477014226664e-05, 1.4301477014226664e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:39,028] [INFO] [timer.py:215:stop] epoch=0/micro_step=2380/global_step=2380, RunningAvgSamplesPerSec=127.9351521397032, CurrSamplesPerSec=128.23504997831185, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:41,530] [INFO] [logging.py:96:log_dist] [Rank 0] step=2390, skipped=22, lr=[1.4108975691532272e-05, 1.4108975691532272e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:41,539] [INFO] [timer.py:215:stop] epoch=0/micro_step=2390/global_step=2390, RunningAvgSamplesPerSec=127.934059022353, CurrSamplesPerSec=127.43875107530047, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:43,023] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:42:43,024] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:42:43,024] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:42:43,024] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:42:43,024] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:42:43,025] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:42:43,025] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:42:43,024] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:42:43,025] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:42:43,024] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:42:43,024] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:42:43,025] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:42:43,024] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:42:43,025] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:42:43,025] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:42:43,025] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 4096.0 to 8192.0 +[2023-06-12 07:42:44,042] [INFO] [logging.py:96:log_dist] [Rank 0] step=2400, skipped=22, lr=[1.3917268094090663e-05, 1.3917268094090663e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:44,052] [INFO] [timer.py:215:stop] epoch=0/micro_step=2400/global_step=2400, RunningAvgSamplesPerSec=127.93255866755182, CurrSamplesPerSec=126.79142731096923, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:46,550] [INFO] [logging.py:96:log_dist] [Rank 0] step=2410, skipped=22, lr=[1.3726368193329758e-05, 1.3726368193329758e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:46,559] [INFO] [timer.py:215:stop] epoch=0/micro_step=2410/global_step=2410, RunningAvgSamplesPerSec=127.93211119703683, CurrSamplesPerSec=127.76897242382472, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:49,063] [INFO] [logging.py:96:log_dist] [Rank 0] step=2420, skipped=22, lr=[1.3536289901813486e-05, 1.3536289901813486e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:49,072] [INFO] [timer.py:215:stop] epoch=0/micro_step=2420/global_step=2420, RunningAvgSamplesPerSec=127.93055843177406, CurrSamplesPerSec=127.18659846372817, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:51,577] [INFO] [logging.py:96:log_dist] [Rank 0] step=2430, skipped=22, lr=[1.334704707222787e-05, 1.334704707222787e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:51,586] [INFO] [timer.py:215:stop] epoch=0/micro_step=2430/global_step=2430, RunningAvgSamplesPerSec=127.92883428631895, CurrSamplesPerSec=127.76349930558001, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:54,084] [INFO] [logging.py:96:log_dist] [Rank 0] step=2440, skipped=22, lr=[1.3158653496371395e-05, 1.3158653496371395e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:54,093] [INFO] [timer.py:215:stop] epoch=0/micro_step=2440/global_step=2440, RunningAvgSamplesPerSec=127.92847424204895, CurrSamplesPerSec=127.88925605345104, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:56,594] [INFO] [logging.py:96:log_dist] [Rank 0] step=2450, skipped=22, lr=[1.2971122904149943e-05, 1.2971122904149943e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:56,603] [INFO] [timer.py:215:stop] epoch=0/micro_step=2450/global_step=2450, RunningAvgSamplesPerSec=127.92778142730064, CurrSamplesPerSec=127.34093546223303, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:42:59,104] [INFO] [logging.py:96:log_dist] [Rank 0] step=2460, skipped=22, lr=[1.2784468962576136e-05, 1.2784468962576136e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:42:59,113] [INFO] [timer.py:215:stop] epoch=0/micro_step=2460/global_step=2460, RunningAvgSamplesPerSec=127.92687485068114, CurrSamplesPerSec=127.9044902650094, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:01,614] [INFO] [logging.py:96:log_dist] [Rank 0] step=2470, skipped=22, lr=[1.2598705274773297e-05, 1.2598705274773297e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:01,623] [INFO] [timer.py:215:stop] epoch=0/micro_step=2470/global_step=2470, RunningAvgSamplesPerSec=127.92595681046971, CurrSamplesPerSec=127.39919564963584, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:04,129] [INFO] [logging.py:96:log_dist] [Rank 0] step=2480, skipped=22, lr=[1.2413845378984126e-05, 1.2413845378984126e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:04,138] [INFO] [timer.py:215:stop] epoch=0/micro_step=2480/global_step=2480, RunningAvgSamplesPerSec=127.92415049034301, CurrSamplesPerSec=127.15201753746084, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:06,642] [INFO] [logging.py:96:log_dist] [Rank 0] step=2490, skipped=22, lr=[1.2229902747583971e-05, 1.2229902747583971e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:06,651] [INFO] [timer.py:215:stop] epoch=0/micro_step=2490/global_step=2490, RunningAvgSamplesPerSec=127.92266844770472, CurrSamplesPerSec=127.43342720258859, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:08,138] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:08,138] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:08,139] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:08,139] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:43:08,139] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:43:08,138] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:08,139] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:43:08,138] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:08,139] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:43:08,139] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:43:08,139] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:08,139] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:43:08,139] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:08,139] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:08,139] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:43:08,139] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:43:09,155] [INFO] [logging.py:96:log_dist] [Rank 0] step=2500, skipped=22, lr=[1.204689078609902e-05, 1.204689078609902e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:09,164] [INFO] [timer.py:215:stop] epoch=0/micro_step=2500/global_step=2500, RunningAvgSamplesPerSec=127.92108580463508, CurrSamplesPerSec=127.89339939968555, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:11,672] [INFO] [logging.py:96:log_dist] [Rank 0] step=2510, skipped=22, lr=[1.1864822832229319e-05, 1.1864822832229319e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:11,681] [INFO] [timer.py:215:stop] epoch=0/micro_step=2510/global_step=2510, RunningAvgSamplesPerSec=127.91892932977089, CurrSamplesPerSec=127.50158215973592, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:14,183] [INFO] [logging.py:96:log_dist] [Rank 0] step=2520, skipped=22, lr=[1.1683712154876714e-05, 1.1683712154876714e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:14,192] [INFO] [timer.py:215:stop] epoch=0/micro_step=2520/global_step=2520, RunningAvgSamplesPerSec=127.91787676305164, CurrSamplesPerSec=127.62014914942232, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:16,693] [INFO] [logging.py:96:log_dist] [Rank 0] step=2530, skipped=22, lr=[1.1503571953177883e-05, 1.1503571953177883e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:16,702] [INFO] [timer.py:215:stop] epoch=0/micro_step=2530/global_step=2530, RunningAvgSamplesPerSec=127.91699322521518, CurrSamplesPerSec=127.72909021697754, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:19,204] [INFO] [logging.py:96:log_dist] [Rank 0] step=2540, skipped=22, lr=[1.1324415355542328e-05, 1.1324415355542328e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:19,213] [INFO] [timer.py:215:stop] epoch=0/micro_step=2540/global_step=2540, RunningAvgSamplesPerSec=127.91597448134003, CurrSamplesPerSec=127.65874912852549, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:21,715] [INFO] [logging.py:96:log_dist] [Rank 0] step=2550, skipped=22, lr=[1.1146255418695634e-05, 1.1146255418695634e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:21,725] [INFO] [timer.py:215:stop] epoch=0/micro_step=2550/global_step=2550, RunningAvgSamplesPerSec=127.91492001992398, CurrSamplesPerSec=127.39363324781434, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:24,226] [INFO] [logging.py:96:log_dist] [Rank 0] step=2560, skipped=22, lr=[1.0969105126727903e-05, 1.0969105126727903e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:24,235] [INFO] [timer.py:215:stop] epoch=0/micro_step=2560/global_step=2560, RunningAvgSamplesPerSec=127.91403594874994, CurrSamplesPerSec=127.22758976322869, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:26,736] [INFO] [logging.py:96:log_dist] [Rank 0] step=2570, skipped=22, lr=[1.0792977390147474e-05, 1.0792977390147474e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:26,745] [INFO] [timer.py:215:stop] epoch=0/micro_step=2570/global_step=2570, RunningAvgSamplesPerSec=127.91318236788061, CurrSamplesPerSec=127.6330132152139, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:29,253] [INFO] [logging.py:96:log_dist] [Rank 0] step=2580, skipped=22, lr=[1.0617885044940063e-05, 1.0617885044940063e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:29,262] [INFO] [timer.py:215:stop] epoch=0/micro_step=2580/global_step=2580, RunningAvgSamplesPerSec=127.91095123385954, CurrSamplesPerSec=126.65491001328662, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:31,762] [INFO] [logging.py:96:log_dist] [Rank 0] step=2590, skipped=22, lr=[1.0443840851633227e-05, 1.0443840851633227e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:31,771] [INFO] [timer.py:215:stop] epoch=0/micro_step=2590/global_step=2590, RunningAvgSamplesPerSec=127.91048525118175, CurrSamplesPerSec=127.18310336952804, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:33,257] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:33,258] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:33,258] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:33,258] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:43:33,258] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:43:33,258] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:33,258] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:43:33,258] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:33,258] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:43:33,258] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:33,258] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:43:33,258] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:33,258] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:43:33,258] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:43:33,258] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:43:33,258] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:43:33,503] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2596 +[2023-06-12 07:43:33,503] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:43:33,503] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2596 +[2023-06-12 07:43:33,503] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2596 +[2023-06-12 07:43:33,503] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2596 +[2023-06-12 07:43:33,503] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2596 +[2023-06-12 07:43:33,503] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:43:33,504] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:43:33,504] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:43:33,504] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:43:33,504] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2596 +[2023-06-12 07:43:33,504] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2596 +[2023-06-12 07:43:33,504] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:43:33,504] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:43:33,504] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 32768.0, reducing to 16384.0 +[2023-06-12 07:43:33,504] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2596 +[2023-06-12 07:43:33,504] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:43:34,249] [INFO] [logging.py:96:log_dist] [Rank 0] step=2600, skipped=23, lr=[1.0288107732566627e-05, 1.0288107732566627e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:34,258] [INFO] [timer.py:215:stop] epoch=0/micro_step=2600/global_step=2600, RunningAvgSamplesPerSec=127.91421499051327, CurrSamplesPerSec=127.5827852529218, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:36,761] [INFO] [logging.py:96:log_dist] [Rank 0] step=2610, skipped=23, lr=[1.0116089908795365e-05, 1.0116089908795365e-05], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:36,770] [INFO] [timer.py:215:stop] epoch=0/micro_step=2610/global_step=2610, RunningAvgSamplesPerSec=127.91300019857147, CurrSamplesPerSec=127.48692814182425, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:39,273] [INFO] [logging.py:96:log_dist] [Rank 0] step=2620, skipped=23, lr=[9.945156807173722e-06, 9.945156807173722e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:39,283] [INFO] [timer.py:215:stop] epoch=0/micro_step=2620/global_step=2620, RunningAvgSamplesPerSec=127.91168849945691, CurrSamplesPerSec=127.4659823793483, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:41,782] [INFO] [logging.py:96:log_dist] [Rank 0] step=2630, skipped=23, lr=[9.775320885108399e-06, 9.775320885108399e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:41,791] [INFO] [timer.py:215:stop] epoch=0/micro_step=2630/global_step=2630, RunningAvgSamplesPerSec=127.91115165418711, CurrSamplesPerSec=127.85417023887092, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:44,292] [INFO] [logging.py:96:log_dist] [Rank 0] step=2640, skipped=23, lr=[9.606594520044945e-06, 9.606594520044945e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:44,301] [INFO] [timer.py:215:stop] epoch=0/micro_step=2640/global_step=2640, RunningAvgSamplesPerSec=127.91042212495985, CurrSamplesPerSec=127.6322849913037, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:46,804] [INFO] [logging.py:96:log_dist] [Rank 0] step=2650, skipped=23, lr=[9.438990008565656e-06, 9.438990008565656e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:46,813] [INFO] [timer.py:215:stop] epoch=0/micro_step=2650/global_step=2650, RunningAvgSamplesPerSec=127.90919777198359, CurrSamplesPerSec=127.99231003233716, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:49,314] [INFO] [logging.py:96:log_dist] [Rank 0] step=2660, skipped=23, lr=[9.272519565493443e-06, 9.272519565493443e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:49,323] [INFO] [timer.py:215:stop] epoch=0/micro_step=2660/global_step=2660, RunningAvgSamplesPerSec=127.90847408833218, CurrSamplesPerSec=127.04754566528814, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:51,821] [INFO] [logging.py:96:log_dist] [Rank 0] step=2670, skipped=23, lr=[9.10719532300162e-06, 9.10719532300162e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:51,830] [INFO] [timer.py:215:stop] epoch=0/micro_step=2670/global_step=2670, RunningAvgSamplesPerSec=127.90840752849742, CurrSamplesPerSec=127.91594878319586, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:54,328] [INFO] [logging.py:96:log_dist] [Rank 0] step=2680, skipped=23, lr=[8.943029329729721e-06, 8.943029329729721e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:54,337] [INFO] [timer.py:215:stop] epoch=0/micro_step=2680/global_step=2680, RunningAvgSamplesPerSec=127.90816067102958, CurrSamplesPerSec=127.42653102881908, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:55,306] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2683 +[2023-06-12 07:43:55,306] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2683 +[2023-06-12 07:43:55,306] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2683 +[2023-06-12 07:43:55,307] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:43:55,307] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:43:55,306] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2683 +[2023-06-12 07:43:55,307] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:43:55,306] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2683 +[2023-06-12 07:43:55,306] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2683 +[2023-06-12 07:43:55,308] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:43:55,308] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 16384.0, reducing to 8192.0 +[2023-06-12 07:43:55,308] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:43:55,308] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:43:55,306] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2683 +[2023-06-12 07:43:55,306] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2683 +[2023-06-12 07:43:55,308] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:43:55,308] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:43:56,804] [INFO] [logging.py:96:log_dist] [Rank 0] step=2690, skipped=24, lr=[8.796280129060475e-06, 8.796280129060475e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:56,813] [INFO] [timer.py:215:stop] epoch=0/micro_step=2690/global_step=2690, RunningAvgSamplesPerSec=127.91388800137813, CurrSamplesPerSec=128.18642835926806, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:43:59,315] [INFO] [logging.py:96:log_dist] [Rank 0] step=2700, skipped=24, lr=[8.634347700284575e-06, 8.634347700284575e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:43:59,324] [INFO] [timer.py:215:stop] epoch=0/micro_step=2700/global_step=2700, RunningAvgSamplesPerSec=127.91300525188942, CurrSamplesPerSec=128.09027358262784, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:01,826] [INFO] [logging.py:96:log_dist] [Rank 0] step=2710, skipped=24, lr=[8.473607981316364e-06, 8.473607981316364e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:01,836] [INFO] [timer.py:215:stop] epoch=0/micro_step=2710/global_step=2710, RunningAvgSamplesPerSec=127.91189445714673, CurrSamplesPerSec=127.32776782732765, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:04,340] [INFO] [logging.py:96:log_dist] [Rank 0] step=2720, skipped=24, lr=[8.31407268668061e-06, 8.31407268668061e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:04,349] [INFO] [timer.py:215:stop] epoch=0/micro_step=2720/global_step=2720, RunningAvgSamplesPerSec=127.91060496861292, CurrSamplesPerSec=127.63944622067866, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:06,849] [INFO] [logging.py:96:log_dist] [Rank 0] step=2730, skipped=24, lr=[8.155753443125036e-06, 8.155753443125036e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:06,858] [INFO] [timer.py:215:stop] epoch=0/micro_step=2730/global_step=2730, RunningAvgSamplesPerSec=127.90996461141324, CurrSamplesPerSec=127.21649539256555, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:09,355] [INFO] [logging.py:96:log_dist] [Rank 0] step=2740, skipped=24, lr=[7.998661788772957e-06, 7.998661788772957e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:09,365] [INFO] [timer.py:215:stop] epoch=0/micro_step=2740/global_step=2740, RunningAvgSamplesPerSec=127.90994942487251, CurrSamplesPerSec=127.56568765171373, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:11,871] [INFO] [logging.py:96:log_dist] [Rank 0] step=2750, skipped=24, lr=[7.842809172282436e-06, 7.842809172282436e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:11,880] [INFO] [timer.py:215:stop] epoch=0/micro_step=2750/global_step=2750, RunningAvgSamplesPerSec=127.90815176213754, CurrSamplesPerSec=128.55439278045006, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:14,387] [INFO] [logging.py:96:log_dist] [Rank 0] step=2760, skipped=24, lr=[7.688206952011861e-06, 7.688206952011861e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:14,396] [INFO] [timer.py:215:stop] epoch=0/micro_step=2760/global_step=2760, RunningAvgSamplesPerSec=127.90637315179274, CurrSamplesPerSec=126.99273057915985, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:16,900] [INFO] [logging.py:96:log_dist] [Rank 0] step=2770, skipped=24, lr=[7.534866395192203e-06, 7.534866395192203e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:16,909] [INFO] [timer.py:215:stop] epoch=0/micro_step=2770/global_step=2770, RunningAvgSamplesPerSec=127.90505624625827, CurrSamplesPerSec=127.14382690261898, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:19,409] [INFO] [logging.py:96:log_dist] [Rank 0] step=2780, skipped=24, lr=[7.382798677105856e-06, 7.382798677105856e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:19,418] [INFO] [timer.py:215:stop] epoch=0/micro_step=2780/global_step=2780, RunningAvgSamplesPerSec=127.90455678143223, CurrSamplesPerSec=126.86201466565593, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:20,652] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:20,653] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:20,653] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:20,653] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:44:20,653] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:44:20,652] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:20,653] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:44:20,652] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:20,653] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:44:20,653] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:20,653] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:44:20,652] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:20,653] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:20,653] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:44:20,653] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:44:20,653] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:44:21,919] [INFO] [logging.py:96:log_dist] [Rank 0] step=2790, skipped=24, lr=[7.2320148802721925e-06, 7.2320148802721925e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:21,928] [INFO] [timer.py:215:stop] epoch=0/micro_step=2790/global_step=2790, RunningAvgSamplesPerSec=127.90391261018638, CurrSamplesPerSec=128.1161942488963, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:24,429] [INFO] [logging.py:96:log_dist] [Rank 0] step=2800, skipped=24, lr=[7.082525993639916e-06, 7.082525993639916e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:24,438] [INFO] [timer.py:215:stop] epoch=0/micro_step=2800/global_step=2800, RunningAvgSamplesPerSec=127.90317647345486, CurrSamplesPerSec=127.25002559833743, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:26,939] [INFO] [logging.py:96:log_dist] [Rank 0] step=2810, skipped=24, lr=[6.934342911786143e-06, 6.934342911786143e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:26,948] [INFO] [timer.py:215:stop] epoch=0/micro_step=2810/global_step=2810, RunningAvgSamplesPerSec=127.90253904163518, CurrSamplesPerSec=127.71705749077694, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:29,445] [INFO] [logging.py:96:log_dist] [Rank 0] step=2820, skipped=24, lr=[6.787476434122461e-06, 6.787476434122461e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:29,454] [INFO] [timer.py:215:stop] epoch=0/micro_step=2820/global_step=2820, RunningAvgSamplesPerSec=127.90251568918812, CurrSamplesPerSec=127.68473836172247, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:31,955] [INFO] [logging.py:96:log_dist] [Rank 0] step=2830, skipped=24, lr=[6.641937264107867e-06, 6.641937264107867e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:31,964] [INFO] [timer.py:215:stop] epoch=0/micro_step=2830/global_step=2830, RunningAvgSamplesPerSec=127.90180511721627, CurrSamplesPerSec=127.52799211749269, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:34,466] [INFO] [logging.py:96:log_dist] [Rank 0] step=2840, skipped=24, lr=[6.497736008468702e-06, 6.497736008468702e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:34,475] [INFO] [timer.py:215:stop] epoch=0/micro_step=2840/global_step=2840, RunningAvgSamplesPerSec=127.9009379536914, CurrSamplesPerSec=127.64442314148305, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:36,980] [INFO] [logging.py:96:log_dist] [Rank 0] step=2850, skipped=24, lr=[6.35488317642568e-06, 6.35488317642568e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:36,989] [INFO] [timer.py:215:stop] epoch=0/micro_step=2850/global_step=2850, RunningAvgSamplesPerSec=127.89952911940284, CurrSamplesPerSec=127.7446510423805, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:39,491] [INFO] [logging.py:96:log_dist] [Rank 0] step=2860, skipped=24, lr=[6.2133891789279365e-06, 6.2133891789279365e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:39,500] [INFO] [timer.py:215:stop] epoch=0/micro_step=2860/global_step=2860, RunningAvgSamplesPerSec=127.89876795912716, CurrSamplesPerSec=127.9049778197083, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:42,000] [INFO] [logging.py:96:log_dist] [Rank 0] step=2870, skipped=24, lr=[6.073264327894332e-06, 6.073264327894332e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:42,009] [INFO] [timer.py:215:stop] epoch=0/micro_step=2870/global_step=2870, RunningAvgSamplesPerSec=127.8981732997756, CurrSamplesPerSec=127.55526157729474, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:44,509] [INFO] [logging.py:96:log_dist] [Rank 0] step=2880, skipped=24, lr=[5.934518835461908e-06, 5.934518835461908e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:44,518] [INFO] [timer.py:215:stop] epoch=0/micro_step=2880/global_step=2880, RunningAvgSamplesPerSec=127.89770668617244, CurrSamplesPerSec=127.76362092533574, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:45,751] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:45,751] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:45,751] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:45,752] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:44:45,752] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:44:45,752] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:45,752] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:45,752] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:44:45,752] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:45,752] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:44:45,752] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:44:45,752] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:45,752] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:44:45,752] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:44:45,752] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:44:45,752] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:44:45,997] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2885 +[2023-06-12 07:44:45,997] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:44:45,998] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2885 +[2023-06-12 07:44:45,998] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2885 +[2023-06-12 07:44:45,998] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:44:45,998] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2885 +[2023-06-12 07:44:45,998] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:44:45,998] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:44:45,998] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2885 +[2023-06-12 07:44:45,998] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2885 +[2023-06-12 07:44:45,998] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:44:45,998] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2885 +[2023-06-12 07:44:45,998] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:44:45,998] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 32768.0, reducing to 16384.0 +[2023-06-12 07:44:45,998] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:44:45,998] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2885 +[2023-06-12 07:44:45,999] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:44:46,996] [INFO] [logging.py:96:log_dist] [Rank 0] step=2890, skipped=25, lr=[5.810835603212231e-06, 5.810835603212231e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:47,005] [INFO] [timer.py:215:stop] epoch=0/micro_step=2890/global_step=2890, RunningAvgSamplesPerSec=127.90106613363557, CurrSamplesPerSec=127.22771036484505, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:49,505] [INFO] [logging.py:96:log_dist] [Rank 0] step=2900, skipped=25, lr=[5.674738665931575e-06, 5.674738665931575e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:49,514] [INFO] [timer.py:215:stop] epoch=0/micro_step=2900/global_step=2900, RunningAvgSamplesPerSec=127.90064842028545, CurrSamplesPerSec=127.92704355998147, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:52,010] [INFO] [logging.py:96:log_dist] [Rank 0] step=2910, skipped=25, lr=[5.5400501313413316e-06, 5.5400501313413316e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:52,019] [INFO] [timer.py:215:stop] epoch=0/micro_step=2910/global_step=2910, RunningAvgSamplesPerSec=127.90076134057966, CurrSamplesPerSec=127.7572970050487, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:54,522] [INFO] [logging.py:96:log_dist] [Rank 0] step=2920, skipped=25, lr=[5.406779815386087e-06, 5.406779815386087e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:54,531] [INFO] [timer.py:215:stop] epoch=0/micro_step=2920/global_step=2920, RunningAvgSamplesPerSec=127.89977994788383, CurrSamplesPerSec=127.99975585984066, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:57,033] [INFO] [logging.py:96:log_dist] [Rank 0] step=2930, skipped=25, lr=[5.274937430652302e-06, 5.274937430652302e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:57,042] [INFO] [timer.py:215:stop] epoch=0/micro_step=2930/global_step=2930, RunningAvgSamplesPerSec=127.89897023283858, CurrSamplesPerSec=127.83821743532498, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:44:59,546] [INFO] [logging.py:96:log_dist] [Rank 0] step=2940, skipped=25, lr=[5.144532585660452e-06, 5.144532585660452e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:44:59,555] [INFO] [timer.py:215:stop] epoch=0/micro_step=2940/global_step=2940, RunningAvgSamplesPerSec=127.89780899940031, CurrSamplesPerSec=126.95369167002454, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:01,274] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2946 +[2023-06-12 07:45:01,274] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2946 +[2023-06-12 07:45:01,274] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2946 +[2023-06-12 07:45:01,275] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:01,275] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:01,274] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2946 +[2023-06-12 07:45:01,275] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:01,275] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 16384.0, reducing to 8192.0 +[2023-06-12 07:45:01,274] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2946 +[2023-06-12 07:45:01,275] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:01,274] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2946 +[2023-06-12 07:45:01,274] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2946 +[2023-06-12 07:45:01,275] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:01,275] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 2946 +[2023-06-12 07:45:01,275] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:01,275] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:01,276] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:02,021] [INFO] [logging.py:96:log_dist] [Rank 0] step=2950, skipped=26, lr=[5.02840517867596e-06, 5.02840517867596e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:02,030] [INFO] [timer.py:215:stop] epoch=0/micro_step=2950/global_step=2950, RunningAvgSamplesPerSec=127.90318812518296, CurrSamplesPerSec=127.64976465900045, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:04,529] [INFO] [logging.py:96:log_dist] [Rank 0] step=2960, skipped=26, lr=[4.90075775488921e-06, 4.90075775488921e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:04,538] [INFO] [timer.py:215:stop] epoch=0/micro_step=2960/global_step=2960, RunningAvgSamplesPerSec=127.9028364718858, CurrSamplesPerSec=128.2019783671021, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:07,045] [INFO] [logging.py:96:log_dist] [Rank 0] step=2970, skipped=26, lr=[4.7745751406263165e-06, 4.7745751406263165e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:07,054] [INFO] [timer.py:215:stop] epoch=0/micro_step=2970/global_step=2970, RunningAvgSamplesPerSec=127.9012007231677, CurrSamplesPerSec=127.74659641214632, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:09,557] [INFO] [logging.py:96:log_dist] [Rank 0] step=2980, skipped=26, lr=[4.649866531930241e-06, 4.649866531930241e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:09,566] [INFO] [timer.py:215:stop] epoch=0/micro_step=2980/global_step=2980, RunningAvgSamplesPerSec=127.90017258845717, CurrSamplesPerSec=127.8654979284143, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:12,070] [INFO] [logging.py:96:log_dist] [Rank 0] step=2990, skipped=26, lr=[4.526641017420119e-06, 4.526641017420119e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:12,079] [INFO] [timer.py:215:stop] epoch=0/micro_step=2990/global_step=2990, RunningAvgSamplesPerSec=127.89906426705373, CurrSamplesPerSec=127.60170708913542, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:14,582] [INFO] [logging.py:96:log_dist] [Rank 0] step=3000, skipped=26, lr=[4.404907577628895e-06, 4.404907577628895e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:14,591] [INFO] [timer.py:215:stop] epoch=0/micro_step=3000/global_step=3000, RunningAvgSamplesPerSec=127.89805185865083, CurrSamplesPerSec=127.40766110621188, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:17,093] [INFO] [logging.py:96:log_dist] [Rank 0] step=3010, skipped=26, lr=[4.284675084348852e-06, 4.284675084348852e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:17,102] [INFO] [timer.py:215:stop] epoch=0/micro_step=3010/global_step=3010, RunningAvgSamplesPerSec=127.89732795081981, CurrSamplesPerSec=128.02539566259176, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:19,600] [INFO] [logging.py:96:log_dist] [Rank 0] step=3020, skipped=26, lr=[4.165952299985004e-06, 4.165952299985004e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:19,609] [INFO] [timer.py:215:stop] epoch=0/micro_step=3020/global_step=3020, RunningAvgSamplesPerSec=127.8971436711895, CurrSamplesPerSec=127.59394360560236, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:22,112] [INFO] [logging.py:96:log_dist] [Rank 0] step=3030, skipped=26, lr=[4.048747876916539e-06, 4.048747876916539e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:22,121] [INFO] [timer.py:215:stop] epoch=0/micro_step=3030/global_step=3030, RunningAvgSamplesPerSec=127.89623754072561, CurrSamplesPerSec=127.2800730578365, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:24,620] [INFO] [logging.py:96:log_dist] [Rank 0] step=3040, skipped=26, lr=[3.933070356866231e-06, 3.933070356866231e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:24,629] [INFO] [timer.py:215:stop] epoch=0/micro_step=3040/global_step=3040, RunningAvgSamplesPerSec=127.89594245262232, CurrSamplesPerSec=127.61881434770868, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:26,615] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:45:26,616] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:45:26,615] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:45:26,616] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:45:26,616] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:45:26,615] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:45:26,616] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:45:26,616] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:45:26,616] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:45:26,616] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:45:26,616] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:45:26,616] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:45:26,616] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:45:26,616] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:45:26,616] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:45:26,616] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:45:27,131] [INFO] [logging.py:96:log_dist] [Rank 0] step=3050, skipped=26, lr=[3.818928170277911e-06, 3.818928170277911e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:27,140] [INFO] [timer.py:215:stop] epoch=0/micro_step=3050/global_step=3050, RunningAvgSamplesPerSec=127.89514046724503, CurrSamplesPerSec=127.29987110456464, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:29,642] [INFO] [logging.py:96:log_dist] [Rank 0] step=3060, skipped=26, lr=[3.7063296357021133e-06, 3.7063296357021133e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:29,651] [INFO] [timer.py:215:stop] epoch=0/micro_step=3060/global_step=3060, RunningAvgSamplesPerSec=127.89437980349093, CurrSamplesPerSec=127.41794210179557, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:32,154] [INFO] [logging.py:96:log_dist] [Rank 0] step=3070, skipped=26, lr=[3.5952829591897746e-06, 3.5952829591897746e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:32,163] [INFO] [timer.py:215:stop] epoch=0/micro_step=3070/global_step=3070, RunningAvgSamplesPerSec=127.89335618217243, CurrSamplesPerSec=127.33706945215292, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:34,667] [INFO] [logging.py:96:log_dist] [Rank 0] step=3080, skipped=26, lr=[3.4857962336942218e-06, 3.4857962336942218e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:34,676] [INFO] [timer.py:215:stop] epoch=0/micro_step=3080/global_step=3080, RunningAvgSamplesPerSec=127.89233934706733, CurrSamplesPerSec=127.87487828719838, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:35,395] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3082 +[2023-06-12 07:45:35,395] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3082 +[2023-06-12 07:45:35,396] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:35,395] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3082 +[2023-06-12 07:45:35,396] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:35,396] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3082 +[2023-06-12 07:45:35,396] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3082 +[2023-06-12 07:45:35,396] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:35,396] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 16384.0, reducing to 8192.0 +[2023-06-12 07:45:35,396] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:35,396] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3082 +[2023-06-12 07:45:35,396] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:35,396] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3082 +[2023-06-12 07:45:35,397] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:35,396] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3082 +[2023-06-12 07:45:35,397] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:35,397] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:45:37,145] [INFO] [logging.py:96:log_dist] [Rank 0] step=3090, skipped=27, lr=[3.3885985360893046e-06, 3.3885985360893046e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:37,154] [INFO] [timer.py:215:stop] epoch=0/micro_step=3090/global_step=3090, RunningAvgSamplesPerSec=127.8970061037381, CurrSamplesPerSec=127.78563791552219, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:39,655] [INFO] [logging.py:96:log_dist] [Rank 0] step=3100, skipped=27, lr=[3.28209760597179e-06, 3.28209760597179e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:39,664] [INFO] [timer.py:215:stop] epoch=0/micro_step=3100/global_step=3100, RunningAvgSamplesPerSec=127.89632706939746, CurrSamplesPerSec=127.49007665491987, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:42,165] [INFO] [logging.py:96:log_dist] [Rank 0] step=3110, skipped=27, lr=[3.17717945145731e-06, 3.17717945145731e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:42,174] [INFO] [timer.py:215:stop] epoch=0/micro_step=3110/global_step=3110, RunningAvgSamplesPerSec=127.89570625009448, CurrSamplesPerSec=127.44613263471945, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:44,676] [INFO] [logging.py:96:log_dist] [Rank 0] step=3120, skipped=27, lr=[3.073851718859594e-06, 3.073851718859594e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:44,685] [INFO] [timer.py:215:stop] epoch=0/micro_step=3120/global_step=3120, RunningAvgSamplesPerSec=127.89500311699142, CurrSamplesPerSec=127.75146009579142, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:47,186] [INFO] [logging.py:96:log_dist] [Rank 0] step=3130, skipped=27, lr=[2.972121938584263e-06, 2.972121938584263e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:47,195] [INFO] [timer.py:215:stop] epoch=0/micro_step=3130/global_step=3130, RunningAvgSamplesPerSec=127.89441509655757, CurrSamplesPerSec=128.1398009608261, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:49,694] [INFO] [logging.py:96:log_dist] [Rank 0] step=3140, skipped=27, lr=[2.8719975245800224e-06, 2.8719975245800224e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:49,703] [INFO] [timer.py:215:stop] epoch=0/micro_step=3140/global_step=3140, RunningAvgSamplesPerSec=127.89407312852991, CurrSamplesPerSec=127.66919212816978, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:52,202] [INFO] [logging.py:96:log_dist] [Rank 0] step=3150, skipped=27, lr=[2.7734857737983317e-06, 2.7734857737983317e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:52,211] [INFO] [timer.py:215:stop] epoch=0/micro_step=3150/global_step=3150, RunningAvgSamplesPerSec=127.89389143794875, CurrSamplesPerSec=127.82433808214533, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:54,710] [INFO] [logging.py:96:log_dist] [Rank 0] step=3160, skipped=27, lr=[2.676593865661639e-06, 2.676593865661639e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:54,719] [INFO] [timer.py:215:stop] epoch=0/micro_step=3160/global_step=3160, RunningAvgSamplesPerSec=127.89365586902977, CurrSamplesPerSec=127.98401078661628, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:57,221] [INFO] [logging.py:96:log_dist] [Rank 0] step=3170, skipped=27, lr=[2.5813288615401247e-06, 2.5813288615401247e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:57,230] [INFO] [timer.py:215:stop] epoch=0/micro_step=3170/global_step=3170, RunningAvgSamplesPerSec=127.89304126228993, CurrSamplesPerSec=127.8362692741059, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:45:59,729] [INFO] [logging.py:96:log_dist] [Rank 0] step=3180, skipped=27, lr=[2.4876977042370795e-06, 2.4876977042370795e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:45:59,738] [INFO] [timer.py:215:stop] epoch=0/micro_step=3180/global_step=3180, RunningAvgSamplesPerSec=127.89279792830571, CurrSamplesPerSec=127.46101936353881, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:00,723] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:00,723] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:00,724] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:00,724] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:00,724] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:00,724] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:00,724] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:00,723] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:00,724] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:00,724] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:00,724] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:00,724] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:00,724] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:00,724] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:00,724] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:00,724] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:02,240] [INFO] [logging.py:96:log_dist] [Rank 0] step=3190, skipped=27, lr=[2.395707217482937e-06, 2.395707217482937e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:02,249] [INFO] [timer.py:215:stop] epoch=0/micro_step=3190/global_step=3190, RunningAvgSamplesPerSec=127.89210096278747, CurrSamplesPerSec=127.98413282655005, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:04,753] [INFO] [logging.py:96:log_dist] [Rank 0] step=3200, skipped=27, lr=[2.3053641054379572e-06, 2.3053641054379572e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:04,762] [INFO] [timer.py:215:stop] epoch=0/micro_step=3200/global_step=3200, RunningAvgSamplesPerSec=127.89103656350647, CurrSamplesPerSec=127.43681507011897, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:07,261] [INFO] [logging.py:96:log_dist] [Rank 0] step=3210, skipped=27, lr=[2.216674952203629e-06, 2.216674952203629e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:07,270] [INFO] [timer.py:215:stop] epoch=0/micro_step=3210/global_step=3210, RunningAvgSamplesPerSec=127.89073334712918, CurrSamplesPerSec=128.22230926345918, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:09,769] [INFO] [logging.py:96:log_dist] [Rank 0] step=3220, skipped=27, lr=[2.129646221342854e-06, 2.129646221342854e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:09,778] [INFO] [timer.py:215:stop] epoch=0/micro_step=3220/global_step=3220, RunningAvgSamplesPerSec=127.89059273156528, CurrSamplesPerSec=127.25195593226766, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:12,253] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3229 +[2023-06-12 07:46:12,253] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3229 +[2023-06-12 07:46:12,253] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3229 +[2023-06-12 07:46:12,254] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:46:12,254] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:46:12,253] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3229 +[2023-06-12 07:46:12,254] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:46:12,253] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3229 +[2023-06-12 07:46:12,253] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3229 +[2023-06-12 07:46:12,254] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:46:12,254] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:46:12,253] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3229 +[2023-06-12 07:46:12,254] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:46:12,253] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3229 +[2023-06-12 07:46:12,254] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:46:12,254] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 16384.0 to 8192.0 +[2023-06-12 07:46:12,254] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 16384.0, reducing to 8192.0 +[2023-06-12 07:46:12,255] [INFO] [logging.py:96:log_dist] [Rank 0] step=3230, skipped=28, lr=[2.0527452693256287e-06, 2.0527452693256287e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:12,255] [INFO] [timer.py:215:stop] epoch=0/micro_step=3230/global_step=3230, RunningAvgSamplesPerSec=127.89517223528777, CurrSamplesPerSec=147.90973188014502, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:14,759] [INFO] [logging.py:96:log_dist] [Rank 0] step=3240, skipped=28, lr=[1.9688887143216263e-06, 1.9688887143216263e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:14,768] [INFO] [timer.py:215:stop] epoch=0/micro_step=3240/global_step=3240, RunningAvgSamplesPerSec=127.89420046053199, CurrSamplesPerSec=127.12046530173863, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:17,269] [INFO] [logging.py:96:log_dist] [Rank 0] step=3250, skipped=28, lr=[1.8867106400655533e-06, 1.8867106400655533e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:17,279] [INFO] [timer.py:215:stop] epoch=0/micro_step=3250/global_step=3250, RunningAvgSamplesPerSec=127.89348565971912, CurrSamplesPerSec=127.79013956039144, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:19,777] [INFO] [logging.py:96:log_dist] [Rank 0] step=3260, skipped=28, lr=[1.8062170356003855e-06, 1.8062170356003855e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:19,786] [INFO] [timer.py:215:stop] epoch=0/micro_step=3260/global_step=3260, RunningAvgSamplesPerSec=127.89329833014285, CurrSamplesPerSec=128.12438833935687, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:22,285] [INFO] [logging.py:96:log_dist] [Rank 0] step=3270, skipped=28, lr=[1.7274137672069145e-06, 1.7274137672069145e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:22,294] [INFO] [timer.py:215:stop] epoch=0/micro_step=3270/global_step=3270, RunningAvgSamplesPerSec=127.89307414818478, CurrSamplesPerSec=127.7356544778662, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:24,789] [INFO] [logging.py:96:log_dist] [Rank 0] step=3280, skipped=28, lr=[1.6503065779761796e-06, 1.6503065779761796e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:24,798] [INFO] [timer.py:215:stop] epoch=0/micro_step=3280/global_step=3280, RunningAvgSamplesPerSec=127.89344929159383, CurrSamplesPerSec=128.01758053931968, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:27,299] [INFO] [logging.py:96:log_dist] [Rank 0] step=3290, skipped=28, lr=[1.5749010873909175e-06, 1.5749010873909175e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:27,308] [INFO] [timer.py:215:stop] epoch=0/micro_step=3290/global_step=3290, RunningAvgSamplesPerSec=127.89287386862631, CurrSamplesPerSec=127.62330424628995, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:29,805] [INFO] [logging.py:96:log_dist] [Rank 0] step=3300, skipped=28, lr=[1.5012027909160675e-06, 1.5012027909160675e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:29,815] [INFO] [timer.py:215:stop] epoch=0/micro_step=3300/global_step=3300, RunningAvgSamplesPerSec=127.89283485240924, CurrSamplesPerSec=128.6913359598751, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:32,314] [INFO] [logging.py:96:log_dist] [Rank 0] step=3310, skipped=28, lr=[1.4292170595982146e-06, 1.4292170595982146e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:32,323] [INFO] [timer.py:215:stop] epoch=0/micro_step=3310/global_step=3310, RunningAvgSamplesPerSec=127.89255370379047, CurrSamplesPerSec=127.81606060461772, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:34,823] [INFO] [logging.py:96:log_dist] [Rank 0] step=3320, skipped=28, lr=[1.3589491396741898e-06, 1.3589491396741898e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:34,832] [INFO] [timer.py:215:stop] epoch=0/micro_step=3320/global_step=3320, RunningAvgSamplesPerSec=127.89212671315367, CurrSamplesPerSec=127.76362092533574, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:37,328] [INFO] [logging.py:96:log_dist] [Rank 0] step=3330, skipped=28, lr=[1.2904041521887122e-06, 1.2904041521887122e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:37,337] [INFO] [timer.py:215:stop] epoch=0/micro_step=3330/global_step=3330, RunningAvgSamplesPerSec=127.8922711871296, CurrSamplesPerSec=127.79756188365103, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:37,568] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:37,568] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:37,568] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:37,568] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:37,568] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:37,568] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:37,568] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:37,569] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:37,568] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:37,569] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:37,569] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:37,569] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:37,569] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:37,569] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:37,569] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:46:37,569] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 8192.0 to 16384.0 +[2023-06-12 07:46:39,838] [INFO] [logging.py:96:log_dist] [Rank 0] step=3340, skipped=28, lr=[1.2235870926211619e-06, 1.2235870926211619e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:39,848] [INFO] [timer.py:215:stop] epoch=0/micro_step=3340/global_step=3340, RunningAvgSamplesPerSec=127.8916840834043, CurrSamplesPerSec=127.74671799972398, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:42,345] [INFO] [logging.py:96:log_dist] [Rank 0] step=3350, skipped=28, lr=[1.15850283052156e-06, 1.15850283052156e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:42,354] [INFO] [timer.py:215:stop] epoch=0/micro_step=3350/global_step=3350, RunningAvgSamplesPerSec=127.8917288816514, CurrSamplesPerSec=127.73091355510404, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:44,854] [INFO] [logging.py:96:log_dist] [Rank 0] step=3360, skipped=28, lr=[1.095156109155629e-06, 1.095156109155629e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:44,863] [INFO] [timer.py:215:stop] epoch=0/micro_step=3360/global_step=3360, RunningAvgSamplesPerSec=127.89127543487183, CurrSamplesPerSec=127.51284745511514, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:47,361] [INFO] [logging.py:96:log_dist] [Rank 0] step=3370, skipped=28, lr=[1.0335515451591503e-06, 1.0335515451591503e-06], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:47,370] [INFO] [timer.py:215:stop] epoch=0/micro_step=3370/global_step=3370, RunningAvgSamplesPerSec=127.89112915918383, CurrSamplesPerSec=127.64648685662114, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:49,874] [INFO] [logging.py:96:log_dist] [Rank 0] step=3380, skipped=28, lr=[9.73693628201483e-07, 9.73693628201483e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:49,883] [INFO] [timer.py:215:stop] epoch=0/micro_step=3380/global_step=3380, RunningAvgSamplesPerSec=127.89012819304345, CurrSamplesPerSec=126.88264244051389, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:52,384] [INFO] [logging.py:96:log_dist] [Rank 0] step=3390, skipped=28, lr=[9.155867206583624e-07, 9.155867206583624e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:52,393] [INFO] [timer.py:215:stop] epoch=0/micro_step=3390/global_step=3390, RunningAvgSamplesPerSec=127.88973539918096, CurrSamplesPerSec=127.7621615035487, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:54,891] [INFO] [logging.py:96:log_dist] [Rank 0] step=3400, skipped=28, lr=[8.59235057294e-07, 8.59235057294e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:54,900] [INFO] [timer.py:215:stop] epoch=0/micro_step=3400/global_step=3400, RunningAvgSamplesPerSec=127.88954194619005, CurrSamplesPerSec=127.67732913759744, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:57,397] [INFO] [logging.py:96:log_dist] [Rank 0] step=3410, skipped=28, lr=[8.046427449524274e-07, 8.046427449524274e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:57,406] [INFO] [timer.py:215:stop] epoch=0/micro_step=3410/global_step=3410, RunningAvgSamplesPerSec=127.88964287169027, CurrSamplesPerSec=127.38710409150919, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:46:59,907] [INFO] [logging.py:96:log_dist] [Rank 0] step=3420, skipped=28, lr=[7.518137622582188e-07, 7.518137622582188e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:46:59,917] [INFO] [timer.py:215:stop] epoch=0/micro_step=3420/global_step=3420, RunningAvgSamplesPerSec=127.88907576059347, CurrSamplesPerSec=127.08543899284363, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:02,413] [INFO] [logging.py:96:log_dist] [Rank 0] step=3430, skipped=28, lr=[7.007519593265204e-07, 7.007519593265204e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:02,422] [INFO] [timer.py:215:stop] epoch=0/micro_step=3430/global_step=3430, RunningAvgSamplesPerSec=127.8892374973014, CurrSamplesPerSec=127.85307411736352, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:02,651] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:02,651] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:02,651] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:02,651] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:02,651] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:02,652] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:02,652] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:02,652] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:02,652] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:02,652] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:02,652] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:02,652] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:02,652] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:02,652] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:02,652] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:02,652] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:03,397] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3433 +[2023-06-12 07:47:03,397] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3433 +[2023-06-12 07:47:03,397] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3433 +[2023-06-12 07:47:03,398] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:03,398] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:03,397] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3433 +[2023-06-12 07:47:03,398] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:03,397] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3433 +[2023-06-12 07:47:03,397] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3433 +[2023-06-12 07:47:03,398] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:03,398] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:03,397] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3433 +[2023-06-12 07:47:03,398] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:03,398] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 32768.0, reducing to 16384.0 +[2023-06-12 07:47:03,397] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3433 +[2023-06-12 07:47:03,398] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:03,398] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:04,895] [INFO] [logging.py:96:log_dist] [Rank 0] step=3440, skipped=29, lr=[6.563103537256809e-07, 6.563103537256809e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:04,904] [INFO] [timer.py:215:stop] epoch=0/micro_step=3440/global_step=3440, RunningAvgSamplesPerSec=127.89283487192752, CurrSamplesPerSec=127.51842027256075, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:07,406] [INFO] [logging.py:96:log_dist] [Rank 0] step=3450, skipped=29, lr=[6.086163379298321e-07, 6.086163379298321e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:07,415] [INFO] [timer.py:215:stop] epoch=0/micro_step=3450/global_step=3450, RunningAvgSamplesPerSec=127.89217632262086, CurrSamplesPerSec=127.36727890414079, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:09,915] [INFO] [logging.py:96:log_dist] [Rank 0] step=3460, skipped=29, lr=[5.626999379591269e-07, 5.626999379591269e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:09,924] [INFO] [timer.py:215:stop] epoch=0/micro_step=3460/global_step=3460, RunningAvgSamplesPerSec=127.89185852929202, CurrSamplesPerSec=127.6304644678836, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:12,423] [INFO] [logging.py:96:log_dist] [Rank 0] step=3470, skipped=29, lr=[5.185645001476724e-07, 5.185645001476724e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:12,432] [INFO] [timer.py:215:stop] epoch=0/micro_step=3470/global_step=3470, RunningAvgSamplesPerSec=127.89154028618431, CurrSamplesPerSec=127.31013471085825, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:14,937] [INFO] [logging.py:96:log_dist] [Rank 0] step=3480, skipped=29, lr=[4.762132410351311e-07, 4.762132410351311e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:14,946] [INFO] [timer.py:215:stop] epoch=0/micro_step=3480/global_step=3480, RunningAvgSamplesPerSec=127.89044613605812, CurrSamplesPerSec=127.755716122793, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:17,448] [INFO] [logging.py:96:log_dist] [Rank 0] step=3490, skipped=29, lr=[4.356492471322665e-07, 4.356492471322665e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:17,458] [INFO] [timer.py:215:stop] epoch=0/micro_step=3490/global_step=3490, RunningAvgSamplesPerSec=127.88974268846509, CurrSamplesPerSec=128.08159494917493, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:19,959] [INFO] [logging.py:96:log_dist] [Rank 0] step=3500, skipped=29, lr=[3.968754746960346e-07, 3.968754746960346e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:19,968] [INFO] [timer.py:215:stop] epoch=0/micro_step=3500/global_step=3500, RunningAvgSamplesPerSec=127.88915659442345, CurrSamplesPerSec=128.42363869308411, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:22,465] [INFO] [logging.py:96:log_dist] [Rank 0] step=3510, skipped=29, lr=[3.598947495141114e-07, 3.598947495141114e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:22,474] [INFO] [timer.py:215:stop] epoch=0/micro_step=3510/global_step=3510, RunningAvgSamplesPerSec=127.88916062958893, CurrSamplesPerSec=127.9258242596151, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:24,975] [INFO] [logging.py:96:log_dist] [Rank 0] step=3520, skipped=29, lr=[3.2470976669896905e-07, 3.2470976669896905e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:24,984] [INFO] [timer.py:215:stop] epoch=0/micro_step=3520/global_step=3520, RunningAvgSamplesPerSec=127.88868856907614, CurrSamplesPerSec=127.56095933699872, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:27,484] [INFO] [logging.py:96:log_dist] [Rank 0] step=3530, skipped=29, lr=[2.9132309049146046e-07, 2.9132309049146046e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:27,493] [INFO] [timer.py:215:stop] epoch=0/micro_step=3530/global_step=3530, RunningAvgSamplesPerSec=127.88836425635921, CurrSamplesPerSec=127.95863153830386, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:28,726] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:28,727] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:28,727] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:28,727] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:28,727] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:28,727] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:28,727] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:28,727] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:28,727] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:28,727] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:28,728] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:28,727] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:28,728] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:28,727] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:28,728] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:28,728] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:28,971] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3535 +[2023-06-12 07:47:28,971] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3535 +[2023-06-12 07:47:28,972] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:28,971] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3535 +[2023-06-12 07:47:28,972] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:28,972] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3535 +[2023-06-12 07:47:28,972] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3535 +[2023-06-12 07:47:28,972] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:28,972] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3535 +[2023-06-12 07:47:28,973] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:28,973] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:28,972] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3535 +[2023-06-12 07:47:28,973] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:28,972] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3535 +[2023-06-12 07:47:28,973] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:28,973] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 32768.0, reducing to 16384.0 +[2023-06-12 07:47:28,973] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:29,969] [INFO] [logging.py:96:log_dist] [Rank 0] step=3540, skipped=30, lr=[2.628146477903104e-07, 2.628146477903104e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:29,978] [INFO] [timer.py:215:stop] epoch=0/micro_step=3540/global_step=3540, RunningAvgSamplesPerSec=127.89143295417861, CurrSamplesPerSec=126.87004910602458, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:32,475] [INFO] [logging.py:96:log_dist] [Rank 0] step=3550, skipped=30, lr=[2.3285134909173112e-07, 2.3285134909173112e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:32,484] [INFO] [timer.py:215:stop] epoch=0/micro_step=3550/global_step=3550, RunningAvgSamplesPerSec=127.89148987970766, CurrSamplesPerSec=127.40911244030266, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:34,984] [INFO] [logging.py:96:log_dist] [Rank 0] step=3560, skipped=30, lr=[2.0469305153599516e-07, 2.0469305153599516e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:34,993] [INFO] [timer.py:215:stop] epoch=0/micro_step=3560/global_step=3560, RunningAvgSamplesPerSec=127.89108704975476, CurrSamplesPerSec=127.78235313158702, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:37,491] [INFO] [logging.py:96:log_dist] [Rank 0] step=3570, skipped=30, lr=[1.7834180726725158e-07, 1.7834180726725158e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:37,500] [INFO] [timer.py:215:stop] epoch=0/micro_step=3570/global_step=3570, RunningAvgSamplesPerSec=127.89100558307919, CurrSamplesPerSec=127.6951856140214, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:40,000] [INFO] [logging.py:96:log_dist] [Rank 0] step=3580, skipped=30, lr=[1.5379953673370084e-07, 1.5379953673370084e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:40,009] [INFO] [timer.py:215:stop] epoch=0/micro_step=3580/global_step=3580, RunningAvgSamplesPerSec=127.89061494415745, CurrSamplesPerSec=127.8687869884495, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:42,507] [INFO] [logging.py:96:log_dist] [Rank 0] step=3590, skipped=30, lr=[1.31068028547629e-07, 1.31068028547629e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:42,516] [INFO] [timer.py:215:stop] epoch=0/micro_step=3590/global_step=3590, RunningAvgSamplesPerSec=127.89059047290596, CurrSamplesPerSec=127.67975829666116, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:45,015] [INFO] [logging.py:96:log_dist] [Rank 0] step=3600, skipped=30, lr=[1.1014893935505367e-07, 1.1014893935505367e-07], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:45,025] [INFO] [timer.py:215:stop] epoch=0/micro_step=3600/global_step=3600, RunningAvgSamplesPerSec=127.89029098424352, CurrSamplesPerSec=127.42290176346332, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:47,519] [INFO] [logging.py:96:log_dist] [Rank 0] step=3610, skipped=30, lr=[9.104379371500105e-08, 9.104379371500105e-08], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:47,528] [INFO] [timer.py:215:stop] epoch=0/micro_step=3610/global_step=3610, RunningAvgSamplesPerSec=127.89068973868224, CurrSamplesPerSec=127.90412460142448, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:50,024] [INFO] [logging.py:96:log_dist] [Rank 0] step=3620, skipped=30, lr=[7.375398398837829e-08, 7.375398398837829e-08], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:50,033] [INFO] [timer.py:215:stop] epoch=0/micro_step=3620/global_step=3620, RunningAvgSamplesPerSec=127.89086018223459, CurrSamplesPerSec=127.89778676480398, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:52,530] [INFO] [logging.py:96:log_dist] [Rank 0] step=3630, skipped=30, lr=[5.8280770236518456e-08, 5.8280770236518456e-08], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:52,539] [INFO] [timer.py:215:stop] epoch=0/micro_step=3630/global_step=3630, RunningAvgSamplesPerSec=127.89091702769119, CurrSamplesPerSec=128.18116425077406, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:54,272] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:54,272] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:54,273] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:54,273] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:54,273] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:54,273] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:54,273] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:54,273] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:54,273] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:54,273] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:54,273] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:54,273] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:54,273] [INFO] [fused_optimizer.py:370:_update_scale] No Grad overflow for 100 iterations +[2023-06-12 07:47:54,274] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:54,274] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:54,274] [INFO] [fused_optimizer.py:371:_update_scale] Increasing dynamic loss scale from 16384.0 to 32768.0 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3637 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3637 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3637 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3637 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3637 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3637 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3637 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:362:_update_scale] +Grad overflow on iteration 3637 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:54,519] [INFO] [fused_optimizer.py:363:_update_scale] Reducing dynamic loss scale from 32768.0 to 16384.0 +[2023-06-12 07:47:54,519] [INFO] [logging.py:96:log_dist] [Rank 0] Overflow detected. Skipping step. Attempted loss scale: 32768.0, reducing to 16384.0 +[2023-06-12 07:47:55,013] [INFO] [logging.py:96:log_dist] [Rank 0] step=3640, skipped=31, lr=[4.5909002174351904e-08, 4.5909002174351904e-08], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:55,022] [INFO] [timer.py:215:stop] epoch=0/micro_step=3640/global_step=3640, RunningAvgSamplesPerSec=127.89422976269, CurrSamplesPerSec=127.92289803356437, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:47:57,520] [INFO] [logging.py:96:log_dist] [Rank 0] step=3650, skipped=31, lr=[3.389031801728504e-08, 3.389031801728504e-08], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:47:57,529] [INFO] [timer.py:215:stop] epoch=0/micro_step=3650/global_step=3650, RunningAvgSamplesPerSec=127.89414981528735, CurrSamplesPerSec=127.15225845446096, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:48:00,029] [INFO] [logging.py:96:log_dist] [Rank 0] step=3660, skipped=31, lr=[2.369113505284737e-08, 2.369113505284737e-08], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:48:00,038] [INFO] [timer.py:215:stop] epoch=0/micro_step=3660/global_step=3660, RunningAvgSamplesPerSec=127.89373988213451, CurrSamplesPerSec=127.45230475879372, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:48:02,542] [INFO] [logging.py:96:log_dist] [Rank 0] step=3670, skipped=31, lr=[1.5312196585692828e-08, 1.5312196585692828e-08], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:48:02,551] [INFO] [timer.py:215:stop] epoch=0/micro_step=3670/global_step=3670, RunningAvgSamplesPerSec=127.89283392302097, CurrSamplesPerSec=127.42024043358931, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +[2023-06-12 07:48:05,048] [INFO] [logging.py:96:log_dist] [Rank 0] step=3680, skipped=31, lr=[8.754113263159668e-09, 8.754113263159668e-09], mom=[(0.9, 0.95), (0.9, 0.95)] +[2023-06-12 07:48:05,057] [INFO] [timer.py:215:stop] epoch=0/micro_step=3680/global_step=3680, RunningAvgSamplesPerSec=127.89297541765943, CurrSamplesPerSec=128.34933949940807, MemAllocated=4.32GB, MaxMemAllocated=12.79GB +Epoch 1/1 with loss 0.5835847191188647 +***** Evaluating reward, Epoch 1/1 ***** +chosen_last_scores (higher is better) : 2.8516085147857666, acc (higher is better) : 0.6974999904632568 +saving model ... +[2023-06-12 07:48:24,156] [INFO] [launch.py:346:main] Process 4245 exits successfully. +[2023-06-12 07:48:24,157] [INFO] [launch.py:346:main] Process 4249 exits successfully. +[2023-06-12 07:48:24,157] [INFO] [launch.py:346:main] Process 4246 exits successfully. +[2023-06-12 07:48:24,157] [INFO] [launch.py:346:main] Process 4244 exits successfully. +[2023-06-12 07:48:24,157] [INFO] [launch.py:346:main] Process 4250 exits successfully. +[2023-06-12 07:48:25,158] [INFO] [launch.py:346:main] Process 4247 exits successfully. +[2023-06-12 07:48:25,160] [INFO] [launch.py:346:main] Process 4243 exits successfully. +[2023-06-12 07:48:25,160] [INFO] [launch.py:346:main] Process 4248 exits successfully.